S3Former: Self-supervised High-resolution Transformer for Solar PV Profiling

TL;DR

S3Former is a novel self-supervised high-resolution transformer model designed for accurate segmentation and localization of solar PV panels from aerial imagery, aiding renewable energy mapping and policy planning.

Contribution

The paper introduces S3Former, combining a Masked Attention Mask Transformer with self-supervised pretraining to improve solar panel detection accuracy in aerial images.

Findings

Outperforms state-of-the-art models on diverse datasets

Effective in challenging weather and roof conditions

Self-supervised pretraining enhances model initialization

Abstract

As the impact of climate change escalates, the global necessity to transition to sustainable energy sources becomes increasingly evident. Renewable energies have emerged as a viable solution for users, with Photovoltaic energy being a favored choice for small installations due to its reliability and efficiency. Accurate mapping of PV installations is crucial for understanding the extension of its adoption and informing energy policy. To meet this need, we introduce S3Former, designed to segment solar panels from aerial imagery and provide size and location information critical for analyzing the impact of such installations on the grid. Solar panel identification is challenging due to factors such as varying weather conditions, roof characteristics, Ground Sampling Distance variations and lack of appropriate initialization weights for optimized training. To tackle these complexities, S3Former features a Masked Attention Mask Transformer incorporating a self-supervised learning pretrained backbone. Specifically, our model leverages low-level and high-level features extracted from the backbone and incorporates an instance query mechanism incorporated on the Transformer architecture to enhance the localization of solar PV installations. We introduce a self-supervised learning phase (pretext task) to improve the initialization weights on the backbone of S3Former. We evaluated S3Former using diverse datasets, demonstrate improvement state-of-the-art models.