Assessing the performance of individual and ensembled models in identifying areas with infiltration potential

Document Type : Research/Original/Regular Article

Authors

1 Graduated Ph.D. Student,/Department of Watershed Management Engineering, Faculty of Agriculture, Lorestan University, Khorramabad, Iran

2 Academic Staff/ Soil and Water Conservation Department of Lorestan Agricultural Research, Education and Extension Organization, Khorramabad, Iran

Abstract

Introduction
Estimating groundwater recharge using other affecting factors such as hydro-meteorological, and physical factors, is the main way to understanding, predicting the sustainability and availability potential of aquifers. The objective of this research was investigating the efficiency of some individual and ensembled models and the effect of the ensembling on promoting the efficiency of Bayesian and Random forest models.
Materials and Methods
The required environmental layers (DEM, aspect, slope, curvatures (profile and plan curvature), lithology, landuse, soil texture, NDVI, fault distance, river distance, SPI, drainage density, TWI), were prepared by ArcGIS 10.6 software for the study area. the Bayesian theory and Random Forest models and ensembling of these models were avaluated. To consider the ensemble effect of these models, input layers were used in two models and then the models were ensembled by several scenarios, which were based on the principles of basic mathematics. The double-ring infiltrometer method were used for understanding the spatial variability of groundwater recharge potential (GWRP). The performance of the models was evaluated using statistical measures. ROC, CCI, and TSS indices were used for evaluating the results of implemented models. Finally, GWRP mapping prepared and the percolation of the study area was classified into five classes: very high infiltration, high infiltration, medium infiltration, low infiltration and very low infiltration.
Results and Discussion
The sandy-clay-loom soil texture and the Quaternary sediments (Qft2), rangeland and agriculture areas (in landuse layer), showed maximum percolation. The results indicated that the random forest (RF) model was identified as the superior model compared to Bayesian and ensembled models, by ROC, TSS and CCI indices (ROC= 0.983, TSS= 0.86, and CCI= 93.9, respectively). Also, among the ensembled models, the RFBa5 model (based on the fifth scenario) was evaluated as the most efficient model through ROC, TSS, and CCI indices (ROC= 0.984, TSS= 0.76, and CCI= 87.94, respectively). Based on the first individual model (RF), 11% of the study area had moderate to very high infiltration potential. This despite the fact that the 89% of the study watershed was found with low and very low potential. While according to RFBa5, 30% of the study area were estimated with moderate to very high potential and 70% with low and very low potential. The Bayesian model was observed as the weakest model. But based on the ensemble of this model with the random forest model, under different scenarios, the strengthening of this model was observed. These results show the positive effect of ensembling the models.
Conclusion
The GWR potential maps are useful in planning with more accuracy for implementation of artificial GWR, soil protection, aquifers and watershed management projects in order to protect water and soil resources by directing runoffs to preventing the soil erosion and aquifers recharge. It is recommended to study different suitable models and their ensembling in this field or other watersheds and select the best model to get the best performance and obtain an accurate map.

