AI-powered digital stethoscopes show promise in bridging screening gaps

(Photo: Eko Health, US) IANS

New Delhi, As tuberculosis (TB) continues as the deadliest infectious cause of deaths globally, a new study has shown that artificial intelligence (AI)-enabled digital stethoscopes can help fill critical screening gaps, especially in hard-to-reach areas.

In a commentary published in the journal Med (Cell Press), global experts contended that stethoscopes combined with digital technology and AI can be a better option against the challenges faced in screening programmes, such as under-detection, high cost, and inequitable access.

“AI-enabled digital stethoscopes have demonstrated promising accuracy and feasibility for detecting lung and cardiovascular abnormalities, with promising results in early TB studies. Training and validation in diverse, high-burden settings are essential to explore the potential of this tool further,” said corresponding author Madhukar Pai from McGill University, Canada, along with researchers from the UAE, Germany, and Switzerland.

Despite advancements in screening and diagnostic tools, an estimated 2.7 million people with TB were missed by current screening programmes, as per data from the World Health Organization (WHO). Routine symptom screening is also likely to miss people with asymptomatic or subclinical TB.

While the WHO recently recommended several AI-powered computer-aided detection (CAD) software, as well as ultra-portable radiography hardware, higher operating costs and upfront hardware act as a deterrent.

This particularly appeared difficult in primary care settings and or among pregnant women due to radiation concerns.

At the same time, AI showed significant potential for screening, including applications beyond CAD of TB from radiographs, said the researchers.

“One application of AI for disease screening is to interpret acoustic (sound) biomarkers of disease, with potential to identify sounds that appear nonspecific or are inaudible to the human ear,” they added, while highlighting the potential of AI in detecting and interpreting cough biomarkers and lung auscultation to analyse breath sounds.

Studies from high-TB burden countries, including India, Peru, South Africa, Uganda, and Vietnam, highlighted that AI-enabled auscultation could hold promise as a TB screening and triage tool.

"AI digital stethoscopes may become useful alternatives to imaging-based approaches for TB screening, with the potential to democratise access to care for populations underserved by radiography," the researchers said."Importantly, AI digital stethoscopes offer a scalable, low-cost, and person-centered tool that could bring us closer to reaching TB case finding goals," they added. AI-powered digital stethoscopes show promise in bridging screening gaps | MorungExpress | morungexpress.com

Read More........→April 12, 2026

Spectacular New Species Found in Cambodia’s Limestone Caves–Asia's 'Little Laboratories'

A new species of pit viper found living in the caves – credit, supplied by Fauna & Flora ©

A breathtaking expedition high among limestone escarpments and deep in the cave systems they contain has revealed several new reptile species, including a dazzling pit viper you have to see to believe.

Exploring over 60 caves across 10 hills in the Battambang province, western Cambodia, the survey uncovered a treasure trove of extraordinary creatures besides, many found nowhere else on Earth.

The survey was led by Fauna & Flora International in collaboration with Cambodia’s Ministry of Environment and field experts. The team identified 6 new geckos, 2 micro-snails, and 2 millipedes in addition to the viper.

They also confirmed the presence of many threatened species in the landscape surrounding the caves—such as the Sunda pangolin, Indochinese silvered langur, long-tailed macaque, and green peafowl, further highlighting the critical need to protect this habitat.

Karst covers 20% of the Earth’s landscape. This soluble bedrock made of limestone has created some of the most spectacular rocky landscapes on Earth—including the upturned egg cartons shapes along the great South China Karst, Ha Long Bay in Vietnam, Tsingy de Bemaraha in Madagascar, The Burren in western Ireland, the world’s largest wellspring in Vrelo Bune, Bosnia, the Cenotes of the Yucatan, in Mexico, and Mammoth Cave in the US.

The susceptibility of karst to erode from rainfall has seen it carved into a million beautiful and dramatic shapes that often play host to microclimates where threatened animals can thrive.

Landscapes along the Li River amid the South China Karst – credit, Sam Beasley via Unsplash

Dr. Lee Grismer, a professor of biology at La Sierra University in the US, was part of the expeditionary team, and spoke to F&F about the importance and uniqueness of the landscape.

“Each one of these isolated karst areas act as their own little laboratory where nature is performing the same experiment over and over and over independently. The results are species that exist nowhere else—not just nowhere else in the world, or that country—but in no other cave.”

The Shiva Gecko – credit, supplied by Fauna & Flora ©

Indeed, caves from easily in karst landscapes, and many of the world’s longest and largest—and least-explored—cave systems are found in East and Southeast Asia.

This is certainly the case in Battambang, where the survey team had first to ascend the steep forested slopes of the karst outcrops before scrambling and squeezing through crevices and crawlspaces to reach the cave systems.

Inside, they documented a rich array of life, both endemic to the caves and others—like a big reticulated python—who were just visiting. While the chatter of the Endangered silvered langur troupe, faded behind them, the team began encountering animal after animal that had never been described by science.

A spectacular new species of pit viper (from the Trimeresurus genus) was collected during the survey and is currently being described. Recognized by their triangular heads, these highly venomous snakes track down their warm-blooded prey using the heat-sensitive pits behind their nostrils.

4 populations of the striped Kamping Poi bent-toed gecko were found and identified as a new species: Cyrtodactylus kampingpoiensis. Despite being described as just one species, it is thought that, due to the geographic isolation of the karst formations, these 4 populations are on separate evolutionary trajectories, and further genetic analyses may reveal whether they are in fact 4 different species instead of 1.

Another new species of gecko was named after the Hindu god of destruction: Shiva.

In a statement, Fauna & Flora International said it is working with local partners to help conserve Cambodia’s karst landscapes, epitomized through the recent release of guidelines for sustainable development and management of cave ecosystems.

The Fauna & Flora International expeditionary team – credit, supplied by Fauna & Flora ©

The guidelines integrate international best practices with Cambodian context, providing practical measures to safeguard bat colonies, preserve rare and endemic cave biodiversity, promote sustainable guano harvesting and ensure responsible tourism development.

“Cambodia’s karst areas are a treasure trove of scientific secrets waiting to be uncovered,” said Sothearen Thi, Karst Biodiversity Coordinator at Fauna & Flora in the statement.“But, without sustainable management, we may never find out what these areas truly hold. Karst landscapes are facing many human-driven challenges, and biologically significant species could go extinct before they have even been discovered. We are working with the Cambodian government and local partners to increase protection of the landscapes, with sustainable management being the number one priority.” Spectacular New Species Found in Cambodia’s Limestone Caves–Asia's 'Little Laboratories'

Read More........→April 11, 2026

India launches world’s 1st clinical trial to test Ayurveda with TB treatment

(File Photo/IANS)

New Delhi, (IANS) On the occasion of World Tuberculosis Day, India announced the world’s first clinical study to scientifically evaluate Ayurveda as an adjunct to standard Anti-Tuberculosis Treatment (ATT), the government said on Tuesday.

The collaborative clinical study between the Department of Biotechnology and the Ministry of Ayush will enrol 1,250 newly diagnosed tuberculosis patients across eight institutions to evaluate Ayurveda as an adjunct to standard treatment, focusing on body weight, nutritional outcomes, disease progression, quality of life, safety, and tolerability.

