Transparent Machine Learning: Training and Refining an Explainable Boosting Machine to Identify Overshooting Tops in Satellite Imagery

2025-07-02

AI Summary

Automated detection of Overshooting Tops (OTs) in satellite imagery lacks interpretability, hindering trust and operational adoption in high-stakes meteorological applications. Method: This paper proposes a domain-informed, interpretable machine learning framework leveraging GOES-16 visible/infrared imagery. It extracts cloud-texture features via Gray-Level Co-occurrence Matrices (GLCMs) and trains an Explainable Boosting Machine (EBM) using Multi-Radar/Multi-Sensor (MRMS) system–derived OT labels. Crucially, it introduces a human-in-the-loop modeling paradigm: meteorological expert knowledge guides EBM feature selection and structural constraints to enforce physical plausibility and transparency. Contribution/Results: The resulting model achieves high detection performance while providing both global and local interpretability—enabling traceable, physics-aligned decision reasoning. It significantly enhances model credibility and offers a reusable methodology and practical exemplar for deploying trustworthy AI in critical weather forecasting and severe storm monitoring.

Technology Category

• Machine Learning: Transparent, Interpretable, Explainable ML
• Computer Vision: Interpretability, Explainability, and Transparency
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

An Explainable Boosting Machine (EBM) is an interpretable machine learning (ML) algorithm that has benefits in high risk applications but has not yet found much use in atmospheric science. The overall goal of this work is twofold: (1) explore the use of EBMs, in combination with feature engineering, to obtain interpretable, physics-based machine learning algorithms for meteorological applications; (2) illustrate these methods for the detection of overshooting top (OTs) in satellite imagery. Specifically, we seek to simplify the process of OT detection by first using mathematical methods to extract key features, such as cloud texture using Gray-Level Co-occurrence Matrices, followed by applying an EBM. Our EBM focuses on the classification task of predicting OT regions, utilizing Channel 2 (visible imagery) and Channel 13 (infrared imagery) of the Advanced Baseline Imager sensor of the Geostationary Operational Environmental Satellite 16. Multi-Radar/Multi-Sensor system convection flags are used as labels to train the EBM model. Note, however, that detecting convection, while related, is different from detecting OTs. Once trained, the EBM was examined and minimally altered to more closely match strategies used by domain scientists to identify OTs. The result of our efforts is a fully interpretable ML algorithm that was developed in a human-machine collaboration. While the final model does not reach the accuracy of more complex approaches, it performs well and represents a significant step toward building fully interpretable ML algorithms for this and other meteorological applications.

Problem

• Develop interpretable ML for meteorological applications using EBMs
• Simplify overshooting top detection via feature engineering and EBMs
• Enhance human-machine collaboration in weather satellite image analysis

Innovation

• Uses Explainable Boosting Machine for interpretable ML
• Combines feature engineering with physics-based algorithms
• Simplifies OT detection via human-machine collaboration