Estimation of Inherent Soil Erodibility against Wind Using Genetic Algorithm in Combination with Artificial Neural Network
Subject Areas : Application of computer in water and soil issuesSayna Jafarian 1 , Ali Mohammadi Torkashvand 2 , Abbas Ahmadi 3 , Nazanin Khakipour 4 , Maryam Marashi 5
1 - Ph.D. Student, Department of Soil Science, Science and Research Branch, Islamic Azad University, Tehran, Iran.
2 - Professor, Department of Soil Science, Science and Research Branch, Islamic Azad University, Tehran, Iran.
3 - Associate Professor, Department of Soil Science, University of Tabriz, Tabriz, Iran.
4 - Assistant Professor, Department of Soil Science, Science and Research Branch, Islamic Azad University, Tehran, Iran.
5 - Assistant Professor, Department of Soil Science, Savadkooh Branch, Islamic Azad University, Savadkooh, Iran.
Keywords: soil salinity, erodibility, modeling, EF, SIWE.,
Abstract :
Background and aim: inherent soil erodibility against wind (SIWE) is the inherent sensitivity of soil constituent particles against uprooting and transport, against erosion. Measuring the inherent erodibility of soil against wind can be done by a wind tunnel device, which is generally expensive, difficult and time-consuming. On the other hand, this feature has significant temporal and spatial changes and depends on the measurement method. Estimating SIWE by artificial intelligence tools can be an important step in planning areas under wind erosion. In this research, the estimation of this index was investigated with the help of genetic algorithm model in combination with artificial neural network. Methods: Seventy two samples were taken from 10 cm of the soil surface in the studied area, which is a part of Allah Abad desert in Qazvin province, adjacent to Alborz province. In the samples, the soil wind erodibility (EF) index, which is the percentage of soil aggregates with a diameter smaller than 0.84 mm, was measured. Also, soil texture (percentage of clay, sand and silt), pH, EC and equivalent calcium carbonate (CCE) were measured. After air-drying, the soil samples taken from the field were passed through a 4.75 mm sieve and poured flat on the tray of the wind tunnel machine. Then, the wind tunnel device created a wind with a constant speed of 18 meters per second for 10 minutes. Using the weight of sediments collected at the end of the tunnel after the test, SIWE was determined. The genetic algorithm model in combination with the artificial neural network was prepared and analyzed according to the Levenberg-Marquardt educational algorithm according to the variables having positive correlation with SIWE as the input of the model. Results: The pH value of the soil varied between 7.00 and 8.81. Electrical conductivity values varied from 0.84 to 49.3 dS/m. The data of the soil texture components show a higher amount of clay compared to the silt and sand in the soils. The minimum lime (CCE) in the soil was 3.15% and the maximum was 30.52%. The inherent erodibility of soil against wind had a significant correlation with only two variables, electrical conductivity and EF. Hybrid genetic algorithm model was prepared with artificial neural network with two input variables EF and EC. The accuracy and precision of the model showed that the value of R2 in the data of the training series was 9% different from test series data and the error value (RMSE) was 1.62 kg s m-4. Conclusion: In the data of the training series, R2 of the results obtained from the model (0.805) was higher than the data of the results obtained from the test series (0.714). Although the training data had more R2, therefore, the error (RMSE) of the training data was higher than the test and in the test series, the model with dispersion (GSDER) was less. Comparing the error, precision and accuracy of the model in estimating the inherent erodibility of the soil against the wind in comparison with different studies of soil erosion and soil physicochemical properties, the integrated model of the genetic algorithm and the neural network of almost appropriate accuracy and precision in predicting and estimating the erosion. The soil has inherent flexibility against the wind.
Abdollahzadeh, A., Mukhlisin, M., & El Shafie, A. (2011). Predict soil erosion with artificial neural network in Tanakami (Japan). WSEAS Transactions on Computers, 10 (2): 51–60.
Ahmadi, A., Neyshabouri, M. R., Rouhipour, H., & Asadi, H. (2011) Fractal dimension of soil aggregates as an index of soil erodibility. J Hydrol 400 (3-4), 305-311.
Aytek A, & Kisi, O. (2008). A genetic programming approach to suspended sediment modeling. Journal of Hydrology, 351: 288-298.
Besalatpour, A. A., Ayoubi, S., Hajabbasi, M. A., Mosaddeghi, M. R., & Schulin, R. (2013). Estimating wet soil aggregate stability from easily available properties in a highly mountainous watershed. Catena, 111: 72-79.
Black, J. M. W. & Chanasyk, D. S. (1989). The wind erodibility of some Alberta soils after seeding: aggregation in addition to field parameter. Canadian Journal of Soil Science 69: 835-875.
Chahar Azar, F., Chahar Azar, Y., & Javad Amiri, M. (2019). The Role of aerosol on Human Health and the Environment, International Dust Conference on Southwest Asia, 23-25 April 2019, University of Zabol, Zabol, Iran. In Persian.
