Skip to main content
ARS Home » Plains Area » Las Cruces, New Mexico » Range Management Research » Research » Publications at this Location » Publication #392972

Research Project: Science and Technologies for the Sustainable Management of Western Rangeland Systems

Location: Range Management Research

Title: Digital ranching as aspirational system for resilient ranching on Southwestern US rangelands

Author
item UTSUMI, SANTIAGO - NEW MEXICO STATE UNIVERSITY
item NYAMURYEKUNG'E, SHALEMIA - NEW MEXICO STATE UNIVERSITY
item MCINTOSH, MATT - NEW MEXICO STATE UNIVERSITY
item CIBILS, ANDRES - NEW MEXICO STATE UNIVERSITY
item Estell, Richard - Rick
item Spiegal, Sheri
item DUFF, GLENN - NEW MEXICO STATE UNIVERSITY
item CAO, H - NEW MEXICO STATE UNIVERSITY
item BOUCHERON, L - NEW MEXICO STATE UNIVERSITY
item CHEN, H - NEW MEXICO STATE UNIVERSITY
item LE, T - NEW MEXICO STATE UNIVERSITY
item WINKLER, Z - NEW MEXICO STATE UNIVERSITY
item RAHMAN, S - NEW MEXICO STATE UNIVERSITY
item GONG, Q - NEW MEXICO STATE UNIVERSITY
item COX, ANDREW - NEW MEXICO STATE UNIVERSITY
item GIFFORD, C - NEW MEXICO STATE UNIVERSITY
item KROHN, M - NEW MEXICO STATE UNIVERSITY
item RAGOSTA, J - NEW MEXICO STATE UNIVERSITY
item GOUVEA, V - NEW MEXICO STATE UNIVERSITY
item BRANDANI, C - NEW MEXICO STATE UNIVERSITY
item WATERHOUSE, TONY - SRUC-SCOTLAND'S RURAL COLLEGE
item HOLLAND, J - SRUC-SCOTLAND'S RURAL COLLEGE
item Elias, Emile
item ANEY, SKYE - NEW MEXICO STATE UNIVERSITY
item Bestelmeyer, Brandon
item STEINER, J - NEW MEXICO STATE UNIVERSITY

Submitted to: Society for Range Management Meeting Abstracts
Publication Type: Abstract Only
Publication Acceptance Date: 2/4/2022
Publication Date: 2/8/2022
Citation: Utsumi, S., Nyamuryekung'E, S., McIntosh, M.M., Cibils, A.F., Estell, R.E., Spiegal, S.A., Duff, G., Cao, H., Boucheron, L., Chen, H., Le, T., Winkler, Z., Rahman, S., Gong, Q., Cox, A., Gifford, C., Krohn, M., Ragosta, J., Gouvea, V., Brandani, C., Waterhouse, T., Holland, J., Elias, E.H., Aney, S., Bestelmeyer, B.T., Steiner, J. 2022. Digital ranching as aspirational system for resilient ranching on Southwestern US rangelands. Society for Range Management Meeting Abstracts. Abstract.

Interpretive Summary:

Technical Abstract: The Sustainable Southwest Beef Project led by New Mexico State University is strategically partnering with ranchers, researchers, extension specialist, educators and industry stakeholders to pioneer a Digital Ranching Platform for improving sustainability outcomes on ranches of the Southwestern US. The goals of the platform are to improve the operational efficiency of managing beef production systems for profitability, climate-resilience, and adaptive capacity. Ultimately, end-users will implement near realtime tracking and scouting of livestock across large pastures, rapid assessments of animal welfare, remote monitoring of rain gauge tipping buckets and tracking of water levels in cattle drinking troughs dispersed across the ranch. Another module is providing unobtrusive scoring of cattle body condition using support vector machine classifiers feeding on video imagery collected by automated infrared depth cameras. Methodologically, our approach fuses traditional statistics and smart analytics with novel dashboard tools to rapidly provide management indicators computed from streams of real-time data which are concurrently collected, logged and transmitted through a network of high throughput sensors, gateways routers and cloud computing services. The IoT infrastructure includes field sensors and accelerometer and GPS sensors on animals, and operates on a Long Range Wide Area Network (LoRa WAN) using solar or grid power and Ethernet, WiFi backhaul, or GSM communication. Our software engineering and IT team is developing a unified web-based server and dashboard application that facilitates the aggregation, visualization and retrieval of computed data, and configurations of sensors. Current analytics seek to enhance the harmonization (i.e. common feature representation) and curation of data using preprocessing, cleansing and normalization steps prior to implementing machine learning variants for classification and predictions objectives. Pilot case studies suggest several advantages of the system along with areas for potential improvement of existing sensors, network infrastructure and engineering, which may enhance future applications of the system on cooperating commercial ranches.