Establishment of multi-scale crop yield prediction using data assimilation technology

2023 Fiscal Year Final Research Report

• Project/Area Number: 21H02314
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Review Section: Basic Section 41040:Agricultural environmental engineering and agricultural information engineering-related
• Research Institution: Nagoya City University (2023); Tokyo University of Agriculture and Technology (2021-2022)
• Principal Investigator: TATSUMI Kenichi 名古屋市立大学, データサイエンス学部, 教授 (40505781)
• Co-Investigator(Kenkyū-buntansha): 本林 隆 東京農工大学, 農学部, 教授 (20262230) ; 桂 圭佑 東京農工大学, (連合)農学研究科(研究院), 准教授 (20432338) ; 斎藤 広隆 東京農工大学, (連合)農学研究科(研究院), 教授 (70447514) ; 山下 恵 東京農工大学, (連合)農学研究科(研究院), 准教授 (70523596)
• Project Period (FY): 2021-04-01 – 2024-03-31
• Keywords: 統合型作物生長モデル / LAI / データ同化 / 野外圃場 / 数理統計手法

Outline of Final Research Achievements

The aim of this study was to establish a highly accurate simulation technique that is independent of spatial scale and can reasonably estimate parameters such as data and conditions that are difficult to observe directly by integrating an integrated crop growth model with mathematical and statistical methods, based on consistency with the model. The effectiveness of data assimilation and measurement of LAI and grass height of tomato was verified, and the prediction accuracy of LAI was improved. On the other hand, prediction accuracy did not improve for yield, which was expected because of improved LAI reproduction and prediction accuracy. Future work includes the addition of model parameters to the expanded spatial vectors and the application of new methods to optimize the estimation of model parameters. These results have been published in 13 refereed papers and 10 conference presentations during the research period.

Free Research Field

農業情報気象学

Academic Significance and Societal Importance of the Research Achievements

本研究の学術的意義は，統合型作物モデルと数理統計手法の融合により，観測困難なデータや条件を合理的に推定し，空間スケールに依存しない高精度なシミュレーション技術を確立することである．この技術により，作物の生長や収量の予測精度が向上し，農業の効率化と省力化に貢献できる．また，UAVや人工衛星を活用することで，広範囲の圃場情報を効率的に収集し、農家の意思決定を支援するシステムを構築することが可能である．