Union MoS for Science & Technology Jitendra Singh said the study reflects the spirit of “whole-of-science,” approach by integrating biotechnology and Ayurveda; “whole-of-government” approach through collaboration between ministries.

DG, CCRAS, Prof. Vaidya Rabinarayan Acharya said the initiative has progressed through consultations, protocol finalisation, and approvals.

Director, BRIC-NII, Dr. Debasisa Mohanty said the study will examine tuberculosis-associated cachexia as an immune-metabolic condition, using advanced tools such as DEXA, MRI, immune profiling, metabolomics, and single-cell RNA sequencing to understand changes in body composition, immune function, and energy metabolism.

It is aimed to assess how integrative interventions influence recovery and long-term outcomes, the statement from the Ministry of Science & Technology said.

Minister Jitendra Singh said India, which accounts for nearly 25 per cent of the global TB burden, saw a 21 per cent drop in a decade in tuberculosis incidence to about 187 cases per 1,00,000 population in 2024.

“The decline in TB incidence is an outcome of India’s dedicated and innovative efforts. Through a collective spirit, we will keep working towards a TB-free India,” he quoted Prime Minister Narendra Modi.

India has adopted an ambitious and accelerated pathway towards TB elimination, strengthening early diagnosis, universal drug susceptibility testing, digital adherence technologies, and patient-centric care under the National TB Elimination Programme, the minister said.

He pointed out the reciprocal relationship between TB and conditions such as diabetes, where each can aggravate the other, making integrated approaches essential for effective disease management.He also referred to the RePORT India programme, one of the largest TB research consortia, with over 4,500 enrolled TB patients and over 5,000 household contacts, generating evidence relevant for global policy frameworks, including WHO guidelines on nutrition and tuberculosis. India launches world’s 1st clinical trial to test Ayurveda with TB treatment | MorungExpress | morungexpress.com

Read More........→April 02, 2026

Planting Billions of Trees Turned Barren Desert into a Carbon Sink That Lowers CO2

A mixed-species section of the Green Great Wall – Credit: 中国新闻网 CC 3.0. BY

China’s multi-decade long, successful effort to plant a ring of trees around one of the world’s most hostile deserts has sprouted an unexpected benefit to humanity.

Along with protecting the nation’s grasslands and agriculture from the spreading sands of the dismal Taklamakan Desert, the giant ring of trees has turned previous unproductive land into a carbon sink that draws CO2 out of the atmosphere.

It’s thought, and some isolated research has indeed demonstrated, that humans can prevent the worst effects of a rise in average global temperatures by planting trees to absorb more CO2 from the atmosphere.

This strategy has limits, however, when viewed on a global scale. Atmospheric CO2 levels continue to rise, while there is a limit in the amount of land that can be turned over to forests.

One-third of our planet is covered in deserts, where vegetation is sparse or absent, and rainfall is scarce, yet despite their vast acreage they collectively hold less than one-tenth of the world’s carbon stock, or the amount of carbon that is held underground.

A study conducted by NASA and California Technical Institute (Caltech) has used satellite data to demonstrate that the “sea of death” as the Taklamakan Desert was called in antiquity, could be utilized to store carbon and reduce the greenhouse effect.

The Taklamakan Desert. Credit: NASA World Wind 1.4.

Starting in 1978, China’s Three-North Shelter Belt program aimed to plant trees along the borders of the great Taklamakan to stop sandstorms from ruining adjacent pasture and agriculture land. As the world’s single farthest point from any ocean, the Taklamakan is one of the driest and most hostile landscapes on our planet.

The massive Himalayas rise to the south and east, the Pamirs to the southwest, and a pair of mountains known as the Tian Shan and the Altai to the west, leaving landscape completely isolated from moisture.

66 billion trees have been planted by estimates since the start of the Shelter Belt program, which finished in 2024. Monikered the “Green Great Wall,” this incredible increase in greenery has raised average rainfall by several millimeters, resulting in a natural growth of foliage during the wet season that boosts photosynthesis along the tree line, leading to greater degrees of sequestration.

“We found, for the first time, that human-led intervention can effectively enhance carbon sequestration in even the most extreme arid landscapes, demonstrating the potential to transform a desert into a carbon sink and halt desertification,” study co-author Yuk Yung, a professor of planetary science at Caltech and a senior research scientist in NASA’s Jet Propulsion Laboratory, told Live Science in an email.

By precise numbers, it has reduced the average carbon content in the desert air from 416 parts per million to 413 ppm. Parts per million is used as a measurement for the greenhouse effect. Worldwide, the number is 429.3. It was 350 in before the advent of industrialization.If more shelter belt-style tree planting efforts could be used to reclaim desert landscapes, it could open vast areas to absorbing carbon. With little to no vegetation, deserts in their natural state have precious little ability to do so. Planting Billions of Trees Turned Barren Desert into a Carbon Sink That Lowers CO2

Read More........→March 10, 2026

Dogs can detect trafficked wildlife hidden in shipping containers from tiny air samples

Georgia Moloney, Adelaide University and Anne-Lise Chaber, Adelaide University

Wildlife trafficking is a global crisis impacting at least 4,000 species of plants and animals, including mammals, reptiles, birds, corals and rare plants.

A shocking case from 2025 involved the seizure of 3.7 tonnes of pangolin scales in Nigeria. These scales were believed to be sourced from more than 1,900 individual pangolins.

While this case was uncovered, many more remain undetected. These crimes aren’t just pushing species toward extinction, they’re also putting people at risk. Hunting, trafficking and handling wild animals creates opportunities for diseases to jump from animals to humans. Wildlife trafficking is therefore not just a conservation crisis, but a serious threat to public health.

In our recent paper published in Conservation Biology, we present a new method for tackling this global crime. It uses a tiny sample of air extracted from a shipping container – and the incredible power of a dogs’ nose.

Traffickers exploit shipping routes

People buy and sell a wide range of wild animals and their parts for many reasons, such as pangolin scales for traditional medicines, monkeys for exotic pets, or even porcupines for bushmeat.

Traffickers exploit global transport routes to move their products, with shipping containers in particular being ideal targets.

Containers carry up to 90% of the world’s cargo, meaning products can be easily concealed and blend into the high volume of container traffic moving through ports.

Despite this, on average only about 2% of containers are physically inspected due to resource limitations.

There are few wildlife specific detection tools, and wildlife crime is often considered a low priority. Combined, this means most trafficking slips through undetected.

Bringing the scent to the dog

To bridge this gap, we investigated air sampling as a way to screen containers for wildlife without opening them, damaging cargo, or disrupting port operations.

This work was part of a four-year project, undertaken in collaboration with the world’s third largest shipping company CMA CGM.

We designed a portable air extraction device that fits onto a standard container vent and draws air through a filter to collect a sample. The sample is then presented to a trained detection dog which can indicate whether the scent of specific wildlife products is present.

In our study, we concealed pelts from five big cat species – lion, tiger, leopard, snow leopard and cheetah – inside standard-sized shipping containers. The pelts were arranged to simulate smuggling scenarios, including being hidden inside cardboard boxes to increase concealment.

