Performance assessment of the artificial intelligence models for prediction of the infiltration rate in the Surface Soil of Geological Formations (Case Study: Aleshtar Watershed, Lorestan Province)

Document Type : Research/Original/Regular Article

Authors

1 PhD Student, Department of Range and Watershed Management, Faculty of Natural Resources, Lorestan University, Khorramabad, Iran

2 Associate Professor, Department of Watershed Science and Engineering, Faculty of Agriculture and Natural Resources, Lorestan University, Khorramabad, Iran

3 MSc Student, Department of Range and Watershed Management, Faculty of Natural Resources, Lorestan University, Khorramabad, Iran

Abstract

Introduction

Water repellency is a property that commonly affects the soil surface layer. It results from hydrophobic coatings on soil particles that originate from organic matter. The most significant effect of soil water repellency is a reduction in infiltration rates. The infiltration rate is one of the primary processes of the hydrological cycle. Hydrogeological and subsurface phenomena as infiltration, percolation mainly affect natural or man-made geotechnical soil. Understanding these phenomena are essential for estimation of runoff process, groundwater seepage, erosion, transport substances, evapotranspiration in surface and into groundwater are mainly influenced by precipitation. It is the property of water by which it moves through the soil particles. Infiltration process plays a fundamental role in streamflow, groundwater recharge, subsurface flow, and surface and subsurface water quality and quantity. Also, Soil infiltration is one of the key processes in design of irrigation systems, water resources management and soil protection and soil erosion control in watershed management and good knowledge of the infiltration rate is useful in calculating the natural and artificial groundwater recharge and surface runoff. Therefore, the prpose of this study was Performance assessment of the artificial intelligence models for prediction of the infiltration rate in the surface soil of geological formations in Alashtar watershed, Lorestan province, Iran.



Materials and Methods

The study area is a part of Kashkan watershed, Lorestan province, Iran. So, it was selected as a suitable watershed to Modeling of infiltration rate in different vegetation types by the various soft computing techniques. The study area located between 48°10′28″ - 48°23′29″ N latitudes and 33°45′ 17″ - 33°51′ 23″ E longitudes, and covers an area of 112.54 Km2 approximately. Elevation of watershed varies from 3613 to 1481 m a.s.l. The studied area has a cold and semiarid climate with a mean annual rainfall Less than 570 mm. Most parts of Alashtar watershed are rangeland, while forest, dry farming, and irrigation lands are in considerable quantities and The surface lithology in the Alashtar watersheds are covered by the Eocene, Quaternary, Cretaceous, Miocene, Oligocene, Paleocene, and Pliocene geologic formations. In this study, The double-ring infiltrometer was used to measure the infiltration in the surface soil of some geological formations in the study area. After determining the infiltration rate, Gaussian Process (GP), Classification And Regression Tree (CART), and Random Forest (RF), Multivariate adaptive regression splines (MARS), M5P model tree (M5P) and Reduced Error Pruning Tree(REP Tree) were used to Modeling of infiltration rate in different Surface Soil of Geological Formations. Total data set consists of some physical characteristic of soil out of which 70% data used to train the model and 30% data were used to test the models. Finally, the models’ accuracy was assessed using three statistical parameters, Root Mean Square Error (RMSE), Nash-Sutcliffe model efficiency (NSE), and Coefficient of Correlation (CC), were selected to compare the efficiency of all models. Also for rapid and reliable comparisons, we also used Taylor diagrams. The Taylor diagram displays Root Mean Square Error (RMSE), Coefficient of Correlation (CC) and standard deviation (SD) values with closer positions on the diagram indicating better model performance.



