Food@Home is a platform for crop yield prediction using recent techniques in AI and machine learning. Food@Home uses free multi spectral imagery from the Sentinel 2A satellite (European Satellite agency) as well as relevent paremters from NASA’s satellites (GPM, MODIS etc) and ground truthing using our smartphones based platform. Food@Home is capable of giving accurate crop yield prediction at 10 metres resolution and up to 1 week frequency. Using Food@Home you can find out the type of crop cultivated and its current yield and health on a weekly basis. The project is currently focused on the province of Punjab in Pakistan, where 3300 crop reporting survey officers have been been equipped with smart Phones for ground truthing. The project builds on the volunteer computing platform SETI@Home to scale up to other parts of the world. Find out more about our models for crop classification and crop yield prediction.

Food@Home predicts yield of different crops based on in-house built model following Burke & Lobelle’s study “A scalable satellite based crop yield mapper” that uses a) classification data of Sentinel 2A Satellite along with its indices and ii) APSIM simulation run on ground-collected data and satellite observations.
Click here to see how this platform works and download Food@Home on your computer.
Crops Distribution
Click on a colored tile to zoom in.
Crop Type

Join Food@home

You can help solve the world’s food security problem by running a free program that downloads and analyzes satellite imagery data for crop yield estimation.

Download Boinc (32-bit) Download Boinc (64-bit) For more information please visit: Boinc Official Downloads

Vote for your city!

Vote for your city to be included in our analysis by downloading our software and running it on your PC.

Frequently asked questions

Learn all about Food@Home and how we work in the links provided.

Crop data is gathered through satellite imagery and processed through volunteer computing to derive appropriate yield results.
A distributed computing architecture consists of a number of client machines with very lightweight software agents installed with one or more dedicated distributed computing management servers. The agents running on the client machines usually detect when the machine is idle and send a notification to the management server that the machine is not in use and available for a processing job. The agents then requests an application package. When the client machine receives this application package from the management server to process, it runs the application software when it has free CPU cycles and sends the result back to the management server. When the user returns and requires the resources again, the management server returns the resources was using to perform different tasks in the user's absence.
Anyone across the globe with a running computer can contribute to Food@Home.
The range for our satellite imagery is scaled at 10 meters.
The data is updated every three days.
You can simply vote for the region you want crop yield estimation in the links provided.