Novel Genetic Algorithm (GA) based hybrid machine learning-pedotransfer Function (ML-PTF) for prediction of spatial pattern of saturated hydraulic conductivity
Saturated hydraulic conductivity (Ks) is an important soil characteristic that controls water moves through the soil. On the other hand, its measurement is difficult, time-consuming, and expensive; hence Pedotransfer Functions (PTFs) are commonly used for its estimation. Despite significant developm...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2022-12-01
|
| Series: | Engineering Applications of Computational Fluid Mechanics |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/19942060.2022.2071994 |
| _version_ | 1817986126096367616 |
|---|---|
| author | Vijay Kumar Singh Kanhu Charan Panda Atish Sagar Nadhir Al-Ansari Huan-Feng Duan Pradosh Kumar Paramaguru Dinesh Kumar Vishwakarma Ashish Kumar Devendra Kumar P. S. Kashyap R. M. Singh Ahmed Elbeltagi |
| author_facet | Vijay Kumar Singh Kanhu Charan Panda Atish Sagar Nadhir Al-Ansari Huan-Feng Duan Pradosh Kumar Paramaguru Dinesh Kumar Vishwakarma Ashish Kumar Devendra Kumar P. S. Kashyap R. M. Singh Ahmed Elbeltagi |
| author_sort | Vijay Kumar Singh |
| collection | DOAJ |
| description | Saturated hydraulic conductivity (Ks) is an important soil characteristic that controls water moves through the soil. On the other hand, its measurement is difficult, time-consuming, and expensive; hence Pedotransfer Functions (PTFs) are commonly used for its estimation. Despite significant development over the years, the PTFs showed poor performance in predicting Ks. Using Genetic Algorithm (GA), two hybrid Machine Learning based PTFs (ML-PTF), i.e. a combination of GA with Multilayer Perceptron (MLP-GA) and Support Vector Machine (SVM-GA), were proposed in this study. We compared the performances of four machine learning algorithms for different sets of predictors. The predictor combination containing sand, clay, Field Capacity, and Wilting Point showed the highest accuracy for all the ML-PTFs. Among the ML-PTFs, the SVM-GA algorithm outperformed the rest of the PTFs. It was noticed that the SVM-GA PTF demonstrated higher efficiency than the MLP-GA algorithm. The reference model for hydraulic conductivity prediction was selected as the SVM-GA PTF paired with the K-5 predictor variables. The proposed PTFs were compared with 160 models from past literature. It was found that the algorithms advocated were an improvement over these PTFs. The current model would help in efficient spatio-temporal measurement of hydraulic conductivity using pre-available databases. |
| first_indexed | 2024-04-14T00:05:25Z |
| format | Article |
| id | doaj.art-ffff2a6504314496bef2586aa16084d9 |
| institution | Directory Open Access Journal |
| issn | 1994-2060 1997-003X |
| language | English |
| last_indexed | 2024-04-14T00:05:25Z |
| publishDate | 2022-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Engineering Applications of Computational Fluid Mechanics |
| spelling | doaj.art-ffff2a6504314496bef2586aa16084d92022-12-22T02:23:33ZengTaylor & Francis GroupEngineering Applications of Computational Fluid Mechanics1994-20601997-003X2022-12-011611082109910.1080/19942060.2022.2071994Novel Genetic Algorithm (GA) based hybrid machine learning-pedotransfer Function (ML-PTF) for prediction of spatial pattern of saturated hydraulic conductivityVijay Kumar Singh0Kanhu Charan Panda1Atish Sagar2Nadhir Al-Ansari3Huan-Feng Duan4Pradosh Kumar Paramaguru5Dinesh Kumar Vishwakarma6Ashish Kumar7Devendra Kumar8P. S. Kashyap9R. M. Singh10Ahmed Elbeltagi11Faculty of Agriculture Science and Technology, Mahatma Gandhi Kashi Vidyapith, Varanasi, Uttar Pradesh, IndiaDepartment of Agricultural Engineering, Institute of Agricultural Sciences, BHU, Varanasi, Uttar Pradesh, IndiaDivision of Agricultural Engineering, Indian Agricultural Research Institute, New Delhi, IndiaDepartment of Civil, Environmental and Natural Resources Engineering, Lulea University of Technology, Lulea, SwedenDepartment of Civil and Environmental Engineering, Faculty of Construction and Environment, The Hong Kong Polytechnic University, Hong KongProduction & Extension Management Division, ICAR-Indian Institute of Natural Resins and Gums, Ranchi, Jharkhand, IndiaDepartment of Irrigation and Drainage Engineering, G.B. Pant University of Agriculture and Technology, Pantnagar, Uttarakhand, IndiaDepartment of Agricultural Engineering, Institute of Agricultural Sciences, BHU, Varanasi, Uttar Pradesh, IndiaDepartment of Soil and Water Conservation Engineering, Govind Ballabh Pant University of Agriculture and Technology, Pantnagar, Uttarakhand, IndiaDepartment of Soil and Water Conservation Engineering, Govind Ballabh Pant University of Agriculture and Technology, Pantnagar, Uttarakhand, IndiaDepartment of Agricultural Engineering, Institute of Agricultural Sciences, BHU, Varanasi, Uttar Pradesh, IndiaAgricultural Engineering Dept, Faculty of Agriculture, Mansoura University, Mansoura, EgyptSaturated hydraulic conductivity (Ks) is an important soil characteristic that controls water moves through