A comparative study of land subsidence susceptibility mapping of Tasuj plane, Iran, using boosted regression tree, random forest and classification and regression tree methods

Land subsidence occurrence in the Tasuj plane is becoming more frequent and hazardous in the near future due to the water crisis. To mitigate damage caused by land subsidence events, it is necessary to determine the susceptible or prone areas. This study focuses on producing and comparing land subsidence susceptibility map (LSSM) using boosted regression tree (BRT), random forest (RF), and classification and regression tree (CART) approaches with twelve influencing variables, namely altitude, slope angle, aspect, groundwater level, groundwater level change, land cover, lithology, distance to fault, distance to stream, stream power index, topographic wetness index, and plan curvature. Moreover, by implementing the Relief-F feature selection method, the most important variables in LSSM procedure were identified. The performance of the adopted methods was assessed using the area under the receiver operating characteristics curve (AUROC) and statistical evaluation indexes. The results showed that all the employed methods performed well; in particular, the BRT model (AUROC = 0.819) yielded higher prediction accuracy than RF (AUROC = 0.798) and CART (AUROC = 0.764). Findings of this study can assist in characterizing and mitigating the related hazard of land subsidence events.

[1]  Jorge Pedro Galve,et al.  Evaluating and comparing methods of sinkhole susceptibility mapping in the Ebro Valley evaporite karst (NE Spain) , 2009 .

[2]  Mariana Belgiu,et al.  Random forest in remote sensing: A review of applications and future directions , 2016 .

[3]  Zahra Sadeghi,et al.  An Improved Persistent Scatterer Interferometry for Subsidence Monitoring in the Tehran Basin , 2013, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[4]  R. Real,et al.  AUC: a misleading measure of the performance of predictive distribution models , 2008 .

[5]  Marko Robnik-Sikonja,et al.  Theoretical and Empirical Analysis of ReliefF and RReliefF , 2003, Machine Learning.

[6]  J. Friedman.  Special Invited Paper-Additive logistic regression: A statistical view of boosting , 2000 .

[7]  Veronica Tofani,et al.  Subsidence mapping at regional scale using persistent scatters interferometry (PSI): The case of Tuscany region (Italy) , 2016, Int. J. Appl. Earth Obs. Geoinformation.

[8]  Guoqing Zhou,et al.  Spatial analysis for susceptibility of second-time karst sinkholes: A case study of Jili Village in Guangxi, China , 2016, Comput. Geosci..

[9]  Gidon Baer,et al.  High-resolution InSAR constraints on flood-related subsidence and evaporite dissolution along the Dead Sea shores: Interplay between hydrology and rheology , 2017 .

[10]  G. De’ath.  Boosted trees for ecological modeling and prediction. , 2007, Ecology.

[11]  ZhouGuoqing,et al.  Spatial analysis for susceptibility of second-time karst sinkholes , 2016 .

[12]  Thomas Blaschke,et al.  Multi-criteria risk evaluation by integrating an analytical network process approach into GIS-based sensitivity and uncertainty analyses , 2018 .

[13]  Bakhtiar Feizizadeh,et al.  A Novel Approach of Fuzzy Dempster–Shafer Theory for Spatial Uncertainty Analysis and Accuracy Assessment of Object-Based Image Classification , 2018, IEEE Geoscience and Remote Sensing Letters.

[14]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[15]  D. Al-Halbouni,et al.  Sinkholes, subsidence and subrosion on the eastern shore of the Dead Sea as revealed by a close-range photogrammetric survey , 2017 .

[16]  Devin L. Galloway,et al.  Land subsidence in the United States , 1999 .

[17]  B. Muys,et al.  Comparison and ranking of different modelling techniques for prediction of site index in Mediterranean mountain forests , 2010 .

[18]  Joseph H. A. Guillaume,et al.  Characterising performance of environmental models , 2013, Environ. Model. Softw..

[19]  J A Swets,et al.  Measuring the accuracy of diagnostic systems. , 1988, Science.

[20]  Ajay Mahaputra Kumar,et al.  Multivariate statistical approach for assessment of subsidence in Jharia coalfields, India , 2017, Arabian Journal of Geosciences.

[21]  Mohammad Reza Nikudel,et al.  Numerical simulation and prediction of regional land subsidence caused by groundwater exploitation in the southwest plain of Tehran, Iran , 2016 .

[22]  J. Perrin,et al.  A multicriteria approach to karst subsidence hazard mapping supported by weights-of-evidence analysis , 2015 .

[23]  René Therrien,et al.  Simulating pumping-induced regional land subsidence with the use of InSAR and field data in the Toluca Valley, Mexico , 2011 .

[24]  Bakhtiar Feizizadeh,et al.  GIS-based forest fire risk mapping using the analytical network process and fuzzy logic , 2019, Journal of Environmental Planning and Management.

[25]  Juan de la Riva,et al.  An insight into machine-learning algorithms to model human-caused wildfire occurrence , 2014, Environ. Model. Softw..

[26]  Seyed Amir Naghibi,et al.  GIS-based groundwater potential mapping using boosted regression tree, classification and regression tree, and random forest machine learning models in Iran , 2015, Environmental Monitoring and Assessment.

[27]  Shaban Shataeea,et al.  Plot-level Forest Volume Estimation Using Airborne Laser Scanner and TM Data, Comparison of Boosting and Random Forest Tree Regression Algorithms , 2011 .

