Prediction of Wind Erosion Threshold Velocity Using Portable Wind Tunnel Combined with Machine Learning Algorithms

Document Type : Research Paper

Authors

1 Department of Soil Science and Engineering, College of Agriculture, Shiraz University, Shiraz, Iran

2 Department of Soil Science and Engineering. College of Agriculture. Shiraz University.Shiraz.Iran

3 Department of Computer Science and Information Technology, Faculty of Engineering, Hormozgan University, Bandar abbas, Iran

Abstract

Wind erosion is a key process in land degradation worldwide, especially in arid and semi-arid regions of Iran. This phenomenon is affected by many soil characteristics. The main objective of this study was to estimate the wind erosion threshold velocity using easily measurable soil characteristics along with data mining methods. For this purpose, wind erosion threshold velocity was measured in 100 areas in Fars province using a portable wind tunnel. Wind erosion threshold velocity was predicted by a support vector regression algorithm using easily measurable soil properties. In this regard, a genetic algorithm was used in order to obtain a set of parameters effective in estimating wind erosion threshold velocity. The results showed that the characteristics of soil moisture (r = 0.77), the size distribution of soil particles including the mean weight diameter of aggregate (r = 0.87) and the wind-erodible fraction of soils (r = -0.81), penetration resistance (r = 0.75), and organic matter (r = 0.33) have a high and significant correlation with wind erosion threshold velocity and play a key role in determining the threshold velocity of wind erosion in the region. According to the evaluation criteria, the combined support vector regression model with the genetic algorithm had the best performance and the most accurate estimate for wind erosion threshold velocity (RMSE = 0.53 and R2 = 0.92) and can be a promising method for estimation of wind erosion threshold velocity.

Keywords

Main Subjects


Prediction of Wind Erosion Threshold Velocity Using Portable Wind Tunnel Combined with Machine Learning Algorithms

EXTENDED ABSTRACT

 

Introduction

Wind erosion is a key process in land degradation worldwide, especially in arid and semi-arid regions. This phenomenon is affected by many soil characteristics. The main objective of the present study was to estimate the wind erosion threshold velocity using easily measurable soil characteristics along with data mining methods. Therefore, the present study aimed 1) to measure the wind erosion threshold velocity by extensive wind tunnel tests; 2) to predict the wind erosion threshold velocity using machine learning algorithms; 3) to determine features affecting the wind erosion threshold velocity using genetic algorithm coupled with machine learning algorithms in the prediction of wind erosion threshold velocity.

 

Materials and Methods

For this purpose, wind erosion threshold velocity was measured in 100 areas in Fars province using a portable wind tunnel. Fars province is located in the southwest region of Iran. Due to the climate conditions, wind erosion occurs in most parts of Fars province. Thirty critical sources of wind erosion with an area of 123,500 ha have been identified in Fars province. Therefore, investigation of the wind erosion threshold velocity in Fras province is vital for guiding the decision-makers to implement conservative practices against wind erosion. Wind erosion threshold velocity was predicted by a support vector regression algorithm using easily measurable soil properties. In this regard, a genetic algorithm was used in order to obtain a set of influential parameters in estimating wind erosion threshold velocity. In this study, the algorithms were provided in MATLAB 2019 programming software packages.

 

Results and Discussion

The results showed that with respect to sand, silt, and clay content, there are a variety of different soil textures according to USDA classification in the study area. The majority of soils had a medium texture class. The results showed that the characteristics of soil moisture (r = 0.77), the size distribution of soil particles including the mean weight diameter of aggregates (r = 0.87) and the wind-erodible fraction of soils (r = -0.81), penetration resistance (r = 0.75), and organic matter (r = 0.33) have a high and significant correlation with wind erosion threshold velocity and play a key role in determining the threshold velocity of wind erosion in the region. According to the evaluation criteria, the combined support vector regression model with the genetic algorithm had the best performance and the most accurate estimate for wind erosion threshold velocity (RMSE = 0.53 and R2 = 0.92) and can be a promising method for the estimation of wind erosion threshold velocity.

