Bayesian Learning for Cost Constrained Cultivation Management

DOI
  • MAEDA Yasunari
    School of Regional Innovation and Social Design Engineering, Kitami Institute of Technology

Bibliographic Information

Other Title
  • コスト制約がある栽培管理におけるベイズ学習

Abstract

There is a lot of previous research on profit maximization in agriculture. In previous research on cultivation management, the expected profit is maximized under the condition that probabilities are unknown. There is no income until the harvest season in agriculture. In reality, there is a limit to the budget that can be spent on cultivation management. However, cost constraint has not been considered in the previous research. In this research, a new cost constrained cultivation management method is proposed. Cost constrained cultivation management is modeled by Markov decision processes with unknown probabilities. The proposed method maximizes the expected profit with respect to a Bayes criterion by dynamic programming. The effectiveness of the proposed method is shown by some numerical calculation examples. The expected profits according to the cost constraints are confirmed. The proposed method is effective for areas without historical data and areas affected by global warming. This research is a basic research, and future extended research is required.

Journal

Keywords

Details 詳細情報について

  • CRID
    1390859558295812480
  • DOI
    10.24466/jbfsa.25.1_21
  • ISSN
    24242578
    13451537
  • Text Lang
    ja
  • Data Source
    • JaLC
  • Abstract License Flag
    Disallowed

Report a problem

Back to top