Solar Forecasting with Causality: A Graph-Transformer Approach to Spatiotemporal Dependencies

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Niu, Yanan, Psaltis, Demetri, Moser, Christophe, Lambertini, Luisa
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918144183894016
author Niu, Yanan
Psaltis, Demetri
Moser, Christophe
Lambertini, Luisa
author_facet Niu, Yanan
Psaltis, Demetri
Moser, Christophe
Lambertini, Luisa
contents Accurate solar forecasting underpins effective renewable energy management. We present SolarCAST, a causally informed model predicting future global horizontal irradiance (GHI) at a target site using only historical GHI from site X and nearby stations S - unlike prior work that relies on sky-camera or satellite imagery requiring specialized hardware and heavy preprocessing. To deliver high accuracy with only public sensor data, SolarCAST models three classes of confounding factors behind X-S correlations using scalable neural components: (i) observable synchronous variables (e.g., time of day, station identity), handled via an embedding module; (ii) latent synchronous factors (e.g., regional weather patterns), captured by a spatio-temporal graph neural network; and (iii) time-lagged influences (e.g., cloud movement across stations), modeled with a gated transformer that learns temporal shifts. It outperforms leading time-series and multimodal baselines across diverse geographical conditions, and achieves a 25.9% error reduction over the top commercial forecaster, Solcast. SolarCAST offers a lightweight, practical, and generalizable solution for localized solar forecasting.
format Preprint
id arxiv_https___arxiv_org_abs_2509_15481
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Solar Forecasting with Causality: A Graph-Transformer Approach to Spatiotemporal Dependencies
Niu, Yanan
Psaltis, Demetri
Moser, Christophe
Lambertini, Luisa
Machine Learning
Social and Information Networks
I.2.6; I.5.4
Accurate solar forecasting underpins effective renewable energy management. We present SolarCAST, a causally informed model predicting future global horizontal irradiance (GHI) at a target site using only historical GHI from site X and nearby stations S - unlike prior work that relies on sky-camera or satellite imagery requiring specialized hardware and heavy preprocessing. To deliver high accuracy with only public sensor data, SolarCAST models three classes of confounding factors behind X-S correlations using scalable neural components: (i) observable synchronous variables (e.g., time of day, station identity), handled via an embedding module; (ii) latent synchronous factors (e.g., regional weather patterns), captured by a spatio-temporal graph neural network; and (iii) time-lagged influences (e.g., cloud movement across stations), modeled with a gated transformer that learns temporal shifts. It outperforms leading time-series and multimodal baselines across diverse geographical conditions, and achieves a 25.9% error reduction over the top commercial forecaster, Solcast. SolarCAST offers a lightweight, practical, and generalizable solution for localized solar forecasting.
title Solar Forecasting with Causality: A Graph-Transformer Approach to Spatiotemporal Dependencies
topic Machine Learning
Social and Information Networks
I.2.6; I.5.4
url https://arxiv.org/abs/2509.15481