FOCUS on Contamination: A Geospatial Deep Learning Framework with a Noise-Aware Loss for Surface Water PFAS Prediction

2025-02-17

AI Summary

To address the high cost and extensive coverage gaps in large-scale surface water PFAS pollution monitoring, this paper proposes the first geospatial deep learning framework tailored for PFAS spatial prediction. Methodologically, it integrates heterogeneous geographic features—including hydrological flow direction, land cover, and proximity to pollution sources—and introduces a novel hydrologically constrained feature encoding module that explicitly embeds hydrological priors into an end-to-end model for the first time. Additionally, we propose a label-noise-aware loss function (NRLoss) that explicitly models uncertainty in measured concentration labels. Experiments on real-world watershed data demonstrate a 37% reduction in MAE compared to both ordinary kriging and transfer-based simulation, significantly outperforming sparse segmentation baselines. The framework supports generation of high-resolution (30 m) PFAS contamination heatmaps over areas up to 100 km², enabling near-real-time monitoring capabilities.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Deep Generative Models & Autoencoders
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Per and polyfluoroalkyl substances (PFAS), chemicals found in products like non-stick cookware, are unfortunately persistent environmental pollutants with severe health risks. Accurately mapping PFAS contamination is crucial for guiding targeted remediation efforts and protecting public and environmental health, yet detection across large regions remains challenging due to the cost of testing and the difficulty of simulating their spread. In this work, we introduce FOCUS, a geospatial deep learning framework with a label noise-aware loss function, to predict PFAS contamination in surface water over large regions. By integrating hydrological flow data, land cover information, and proximity to known PFAS sources, our approach leverages both spatial and environmental context to improve prediction accuracy. We evaluate the performance of our approach through extensive ablation studies and comparative analyses against baselines like sparse segmentation, as well as existing scientific methods, including Kriging and pollutant transport simulations. Results highlight our framework's potential for scalable PFAS monitoring.

Problem

• Predict PFAS contamination in surface water
• Integrate geospatial and environmental data
• Improve accuracy with noise-aware loss function

Innovation

• Geospatial deep learning framework
• Noise-aware loss function
• Integration of hydrological data