XGeoS-AI: an interpretable learning framework for deciphering geoscience image segmentation

Abstract

As Earth science transitions into the era of big data, artificial intelligence (AI) not only holds significant potential for addressing geoscience challenges, but also plays a pivotal role in accelerating our comprehension of the complex, interactive, and multi-scale processes of Earth's behaviors. As geoscience AI models are progressively utilized for significant predictions in crucial situations, geoscience researchers are increasingly demanding their interpretability and versatility. This study proposes an interpretable geoscience artificial intelligence (XGeoS-AI) framework to unravel the mystery of image recognition in the Earth sciences, and its effectiveness and versatility are exemplified through the application to computed tomography (CT) image analysis. To enhance interpretability, the XGeoS-AI framework incorporates a local region threshold generation method (LRT) inspired by human visual mechanisms. Different kinds of artificial intelligence (AI) engines, including support vector regression (SVR), multilayer perceptron (MLP), convolutional neural network (CNN), are integrated within the XGeoS-AI framework to efficiently address geoscience image recognition challenges. Experimental findings affirm the effectiveness, versatility, and heuristics of the XGeoS-AI framework, underscoring its potential to revolutionize geoscience image recognition. Interpretable AI should receive more and more attention in the field of the Earth sciences, which is the key to promoting more rational and wider applications of AI in the field of Earth sciences.