Conclusion

The threshold velocity of wind erosion is a very important parameter for studying soil wind erosion potential in arid and semi-arid regions. Therefore, this study was conducted to determine the threshold velocity of wind erosion using a portable wind tunnel and to predict the threshold velocity of wind erosion using easily measurable soil properties with support vector regression. The results of this study can be helpful in efficiently assessing vast areas prone to wind erosion and dust emission and can help policymakers to prioritize regions for soil conservation practices. The latter is very important for developing countries where only a limited budget is available for soil conservation programmers. In addition, portable wind tunnel is not always available for wind erosion studies, such fast and easy-to-apply methods introduced in this study can be a good alternative for wind erosion monitoring without disturbing the soil. We suggest that using other data mining approaches (e.g., random forest and artificial neural networks) for predicting the threshold velocity of wind erosion in future studies.

Azimzadeh, H. R., Derakhshan, Z., & Shirgahi, F. (2022). Field scale spatio-temporal variability of wind erosion transport capacity and soil loss at Urmia Lake. Environmental Research, 215, 114250.
Besalatpour, A. A., Shirani, H., & Esfandiarpour Borujeni, I. (2015). Modeling of soil aggregate stability using support vector machines and multiple linear regression. Water and Soil, 29(2), 406-417. (In Persian).
Borrelli, P., Ballabio, C., Panagos, P., & Montanarella, L. (2014). Wind erosion susceptibility of European soils. Geoderma, 232, 471-478.
Chappell, A., Webb, N. P., Guerschman, J. P., Thomas, D. T., Mata, G., Handcock, R. N., ... & Butler, H. J. (2018). Improving ground cover monitoring for wind erosion assessment using MODIS BRDF parameters. Remote Sensing of Environment, 204, 756-768.
Chen, W., Zhibao, D., Zhenshan, L., & Zuotao, Y. (1996). Wind tunnel test of the influence of moisture on the erodibility of loessial sandy loam soils by wind. Journal of Arid Environments, 34(4), 391-402.
Chepil, W. S., & Woodruff, N. P. (1954). Estimations of wind erodibility of field surfaces. Journal of Soil and Water Conservation, 9, 257-265.
Ciric, V., Manojlovic, M., Nesic, L., & Belic, M. (2012). Soil dry aggregate size distribution: effects of soil type and land use. Journal of Soil Science and Plant Nutrition, 12(4), 689-703.
Gholami, H., & Mohammadifar, A. (2022). Novel deep learning hybrid models (CNN-GRU and DLDL-RF) for the susceptibility classification of dust sources in the Middle East: a global source. Scientific Reports, 12(1), 1-12.
Han, Q., Qu, J., Zhang, K., Zu, R., Niu, Q., & Liao, K. (2009). Wind tunnel investigation of the influence of surface moisture content on the entrainment and erosion of beach sand by wind using sands from tropical humid coastal southern China. Geomorphology, 104(3-4), 230-237.
Hoogsteen, M. J. J., Lantinga, E. A., Bakker, E. J., & Tittonell, P. A. (2018). An evaluation of the loss-on-ignition method for determining the soil organic matter content of calcareous soils. Communications in Soil Science and Plant Analysis, 49(13), 1541-1552.
Jahanbazi, L., Jafarzadeh, A. A., & Forughyfar, H. (2016). Relation between soil evolution and landforms diversity in Dasht-E-Tabriz. Journal of Agriculture Science, 26(2), 191-204. (In Persian).
Kaewmano, C., Kheoruenromne, I., Suddhiprakarn, A., & Gilkes, R. J. (2010, August). Chemistry and clay mineralogy of Thai Natraqualfs. In 19th World Congress of Soil Science, Soil Solutions for a Changing World (pp. 1-6).
Kemper, W. D., & Rosenau, R. C. (1986). Aggregate stability and size distribution. Methods of soil analysis: Part 1 Physical and mineralogical methods, 5, 425-442.
