Landslide and Wildfire Susceptibility Assessment in Southeast Asia Using Ensemble Machine Learning Methods

Southeast Asia (SEA) is a region affected by landslide and wildfire; however, few studies on susceptibility modeling for the two hazards together have been conducted for this region, and the intersection and the uncertainty of the two hazards are rarely assessed. Thus, the intersection of landslide and wildfire susceptibility and the spatial uncertainty of the susceptibility maps were studied in this paper. Reliable landslide and wildfire susceptibility maps are necessary for disaster management and land use planning. This work used three advanced ensemble machine learning algorithms: RF (Random Forest), GBDT (Gradient Boosting Decision Tree) and AdaBoost (Adaptive Boosting) to assess the landslide and wildfire susceptibility for SEA. A geo-database was established with 2759 landslide locations, 1633 wildfire locations and 18 predictor variables in total. The performances of the models were assessed using the overall classification accuracy (ACC), Precision, the area under the ROC (receiver operating curve) (AUC) and confusion matrix values. The results showed RF performs superior in both landslide (ACC = 0.81, Precision = 0.78 and AUC= 0.89) and wildfire (ACC= 0.83, Precision = 0.83 and AUC = 0.91) susceptibility modeling, followed by GBDT and AdaBoost. The overall superiority of RF over other models indicates that it is potentially an efficient model for landslide and wildfire susceptibility mapping. The landslide and wildfire susceptibility were obtained using the RF model. This paper also conducted an overlay analysis of the two hazards. The uncertainty of the susceptibility was further assessed using the coefficient of variation (CV). Additionally, the distance to roads is relatively important in both landslide and wildfire susceptibility, which is the most important in landslides and the second most important in wildfires. The result of this paper is useful for mastering the whole situation of hazard susceptibility and proves that RF is a robust model in the hazard susceptibility assessment in SEA.

[1]  Saro Lee,et al.  Application of Ensemble-Based Machine Learning Models to Landslide Susceptibility Mapping , 2018, Remote. Sens..

[2]  B. Pham,et al.  Assessment of advanced random forest and decision tree algorithms for modeling rainfall-induced landslide susceptibility in the Izu-Oshima Volcanic Island, Japan. , 2019, The Science of the total environment.

[3]  Binh Thai Pham,et al.  Coupling RBF neural network with ensemble learning techniques for landslide susceptibility mapping , 2020 .

[4]  H. Pourghasemi,et al.  Prediction of the landslide susceptibility: Which algorithm, which precision? , 2018 .

[5]  Shinji Takarada,et al.  Mobile Application and a Web-Based Geographic Information System for Sharing Geological Hazards Information in East and Southeast Asia , 2019 .

[6]  J. Abatzoglou,et al.  TerraClimate, a high-resolution global dataset of monthly climate and climatic water balance from 1958–2015 , 2018, Scientific Data.

[7]  H. Pourghasemi,et al.  Gully erosion spatial modelling: Role of machine learning algorithms in selection of the best controlling factors and modelling process , 2020 .

[8]  H. Hong,et al.  Predicting spatial patterns of wildfire susceptibility in the Huichang County, China: An integrated model to analysis of landscape indicators , 2019, Ecological Indicators.

[9]  Mauro Rossi,et al.  LAND-SE: a software for statistically based landslide susceptibilityzonation, version 1.0 , 2016 .

[10]  Thomas Blaschke,et al.  Multi-Hazard Exposure Mapping Using Machine Learning for the State of Salzburg, Austria , 2020, Remote. Sens..

[11]  Martina Wilde,et al.  Pan-European landslide susceptibility mapping: ELSUS Version 2 , 2018 .

[12]  K. Allstadt,et al.  A Global Empirical Model for Near‐Real‐Time Assessment of Seismically Induced Landslides , 2018, Journal of Geophysical Research: Earth Surface.

[13]  Mazlan Hashim,et al.  Landslide susceptibility mapping using GIS-based statistical models and Remote sensing data in tropical environment , 2015, Scientific Reports.

[14]  W. Shi,et al.  A new method of pseudo absence data generation in landslide susceptibility mapping with a case study of Shenzhen , 2010 .

[15]  Tarunpreet Bhatia,et al.  GIS-based evolutionary optimized Gradient Boosted Decision Trees for forest fire susceptibility mapping , 2018, Natural Hazards.

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

[17]  H. Ramesh,et al.  Evaluating the effects of forest fire on water balance using fire susceptibility maps , 2020 .