Results and Discussion

The results indicated that the surface soil of OML geological formations had a higher cumulative infiltration and average infiltration rate. In this study, Gaussian Process (GP), Classification And Regression Tree (CART), Random Forest (RF), Multivariate adaptive regression splines (MARS), M5P model tree (M5P) and Reduced Error Pruning Tree(REP Tree) were used for infiltration rate in Alashtar watershed, Lorestan province, Iran. Comparison of these models showed that the M5P model tree (M5P) and Reduced Error Pruning Tree (REP Tree) models, with the combination of time, sand, clay, silt, soil density and soil moisture, could estimate infiltration rate with much less error than the other models. The obtained results suggest that the bagging M5P model tree regression technique in training and testing phase (with CC = 0.99, RMSE = 0.009, NSH = 0.006 and CC = 0.99, RMSE = 0.009, NSH = 0.006 respectivly) is more accurate to estimate the infiltration rate as compare to the GP, CART, RF, MARS and REPTree thegiven study area. Finaly The results showed that M5P model is effective in predicting Infiltration Rate (IR) content in the surface soil of geological formations. Comparison of results suggests that there is no significant difference between conventional and soft-computing based infiltration models. The performance of the developed models was also compared using a Taylor diagram, in which an accurate model is indicated by a reference point, with a correlation coefficient of 1 having the same amplitude of variation as the observations. Thus, M5P was shown to be the most accurate model for cumulative infiltration prediction.

Conclusion

Prediction of the infiltration rate is an essential element of hydrologic design, watershed management, irrigation, and agriculture studies. This investigation identifies the optimal model for predicting Infiltration Rate (IR) using several computing approaches, such as Gaussian Process (GP), Classification And Regression Tree (CART), Random Forest (RF), Multivariate adaptive regression splines (MARS), M5P model tree (M5P) and Reduced Error Pruning Tree(REP Tree) models. In this study, 8 input variables, including time, sand, clay, silt, moisture content, soil bulk density, porosity and infiltration rate, were evaluated using three key performance metrics to assess the efficacy of various predictive models. These metrics comprised the CC, MAE, RMSE. Based on the evaluation results, the soft computing techniques model has a suitable capability to predict the infiltration rate of the soil. Finaly, the results shown that Learning algorithms can be used to quantify the amount of infiltration and also to estimate the amount of runoff in different geological formations. Also, the results shown that these models can be used to quantify the amount of infiltration and estimate the amount of runoff in the Surface Soil of Geological Formations. As well as, the results of this research can be used by the local authority to manage properly, systematically and plan development within their areas.

