Increasing the Reliability of Intercropping in Agriculture Using Machine Learning
M. Srikanth, R. N. V. Jagan Mohan, M. Chandra Naik
Abstract
Machine learning has the potential to revolutionize agriculture by helping farmers optimize crop yields, reduce costs, and improve sustainability. One way to use machine learning in agriculture is to optimize multi-cropping, which involves growing multiple crops simultaneously on the same piece of land. This paper proposes a new approach to optimizing multi- cropping using reinforcement learning. Reinforcement learning is a type of machine learning that allows agents to learn to behave in an environment by trial and error. In the context of multi-cropping, the agent is a machine learning model that is trying to learn to select the best crops to grow together and how to manage them in order to maximize yield. The proposed approach uses reinforcement learning to optimize the hyper parameters of the machine learning model. Hyper parameters are the settings of the machine learning model, such as the number of trees in a random forest model or the learning rate of a neural network. By optimizing the hyper parameters, the machine learning model can be trained to better predict crop yields and make better decisions about crop management. The proposed approach was evaluated on a real-world dataset of crop yields from India. The results showed that the proposed approach was able to significantly improve crop yields compared to traditional methods of multi-cropping.