Integrated Watershed Management

Integrated Watershed Management

Evaluation of Artificial Neural Network and regression models in prediction of soil organic carbon (Case study: The Pakal Catchment, Markazi province)

Document Type : Original Article

Authors
Amir Moradinejad 1
Saied Khosrobeig 2
1 Assist. Prof., Soil Conservation and Watershed Management Research Department, Markazi Agricultural and Natural Resources Research and Education Center, Arak, Agricultural Research Education & Extention Organization (AREEO). Iran
2 PhD in Watershed Management and Head of Technical and Engineering Department of the General Department of Natural Resources of Markazi Province, Iran
10.22034/iwm.2022.1972720.1050
Abstract
Extended Abstract
Introduction: Organic carbon is one of the most important components of soil ecosystems, and changes in its amount and composition have fundamental effects on the processes that occur in each system. Soil is a source for carbon storage and deposition in connection with the atmosphere. Since pastures have a great capacity for carbon sequestration and are broad in arid and semi-arid areas of Iran, the study of organic carbon content and spatial changes in these ecosystems are important. In developing countries such as Iran, which are facing a soil erosion crisis, this issue can lead to the creation of a solution that aims at soil conservation, optimal utilization of land, as well as reforming and reviving destroyed pastures. Considering the role of organic carbon in soil management and stability, preventing soil erosion, monitoring the amount of carbon dioxide in the air, and predicting soil organic carbon on a regional, national and global scale are of particular importance.
Materials and methods: The study area of this project is the Pakel catchment from the sub-basins of the Qara Chai River. This catchment is located in the southwest of Shazand city, at a distance of 43 kilometers from the city of Arak. Random-systematic sampling was done in 60 points from the soil depth of 0-30 cm. Soil properties such as apparent specific gravity by cylinder method, pH and EC were measured after the preparation of saturated soil. Organic matter were measured using cold method based on oxidation of organic carbon. Then, soil properties were used to model soil organic carbon. For this purpose, statistical regression and artificial neural network were used.
Discussion and results: The amount of organic carbon in the soil is affected by the physical and chemical properties of the soil. It is therefore necessary to use calculation methods with optimal accuracy in estimating this complex and important parameter. It is possible to compare different models using RMSE, R2 and CE indices. Paying attention to the index values ​​shows the relative advantage of the models. The general results of the research show that in natural areas where the problem of sampling and the costs of their analysis are at a high level, it is possible to use artificial intelligence methods with the help of data to estimate soil organic carbon. It is expected that in future studies, in order to create a more reliable model that predicts more variability of the amount of soil organic carbon, denser sampling and integration of physiographic and soil variables affecting organic carbon will lead to satisfactory results. Due to the complexity of soil organic carbon relationships and soil physical and chemical properties, it is better to ignore complex analyses that include various coefficients for adjusting the mathematical formulas of models and use artificial intelligence methods which have high flexibility.
Conclusion: The results showed that the artificial neural network with RMSE=0.043 and CE=0.87 compared to the regression model with RMSE=0.08 and CE=0.51 is better in estimating organic carbon. The comparison between the regression and neural network models showed that the values ​​estimated by the neural network are more accurate than the regression method. It is suggested to carry out periodic carbon deposition monitoring studies in the study area in order to check the temporal changes of carbon deposition in the intended land uses.
Keywords
soil characteristics
modeling
efficiency coefficient
soil carbon