Our detection dog successfully detected the pelts with almost 98% accuracy when air was extracted from the shipping container. They did so even when the pelts were concealed, demonstrating that the scent can escape into the container airspace and be reliably captured.

Detection dogs are already widely used by customs and border agencies around the world, but their ability to screen sealed containers at scale is limited. Containers are often inaccessible, stacked high, or in environments that are unsafe for dogs.

Our approach brings the scent to the dog, allowing many more containers to be screened efficiently and safely.

While the study was conducted under controlled conditions, these early results are encouraging. Pairing detection dogs with air-sampling could dramatically improve the detection of illegally trafficked wildlife hidden inside shipping containers.

The air extraction device is low cost, portable and scalable, making it well suited for use in high-risk ports and border crossings worldwide. The method could also be readily adapted for detecting other forms of trafficking, such as drugs, increasing its appeal to border agencies.

Disrupting criminal networks

Further trials are planned to validate the effectiveness of this approach in operational port environments across a broader range of wildlife products.

We are also exploring machine-based detectors to analyse samples and support the future development of this project.

However, initial findings show the dogs still outperform these technologies, which currently remain our most effective approach.

Our goal is to give frontline agencies practical tools to fight wildlife trafficking.

Through applying science-based research in the field, we can bridge enforcement gaps and detect trafficked wildlife faster, allowing us to better protect threatened species and disrupt the criminal networks behind this devastating trade.

Georgia Moloney, Researcher, School of Animal and Veterinary Sciences, Adelaide University and Anne-Lise Chaber, One Health Lecturer, School of Animal and Veterinary Science, Adelaide University

This article is republished from The Conversation under a Creative Commons license. Read the original article.

Read More........→March 03, 2026

Raincoat no longer waterproof? A textile scientist explains why – and how to fix it

Alesia Kazantceva/Unsplash Carolina Quintero Rodriguez, RMIT University

You pull on your rain jacket, step out into the storm, and within half an hour your undershirt is soaked. The jacket you purchased as “waterproof” seems to have stopped working, and all the marketing claims feel a bit suspect.

In reality, the jacket probably hasn’t failed overnight: a mix of how it’s built, the exact level of water protection it offers, and years of sweat, skin oil and dirt have all played a part.

But there are a few simple ways you can care for your rain jacket to ensure you stay dry, even when it’s pouring.

The science behind rain jackets

Most proper rain jackets are built around a waterproof “membrane” sandwiched inside the fabric. Gore-Tex is the most popular technology used which includes a very thin layer of chemicals known as PTFE (polytetrafluoroethylene) or expanded PTFE (ePTFE) which are full of microscopic pores.

Those pores are much smaller than liquid water droplets. But they’re big enough for individual water vapour molecules, so rain on the outside can’t push through, but sweat vapour from your body can escape outwards.

Other fabrics use solid, non-porous membranes made from polyurethane or polyester that move water vapour by absorbing it and passing it through the material molecule by molecule rather than via tiny holes. This can make them a bit more tolerant of dirt.

The outer fabric is sometimes treated with a very thin chemical finish that makes water roll off the surface instead of soaking into the fibres – a bit like wax on a car. This finish is known as “Durable Water Repellent” and helps to reduce saturation of water in the exterior of the jacket.

In the past, many of these chemical finishes used “forever chemicals” (PFAS) that repelled both water and oil, but persist in the environment and build up in wildlife and people.

Because of this, brands and regulators have started using alternatives based on silicones or hydrocarbons. These still repel water but are generally less hazardous.

It’s also useful to understand the words you see on labels.

A waterproof jacket is built to stop rain coming through, even in heavy or prolonged downpours, and usually has a membrane, a chemical finish plus fully taped seams.

“Water resistant” means the fabric slows water down and copes with light showers but will eventually let water through. It often relies on a tight weave and a chemical finish but no true membrane.

“Water repellent” just describes that beading effect from the chemical finish. It can apply to both waterproof and non-waterproof fabrics.

Some brands also say rainproof or weatherproof as a friendlier way of saying “pretty much waterproof”, but there’s rarely a separate test behind that word.

 

The outer fabric of a rain jacket is sometimes treated with a very thin chemical finish that makes water roll off the surface instead of soaking into the fibres. Claudio Schwarz/Unsplash

Why do rain jackets degrade over time?

When you realise your jacket isn’t waterproof anymore, the first thing that has usually gone wrong isn’t the membrane. It’s the chemical finish on the outside.

That ultra thin surface layer gets scuffed by backpack straps and seat belts, baked by sun, and contaminated by mud, smoke and city grime.

These coatings can gradually lose their water repellent properties through abrasion and washing if harsh detergents and washing cycles are used, and bits of them are shed into the environment over time.

Body oils, sunscreen and insect repellent also play a role, as they build up in the fabric over time. Outdoor gear care guides and lab work on waterproof fabrics both point out that these oily contaminants can damage the chemical finish and clog the pores of the membrane, making it harder both for rain to be repelled and for sweat vapour to escape.

Over many years, slow physical ageing also takes a toll. Constant flexing can cause a membrane to thin or develop tiny cracks and the finish to deteriorate. Seam tapes can also start to peel away, especially on shoulders where backpack straps press.

How to keep a jacket waterproof

The single best thing you can do for both your comfort and the planet is to keep a good jacket working for as long as possible, because making new technical fabrics has a significant environmental footprint.

Gentle washing will help extend the life of your rain jacket, as it removes the build up of contamination such as dirt and body oils. Brands and care guides recommend closing zips and Velcro, then washing on a gentle cycle with a cleaner designed for waterproof fabrics or a very mild soap, avoiding normal detergents and softeners that leave residues.

Depending on the type of chemical finish, this coat can be re-applied through spray-on or wash-in products found commercially. Some finishes can be re-activated by exposure to low heat (low dryer heat or low ironing heat). Heat makes the water-repelling molecules stand back up after they have been “flattened” by use and contamination.

Although the above will help you to keep your jacket waterproof, it is best to follow the care instructions given by the manufacturer as they change according to the type of composition of the fabric.

In any case, it is important to avoid leaving the jacket wet and scrunched up for weeks, and be mindful of heavy sunscreens and repellents.

Carolina Quintero Rodriguez, Senior Lecturer and Program Manager, Bachelor of Fashion (Enterprise) program, RMIT University

This article is republished from The Conversation under a Creative Commons license. Read the original article.

Read More........→February 27, 2026

Wildlife Poachers to Be Targeted Using State of the Art AI Listening Technology

A photo of a male forest elephant captured near the site where some of the gunshot recordings were taken – credit, Anahita Verahrami / SWNS

Wildlife poachers can now be located and arrested across the central African forests thanks to state-of-the-art AI listening technology.

A network of microphones has been deployed across the rainforests to detect gunshots from illegal poaching of elephants and other animals, and American scientists are using AI to ensure the network can distinguish gunshots over the din of the jungle environment.

The web of acoustic sensors was deployed in Gabon, Congo, and Cameroon, creating the possibility of real-time alerts to the sounds of gun-based poaching.

