arXiv cs.CY· Abdullah Rehman, Quentin Paletta, Rui Song·· 11 小时前AI 评分38
利用地理空间嵌入进行全球太阳能选址
Global Solar Siting from Geospatial Embeddings
AI 导读
研究团队用地理空间嵌入向量分析 38,591 个现有太阳能电站及其占地，训练出随机森林与多层感知机（RF+MLP）软投票集成模型来识别潜在太阳能适宜性信号。该模型在 13 个国家的未来装机验证中区分现有电站与随机土地的中位 ROC-AUC 达 0.90，较已发表 MCDA 方法在每个国家提升 0.06-0.30。
正文 · 原文
Abstract:Global solar photovoltaic (PV) capacity is rapidly growing, helping decrease our emissions and dependence on fossil fuels. However, optimally siting a solar plant remains challenging, requiring anticipation of geographical, urban, and infrastructure needs. Current methods rely on multi-criteria decision analysis (MCDA) using hand-picked geophysical layers and solar-resource products, however these strategies are not geographically transferable and do not capture the practical requirements of solar sites. We use geospatial embeddings, dense vectors representing geophysical properties of a location, to analyse 38,591 existing solar sites and the land they were built on to learn the latent solar suitability signal. We assess a set of linear and non-linear models and select a soft-voting ensemble of a random forest and a multilayer perceptron (RF+MLP ensemble), chosen for accuracy and large scale deployability. Validated against future installations in thirteen countries, the ensemble separates existing solar sites from random land with a median ROC-AUC of 0.90. Compared with published MCDA strategies, the ensemble increases ROC-AUC by 0.06-0.30 in every country. The ranking also concentrates real deployment: the most-suitable 20% of land holds 84% of estimated generation (annual energy yield) and 67% of installed capacity (potential power output). After applying standard siting constraints, 5.6% of global land (9.8% if cropland is permitted) remains highly suited to solar. The global 10 m resolution solar suitability dataset and code can be found here: this https URL.
| Comments: | Accepted at Tackling Climate Change with Machine Learning workshop at NeurIPS 2026. 17 pages, 11 figures |
| Subjects: | Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Computers and Society (cs.CY) |
| Cite as: | arXiv:2611.08831 [cs.LG] |
| (or arXiv:2611.08831v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.08831 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Abdullah Rehman [view email]
[v1]
Fri, 6 Nov 2026 00:37:39 UTC (16,103 KB)
来源：arXiv cs.CY · arxiv.org