Lacuna - Correct Field Detection Challenge
$10 000 USD
Can you design a method to accurately find field locations?
594 data scientists enrolled, 110 on the leaderboard
26 March—4 July
101 days

Crop yield prediction is a valuable tool for agronomists and policymakers. It is also a hard task, especially when dealing with small fields in a subsistence setting. One challenge with many existing datasets is that of location accuracy. GPS locations for fields can end up offset from the true location due to sensor inaccuracies or from locations being collected at the edges of fields rather than the field centres. This makes it harder to connect remote-sensed data to the yield values - a problem faced by participants in our CGIAR Crop Yield Prediction Challenge.

The objective of this competition is to design a method that can help correct these location offsets by finding the most probable field center given an input location. Your model may use any publically available data (subject to approval), including any datasets that can be accessed through tools such as Google Earth Engine. You may NOT use datasets that are not freely available (such as very-high-resolution satellite images) to ensure that we keep the playing field level. For each location, we also provide approximate plot size and measured yield in case these help with creating your solution.

The data for this competition is part of a larger dataset of maize yields collected from East Africa. The top solutions will be incorporated into a research project that aims to correct location errors in this dataset to produce a new high-accuracy plot location and yield dataset that can be used to better understand the agricultural landscape. This, combined with the results of the previous Crop Yield Prediction challenge, will hopefully enable yield prediction at a higher accuracy than previously achieved.

About CGIAR (

The CGIAR (formerly the Consultative Group for International Agricultural Research) is a consortium of international agricultural research centers scattered across the world who focus on issues related to agricultural productivity, food security, poverty, and the environment. The CGIAR is made up of 15 research centers and operates in dozens of countries across Asia, Africa, and Latin America.

About The Platform for Big Data in Agriculture (

The CGIAR Platform for Big Data in Agriculture is a cross-center platform of the CGIAR with the goal of leveraging and harnessing the power of big data to accelerate and enhance the impact of international agricultural research. This 5-year platform (2017 - 2021) will provide global leadership in organizing open data, convening partners to develop innovative ideas, and demonstrating the power of big data analytics through inspiring projects. It is where information becomes power: power to predict, prescribe, and produce more food, more sustainably. It democratizes decades of agricultural data empowering analysts, statisticians, programmers and more to mine information for trends and quirks, and develop rapid, accurate and compelling recommendations for farmers, researchers and policymakers.

About Lacuna Fund

Lacuna Fund - an initiative co-founded by The Rockefeller Foundation,, and Canada’s International Development Research Centre and facilitated by Meridian Institute - is the world’s first collaborative effort to provide data scientists, researchers, and social entrepreneurs in low- and middle-income contexts globally with the resources they need to produce labeled datasets that address urgent problems in their communities. With an initial focus on agriculture, languages, and health, Lacuna Fund aims to create the building blocks of labeled training data that allow robust machine learning applications. Funding from the first call for agricultural datasets will support a variety of products, from personalized information on fertilizers and regenerative agriculture practices for farmers, to better information about crop yields and food security to inform decision-makers worldwide.

About One Acre Fund (

One Acre Fund is a non-profit social enterprise that provides smallholder farmers with seeds, fertilizer, and agronomic training on credit. They currently serve over one million farmers across Africa.

About Visual and AI Solutions (VAIS) (

Visual and AI Solutions (VAIS) is a Nile University spinoff and incubated company that is founded by established academics and is the culmination of many years of research and development experience in the areas of computer vision, artificial intelligence and machine/deep learning, big data engineering and wireless sensor networks. VAIS develops novel artificial intelligence and visual computing technologies that can be deployed on mobile/handheld devices and on the cloud to enable smart applications in the domain of agricultural technology (AgriTech). VAIS AgriTech algorithms and modules enable advanced precision agriculture and deliver dependable field analytics to farmers, traders, and insurers through applications such as intelligent ag field scouting, in-situ plant disease detection & diagnosis, and creation of field precision maps. Additional VAIS activities include development of multispectral satellite imagery analytics and AI-based consultancy services.