But the belly of the rainforest is loud, and scientists say sorting through a constant influx of sound data is computationally demanding. Detectors can distinguish a loud bang from the whistles, chirps, and rasps of birds and bugs, but they often confuse the sounds of branches cracking or trees falling with gunshot noises, resulting in a high percentage of false positives.

Project leader Naveen Dhar at Center for Conservation Bioacoustics at Cornell University aimed to develop a lightweight gunshot detection neural network that can accompany sensors and process signals in real-time to minimize false positives.

He worked alongside colleagues at the Elephant Listening Project to create a model that will work through autonomous recording units (ARUs), which are power-efficient microphones that capture continuous, long-term soundscapes.

“The proposed system utilizes a web of ARUs deployed across the forest, each performing real-time detection, with a central hub that handles more complex processing.”

An initial scan filters all audio for “gunshot likely” signals and sends them to the ARU’s microprocessor, where the lightweight gunshot detection model lives.

If confirmed as a gunshot by the microprocessor, the ARU passes the information to the central hub, initiating data collection from other devices in the web.

By determining if other sensors also hear a “gunshot likely” noise, the central hub then decides whether the event was a true gunshot or a potential false positive.

If it determines a true positive, the central hub collates audio files from each sensor, allowing it to pinpoint the location of the gunshot and alert rangers on the ground with coordinates for immediate poaching intervention.

“Down the road, the device can be used as a tool for rangers and conservation managers, providing accurate and verifiable alerts for on-the-ground intervention along with low-latency data on the spatiotemporal trends of poachers,” Dhar said.

He plans to expand the model to detect the type of gun that fires each gunshot and other human activities, such as chainsaws or trucks, before field-testing the system, which is currently under development.

“I hope the device can coalesce with Internet of Things infrastructure innovations and cost reduction of materials to produce a low-cost, open-source framework for real-time detection usable in any part of the globe.”He is due to present his findings at a joint meeting of the Acoustical Society of America and Acoustical Society of Japan, in Honolulu, Hawaii. Wildlife Poachers to Be Targeted Using State of the Art AI Listening Technology:

Read More........→February 26, 2026

New Spray-on Powder Instantly Seals Life-Threatening Wounds in Battle or During Disasters

South Korean scientists win award for wound powder – SWNS

A spray-on powder that instantly seals life-threatening wounds could save thousands of lives, say scientists.

The new substance can help prevent excessive bleeding which is the leading cause of death due to injuries in war, according to a study.

The fast-acting powder that stops bleeding in just one second was developed by South Korean scientists who say it can also be applied in emergency hospital procedures.

The research team at the Korea Advanced Institute of Science and Technology (KAIST) in Daejeon, which included an Army Major, created the powder that rapidly forms a strong hydrogel barrier when sprayed directly onto a bullet wound.

The team designed the technology with real combat conditions in mind, and the direct involvement of an Army Major helped ensure its practical readiness.

Major Kyusoon Park, who is also a PhD candidate and served as a study co-author, said the substance not only allows “instant hardening” under extreme conditions like combat or disasters but also delivers high usability and storage stability.

“Until now, patch-type hemostatic agents widely used in medical fields have had limitations due to their flat structure and sensitivity to temperature and humidity.”

They cannot withstand pressure applied to the wound. Also, current powders that stop blood flow have limited functionality by physically absorbing blood to form a barrier, according to the study published in the journal Advanced Functional Materials.

Medical first aide equipment for combat care at Marine Corps Base Camp Lejeune – Credit: Navy Medicine via Unsplash

“The new AGCL powder reacts with cations, such as calcium in the blood, to turn into a gel state in one second, instantly sealing the wound,” said study co-leader Professor Steve Park.

“Furthermore, by forming a three-dimensional structure inside the powder, it can absorb blood amounting to more than seven times its own weight.”

“It shows superior sealing performance compared to commercial hemostatic agents—with a high adhesive strength and a level of pressure that can withstand being pressed strongly by hand.”

AGCL powder is composed entirely of naturally derived materials with an antibacterial effect of 99.9%.

It has a structure that combines biocompatible natural materials such as alginate and gellan gum—that react with calcium for fast gelation and physical sealing—and chitosan, which bonds with blood components to enhance chemical and biological hemostasis.

“In animal experiments, excellent tissue-regeneration effects, such as rapid wound recovery and promotion of blood vessel and collagen regeneration, were confirmed,” explained Prof. Park.

“In surgical liver injury experiments, the amount of bleeding and hemostasis time were significantly reduced compared to commercial methods.”

“It also maintains its performance for two years, even in room temperature and high humidity environments, possessing the advantage of being ready for immediate use in harsh environments.

“Although this is an advanced new material technology developed with national defense purposes in mind,” said Major Park, “it has great potential for emergency medicine, disaster sites, developing countries, and medically underserved areas.”“I started the research with a sense of mission to save even one more soldier—but I also hope this technology will be used as a life-saving technology in private medical fields.” New Spray-on Powder Instantly Seals Life-Threatening Wounds in Battle or During Disasters

Read More........→February 23, 2026

Samsung's 600-Mile-Range Batteries That Charge in 9 Minutes Ready for Production/Sale Next Year

A mock-up design of Samsung SDI’s solid-state battery – credit, Samsung, released

In late October, Samsung announced that it was preparing to take its long-anticipated solid-state batteries to market with a trilateral agreement between itself, BMW, and American battery expert Solid Power.

It was January of last year that industry outlets began to get some of the promises that all-solid-state batteries (ASSBs) developed by Samsung SDI would bring. With an energy density of 500 watt-hours per kilogram, they’re twice as dense as conventional lithium-ion batteries.

Samsung claimed they were smaller, lighter, and safer, capable of driving 600 miles, and charging with

in 9 minutes. Typically, a lithium-ion battery pack in a modern EV charges from 10% to 80% in around 45 minutes, and has a limit of around 300 miles of range.

“Samsung SDI’s preparations for mass-producing next-generation products of various form factors such as an all-solid-state battery are well underway as we are set to lead the global battery market with our unrivaled ‘super-gap’ technology,” said Samsung SDI CEO Yoon-ho Choi.

ASSB cells use solid electrolyte instead of liquid electrolyte found in a lithium-ion battery. They offer superior safety, as they aren’t flammable, and last for 20 years, or 2,000 charge-discharges, equating to 1.2 million miles.

Under the trilateral agreement, Samsung will supply ASSB cells featuring the solid electrolyte developed by Solid Power to the German automotive group BMW, which will then develop modules and packs for ASSB cells to fit into their next-generation evaluation vehicles, expected in late 2026.

Metal Tech News reported in January that ASSBs will also debut in some smaller Samsung devices during 2026, including the Galaxy Ring fitness tracker, as a way of testing the new power supplies in the real world before incorporating them into smartphones, laptops, and other devices.Samsung’s ASSBs use a silver-carbon layer as the anode and a nickel-manganese-cobalt material for the cathode. Silver is not only the most electrically conductive metal available, it’s also substantially more plentiful in the Earth’s crust than lithium. Samsung's 600-Mile-Range Batteries That Charge in 9 Minutes Ready for Production/Sale Next Year

Read More........→February 14, 2026

IIT Bombay’s new smart platform to help researchers decode brain diseases

(Photo: IIT Bombay) IANS

New Delhi, (IANS) A team of bioengineers at the Indian Institute of Technology (IIT) Bombay has developed new smart platforms --BrainProt and DrugProtAI -- that unify data on scattered brain diseases to help researchers find markers, explore treatments, and pinpoint druggable targets.

