Modelling the domestic poultry population in the United States: A novel approach leveraging remote sensing and synthetic data methods

Abstract

Comprehensive and spatially accurate poultry population demographic data do not currently exist in the United States; however, these data are critically needed to adequately prepare for, and efficiently respond to and manage disease outbreaks. In response to absence of these data, this study developed a national-level poultry population dataset by using a novel combination of remote sensing and probabilistic modelling methodologies. The Farm Location and Agricultural Production Simulator (FLAPS) (Burdett et al., 2015) was used to provide baseline national-scale data depicting the simulated locations and populations of individual poultry operations. Remote sensing methods (identification using aerial imagery) were used to identify actual locations of buildings having the characteristic size and shape of commercial poultry barns. This approach was applied to 594 U.S. counties with > 100,000 birds in 34 states based on the 2012 U.S. Department of Agriculture (USDA), National Agricultural Statistics Service (NASS), Census of Agriculture (CoA). The two methods were integrated in a hybrid approach to develop an automated machine learning process to locate commercial poultry operations and predict the number and type of poultry for each operation across the coterminous United States. Validation illustrated that the hybrid model had higher locational accuracy and more realistic distribution and density patterns when compared to purely simulated data. The resulting national poultry population dataset has significant potential for application in animal disease spread modelling, surveillance, emergency planning and response, economics, and other fields, providing a versatile asset for further agricultural research.

Using an adaptive modeling framework to identify avian influenza spillover risk at the wild-domestic interface

“…An important limitation of the high spatial resolution model sets (3 km 2 ) comes from the application of the hybrid poultry model inputs 37 which are the most recent spatially explicit, high-resolution predictions of poultry operation locations available for the United States. This model provides likely coordinates of poultry farm locations by farm type (broiler, layer, pullet, or turkey; commercial or backyard; and breeding or production) based on environmental covariates, artificial intelligence to identify commercial facilities, and constraints by the number and size of operations reported in the USDA-NASS CoA.…”

“…On the poultry side of the equation, although some actual poultry population data exist for specific geographic areas or poultry sectors, a national, comprehensive database of U.S. poultry operations is lacking. The hybrid model used here 37 , and FLAPS 46 provide population datasets of farm location and type suitable for modeling in the absence of true farm location data. Any updates to those datasets (e.g.…”

“…The number and type of poultry operations ( Pn t ) comes from the “hybrid poultry model” developed by the U.S. Department of Agriculture (USDA) 37 . This model uses a baseline population from the Farm Location and Agricultural Production Simulator (FLAPS) that combines a poultry farm suitability surface with poultry farm numbers and types from the USDA, National Agricultural Statistics Service (NASS), Census of Agriculture (CoA), to stochastically place likely farm locations and assign them an operation type 46 .…”

The spatial–temporal relationship of blue‐winged teal to domestic poultry: Movement state modelling of a highly mobile avian influenza host

“…The Hybrid Poultry Model available from the US Department of Agriculture Animal and Plant Health Inspection Service (Patyk et al., 2020) was used to establish the geographic locations of commercial poultry facilities (chicken and turkey) as well as backyard chicken and turkey producers that manage lesser quantities of poultry for meat, egg production or exhibition. Poultry classes falling under the chicken category included broilers, layers and pullets.…”

Roof3d: A Real and Synthetic Data Collection for Individual Building Roof Plane and Building Sections Detection

“…The pseudo-real images are then used for training a neural network on aircraft detection. In (Patyk et al, 2020), simulated and real data are leveraged together as well. In their work, the authors use synthetic poultry distributions and aerial imagery jointly to model poultry populations.…”