The objective of this challenge is to develop and test a methodological framework for predicting maize price variations based on high and moderate-resolution satellite data directly used for estimating yields.
The yields have direct impact on the available supply and therefore the price that crops can be bought for.
Accurate forecasts aid in resource allocation and budget planning, ensuring efficient use of limited funds. it also contributes to food security by helping anticipate shortages and vulnerabilities, enabling proactive interventions.
A machine algortihm trains on the NDVI data of the Copernicus Satellites as well as on ground yield data collected by farmers. The result is an estimation for the yield in the curretn season way in advance to be able to prepare for food shortages or stretch limited funds to the maximum.
EU space technologies
Copernicus Sentinel-2 data, specifically the NDVI, is used to get information on the vegetation of specific locations. This is valuable, because we can use it to predict vegetation growth and health of farms.
On the ground data of farmers regarding thei yields.
We need this data as ground truth for the Machine Learning algorithm to be able to train it.
Space for International Development & Humanitarian Aid
Strengthening food security & access to clean water is the challenge we are addressing with our project. By predicting prices through yields in a season, we can better prepare for any emergencies way in advance.