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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Massey, Matthew, Munia, Nusrat, Imran, Abdullah-Al-Zubaer
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912945956454400
author Massey, Matthew
Munia, Nusrat
Imran, Abdullah-Al-Zubaer
author_facet Massey, Matthew
Munia, Nusrat
Imran, Abdullah-Al-Zubaer
contents Surficial geologic (SG) maps are essential for understanding surface processes and supporting infrastructure planning, but current workflows are labor-intensive and difficult to scale. We introduce EarthScape, an AI-ready multimodal dataset for SG mapping that integrates digital elevation models, aerial imagery, multi-scale terrain features, and hydrologic and infrastructure vector data within a unified, reproducible pipeline. We report baseline benchmarks across single-modality, multi-scale, and multimodal configurations. Our experiments show that terrain features provide the most reliable predictive signal, while raw spectral and elevation inputs degrade substantially under cross-region evaluation. EarthScape offers a geographically compact, but modality-rich benchmark for multimodal fusion, domain adaptation, and surface modeling. EarthScape is available for direct download at https://uknowledge.uky.edu/kgs_data/16/, and code is available at https://github.com/masseygeo/earthscape.
format Preprint
id arxiv_https___arxiv_org_abs_2503_15625
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EarthScape: A Multimodal Dataset for Surficial Geologic Mapping and Earth Surface Analysis
Massey, Matthew
Munia, Nusrat
Imran, Abdullah-Al-Zubaer
Computer Vision and Pattern Recognition
Surficial geologic (SG) maps are essential for understanding surface processes and supporting infrastructure planning, but current workflows are labor-intensive and difficult to scale. We introduce EarthScape, an AI-ready multimodal dataset for SG mapping that integrates digital elevation models, aerial imagery, multi-scale terrain features, and hydrologic and infrastructure vector data within a unified, reproducible pipeline. We report baseline benchmarks across single-modality, multi-scale, and multimodal configurations. Our experiments show that terrain features provide the most reliable predictive signal, while raw spectral and elevation inputs degrade substantially under cross-region evaluation. EarthScape offers a geographically compact, but modality-rich benchmark for multimodal fusion, domain adaptation, and surface modeling. EarthScape is available for direct download at https://uknowledge.uky.edu/kgs_data/16/, and code is available at https://github.com/masseygeo/earthscape.
title EarthScape: A Multimodal Dataset for Surficial Geologic Mapping and Earth Surface Analysis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.15625