Keywords

References

Ahmadi, F., & Radmanesh, F., & Mirabbasi Najafabadi, R. (2016). Comparing the performance of support vector machines and bayesian networks in predicting daily river flow (case study: baranduz chai river). Journal of Water and Soil Conservation (Journal of Agricultural Sciences and Natural Resources), 22(6), 171-186 (in Persian).
Akhoni Pourhosseini, f., & Ghorbani, M. (2018). Application of Shannon Entropy for Selecting the Optimum input Variables in River Flow Simulation using Intelligent Models (Case Study: SofyChay). Irrigation Sciences and Engineering (JISE) (Scientific Journal of Agriculture), 41(2 ), 183-195 (in Persian).
Al-Abadi, A.M., Pradhan, B., & Shahid, S. (2016). Prediction of groundwater flowing well zone at An-Najif Province, central Iraq using evidential belief functions model and GIS. Environmental monitoring and assessment, 188(10), 549.
Al-Fugara, A.K., Pourghasemi, H.R., Al-Shabeeb, A.R., Habib, M., Al-Adamat, R., Al-Amoush, H., & Collins, A.L. (2020). A comparison of machine learning models for the mapping of groundwater spring potential. Environmental Earth Sciences, 79, 1-19.
Althuwaynee, O.F., Pradhan, B., Park, H.-J. & Lee, J.H. (2014). A novel ensemble decision tree-based CHi-squared Automatic Interaction Detection (CHAID) and multivariate logistic regression models in landslide susceptibility mapping. Landslides 11, 1063–1078.
Arthur, J.D., Wood, H.A.R., Baker, A.E., Cichon, J.R., & Raines, G.L. (2007). Development and implementation of a Bayesian-based aquifer vulnerability assessment in Florida. Natural Resources Research, 16(2), 93-107.
ASTM (American Society for Testing Materials), (1998). Standard Test Method for Particle- Analysis of Soils, D422-63.
Avand, M., & Janizadeh, S., & Farzin, M. (2019). Groundwater Potential Determination on Yasouj-Sisakht area Using Random Forest and Generalized Linear Statistical Models. Journal of Range and Watershed Management (Iranian Journal of Natural Resources), 72(3 ), 609-623 (in Persian).
Bagheri Dadvokalaii, O., Mohammadvali Samani, J., Sarvarian, J. (2017). Determine the best place to implement groundwater artificial pond design by using two methods of boolean and AHP. Journal of Engineering & Construction Management, 2(1), 12-16 (in Persian).
Chen, W.B., Pradhan, S., Li, H., Shahabi, H.M., Rizeei, E. H., & Wang, S. (2019). Novel Hybrid Integration Approach of Bagging-Based Fisher’s Linear Discriminant Function for Groundwater Potential Analysis. Natural Resources Research, 1-20.
Farmani, R., Henriksen, H.J., & Savic, D. (2009), An evolutionary Bayesian belief network methodology for participatory decision making under uncertainty: an application to groundwater management. Integrated Environmental Assessment and Management, 8(3), 456-461.
Fielding, A.H., & Bell, J.F. (1997). A review of methods for the assessment of prediction errors in conservation presence/absence models. Environmental Conservation, 24, 38–49.
Gelman, A., Carlin, J.B., Stern Hal, S., Dunson David, B., Vehtari, Aki, R., & Donald, B. (2013). Bayesian Data Analysis. 3rd Edition: Chapman and Hall/CRC, 657 pages.
Graham, W.D., & Neff, C.R. (1994). Optimal estimation of spatially variable recharge and transmissivity fields under steady-state groundwater flow. Part 2. Case study. Journal of Hydrology, 157(1-4), 267-285.
Guo, C., Montgomery, D.R., Zhang, Y., Wang, K., & Yang, Z. (2015). Quantitative assessment of landslide susceptibility along the Xianshuihe fault zone, Tibetan Plateau, China. Geomorphology Journal, 248, 93–110.
Jeffreys, H. (2011). Scientific Inference. 3rd Edition: Cambridge University Press, 282 pages.
Konikow, L.F., & Kendy. E. (2005). Groundwater depletion: A global problem. Hydrogeology Journal, 13(1), 317-320.
Kordestani, M.D., Naghibi, S.A., Hashemi, H., Ahmadi, K., Kalantar, B., & Pradhan, B. (2019). Groundwater potential mapping using a novel data-mining ensemble model. Hydrogeology Journal, 27(1), 211-224.
Lee, S., & Min, K. (2001). Statistical analysis of landslide susceptibility at Youngin, Korea. Environmental Geology, 40, 1095–1113.
Li, X., Zhao, S., Yang, H., Cong, D., & Zhang, Z. (2017). Abi-band binary mask-based land-use change detection using Landsat 8 OLI imagery. Sustainability, 9(3), 479.
Liu, X., He, J., Yao, Y., Zhang, J., Liang, H., Wang, H., & Hong, Y. (2017). Classifying urban land use by integrating remote sensing and social media data. International Journal of Geographical Information Science, 31(8), 1675-1696.
Lorestan Regional Water Company, (2001). Feasibility studies for soil protection and watershed management in the Marbareh watershed and a small part of the Tireh River in the north of Dorud (in Persian).
Marker, M., Pelacani, S., & Schroder, B. (2012). A functional entity approach to predict soil erosion processes in a small Plio-Pleistocene Mediterranean catchment in Northern Chianti, Italy. Geomorphology, 125(4), 530-540.
Messenzehl, K., Meyer, H., Otto, J.C., Hoffmann, T., & Dikau, R. (2017). Regional-scale controls on the spatial activity of rockfalls (Turtmann Valley, Swiss Alps)—A multivariate modeling approach. Geomorphology, 287, 29-45.
Miraki, S., Zanganeh, S.H., Chapi, K., Singh, V.P., Shirzadi, A., Shahabi, H., & Pham, B.T. (2019). Mapping groundwater potential using a novel hybrid intelligence approach. Water resources management, 33(1), 281-302.
Mogaji, K.A., Omosuyi, G.O., Adelusi, A.O., & Lim, H.S. (2016). Application of GIS-based evidential belief function model to regional groundwater recharge potential zones mapping in hardrock geologic terrain. Environmental Processes, 3(1), 93-123.
