Rapid forecasting of urban flood inundation using multiple machine learning models

Natural Hazards - Urban flood inundation is worsening as the number of short-duration rainstorms increases, and it is difficult to accurately predict urban flood inundation over a long lead time;...     

Municipal flood hazard mapping: the case of British Columbia,Canada

Historical responses to flood hazards have stimulated development in hazardous areas. Scholars recommend an alternative approach to reducing flood losses that combines flood hazard mapping with land use planning to identify and direct development away from flood-prone areas. Creating flood hazard maps to inform municipal land use planning is an expensive and complex process that can require resources not always available at the municipal government level. Senior levels of government in some countries have addressed deficiencies in municipal capacity by assuming an active role in producing municipal flood hazard maps. In other countries, however, senior governments do not contribute to municipal flood hazard mapping. Despite a large body of research on the importance of municipal land use planning for addressing flood hazards, little is known about the extent of flood hazard information that is available to municipalities that do not receive outside assistance from senior governments for flood hazard mapping. We assess the status of flood hazard maps in British Columbia, where municipalities do not receive outside assistance in creating the maps. Our analysis shows that these maps are generally outdated and/or lacking a variety of features that are critical for supporting effective land use planning. We recommend that senior levels of government play an active role in providing municipalities with (1) detailed and current information regarding flood hazards in their jurisdiction and (2) compelling incentives to utilize this information.     

Comparison of machine learning models for gully erosion susceptibility mapping

Gully erosion is a disruptive phenomenon which extensively affects the Iranian territory,especially in the Northern provinces.A number of studies have been recently undertaken to study this process and to predict it over space and ultimately,in a broader national effort,to limit its negative effects on local communities.We focused on the Bastam watershed where 9.3% of its surface is currently affected by gullying.Machine learning algorithms are currently under the magnifying glass across the geomorphological community for their high predictive ability.However,unlike the bivariate statistical models,their structure does not provide intuitive and quantifiable measures of environmental preconditioning factors.To cope with such weakness,we interpret preconditioning causes on the basis of a bivariate approach namely,Index of Entropy.And,we performed the susceptibility mapping procedure by testing three extensions of a decision tree model namely,Alternating Decision Tree(ADTree),Naive-Bayes tree(NBTree),and Logistic Model Tree(LMT).We dichotomized the gully information over space into gully presence/absence conditions,which we further explored in their calibration and validation stages.Being the presence/absence information and associated factors identical,the resulting differences are only due to the algorithmic structures of the three models we chose.Such differences are not significant in terms of performances;in fact,the three models produce outstanding predictive AUC measures(ADTree=0.922;NBTree=0.939;LMT=0.944).However,the associated mapping results depict very different patterns where only the LMT is associated with reasonable susceptibility patterns.This is a strong indication of what model combines best performance and mapping for any natural hazard-oriented application.     

Juggling through Ghanaian urbanisation: flood hazard mapping of Kumasi

More recently, driven by rapid and unguided urbanisation and climate change, Ghanaian cities are increasingly becoming hotspots for severe flood-related events. This paper reviews urbanisation dynamics in Ghanaian cities, and maps flood hazard zones and access to flood relief services in Kumasi, drawing insight from multi-criteria analysis and spatial network analysis using ArcGIS 10.2. Findings indicate that flood hazard zones in Kumasi have been created by natural (e.g., climate change) and anthropogenic (e.g., urbanisation) factors, and the interaction thereof. While one would have expected the natural factors to guide, direct and steer the patterns of urban development from flood hazard zones, the GIS analysis shows that anthropogenic factors, particularly urbanisation, are increasingly concentrating population and physical structures in areas liable to flooding in the urban environment. This situation is compounded by rapid land cover/use changes and widespread haphazard development across the city. Regrettably, findings show that urban residents living in flood hazard zones in Kumasi are also geographically disadvantaged in terms of access to emergency services compared to those living in well-planned neighbourhoods.     

Landslide hazard mapping at Selangor, Malaysia using frequency ratio and logistic regression models

The aim of this study is to evaluate the landslide hazards at Selangor area, Malaysia, using Geographic Information System (GIS) and Remote Sensing. Landslide locations of the study area were identified from aerial photograph interpretation and field survey. Topographical maps, geological data, and satellite images were collected, processed, and constructed into a spatial database in a GIS platform. The factors chosen that influence landslide occurrence were: slope, aspect, curvature, distance from drainage, lithology, distance from lineaments, land cover, vegetation index, and precipitation distribution. Landslide hazardous areas were analyzed and mapped using the landslide-occurrence factors by frequency ratio and logistic regression models. The results of the analysis were verified using the landslide location data and compared with probability model. The comparison results showed that the frequency ratio model (accuracy is 93.04%) is better in prediction than logistic regression (accuracy is 90.34%) model.     

