Indigenous rangers in the Warddeken Indigenous Protected Area in West Arnhem, Northern Territory, ran the AI animal-detection model MegaDetector over…
Our take This is AI as a sieve, not a judge: it threw out the empty frames so rangers could spend their time on work only they can do. The credit goes to the Warddeken rangers and elders who set the terms first. Any program bringing AI onto Indigenous land should copy the order: consent, then code.
University of Kent researchers David Roberts and Jason R.C.
Our take Credit where it's due: the chatbots did better than search. But a safeguard that guards tigers and waves through corals and orchids protects what people find appealing, not what is endangered, and that gap is the AI companies' to close.
Researchers at Inria, Sorbonne Université and the insurer AXA compared three AI weather models — GenCast, FourCastNet 3 and FGN — with ECMWF's operational…
Our take Better cyclone tracks mean earlier warnings for the people in a storm's path. The catch is in the same paper: a model that places a storm well can still misjudge its strength. Forecasters should take the first finding and keep checking the second.
The European Centre for Medium-Range Weather Forecasts (ECMWF) said on Oct 12 that it has extended its machine-learning forecasting system, AIFS, into a…
Our take Ships, ports and coastal towns gain most if one model can forecast wind, waves and sea ice together a day further out. This is a prototype, not a service, and ECMWF is candid about where it still drifts. That candor is the standard other AI forecasters should copy.
The European Centre for Medium-Range Weather Forecasts (ECMWF) has introduced AIFS-COMPO, an experimental AI system that forecasts aerosols and pollutants…
Our take Air-pollution forecasts are a public-health tool, and a cheaper one can look further ahead. The credit belongs to two decades of physics-based reanalysis the model learned from: the AI doesn't replace that work, it stands on it, which is the right order of operations.
The European Space Agency has released Earth Virtual Expert (EVE), a large language model built by ESA Φ-lab with Pi School, Mistral and Imperative Space…
Our take An open model built on agency science, with its code and training data public, is the right way to put a chatbot between the public and Earth observation evidence. Its worth rests on that judge step: an assistant that misstates satellite science to a policymaker does more harm than none.
A machine learning method called probabilistic bias correction, which learns a forecast model's systematic errors from its own past forecasts and corrects…
Our take Two to six weeks out is when farmers plan planting and water managers set allocations, and it has been forecasting's blind spot. This gain is measured, not promised. Whether it reaches farmers depends on the forecasters testing it in Kenya, not the lab that built it.
The National Hurricane Center's track forecast for Hurricane Isaias favored the eastward solutions of AI-based models, including the Google DeepMind…
Our take A forecast that points the right way days out is time people on the Panhandle can use. The judgment was the forecasters'; the model is Google's. A public warning service that leans on a private company's model needs guaranteed access to it, not goodwill.
A study published Oct. 14 in Nature ran a year-long, single-blind test of space-based methane detection: 481 metered methane releases in Arizona and 265…
Our take This is what honest evaluation looks like: blind, a year long, and willing to report where AI fails. Satellites can catch methane leaks that matter for the climate. An AI alarm that cries wolf costs regulators and operators trust, so AI methods should be held to this kind of test before anyone acts on their alerts.
University of Michigan-led researchers used the large language models Claude and ChatGPT to find and classify interactions between species described in…
Our take This is AI in a supporting role: reading what nature watchers already wrote down so ecologists can see how living communities are shifting. The credit belongs to the people who took the notes and the researchers who checked the machine's work, and it's the kind of AI use worth more of.
When weighing climate policy trade-offs, large language models were on average 7.5 times more likely to recommend staying the course than doing something…
Our take Advice that defaults to what people already do is not neutral when what people already do runs on fossil fuel. A tool people ask what to buy, cook and fund could quietly slow the change the climate needs. Developers can fix a default; they have to decide it is worth fixing.