Predicting the spatial distribution and demographics of commercial swine farms in the United States

TL;DR

This study developed a machine learning pipeline combining semantic segmentation and Random Forest classifiers to accurately identify and classify commercial swine farms in the U.S., providing valuable spatial and demographic data for disease monitoring.

Contribution

The paper introduces a novel approach integrating semantic segmentation and classification models to map and characterize swine farms at a national scale.

Findings

Achieved 92% F2 score in farm location detection

Reduced false positives by over 80% with Random Forest classifier

Predicted farm population sizes with up to 87% accuracy within 500 pigs

Abstract

Data on livestock farm locations and demographics are essential for disease monitoring, risk assessment, and developing spatially explicit epidemiological models. Our semantic segmentation model achieved an F2 score of 92 % and a mean Intersection over Union of 76 %. An initial total of 194,474 swine barn candidates were identified in the Southeast (North Carolina = 111,135, South Carolina = 37,264 Virginia = 46,075) and 524,962 in the Midwest (Iowa = 168,866 Minnesota = 165,714 Ohio = 190,382). The post processing Random Forest classifier reduced false positives by 82 % in the Southeast and 88 % in the Midwest, resulting in 45,580 confirmed barn polygons. These were grouped into 16,976 predicted farms and classified into one of the four production types. Population sizes were then estimated using the Random Forest regression model, with prediction accuracy varying by production type. Across all farms, 87 % of predictions for operations with 1,000 2,000 pigs were within 500 pigs of the reference value, with nursery farms showing the highest agreement (R2= 0.82), followed by finisher farms (R2 = 0.77) and sow farms (R2 = 0.56). Our results revealed substantial gaps in the existing spatial and demographic data on U.S. swine production.