Abstract
The optimal control of sugar content and its associated technology is important for producing high-quality crops more stably and efficiently. Model-based reinforcement learning (RL) indicates a desirable action depending on the type of situation based on trial-and-error calculations conducted by an environmental model. In this paper, we address plant growth modeling as an environmental model for the optimal control of sugar content. In the growth process, fruiting plants generate sugar depending on their state and evolve via various external stimuli; however, sugar content data are sparse because appropriate remote sensing technology is yet to be developed, and thus, sugar content is measured manually. We propose a semisupervised deep state-space model (SDSSM) where semisupervised learning is introduced into a sequential deep generative model. SDSSM achieves a high generalization performance by optimizing the parameters while inferring unobserved data and using training data efficiently, even if some categories of training data are sparse. We designed an appropriate model combined with model-based RL for the optimal control of sugar content using SDSSM for plant growth modeling. We evaluated the performance of SDSSM using tomato greenhouse cultivation data and applied cross-validation to the comparative evaluation method. The SDSSM was trained using approximately 500 sugar content data of appropriately inferred plant states and reduced the mean absolute error by approximately 38% compared with other supervised learning algorithms. The results demonstrate that SDSSM has good potential to estimate time-series sugar content variation and validate uncertainty for the optimal control of high-quality fruit cultivation using model-based RL.
Highlights
Several studies have been performed to evaluate advanced cultivation techniques for stable and efficient production of high-quality crops based on farmers’ experience and intuition [1,2,3,4]
The results demonstrate that all semisupervised semisupervised deep state-space model (SDSSM) reduced the estimation errors for all error indicators
We have proposed a novel plant growth model using a semisupervised deep state-space model (SDSSM) for model-based reinforcement learning to determine the optimal control of sugar content
Summary
Several studies have been performed to evaluate advanced cultivation techniques for stable and efficient production of high-quality crops based on farmers’ experience and intuition [1,2,3,4]. A fine balance must be achieved because insufficient water stress does not improve sugar content while excessive water stress causes permanent withering Such a technique is currently limited to expert farmers, and there have been some studies conducted to estimate water stress indirectly from soil moisture or climatic environmental factors such as temperature, humidity, and sunlight [5,6,7,8,9,10]. The purpose of water stress cultivation is to raise the sugar content, and a technique to directly control the sugar content flexibly is of interest In this regard, our final goal is to develop a method to determine the optimal action to achieve the desired sugar content of greenhouse tomato plants at harvest stably and efficiently. We aim to develop a plant growth model to estimate timeseries sugar content variation employing reinforcement learning, as the first step toward the final goal
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
