GateFormer is a dual‑decoder Vision Transformer that forecasts intra‑hour global horizontal irradiance (GHI) from sky images by embedding observed GHI into the visual token stream and predicting both a future GHI trajectory and the final‑horizon change. The two predictions are adaptively weighted in prediction space, with magnitude‑ and direction‑supervision to reduce remaining error. On multiple benchmarks, GateFormer achieves the lowest final‑horizon RMSE, outperforming state‑of‑the‑art transformers and showing significant gains especially during positive ramp events.
The paper introduces SolCloudLLM, a large language model–based framework that fuses sky‑image patches with time‑series data through bidirectional multimodal fusion for short‑term solar forecasting. Experiments on the SIRTA and SKIPP'D datasets show that SolCloudLLM outperforms existing baselines, achieving up to a 25.4% reduction in mean squared error, especially under cloudy conditions and in few‑shot scenarios.
By Ken Chen, Maneesha Perera, Wei Wang, Sachith Seneviratne, Hansani Weeratunge, Saman Halgamuge
The paper introduces a dual‑framework Vision Transformer (ViT) method for estimating diffuse horizontal irradiance (DHI) from sky images in data‑scarce settings. It combines physics‑based atmospheric parameters, a sequential pipeline that first predicts synthetic global horizontal irradiance (GHI), and a dual‑parallel architecture that processes raw and physics‑informed overlay‑enhanced fisheye images. Tested on Chilbolton Observatory data, the approach achieves RMSE within 2–6 W/m² of a ViT trained on a full dataset, demonstrating a scalable, cost‑effective solution for solar resource assessment when long‑term sky imagery is limited.
By David Hamlyn, Sunny Chaudhary, Tasmiat Rahman
arXiv:2610.40418v1 Announce Type: cross
Abstract: This work develops a physics-informed multimodal deep learning framework for 10- to 110-minute-ahead probabilistic photovoltaic power forecasting. Th...
By Anushka Katiyar, Cong Feng, Jing Wang, Tristan Liu, Simon Julien, Zachary Jacobs
arXiv:2606. 19026v1 Announce Type: cross Abstract: Forecast errors in high-resolution numerical weather prediction (NWP) systems are often linked to unresolved planetary boundary layer (PBL) processes, convection, terrain-induced circulations, and other vertically structured atmospheric phenomena.
By David Aaron Evans, Jay C. Rothenberger, Kara J. Sulia, Nick P. Bassill, Chris D. Thorncroft
The paper introduces a single-stage diffusion model that jointly denoises future sky images and clear-sky index sequences, eliminating the need for a separate regression stage. Trained solely on sky images and deterministic covariates, the model achieves a pooled RMSE of 104.1 W m⁻² and a CRPS skill of +0.34 on 2023 SIRTA data, outperforming twelve baseline configurations and maintaining performance when retrained on earlier years. Compared to a separate regressor applied to the model’s generated frames, the joint training recovers roughly 46 W m⁻² of accuracy, while a deterministic network that also uses measured irradiance attains a slightly lower RMSE of 97.6 W m⁻² but lower CRPS skill.
By Kanawut Suwandee, Suwichaya Suwanwimolkul