Mokarram, M., Saber, A., Mohammadizadeh, P., & Abdolali, A. (2020). Determination of artificial recharge location using analytic hierarchy process and Dempster–Shafer theory. Environmental Earth Sciences, 79(10), 1-15.
Mukherjee, S. (1996). Targeting saline aquifer by remote sensing and geophysical methods in a part of Hamirpur-Kanpur, India. Hydrogeology Journal, 19, 53-64.
Naghibi, S.A., Moghaddam, D.D., Kalantar, B., Pradhan, B., & Kisi, O. (2017). A comparative assessment of GIS-based data mining models and a novel ensemble model in groundwater well potential mapping. Journal of Hydrology, 548, 471-483.
Norouzi, H., Nadiri, A., Asghari Moghaddam,, A., & Gharekhani, M. (2017). Prediction of Transmissivity of Malikan Plain Aquifer Using Random Forest Method. Water and Soil Science, 27(2), 61-75 (in Persian).
Pars Ray Ab Consulting Engineering Company, (2012). Azna Aligudarz Comprehensive Report, Chapters 2, 3, 6 and 16 (in Persian).
Pourghasemi, H.R., Mohammady, M., & Pradhan, B. (2012). Landslide susceptibility mapping using index of entropy and conditional probability models in GIS: Safarood Basin. Iran. Catena 97, 71–84.
Qureshi, M.E., Reeson, A., Reinelt, P., Brozović, N., & Whitten, S. (2012). Factors determining the economic value of groundwater. Hydrogeology Journal, 21(3), 1-9.
Reggiani, P., & Weerts, A. (2008). Bayesian approach to decision-making under uncertainty: An application to real time forecasting in the river Rhine. Journal of Hydrology, 356, 56-69.
Rittel, H.W., & Webber, M.M. (1973). Dilemmas in a general theory of planning. Policy sciences, 4(2), 155-169.
Rojas, R., Feyen, L., & Dassargues, A. (2008). Conceptual model uncertainty in groundwater modeling: Combining generalized likelihood uncertainty estimation and Bayesian model averaging. Water Resources Research, 44, W12418.
Rukundo, E., & Doğan, A. (2019). Dominant Influencing Factors of Groundwater Recharge Spatial Patterns in Ergene River Catchment, Turkey. Water, 11(4), 653.
Rwanga, S.S., & Ndambuki, J.M. (2017). Accuracy assessment of land use/land cover classification using remote sensing and GIS. International Journal of Geosciences, 8(04), 611.
Sadoddin, A., Letcher, R.A., Jakeman, A.J., & Newham, L.T. (2005). A Bayesian decision network approach for assessing the ecological impacts of salinity management. Mathematics and Computers in Simulation, 69(1-2), 162-176.
Saha, A.K., Gupta, R.P., Sarkar, I., Arora, M.K., & Csaplovics, E. (2005). An approach for GIS-based statistical landslide susceptibility zonation with a case study in the Himalayas. Landslides, 2, 61–69.
Seiler, K.P., & Gat, J.R. (2007). Groundwater Recharge from Run-Off, Infiltration and Percolation. Water Science and Technology Library, Springer Dordrecht, New York, USA, 248 pages.
Sekertekin, A., Marangoz, M., & Akcin, H. (2017). pixel-based classification analysis of land use land cover using sentinel-2 and landsat-8 data. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII-4/W6, 91-93.
Shah, T., Burke, J., Villholth, K., Angelica, M., Custodio, E., Daibes, F., Hoogesteger, J., Giordano, M., Girman, J., van der Gun, J. Kendy, E., Kijne, J., Llamas, R., Masiyandima, M., Margat, J., Marin, L., Peck, J., Rozelle, S., Sharma, B.R., Vincent, L., & Wang, J. (2007). Groundwater: a global assessment of scale and significance. Pp.395-423, In: Molden, David (Ed.), Water for food, water for life: a Comprehensive Assessment of Water Management in Agriculture, London, UK: Earthscan; Colombo, Sri Lanka: International Water Management Institute (IWMI).
Sihag, P., Angelaki, A., & Chaplot, B. (2020). Estimation of the recharging rate of groundwater using random forest technique. Applied Water Science, 10(7), 1-11.
Simmers, I., Hendrickx, J.M.H., Kruseman, G.P., & Rushton, K.R. (1997). Recharge of phreatic aquifers in (semi-)arid areas. IAH International Contributions to hydrogeology 19, 1st Edition: CRC Press, 240 pages.
Vrugt, J.A., & Sadegh, M. (2013). Toward diagnostic model calibration and evaluation: Approximate Bayesian computation. Water Resources Research, 49(7), 4335-4345.
Wada, Y., Van Beek, L.P.H., Van Kempen, C.M., Reckman, J.W.T.M., Vasak, S., & Bierkens, M.F.P. (2010). Global depletion of groundwater resources. Geophysical Research Letters, 37(20), L20402.
Yeh, H.F., Cheng, Y.S., Lin, H.I., & Lee, C.H. (2016). Mapping groundwater recharge potential zone using a GIS approach in Hualian River, Taiwan. Sustainable Environment Research, 26(1), 33-43.
Yenehun, A., Walraevens, K., & Batelaan, O. (2017). Spatial and temporal variability of groundwater recharge in Geba bain. Northern Ethiopia. Journal of African Earth Sciences,134, 198–212.
Zektser, I.S. (2012). Investigation of Transboundary Aquifers in Russia: Modern State and Main Tasks, Proceedings of NATO Advanced Research Workshop on Sustainable Use and Protection of Groundwater Resources. Transboundary Water Management, 79-85.
Zhang, K., Wu, X., Niu, R., Yang, K., & Zhao, L. (2017). The assessment of landslide susceptibility mapping using random forest and decision tree methods in the Three Gorges Reservoir area, China. Environmental Earth Sciences, 76(11), 1-20.
 
Water and Soil Management and Modelling
Volume 2, Issue 2
June 2022
Pages 69-86

Files

History

  • Receive Date: 14 November 2021
  • Revise Date: 29 November 2021
  • Accept Date: 29 November 2021

Share

How to cite

Statistics