Keywords

Main Subjects


منابع
احمدی، حسن (1394). ژئومورفولوژی کاربردی، جلد اول: فرسایش آبی. چاپ هشتم، انتشارات دانشگاه تهران، 688 صفحه.
آوند، محمدتقی، مرادی، حمیدرضا، و رمضان‌زاده لسبوئی، مهدی (1399). تهیه نقشه حساسیت سیل با استفاده از دو مدل یادگیری ماشین جنگل تصادفی و مدل خطی تعمیم یافته بیزین. محیط زیست و مهندسی آب، 6(1)، 83-95. doi. 10.22034/jewe.2020.220593.1351
بختیاری یگانه، عباس، و حمزه ضیابری، سید محمود (1396). پیش‌بینی حرکات سواش امواج فراثقلی بر روی سواحل طبیعی با استفاده از مدل‌های درختی M5 و MARS. مهندسی امیرکبیر، 50(3)، 445-452. doi: 10.22060/ceej.2017.8712.4640
حسنوند، شکوفه، سپه‌وند، علیرضا، ترنیان، فرج الله و پروین، سیهاک (1400). ارزیابی مدل‌های نفوذ در خاک سطحی سازندهای زمین‌شناسی حوضه الشتر، استان لرستان. پژوهش‌های آبخیزداری، 34(4)، 150-164. .doi:10.22092/wmrj.2021.354035.1398
رفاهی، حسینقلی (1394). فرسایش آبی و کنترل آن. انتشارات دانشگاه تهران، چاپ هفتم، 681 صفحه.
سپه‌وند، علیرضا، طایی سمیرمی، مجید، میرنیا، خلاق و مرادی، حمیدرضا (1390). ارزیابی حساسیت مدل‌های نفوذ به تغییرپذیری رطوبت خاک. آب و خاک، 25(2)، 1-11. doi:10.22067/jsw.v0i0.9387
ستاری، محمدتقی و نهرین، فرناز (1392). پیش‌بینی مقادیر حداکثر بارش روزانه با استفاده از سیستم‌های هوشمند و مقایسة آن با مدل درختیM5؛ مطالعة موردی ایستگاه‌های اهر و جلفا. مهندسی آبیاری و آب ایران، 4(2)، 83-98.
سعیدیان، حمزه، و مرادی، حمیدرضا (1399). تعیین مهم‌ترین عامل‌های مؤثر بر نفوذپذیری خاک تشکیل شده از سازندهای گچساران و آغاجاری در کاربری‌های مختلف. پژوهش‌های آبخیزداری، 33(2)، 97-109. doi:10.22092/wmej.2019.126695.1231  
سلیمانی، لیلی، میردریکوند، بهرام، و سپه وند، علیرضا (1401). مدل‌سازی نفوذپذیری در رده‌های گوناگون بافت خاک با الگوریتم‌های یادگیری در آبخیز کشکان، استان لرستان. پژوهش‌های آبخیزداری، 35(4)، 104-116. doi:10.22092/wmrj.2022.358213.1461.
صادقی، حمیدرضا (1389). مطالعه و اندازه‌گیری فرسایش خاک. انتشارات دانشگاه تربیت مدرس، چاپ اول، 171 صفحه.
طالبی، علی، و اکبری، زینب (1392). بررسی کارایی مدل درختان تصمیم در برآورد رسوبات معلق رودخانه‌‍ای. علوم آب و خاک، 17(63)، 121-109. doi:20.1001.1.24763594.1392.17.63.10.8
ظهیری، جواد، و کاشفی پور، سیدمحمود (1397). بررسی کارآیی الگوریتم M5 در محاسبة حداکثر عمق چاله آبشستگی اطراف تکیه گاه پل. علوم مهندسی و آبیاری، 41(1 )، 1-16. doi: 10.22055/JISE.2018.13543
علیزاده، امین (1397). هیدرولوژی کاربردی. دانشگاه بین المللی امام رضا، چاپ چهل و سوم، 941 صفحه.
قربانی دشتکی، شجاع، همایی، مهدی و مهدیان، محمدحسین (1389). تأثیر تغییر کاربری اراضی بر تغییرات مکانی پارامترهای نفوذ آب به خاک. آبیاری و زهکشی ایران، 4(2)، 206-221.
قیومی محمدی، امیرمسعود، قربانی دشتکی، شجاع، رئیسی، فایز، و طهماسبی، پژمان (1392). اثر رهاسازی اراضی بر تغییرات نفوذ آب به خاک. حفاظت منابع آب و خاک، 2(4)، 41-51. doi: 20.1001.1.22517480.1392.2.4.4.9.
کاویان، عطا اله، احمدی، رضا، حبیب نژاد، محمود و جعفریان، زینب (1396). بررسی تغییرات مکانی نفوذپذیری خاک با استفاده از روش‌های تجربی و زمین‌آماری در دشت ساحلی بهشهر- گلوگاه. پژوهش‌های آب و خاک ایران، 48(1)، 177-186. doi: 10.22059/ijswr.2017.61351
کرنژادی، آیدینگ، و پورقاسمی، حمیدرضا (1398). ارزیابی حساسیت زمین لغزش با استفاده از مدل‌های داده کاوی، مطالعة موردی: حوزة آبخیز چهل چای. مهندسی و مدیریت آبخیز، 11(1)، 28-42. doi: 10.22092/ijwmse.2019.118436
مظفری، غلامعلی، شفیعی، شهاب و تقی زاده، زهرا (1394). ارزیابی کارایی مدل درخت تصمیم ‌رگرسیونی در پیش‌بینی خشکسالی نمونة موردی: ایستگاه سینوپتیک سنندج. مخاطرات محیط طبیعی، 4(6)، 1-19. doi: 10.22111/jneh.2016.2520
میرهاشمی، سیدحسن، حقیقت جو، پرویز، میرزایی، فرهاد، و پناهی، مهدی (1396). استفاده از الگوریتم CART در پیش‌بینی نوسانات سطح آب زیرزمینی در داخل و خارج از شبکه آبیاری. پژوهش‌های آب و خاک ایران، 49(2)، 395-385. doi: 10.22059/ijswr.2017.232795.667677
نوروزی قوشبلاغ، حسین، و ندیری، عطاالله (1397). پیش‌بینی سطح آب زیرزمینی دشت بوکان با استفاده از مدل‌های منطق فازی، جنگل تصادفی و شبکة عصبی. مرتع و آبخیزداری، 71(3)، 845-829. doi: 10.22059/jrwm.2018.68924
واعظی، علی رضا، و صالحی، یاسین (1399). کارآیی مدل‌های نفوذ آب به خاک در کاربری‌های مختلف زمین در حوزة آبخیز تهم‌چای. پژوهش‌های آب و خاک ایران، 51(5)، 1281-1291. doi: 10.22059/ijswr.2020.293712.668424
 
