Weather, water, farms, conservation. A place to discover developments quickly, then stay with the questions that matter to you.
Newest source publications first. These are source dates, not live activity.
Weather forecasting has spent fifty years as one of the largest users of supercomputing. AI models trained on the archive now produce comparable global forecasts in minutes, and the weights are published. The measurements they depend on are the part that has not become cheap.
Deployed · NOAA / ECMWF / World Meteorological Organization / NVIDIAIndia's Agriculture Ministry reported that a Kharif 2025 pilot sent local monsoon-onset forecasts by SMS to 38,845,214 farmers in 13 states, using a blend that included NeuralGCM, ECMWF AIFS, and 125 years of India Meteorological Department rainfall data.
Deployed · India Ministry of Agriculture and Farmers Welfare / University of Chicago Development Innovation Lab / India Meteorological Department / ECMWF / Google ResearchResearchers trained a deep-learning detector on microscopic bacterial microcolonies and visually similar chicken, spinach, and cheese debris, aiming to make food-safety screening faster and more reliable in messy samples.
Experimental · Korea University / Florida State University / Oregon State University / University of California, DavisA machine drives a vegetable field, photographs every plant, decides which are weeds, and burns them with short laser pulses. In 2024 field trials in New Jersey and New York, it controlled weeds as well as or better than the standard herbicide programme.
Deployed · Cornell AgriTech / Rutgers University / Western Growers / Carbon RoboticsNVIDIA reports that Pano uses human-in-the-loop AI detection and alerts for wildfire monitoring.
Deployed · Pano AI / NVIDIAAi2’s EarthRanger brings wildlife observations and field reports together for conservation teams.
Emerging · Ai2 / NVIDIAECMWF brought its Artificial Intelligence Forecasting System into operational service.
Deployed · ECMWFA study combined image-based tillage classification, soil sensors, weather, slope, and crop inputs to recommend tilling intensity and fertilizer amount; authors report stationary prototypes deployed on 155 farms across five countries.
Experimental · npj Sustainable AgricultureGenCast used machine learning to generate ensembles of possible weather outcomes up to 15 days ahead.
Demonstrated · Google DeepMindClearbot uses electric boats and computer vision for waterway waste collection, as described in NVIDIA’s field report.
Deployed · Clearbot / NVIDIANeuralGCM combined atmospheric physics with machine learning for weather and climate modeling.
Demonstrated · Google Research & collaboratorsResearchers demonstrated useful river-flood forecasts in watersheds with no local streamflow gauges.
Demonstrated · Google Research