P.PSH.1315 - Producer led deployment of Smart GPS ear tags for livestock

Summary

Producers need reliable, near real time livestock traceability and management across vast, remote properties where connectivity is limited and large scale GPS ear tag deployments haven’t been proven. MLA funded a producer-led demonstration that deployed Smart Paddock GPS ear tags across multiple commercial sites, installed LoRaWAN gateways, integrated with farm software (e.g., Cibolabs), and captured technical performance, retention and producer feedback. The project demonstrated scalable station wide tracking (individual sites ~100k–300k ha; >1M ha total), ~90% 12 month tag retention and live platform integration, while identifying potential productivity and cost benefits such as faster mustering and alerts for strays/illness/theft.

Objectives

Demonstrate a commercially practical procedure for deploying GPS smart ear tags at scale, targeting application times comparable to standard NLIS tagging. Establish and operate trials across at least three commercial sites with 2,000–5,000 head to capture real‑time location and activity data. Integrate live data with participating farm management platforms to test interoperability. Prove reliable livestock tracking over 100,000–250,000 ha in remote, low‑connectivity environments. Achieve and measure tag retention ≥85% over the evaluation period, including the ability to locate and retrieve a portion of lost tags. Quantify benefits versus costs.

Key findings

The project demonstrated station‑scale traceability, deploying >3,900 GPS ear tags across multiple commercial sites and tracking animals over >1.0–1.2 million ha, including single‑property deployments of ~300,000 ha using as few as three gateways. It achieved an average 12‑month retention of ~90% (property rates 91–100%, state‑level 85–100%), exceeding the 85% target for the measured period, supported by a dropped‑tag detection algorithm to monitor losses and trigger replacements.

 Interoperability was demonstrated via live integration with Cibolabs and new standard APIs, while web/mobile apps (incl. offline mode) delivered real‑time locations, alerts (e.g. dropped‑tag versus downed‑animal) and coverage diagnostics to inform on‑farm decisions. Indicative economic/productivity benefits included modelled ROI showing full cost recovery by preventing loss of 1–2 animals in 100‑head herds over 12–18 months, with producers reporting easier mustering and better boundary/stray management and animal oversight.

Benefits to industry

This project has proven the feasibility of station‑scale, near‑real‑time traceability in remote environments, tracking herds across 100k–300k ha with ~90% 12‑month retention and live integration demonstrating the technology works at commercial scale. By delivering practical integration pathways (e.g. with Cibolabs), it has lowered adoption barriers and highlighted opportunities to improve mustering efficiency, boundary/stray management and animal oversight. Project outcomes are also guiding MLA’s future investments (e.g. longer‑run retention cohorts, validated alerting, satellite connectivity), accelerating digital capability across the red meat sector.

MLA action

The demonstrated outcomes – station‑scale coverage, ~90% 12‑month retention, and live integration feasibility – are informing future investment priorities (e.g. longer‑run retention cohorts, validated health/'downed animal' analytics, satellite connectivity, and interoperability with industry platforms/ISC). 

MLA is also using these findings to create new partnership opportunities (e.g. platform integrations proven with Cibolabs) and to scope a larger, multi‑site ROI study that links on‑farm data to processing outcomes to accelerate industry adoption.

Future research

Finalise lighter, more robust tag hardware and evaluate direct‑to‑satellite connectivity as alternative to LoRaWAN towers. Re‑establish sheep trials when technology platforms permit. Ground‑truth downed/illness/calving detection with controlled trials and report diagnostic accuracy; quantify mustering/time/labour savings via before/after studies. Operationalise integrations with farm platforms and test virtual fencing interoperability. Scale adoption & ROI evidence. Run a larger, multi‑site whole‑of‑supply‑chain ROI study linking on‑farm data to processing and product outcomes. In parallel, a staged, realistic data integration and AI program should be embedded within commercial scale deployments, evolving from foundational data plumbing to advanced decision support only as data depth, quality, and coverage improve.