BrainProt v3.0 is a database that combines various types of biological data -- from genes to proteins -- into a single platform to enable systematic insights into human brain function in both healthy and diseased states.

It is the first system to integrate multi-disease data from genomics, transcriptomics, proteomics, and biomarker research and multi-database information into one portal.

“BrainProt also includes resources to identify and understand protein expression differences between the left and right hemispheres of the human brain across 20 neuroanatomical regions. This is the first resource of its kind,” said Prof. Sanjeeva Srivastava from the Department of Biosciences and Bioengineering, IIT Bombay.

BrainProt includes data on 56 human brain diseases and 52 multi-omics datasets derived from more than 1,800 patient samples. These datasets include transcriptomic data for 11 diseases and proteomic data for six diseases.

For each disease, users can examine genes and proteins frequently associated with the disease, assess how strongly these genes and proteins are already supported by existing medical and scientific databases, and how their activity levels change in patient samples.

DrugProtAI was developed to understand whether a protein can be druggable (has the biological and physical characteristics needed to be a useful drug target) before doing costly experiments.

This is crucial because only about 10 per cent of human proteins currently have an FDA-approved drug, with another 3-4 per cent under investigation.

“Before investing years of work in a protein target, DrugProtAI predicts whether the protein is druggable by looking beyond the protein’s sequence, such as cellular location, structural attributes, and other unique characteristics it has,” said Dr. Ankit Halder, co-author of the study.

The tool generates a “druggability index” -- a probability score indicating how likely a protein is to be druggable. A higher score suggests that the protein shares many properties with proteins that already have approved drugs, while a lower score indicates that drug development would be more challenging.“By integrating DrugProtAI directly into BrainProt, we created a pipeline where researchers can move from identifying a disease marker to examining its expression patterns to evaluating its druggability and exploring existing compounds or clinical trials, all within an hour,” Halder said. IIT Bombay’s new smart platform to help researchers decode brain diseases | MorungExpress | morungexpress.com

Read More........→January 23, 2026

Mom and Baby Beat 1-in-a-Million Odds to Survive the ‘Rarest of Pregnancies’

This photo provided by the family shows, from left, Kaila, Suze, Ryu and Andrew Lopez at Cedars-Sinai hospital in Los Angeles in August 2025 – family photo

A Los Angeles woman recently celebrated the first Christmas with her baby boy, Ryu, born to truly remarkable circumstances.

Ryu developed outside his mother’s womb, and remained hidden for months behind an ovarian cyst that grew to be the size of a basketball. It was so unbelievable, the surgical/OBGYN team that delivered Ryu documented it for a case study in a medical journal.

The manner in which Ryu came into being represents a circumstance that’s “far, far less than 1 in a million,” said Dr. John Ozimek, medical director of labor and delivery at Cedars-Sinai in Los Angeles, where Ryu was born. “I mean, this is really insane.”

Now 41, Suze Lopez has always had an irregular cycle, so missed periods—even consecutive ones—are a normal occurrence. It was almost 20 years ago that she was diagnoses with a pair of ovarian cysts, one of which was removed immediately, and one of which was not.

So in early 2025 when Lopez noted her abdomen swelling, her first thought was the cyst. She never felt kicking, and never had morning sickness—and indeed her instinct was at least partly correct.

The pressure and pain in her abdomen grew as days passed, and she was certain that, even if it risked her ability to conceive again, it was time to remove the other cyst which unbeknownst to her had grown to weigh a mind-boggling 22 pounds.

She needed a CT scan to prepare for surgery, which required a pregnancy test for the radiation, and to her utter surprise the test came back positive. Lopez was delighted, but the pain and discomfort grew and soon she had to be hospitalized at Cedars-Sinai where her medical team found a near fully-developed fetus in an amniotic sack lodged against her pelvis.

The term for where the fetus develops is “implants” and the term for a fetus that implants outside of the womb is an “ectopic pregnancy.” Almost all of these go on to rupture and hemorrhage. As such, fetal mortality can be as high as 90% in such cases and birth defects are seen in about 1 in 5 surviving babies, SF Gate reports.

However, because fetal Ryu implanted against the pelvic wall and not against the liver, it was far more manageable, and the reason why Lopez didn’t have more pain earlier.

Lopez and her boy beat the odds, despite a mammoth surgical procedure that both delivered Ryu at 8 pounds and removed the ovarian cyst—together weighing as much as an adult bobcat. During the procedure, Lopez lost half her blood, and had to be continually given transfusions.

“The whole time, I might have seemed calm on the outside, but I was doing nothing but praying on the inside,” Andrew Lopez, Suze’s husband, told SF Gate. “It was just something that scared me half to death, knowing that at any point I could lose my wife or my child.”Instead, they both survived without any maleffects. Ryu “completes” their family, said his mother, and recently celebrated his first Christmas alongside his older sister Kaila. Mom and Baby Beat 1-in-a-Million Odds to Survive the ‘Rarest of Pregnancies

Read More........→January 10, 2026

How facial recognition for bears can help ecologists manage wildlife

Emily Wanderer, University of Pittsburgh

When a grizzly bear attacked a group of fourth- and fifth-graders in western Canada in late November 2025, it sparked more than a rescue effort for the 11 people injured – four with severe injuries. Local authorities began trying to find the specific bear that was involved in order to relocate or euthanize it, depending on the results of their assessment.

The attack, in Bella Coola, British Columbia, was very unusual bear behavior and sparked an effort to figure out exactly what had happened and why. That meant finding the bear involved – which, based on witness statements, was a mother grizzly with two cubs.

Searchers combed the area on foot and by helicopter and trapped four bears. DNA comparisons to evidence from the attack cleared each of the trapped bears, and they were released back to the wild. After more than three weeks without finding the bear responsible for the attack, officials called off the search.

The case highlights the difficulty of identifying individual bears, which becomes important when one is exhibiting unusual behavior. Bears tend to look a lot alike to people, and untrained observers can have a very hard time telling them apart. DNA testing is excellent for telling individuals apart, but it is expensive and requires physical samples from bears. Being trapped and having other contact with humans is also stressful for them, and wildlife managers often seek to minimize trapping.

Recent advances in computer vision and other types of artificial intelligence offer a possible alternative: facial recognition for bears.

As a cultural anthropologist, I study how scientists produce knowledge and technologies, and how new technology is transforming ecological science and conservation practices. Some of my research has looked at the work of computer scientists and ecologists making facial recognition for animals. These tools, which reflect both technological advances and broader popular interest in wildlife, can reshape how scientists and the general public understand animals by getting to know formerly anonymous creatures as individuals.

New ways to identify animals

A facial recognition tool for bears called BearID is under development by computer scientists Ed Miller and Mary Nguyen, working with Melanie Clapham, a behavioral ecologist working for the Nanwakolas Council of First Nations, conducting applied research on grizzly bears in British Columbia.

