mlsanityData to 14 Oct 2026

Data-driven solar forecasting enables near-optimal economic decisions

arXiv 2509.06925 ↗First posted 8 Sep 2025physics.geo-ph cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Solar energy adoption is critical to achieving net-zero emissions. However, it remains difficult for many industrial and commercial actors to decide on whether they should adopt distributed solar-battery systems, which is largely due to the unavailability of fast, low-cost, and high-resolution irradiance forecasts. Here, we present SunCastNet, a lightweight data-driven forecasting system that provides 0.05^circ, 10-minute resolution predictions of surface solar radiation downwards (SSRD) up to 7 days ahead. SunCastNet, coupled with reinforcement learning (RL) for battery scheduling, reduces operational regret by 76--93% compared to robust decision making (RDM). In 25-year investment backtests, it enables up to five of ten high-emitting industrial sectors per region to cross the commercial viability threshold of 12% Internal Rate of Return (IRR). These results show that high-resolution, long-horizon solar forecasts can directly translate into measurable economic gains, supporting near-optimal energy operations and accelerating renewable deployment.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 75 references that are in the map. First posted on arXiv 8 Sep 2025.

Builds on

19 of 75 references.

References · 19

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  3. 2022FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operatorscited by 776
  4. 2023ClimaX: A foundation model for weather and climatecited by 337
  5. 2023Neural General Circulation Models for Weather and Climatecited by 239
  6. 2023WeatherBench 2: A benchmark for the next generation of data-driven global weather modelscited by 236
  7. 2023Spherical Fourier Neural Operators: Learning Stable Dynamics on the Spherecited by 233
  8. 2023FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Leadcited by 175
  9. 2022Forecasting Global Weather with Graph Neural Networkscited by 168
  10. 2023Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscalingcited by 110
  11. 2022Physically Constrained Generative Adversarial Networks for Improving Precipitation Fields from Earth System Modelscited by 29
  12. 2024FuXi Weather: A data-to-forecast machine learning system for global weathercited by 21
7 more
  1. 2014Optimal Hour-Ahead Bidding in the Real-Time Electricity Market with Battery Storage using Approximate Dynamic Programmingcited by 6
  2. 2024Modulated Adaptive Fourier Neural Operators for Temporal Interpolation of Weather Forecastscited by 4
  3. 2017Factoring the Cycle Aging Cost of Batteries Participating in Electricity Marketscited by 3
  4. 2024Data-driven Surface Solar Irradiance Estimation using Neural Operators at Global Scalecited by 3
  5. 2025Finetuning a Weather Foundation Model with Lightweight Decoders for Unseen Physical Processescited by 3
  6. 2024Balancing Forecast Accuracy and Switching Costs in Online Optimization of Energy Management Systemscited by 2
  7. 2025SolarSeer: Ultrafast and accurate 24-hour solar irradiance forecasts outperforming numerical weather prediction across the USAcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Attentive Convolutional Deep Reinforcement Learning for Optimizing Solar-Storage Systems in Real-Time Electricity Markets
  2. 2024Learning a local trading strategy: deep reinforcement learning for grid-scale renewable energy integration
  3. 2018Learning to Compensate Photovoltaic Power Fluctuations from Images of the Sky by Imitating an Optimal Policy ↗
  4. 2026Reinforcement Learning for Sequential Solar PV Policy Design under Uncertainty: An Agent-Based Approach
  5. 2026FarSky: Task-Aware Latent-Space Coupling for Generative Intra-Hour Solar Forecasting
  6. 2026Comparative Evaluation of MILP, MPC, and Reinforcement Learning for Commercial Battery Dispatch Under Time-of-Use Tariffs
  7. 2026PARA-PV: Physics-Aware Retrieval-Augmented PV Prediction Based on Frozen Foundation Model and Distribution Shift Correction
  8. 2025Green Energy Management for Sustainable Data Centers Using Deep Reinforcement Learning