CORDEX-ML-Bench benchmarks 40 ML models for climate downscaling and finds generative models outperform deterministic ones on precipitation while historically trained models underestimate future climate signals.
Fixing the double penalty in data-driven weather forecasting through a modified spherical harmonic loss function
5 Pith papers cite this work, alongside 5 external citations. Polarity classification is still indexing.
5
Pith papers citing it
5
external citations · external index
years
2026 5representative citing papers
Online conformal prediction post-processing guarantees calibrated uncertainty coverage for GenCast, NeuralGCM, and AIFS-ENS forecasts of temperature and precipitation including extremes.
PhysMetrics.Weather is an evaluation framework that quantifies physical realism of ML weather prediction models using conservation, spectral, and dynamical metrics.
SEETO achieves 6% better hypervolume in NWP parameter calibration with only 20 evaluations by using meteorological state representations for bi-level knowledge transfer from similar past tasks.
A typology of blended ML and physics-based modeling approaches for weather and climate is presented to support informed decision-making in prediction systems.
citing papers explorer
-
CORDEX-ML-Bench: A Benchmark for Data-Driven Regional Climate Downscaling -Experiment Design and Overview
CORDEX-ML-Bench benchmarks 40 ML models for climate downscaling and finds generative models outperform deterministic ones on precipitation while historically trained models underestimate future climate signals.
-
Rigorous uncertainty quantification of probabilistic AI weather forecasts with conformal prediction
Online conformal prediction post-processing guarantees calibrated uncertainty coverage for GenCast, NeuralGCM, and AIFS-ENS forecasts of temperature and precipitation including extremes.
-
PhysMetrics.Weather: An Evaluation Framework for Physical Consistency in ML Weather Models
PhysMetrics.Weather is an evaluation framework that quantifies physical realism of ML weather prediction models using conservation, spectral, and dynamical metrics.
-
Efficient Parameter Calibration of Numerical Weather Prediction Models via Evolutionary Sequential Transfer Optimization
SEETO achieves 6% better hypervolume in NWP parameter calibration with only 20 evaluations by using meteorological state representations for bi-level knowledge transfer from similar past tasks.
-
Blending machine learning and physics-based approaches for weather and climate: a typology
A typology of blended ML and physics-based modeling approaches for weather and climate is presented to support informed decision-making in prediction systems.