International Journal of Digital Earth

Over the last couple decades, the field of Artificial Intelligence (AI) has progressed rapidly and has impacted several research fields including Geographic Information Systems (GIS). The combination of AI and GIS has advanced various sectors ranging from data fusion, spatial modelling and intelligence, natural hazards, feature extraction and many more. This has led to a paradigm shift in how the intersection of these two disciplines is studied and applied to various research problems.

Significant progress has been made in the combined fields of machine/deep learning and GIS with applications ranging from image segmentation to time-series forecasting applicable in various fields like examining traffic patterns, autonomous vehicles, medical imaging and segmentations, predicting hydro climatological natural hazards, spatial clustering, crop yield and several others. New tools and algorithms such as support vector machine algorithms, prediction algorithms, deep learning structures algorithms, and graph machine learning have been developed to solve these challenges.

A collection of articles focusing on the advancement of such topics is needed given the rapid development of the field. This Article Collection is devoted to the publication of review articles and cutting-edge research papers on new data-driven methods, advanced machine/deep learning models, algorithms, and architectures of data-driven models encapsulating the key benefits of machine learning and GIS and addressing the field's major challenges. This collection will serve as a reference point for young researchers, scientists, and educators who are currently or looking to work in this dynamic field.

The topics to be covered are:

• Data-driven approaches for image analysis (e.g., object detection, image classification, semantic segmentation, medical imaging) for various remote sensing and benchmark datasets.
• Data-driven algorithms and models for application in different fields (crop monitoring, natural hazards, environmental problems, autonomous vehicles).
• Transfer learning serving specific application.
• Understanding of deep learning architectures/algorithms for remote sensing images.
• Explainable AI for classification/regression.

Instructions for AuthorsSubmit an Article