Characterizing flood hazard risk in data-scarce areas,using a remote sensing and GIS-based flood hazard index

The frequency in occurrence and severity of floods has increased globally. However, many regions around the globe, especially in developing countries, lack the necessary field monitoring data to characterize flood hazard risk. This paper puts forward methodology for developing flood hazard maps that define flood hazard risk, using a remote sensing and GIS-based flood hazard index (FHI), for the Nyamwamba watershed in western Uganda. The FHI was compiled using analytical hierarchy process and considered slope, flow accumulation, drainage network density, distance from drainage channel, geology, land use/cover and rainfall intensity as the flood causative factors. These factors were derived from Landsat, SRTM and PERSIANN remote sensing data products, except for geology that requires field data. The resultant composite FHI yielded a flood hazard map pointing out that over 11 and 18% of the study area was very highly and highly susceptible to flooding, respectively, while the remaining area ranged from medium to very low risk. The resulting flood hazard map was further verified using inundation area of a historical flood event in the study area. The proposed methodology was effective in producing a flood hazard map at the watershed local scale, in a data-scarce region, useful in devising flood mitigation measures.     

Flood susceptibility modelling using advanced ensemble machine learning models

Floods are one of nature's most destructive disasters because of the immense damage to land, buildings, and human fatalities.It is difficult to forecast the areas that are vulnerable to flash flooding due to the dynamic and complex nature of the flash floods.Therefore, earlier identification of flash flood susceptible sites can be performed using advanced machine learning models for managing flood disasters.In this study, we applied and assessed two new hybrid ensemble models, namely Dagging and Random Subspace(RS) coupled with Artificial Neural Network(ANN), Random Forest(RF), and Support Vector Machine(SVM) which are the other three state-of-the-art machine learning models for modelling flood susceptibility maps at the Teesta River basin, the northern region of Bangladesh.The application of these models includes twelve flood influencing factors with 413 current and former flooding points, which were transferred in a GIS environment.The information gain ratio, the multicollinearity diagnostics tests were employed to determine the association between the occurrences and flood influential factors.For the validation and the comparison of these models, for the ability to predict the statistical appraisal measures such as Freidman, Wilcoxon signed-rank, and t-paired tests and Receiver Operating Characteristic Curve(ROC) were employed.The value of the Area Under the Curve(AUC) of ROC was above 0.80 for all models.For flood susceptibility modelling, the Dagging model performs superior, followed by RF,the ANN, the SVM, and the RS, then the several benchmark models.The approach and solution-oriented outcomes outlined in this paper will assist state and local authorities as well as policy makers in reducing flood-related threats and will also assist in the implementation of effective mitigation strategies to mitigate future damage.     

Earthquake-induced liquefaction hazard mapping at national-scale in Australia using deep learning techniques

Australia is a relatively stable continental region but not tectonically inert, having geological conditions that are susceptible to liquefaction when subjected to earthquake ground motion. Liquefaction hazard assessment for Australia was conducted because no Australian liquefaction maps that are based on modern AI techniques are currently available. In this study, several conditioning factors including Shear wave velocity (Vs30), clay content, soil water content, soil bulk density, soil thickness, soil pH, distance from river, slope and elevation were considered to estimate the liquefaction potential index (LPI). By considering the Probabilistic Seismic Hazard Assessment (PSHA) technique, peak ground acceleration (PGA) was derived for 50 yrs period (500 and 2500 yrs return period) in Australia. Firstly, liquefaction hazard index (LHI) (effects based on the size and depth of the liquefiable areas) was estimated by considering the LPI along with the 2% and 10% exceedance probability of earthquake hazard. Secondly, ground acceleration data from the Geoscience Australia projecting 2% and 10% exceedance rate of PGA for 50 yrs were used in this study to produce earthquake induced soil liquefaction hazard maps. Thirdly, deep neural networks (DNNs) were also exerted to estimate liquefaction hazard that can be reported as liquefaction hazard base maps for Australia with an accuracy of 94% and 93%, respectively. As per the results, very-high liquefaction hazard can be observed in Western and Southern Australia including some parts of Victoria. This research is the first ever country-scale study to be considered for soil liquefaction hazard in Australia using geospatial information in association with PSHA and deep learning techniques. This study used an earthquake design magnitude threshold of M_w 6 using the source model characterization. The resulting maps present the earthquake-triggered liquefaction hazard and are intending to establish a conceptual structure to guide more detailed investigations as may be required in the future. The limitations of deep learning models are complex and require huge data, knowledge on topology, parameters, and training method whereas PSHA follows few assumptions. The advantages deal with the reusability of model codes and its transferability to other similar study areas. This research aims to support stakeholders’ on decision making for infrastructure investment, emergency planning and prioritisation of post-earthquake reconstruction projects.     

