Rice crop life-cycle optimisation for Indian farmers using IoT sensing and machine learning
Cutting post-harvest rice losses in India with low-cost sensing and machine learning.
The Challenge
Rice farmers in India lose a significant share of their crop after harvest: drying, storage and delivery are managed by periodic manual inspection, expert knowledge is scarce, and spoilage from moisture and temperature problems sets in faster than farmers can respond. For rural smallholders and industrial producers alike, these post-harvest losses translate directly into lost income and wasted food.
The Solution
GrainSense applied NquiringMinds’ low-cost sensing and machine-learning/data-analytics technology to the full rice crop life cycle — sowing, growing, harvesting, drying, storage and delivery — to identify where losses occur and drive corrective action. It builds on NQM’s earlier AgriSense work, in which NQM developed a suite of agritech sensors for gathering key harvest-data metrics and deployed machine learning to drive improvements in efficiency, energy use and environmental impact; AgriSense raised NQM’s technology-readiness level from TRL 2 to TRL 4 and was pivotal in unlocking this substantially larger follow-on programme, with pilots in India for innovative rice drying and storage.
Outcomes
The project delivered sensing hardware, cloud analytics and machine-learning models targeted at rice-paddy optimisation and reduced post-harvest losses for rural and industrial farmers in India, extending NQM’s agritech sensing line of work alongside the related GrainCare grain-spoilage project.
This page is distinct from GrainCare, the related but separate grain-spoilage sensing work.
In Detail
Optimising the rice crop life cycle for Indian farmers. GrainSense applies low-cost IoT sensing and machine learning across the full rice life cycle — sowing, growing, harvesting, drying, storage and delivery — identifying where post-harvest losses occur and driving corrective action, so scarce expert knowledge reaches every harvest at once through cloud analytics and control.
The UK Prime Minister selected NquiringMinds to represent the best of UK innovation on her first ever trade mission (India Tech Summit) — the UK–India programme under which this Newton Fund work sat.
“The proliferation of digital technology and data analytics in agriculture is contributing to the lives of farmers and agricultural service providers in developing country economies.” — IIFPT, Ministry of Food Processing Industries
Features
Low-cost IoT sensor suite for key harvest-data metrics (moisture, temperature and related indicators).
Machine-learning analytics across the complete rice life cycle: sowing, growing, harvesting, drying, storage and delivery.
Cloud-based visualisations, analytics and control systems allowing scarce expert knowledge to be shared across many simultaneous harvests.
Whole-life-cycle rice optimisation aimed at low-cost deployment for rural Indian farmers, not just industrial operators.
Benefits
Reduced post-harvest losses and improved rice quality for rural and industrial farmers in India (project objective; pilots recorded in India for innovative rice drying and storage).
Efficiency, energy-use and environmental-impact improvements from ML-driven drying and storage control (demonstrated in the AgriSense precursor).
Precursor AgriSense work raised NQM technology readiness from TRL 2 to TRL 4 and unlocked this £1.5m-scale Innovate UK investment.