It uses deep learning, a subset of machine learning that makes use of artificial neural networks, to analyze images of bears and identify individual animals. The photos are drawn from a collection of images taken by naturalists at Knight Inlet, British Columbia, and by National Park Service staff and independent photographers at Brooks River in Katmai National Park, Alaska.

Bears’ bodies change dramatically from post-hibernation skinny in the spring to fat and ready for winter in the fall. However, the geometry of each bear’s face – the arrangement of key features like their eyes and nose – remains relatively stable over seasons and years.

BearID uses an algorithm to locate bear faces in pictures and make measurements between those key features. Each animal has a unique set of measurements, so a photograph of one taken yesterday can be matched with an image taken some time ago.

In addition to helping identify bears that have attacked humans or are otherwise causing trouble for people, identifying bears can help ecologists and wildlife managers more accurately estimate bear population sizes. And it can help scientific research, like the behavioral ecology projects Clapham works on, by allowing individual tracking of animals and thus better understanding of bear behavior.

Miller has built a web tool to automatically detect bears in the webcams from Brooks River that originally inspired the project. The BearID team has also been working with Rebecca Zug, a professor and director of the carnivore lab at the Universidad San Francisco de Quito, to develop a bear identification model for Andean bears to use in bear ecology and conservation research in Ecuador.

Animal faces are less controversial

Human facial recognition is extremely controversial. In 2021, Meta ended the use of its face recognition system, which automatically identified people in photographs and videos uploaded to Facebook. The company described it as a powerful technology that, while potentially beneficial, was currently not suitable for widespread use on its platform.

In the years following that announcement, Meta gradually reintroduced facial recognition technology, using it to detect scams involving public figures and to verify users’ identities after their accounts had been breached.

When used on humans, critics have called facial recognition technology the “plutonium of AI” and a dangerous tool with few legitimate uses. Even as facial recognition has become more widespread, researchers remain convinced of its dangers. Researchers at the American Civil Liberties Union highlight the continued threat to Americans’ constitutional rights posed by facial recognition and the harms caused by inaccurate identifications.

For wildlife, the ethical controversies are perhaps less pressing, although there is still potential for animals to be harmed by people who are using AI systems. And facial recognition could help wildlife managers identify and euthanize or relocate bears that are causing significant problems for people.

A focus on specific animals

Wildlife ecologists sometimes find focusing on individual animals problematic. Naming animals may make them “seem less wild.” Names that carry cultural meaning can also frame people’s interpretations of animal behavior. As the Katmai rangers note, humans may interpret the behaviors of a bear named Killer differently than one named Fluffy.

Wildlife management decisions are meant to be made about groups of animals and areas of territory. When people become connected to individual animals, including by naming them, decisions become more complicated, whether in the wild or in captivity.

When people connect with particular animals, they may object to management decisions that harm individuals for the sake of the health of the population as a whole. For example, wildlife managers may need to move or euthanize animals for the health of the broader population or ecosystem.

But knowing and understanding bears as individual animals can also deepen the fascination and connections people already have with bears.

For example, Fat Bear Week, an annual competition hosted by explore.org and Katmai National Park, drew over a million votes in 2025 as people campaigned and voted for their favorite bear. The winner was Bear 32, also known as “Chunk.” Chunk was identified in photographs and videos the old-fashioned way, based on human observations of distinguishing characteristics – such as a large scar across his muzzle and a broken jaw.

In addition to identifying problematic animals, I believe algorithmic tools like facial recognition could help an even broader audience of humans deepen their understanding of bears as a whole by connecting with one or two specific animals.

Emily Wanderer, Associate Professor of Anthropology, University of Pittsburgh

This article is republished from The Conversation under a Creative Commons license. Read the original article.

Read More........→January 06, 2026

First projects selected for INL reactor experiments

(Image: INL)

The five initial selections for end user experiments at Idaho National Laboratory's Microreactor Application Research Validation and Evaluation (MARVEL) reactor include projects related to data centres, technology application in commercial and advanced reactors, and applications for nuclear-generated process heat.

MARVEL is a sodium-potassium-cooled microreactor being developed by the US Department of Energy (DOE). It will generate 85 kilowatts of thermal energy and up to 20 kilowatts of electricity. It is to be located at the Transient Reactor Test Facility at the Idaho National Laboratory (INL), and will serve as a nuclear test bed to demonstrate microreactor operations and end-use applications, providing a platform for the private sector to access to an operational microreactor to demonstrate innovative new use cases for the technology. The reactor will be connected to INL's microgrid, and is expected to be operational by late 2027.

The projects selected in a competitive process as the first potential end-users for Marvel are:

- Amazon Web Services Inc, which proposes coupling the MARVEL reactor with a modular data centre, which could potentially provide a simple and cost-effective way for government agencies to build data centres anywhere in the world by enabling the creation of a self-sustaining, rapidly deployable system that can operate independently of traditional power infrastructure;

- DCX USA and Arizona State University, with a proposal to use MARVEL to demonstrate the feasibility of a microreactor to power a data centre for artificial intelligence to yield valuable data on how to provide a stable, continuous power supply capable of handling the unique demands of AI processing;

- General Electric Vernova, which proposes to use MARVEL to demonstrate remote and autonomous reactor operations and establish controls standards for broader application of the technology with commercial reactors;

- Radiation Detection Technologies Inc, proposing to use MARVEL to test advanced high-performance sensor technologies that could help monitor the performance of advanced reactors;

- Shepherd Power, NOV and ConocoPhillips with a proposal to leverage MARVEL for a pilot-scale desalination project using nuclear-generated process heat to demonstrate the viability of advanced nuclear energy for addressing produced water challenges in oil and gas operations.

"Nowhere else in the world will you find this level of support for public sector innovation in nuclear energy," said John Jackson, national technical director for the DOE Office of Nuclear Energy's Microreactor Program. "With access to MARVEL, companies can explore how microreactors will potentially help us win the global AI race, solve water challenges and so much more."The selectees will now work with DOE and national laboratory staff to create implementation plans and to determine the feasibility of their proposed application using MARVEL. Final agreements for proposed projects are expected to be announced in 2026. First projects selected for INL reactor experiments

Read More........→January 06, 2026

New Underwater Tool Lets Ecologists ID Fish From Their Sounds–46 Species So Far (LISTEN to 5 of Them)

The FishEye Collaborative / Cornell Lab of Ornithology

Underwater coral reefs are filled with thumps, pops, and snaps from shrimp and fish, and ecologists often use underwater microphones to monitor the health of marine environments.

But until now, ecologists have largely been unable to interpret these sounds because reefs are crowded with hundreds of different species—very few of which have had sounds accurately attributed to them.

A new tool from the FishEye Collaborative combines underwater sound recordings and a camera equipped with a 360° view to pinpoint the sounds made by individual fish.

The collaboration between bioacoustic researchers at the Cornell Lab of Ornithology and Aalto University have already identified 46 fish species from the coral reefs of Curaçao in the Caribbean—more than half of them were never known to make sound.

