EarthScape: A Multimodal Dataset for Surficial Geologic Mapping and Earth Surface Analysis

Matthew A. Massey, Nusrat Munia, Abdullah-Al-Zubaer Imran

Keywords: Datasets and Benchmarks, Multimodal Learning, Multimodal Fusion, Remote Sensing, Geospatial Analysis, Earth Science, Surficial Geology

Abstract: Surficial geologic (SG) maps are critical for understanding Earth surface processes, supporting infrastructure planning, and addressing challenges related to climate change and natural hazards. Advancements in artificial intelligence (AI) and the proliferation of remote sensing imagery present an opportunity to transform SG mapping and overcome many of the limitations (e.g., labor-intensive, not scalable, etc.) of current workflows. We introduce EarthScape, a new AI-ready multimodal dataset designed to advance SG mapping. EarthScape integrates digital elevation models, aerial imagery, multi-scale terrain derivatives, and vector data for hydrologic and infrastructure features. We present a complete data processing pipeline to support reproducibility and benchmarking and report baseline results across single-modality, multi-scale, and multimodal configurations. Our experiments highlight the predictive value of terrain-derived features and the challenge of generalizing across geologically diverse regions.

Dataset URL: https://uknowledge.uky.edu/kgs_data/16/

Code URL: https://github.com/masseygeo/earthscape

Primary Area: Datasets & Benchmarks for applications in computer vision

Submission Number: 471