To Measure or Not: A Cost-Sensitive, Selective Measuring Environment for Agricultural Management Decisions with Reinforcement Learning

TL;DR

This paper introduces a cost-sensitive reinforcement learning approach for agricultural management that optimizes the timing of crop measurements and fertilizer application, reducing unnecessary measurements and costs.

Contribution

It presents a novel RL environment incorporating measurement costs and demonstrates adaptive measuring policies aligned with crop development stages.

Findings

RL agent effectively balances measurement costs and crop management decisions.

Adaptive policies follow critical crop development stages.

Results align with expert agricultural practices.

Abstract

Farmers rely on in-field observations to make well-informed crop management decisions to maximize profit and minimize adverse environmental impact. However, obtaining real-world crop state measurements is labor-intensive, time-consuming and expensive. In most cases, it is not feasible to gather crop state measurements before every decision moment. Moreover, in previous research pertaining to farm management optimization, these observations are often assumed to be readily available without any cost, which is unrealistic. Hence, enabling optimization without the need to have temporally complete crop state observations is important. An approach to that problem is to include measuring as part of decision making. As a solution, we apply reinforcement learning (RL) to recommend opportune moments to simultaneously measure crop features and apply nitrogen fertilizer. With realistic considerations, we design an RL environment with explicit crop feature measuring costs. While balancing costs, we find that an RL agent, trained with recurrent PPO, discovers adaptive measuring policies that follow critical crop development stages, with results aligned by what domain experts would consider a sensible approach. Our results highlight the importance of measuring when crop feature measurements are not readily available.