[18]  M. Hashim,et al.  Landslide Mapping and Assessment by Integrating Landsat-8, PALSAR-2 and GIS Techniques: A Case Study from Kelantan State, Peninsular Malaysia , 2018, Journal of the Indian Society of Remote Sensing.

[19]  Wei Chen,et al.  Landslide Detection and Susceptibility Mapping by AIRSAR Data Using Support Vector Machine and Index of Entropy Models in Cameron Highlands, Malaysia , 2018, Remote. Sens..

[20]  Xiangzheng Deng,et al.  Evaluation and convergence analysis of socio-economic vulnerability to natural hazards of Belt and Road Initiative countries , 2021 .

[21]  Nguyen Thi Thuy Linh,et al.  Flood susceptibility modelling using advanced ensemble machine learning models , 2020 .

[22]  Hong Wen,et al.  Adaboost-based security level classification of mobile intelligent terminals , 2019, The Journal of Supercomputing.

[23]  Wei Chen,et al.  Combining Evolutionary Algorithms and Machine Learning Models in Landslide Susceptibility Assessments , 2020, Remote. Sens..

[24]  Xiyong Hou,et al.  Characteristics of Coastline Changes on Southeast Asia Islands from 2000 to 2015 , 2020, Remote. Sens..

[25]  Bruce D. Malamud,et al.  A review of quantification methodologies for multi-hazard interrelationships , 2019, Earth-Science Reviews.

[26]  Francesco Carotenuto,et al.  Machine learning ensemble modelling as a tool to improve landslide susceptibility mapping reliability , 2020, Landslides.

[27]  Dieu Tien Bui,et al.  Spatial pattern assessment of tropical forest fire danger at Thuan Chau area (Vietnam) using GIS-based advanced machine learning algorithms: A comparative study , 2018, Ecol. Informatics.

[28]  L. Baise,et al.  An Updated Geospatial Liquefaction Model for Global Application , 2017 .

[29]  A. Ziegler,et al.  Highland cropland expansion and forest loss in Southeast Asia in the twenty-first century , 2018, Nature Geoscience.

[30]  C. Surussavadee,et al.  Evaluation of CMIP5 Global Climate Models for Simulating Climatological Temperature and Precipitation for Southeast Asia , 2019, Advances in Meteorology.

[31]  Soo Chin Liew,et al.  Fire Distribution in Peninsular Malaysia, Sumatra and Borneo in 2015 with Special Emphasis on Peatland Fires , 2017, Environmental Management.

[32]  A. S. Thoha,et al.  Spatio-temporal distribution of forest and land fires in Labuhanbatu Utara District, North Sumatera Province, Indonesia , 2020, IOP Conference Series: Earth and Environmental Science.

[33]  Wei Chen,et al.  GIS-based landslide susceptibility assessment using optimized hybrid machine learning methods , 2021, CATENA.

[34]  G. Rawat,et al.  Landslide susceptibility zonation mapping and its validation in part of Garhwal Lesser Himalaya, India, using binary logistic regression analysis and receiver operating characteristic curve method , 2009 .

[35]  Tetsuya Kubota,et al.  Comparison of GIS-based landslide susceptibility models using frequency ratio, logistic regression, and artificial neural network in a tertiary region of Ambon, Indonesia , 2018, Geomorphology.

[36]  Paraskevas Tsangaratos,et al.  Flash flood susceptibility modeling using an optimized fuzzy rule based feature selection technique and tree based ensemble methods. , 2019, The Science of the total environment.

[37]  Thomas Blaschke,et al.  Spatial Prediction of Wildfire Susceptibility Using Field Survey GPS Data and Machine Learning Approaches , 2019, Fire.

[38]  Silvia Liberata Ullo,et al.  Landslide Susceptibility Assessment of Wildfire Burnt Areas through Earth-Observation Techniques and a Machine Learning-Based Approach , 2020, Remote. Sens..

[39]  S. Cannon,et al.  Conditions for generation of fire-related debris flows, Capulin Canyon, New Mexico , 2000 .

[40]  Yu Huang,et al.  Review on landslide susceptibility mapping using support vector machines , 2018, CATENA.

[41]  Marco Pagani,et al.  The GEM Global Active Faults Database , 2020 .

[42]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[43]  Jakob van Zyl,et al.  The Shuttle Radar Topography Mission (SRTM): a breakthrough in remote sensing of topography , 2001 .

[44]  B. Pham,et al.  Bagging based Support Vector Machines for spatial prediction of landslides , 2018, Environmental Earth Sciences.

