Kalman Filtering for Accurate and Fast Plant Growth Dynamics Assessment

Abstract

Artificial growth systems are the essential part of the precision agriculture. It allows solving many problems associated with the growing demand in the environmental friendly food production in the context of increasing world population. Accurate and reliable assessment of plant growth dynamics parameters is crucial for the future success of the whole growing system parameters optimization. In this research, we report on the implementation of the extended Kalman filtering method for insitu evaluation of plant growth dynamics parameters. We show the reliability and benefits of the proposed approach on the simulated and experimental data obtained from the IoT-based testbed. We demonstrate that our method serves as a robust and computationally cost-effective tool for the accurate assessment of the growing dynamics that, in turn, could be used for the further optimization of the whole plant cultivation process in artificial conditions.