Data driven ensemble learning for soybean yield prediction

Souradeep Chattopadhyay, Matthew Eden Carroll, Baskar Ganapathysubramanian, Asheesh K Singh, Soumik Sarkar

Keywords: ML:Ensemble Methods, ML: Applications

TL;DR: A cluster based ensemble learning approach for soybean yield prediction

Abstract: Soybean yield prediction is a challenging problem in agronomy that is often affected by many different factors simultaneously. Hyperspectral reflectance data from plants provide agronomist's with useful data about the health of soybean plants and using this data for yield prediction is an active area of research. Often breeding programs suffer from issues such as data imbalance and several external factors such as genotype variablility in different environment which can pose a serious challenge for developing yield prediction models for large scale breeding programs. In this work we demonstrate a cluster based ensemble approach for yield prediction that can perform well for large scale breeding programs by efficiently harnessing useful information from data through an unsupervised approach.