A novel hybrid approach of Bayesian Logistic Regression and its ensembles for landslide susceptibility assessment

Abstract

A novel artificial intelligence approach of Bayesian Logistic Regression (BLR) and its ensembles [Random Subspace (RS), Adaboost (AB), Multiboost (MB) and Bagging] was introduced for landslide susceptibility mapping in a part of Kamyaran city in Kurdistan Province, Iran. A spatial database was generated which includes a total of 60 landslide locations and a set of conditioning factors tested by the Information Gain Ratio technique. Performance of these models was evaluated using the area under the ROC curve (AUROC) and statistical index-based methods. Results showed that the hybrid ensemble models could significantly improve the performance of the base classifier of BLR (AUROC?=?0.930). However, RS model (AUROC?=?0.975) had the highest performance in comparison to other landslide ensemble models, followed by Bagging (AUROC?=?0.972), MB (AUROC?=?0.970) and AB (AUROC?=?0.957) models, respectively.     

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.     

An Agent‐Based Simulation of Residential Location Choice of Tenants in Tehran,Iran

Residential location choice modeling is one of the substantial components of land use and transportation models. While numerous aggregated mathematical and statistical approaches have been developed to model the residence choice behavior of households, disaggregated approaches such as the agent‐based modeling have shown interesting capabilities. In this article, a novel agent‐based approach is developed to simulate the residential location choice of tenants in Tehran, the capital of Iran. Tenants are considered as agents who select their desired residential alternatives according to their characteristics and preferences for various criteria such as the rent, accessibility to different services and facilities, environmental pollution, and distance from their workplace and former residence. The choice set of agents is limited to their desired residential alternatives by applying a constrained NSGA‐II algorithm. Then, agents compete with each other to select their final residence among their alternatives. Results of the proposed approach are validated by comparing simulated and actual residences of a sample of tenants. Results show that the proposed approach is able to accurately simulate the residence of 59.3% of tenants at the traffic analysis zone level.     

Landslide susceptibility analysis with a bivariate approach and GIS in Northern Iran

Globally, landslides cause hundreds of billions of dollars in damage and hundreds of thousands of deaths and injuries each year. A landslide susceptibility map describes areas where landslides are likely to occur in the future by correlating some of the principal factors that contribute to landslides with the past distribution of landslides. A case study is conducted in the mountainous northern Iran. In this study, a landslide susceptibility map of the study area was prepared using bivariate method with the help of the geographic information system. Area density (bivariate) method was used to weight landslide-influencing data layers. An overlay analysis is carried out by evaluating the layers obtained according to their weight and the landslide susceptibility map is produced. The study area was classified into five hazard classes: very low, low, moderate, high, and very high. The percentage distribution of landslide susceptibility degrees was calculated. It was found that about 26% of the study area is classified as very high and high hazard classes.     

Mapping landslide susceptibility with frequency ratio,statistical index,and weights of evidence models: a case study in northern Iran

The main objective of this study is to investigate potential application of frequency ratio (FR), weights of evidence (WoE), and statistical index (SI) models for landslide susceptibility mapping in a part of Mazandaran Province, Iran. First, a landslide inventory map was constructed from various sources. The landslide inventory map was then randomly divided in a ratio of 70/30 for training and validation of the models, respectively. Second, 13 landslide conditioning factors including slope degree, slope aspect, altitude, plan curvature, stream power index, topographic wetness index, sediment transport index, topographic roughness index, lithology, distance from streams, faults, roads, and land use type were prepared, and the relationships between these factors and the landslide inventory map were extracted by using the mentioned models. Subsequently, the multi-class weighted factors were used to generate landslide susceptibility maps. Finally, the susceptibility maps were verified and compared using several methods including receiver operating characteristic curve with the areas under the curve (AUC), landslide density, and spatially agreed area analyses. The success rate curve showed that the AUC for FR, WoE, and SI models was 81.51, 79.43, and 81.27, respectively. The prediction rate curve demonstrated that the AUC achieved by the three models was 80.44, 77.94, and 79.55, respectively. Although the sensitivity analysis using the FR model revealed that the modeling process was sensitive to input factors, the accuracy results suggest that the three models used in this study can be effective approaches for landslide susceptibility mapping in Mazandaran Province, and the resultant susceptibility maps are trustworthy for hazard mitigation strategies.     