References
Ahmadi, H. (2015). Applied geomorphology. The first volume: Water erosion. 8th Edition, Tehran University Press, 688 pages. [In Persian].
Alizadeh, A. (2019). Applied hydrology. Imam Reza International University, 43rd, 941 pages. [In Persian].
Avand, M., Moradi, H., & Ramzanzadeh Labsoi., M. (2019). Preparation of flood sensitivity map using Bayesian random forest and generalized linear machine learning models. Environment and Water Engineering, 6(1), 85-73. https://sid.ir/paper/362700/fa [In Persian].
Bahremand, A., De Smedt, F., Corluy, J., Liu, Y.B., Poorova, J., Velcicka, L., & Kunikova, E. (2007). WetSpa model application for assessing reforestation impacts on floods in Margecany-Hornad Watershed, Slovakia. Journal of Water Resources Management, 21(8):1373-1391. doi:10.1007/s11269-006-9089-0
Bakhtiari Yeganeh, A., & Ziabri, S.M.H. (2017). Forecasting the swash movements of hypergravity waves on natural beaches using M5 and MARS tree models. Amirkabir Journal of Civil Engineering, 50(3), 445-452. doi:10.22060/ceej.2017.8712.4640 [In Persian].
Berry, M.J.A., & Linoff, G.S. (2004). Data mining techniques: for marketing, sales, and customer relationship management. 2nd Edition: Wiley. 672 pages.
Chattamvelli, R. (2011). Data Mining Algorithms. 1st Edhtion. Oxford: Alpha Science, 274-290.
Fischer, C., Tischer, J., Roscher, C., Eisenhauer, N., Ravenek, J., Gleiner, G., Attinger, S., Jensen, B., Kroon, H., Momer, L., Scheu, S., & Hildebrandt, A. (2015). Plant species diversity affects infiltration capacity in an experimental grassland through changes in soil properties. Plant and Soil, 397(1), 1-16. doi:10.1007/s11104-014-2373-5
Fox, D.M., Bryan, R.B., & Price, A.G. (1997). The influence of slope angle on final infiltration rate for interrill conditions. Geoderma, 80(1–2), 181–194. doi:10.1016/S00167061(97)0007-X
Ghaiumi Mohammadi, A., Ghorbani Dashtaki, S., Raisi, F. & Tahmasabi, P. (2013). Effect of land abandonment on variation of soil water infiltration parameters. Journal of Water and Soil Resources Conservation, 2(4), 41-51. doi: 20.1001.1.22517480.1392.2.4.4.9 [In Persian].
Ghorbani Dashtaki, Sh., Homai, M. & Mahdian, M. (2009). Effect of land abandonment on variation of soil water infiltration parameters. Iranian Journal of Irrigation & Drainage, 4(2), 206-221. [In Persian].
Hasanvand, SH., Spahvand, A., Tarnian, F., & Sihag, P. (2021). An assessment of infilteration models in the surface soil of geological formations in Alshtar Watershed, the Province of Lorestan. Watershed Managemant Research, 34(4), 150-164. doi:10.22092/wmrj.2021.354035.1398 [In Persian].
Horton Robert, E. (1993). The role of infiltration in the hydrologic cycle. Transactions American Geophysical Union (AGU), Advancing earth and space sciences, 14(1), 446-460. doi:10.1029/TR014i001p00446
Kavian, A., Ahmadi, R., Habibnejad, M., & Jafarian, Z. (2017). Evaluation of spatial changes in soil infiltration using experimental and geostatistical methods in coastal plain of Behshahr-Galugah. Iranian Journal of Soil and Water Research, 48(1), 177-186. doi:10.22059/ijswr.2017.61351 [In Persian].
Kocev, D., Saso, D., White, M.D., Newell, G.R., & Griffioen, P. (2009). Using single-and multitarget regression trees and ensembles to model a compound index of vegetation condition. Ecological Modeling, 220(8), 1159 –1168. doi: 10.1016/j.ecolmodel.2009.01.037
Kornejady, A., & Pourghasemi, H.R. (2019). Landslide susceptibility assessment using data mining models, A case study: Chehel-Chai basin. Watershed Engineering and Management, 11(1), 28-42. doi: 10.22092/ijwmse.2019.118436 [In Persian].
