Abstract
The research aimed to model CO2 flux from soil to atmosphere in greenhouse conditions, using multiple linear regression (MLR) artificial neural networks (ANN), and deep learning neural networks (DLNN). Following the purpose, crop species, soil temperature, soil moisture content, photosynthetic active radiation (PAR), and soil oxygen exchange were considered as input parameters and CO2 flux as an output parameter. Levenberg–Marquardt learning function and logarithmic symmetric sigmoid transfer function were utilized in both ANN and DLNN. The optimal number of hidden layer neurons was determined through empirical observation, the model which produces the least mean absolute error value was chosen in each structure. Thus, ANN utilized 8 neurons, while DLNN utilized 14 neurons in the first hidden layer and 10 neurons in the second hidden layer. According to the result, CO2 flux from soil to atmosphere was modeled using MLR with an accuracy of 95.63%, ANN with an accuracy of 95.56% and DLNN with an accuracy of 98.29%. Sensitivity analyses were conducted for both models to determine the pro rota efficiency of the input parameters on CO2 flux. In the research, it was concluded that CO2 flux from soil to atmosphere can be modeled in high accuracy, and deep artificial neural networks can have higher efficiency in similar works.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Aleboyeh A, Kasiri MB, Olya ME, Aleboyeh H (2008) Prediction of azo dye decolorization by UV/H2O2 using artificial neural networks. Dyes Pigm 77:288–294. https://doi.org/10.1016/j.dyepig.2007.05.014
Altikat S, Küçükerdem HK, Altikat A (2018) Effects of wheel traffic and farmyard manure applications on soil CO2 emission and soil oxygen content. Turk J Agric For 42:288–297. https://doi.org/10.3906/tar-1709-79
Altıkat S, Küçükerdem HK, Altikat A (2019) The Response of CO2 flux to soil warming, manure application and soil salinity. J Inst Sci Technol 9(3):1334–1342. https://doi.org/10.21597/jist.515501
Barcenas OP, Olivas ES, Guerrero JDM, Valls GC, Rodriguez JLC, Tascon SV (2005) Unbiased sensitivity analysis and pruning techniques in neural networks for surface ozone modeling. Ecol Model 182:149–158. https://doi.org/10.1016/j.ecolmodel.2004.07.015
Choab N, Allouhi A, El Maakoul A, Kousksou T, Saadeddine S, Jamil A (2019) Review on greenhouse microclimate and application: design parameters, thermalmodeling and simulation, climate controlling technologies. Sol Energy 191:109–137. https://doi.org/10.1016/j.solener.2019.08.042
Choi W, Paulson SE, Casmassi J, Winer AM (2013) Evaluating meteorological comparability in air quality studies: classification and regression trees for primary pollutants in California’s South Coast Air Basin. Atmos Environ 64:150–159. https://doi.org/10.1016/j.atmosenv
Dong S, Zhang J, Li Y, Liu S, Dong Q, Zhou H, Yeomas J, Li YV, Gao X (2020) Effect of grassland degradation on aggregate-associated soil organic carbon of alpine grassland ecosystems in the Qinghai-Tibetan Plateau. Eur J Soil Sci 71:69–79. https://doi.org/10.1111/ejss.12835
Eby M, Zickfeld K, Montenegro A, Archer D, Meissner KJ, Weaver AJ (2009) Lifetime of anthropogenic climate change: millennial time scales of potential CO2 and surface temperature perturbations. J Clim 2:2501–2511. https://doi.org/10.1175/2008JCLI2554.1
Gao X, Li W, Salman A, Wang R, Du L, Yao L, Hu Y, Guo S (2020) Impact of topsoil removal on soil CO2 emission and temperature sensitivity in Chinese Loess Plateau. Sci Total Environ 708:1035102. https://doi.org/10.1016/j.scitotenv.2019.135102
Garcia Nieto PJ, Alvarez Anton JC (2014) Nonlinear air quality modeling using multivariate adaptive regression splines in Gijón urban area (Northern Spain) at local scale. Appl Math Comput 235:50–65. https://doi.org/10.1016/j.amc.2014.02.096
Hagan MT, Demuth HB, Beale M (1996) Neural network design. PWS Publishing Co. a Division of Thomson Learning, Boston
He HL, Yu GR, Zhang LM, Sun X, Su W (2006) Simulation CO2 flux of three different ecosystem in China flux based on artificial neural network. Sci China Ser D-Earth Sci 49:252–261. https://doi.org/10.1007/s11430-006-8252-z
Ishida K, Tsujimoto G, Ercan A, Tu T, Kiyama M, Amagasaki M (2020) Hourly-scale coastal sea level modeling in a changing climate using long short-term memory neural network. Sci Total Environ 720:137613. https://doi.org/10.1016/j.scitotenv.2020.137613
Ito E, Ono K, Ito YM, Araki M (2008) A neural network approach to simple prediction of soil nitrification potential: a case study in Japanese temperate forests. Ecol Model 219:200–211. https://doi.org/10.1016/j.ecolmodel.2008.08.011
Jung DH, Kim HS, Jhin C, Kim H, Park SH (2020) Time-serial analysis of deep neural network models for prediction ofclimatic conditions inside a greenhouse. Comput Electron Agric 173:105402. https://doi.org/10.1016/j.compag.2020.105402
