All Issue

2020 Vol.38, Issue 2 Preview Page

Research Article

Prediction of CO2 Concentration via Long Short-Term Memory Using Environmental Factors in Greenhouses
Taewon Moon1
,
Ha Young Choi1
,
Dae Ho Jung1
,
Se Hong Chang2
,
Jung Eek Son1*
1Department of Plant Science and Research Institute of Agriculture and Life Sciences, Seoul National University
2Korea Electronics Technology Institute
* Corresponding Author
30 April 2020. pp. 201-209
PDF XML Citation
Abstract

In greenhouses, photosynthesis efficiency is a crucial factor for increasing crop production. Since plants use CO2 for photosynthesis, predicting CO2 concentration is helpful for improving photosynthetic efficiency. The objective of this study was to predict greenhouse CO2 concentration using a long short-term memory (LSTM) algorithm. In a greenhouse where mango trees (Mangifera indica L. cv. Irwin) were grown, temperature, relative humidity, solar radiation, atmospheric pressure, soil temperature, 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 nine sensors were used as inputs, and the average CO2 concentration was used as an output. In this experiment, LSTM, one of the recurrent neural networks, predicted changes in CO2 concentration from the present to 2 h later using historical data. The data were measured every 10 min from February. 1, 2017 to May 31, 2018, and missing data were interpolated with a linear method and multilayer perceptron. In this study, LSTM predicted the 2-h change in CO2 concentrations at an interval of 10 min with adequate test accuracy (R2 = 0.78). Therefore, the trained LSTM can be used to predict the future CO2 concentration and applied to efficient CO2 enrichment for photosynthesis enhancement in greenhouses.

Keywords
CO2 enrichment
deep learning
mango tree
photosynthesis
recurrent neural network