Chandler, D. G. (2005). Predicting wind erodibility of loessial soils in the Pacific Northwest by particle sizing. Arid Land Res Manag 19: 13-27.
Chepil, W. (1958). Soil conditions that influence wind erosion. USDATech, Bui, No, 1185.
Chepil, W. (1960). Conservation of relative field erodibility to annual soil loss by wind. Soil Sci Soc Am J 24(2):143-148.
Colazo, J. C., & Buschiazzo, D. E. (2010). Soil dry aggregate stability and wind erodible fraction in a semiarid environment of Argentina. Geoderma, 159 (1-2): 228-236.
Gholami, H., Mohammadifar, A., Golzari, S., Kaskaoutis, D. G., & Collins, A. L., (2021). Using the Boruta algorithm and deep learning models for mapping land susceptibility to atmospheric dust emissions in Iran. Aeolian Res. 50, 100682.
Goldberg, D. E. (1989). Genetic algorithm in search, optimization and machine learning. Addison Wesley, Reading, MA, 412p.
Hosseini, M., Hemmati, M., & Yasi, M. (2023). 'Predicting River Suspended Load Using Artificial Neural Network and Non-Dominant Genetic Sorting Algorithm', Applied Soil Research, 10(4), pp. 45-60.
Jain, A. & Srinivasulu, S. (2004). Development of effective and efficient rainfall-runoff models using integration of deterministic, real-coded genetic algorithms and artificial neural network techniques. Water and resource research, 40(4), W04302.
Khanbabakhani E., Mohammadi Torkashvand A., & Mahmoodi M. A., (2020). The possibility of preparing soil texture class map by artificial neural networks, inverse distance weighting, and geostatistical methods in Gavoshan dam basin, Kurdistan. Arabian J Geosci 13 (5), 1-14
Klute, A. (1986). Methods of Soil Analysis: Part 1. Physical and Mineralogical Methods (Sssa Book Series No 5) 2nd Edition, Am Soc Agron Soil Sci Soc Am, Madison, WI.
Kokelj S. V., Lantz T. C., Solomon S., Pisaric M. F. J., Keith D., Morse P., Thienpont J. R., Smol J. P., & Esagok D. (2012). Using multiple sources of knowledge to investigate northern environmental change: regional ecological impacts of a storm surge in the outer Mackenzie delta, N.W.T. Arctic, 65(3): 257 – 272.
Kouchami-Sardoo, I., Shirani, H., Esfandiarpour-Boroujeni, I., & Besalatpour, A. A. (2020). Development and application of two hybrid metaheuristic algorithms to identify the most important parameters influencing wind erosion. Journal of Arid Biome, 10(1), pp. 31-45. doi: 10.29252/aridbiom.2021.1997
Li, H., Zhu, L., Dai, Z., Gong, H., Guo, T., Guo, G., Wang, J., & Teatini, P., (2021). Spatiotemporal modeling of land subsidence using a geographically weighted deep learning method based on PS-InSAR. Sci. Total Environ. 799, 149244.
Lyles, L. & Tatarko, J. 1986. Wind erosion effects on soil texture and organic matter. Journal of Soil and Water Conservation 41: 191-194.
Lyles, L., Disrud, L. A. & Woodruff, N. P. (1969). Effects of soil physical properties, rainfall characteristics, and wind velocity on clod disintegration by simulated rainfall. SSSA Proc, 33(2): 302-306.
Marashi, M., Mohammadi Torkashvand, A., Ahmadi, A., & Esfandiari, M. (2017). Estimation of soil aggregate stability indices using artificial neural network and multiple linear regression models. Spanish J Soil Sci 7(2): 89-99.
Marashi, M., Mohammadi Torkashvand, A., Ahmadi, A., & Esfandiari, M. (2019). Adaptive neuro-fuzzy inference system: estimation of soil aggregates stability. Acta Ecol Sinica. 39(1):95-101.
Menhaj, M. (2001). Artificial neural network training. Sharif University of Technology Press, Tehran, Iran.
Merrill, S. D., Black, A. L., & Halvorson, A. (1997). Soil-inherent wind erodibility: Progress and prospects; Paper presented at the Proceedings Wind Erosion: An International Symposium/Workshop.
Mohammadi Torkashvand A., Nikkami, D. (2008). Investigating some methodologies of preparing erosion features map by using RS and GIS. Int J Sediment Res 23 (2): 124-132.
Mohammadi Torkashvand, A., Haghighat, N. (2009). Investigation of some models derived from data layers integration in geographic information system with slope layer for providing water-soil erosion types maps. Res J Environ Sci 3 (2), 202-209.
Mokhtari, P., Ayoubi, S. H., Honarju, N., & Jalalian, A. (2011). Predicting soil organic matter by artificial neural network in landscape scale using remotely sensed data and topographic attributes. Geophys Res Abs 13: 10-75.
