PRISM-CAFO: Prior-conditioned Remote-sensing Infrastructure Segmentation and Mapping for CAFOs

2026-01-16

AI Summary

This study addresses the urgent need for accurate and scalable remote sensing methods to identify concentrated animal feeding operations (CAFOs), which pose significant environmental and public health risks. The authors propose an infrastructure-centric, interpretable framework that first employs a domain-finetuned YOLOv8 model to detect CAFO-related structures, followed by SAM2-based mask generation and extraction of structured geometric descriptors. A lightweight spatial cross-attention mechanism is then introduced to integrate geometric priors with deep visual features for CAFO-type classification and decision attribution. By embedding domain knowledge directly into the segmentation and classification pipeline—a novel contribution in remote sensing—this approach achieves state-of-the-art performance across multiple U.S. regions, with Swin-B+PRISM-CAFO outperforming the best baseline by up to 15%. The results further demonstrate the critical role of domain priors in enhancing both model accuracy and interpretability.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Calibration & Uncertainty Quantification
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Large-scale livestock operations pose significant risks to human health and the environment, while also being vulnerable to threats such as infectious diseases and extreme weather events. As the number of such operations continues to grow, accurate and scalable mapping has become increasingly important. In this work, we present an infrastructure-first, explainable pipeline for identifying and characterizing Concentrated Animal Feeding Operations (CAFOs) from aerial and satellite imagery. Our method (i) detects candidate infrastructure (e.g., barns, feedlots, manure lagoons, silos) with a domain-tuned YOLOv8 detector, then derives SAM2 masks from these boxes and filters component-specific criteria; (ii) extracts structured descriptors (e.g., counts, areas, orientations, and spatial relations) and fuses them with deep visual features using a lightweight spatial cross-attention classifier; and (iii) outputs both CAFO type predictions and mask-level attributions that link decisions to visible infrastructure. Through comprehensive evaluation, we show that our approach achieves state-of-the-art performance, with Swin-B+PRISM-CAFO surpassing the best performing baseline by up to 15\%. Beyond strong predictive performance across diverse U.S. regions, we run systematic gradient--activation analyses that quantify the impact of domain priors and show how specific infrastructure (e.g., barns, lagoons) shapes classification decisions. We release code, infrastructure masks, and descriptors to support transparent, scalable monitoring of livestock infrastructure, enabling risk modeling, change detection, and targeted regulatory action. Github: https://github.com/Nibir088/PRISM-CAFO.

Problem

• CAFO mapping
• remote sensing
• infrastructure segmentation
• large-scale livestock operations
• environmental risk

Innovation

• PRISM-CAFO
• infrastructure-first segmentation
• domain-tuned YOLOv8
• spatial cross-attention classifier
• explainable remote sensing