Yield Consortium

Agriculture is becoming more and more demanding. In order to increase agricultural yields while using resources efficiently, it is important to be able to take decisions early on, for example the efficient distribution of fertilizers and pesticides.

Machine learning can support farmers but is often limited by the availability of relevant data. Since it is often challenging to get access to and harmonize the needed agricultural data, the Yield Consortium focuses on the use of earth observation data instead. We develop techniques for processing satellite data, yield maps, weather data, soil data and digital elevation maps, then combine those sources in machine-learning models to predict agricultural yields with sub-field precision.

In addition, we aim to bring digitalization and agriculture closer together. Many farmers have a multitude of relevant data sources. Their use is often limited because of missing harmonization. We help farmers make use of their data, such as agricultural yield maps.

It is well known that indices derived from satellite imagery, such as the normalized difference vegetation index (NDVI), can be used to predict the biomass of crops. It is, however, challenging to predict yield from biomass alone. Crops with a large biomass can still result in low yield when they suffer from nutrient deficiencies.

We use artificial intelligence to directly predict yield from the full spectral information of satellite imagery. We fuse further data sources into our machine-learning models and create pixel-wise, sub-field yield predictions at a resolution of 10 x 10 metres per pixel.