Risk-Based Thresholding for Reliable Anomaly Detection in Concentrated Solar Power Plants
Estievenart, Yorick Patra, Sukanya Ben Taieb, Souhaib
Estievenart, Yorick
Patra, Sukanya
Ben Taieb, Souhaib
Supervisor
Department
Statistics and Data Science
Embargo End Date
Type
Conference proceeding
Date
2026
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Efficient and reliable operation of Concentrated Solar Power (CSP) plants is essential for meeting the growing demand for sustainable energy. However, high-temperature solar receivers face severe operational risks, such as freezing, deformation, and corrosion, resulting in costly downtime and maintenance. To monitor CSP plants, cameras mounted on solar receivers record infrared images at irregular intervals ranging from one to five minutes throughout the day. Anomalous images can be detected by thresholding an anomaly score, where the threshold is chosen to optimize metrics such as the F1-score on a validation set. This work proposes a framework, using risk control, for generating more reliable decision thresholds with finite-sample coverage guarantees on any chosen risk function. Our framework also incorporates an abstention mechanism, allowing high-risk predictions to be deferred to domain experts. Second, we propose a density forecasting method to estimate the likelihood of an observed image given a sequence of previously observed images, using this likelihood as its anomaly score. Third, we analyze the deployment results of our framework across multiple training scenarios over several months for two CSP plants. This analysis provides valuable insights to our industry partner for optimizing maintenance operations. Finally, given the confidential nature of our dataset, we provide an extended simulated dataset (https://tinyurl.com/macmnjyt), leveraging recent advancements in generative modeling to create diverse thermal images that simulate multiple CSP plants. Our code is publicly available (https://github.com/yoest/reliable-ad-csp).
Citation
Y. Estievenart, S. Patra, and S. Ben Taieb, “Risk-Based Thresholding for Reliable Anomaly Detection in Concentrated Solar Power Plants,” pp. 111–128, 2026, doi: 10.1007/978-3-032-06129-4_7
Source
Lecture Notes in Computer Science
Conference
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2025
Keywords
Concentrated Solar Power Plants, Deep Image Anomaly Detection, Density Estimation, Irregular Time-series, Non-stationarity, Reliable Decision Thresholds, Risk Control
Subjects
Source
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2025
Publisher
Springer Nature