Prediction of CO₂ Concentration via Long Short-Term Memory Using Environmental Factors in Greenhouses

In greenhouses, photosynthesis efficiency is a crucial factor for increasing crop production. Sinceplants use CO2 for photosynthesis, predicting CO2 concentration is helpful for improving photosyntheticefficiency. The objective of this study was to predict greenhouse CO2 concentration using a longsh...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Weon'ye gwahag gi'sulji 2020, 38(2), , pp.201-209
Hauptverfasser: Moon, Taewon, Choi, Ha Young, Jung, Dae Ho, Chang, Se Hong, Son, Jung Eek
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In greenhouses, photosynthesis efficiency is a crucial factor for increasing crop production. Sinceplants use CO2 for photosynthesis, predicting CO2 concentration is helpful for improving photosyntheticefficiency. The objective of this study was to predict greenhouse CO2 concentration using a longshort-term memory (LSTM) algorithm. In a greenhouse where mango trees (Mangifera indica L. cv. Irwin) were grown, temperature, relative humidity, solar radiation, atmospheric pressure, soiltemperature, soil humidity, and CO2 concentration were measured using complex sensor modules. Nine sensors were installed in the greenhouse. The averages of environmental factors from the ninesensors were used as inputs, and the average CO2 concentration was used as an output. In thisexperiment, LSTM, one of the recurrent neural networks, predicted changes in CO2 concentrationfrom the present to 2 h later using historical data. The data were measured every 10 min fromFebruary. 1, 2017 to May 31, 2018, and missing data were interpolated with a linear method andmultilayer perceptron. In this study, LSTM predicted the 2-h change in CO2 concentrations at aninterval of 10 min with adequate test accuracy (R2 = 0.78). Therefore, the trained LSTM can be usedto predict the future CO2 concentration and applied to efficient CO2 enrichment for photosynthesisenhancement in greenhouses. KCI Citation Count: 7
ISSN:1226-8763
2465-8588
2465-8588
1226-8763
DOI:10.7235/HORT.20200019