Cross-Domain Generalization of Multimodal LLMs for Global Photovoltaic Assessment
This work addresses the challenge of scalable global PV mapping for power grid management, representing an incremental improvement with a novel method for a known bottleneck in domain generalization.
This study tackled the problem of detecting undocumented photovoltaic (PV) systems from satellite imagery by investigating cross-domain generalization of a multimodal large language model (LLM), achieving the smallest performance degradation across unseen regions compared to conventional computer vision and transformer baselines using the ΔF1 metric.
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 $Δ$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.