Select Page
An integrated data pipeline for smallscale fisheries

An integrated data pipeline for smallscale fisheries

Every day, about 40 million small-scale fishers go out fishing, yet virtually none of these activities or yields are documented. This global data deficiency underpins SDG 14, yet we are now at a moment in time when technologies are small enough and cheap enough to solve it. WorldFish are testing novel linkages of these technologies to create an automated data pipeline to highlight temporal and spatial changes in fish production. This pilot will provide a national proof of concept in Timor-Leste before transitioning to scale.

CubicA, the new farmer advisory app

CubicA, the new farmer advisory app

CubicA is a free hotline that provides Ugandan farmers with weather and agricultural information anywhere, anytime, and in their local language. Through the integration of machine learning and big data, CubicA – which is proposed by Dalberg Data Insights, Viamo and Bioversity International – leverages previous caller data along with satellite images, weather forecasts and other data sources to build customized callers profile and optimize the structure and content of the service over time. CubicA brings more tailored information and advice to farmers by considering their customer journey, location and agronomic context as well as their profile, including gender. This will allow farmers greater access to information and knowledge, empowering them with greater agency and access to innovation.

Machine learning for smarter seed selection

Machine learning for smarter seed selection

Each year farmers make the decision as to what to plant on their fields. Some crop varieties are record-breakers, but they often present a higher risk and only perform well in ideal conditions. Other varieties have stable but lower yield. Using machine learning, researchers can predict yield and risk at a specific farm and select a mixture of varieties that represents the optimal trade-off between risk and yield. Using CIMMYT’s data from agricultural experiments, BioSense will develop machine learning models that predict the performance of seed varieties in particular conditions. The project will give farmer in Mexico and Ethiopia recommendations on which seeds to plant.

Revealing informal food flows through free WiFi

Revealing informal food flows through free WiFi

Food flows at traditional and informal markets are largely invisible despite of being the main source of food for the poor and also of food safety hazard. Unraveling those flows would contribute to identify better policy and planning options to upgrade distribution channels. The project proposes to characterize and monitor food flows between traders, retailers and consumers in Hanoi, Vietnam by providing free Internet to a series of wholesale and markets around the city. Project partners CIAT and GSO will survey actors and track in space and time all the devices in the range of the router. By crossing the data gathered the initiative aims to model food flows and linked actors at key markets.

Using Commercial Microwave Links (CML) to estimate rainfalls

Using Commercial Microwave Links (CML) to estimate rainfalls

The lack of accurate, real-time rainfall measurements leads to imprecision in crop yield monitoring, which in turn leads to high basis risks of rainfall-based index insurance. The project proposed by IFPRI and Cornell aims to demonstrate the potential of using recent advances in Commercial Microwave Links (CML) technology to estimate rainfalls in crop production monitoring and improve the design of rainfall-based index insurance in Kenya. Farmers will benefit from better design of rainfall-based index insurance and poor households will benefit from more accurate crop yield monitoring by policymakers.