[45]  Naruset Prasertsri,et al.  Spatial Environmental Modeling for Wildfire Progression Accelerating Extent Analysis Using Geo-Informatics , 2020 .

[46]  Jocelyne S. Sze,et al.  Evaluating the social and environmental factors behind the 2015 extreme fire event in Sumatra, Indonesia , 2019, Environmental Research Letters.

[47]  Hailiang Liu,et al.  A Hybrid Model Consisting of Supervised and Unsupervised Learning for Landslide Susceptibility Mapping , 2021, Remote. Sens..

[48]  H. Pourghasemi,et al.  Is multi-hazard mapping effective in assessing natural hazards and integrated watershed management? , 2020 .

[49]  T. Glade,et al.  Landslide Susceptibility Mapping at National Scale: A First Attempt for Austria , 2017 .

[50]  Qingyun Du,et al.  A hybrid model considering spatial heterogeneity for landslide susceptibility mapping in Zhejiang Province, China , 2020 .

[51]  Mikhail F. Kanevski,et al.  Wildfire susceptibility mapping: Deterministic vs. stochastic approaches , 2018, Environ. Model. Softw..

[52]  Yang Lin,et al.  Sensitivity of BCS for Sampling Landslide Absence Data in Landslide Susceptibility Assessment , 2016 .

[53]  S. Jayachandran.  Air Quality and Early-Life Mortality: Evidence from Indonesia's Wildfires , 2008 .

[54]  K. Sassa.  Advancing Culture of Living with Landslides , 2017 .

[55]  Yanli Wu,et al.  Application of alternating decision tree with AdaBoost and bagging ensembles for landslide susceptibility mapping , 2020 .

[56]  H. Pourghasemi,et al.  Assessing and mapping multi-hazard risk susceptibility using a machine learning technique , 2020, Scientific Reports.

[57]  Dong-Kun Lee,et al.  Estimating landslide susceptibility areas considering the uncertainty inherent in modeling methods , 2018, Stochastic Environmental Research and Risk Assessment.

[58]  E. Rotigliano,et al.  Assessment of susceptibility to earth-flow landslide using logistic regression and multivariate adaptive regression splines: A case of the Belice River basin (western Sicily, Italy) , 2015 .

[59]  Chang-ming Wang,et al.  Application and comparison of different ensemble learning machines combining with a novel sampling strategy for shallow landslide susceptibility mapping , 2020, Stochastic Environmental Research and Risk Assessment.

[60]  B. Ridwan,et al.  Development of a Landslide Early Warning System in Indonesia , 2019, Geosciences.

[61]  Tao Guo,et al.  Landslide Susceptibility Mapping Based on Weighted Gradient Boosting Decision Tree in Wanzhou Section of the Three Gorges Reservoir Area (China) , 2018, ISPRS Int. J. Geo Inf..

[62]  G. Rich,et al.  Posttraumatic Growth and Resilience in Southeast Asia , 2020 .

[63]  Kaiwei Zhu,et al.  Flood risk assessment using the CV-TOPSIS method for the Belt and Road Initiative: an empirical study of Southeast Asia , 2020, Ecosystem Health and Sustainability.

[64]  Kang-Tsung Chang,et al.  Modelling the spatial variability of wildfire susceptibility in Honduras using remote sensing and geographical information systems , 2017 .

[65]  Wu Hao,et al.  Predicting Hard Rock Pillar Stability Using GBDT, XGBoost, and LightGBM Algorithms , 2020, Mathematics.

[66]  Saeed Jazebi,et al.  Review of Wildfire Management Techniques—Part I: Causes, Prevention, Detection, Suppression, and Data Analytics , 2020, IEEE Transactions on Power Delivery.

[67]  Wei Chen,et al.  Optimization of Computational Intelligence Models for Landslide Susceptibility Evaluation , 2020, Remote. Sens..

[68]  Marj Tonini,et al.  A Machine Learning-Based Approach for Wildfire Susceptibility Mapping. The Case Study of the Liguria Region in Italy , 2020 .

[69]  Biswajeet Pradhan,et al.  Modeling flood susceptibility using data-driven approaches of naïve Bayes tree, alternating decision tree, and random forest methods. , 2019, The Science of the total environment.

[70]  Biswajeet Pradhan,et al.  Application of convolutional neural networks featuring Bayesian optimization for landslide susceptibility assessment , 2020, CATENA.

[71]  J. Adamowski,et al.  An ensemble prediction of flood susceptibility using multivariate discriminant analysis, classification and regression trees, and support vector machines. , 2019, The Science of the total environment.