[28]  Thomas Blaschke,et al.  Comparing GIS-based support vector machine kernel functions for landslide susceptibility mapping , 2017, Arabian Journal of Geosciences.

[29]  George F. Jenks,et al.  ERROR ON CHOROPLETHIC MAPS: DEFINITION, MEASUREMENT, REDUCTION , 1971 .

[30]  B. Pradhan,et al.  A comparative study of logistic model tree, random forest, and classification and regression tree models for spatial prediction of landslide susceptibility , 2017 .

[31]  Thomas Blaschke,et al.  An interval matrix method used to optimize the decision matrix in AHP technique for land subsidence susceptibility mapping , 2018, Environmental Earth Sciences.

[32]  A. Townsend Peterson,et al.  Rethinking receiver operating characteristic analysis applications in ecological niche modeling , 2008 .

[33]  M. Saroli,et al.  Spatial analysis of land subsidence induced by groundwater withdrawal , 2013 .

[34]  E. Alexander,et al.  Karst database implementation in Minnesota: analysis of sinkhole distribution , 2005 .

[35]  Xiaoqing Shi,et al.  Regional land subsidence simulation in Su-Xi-Chang area and Shanghai City, China , 2008 .

[36]  J Elith,et al.  A working guide to boosted regression trees. , 2008, The Journal of animal ecology.

[37]  T. Blaschke,et al.  GIS-multicriteria decision analysis for landslide susceptibility mapping: comparing three methods for the Urmia lake basin, Iran , 2012, Natural Hazards.

[38]  H. Gong,et al.  Land subsidence due to groundwater withdrawal in the northern Beijing plain, China , 2015 .

[39]  A. Prasad,et al.  Newer Classification and Regression Tree Techniques: Bagging and Random Forests for Ecological Prediction , 2006, Ecosystems.

[40]  B. Motamedvaziri,et al.  Simulation of land subsidence using finite element method: Rafsanjan plain case study , 2014, Natural Hazards.

[41]  S. Roessner,et al.  Quantifying groundwater exploitation induced subsidence in the Rafsanjan plain, southeastern Iran, using InSAR time-series and in situ measurements , 2017 .

[42]  Hyung-Sup Jung,et al.  Spatial prediction of flood susceptibility using random-forest and boosted-tree models in Seoul metropolitan city, Korea , 2017 .

[43]  Huili Gong,et al.  Measuring Spatiotemporal Features of Land Subsidence, Groundwater Drawdown, and Compressible Layer Thickness in Beijing Plain, China , 2017 .

[44]  Hyun-Joo Oh,et al.  Assessment of ground subsidence using GIS and the weights-of-evidence model , 2010 .

[45]  Jong-Kuk Choi,et al.  Spatial Prediction of Ground Subsidence Susceptibility Using an Artificial Neural Network , 2012, Environmental Management.

[46]  J. Franklin,et al.  The elements of statistical learning: data mining, inference and prediction , 2005 .

[47]  Robert E. Schapire,et al.  The Boosting Approach to Machine Learning An Overview , 2003 .

[48]  Mohsen Azadbakht,et al.  Downscaling MODIS land surface temperature over a heterogeneous area: An investigation of machine learning techniques, feature selection, and impacts of mixed pixels , 2019, Comput. Geosci..

[49]  Lee Saro,et al.  Ensemble of ground subsidence hazard maps using fuzzy logic , 2014 .

[50]  Dieu Tien Bui,et al.  Hybrid integration of Multilayer Perceptron Neural Networks and machine learning ensembles for landslide susceptibility assessment at Himalayan area (India) using GIS , 2017 .

[51]  Saro Lee,et al.  Erratum to: Prediction of ground subsidence in Samcheok City, Korea using artificial neural networks and GIS , 2009 .

[52]  Larry A. Rendell,et al.  A Practical Approach to Feature Selection , 1992, ML.

[53]  Hyun-Joo Oh,et al.  Prediction of ground subsidence in Samcheok City, Korea using artificial neural networks and GIS , 2009 .

[54]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[55]  Jaime Joaquim da Silva Pereira Cabral,et al.  Monitoring of soil subsidence in urban and coastal areas due to groundwater overexploitation using GPS , 2012, Natural Hazards.

[56]  Daniel W. McKenney,et al.  Spatial models of site index based on climate and soil properties for two boreal tree species in Ontario, Canada , 2003 .

[57]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[58]  Joong-Sun Won,et al.  Application of a fuzzy operator to susceptibility estimations of coal mine subsidence in Taebaek City, Korea , 2010 .

[59]  I. Moore,et al.  Digital terrain modelling: A review of hydrological, geomorphological, and biological applications , 1991 .

[60]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[61]  Khosro Moghtased-Azar,et al.  Investigation of correlation of the variations in land subsidence (detected by continuous GPS measurements) and methodological data in the surrounding areas of Lake Urmia , 2012 .

[62]  Thomas Blaschke,et al.  A GIS based spatially-explicit sensitivity and uncertainty analysis approach for multi-criteria decision analysis☆ , 2014, Comput. Geosci..

[63]  M. H. Abokharima,et al.  Land subsidence susceptibility mapping at Kinta Valley (Malaysia) using the evidential belief function model in GIS , 2014, Natural Hazards.