arXiv:2607. 22342v1 Announce Type: new Abstract: The development of effective urban climate adaptation strategies requires comprehensive spatial information on rooftops and buildings, since such information underpins the assessment of ecosystem services provided by green infrastructure, particularly for urban heat island (UHI) mitigation.
By Htet Yamin Ko Ko
SolarBench is an open global benchmark for image-based solar nowcasting that consolidates over six million sky and satellite images from 11 sites across a decade, paired with irradiance, PV output, and atmospheric data. The benchmark includes a toolbox for reproducible data access, processing, model development, and evaluation. Using SolarBench, the authors benchmark representative models, uncover a gap between average forecasting accuracy and the capture of rapid solar fluctuations, quantify predictability across cloud regimes, and demonstrate data‑efficient adaptation to new PV systems.
By Yuhao Nie, Stephen Campbell, Quentin Paletta, Liwenbo Zhang, Tao Jing, Samer Chaaraoui, Jonathan Giezendanner, Andea Scott, Tao Sun, Cong Feng, Max Aragon, Jacques Camier, Adam Jensen, Florian Kotthoff, Yuexing Yang, Yang Ming, Mengying Li, Stefanie Meilinger, Yupeng Wu, Adam Brandt, Sherrie Wang
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
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 presents a global solar photovoltaic (PV) siting method that uses geospatial embeddings—dense vectors capturing geophysical properties—to learn a latent solar suitability signal from 38,591 existing solar sites. A soft‑voting ensemble of a random forest and a multilayer perceptron achieves a median ROC‑AUC of 0.90, outperforming traditional multi‑criteria decision analysis (MCDA) approaches by 0.06–0.30 across thirteen countries. The model identifies that the top 20% of suitable land could support 84% of projected annual energy yield and 67% of installed capacity, with 5.6% of global land (9.8% if cropland is allowed) remaining highly suitable after standard constraints.
whyItMatters":"The study provides a scalable, data‑driven tool that improves solar site selection accuracy and highlights the vast potential of underutilized land for renewable energy deployment."
By Abdullah Rehman, Quentin Paletta, Rui Song
The paper introduces IMPACT, a physics‑informed multimodal deep‑learning framework that forecasts photovoltaic power 10–110 minutes ahead with probabilistic outputs. It uses a four‑branch architecture to encode plant‑level temporal history, inverter‑level spatial cloud dynamics, known‑future solar geometry, and current meteorological data, fusing them via gated cross‑attention. The model outperforms 14 baselines, achieving a forecast skill score of 0.2950 and maintaining strong performance under overcast and variable sky conditions.
By Anushka Katiyar, Cong Feng, Jing Wang, Tristan Liu, Simon Julien, Zachary Jacobs