[72]  B. Pradhan,et al.  A comparative assessment of flood susceptibility modeling using Multi-Criteria Decision-Making Analysis and Machine Learning Methods , 2019, Journal of Hydrology.

[73]  F. Achard,et al.  Remote sensing of forest degradation in Southeast Asia—Aiming for a regional view through 5–30 m satellite data , 2014 .

[74]  B. Setiawan,et al.  Increased fire hazard in human-modified wetlands in Southeast Asia , 2018, Ambio.

[75]  Dalia Kirschbaum,et al.  Using citizen science to expand the global map of landslides: Introducing the Cooperative Open Online Landslide Repository (COOLR) , 2019, PloS one.

[76]  Thomas Stanley,et al.  A heuristic approach to global landslide susceptibility mapping , 2017, Natural Hazards.

[77]  E. Wood,et al.  Accelerating forest loss in Southeast Asian Massif in the 21st century: A case study in Nan Province, Thailand , 2018, Global change biology.

[78]  Francisco Martínez-Álvarez,et al.  A novel ensemble modeling approach for the spatial prediction of tropical forest fire susceptibility using LogitBoost machine learning classifier and multi-source geospatial data , 2018, Theoretical and Applied Climatology.

[79]  Le Yu,et al.  Mapping global urban boundaries from the global artificial impervious area (GAIA) data , 2020, Environmental Research Letters.

[80]  Ali P. Yunus,et al.  Machine learning methods for landslide susceptibility studies: A comparative overview of algorithm performance , 2020 .

[81]  Makoto Ooba,et al.  The future of Southeast Asia’s forests , 2019, Nature Communications.

[82]  Alaa M. Al-Abadi,et al.  Mapping flood susceptibility in an arid region of southern Iraq using ensemble machine learning classifiers: a comparative study , 2018, Arabian Journal of Geosciences.

[83]  Jens Hartmann,et al.  The new global lithological map database GLiM: A representation of rock properties at the Earth surface , 2012 .

[84]  D. Kirschbaum,et al.  Spatial and temporal analysis of a global landslide catalog , 2015 .

[85]  Hamid Reza Pourghasemi,et al.  Landslide susceptibility mapping using machine learning algorithms and comparison of their performance at Abha Basin, Asir Region, Saudi Arabia , 2021, Geoscience Frontiers.

[86]  Bin Chen,et al.  Stable classification with limited sample: transferring a 30-m resolution sample set collected in 2015 to mapping 10-m resolution global land cover in 2017. , 2019, Science bulletin.

[87]  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 .

[88]  Tri Dev Acharya,et al.  Landslide susceptibility mapping using J48 Decision Tree with AdaBoost, Bagging and Rotation Forest ensembles in the Guangchang area (China) , 2018 .

[89]  Hamid Reza Pourghasemi,et al.  A machine learning framework for multi-hazards modeling and mapping in a mountainous area , 2020, Scientific Reports.

[90]  P. Fulé,et al.  Wildfire effects on forest structure of Pinus merkusii in Sumatra, Indonesia , 2020 .

[91]  Binh Thai Pham,et al.  GIS Based Novel Hybrid Computational Intelligence Models for Mapping Landslide Susceptibility: A Case Study at Da Lat City, Vietnam , 2019 .

[92]  S. L. Kuriakose,et al.  Forests and landslides The role of trees and forests in the prevention of landslides and rehabilitation of landslide-affected areas in Asia , 2011 .

[93]  Samuel S. P. Shen,et al.  Human amplification of drought-induced biomass burning in Indonesia since 1960 , 2009 .

[94]  Philippe Ciais,et al.  Seasonal and interannual changes in vegetation activity of tropical forests in Southeast Asia , 2016 .

[95]  Markus Meinhardt,et al.  Landslide susceptibility analysis in central Vietnam based on an incomplete landslide inventory: Comparison of a new method to calculate weighting factors by means of bivariate statistics , 2015 .

[96]  C. Justice,et al.  Trends in Vegetation fires in South and Southeast Asian Countries , 2019, Scientific Reports.

[97]  K. Takeuchi,et al.  Floods and Exports: An Empirical Study on Natural Disaster Shocks in Southeast Asia , 2018, Economics of Disasters and Climate Change.

[98]  Yenni Vetrita,et al.  Fire Frequency and Related Land-Use and Land-Cover Changes in Indonesia's Peatlands , 2019, Remote. Sens..

[99]  Shuai Yin.  Biomass burning spatiotemporal variations over South and Southeast Asia. , 2020, Environment international.