the soil. On the other hand, its measurement is difficult, time-consuming, and expensive; hence Pedotransfer Functions (PTFs) are commonly used for its estimation. Despite significant development over the years, the PTFs showed poor performance in predicting Ks. Using Genetic Algorithm (GA), two hybrid Machine Learning based PTFs (ML-PTF), i.e. a combination of GA with Multilayer Perceptron (MLP-GA) and Support Vector Machine (SVM-GA), were proposed in this study. We compared the performances of four machine learning algorithms for different sets of predictors. The predictor combination containing sand, clay, Field Capacity, and Wilting Point showed the highest accuracy for all the ML-PTFs. Among the ML-PTFs, the SVM-GA algorithm outperformed the rest of the PTFs. It was noticed that the SVM-GA PTF demonstrated higher efficiency than the MLP-GA algorithm. The reference model for hydraulic conductivity prediction was selected as the SVM-GA PTF paired with the K-5 predictor variables. The proposed PTFs were compared with 160 models from past literature. It was found that the algorithms advocated were an improvement over these PTFs. The current model would help in efficient spatio-temporal measurement of hydraulic conductivity using pre-available databases.https://www.tandfonline.com/doi/10.1080/19942060.2022.2071994Hydraulic conductivityPedotransfer Functionsgenetic algorithmMultilayer Perceptronsupport vector machine |
| spellingShingle | Vijay Kumar Singh Kanhu Charan Panda Atish Sagar Nadhir Al-Ansari Huan-Feng Duan Pradosh Kumar Paramaguru Dinesh Kumar Vishwakarma Ashish Kumar Devendra Kumar P. S. Kashyap R. M. Singh Ahmed Elbeltagi Novel Genetic Algorithm (GA) based hybrid machine learning-pedotransfer Function (ML-PTF) for prediction of spatial pattern of saturated hydraulic conductivity Engineering Applications of Computational Fluid Mechanics Hydraulic conductivity Pedotransfer Functions genetic algorithm Multilayer Perceptron support vector machine |
| title | Novel Genetic Algorithm (GA) based hybrid machine learning-pedotransfer Function (ML-PTF) for prediction of spatial pattern of saturated hydraulic conductivity |
| title_full | Novel Genetic Algorithm (GA) based hybrid machine learning-pedotransfer Function (ML-PTF) for prediction of spatial pattern of saturated hydraulic conductivity |
| title_fullStr | Novel Genetic Algorithm (GA) based hybrid machine learning-pedotransfer Function (ML-PTF) for prediction of spatial pattern of saturated hydraulic conductivity |
| title_full_unstemmed | Novel Genetic Algorithm (GA) based hybrid machine learning-pedotransfer Function (ML-PTF) for prediction of spatial pattern of saturated hydraulic conductivity |
| title_short | Novel Genetic Algorithm (GA) based hybrid machine learning-pedotransfer Function (ML-PTF) for prediction of spatial pattern of saturated hydraulic conductivity |
| title_sort | novel genetic algorithm ga based hybrid machine learning pedotransfer function ml ptf for prediction of spatial pattern of saturated hydraulic conductivity |
| topic | Hydraulic conductivity Pedotransfer Functions genetic algorithm Multilayer Perceptron support vector machine |
| url | https://www.tandfonline.com/doi/10.1080/19942060.2022.2071994 |
| work_keys_str_mv | AT vijaykumarsingh novelgeneticalgorithmgabasedhybridmachinelearningpedotransferfunctionmlptfforpredictionofspatialpatternofsaturatedhydraulicconductivity AT kanhucharanpanda novelgeneticalgorithmgabasedhybridmachinelearningpedotransferfunctionmlptfforpredictionofspatialpatternofsaturatedhydraulicconductivity AT atishsagar novelgeneticalgorithmgabasedhybridmachinelearningpedotransferfunctionmlptfforpredictionofspatialpatternofsaturatedhydraulicconductivity AT nadhiralansari novelgeneticalgorithmgabasedhybridmachinelearningpedotransferfunctionmlptfforpredictionofspatialpatternofsaturatedhydraulicconductivity AT huanfengduan novelgeneticalgorithmgabasedhybridmachinelearningpedotransferfunctionmlptfforpredictionofspatialpatternofsaturatedhydraulicconductivity AT pradoshkumarparamaguru novelgeneticalgorithmgabasedhybridmachinelearningpedotransferfunctionmlptfforpredictionofspatialpatternofsaturatedhydraulicconductivity AT dineshkumarvishwakarma novelgeneticalgorithmgabasedhybridmachinelearningpedotransferfunctionmlptfforpredictionofspatialpatternofsaturatedhydraulicconductivity AT ashishkumar novelgeneticalgorithmgabasedhybridmachinelearningpedotransferfunctionmlptfforpredictionofspatialpatternofsaturatedhydraulicconductivity AT devendrakumar novelgeneticalgorithmgabasedhybridmachinelearningpedotransferfunctionmlptfforpredictionofspatialpatternofsaturatedhydraulicconductivity AT pskashyap novelgeneticalgorithmgabasedhybridmachinelearningpedotransferfunctionmlptfforpredictionofspatialpatternofsaturatedhydraulicconductivity AT rmsingh novelgeneticalgorithmgabasedhybridmachinelearningpedotransferfunctionmlptfforpredictionofspatialpatternofsaturatedhydraulicconductivity AT ahmedelbeltagi novelgeneticalgorithmgabasedhybridmachinelearningpedotransferfunctionmlptfforpredictionofspatialpatternofsaturatedhydraulicconductivity |