Machine learning in agroecology

Simulation models are a widely used tool for modelling systems for which it is hard to obtain real data. However, the simulation models are usually complex and it is not an easy task to induce new knowledge and find relationships and dependencies among different parts of the simulation model. Previous attempts to analyze the outputs from simulation models were mainly focused on speeding up the simulation process. In this monograph we are proposing a methodology for analyzing results of complex simulation models. The methodology combines simulation outputs, background knowledge, and machine learning, to obtain new and interesting knowledge about a certain problem of interest. We apply our methodology to three different simulation models that simulate the co-existence between genetically-modified and conventional crops at different levels. The induced machine learning models provide us with new co-existence knowledge about the positive and negative influences on the co-existence between genetically-modified and conventional crops. The results encourage us to try the same methodology on different types of simulation models and different scientific areas.