References
1
Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, Devin M, Ghemawat S, Irving G, et al. (2016) TensorFlow: A system for large-scale machine learning. In Proceedings of 12th USENIX OSDI, 265-283. Savanah, GA, USA, 02-04 November 2016
2
Ba JL, Kiros JR, Hinton GE (2016) Layer normalization. arXiv preprint arXiv:1607.06450
3
Boulard T, Kittas C, Roy JC, Wang S (2002) SE-structures and environment: Convective and ventilation transfers in greenhouses, part 2: Determination of the distributed greenhouse climate. Biosyst Eng 83:129-147. doi:10.1006/bioe.2002.0114
10.1006/bioe.2002.0114
4
Cock JH, Yoshida S (1973) Photosynthesis, crop growth, and respiration of a tall and short rice varieties. Soil Sci Plant Nutr 19:53-59. doi:10.1080/00380768.1973.10432519
10.1080/00380768.1973.10432519
5
Davison IR (1991) Environmental effects on algal photosynthesis: Temperature. J Phycol 27:2-8. doi:10.1111/j.0022-3646.1991.00002.x
10.1111/j.0022-3646.1991.00002.x
6
Donohue RJ, Roderick ML, McVicar TR, Farquhar GD (2013) Impact of CO2 fertilization on maximum foliage cover across the globe's warm, arid environments. Geophys Res Lett 40:3031-3035. doi:10.1002/grl.50563
10.1002/grl.50563
7
Gifford RM, Rawson HM (1994) Investigation of wild and domesticated vegetation in CO2 enriched greenhouses. In Proc. IGBP Workshop on Design and Execution of Experiments on CO2 Enrichment, Weidenberg, Germany, October 26-30, 1992
8
Goto E (2012) Plant production in a closed plant factory with artificial lighting. Acta Hortic 956:37-49. doi:10.17660/ActaHortic.2012.956.2
10.17660/ActaHortic.2012.956.2
9
Graamans L, Baeza E, Van Den Dobbelsteen A, Tsafaras I, Stanghellini C (2018) Plant factories versus greenhouses: Comparison of resource use efficiency. Agric Syst 160:31-43. doi:10.1016/j.agsy.2017.11.003
10.1016/j.agsy.2017.11.003
10
Greff K, Srivastava RK, Koutník J, Steunebrink BR, Schmidhuber J (2017) LSTM: A search space odyssey. IEEE Trans Neural Netw Learn Syst 28:2222-2232. doi:10.1109/TNNLS.2016.2582924
10.1109/TNNLS.2016.258292427411231
11
Han S, Kang J, Mao H, Hu Y, Li X, Li Y, Xie D, Luo H, Yao S, et al. (2017) ESE: Efficient speech recognition engine with sparse LSTM on FPGA. Proceedings of the 2017 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays 75-84. doi:10.1145/3020078.3021745
10.1145/3020078.3021745
12
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9:1735-1780. doi:10.1162/neco.1997.9.8.1735
10.1162/neco.1997.9.8.17359377276
13
Hu Q, Zhang R, Zhou Y (2016) Transfer learning for short-term wind speed prediction with deep neural networks. Renew Energ 85:83-95. doi:10.1016/j.renene.2015.06.034
10.1016/j.renene.2015.06.034
14
Jung DH, Kim D, Yoon HI, Moon TW, Park KS, Son JE (2016) Modeling the canopy photosynthetic rate of romaine lettuce (Lactuca sativa L.) grown in a plant factory at varying CO2 concentrations and growth stages. Hortic Environ Biotechnol 57:487-492. doi:10.1007/s13580-016-0103-z
10.1007/s13580-016-0103-z
15
Kamilaris A, Prenafeta-Boldú FX (2018) Deep learning in agriculture: A survey. Comput Electron Agric 147:70-90. doi:10.1016/j.compag.2018.02.016
10.1016/j.compag.2018.02.016
16
Kaplan A, Badger MR, Berry JA (1980) Photosynthesis and the intracellular inorganic carbon pool in the bluegreen alga Anabaena variabilis: Response to external CO2 concentration. Planta 149:219-226. doi:10.1007/BF00384557
10.1007/BF0038455724306290
17
Kingma D, Ba J (2014) Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980v9
18
Kläring HP, Hauschild C, Heißner A, Bar-Yosef B (2007) Model-based control of CO2 concentration in greenhouses at ambient levels increasescu cumber yield. Agric Forest Meteorol 143:208-216. doi:10.1016/j.agrformet.2006.12.002
10.1016/j.agrformet.2006.12.002
19
Lashof DA (1989) The dynamic greenhouse: Feedback processes that may influence future concentrations of atmospheric trace gases and climatic change. Climatic Change 14:213-242. doi:10.1007/BF00134964
10.1007/BF00134964
20
Lawlor DW (1995) Photosynthesis, productivity and environment. J Exp Bot 1449-1461. doi:10.1093/jxb/46.special_issue.1449
10.1093/jxb/46.special_issue.1449
21
Linker R, Seginer I, Gutman PO (1998) Optimal CO2 control in a greenhouse modeled with neural networks. Comput Electron Agric 19:289-310. doi:10.1016/S0168-1699(98)00008-8
10.1016/S0168-1699(98)00008-8
22
Liu Y, Racah E, Correa J, Khosrowshahi A, Lavers D, Kunkel K, Wehner M, Collins W (2016) Application of deep convolutional neural networks for detecting extreme weather in climate datasets. arXiv preprint arXiv:1605.01156
23
Lotfiomran N, Köhl M, Fromm J (2016) Interaction effect between elevated CO2 and fertilization on biomass, gas exchange and C/N ratio of European beech (Fagus sylvatica L.). Plants 5:38. doi:10.3390/plants5030038
10.3390/plants503003827618119PMC5039746
24
