Prediction of Stress-Dependent Soil Water Retention Using Machine Learning

被引:26
作者
Mojtahedi, Seyed Farid Fazel [1 ]
Akbarpour, Ali [2 ]
Darzi, Ali Golaghaei [3 ]
Sadeghi, Hamed [3 ]
van Genuchten, Martinus Theodorus [4 ]
机构
[1] Univ Melbourne, Dept Infrastruct Engn, Parkville, Australia
[2] Univ Oklahoma, Sch Civil Engn & Environm Sci, Norman, OK USA
[3] Sharif Univ Technol, Dept Civil Engn, Tehran, Iran
[4] Univ Fed Rio de Janeiro, Dept Nucl Engn, Rio De Janeiro, Brazil
关键词
Soil water retention; Net stress; Machine learning; Group method of data handling; Multilayer perceptron; UNSATURATED SHEAR-STRENGTH; PEDOTRANSFER FUNCTIONS; MODEL; STATE; TEMPERATURE; SIMULATION; NETWORKS; BEHAVIOR;
D O I
10.1007/s10706-024-02767-8
中图分类号
P5 [地质学];
学科分类号
0709 ; 081803 ;
摘要
The soil water retention curve (SWRC) provides information for a wide range of geoenvironmental problems, such as analyses of transient two-phase flow, the bearing capacity and shear strength of unsaturated soils. Many past studies have shown experimentally the effects of stress on the SWRC. Unfortunately, direct stress-dependent water retention measurements are relatively time-consuming and generally require special equipment and a certain level of expertise. This study primarily aimed to develop a novel predictive framework within the context of soft computing to capture the dependency of the SWRC on several variables, with an emphasis on stress and soil type. To achieve this, the three shape parameters of van Genuchten's water retention model were estimated using a comprehensive database of 102 SWRC tests retrieved from the literature. In this study, 60% of the datasets were employed for model training, with an additional 20% being designated for validation, while the remaining 20% were set aside for testing the model's performance. The data were analyzed using two machine learning techniques: the group method of data handling and multi-layer perceptron approaches. Results showed excellent performance of the two methods. A sensitivity analysis was conducted to explore the relative significance of the different variables. Interestingly, net stress was found to be almost as significant as soil type. The introduced artificial intelligence based predictive framework provided a very effective method of integrating theory and practice.
引用
收藏
页码:3939 / 3966
页数:28
相关论文
共 91 条
[1]   Dynamic Neural Network Modelling of Soil Moisture Content for Predictive Irrigation Scheduling [J].
Adeyemi, Olutobi ;
Grove, Ivan ;
Peets, Sven ;
Domun, Yuvraj ;
Norton, Tomas .
SENSORS, 2018, 18 (10)
[2]   Combination of water head control and axis translation techniques in new unsaturated cyclic simple shear tests [J].
Ahmadinezhad, Adel ;
Jafarzadeh, Fardin ;
Sadeghi, Hamed .
SOIL DYNAMICS AND EARTHQUAKE ENGINEERING, 2019, 126
[3]   The relationship between the shear strength and water retention curve of unsaturated sand at different hydraulic phases [J].
Albadri, Wael M. ;
Noor, Mohd Jamaludin Md ;
Alhani, Israa J. .
ACTA GEOTECHNICA, 2021, 16 (09) :2821-2835
[4]  
Assouline S, 2013, VADOSE ZONE J, V12, DOI [10.2136/vzj2012.0216, 10.2136/vzj2013.07.0121]
[5]   Combination of artificial neural networks and fractal theory to predict soil water retention curve [J].
Bayat, Hossein ;
Neyshaburi, Mohammad Reza ;
Mohammadi, Kourosh ;
Nariman-Zadeh, Nader ;
Irannejad, Mandi ;
Gregory, Andrew S. .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2013, 92 :92-103
[6]   An unsteady state retention model for fluid desorption from sorbents [J].
Bazargan, Alireza ;
Sadeghi, Named ;
Garcia-Mayoral, Ricardo ;
McKay, Gordon .
JOURNAL OF COLLOID AND INTERFACE SCIENCE, 2015, 450 :127-134
[7]   Proposing a new model to approximate the elasticity modulus of granite rock samples based on laboratory tests results [J].
Behzadafshar, Katayoun ;
Sarafraz, Mehdi Esfandi ;
Hasanipanah, Mahdi ;
Mojtahedi, S. Farid F. ;
Tahir, M. M. .
BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT, 2019, 78 (03) :1527-1536
[8]   "Deep" Learning for Missing Value Imputation in Tables with Non-Numerical Data [J].
Biessmann, Felix ;
Salinas, David ;
Schelter, Sebastian ;
Schmidt, Philipp ;
Lange, Dustin .
CIKM'18: PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, 2018, :2017-2025
[9]   Volume change behavior of compacted loess under drying/wetting and freezing/thawing cycles [J].
Cai, Guoqing ;
Liu, Qianqian ;
Li, Kunhong ;
Zhang, Jun ;
Liu, Yi ;
Zhou, Annan .
ENGINEERING GEOLOGY, 2023, 326
[10]   A soil-brine retention model for wetting processes considering the hysteresis effects [J].
Darzi, Ali Golaghaei ;
Sadeghi, Hamed ;
Zhou, Chao .
TRANSPORTATION GEOTECHNICS, 2023, 41