Deep learning neural networks for spatially explicit prediction of flash flood probability

Flood probability maps are essential for a range of applications, including land use planning and developing mitigation strategies and early warning systems. Th...     

Flow discharge simulation based on land use change predictions

Haraz River is one of the most important rivers in Iran, which has been faced with successive inappropriate land use changes and environmental degradation practices in recent decades. In this way, the impact of land use changes on stream flow generation, evaporation and hydrological processes of the Haraz basin has been studied. Land use maps for the years of 1988, 2000 and 2013 were prepared and assessed for any changes in land use using land change modeler and logistic regression methods. GEOMOD method was also used for accuracy tests of models. The calibration periods of 1988–2000, 1988–2013 and also Markov chain with hard prediction model were applied in order to predict the future land use for 2025. Besides, SWAT model was used to evaluate the watershed-scale impacts of land use change. Evaluating the calibration periods using GEOMOD method and some parameters showed a more accurate prediction for the period of 1988–2013 than the 1988–2000 period. Likewise, the results indicated that the rate of changes from 2013 to 2025 will be decreased in terms of forest and range lands (6751.05 and 168,09.01 ha, respectively) and will be increased in terms of residential areas, irrigated farming, gardens and bare lands up to 1567.2, 1405.68, 3039.38 and 174,05.55 ha, respectively. The assessment of model efficiency showed that the SWAT model has acceptable performance to simulate the flow discharge. Overall, the model outcomes indicated that land use changes lead to increase the average runoff in the study area. As a matter of fact, this issue has significant effects on water resources, economic and social situations, and hence, efficient strategies are needed for an integrated management in the Haraz basin.     

Impact of season and road on stream crossings and river water quality in Darabkola,hyrcanian forest

Nutrients are important building blocks for healthy aquatic ecosystems and are generally nontoxic; but they can change with alteration in environmental parameters. The main objective of this study was to consider the seasonal variability of NO ₃ ^– , PO ₄ ^3– and total suspended solids (TSS) concentrations in water. The study sites, stream crossings (L30, L15) and river (R), are located in the hyrcanian forests, district 1 of Darabkola forest. The sampling was conducted in winter and spring. Water samples were taken into plastic bottles, labeled, and carried out to the laboratory for NO ₃ ^– , PO ₄ ^3– and TSS analysis. T-test results showed that there was a seasonal change in nutrient concentrations (p < 0.05) except for NO ₃ ^– concentration at L30. Also, there was no significant seasonal change in TSS concentrations at all stations. Pearson correlation analysis did not reveal the same trend. Further analysis showed that the effect of road age on water quality parameters was statistically significant for PO ₄ ^3– in spring and winter. Atmospheric precipitation plays vital role in nutrient loss and increasing concentration of suspended sediment. To prevent soil erosion from activities and discharge of wastes in the vicinity of river and stream an effective management should be planned and enforced.     

Soil loss and displacement by heavy equipment in forest road subgrading projects

Forest soil is an important component of the natural environment, and is a primary medium for many biological activities. In this study, soil loss and displacement by excavator and bulldozer （heavy equipments） were measured on cut and fills slopes of forest roads located in Mazandaran province, lran. The volumes of soil losses were estimated by prismoidal analyses of cut and fill slopes deformation between two time treatments （under subgrading and two years later） in slope classes of 30-50% and 50-70%. Weights of soil losses were calculated by multiplying the volumes of soil losses （cm^3） to the general bulk density （1.3g/cm^3）. Soil displaced area by heavy equipment was evaluated according to earth working width. Results indicated that heavy equipment has significant effect on deformation of cut slope gradient and fill slope length （p〈0.0001）. During the two-year period, the cut （p〈0.0002） and fill （p〈0.0001） slope gradients were significantly deformed in different slope classes. The average soil loss by excavator and bulldozer were 160.35 t/ha·yr and 429.09 t/ha·yr, respectively. Moreover, the soil displaced area during the subgrading process by bulldozer was greater than excavator in both two slope classes （p〈0.05）. Soil loss and displacement in forest roads can be rednced by applying powerful excavators in subgrading project, especially in steep terrains.