This project aims to evaluate the benefit of Common Agricultural Policy Regional Impact (CAPRI) data for regional crop yield forecasting. CAPRI data includes economic data from representative farms across Europe summarized at NUTS2 level. You could also combine CAPRI data with data from the European Commission’s MARS Crop Yield Forecasting System and Eurostat for regional crop yield forecasting. In both cases, you will experiment with machine learning or deep learning methods to predict regional crop yield, for several crops across Europe.
The CAPRI model was designed for impact assessment of agricultural, environmental and trade policies. CAPRI uses economic farm data from multiple sources, including EUROSTAT and the Farm Accounting Data Network (FADN). You will be challenged to predict regional crop yields using economic indicators from the CAPRI database or by combining CAPRI data with crop model simulation outputs, weather observations, remote sensing indicators and regional yield statistics from MCYFS and Eurostat. The work of Paudel at al (2020) provides some initial guidance on regional crop yield forecasting using machine learning.
Application of machine learning or deep learning to a real-world problem using data from the CAPRI database, MARS Crop Yield Forecasting System and Eurostat.
- Become familiar with farm economic data from the CAPRI database and the data used by MARS Crop Yield Forecasting System to forecast crop yield.
- Evaluate the benefits and limitations of farm economic data in crop yield forecasting.
- Understand the usefulness of machine/deep learning methods for regional crop yield forecasting.
- Getting started with CAPRI
- Paudel, D., et al. (2021). Machine learning for large-scale crop yield forecasting. Agricultural Systems, 187, 103016.
- Machine Learning (FTE-35306)
- Deep Learning (GRS-34806)
- Programming in Python, Geo-Scripting
Theme(s): Modelling & visualisation