Subjects

Agharaz, H. (2018). Biomechanical Operation effect on soil carbon of Pakal Basin, Markazi Province. Journal of Watershed Engineering and Management. 10(4), 529-536.
Allison, L.E. (1975). Organic carbon. In: Black CA, Evans DD, White JL, Ensminger LE, Clark FE. (Eds.), Methods of soil analysis, Part 2, Chemical and microbiological properties. American Society of Agronomy, Madison. 1367p.
Auobi, S. & Alizadeh, M. (2006). Soil surface attributes prediction using digital topographic model (Case Study: part of Mehr Watershed, Sabzevar, and Khorasan Province). Science and Technology of Agriculture and Natural Resources, 10(2), 85-96.
Baiat varkesh, M., Zare abiane, H., Marofi, S., Sabziparvar, A. & Soltani, F. (2009). Simulates daily crop reference evapotranspiration using artificial intelligence methods and compared with experimental measurements of having cold semi arid climate, Hamedan. J SOIL WATER CONSERV. 16(4), 79-83.
Bird, S.B., Herrick, J.E., Wander, M.M., & Wright, S.F. (2013). Spatial heterogeneity of aggregate stability and soil carbon in semi-arid rangeland. Environ. P0ll, 116(3), 445-455.‏
Blake, G.R. & Hartge, K.H. (1986). Bulk density Methods of Soil Analysis, Physical & Mineralogical Methods. Soil Science Society of America Journal, 9(1), 361-376.
Broge, N.H., Greve, M.H. & Larsen, R. (2005). Estimating topsoil organic matter content in two experimental fields in Denmark using multi-spectral aerial imagery and topographic data. Geografisk Tidsskrift, D, J, G. 105(2), 1-14.     
Chen, S., Arrouays, D., Angers, D.A., Chenu, C., Barré, P., Martin, M.P., Saby, N.P. & Walter, C. (2019). National estimation of soil organic carbon storage potential for arable soils: A data-driven approach coupled with carbon-landscape zones. Science of the Total Environment, 666, 355-367.
Crowther Thomas, W., Mark, A. & Bradford, A. (2013). Thermal acclimation in widespread heterotrophic soil microbes. ECOL LETT, 16.4, 469-477.‏
Eskandari, Sh., Nabiollahi, K., & Taghizadeh-Mehrjardi, R. (2018). Digital Mapping of Soil Organic Carbon (Case Study: Marivan, Kurdistan Province). Journal of Water and Soil. 2-4, 737-750 (In Persian)
Follett, R.F., Samson-Liebig, E., Kimble, J.M., Pruessner, E.G. & Waltman, S. (2001). Carbon sequestration under CRP in the historic grassland soils of the USA. SSSA Special Publication, 57, 27-40.‏
Gee, G.W. & Bauder, J.W. (1986). Particle size analysis. 383-411p, In: Methods of soil analysis. Part 2nd ed. Klute, A. (Ed). Agron. Monogr. 9. ASA. Madison. WI.
Hengl, T., Huvelink, G.B.M., & Stein, A. (2004). A genericframework for spatial prediction of soil variables based on regression-kriging. Geoderma, 120(1–2), 75–93.
Hernandez, R., Koohafkan, P. & Antoine, J. (2004). Assessing Carbon Stocks and modeling win-win Scenarios of carbon sequestration throughland-use change, 166 pp.
Holmberg, M., Forsius, M., Starr, M., & Huttunen, M. (2006). An application of artificial neural networks to carbon, nitrogen and phosphorus concentration in three boreal streams and impacts of climate change. International Society for Ecological Information 3rd Conference. Grottaferrata, Roma, ITALIE. 195, 51-60.
Ingleby, H.R., & Crowe, T.G. (2001). Neural network models for predicting organic matter content in Saskatchewan soils. Can, Biosyst, Eng. 43, 71-75.
Karkaj, A., Sepehri, E., Barani, H. & Motamedi, J. (2017). The relationship between soil organic carbon storage and some soil properties in East Azarbaijan rangelands. Rangeland Scientific Journal 2, 125-138. (In Persian).
Khamoshi, S.E., Sarmadian, F.S., Mousavi, R. & Rahmani, A. (2019). Organic soil carbon mapping using random forest model. In: 16th Iranian Soil Science Congress, University of Zanjan, Iran, 1-6. (In Persian).
Khordehbin, S., Hojatia, S., Landi A. & Ahmadianfar, I. (2020). Comparison of different data mining methods in predicting soil organic carbon storage in some lands of Behbahan city. Iranian Journal of Soil and Water Research, 4(51), 1041-1054. (In Persian).
Mahmoudzadeh, H., Matinfar, H.R., Taghizadeh-Mehrjardi, R., & Kerry, R. (2020). Spatial prediction of soil organic carbon using machine learning techniques in western Iran. Geoderma Regional.
Mahmoudzadeh, H., Metinfar, H. & Taghizadeh Mehrjardi, R. (2020). Digitization of soil organic carbon with artificial neural network and multivariable linear regression in Kurdistan province. Journal of soil management and sustainable production, 10(4), 77-98. (In Persian).