Maroco JP, Breia E, Faria T, Pereira JS, Chaves MM (2002) Effects of long‐term exposure to elevated CO2 and N fertilization on the development of photosynthetic capacity and biomass accumulation in Quercus suber L. Plant Cell Environ 25:105-113. doi:10.1046/j.0016-8025.2001.00800.x
10.1046/j.0016-8025.2001.00800.x
25
McGrath JM, Lobell DB (2013) Regional disparities in the CO2 fertilization effect and implications for crop yields. Environ Res Lett 8:014054. doi:10.1088/1748-9326/8/1/014054
10.1088/1748-9326/8/1/014054
26
Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland, AK, et al. (2015) Human-level control through deep reinforcement learning. Nature 518:529-533. doi:10.1038/nature14236
10.1038/nature1423625719670
27
Moon T, Ahn TI, Son JE (2018a) Forecasting root-zone electrical conductivity of nutrient solutions in closed-loop soilless cultures via a recurrent neural network using environmental and cultivation information. Front Plant Sci 9:859. doi:10.3389/fpls.2018.00859
10.3389/fpls.2018.0085929977249PMC6021533
28
Moon TW, Jung DH, Chang SH, Son JE (2018b) Estimation of greenhouse CO2 concentration via an artificial neural network that uses environmental factors. Hortic Environ Biotechnol 59:45-50. doi:10.1007/s13580-018-0015-1
10.1007/s13580-018-0015-1
29
Moon T, Ahn TI, Son JE (2019) Long short-term memory for a model-free estimation of macronutrient ion concentrations of root-zone in closed-loop soilless cultures. Plant Methods 15:59. doi:10.1186/s13007-019-0443-7
10.1186/s13007-019-0443-731160918PMC6540585
30
Oechel WC, Cowles S, Grulke N, Hastings SJ, Lawrence B, Prudhomme T, Riechers G, Strain B, Tissue D, et al. (1994) Transient nature of CO2 fertilization in Arctic tundra. Nature 371:500. doi:10.1038/371500a0
10.1038/371500a0
31
Oord AVD, Dieleman S, Zen H, Simonyan K, Vinyals O, Graves A, Kalchbrenner N, Senior A, Kavukcuoglu K (2016) Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499
32
Roy JC, Boulard T, Kittas C, Wang S (2002) PA-Precision Agriculture: Convective and ventilation transfers in greenhouses, Part 1: The greenhouse considered as a perfectly stirred tank. Biosyst Eng 83:1-20. doi:10.1006/bioe.2002.0107
10.1006/bioe.2002.0107
33
Rumelhart DE, Hinton GE, Williams RJ (1988) Learning representations by back-propagating errors. Cognit Model 5:1
34
Rußwurm M, Körner, M (2017) Multi-temporal land cover classification with long short-term memory neural networks. Int Arch Photogramm Remote Sens Spat Inf Sci 42:551. doi:10.5194/isprs-archives-XLII-1-W1-551-2017
10.5194/isprs-archives-XLII-1-W1-551-2017
35
Sharma-Natu P, Khan FA, Ghildiyal MC (1998) Photosynthetic acclimation to elevated CO2 in wheat cultivars. Photosynthetica 34:537-543. doi:10.1023/A:1006809412319
10.1023/A:1006809412319
36
Silver D, Huang A, Maddison CJ, Guez A, Sifre L, Van Den Driessche G, Schrittwieser J, Antonoglou I, Panneershelvam V, et al. (2016) Mastering the game of Go with deep neural networks and tree search. Nature 529:484-489. doi:10.1038/nature16961
10.1038/nature1696126819042
37
Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. In Z Ghahramani, M Welling, C Cortes, ND Lawrence, KQ Weinberger, eds, Advances in Neural Information Processing Systems, Ed 27, pp 3104-3112
38
Wang X, Gao L, Song J, Shen H (2017) Beyond frame-level CNN: Saliency-aware 3-D CNN with LSTM for video action recognition. IEEE Signal Process Lett 24:510-514. doi:10.1109/LSP.2016.2611485
10.1109/LSP.2016.2611485
39
Wen TH, Gasic M, Mrksic N, Su PH, Vandyke D, Young S (2015) Semantically conditioned LSTM-based natural language generation for spoken dialogue systems. arXiv preprint arXiv:1508.01745. doi:10.18653/v1/D15-1199
10.18653/v1/D15-119925851951
40
William WE, Garbutt K, Bazzaz FA, Vitousek PM (1986) The response of plants to elevated CO2. Oecologia 69:454-459. doi:10.1007/BF00377068
10.1007/BF0037706828311348
41
Wu Y, Schuster M, Chen Z, Le QV, Norouzi M, Macherey W, Krikun M, Cao Y, Gao Q, et al. (2016) Google's neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144
42
Zhang J, Zhu Y, Zhang X, Ye M, Yang J (2018) Developing a long short-term memory (LSTM) based model for predicting water table depth in agricultural areas. J Hydrol 561:918-929. doi:10.1016/j.jhydrol.2018.04.065
10.1016/j.jhydrol.2018.04.065
43
Zhao F, Feng J, Zhao J, Yang W, Yan S (2018) Robust LSTM-autoencoders for face de-occlusion in the wild. IEEE Trans Image Process 27:778-790. doi:10.1109/TIP.2017.2771408
10.1109/TIP.2017.277140829757731
Information
  • Publisher :KOREAN SOCIETY FOR HORTICULTURAL SCIENCE
  • Publisher(Ko) :원예과학기술지
  • Journal Title :Horticultural Science and Technology
  • Journal Title(Ko) :원예과학기술지
  • Volume : 38
  • No :2
  • Pages :201-209
  • Received Date : 2019-08-03
  • Revised Date : 2019-09-21
  • Accepted Date : 2020-01-26
  • DOI :https://doi.org/10.7235/HORT.20200019
Journal Informaiton Horticultural Science and Technology Horticultural Science and Technology
Online Submission
  • scopus
  • NRF
  • KOFST
  • crossref crossmark
  • crossref cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close