Climate change · AI and machine learning
New weather and climate research on climate change with AI and machine learning as the main approach, one page per paper.
All summaries
-
Climate changeA three-tier benchmark scores physical, data-driven and hybrid climate models on equal terms
ClimateBench v2 proposes an open, three-tier test that holds back all observations after 2015 and scores any climate model, physical or machine-learned, with probabilistic skill scores.
-
Climate changeDiffusion model sharpens and bias-corrects climate model rain, keeping trends
A diffusion model trained only on ERA5 observations can turn coarse GFDL-ESM4 precipitation into sharp 0.25° fields with fewer extreme-rain biases than quantile mapping, while keeping the model's large-scale patterns and climate change signal.
-
Climate changeChina's forest biomass density rose from 95.74 to 122.69 Mg per hectare between 1985 and 2023
A 30 m annual map of China's forest biomass from 1985 to 2023 shows aboveground carbon stock rising from 5.50 to 13.97 PgC, mostly through growth of existing forest.
-
Climate changeOpen global dataset maps 2.75 billion buildings with heights from satellite images
Using only PlanetScope satellite images plus existing footprint data, the authors built the first complete global set of building outlines, 3 m height maps and simple 3D models, with height errors of 1.5 to 8.9 m by continent.