š Earth Science¶
š§ NeurIPS2025 Ā· 6 paper notes
š Same area in other venues: š· CVPR2026 (1) Ā· š¬ ICLR2026 (7) Ā· š§Ŗ ICML2026 (2) Ā· š¤ AAAI2026 (2)
- A Probabilistic U-Net Approach to Downscaling Climate Simulations
-
This work presents the first application of a probabilistic U-Net to statistical climate downscaling (16Ć super-resolution). By sampling from a variational latent space, the model generates ensemble forecasts for uncertainty quantification. The paper systematically compares four training objectives ā WMSE, MS-SSIM, WMSE-MS-SSIM, and afCRPS ā revealing complementary trade-offs between extreme event capture and fine-scale spatial variability preservation.
- Adaptive Online Emulation for Accelerating Complex Physical Simulations
-
This paper proposes Adaptive Online Emulation (AOE), a framework that dynamically trains an ELM-based neural network surrogate model during physical simulation execution to replace expensive computational components, requiring no offline pretraining. On an exoplanetary atmospheric simulation, AOE achieves an 11.1Ć speedup (91% time savings) with only ~0.01% accuracy loss.
- ControlFusion: A Controllable Image Fusion Framework with Language-Vision Degradation Prompts
-
This paper proposes ControlFusion, a controllable infrared-visible image fusion framework based on language-vision degradation prompts. It employs a physics-driven degradation imaging model to simulate compound degradations, and uses a prompt-modulated network to perform dynamic restoration and fusion, achieving comprehensive state-of-the-art performance under both real-world and compound degradation scenarios.
- Power Ensemble Aggregation for Improved Extreme Event AI Prediction
-
This paper proposes an adaptive ensemble aggregation method based on the power mean. By applying nonlinear aggregation (power exponent \(p>1\)) to the score of ensemble members from generative weather prediction models, the method significantly improves classification performance for extreme high-temperature events, with greater gains at higher quantile thresholds.
- Predicting Public Health Impacts of Electricity Usage
-
This paper proposes HealthPredictor, an AI pipeline that maps electricity consumption end-to-end to public health damages (measured in $/MWh), comprising three modules: fuel mix prediction, air quality conversion, and health impact assessment. Health-driven optimization significantly reduces health impact prediction error compared to fuel-mix-driven baselines, and achieves a 24ā42% reduction in health damages in an EV charging scheduling case study.
- Reasoning With a Star: A Heliophysics Dataset and Benchmark for Agentic Scientific Reasoning
-
This paper introduces Reasoning With a Star (RWS), a 158-question scientific reasoning benchmark derived from NASA heliophysics summer school problem sets, spanning three answer types (numeric/symbolic/textual). Paired with a unit-aware grader, it evaluates four multi-agent coordination paradigms (HMAW/PACE/PHASE/SCHEMA) and finds that no single paradigm dominates across all tasks ā the systems-engineering-inspired SCHEMA achieves the strongest performance on tasks requiring rigorous constraint validation.