Optimizing Nitrogen Management with Deep Reinforcement Learning and Crop Simulations
This work addresses the problem of sustainable agriculture by improving nitrogen management for farmers and environmentalists, though it is incremental as it applies existing RL methods to a specific domain.
The paper tackled optimizing nitrogen management for maize crops by proposing a deep reinforcement learning system integrated with crop simulations, achieving higher or similar yields while using less fertilizer compared to previous empirical methods.
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