Flood-prone area mapping using machine learning techniques: a case study of Quang Binh province,Vietnam

Natural Hazards - Vietnam’s central coastal region is the most vulnerable and always at flood risk, severely affecting people’s livelihoods and socio-economic development. In...     

MODIS-FIRMS and ground-truthing-based wildfire likelihood mapping of Sikkim Himalaya using machine learning algorithms

Natural Hazards - Wildfires in limited extent and intensity can be a boon for the forest ecosystem. However, recent episodes of wildfires of 2019 in Australia and Brazil are sad reminders of their...     

Simulating storm surge waves for structural vulnerability estimation and flood hazard mapping

Natural Hazards - Wave action during storm surge is a common cause of building damage and therefore a critical consideration when estimating structural vulnerability and mapping flood risk....     

Improved flood susceptibility mapping using a best first decision tree integrated with ensemble learning techniques

Improving the accuracy of flood prediction and mapping is crucial for reducing damage resulting from flood events. In this study, we proposed and validated three ensemble models based on the Best First Decision Tree (BFT) and the Bagging (Bagging-BFT), Decorate (Bagging-BFT), and Random Subspace (RSS-BFT) ensemble learning techniques for an improved prediction of flood susceptibility in a spatially-explicit manner. A total number of 126 historical flood events from the Nghe An Province (Vietnam) were connected to a set of 10 flood influencing factors (slope, elevation, aspect, curvature, river density, distance from rivers, flow direction, geology, soil, and land use) for generating the training and validation datasets. The models were validated via several performance metrics that demonstrated the capability of all three ensemble models in elucidating the underlying pattern of flood occurrences within the research area and predicting the probability of future flood events. Based on the Area Under the receiver operating characteristic Curve (AUC), the ensemble Decorate-BFT model that achieved an AUC value of 0.989 was identified as the superior model over the RSS-BFT (AUC = 0.982) and Bagging-BFT (AUC = 0.967) models. A comparison between the performance of the models and the models previously reported in the literature confirmed that our ensemble models provided a reliable estimate of flood susceptibilities and their resulting susceptibility maps are trustful for flood early warning systems as well as development of mitigation plans.     

Comparing classical statistic and machine learning models in landslide susceptibility mapping in Ardanuc (Artvin), Turkey

Natural Hazards - Landslide susceptibility maps provide crucial information that helps local authorities, public institutions, and land-use planners make the correct decisions when they are...     

Assessing flood hazard using flood marks and analytic hierarchy process approach: a case study for the 2013 flood event in Quang Nam,Vietnam

The production of flood hazard assessment maps is an important component of flood risk assessment. This study analyses flood hazard using flood mark data. The chosen case study is the 2013 flood event in Quang Nam, Vietnam. The impacts of this event included 17 deaths, 230 injuries, 91,739 flooded properties, 11,530 ha of submerged and damaged agricultural land, 85,080 animals killed and widespread damage to roads, canals, dykes and embankments. The flood mark data include flood depth and flood duration. Analytic hierarchy process method is used to assess the criteria and sub-criteria of the flood hazard. The weights of criteria and sub-criteria are generated based on the judgements of decision-makers using this method. This assessment is combined into a single map using weighted linear combination, integrated with GIS to produce a flood hazard map. Previous research has usually not considered flood duration in flood hazard assessment maps. This factor has a rather strong influence on the livelihood of local communities in Quang Nam, with most agricultural land within the floodplain. A more comprehensive flood hazard assessment mapping process, with the additional consideration of flood duration, can make a significant contribution to flood risk management activities in Vietnam.     

Comparison of new individual and hybrid machine learning algorithms for modeling and mapping fire hazard: a supplementary analysis of fire hazard in different counties of Golestan Province in Iran

Natural Hazards - The forest fire hazard mapping using the accurate models in the fire-prone areas has particular importance to predict the future fire occurrence and allocate the resources for...     

