Farm of the Future

IoT data infrastructure for CAST, Cornell CALS' data-driven agriculture testbed.

CAST - the Cornell Agricultural Systems Testbed and Demonstration Site - is a Cornell CALS initiative to accelerate a smart agricultural transformation through data-driven technologies and management practices, using field crops and dairy production as models for the broader U.S. agricultural economy. It runs across three Cornell-operated farms in New York: the Cornell University Ruminant Center (integrated field crops and dairy) in Harford, the Cornell Teaching Dairy Barn in Ithaca, and Musgrave Research Farm (field crops) in Aurora.

CAST-NET, its extension and teaching network, brings in farmers, equipment manufacturers, consultants, and academic experts who take part at every stage - problem identification, planning, implementation, evaluation - so what gets tested at CAST is built toward actually being adopted, not just published.

cals.cornell.edu/cast-farm-future

Diagram of CAST's three farms - Cornell University Ruminant Center, Cornell Teaching Dairy Barn, and Musgrave Research Farm - and its stakeholder network — CAST's three farms and stakeholder network, from the CAST team's own materials.

The data integration problem

Every barn and field at CAST already produces data - just not in one place or one shape. Collar sensors like SmaxTec and SilentHerdsman report activity and rumination continuously; parlor systems like AfiFarm log milk yield, fat, and protein per milking; herd-management software like DairyComp 305 holds lactation history and health events. Each source has its own units, its own collection frequency - continuous, per-session, per-lactation - and its own server, cloud or local. None of it arrives pre-joined.

The field side adds another layer: soil maps sampled once a season, yield maps from the combine, and satellite imagery (Landsat, Sentinel-2, Planet) at resolutions from 30 meters down to 3, refreshed anywhere from daily to every couple of weeks. Reconciling a per-second cow sensor reading with a once-a-season soil sample is a genuinely different problem than reconciling two dairy vendors' APIs with each other.

What I built

I worked on the data infrastructure that turns those streams into something usable: piping live IoT sensor readings into Postgres, building a React dashboard that surfaces gaps and spikes as they happen instead of after a report runs, and training simple models to flag flaky sensors before a bad reading gets treated as real data - feeding decision-support tools like MyCow$ (real-time cash flow per cow) and predictive models like RuFaS.

Research at CAST

That infrastructure supports two research thrusts: precision management on the crop side - input rates, cover cropping, soil amendments like biochar for carbon sequestration - and precision animal management on the dairy side - feeding, health, and reproductive monitoring. Both are aimed at testing technology under real commercial-farm conditions instead of a controlled lab, then extending what works through CAST-NET.

Mohammad Labadi with the CAST research group — With the CAST research group.

Dairy cows at CAST's freestall barn — Dairy cows at CAST's barn, on-site.

A tagged dairy cow at CAST, photo via Cornell CALS — Via Cornell CALS / CAST.

AWS
React
PostgreSQL
scikit-learn