Kheirabadi, H., Mahmoodabadi, M., Jalali, V., & Naghavi, H. (2018). Sediment flux, wind erosion and net erosion influenced by soil bed length, wind velocity and aggregate size distribution. Geoderma, 323, 22-30.
Kouchami-Sardoo, I., Shirani, H., Esfandiarpour-Boroujeni, I., Álvaro-Fuentes, J., & Shekofteh, H. (2019). Optimal feature selection for prediction of wind erosion threshold friction velocity using a modified evolution algorithm. Geoderma, 354, 113873.
Kouchami-Sardoo, I., Shirani, H., Esfandiarpour-Boroujeni, I., Besalatpour, A. A., & Hajabbasi, M. A. (2020). Prediction of soil wind erodibility using a hybrid Genetic algorithm–Artificial neural network method. Catena, 187, 104315.
Lamorski, K., Pastuszka, T., Krzyszczak, J., Sławiński, C., & Witkowska-Walczak, B. (2013). Soil water dynamic modeling using the physical and support vector machine methods. Vadose Zone Journal, 12(4), 1-12.
Leys, J., Koen, T., & McTainsh, G. (1996). The effect of dry aggregation and percentage clay on sediment flux as measured by a portable field wind tunnel. Soil Research, 34(6), 849-861.
Li, J., Flagg, C., Okin, G. S., Painter, T. H., Dintwe, K., & Belnap, J. (2015). On the prediction of threshold friction velocity of wind erosion using soil reflectance spectroscopy. Aeolian Research, 19, 129-136.
Liao, K., Xu, S., Wu, J., Zhu, Q., & An, L. (2014). Using support vector machines to predict cation exchange capacity of different soil horizons in Qingdao City, China. Journal of Plant Nutrition and Soil Science, 177(5), 775-782.
Liu, L. Y., Li, X. Y., Shi, P. J., Gao, S. Y., Wang, J. H., Ta, W. Q., ... & Xiao, B. L. (2007). Wind erodibility of major soils in the farming-pastoral ecotone of China. Journal of Arid Environments, 68(4), 611-623.
Mina, M., Emami, H., & Karimi, A. (2020). Evaluation the efficiency of different mulches to combat wind erosion of sandy soil running title: Efficiency of different mulches to control wind erosion. Sustainable Earth Review, 1(1), 16-22.
Mina, M., Rezaei, M., Sameni, A., Moosavi, A. A., & Ritsema, C. (2021). Vis-NIR spectroscopy predicts threshold velocity of wind erosion in calcareous soils. Geoderma, 401, 115163.
Mina, M., Rezaei, M., Sameni, A., Ostovari, Y., & Ritsema, C. (2022). Predicting wind erosion rate using portable wind tunnel combined with machine learning algorithms in calcareous soils, southern Iran. Journal of Environmental Management, 304, 114171.
Moosavi, A. A., & Sepaskhah, A. R. (2012). Spatial variability of physico-chemical properties and hydraulic characteristics of a gravelly calcareous soil. Archives of Agronomy and Soil Science, 58, 631-656.
Moradi, F., Moosavi, A. A., & Khalili Moghaddam, B. (2016). Spatial variability of water retention parameters and saturated hydraulic conductivity in a calcareous Inceptisols (Khuzestan province of Iran) under sugarcane cropping. Archives of Agronomy and Soil Science, 62, 1686-1699.
Mozaffari, H., Moosavi, A. A., & Sepaskhah, A. (2021). Land use-dependent variation of near-saturated and saturated hydraulic properties in calcareous soils. Environmental Earth Sciences, 80(23), 769.
Mozaffari, H., Moosavi, A. A., Sepaskhah, A. R. & Cornelis, W. (2022). Long-term effects of land use type and management on sorptivity, macroscopic capillary length and water-conducting porosity of calcareous soils. Arid Land Research and Management, 36, 371-397.
Nafarzadegan, A. R., Zadeh, M. R., Kherad, M., Ahani, H., Gharehkhani, A., Karampoor, M. A., & Kousari, M. R. (2012). Drought area monitoring during the past three decades in Fars province, Iran. Quaternary International, 250, 27-36.
Narimani, Z., & Manafi, Sh. (2016). The study of physico-chemical and mineralogical properties and classification of some saline-sodic soils in the east of Urmia plain. Journal of Water and Soil Conservation (Journal of Agricultural Sciences and Natural Resources), 23(1), 65-82.