Lee, S., Hwang, J., & Park, I. (2013). Application of data-driven evidential belief functions to landslide susceptibility mapping in Jinbu, Korea. Catena, 100(3), 15-30. doi:10.1016/j.catena.2012.07.014
Machiwal, D., Jha, M.K., & Mal, B.C. (2006). Modelling Infiltration and quantifying Spatial Soil Variability in a Wasteland of Kharagpur, India. Biosystems Engineering, 95(4), 569-582. doi: 10.1016/j.biosystemseng.2006.08.007
Mahesh, P., & Mather, P. M. (2003). An assessment of the effectiveness of decision tree methods for land cover classification. Remote Sensing of Environment, 86(4), 554–565. doi:10.1016/S0034-4257(03)00132-9
Maria, A. (1997). Introduction to modeling and simulation. Proceedings of the 29th Conference on Winter simulation, December 07 – 10, Atlanta, GA, USA, 7-13.
Mehta, V., Hasanvand, Sh., Sepahvand, A., Sihag, P., Beiranvand, N., & Singh, B., (2024). A benchmark comparison of AI-based modeling of soil infiltration rates. Journal of Hydroinformatics, 26(12): 3060-3079. doi: 10.2166/hydro.2024.086
Mirhashemi, S.H., Haghighat jou, P., Mirzaei, F., & Panahi, M. (2018). Using CART algorithm in predicting groundwater table fluctuations inside and outside of an irrigation system (case study: irrigating area of Qazvin). Water and Soil Research, 49(2), 395-385. doi:10.22059/ijswr.2017.232795.667677 [In Persian].
Mozaffari, G., Shafie, S., & Tagizadeh, Z. (2015). Evaluate the performance regression decision tree model in predicting drought (case study: synoptic station in Sanandaj). Journal of Natural Environmental Hazards, 4(6(Serial Number 6)), 1-19. doi:10.22111/jneh.2016.2520 [In Persian].
Mukheibir, P. (2008). Water resources management strategies for adaptation to climate-induced impacts in South Africa. Water Resource Management, 22(9), 1259–1276. doi:10.1007/s11269-007-9224-6
Norouzi, H., & Nadiri, A. (2018). Groundwater level prediction of Boukan Plain using fuzzy logic, random forest and neural network models. Journal of Range and Watershed Managment, 71(3), 829-845. doi: 10.22059/jrwm.2018.68924 [In Persian].
Osuji, G.E., Okon, M.A., Chukwuma, M.C., & Nwarie, I.I. (2010). Infiltration characteristics of soils under selected land use practices in Owerri, Southeastern Nigeria. World Journal of Agricultural Sciences, 6(3), 322-326.
Pal, M., & Deswal, S. (2010). Modelling plie capacity using Gaussian process regression. Computers and Geotechnics, 37(7-8), 942-947. doi:10.1016/j.compgeo.2010.07.012
Refahi, H. (2015). Water erosion and control. 7th Edition, Tehran University Press. 681 pages. [In Persian].
Ribolzi, O., Patin, J., Bresson, L.M., Latsachack, K.O., Mouche, E., Sengtaheuanghoung, O., Silvera, N., Thiebaux, J.P., & Valentin, C. (2011). Impact of slope gradient on soil surface features and infiltration on steep slopes in northern Laos. Geomorphology, 127(1–2), 53-63. doi:10.1016/j.geomorph.2010.12.004
Rusjan, S., & Micos, M. (2008). Assessment of hydrolpgical and seasonal controls over thenitrate flushing from a forested watershed using a data mining technique. Hydrology and Earth System Sciences, 12(2), 645-656. doi: 10.5194/hessd-4-4211-2007
Sadeghi, H.R. (2010). Study and measurement of soil erosion. Tarbiat Modares University Publication. 1st Edition. 171 pages. [In Persian].
Saeediyan, H., & Moradi, H. R. (2020). Determining of the most important factors in infiltration rates of the soils formed on Gachsaran and Aghajari formations in various land uses. Watershed Management Research, 33(2(Serial Number 127)), 97-109. doi: 10.22092/wmej.2019.126695.1231 [In Persian].
