Research themes
Where the work is focused.
Eight areas that together determine whether agricultural intelligence is accurate, timely and usable in the field.
Artificial Intelligence
Applied AI for agronomic decision support in low-connectivity, low-resource field conditions.
Machine Learning
Predictive modelling for crop performance, production risk and yield outcomes.
Satellite Data
Remote sensing for plot-level monitoring, vegetation signals and seasonal change detection.
IoT and Sensors
Field-level instrumentation and edge processing where bandwidth is constrained.
Soil Data
Soil characteristics linked to crop suitability and input recommendations.
Crop & Yield Modelling
Models that translate field, weather and management data into yield expectations.
Climate Intelligence
Weather and climate risk signals applied to agricultural planning decisions.
Agricultural Data Science
Data infrastructure and methods that make fragmented agricultural data usable.
Pilot work
Selected results and learnings.
Figures below come from AgriPulse pilot activity. They are reported as pilot-stage evidence, not as generalised platform performance.
Measured within pilot conditions on pilot datasets.
Satellite, sensor and survey data combined in a single pipeline.
Reported by participating farmers during the pilot period.
Further deployment data, methodology notes and evaluation detail are available to research and institutional partners on request.
From data to decision
How research becomes field action.
- Field & Satellite Data
- AgriPulse Data Platform
- AI / Machine Learning
- Agricultural Intelligence
- Action
Research and technology collaboration
AgriPulse works with universities, research institutions and development organisations on agricultural data science, model validation and field evaluation. We welcome collaboration on crop modelling, remote sensing, climate risk and evaluation design.
Research partners
Advancing agricultural research together.
AgriPulse collaborates with academic and research institutions to connect field evidence, applied science and digital agricultural intelligence.
