Greenhouse Microclimate Prediction based on Neural Networks

• Item type: SIG Technical Reports(1)
• 公開日: 2022-06-30
• タイトル: Greenhouse Microclimate Prediction based on Neural Networks
• タイトル / 言語: en
• タイトル: Greenhouse Microclimate Prediction based on Neural Networks
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: LOIS
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: Graduate School of Science and Technology
• 著者所属: Center for Computational Sciences
• 著者所属: Faculty of Life and Environmental Sciences University of Tsukuba
• 著者所属(英): en
• 著者所属(英): Graduate School of Science and Technology
• 著者所属(英): en
• 著者所属(英): Center for Computational Sciences
• 著者所属(英): en
• 著者所属(英): Faculty of Life and Environmental Sciences University of Tsukuba
• 著者名: Mujawamariya, Marie Grace; Toshiyuki, Amagasa; Naoya, Fukuda
• 著者名(英): Mujawamariya, Marie Grace; Toshiyuki, Amagasa; Naoya, Fukuda
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Multivariate time series prediction approaches have been significant in wide range of real-world application. This paper presents Neural Networks forecasting techniques which take as input multivariate time series data captured by sensors inside a greenhouse, and satellite weather data and predict environmental parameters such as temperature inside the greenhouse over 6 hours and 12 hours in the future. We report results of the prediction model and evaluate our models predictions accuracy based on MAE metric and standard deviation for the stability. Finally, we highlight and discuss about microclimate parameters that have significant effect for predicting precise temperature inside the greenhouse.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Multivariate time series prediction approaches have been significant in wide range of real-world application. This paper presents Neural Networks forecasting techniques which take as input multivariate time series data captured by sensors inside a greenhouse, and satellite weather data and predict environmental parameters such as temperature inside the greenhouse over 6 hours and 12 hours in the future. We report results of the prediction model and evaluate our models predictions accuracy based on MAE metric and standard deviation for the stability. Finally, we highlight and discuss about microclimate parameters that have significant effect for predicting precise temperature inside the greenhouse.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN10539261
• 書誌情報: 研究報告ドキュメントコミュニケーション（DC）; 巻 2022-DC-125, 号 1, p. 1-6, 発行日 2022-06-30
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8892
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会