The findings culled from their eavesdropping along with a description of their invention, the Omnidirectional Underwater Passive Acoustic Camera (UPAC-360), were published recently in the journal Methods in Ecology and Evolution.

“The diversity of fish sounds on a coral reef rivals that of birds in a rainforest,” explained Marc Dantzker, lead author and the Director of FishEye Collaborative. “In the Caribbean alone we estimate that over 700 fish species produce sounds. The same biodiversity we aim to protect is also our greatest challenge, when it comes to identifying sounds.”

The FishEye Collaborative / Cornell Lab of Ornithology

“Spatial Audio lets you hear the direction from which sounds arrive at the camera,” explained Dantzker. “When we visualize that sound and lay the picture on top of the 360° image, the result is a video that can reveal which sound came from which fish.”

Now the most extensive collection of fish sounds ever published—and the growing library—is available to everyone at fisheyecollaborative.org/library.

The researchers say that identified sounds from the library can be used to automatically train machine learning systems to detect fish species in underwater recordings.

The technology is similar to smartphone apps like the Cornell Lab of Ornithology’s Merlin Bird ID that automatically identifies bird species by song or call, but no one needs to be on site. The UPAC-360 can be placed in reefs and left to collect data without the need for a diver or boat to be present.

The FishEye Collaborative / Cornell Lab of Ornithology

“We are a long way from being able to build ‘Merlin’ for the oceans, but the sounds are useful for scientists and conservationists right away,” says Aaron Rice, a senior author of the study and principal ecologist at the Cornell Lab.

Dantzker adds, “We’re making it possible to decode reef soundscapes, transforming acoustic monitoring into a powerful tool for ocean conservation.”

“By discovering the identity of these hidden voices, acoustics will become a powerful indicator of reef health and a strategy to monitor wider and deeper,” said Matt Duggan, co-author and PhD candidate at Cornell.

“The fact that our recording system is put out in nature and can record for long periods of time means that we’re able to capture species’ behaviors and sounds that have never before been witnessed,” said Rice.

The researchers are expanding the research, growing the library for the Caribbean, and broadening their efforts to other reefs around the world, including Hawai’i and Indonesia, in the coming months.

LISTEN to 5 fish sounds below… [NOTES: It’s loud at first. Also, be sure to read the text.]

New Underwater Tool Lets Ecologists ID Fish From Their Sounds–46 Species So Far (LISTEN to 5 of Them)

Read More........→December 19, 2025

First Human Cornea Transplant Using 3D Printed, Lab-Grown Tissue Restores Sight in a ‘Game Changer’ for Millions Who are Blind

File photo – credit: Maria Maximova

The first successful human implant of a 3D-printed cornea made from human eye cells cultured in a laboratory has restored a patient’s sight.

The North Carolina-based company that developed the cornea described the procedure as a ‘world first’—and a major milestone toward its goal of alleviating the lack of available donor tissue and long wait-times for people seeking transplants.

According to Precise Bio, its robotic bio-fabrication approach could potentially turn a single donated cornea into hundreds of lab-grown grafts, at a time when there’s currently only one available for an estimated 70 patients who need one to see.

“This achievement marks a turning point for regenerative ophthalmology—a moment of real hope for millions living with corneal blindness,” Aryeh Batt, Precise Bio’s co-founder and CEO, said in a statement.

“For the first time, a corneal implant manufactured entirely in the lab from cultured human corneal cells, rather than direct donor tissue, has been successfully implanted in a patient.”

The company said the transplant was performed Oct. 29 in one eye of a patient who was considered legally blind.

“This is a game changer. We’ve witnessed a cornea created in the lab, from living human cells, bring sight back to a human being,” said Dr. Michael Mimouni, director of the cornea unit at Rambam Medical Center in Israel, who performed the procedure.

“It was an unforgettable moment—a glimpse into a future where no one will have to live in darkness because of a shortage of donor tissue.”

Dubbed PB-001, the implant is designed to match the optical clarity, transparency and bio-mechanical properties of a native cornea. Previously tested in animal models, the company said its graft is capable of integrating with a patient’s own tissue.

The outer layer of the eye—covering the iris and pupil—can end up clouding a person’s vision following injuries, infections, scarring and other conditions. PB-001 is currently being tested in a single-arm phase 1 trial in Israel, which aims to enroll between 10 and 15 participants with excess fluid buildups in the cornea due to dysfunction within its inner cell layers.

Precise Bio said it plans to announce top-line results from the study in the second half of 2026, tracking six-month efficacy outcomes.

The corneas are designed to be compatible with current surgery hardware and workflows. Shipped under long-term cryopreservation, it is delivered preloaded on standard delivery devices and unrolls during implantation to form a natural corneal shape.

“PB-001 has the potential to offer a new, standardized solution to one of ophthalmology’s most urgent needs—reliable, safe, and effective corneal replacement,” said Anthony Atala, M.D., co-founder of Precise Bio and director of the Wake Forest Institute for Regenerative Medicine.


“The ability to produce patient-ready tissue on demand could lead the way towards reshaping transplant medicine as we know it.”(Edited from original article by Conor Hale) First Human Cornea Transplant Using 3D Printed, Lab-Grown Tissue Restores Sight in a ‘Game Changer’ for Millions Who are Blind

Read More........→December 17, 2025

Volcanic ash plume from Ethiopia moving over North India will not impact AQI: Experts

IANS Photo

New Delhi, (IANS) A massive ash cloud from the Hayli Gubbi volcanic eruption in northern Ethiopia that drifted across the Arabian Sea and reached India on Monday night is now moving over parts of north India, prompting aviation authorities to issue safety guidelines for airlines. However, it is not expected to impact the air quality as the ash cloud is primarily at mid-levels of the atmosphere, experts said on Tuesday.

The eruption, which occurred on Sunday after the long-dormant volcano suddenly became active, released a thick plume that travelled across the Red Sea toward Yemen and Oman before advancing toward the Indian subcontinent.

By 11 p.m. on Monday, the ash plume had entered Indian airspace and was observed over Delhi, with movement expected towards Punjab and Haryana through the night and well into Tuesday.

The unusual atmospheric event led the Directorate General of Civil Aviation (DGCA) to issue a detailed advisory to airlines, urging them to strictly avoid designated volcanic ash–affected areas and flight levels.

Airlines have been asked to modify flight planning, routing, altitude selection, and fuel calculations in accordance with the latest Volcanic Ash Advisories (VAAs).

The DGCA’s guidance comes amid reports of rerouted and delayed flights as aircraft operators attempt to navigate safely around the affected zones.

Volcanic ash poses a serious risk to aviation, especially jet engines, as ash particles can melt inside engines and cause severe damage.

IndiaMetSky Weather posted an explanation of the phenomenon on X, noting that the plume currently contains sulphur dioxide (SO₂) with low to moderate concentrations of volcanic ash.

In its post, IndiaMetSky Weather wrote: “The Ash plume mostly consists of Sulphur Dioxide with low to moderate concentrations of Volcanic Ash. It’s now stretching from Oman–Arabian Sea region into plains of North & Central India. It will not impact AQI levels but it will impact SO₂ levels at #Hills of #Nepal, #Himalayas and adjoining Terai belt of #UttarPradesh as some of the material will bump into the hills and later move into China."