Négyesi, G., Lóki, J., Buró, B., & Szabó, S. (2016). Effect of soil parameters on the threshold wind velocity and maximum eroded mass in a dry environment. Arabian Journal of Geosciences, 9(11), 1-10.
Nelson, R. E. (1983). Carbonate and gypsum. Methods of soil analysis: Part 2 Chemical and microbiological properties, 9, 181-197
Ostovari, Y., Moosavi, A. A., & Pourghasemi, H. R. (2020). Soil loss tolerance in calcareous soils of a semiarid region: evaluation, prediction, and influential parameters. Land Degradation & Development.1-12.
Page, A. I., Miller, R. H., & Keeny, D. R. (1982). Methods of soil analysis. Part II. Chemical and microbiological methods. Amer. Soc. Agron., Madison, Wisconsin, USA.
Pásztor, L., Négyesi, G., Laborczi, A., Kovács, T., László, E., & Bihari, Z. (2016). Integrated spatial assessment of wind erosion risk in Hungary. Natural Hazards and Earth System Sciences, 16(11), 2421-2432.
Perfect, E., Kay, B. D., Ferguson, J. A., Da Silva, A. P., & Denholm, K. A. (1993). Comparison of functions for characterizing the dry aggregate size distribution of tilled soil. Soil and Tillage Research, 28(2), 123-139.
Rezaei, M., Mina, M., Ostovari, Y., & Riksen, M. J. (2022). Determination of the threshold velocity of soil wind erosion using a wind tunnel and its prediction for calcareous soils of Iran. Land Degradation & Development, 33(13), 2340-2352.
Rezaei, M., Sameni, A., Shamsi, S. R. F., & Bartholomeus, H. (2016). Remote sensing of land use/cover changes and its effect on wind erosion potential in southern Iran. PeerJ, 4, e1948.
Sanikhani, H., Dinpashoh, Y., & Ghorbani, M. A. (2015). Baranduz-Chay River Flow Modeling Using the K-Nearest Neighbor and Intelligent Methods. Water and Soil Science, 25(1), 219-233. (In Persian).
Shao, Y. (Ed.). (2008). Physics and modeling of wind erosion. Dordrecht: Springer Netherlands.
Sharratt, B. S., & Vaddella, V. (2014). Threshold friction velocity of crusted windblown soils in the Columbia Plateau. Aeolian Research, 15, 227-234.
Sirjani, E., Sameni, A., Moosavi, A. A., Mahmoodabadi, M., & Laurent, B. (2019). Portable wind tunnel experiments to study soil erosion by wind and its link to soil properties in the Fars province, Iran. Geoderma, 333, 69-80.
Twarakavi, N. K., Šimůnek, J., & Schaap, M. G. (2009). Development of pedotransfer functions for estimation of soil hydraulic parameters using support vector machines. Soil Science Society of America Journal, 73(5), 1443-1452.
Vapnik, V., Golowich, S., & Smola, A. (1996). Support vector method for function approximation, regression estimation and signal processing. Advances in neural information processing systems, 9.
Visser, S. M., Sterk, G., & Ribolzi, O. (2004). Techniques for simultaneous quantification of wind and water erosion in semi-arid regions. Journal of Arid Environments, 59(4), 699-717.
Yan, N., Marschner, P., Cao, W., Zuo, C., & Qin, W. (2015). Influence of salinity and water content on soil microorganisms. International Soil and Water Conservation Research, 3(4), 316-323.
Zahedifar, M. )2023a(. Assessing alteration of soil quality, degradation, and resistance indices under different land uses through network and factor analysis. Catena, 222, 106807-0.
Zahedifar, M. )2023b(. Feasibility of fuzzy analytical hierarchy process (FAHP) and fuzzy TOPSIS methods to assess the most sensitive soil attributes against land use change. Environmental Earth Sciences, 82, 1-17.
Zhou, T., Geng, Y., Chen, J., Pan, J., Haase, D., & Lausch, A. (2020). High-resolution digital mapping of soil organic carbon and soil total nitrogen using DEM derivatives, Sentinel-1 and Sentinel-2 data based on machine learning algorithms. Science of the Total Environment, 729, 138244.