Moradi, G, & Aprajunqani, A. (2019) Investigating the Origin of aerosol and their Impacts on Air Pollution, International Dust Conference on Southwest Asia, 23-25 April 2019, University of Zabol, Zabol, Iran. In Persian.
Munns, R. (2003). Comparative physiology of salt and water stress. Plant Cell Environ 25: 239-50.
Munson, SM, Belnap, J, Okin, SG (2011). Responses of wind erosion to climate-induced vegetation changes on the Colorado Plateau. Proceedings of the National Academy of Sciences of the United States of America, 108(10): 3854–3859.
Nasseh, S., Mohebbi, A., Sarrafi, A., & Taheri, M. (2009). Estimation of pressure drop in venturi scrubbers based on annular two-phase flow model, artificial neural networks and genetic algorithm. J Chem Engin 150: 1. 131-138.
Nelson, D. W., & Sommers, L. E. (1982). Total carbon, organic carbon, and organic matter: 539-579, In: Page AL (ed.) Methods of Soil Analysis. Part 2. 2nd ed. American Society of Agronomy, Madison,WI .
Nosrati, H., Eftekhari, M. (2014). A new approach for variable selection using fuzzy logic. Computational Intelligence in Electrical Engineering, 4, 71 -83.
Nouri, A., Esfandiari, M., Eftekhari, E., Mohammadi Torkashvand, A., & Ahmadi, A. (2023). Development support vector machine, artificial neural network and artificial neural network – genetic algorithm hybrid models for estimating erodible fraction of soil to wind erosion. International Journal of River Basin Management. https://doi.org/10.1080/15715124.2022.2153856
Ostovari, Y., Ghorbani-Dashtaki, S., Bahrami, H. A., Naderi, M., Dematte, J. A. M., & Kerry, R. (2016). Modification of the USLE K factor for soil erodibility assessment on calcareous soils in Iran. Geomorphology, 273, 385–395.
Qorbanian, R. (2016). Development of Pedotransfer functions for estimation of soil inherent wind erodibility (A case study: Dash-e –Tabriz). University of Tabriz.
Rajabi Agereh, S., Kiani, F., Khavazi, K., Rouhipour, H., & Khormali, F., (2019). An environmentally friendly soil improvement technology for sand and dust storms control. Environ. Health Eng. Manag. J. 6 (1), 63–71.
Sarani, A., & Rahdari, S. (2019). Aerosol on Agricultural Performance and Extension Activities. International Dust Conference on Southwest Asia, 23-25 April 2019, University of Zabol, Zabol, Iran.
Sarkar, T., & Mishra, M. (2018). Soil erosion susceptibility mapping with the application of logistic regression and artificial neural network. J Geovisual Spatial Anal 2: 1-17.
Saxton, K., Chandler, D., Stetler, L., Lamb, B., Claiborn, C. & Lee, B. H. (2000). Wind erosion and fugitive dust fluxes on agricultural lands in the Pacific Northwest. Transactions of the ASAE, 43: 623-630.
Shahkoui, A., & Rahmani, T. (2018). Climatic Survey of aerosol at Northwest of Iran, Second National Meteorological Conference of Iran, 9th May 2018, Ferdowsi University of Mashhad, Mashhad, Iran.
Song, Y., Liu, L., Yan, P., & Cao, T. (2005). A review of soil erodibility in water and wind erosion research. J Geograph Sci 15, 167-176.
Taghizadeh Mehrjerdi, R., Sarmadian, F., Savaghebi, G., Mahmoodian, A., Tmonanian, N., Roosta, M. J., & Rahimian, MH. (2013). The comparison of Neuro-fuzzy, Genetic Algorithm, Neural Network, and Multivariate Regression methods in anticipation of soil salinity (case study: Ardakan city). Pasture Watershed Manag (Natural Resources of Iran). 66(2):207-222.
Tanasan, M. (2013). Designing spatial optimization land use model using multi-objective genetic algorithm whit land use planning approach, MSc Thesis, Department of Remote Sensing and GIS, Shahid Beheshti University, (In Persian).
Tietje, O., and V. Hennings. 1996. Accuracy of the saturated hydraulic conductivity prediction by pedo-transfer functions compared to the variability within FAO textural classes. Geoderma 69, 71–84.
Vaezi, A. R., Sadeghi, S. H., Bahrami H.A., & Mahdian, M. (2008). Modeling the USLE K-factor for calcareous soils in northwestern Iran. Geomorphology 97, 414–423.
Young, R.A., & Muchler, C.K. (1977). Erodibility of some Minesota Soils. Journal of Soil and Water Conservation 32: 180-182.
Zhao H. L., Yi, X. Y., Zhou, R. L., Zhao, X. Y., Zhang, T. H., & Drake, S. (2006). Wind erosion and sand accumulation effects on soil properties in Horqin Sandy Farmland, Inner Mongolia. Catena, 65: 71-79.