Lei XD, Peng CH, Tian DL, Sun JF (2007) Meta-analysis and its application in global change research. Chin Sci Bull 52:289–302. https://doi.org/10.1007/s11434-007-0046-y
Liu Z, Peng CH, Xiang WH, Tian D, Deng XW, Zhao MF (2010) Application of artificial neural networks in global climate change and ecological research: an overview. Chin Sci Bull 55:3853–3863. https://doi.org/10.1007/s11434-010-4183-3
Luesma SF, Cavero J, Bonilla DP, Martinez CC, Arrue JL, Fuentes JA (2020) Tillage and irrigation system effects on soil carbon dioxide (CO2) and methane (CH4) emissions in a maize monoculture under Mediterranean conditions. Soil Tillage Res 196:104488. https://doi.org/10.1016/j.still.2019.104488
Lv M, Li Y, Chen L, Chen T (2019) Air quality estimation by exploiting terrain features and multi-view transfer semi-supervised regression. Inf Sci 483:82–95. https://doi.org/10.1016/j.ins.2019.01.038
Matthews HD, Gillett NP, Stott PA, Zickfeld K (2009) The proportionality of global warming to cumulative carbon emissions. Nature 459:829–832. https://doi.org/10.1038/nature08047
Melesse AM, Hanley RS (2005) Artificial neural network application for multi-ecosystem carbon flux simulation. Ecol Model 189:305–314. https://doi.org/10.1016/j.ecolmodel.2005.03.014
Nagendra SMS, Khare M (2006) Artificial neural network approach for modelling nitrogen dioxide dispersion from vehicular exhaust emissions. Ecol Model 190:99–115. https://doi.org/10.1016/j.ecolmodel.2005.01.062
Pramanik P, Phukan M (2020) Enhanced microbial respiration due to carbon sequestration in pruning litter incorporated soil reduced the net carbon dioxide flux from atmosphere to tea ecosystem. J Sci Food Agric 100:295–300. https://doi.org/10.1002/jsfa.10038
Pratibha G, Srinivas I, Rao KV, Shanker AK, Raju BMK, Choudhary DK, Srinivas Rao K, Srinivasarao CH, Maheswari M (2016) Net global warming potential and greenhouse gas intensity of conventional and conservation agriculture system in rainfed semi arid tropics of India. Atmos Environ 145:239–250. https://doi.org/10.1016/j.atmosenv.2016.09.039
Rahman GKMM, Rahman MM, Alam MSA, Kamal MZ, Mashuk HA, Datta R, Meena RS (2020) Biochar and organic amendments for sustainable soil carbon and soil health. Carbon and nitrogen cycling in soil. Springer, Singapore, pp 45–85
Sainju UM, Stevens WB, CaesarTonThat T, Jabro JD (2010) Land use and management practices impact on plant biomass carbon and soil carbon dioxide emission. Soil Sci Soc Am J 74(74):1613–1622. https://doi.org/10.2136/sssaj2009.0447
Schmidt A, Creason W, Law BE (2018) Estimating regional effects of climate change and altered land use on biosphere carbon fluxes using distributed time delay neural networks with Bayesian regularized learning. Neural Netw 108:97–113. https://doi.org/10.1016/j.neunet.2018.08.004
Vaczi P (2019) Autonomous in situ measurement of daily courses of the net CO2 exchange rate in a moss from alpine environment. Czech Polar Rep 9(2):220–227. https://doi.org/10.5817/CPR2019-2-18
Viotti P, Liuti G, Genov PD (2002) Atmospheric urban pollution: applications of an artificial neural network (ANN) to the city of Perugia. Ecol Model 148:27–46. https://doi.org/10.1016/S0304-3800(01)00434-3
Wang SJ, Guan DS (2007) Remote sensing method of forest biomass estimation by artificial neural network models (in Chinese). Ecol Environ. 16:108–111. https://doi.org/10.3390/rs9030241
Wang XG, Zhu B, Gao MR, Wang YQ, Zheng XH (2008) Seasonal variations in soil respiration and temperature sensitivity under three land-use types in hilly areas of the Sichuan Basin. Aust J Soil Res 46:727–734. https://doi.org/10.1071/SR07223
Yu Q, Hu X, Ma J, Ye J, Sun W, Wang Q, Lin H (2020) Effects of long-term organic material applications on soil carbon and nitrogen fractions in paddy fields. Soil Tillage Res 196:1–7. https://doi.org/10.1016/j.still.2019.104483
Zhang L, Traore S, Ge J, Li Y, Wang S, Zhu G, Cui Y, Fipps G (2019) Using boosted tree regression and artificial neural networks to forecast upland rice yield under climate change in Sahel. Comput Electron Agric 166:105031. https://doi.org/10.1016/j.compag.2019.105031
Zhang H, Qian Z, Zhuang S (2020) Effects of soil temperature, water content, species, and fertilization on soil respiration in bamboo forest in subtropical China. Forests 11(1):99. https://doi.org/10.3390/f11010099
Acknowledgements
This research was supported by the scientific research project unit of Iğdır University. The author is thankful to the Iğdır University for providing the supports.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Editorial responsibility: Samareh Mirkia.
Rights and permissions
About this article
Cite this article
Altikat, S. Prediction of CO2 emission from greenhouse to atmosphere with artificial neural networks and deep learning neural networks. Int. J. Environ. Sci. Technol. 18, 3169–3178 (2021). https://doi.org/10.1007/s13762-020-03079-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13762-020-03079-z