# Benchmarking Vision Transformers and CNNs for Thermal Photovoltaic Fault Detection with Explainable AI Validation

arXiv: https://arxiv.org/abs/2509.07039 · HTML: https://mlsanity.com/paper/2509.07039/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 20 references that are in the map.
- First posted on arXiv 8 Sep 2025.

## Builds on (most cited first, 6 of 6)

- [Trustworthy AI: From Principles to Practices](https://mlsanity.com/paper/2110.01167/) (2021)
- [A Survey on Trustworthy Edge Intelligence: From Security and Reliability To Transparency and Sustainability](https://mlsanity.com/paper/2310.17944/) (2023)
- [False Sense of Security in Explainable Artificial Intelligence (XAI)](https://mlsanity.com/paper/2405.03820/) (2024)
- [Anomaly Detection in IR Images of PV Modules using Supervised Contrastive Learning](https://mlsanity.com/paper/2112.02922/) (2021)
- [Trustworthy artificial intelligence in the energy sector: Landscape analysis and evaluation framework](https://mlsanity.com/paper/2412.07782/) (2024)
- [HOTSPOT-YOLO: A Lightweight Deep Learning Attention-Driven Model for Detecting Thermal Anomalies in Drone-Based Solar Photovoltaic Inspections](https://mlsanity.com/paper/2508.18912/) (2025)

## Built on by (most cited first, 1 of 1)

- [Joint-Embedding Predictive Architecture for Solar PV Panel Fault Classification](https://mlsanity.com/paper/2607.09205/) (2026)

## Abstract (arXiv)

Artificial intelligence deployment for automated photovoltaic (PV) monitoring faces interpretability barriers that limit adoption in energy infrastructure applications. While deep learning achieves high accuracy in thermal fault detection, validation that model decisions align with thermal physics principles remains lacking, creating deployment hesitancy where understanding model reasoning is critical. This study provides a systematic comparison of convolutional neural networks (ResNet-18, EfficientNet-B0) and vision transformers (ViT-Tiny, Swin-Tiny) for thermal PV fault detection, using XRAI saliency analysis to assess alignment with thermal physics principles. This represents the first systematic comparison of CNNs and vision transformers for thermal PV fault detection with physics-validated interpretability. Evaluation on 20,000 infrared images spanning normal operation and 11 fault categories shows that Swin Transformer achieves the highest performance (94% binary accuracy; 73% multiclass accuracy) compared to CNN approaches. XRAI analysis reveals that models learn physically meaningful features, such as localized hotspots for cell defects, linear thermal paths for diode failures, and thermal boundaries for vegetation shading, consistent with expected thermal signatures. However, performance varies significantly across fault types: electrical faults achieve strong detection (F1-scores >0.90) while environmental factors like soiling remain challenging (F1-scores 0.20-0.33), indicating limitations imposed by thermal imaging resolution. The thermal physics-guided interpretability approach provides methodology for validating AI decision-making in energy monitoring applications, addressing deployment barriers in renewable energy infrastructure.