Cross-Domain Generalization of Multimodal LLMs for Global Photovoltaic Assessment

TL;DR

This paper explores the use of multimodal large language models to improve global photovoltaic assessment from satellite imagery, demonstrating enhanced cross-region generalization and robustness compared to traditional computer vision methods.

Contribution

It introduces a fine-tuned multimodal LLM framework that integrates detection, localization, and quantification for PV assessment, outperforming conventional models in cross-domain scenarios.

Findings

The proposed model shows minimal performance degradation across unseen regions.

Multimodal LLMs outperform traditional CV and transformer baselines.

Results indicate high robustness and transferability for global PV mapping.

Abstract

The rapid expansion of distributed photovoltaic (PV) systems poses challenges for power grid management, as many installations remain undocumented. While satellite imagery provides global coverage, traditional computer vision (CV) models such as CNNs and U-Nets require extensive labeled data and fail to generalize across regions. This study investigates the cross-domain generalization of a multimodal large language model (LLM) for global PV assessment. By leveraging structured prompts and fine-tuning, the model integrates detection, localization, and quantification within a unified schema. Cross-regional evaluation using the $\Delta$F1 metric demonstrates that the proposed model achieves the smallest performance degradation across unseen regions, outperforming conventional CV and transformer baselines. These results highlight the robustness of multimodal LLMs under domain shift and their potential for scalable, transferable, and interpretable global PV mapping.