Prediction of CBR and resilient modulus of crushed waste rocks using machine learning models

Acta Geotechnica - California bearing ratio (CBR) and resilient modulus are critical factors for designing pavements. However, the measurement of CBR and resilient modulus of crushed waste rocks...     

Recognition of debris flow,debris flood and flood hazard through watershed morphometrics

Debris flows, debris floods and floods in mountainous areas are responsible for loss of life and damage to infrastructure, making it important to recognize these hazards in the early stage of planning land developments. Detailed terrain information is seldom available and basic watershed morphometrics must be used for hazard identification. An existing model uses watershed area and relief (the Melton ratio) to differentiate watersheds prone to flooding from those subject to debris flows and debris floods. However, the hazards related to debris flows and debris floods are not the same, requiring further differentiation. Here, we demonstrate that a model using watershed length combined with the Melton ratio can be used to differentiate debris-flow and debris-flood prone watersheds. This model was tested on 65 alluvial and colluvial fans in west central British Columbia, Canada, that were examined in the field. The model correctly identified 92% of the debris-flow, 83% of the debris-flood, and 88% of the flood watersheds. With adaptation for different regional conditions, the use of basic watershed morphometrics could assist land managers, scientists, and engineers with the identification of hydrogeomorphic hazards on fans elsewhere.     

Landslide susceptibility mapping using machine learning algorithms and comparison of their performance at Abha Basin,Asir Region,Saudi Arabia

The current study aimed at evaluating the capabilities of seven advanced machine learning techniques(MLTs),including,Support Vector Machine(SVM),Random Forest(RF),Multivariate Adaptive Regression Spline(MARS),Artificial Neural Network(ANN),Quadratic Discriminant Analysis(QDA),Linear Discriminant Analysis(LDA),and Naive Bayes(NB),for landslide susceptibility modeling and comparison of their performances.Coupling machine learning algorithms with spatial data types for landslide susceptibility mapping is a vitally important issue.This study was carried out using GIS and R open source software at Abha Basin,Asir Region,Saudi Arabia.First,a total of 243 landslide locations were identified at Abha Basin to prepare the landslide inventory map using different data sources.All the landslide areas were randomly separated into two groups with a ratio of 70%for training and 30%for validating purposes.Twelve landslide-variables were generated for landslide susceptibility modeling,which include altitude,lithology,distance to faults,normalized difference vegetation index(NDVI),landuse/landcover(LULC),distance to roads,slope angle,distance to streams,profile curvature,plan curvature,slope length(LS),and slope-aspect.The area under curve(AUC-ROC)approach has been applied to evaluate,validate,and compare the MLTs performance.The results indicated that AUC values for seven MLTs range from 89.0%for QDA to 95.1%for RF.Our findings showed that the RF(AUC=95.1%)and LDA(AUC=941.7%)have produced the best performances in comparison to other MLTs.The outcome of this study and the landslide susceptibility maps would be useful for environmental protection.     

Flash flood susceptibility mapping using a novel deep learning model based on deep belief network,back propagation and genetic algorithm

Flash floods are responsible for loss of life and considerable property damage in many countries.Flood susceptibility maps contribute to flood risk reduction in areas that are prone to this hazard if appropriately used by landuse planners and emergency managers.The main objective of this study is to prepare an accurate flood susceptibility map for the Haraz watershed in Iran using a novel modeling approach(DBPGA) based on Deep Belief Network(DBN) with Back Propagation(BP) algorithm optimized by the Genetic Algorithm(GA).For this task, a database comprising ten conditioning factors and 194 flood locations was created using the One-R Attribute Evaluation(ORAE) technique.Various well-known machine learning and optimization algorithms were used as benchmarks to compare the prediction accuracy of the proposed model.Statistical metrics include sensitivity,specificity accuracy, root mean square error(RMSE), and area under the receiver operatic characteristic curve(AUC) were used to assess the validity of the proposed model.The result shows that the proposed model has the highest goodness-of-fit(AUC = 0.989) and prediction accuracy(AUC = 0.985), and based on the validation dataset it outperforms benchmark models including LR(0.885), LMT(0.934), BLR(0.936), ADT(0.976), NBT(0.974), REPTree(0.811), ANFIS-BAT(0.944), ANFIS-CA(0.921), ANFIS-IWO(0.939), ANFIS-ICA(0.947), and ANFIS-FA(0.917).We conclude that the DBPGA model is an excellent alternative tool for predicting flash flood susceptibility for other regions prone to flash floods.