AI Weather Models Forecast Well but Miss the Butterfly Effect
A modeling study across ERA5, PlaSim and Lorenz 96 finds a trade-off between large-scale forecast skill and physically realistic error growth.
Scientific publication4 min read
Research field
Climate, atmosphere, oceans, water, geology, and the living environment.
A modeling study across ERA5, PlaSim and Lorenz 96 finds a trade-off between large-scale forecast skill and physically realistic error growth.
Scientific publication4 min read
A commentary on the AMOC–cryosphere system argues that stabilizing feedbacks deserve a place in tipping-risk assessments, while leaving their net effect unresolved.
Scientific publication4 min read
A 2026 arXiv preprint reports a continually learning neural-operator surrogate that inverted 2,131,667 in-range airborne electromagnetic soundings in 24.9 seconds on one GPU. Posterior similarity was tested separately on matched comparisons involving 15 soundings, not across the survey-scale application.
Scientific publication4 min read
A laboratory study found that growing and decaying rupture pulses approximately followed a common size–speed relation predicted by a two-dimensional friction theory.
Scientific publication4 min read
GeoFormer, a geometry-aware Transformer for prestack seismic data, recorded the lowest reported RMSE on all four field datasets, but the study's noise examples were qualitative.
Scientific publication3 min read
A preprint using Sentinel-3 reflectance and Norwegian monitoring data found large accuracy differences across feature-engineering choices for chlorophyll-a and Secchi disk depth, with the best setup varying by model and target.
Scientific publication4 min read
A numerical model of subduction initiation showed heat and uplift associated with an arc-like structure, even though no clearly developed cold slab appeared during the modeled period.
Scientific publication3 min read