Interpretable Machine Learning in Remote Sensing: Image Analysis and Classification

The application of artificial intelligence (AI) to a variety of remote sensing problems has seen rapid growth in recent years, with advances in its use across the scientific process from modeling to data analysis. Although these techniques have provided excellent results in applications ranging from parameter estimation to image classification and anomaly detection, the interpretability of these methods is required to better understand the model outcomes, i.e., how and why the models are coming to their decisions. This collection aims to collect the recent developments in interpretable machine learning in the remote sensing field focusing on image analysis and classification research. Review articles on methodologies or applications including the advantages and limitations of each are welcome.

The contributions to this collection will undergo peer review. Novelty may vary, but the utility in facilitating research and development of the proposed AI/machine learning algorithms must be evident. We welcome contributions covering all aspects of Image Analysis and Classification. Some topics of particular interest may include (but are not limited to):

• Object-based image segmentation using machine learning;
• Target detection using machine learning;
• Semantic image segmentation using machine learning;
• Remote sensing image super-resolution.