Optimizing Nitrogen Management with Deep Reinforcement Learning and Crop Simulations

TL;DR

This paper introduces a deep reinforcement learning approach integrated with crop simulations to optimize nitrogen management, aiming to improve crop yield and reduce fertilizer use while minimizing environmental impact.

Contribution

It formulates nitrogen management as an RL problem and demonstrates that RL-trained policies outperform traditional methods in crop yield and fertilizer efficiency.

Findings

RL policies achieve higher or similar yields compared to empirical methods.

RL policies use less fertilizer, reducing environmental impact.

Effective integration of deep RL with crop simulations for agricultural decision-making.

Abstract

Nitrogen (N) management is critical to sustain soil fertility and crop production while minimizing the negative environmental impact, but is challenging to optimize. This paper proposes an intelligent N management system using deep reinforcement learning (RL) and crop simulations with Decision Support System for Agrotechnology Transfer (DSSAT). We first formulate the N management problem as an RL problem. We then train management policies with deep Q-network and soft actor-critic algorithms, and the Gym-DSSAT interface that allows for daily interactions between the simulated crop environment and RL agents. According to the experiments on the maize crop in both Iowa and Florida in the US, our RL-trained policies outperform previous empirical methods by achieving higher or similar yield while using less fertilizers