DIGMAPPER: A Modular System for Automated Geologic Map Digitization

2025-06-19

AI Summary

Historical geological maps contain critical spatial information—including lithology, faults, and folds—essential for strategic mineral resource assessment; however, their digitization has long relied on labor-intensive manual interpretation, severely limiting scalability. To address this, we propose the first integrated paradigm synergizing large language model–enabled in-context learning, controllable synthetic data generation, and Transformer-based architectures to overcome the multi-element joint parsing bottleneck under few-shot conditions. Our modular system integrates deep learning–based layout analysis, semantic feature extraction, and geographic registration models, supporting end-to-end containerized deployment. Evaluated on over 100 expertly annotated maps from the DARPA–USGS benchmark, it achieves high-accuracy multi-element recognition and robust georegistration. The system has been deployed operationally within the USGS production environment, substantially accelerating national-scale strategic mineral assessment data generation.

Technology Category

• Natural Language Processing: Language Grounding & Multi-modal NLP
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Intelligent Robots: Localization, Mapping, and Navigation

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Historical geologic maps contain rich geospatial information, such as rock units, faults, folds, and bedding planes, that is critical for assessing mineral resources essential to renewable energy, electric vehicles, and national security. However, digitizing maps remains a labor-intensive and time-consuming task. We present DIGMAPPER, a modular, scalable system developed in collaboration with the United States Geological Survey (USGS) to automate the digitization of geologic maps. DIGMAPPER features a fully dockerized, workflow-orchestrated architecture that integrates state-of-the-art deep learning models for map layout analysis, feature extraction, and georeferencing. To overcome challenges such as limited training data and complex visual content, our system employs innovative techniques, including in-context learning with large language models, synthetic data generation, and transformer-based models. Evaluations on over 100 annotated maps from the DARPA-USGS dataset demonstrate high accuracy across polygon, line, and point feature extraction, and reliable georeferencing performance. Deployed at USGS, DIGMAPPER significantly accelerates the creation of analysis-ready geospatial datasets, supporting national-scale critical mineral assessments and broader geoscientific applications.

Problem

• Automates labor-intensive geologic map digitization
• Overcomes limited training data with innovative techniques
• Accelerates creation of geospatial datasets for mineral assessments

Innovation

• Modular dockerized workflow-orchestrated architecture
• Deep learning for layout and feature extraction
• In-context learning and synthetic data generation