2018 WinnerMachine learning for smarter seed selection
The Inspire Challenge is an initiative to challenge partners, universities, and others to use CGIAR data to create innovative pilot projects that will scale. We look for novel approaches that democratize data-driven insights to inform local, national, regional, and global policies and applications in agriculture and food security in real time; helping people–especially smallholder farmers and producers–to lead happier and healthier lives.
This proposal was selected as a 2018 winner, with the team receiving 100,000 USD to put their ideas into practice.
Machine learning for smarter seed selection
Each year farmers decide what to plant on their fields. Some varieties are record-breakers but they are risky and only grow well in perfect conditions. Other varieties have stable but comparatively lower yields.
Using machine learning, researchers can predict both yields and risks associated with different seeds at a specific farm and select a mixture of varieties that represents the optimal trade-off. Using CIMMYT’s data from hundreds of on farm as well as experimental station sites and a network of seed companies producing varieties for diverse agro ecologies, BioSense will develop machine learning models that predict the performance of seed varieties in particular conditions in order to advise maize farmers in Mexico as regards to what to plant.
Dr Sanja Brdar | Email
Head of Knowledge Technologies Group at BioSense Institute
Marko Panić | Email
Machine Learning Expert at BioSense Institute
Oskar Marko | Email
Data Analytics Expert at BioSense Institute
Weather and Climate Expert at BioSense Institute
Dr Kai Sonder | Email
Head of GIS Unit at CIMMYT
Dr Alberto Chassaign
Maize Seed systems specialist for Latin America at CIMMYT
Step by step
The first step is to form a database with all the necessary data about maize production in Mexico. It will include satellite images, performance data and weather information.
Development of machine learning algorithms
Based on the database, the team will develop machine learning models for prediction of performance of different hybrids in various climate and soil conditions.
Development of seed selection algorithm
The inputs of this section will include predicted yield, risk and consumption of raw materials, while the output would be a mixture of seeds that maximises profit and minimises risk and environmental footprint.
The system will be thoroughly tested and its performance will be evaluated. The team will then assess its potential for scaling up on a global level.