"Low chances of Ashfall over plains but some places may see something. NO IMPACT ON AQI LEVEL AT SURFACE LEVEL AT ANY PLACE IS EXPECTED," the post mentioned.

"Plume will slowly continue to drift over Delhi, Haryana and Rajasthan region. Once again this is at middle levels of the atmosphere so there will not be any impact on the surface apart from some delays & changes in flight routes and some particles might fall to the surface (low chances),” it added.

Meteorologists emphasise that the ash cloud is primarily at mid-levels of the atmosphere, meaning it is unlikely to affect surface air quality for most regions in India. However, hills across Nepal, the Himalayas, and Uttar Pradesh’s Terai belt may see higher sulphur dioxide levels as the plume interacts with mountainous terrain.The plume is expected to gradually drift westward and weaken, but authorities continue to monitor its movement closely. Passengers have been advised to check with airlines for updated flight schedules as temporary disruptions may continue until the plume disperses. Volcanic ash plume from Ethiopia moving over North India will not impact AQI: Experts | MorungExpress | morungexpress.com

Read More........→November 25, 2025

TinyML: The Small Technology Tackling the Biggest Climate Challenge

Image by Gerd Altmann from Pixabay | For Representational Purpose Only

Tanveer Singh: As the planet struggles under the weight of 40+ billion metric tons of CO₂ emissions in 2024 alone, and an ever-rising energy demand, the search for smarter, leaner solutions has never been more urgent. There enters the TinyML, where the power of AI meets ultra-low energy computing to drive sustainability at scale.

It may be shocking, but as you are reading this, billions of sensors are tracking the planet’s health – from the air we breathe to the energy we consume. Already, more than 14 billion IoT devices are being used to monitor climate change and are projected to reach a whopping 30 billion by the end of 2030. But the concerning part is that the energy consumed by these devices is around 200 terawatt-hours of electricity annually, which is roughly equivalent to the entire energy consumption of countries like Thailand. To meet this demand, energy is produced through the traditional method of burning fuel, which further emits millions of Carbon footprints annually, that is even more than the lifetime emissions of 4 cars, just to monitor climate change. And therein lies the irony.

Furthermore, the constant transmission of data through these sensors requires millions of dollars for their deployment and maintenance. Like a large-scale smart city as big as New York, IoT networks can cost over $10–15 million per year to operate. This is exactly where TinyML comes as the solution, offering a path that enables IoT devices to process data locally, reducing energy consumption by up to 90% and significantly lowering costs.

Tiny ML bridges the gap between artificial intelligence and embedded systems, allowing machine learning activities even in sensors as small as a grain of sand. It is based on the idea of machine learning that is focused on building machine learning models on low-power devices like microcontrollers, enabling the device to process data instantly and anywhere, without depending on external internet storage to compute it. One clear example is Alexa, which uses TinyML models to send instant responses to the device for processing instead of sending through the cloud (external storage ), which will take a longer time.

Additionally, TinyML improves privacy and data security by running locally and reduces overall operational cost by 50-60% as compared to large ML models working on external storage. Take the example of Google's TinyML image classification that runs directly on devices, keeping images private while cutting storage and cloud costs by over 50%. TinyML can be best understood as having a mini robot in your pocket that can solve problems instantly, instead of always asking a big computer far away for help. It is faster, saves energy, and keeps your information private. When this field is applied to the climate, its efficiency becomes a distinguished factor.

Besides being cost-effective and having higher efficiency, it also helps in tracking air quality to predict natural disasters and, hence, supports the fight against climate change. Tiny ML sensors enable the quick detection of forest fires through heat or smoke detection, and aid in local air and water quality checks, eliminating the need for cloud computing dependency. For instance, Arduino-based air quality sensors are used to measure air quality and provide data on the temperature and humidity of an area. These models can also be used in solar or wind farms to check the performance of the solar cells and windmills through the consumption of energy, which can further help in increasing the efficiency of the farms. For example, Google’s DeepMind AI was successfully used with wind farms in the U.S. to predict wind power output 36 hours in advance, boosting the value of wind energy by around 20%. Interestingly, these sensors can also aid in monitoring birds' and whales' calls or other animals to track migration patterns and population health, as well as because of their small size and working on low power, and hence, they can help researchers to get valuable data on ecosystems without disturbing the wildlife. Moreover, TinyML sensors used in smart grids help in improving energy utilization by constantly monitoring and managing the transport of electricity so that energy is not wasted. Besides this, these devices can help in measuring the water pressure, tidal patterns, and ground movement of an area, and the data from this can be used to detect disasters earlier. For instance, in Japan, Tiny ML sensors placed along coastlines measure tidal waves and ground vibration in real time, which helps authorities to issue faster tsunami and earthquake warnings.

However, while these applications highlight the transformative impact of Tiny ML in tackling climate related problems, the integration also brings forth several challenges that need to be addressed to ensure reliability and scalability. First and foremost is the limitation of hardware, which is that there is limited storage, approximately in kilobytes or 1 to 5 megabytes, to store data compared to traditional models that have memory in gigabytes and terabytes. As a result, small models in TinyML will be less precise than the traditional models, which can be a huge challenge in models that work on reliability, for example, disaster management models. Furthermore, the harsh conditions like weather or wildlife can damage these devices, leading to malfunctioning and increasing the cost of maintenance.

Additionally, even though these devices are cost-effective, deploying billions of devices will still require huge funding, which can limit their production and scalability.

Despite these challenges, the future of TinyML is being shaped by the integration of emerging technologies, large-scale adoption, and the expanding market of AI. The combination of TinyML with the 5 G network, which provides 100 times faster speed than 4 G and the ability to connect over one million devices per square kilometer, can enable the creation of massive, interconnected sensors all over the cities that can provide faster and reliable data. Additionally, integrating it with federated learning- an ML technique that enables multiple devices to train a model together without sharing the raw data - can help in ensuring data privacy and increasing the accuracy of the models. Furthermore, Government and Research institutes are likely to adopt TinyML models in various tasks as they provide a scalable and cost-effective solution, especially in environments with limited resources. For instance, the U.S. National Aeronautics and Space Administration (NASA) has explored TinyML to process sensor data directly on satellites, reducing the need for constant communication with Earth.

It won’t be an exaggeration to say that the Tiny ML models have the potential to shape the future of the world. By offering scalable as well as energy-efficient solutions, Tiny ML stands out as the best alternative to tackle the climate change problems. From reducing the CO2 emissions to providing faster processing of data and strengthening the privacy and accuracy of the data, the Tiny ML model can be a changemaker catalyst not only in the world of climate change but in other fields, too. Undoubtedly, Tiny ML paves the way for a future where artificial intelligence works in harmony with the planet.Tanveer Singh, a first-year student at Plaksha University, has been passionate about writing articles and poems since high school. From raising public awareness of new technologies to highlighting environmental and societal issues, he has explored a wide range of themes through his work and aspires to continue making an impact in this space for the long run. TinyML: The Small Technology Tackling the Biggest Climate Challenge | MorungExpress | morungexpress.com

Read More........→November 24, 2025