Fine-Scale Soil Mapping in Alaska with Multimodal Machine Learning

TL;DR

This paper introduces MISO, a multimodal machine learning model that significantly improves fine-scale soil mapping in Alaska, especially for permafrost regions, by integrating visual features, neural representations, and contrastive learning.

Contribution

The novel MISO model combines geospatial visual features, neural representations, and multimodal contrastive learning to enhance soil and permafrost mapping accuracy over traditional methods.

Findings

MISO outperforms Random Forest in generalization to unseen locations.

MISO achieves higher recall in permafrost detection.

The approach improves monitoring of permafrost thaw and environmental changes.

Abstract

Fine-scale soil mapping in Alaska, traditionally relying on fieldwork and localized simulations, remains a critical yet underdeveloped task, despite the region's ecological importance and extensive permafrost coverage. As permafrost thaw accelerates due to climate change, it threatens infrastructure stability and key ecosystem services, such as soil carbon storage. High-resolution soil maps are essential for characterizing permafrost distribution, identifying vulnerable areas, and informing adaptation strategies. We present MISO, a vision-based machine learning (ML) model to produce statewide fine-scale soil maps for near-surface permafrost and soil taxonomy. The model integrates a geospatial foundation model for visual feature extraction, implicit neural representations for continuous spatial prediction, and contrastive learning for multimodal alignment and geo-location awareness. We compare MISO with Random Forest (RF), a traditional ML model that has been widely used in soil mapping applications. Spatial cross-validation and regional analysis across Permafrost Zones and Major Land Resource Areas (MLRAs) show that MISO generalizes better to remote, unseen locations and achieves higher recall than RF, which is critical for monitoring permafrost thaw and related environmental processes. These findings demonstrate the potential of advanced ML approaches for fine-scale soil mapping and provide practical guidance for future soil sampling and infrastructure planning in permafrost-affected landscapes. The project will be released at https://github.com/knowledge-computing/Peatland-permafrost.