Sattari, M.T., & Nahrin, F. (2012). Monthly rainfall prediction using Artificial Neural Networks and M5 model tree (Case study: Stations of Ahar and Jolfa). Irrigation and Water Engineering, 4(2(Serial Number 14)), 83-98. [In Persian].
Sepahvand, A., Sihag, B., Ghobadi, M., & Sihag, P. (2021). Estimation of infiltration rate using datadriven models. Arabian Journal of Geosciences, 14(1), 1-11. doi: 10.1007/s12517-020-06245-2
Sepahvand, A., Sihag, P., Singh, B., & Zand, M. (2018). Comparative evaluation of infiltration Models. KSCE Journal of Civil Engineering, 22(10), 4173-4184. doi:10.1007/s12205-018-1347-1
Sepavand, A., Taie Semiromi, M., Mirnia, S.K., & Moradi, H.R. (2011). Assessing the Sensitivity of Infiltration Models to Variability of Soil Moisture. Journal of Water and Soil, 25(2), 1-11. doi: 10.22067/jsw.v0i0.9387 [In Persian].
Sihag, P., Singh, B., Sepahvand, A., & Mehdipour, V. (2020). Modeling the infiltration process with soft computing techniques. Indian Society for Hydraulics (ISH) Journal of Hydraulic Engineering, 26(2), 138-152. doi:10.1080/09715010.2018.1464408
Sihag, P., Singh, V.P., Angelaki, A., Kumar, V., Sepahvand, A., & Golia, E. (2019). Modelling of infiltration using artificial intelligence techniques in semi-arid Iran. Hydrological Sciences Journal, 64(13):1647-1658. doi:10.1080/02626667.2019.1659965
Soleimani, L., Mir Derikvand, B., & Sepahvand, A. (2022). Modelling of infiltration rate in different soil textures using soft computing techniques in Kashkan Watershed, Lorestan Province. Watershed Management Research, 35(4), 104-116. doi: 10.22092/wmrj.2022.358213.1461 [In Persian].
Talebi, A., & Akbari, Z. (2013). Investigation of ability of decision trees model to estimate river suspended sediment (case study: Ilam Dam Basin). Journal of Water and Soil Science, 17(63), 109-121. doi: 20.1001.1.24763594.1392.17.63.10.8 [In Persian].
Trigila, A., Frattini, P., Casagli, N., Catani, F., Crosta, G., Esposito, C., & Spizzichino, D. (2013). Landslide susceptibility mapping at national scale: the Italian case study. Landslide Science and Practice, Springer Berlin Heidelberg, 12, 287-295. doi:10.1007/978-3-642-31325-7_38
Vaezi, A., & Salehi, Y. (2020). The efficiency of water infiltration models in different land uses of the Tahamchai Catchment. Iranian Journal of Soil and Water Research, 51(5), 1281-1291. doi: 10.22059/ijswr.2020.293712.668424 [In Persian].
Ward, A.D., & Trimble, S.W. (2004). Environmental Hydrology. 2nd Edition, CRC Press LLC, 475 pages.
Witten, I.H., Frank, E., & Hall, M. (2005). Data Mining: Practical machine learning tools and techniques. 2nd Edition, The Morgan Kaufmann Series in Data Management Systems, 664 pages.
Yang, D., Zhang, X., Pan, R., Wang, Y., & Chen, Z. (2018). A novel Gaussian process regression model for state-of-health estimation of lithium-ion battery using charging curve. Journal of Power Sources, 384, 387-395. doi: 10.1016/j.jpowsour.2018.03.015
Yimer, F., Messing, I., Ledin, S., & Abdelkadir, A. (2008). Effects of different land use types on infiltration capacity in a catchment in highlands of Ethiopia. Soil Use and Management, 24(4), 344-349. doi:10.1111/j.1475-2743.2008.00182.x
Zahiri, J., & Kashefipour, S.M. (2018). Predicting maximum scour depth around bridge abutment using M5 model. Journal of Irrigation Sciences and Engineering. 41 (1), 1-16. doi: 10.22055/JISE.2018.13543 [In Persian].