Matinfar, H.R., Mahmodzadeh, H. & Fariabi, A. (2018). Estimation soil organic matter (SOM) content using visible and near infrared spectral data, PLSR and PCR statistical models. Iranian Remote Sensing & GIS, 10(2), 15-32. (In Persian).
Menhaj, M.B. (1998). Fundamentals of neuralnetworks. First Edition, Professor Hesabi Publishers, 502 pp.
Merdun, H., Ozer, T., Meral, R. & Apan, M. (2006). Comparison of artificial neural network and regression pedotransfer functions for prediction of soil water retention and saturated hydraulic conductivity. Soil and Tillage Research, 90, 108-116.
Moghaddamnia, A., Ghafari Gousheh, M., Piri, J., Amin, S. & Han, D. (2009). Evaporation estimation using artificial neural networks and adaptive neuro fuzzy inference system techniques.  Adv Water Resour, 32, 89-97.
Navabian, M., Liaghat, A.M. & Homaee, M. (2007). Comparison of transfer functions of artificial neural network and regression in estimating the saturated hydraulic conductivity. Proceedings of the Tenth Soil Science Congress of Iran, Karaj, Pp. 189-204.
Norani, V. & Salehi, K. (2008). Rainfall-runoff modeling using adaptive fuzzy neural network and comparison with neural network and fuzzy inference. National Congress on Civil Engineering, Tehran University. Proceedings of the Fourth NationalCongress of Civil Engineering. Proceedings of the Tenth Soil Science Congress of Iran, Karaj, Pp. 967-969.
Pahlavan-Rad, M.R., Dahmardeh, K., & Brungard, C. (2018). Predicting soil organic carbon concentrations in a low relief landscape, eastern Iran. Geoderma Regional 15, e00195.
Parasurman, K, Elshorbagy, A. & Si, B. (2006). Estimating saturated hydraulic conductivity in spatially variable fields using neural network in Ensembles. Soil Science Society of America Journal, 70, 1851-1859.
Parsafar, N. A. & Marofi, S. (2011). Estimated temperatures at depths using network neural network - Fuzzy (Case Study: Kermanshah region). Journal of Soil and Water Sci. 21(3), 21-22. (in Persian).
Pilevari, A., Auobi, S.h. & Khademi, H. (2010). Comparison of artificial neural network and multiple linear regression analysis to predict soil organic carbon data to the ground. Journal of Soil and Water Conservation, 24(6), 1151-1163.
Raei, B., Ahmadi, A., Neyshaburi, M.R., Ghorbani, M.A., & Asadzadeh, F. (2020). Journal of water and soil research in Iran, 51(1), 61-76. DOI: 0.22059/ijswr. 2019. 283359. 668233
Schaap, M.G. & Bouten, W. (1996). Modeling water retention curves of sandy soil using neural networks. WATER RESOUR RES, 32, 3033-3040.
Somarathna, P.D.S.N., Minasny, B. & Malone, B.P. (2017). More data or a better model? Figuring out what matters most for the spatial prediction of soil carbon. Soil Science Society of America Journal, 81(6), 1413-1426.
Sumfleth, K., & Duttmann, R. (2008). Prediction of soil property distribution in paddy soil landscapes using terrain data and satellite information as indicators. ECOL, INDIC, 8,  485 – 501.
Taghizadeh-Mehrjardi, R., Neupane, R., Sood, K. & Kumar, S. (2017). Artificial bee colony feature selection algorithm combined with machine learning algorithms to predict vertical and lateral distribution of soil organic matter in South Dakota, USA. Carbon Management, 8-3, 277-291.
Thompson, J.A. & Kolka, R.K. (2005). Soil carbon storage estimation in a forested watershed using quantities soil - landscape modeling. Soil Science Society of America Journal, 69, 1086–1093.
Wang, B., Waters, C., Orgill, S., Cowie, A., Clark, A., Liu, D.L., Simpson, M., McGowen, I. & Sides, T. (2018). Estimating soil organic carbon stocks using different modelling techniques in the semi-arid rangelands of eastern Australia. Ecological Indicators, 88, 425-438.
Zeraatpisheh, M., Ayoubi, S., Jafari, A., Tajik, S. & Finke, P. (2019). Digital mapping of soil properties using multiple machine learning in a semi-arid region, central Iran. Geoderma, 338, 445-452.
Zhang, H., P. Wu., Yin, A., Yang, X., Zhang, M. & Gao, C. (2017). Prediction of soil organic carbon in an intensively managed reclamation zone of eastern China: A comparison of multiple linear regressions and the random forest model. Science of the Total Environment 592, 704-713.
Integrated Watershed Management
Volume 2, Issue 3 - Serial Number 5
Autumn 2022
Pages 95-110

  • Receive Date 15 November 2022
  • Revise Date 10 December 2022
  • Accept Date 18 December 2022