Multi-Hazard Exposure Mapping Using Machine Learning Techniques: A Case Study from Iran

被引:67
作者
Rahmati, Omid [1 ,2 ]
Yousefi, Saleh [3 ]
Kalantari, Zahra [4 ,5 ]
Uuemaa, Evelyn [6 ,7 ]
Teimurian, Teimur [8 ]
Keesstra, Saskia [9 ]
Tien Dat Pham [10 ]
Dieu Tien Bui [11 ]
机构
[1] Ton Duc Thang Univ, Geog Informat Sci Res Grp, Ho Chi Minh 758307, Vietnam
[2] Ton Duc Thang Univ, Fac Environm & Labour Safety, Ho Chi Minh 758307, Vietnam
[3] AREEO, Chaharmahal & Bakhtiari Agr & Nat Resources Res &, Soil Conservat & Water Management Res Dept, Shahrekord 8814843114, Iran
[4] Stockholm Univ, Dept Phys Geog, SE-10691 Stockholm, Sweden
[5] Stockholm Univ, Bolin Ctr Climate Res, SE-10691 Stockholm, Sweden
[6] Univ Tartu, Dept Geog, Vanemuise St 46, EE-51003 Tartu, Estonia
[7] NIWA, Gate 10 Silverdale Rd, Hamilton 3216, New Zealand
[8] Univ Tehran, Fac Nat Resources, Karaj 3158777871, Iran
[9] Wageningen Univ, Soil Phys & Land Management Grp, Droevendaalsesteeg 4, NL-6708 PB Wageningen, Netherlands
[10] VNUA, CARES, Hanoi 100000, Vietnam
[11] Duy Tan Univ, Inst Res & Dev, Da Nang 550000, Vietnam
关键词
natural disasters; Sentinel-1; hazard; artificial intelligence; Asara watershed; SUSCEPTIBILITY ASSESSMENT; FLOOD PROBABILITY; NATURAL HAZARDS; GULLY EROSION; LANDSLIDE; MODEL; RISK; SOIL; CHALLENGES; REGION;
D O I
10.3390/rs11161943
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Mountainous areas are highly prone to a variety of nature-triggered disasters, which often cause disabling harm, death, destruction, and damage. In this work, an attempt was made to develop an accurate multi-hazard exposure map for a mountainous area (Asara watershed, Iran), based on state-of-the art machine learning techniques. Hazard modeling for avalanches, rockfalls, and floods was performed using three state-of-the-art models-support vector machine (SVM), boosted regression tree (BRT), and generalized additive model (GAM). Topo-hydrological and geo-environmental factors were used as predictors in the models. A flood dataset (n = 133 flood events) was applied, which had been prepared using Sentinel-1-based processing and ground-based information. In addition, snow avalanche (n = 58) and rockfall (n = 101) data sets were used. The data set of each hazard type was randomly divided to two groups: Training (70%) and validation (30%). Model performance was evaluated by the true skill score (TSS) and the area under receiver operating characteristic curve (AUC) criteria. Using an exposure map, the multi-hazard map was converted into a multi-hazard exposure map. According to both validation methods, the SVM model showed the highest accuracy for avalanches (AUC = 92.4%, TSS = 0.72) and rockfalls (AUC = 93.7%, TSS = 0.81), while BRT demonstrated the best performance for flood hazards (AUC = 94.2%, TSS = 0.80). Overall, multi-hazard exposure modeling revealed that valleys and areas close to the Chalous Road, one of the most important roads in Iran, were associated with high and very high levels of risk. The proposed multi-hazard exposure framework can be helpful in supporting decision making on mountain social-ecological systems facing multiple hazards.
引用
收藏
页数:20
相关论文
共 80 条
[1]   Assessing the accuracy of species distribution models: prevalence, kappa and the true skill statistic (TSS) [J].
Allouche, Omri ;
Tsoar, Asaf ;
Kadmon, Ronen .
JOURNAL OF APPLIED ECOLOGY, 2006, 43 (06) :1223-1232
[2]  
[Anonymous], GEN ADDITIVE MODELS
[3]  
[Anonymous], 2001, J. Am. Stat. Assoc.
[4]  
Anzai Y., 2012, Pattern Recognition and Machine Learning
[5]   A Case Study on Seasonal Floods in Iran, Watershed of Ghotour Chai Basin [J].
Asgharpour, Seyed Esmaeil ;
Ajdari, Behrouz .
2ND INTERNATIONAL GEOGRAPHY SYMPOSIUM-MEDITERRANEAN ENVIRONMENT 2010, 2011, 19 :556-566
[6]   Avalanche hazard mapping over large undocumented areas [J].
Barbolini, M. ;
Pagliardi, M. ;
Ferro, F. ;
Corradeghini, P. .
NATURAL HAZARDS, 2011, 56 (02) :451-464
[7]   Major flood disasters in Europe: 1950-2005 [J].
Barredo, Jose I. .
NATURAL HAZARDS, 2007, 42 (01) :125-148
[8]   A trend analysis of normalized insured damage from natural disasters [J].
Barthel, Fabian ;
Neumayer, Eric .
CLIMATIC CHANGE, 2012, 113 (02) :215-237
[9]  
Bell R., 2012, Landslides, P1
[10]   Hybrid integration of Multilayer Perceptron Neural Networks and machine learning ensembles for landslide susceptibility assessment at Himalayan area (India) using GIS [J].
Binh Thai Pham ;
Dieu Tien Bui ;
Prakash, Indra ;
Dholakia, M. B. .
CATENA, 2017, 149 :52-63