Climate Modeling Comparison Hub

3 papers - avg viability 5.0

Reference Surfaces

Ensemble Graph Neural Networks for Probabilistic Sea Surface Temperature Forecasting via Input Perturbations(7.0)
Improve sea surface temperature forecasting by using graph neural networks and input perturbations to generate probabilistic forecasts, enabling better risk management for maritime industries.
CarbonBench: A Global Benchmark for Upscaling of Carbon Fluxes Using Zero-Shot Learning(4.0)
CarbonBench is a benchmark for evaluating zero-shot learning models in carbon flux upscaling across diverse ecosystems.
Data-Driven Integration Kernels for Interpretable Nonlocal Operator Learning(4.0)
A framework for interpretable nonlocal operator learning in climate models using data-driven integration kernels.