Stony Brook University Develops Machine Learning Models that Predict PV System Underperformance on Heterogeneous Portfolios

US researchers use machine learning to detect hidden solar array defects

US researchers say a self-supervised machine-learning tool can identify long-term physical defects in solar assets weeks or years before conventional inspections, potentially reducing operations and maintenance costs.From pv magazine USA Researchers from Stony Brook University, in collaboration with Ecosuite and Ecogy Energy, have developed a self-supervised machine-learning algorithm designed to identify physical anomalies in solar energy syste…

Machine Learning Models Identify Hidden Physical defects in solar arrays

The software tool developed by Stony Brook University uses self-supervised learning to detect long-term solar equipment damage weeks or years before manual inspections find it.Researchers from Stony Brook University, in collaboration with Ecosuite and Ecogy Energy, have developed a self-supervised machine learning algorithm designed to identify physical anomalies in solar energy systems. The project aims to reduce operations and maintenance (O&M…

Stony Brook University Develops Machine Learning Models that Predict PV System Underperformance on Heterogeneous Portfolios

STONY BROOK, N.Y., Dec. 18, 2025 /PRNewswire/ -- Researchers Yue Zhao and Kang Pu from Stony Brook University—in collaboration with Ecosuite's John Gorman and Philip Court, and leveraging historical datasets provided by Ecogy Energy—have devised a data-driven algorithm to detect…