Deployment of a LoRa-WAN near real-time precision ranching system on extensive desert rangelands: What we have learned

Authors: MCINTOSH, MATT - New Mexico State University; UTSUMI, S - New Mexico State University; Cibils, Andres; NYAMURYEKUNG'E, SHELEMIA - New Mexico State University; Estell, Richard - Rick; COX, ANDREW - New Mexico State University; DUNI, D - New Mexico State University; DONG, Q - New Mexico State University; WATERHOUSE, T - Sruc-Scotland'S Rural College; HOLLAND, J - Sruc-Scotland'S Rural College; CAO, H - New Mexico State University; BOUCHERON, L - New Mexico State University; CHEN, H - New Mexico State University; Spiegal, Sheri

Submitted to: Applied Animal Science
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 6/5/2023
Publication Date: 8/16/2023
Citation: McIntosh, M.M., Utsumi, S.A., Cibils, A.F., Nyamuryekung'E, S., Estell, R.E., Cox, A., Duni, D., Dong, Q., Waterhouse, T., Holland, J., Cao, H., Boucheron, L., Chen, H., Spiegal, S.A. 2023. Deployment of a LoRa-WAN near real-time precision ranching system on extensive desert rangelands: What we have learned. Applied Animal Science. 13. Article e2641. https://doi.org/10.3390/ani13162641 .
DOI: https://doi.org/10.3390/ani13162641

Interpretive Summary: This study describes the deployment of a near real-time precision livestock system in New Mexico tested for three months from March to June 2020. This system included a remote solar-power base station and proprietary components, including the gateway, antenna, backhaul bridge, and a network of sensors (GPS cattle trackers and sensors to monitor precipitation and water trough levels). Consistent data collection was detected for both the water trough level and precipitation sensors deployed at stationary locations. GPS trackers mounted on cows resulted in 46 ± 4% of total data packets successfully logged and transmitted through the network system, but exceeded 80% in several cases. This report details infrastructure development, performance, and maintenance of system components as well as ‘how to’ tips that were not readily available at the onset of this study. This information could simplify the process for ranchers and researchers interested in deploying a similar system. This system was successful in yielding near-real time data that allowed the ranch manager to manage inventories and quickly identify and address animal welfare issues.

Technical Abstract: Animal welfare monitoring relies on sensor accuracy for detecting changes in animal well-being. We compared the distance calculations based on global positioning system (GPS) data alone or combined with motion data from triaxial accelerometers. The assessment involved static trackers placed outdoors or indoors vs. trackers mounted on cows grazing on pasture. Trackers communicated motion data at 1 min intervals and GPS positions at 15 min intervals for seven days. Daily distance walked was determined using the following: (1) raw GPS data (RawDist), (2) data with erroneous GPS locations removed (CorrectedDist), or (3) data with erroneous GPS locations removed, combined with the exclusion of GPS data associated with no motion reading (CorrectedDist_Act). Distances were analyzed via one-way ANOVA to compare the effects of tracker placement (Indoor, Outdoor, or Animal). No difference was detected between the tracker placement for RawDist. The computation of CorrectedDist differed between the tracker placements. However, due to the random error of GPS measurements, CorrectedDist for Indoor static trackers differed from zero. The walking distance calculated by CorrectedDist_Act differed between the tracker placements, with distances for static trackers not differing from zero. The fusion of GPS and accelerometer data better detected animal welfare implications related to immobility in grazing cattle.