We are proud to announce the finalists of the 2019 Inspire Challenge.

Finalists will pitch their proposals to a panel of expert judges at the Big Data in Agriculture Convention in Hyderabad, India, 16-18 October.

Five winning projects will be revealed at the closing ceremony on 18 October, and each winning project will be awarded 100,000 USD.

The Inspire Challenge is the innovation process of the CGIAR Platform for Big Data in Agriculture and seeks to source and foster new solutions for digital agriculture in developing economies. It challenges research organizations to partner with industry in order to leverage public good data, especially CGIAR data, to solve intractable challenges at scale.

For more info about the 2019 finalists, visit their project pages below:

• Farmer’s friend | Africa Rice Center & Limitless AI

Farmer’s friend is a tool designed to improve farming efficiency and enable higher crop yields by using big data sets and user location along with machine learning algorithms and predictive analysis models to provide farmers with daily guidance on activities from pre-planting to post-harvesting.

• Gamifying weather forecasting: “Let it rain” campaign | CIAT & The Mediae Company

The “Let it rain” campaign is conceived as a platform that will gamify weather prediction to incentivize farmers uptake of localised agro-advisories and help crowdsource weather information, which, when run through machine learning, will further improve weather forecasts.

• Hungry cities: Inclusive food markets in Africa | CIAT & Twiga Foods

The project proposes to analyze five years of commercial data on 17 fruit and vegetable crops from more than 20,000 farmers and 12,000 retailers and wholesale markets in metro Nairobi. Insights will support data-driven policy engagement, improved business decisions and further research on the role of fresh fruits and vegetables (FFV) in ameliorating nutrient deficiencies for low-income consumers.

• SLAM!: Self-learning advice for farm managers | CIMMYT &  Wageningen University and Research

SLAM! is a self-learning platform that uses farmer feedback and news items to improve the automatically generated advice to farmers based on simple agronomic models. With SLAM!, farmers take ownership of their digital crop management advice service and contribute to improving it over time.

• Citizen-H2D3 for food and nutrition security | IITA & EC-JRC

Citizen-H2D3 is conceived as a (near) real-time system for monitoring dietary diversity in space and time, based on a citizen-driven spontaneous crowdsourcing approach in Rwanda. Nuanced and disaggregated insights into household diets will offer the Rwandan government and development agencies the needed information to solve critical food security issues.

• One village, one mill | CIAT & VIA

The project proposes to help deploy appropriately sized modern micro solar mills in an optimal way by developing a model combining big data sets of rural household locations with crop location. These micro mills allow cost-effective crop processing in villages of 30-100 households, are simple to use, clean, and easy to maintain.

• Rapid genomic detection of aquaculture pathogens | WorldFish & The University of Queensland

The project proposes leveraging offline supervised machine learning associated with the MinION portable sequencing device for low-cost diagnostics of fish pathogens in remote locations, allowing real-time disease investigation and data-driven management.

• Real-time East Africa live groundwater use database | IWMI & Futurepump Ltd.

This project proposes to reduce information gaps by turning the network of solar pumps developed by Futurepump into IoT devices linked to an open, online water information platform at IWMI. The system would then be able to provide real-time information on water withdrawal, area irrigated, and energy use.

• Climate information services to manage climate risk | ICRISAT & SourceTrace Systems India

Climate information services to manage climate risk proposes to design and deploy an automated messaging system for smallholder farmers and extension workers in India to deliver real-time, location-specific and crop-based agro-advisories using machine learning for managing climate risk.

• Show me what you eat: Assessing diets with images | IFPRI & Washington University in St. Louis

This project will assess the use of meal pictures taken with a smartphone on a daily basis to measure overall dietary quality and dietary diversity patterns in Guatemala. A more precise understanding of dietary habits can lead to individually-tailored interventions that promote healthier diets, especially among the most vulnerable, including women and children.