Search

The purpose of this investigation is to develop an optimal model to flood susceptibility mapping in the Kan watershed, Tehran, Iran. Therefore, in this study, three Bayesian optimization hyperparameter algorithms including Upper confidence bound (UCB), Probability of improvement (PI) and Expected improvement (EI) in order to Extreme Gradient Boosting (XGB) machine learning model optimization and Extreme randomize tree (ERT) model for modeling flood hazard were used. In order to perform flood susceptibility mapping, 118 historic flood locations were identified and analyzed using 17 geo-environmental explanatory variables to predict flooding susceptibility. Flood locations data were divided into 70% for training and 30% for testing of models developed. The receiver operating characteristic (ROC) curve parameters were used to evaluate the performance of the models. The evaluation results based on the criterion area under curve (AUC) in the testing stage showed that the ERT and XGB models have efficiencies of 91.37% and 91.95%, respectively. The evaluation of the efficiency of Bayesian hyperparameters optimization methods on the XGB model also showed that these methods increase the efficiency of the XGB model, so that the model efficiency using these methods EI-XGB, POI-XGB and UCB-XGB based on the AUC in the testing stage were 95.89%, 96.87% and 96.38%, respectively. The results of the relative importance of the five models shows that the variables of elevation and distance from the river are the significant compared to other variables in predicting flood hazard in the Kan watershed. [ABSTRACT FROM AUTHOR]

Landslides are most catastrophic and frequently occurred across the world. In mountainous areas of the globe, recurrent occurrences of landslide have caused huge amount of economic losses and a large number of casualties. In this research, we attempted to estimate the potential impact of climate and LULC on future landslide susceptibility in of Markazi Province of Iran. We considered the boosted tree (BT), random forest (RF) and extremely randomized tree (ERT) models for landslide susceptibility assessment in Markazi Province. The results of evaluation criteria showed that ERT model is most optimal than other models used in this study with AUC values of 0.99 and 0.93 for the training and validation datasets, respectively. According to the ERT model, the spatial coverage of the very high and high land slide susceptible zones for the current period, 2050s considering RCP 2.6 and 2050s considering RCP 8.5 are 428.5 km², 439.6 km² and 465.2 km² it is clear that the impact of climate and LULC changes on future landslide susceptibility is prominent. The results of the present study help managers to reduce landslide damages, not only for current but also for future conditions, based on climate and LULC changes. [ABSTRACT FROM AUTHOR]

The main aim of this research is to predict the impact of seasonal precipitation regimes on flood hazard applying machine learning models. For this purpose, twelve static variables and eight rainfall dynamics variables for 2050s (RCP 2.6 and 8.5) were used as conditioning factors. Four machine learning algorithms including K-Nearest Neighbour (KNN), Extremely Randomize Trees (ERT), Random Forest (RF) and Oblique-Random Forest (ORF) were used to model flood risk. Considering the area under curve (AUC) and other indices, the ORF was the most optimal model. The AUC of the KNN, ERT, RF and ORF for the validation datasets were 0.85, 0.90, 0.89 and 0.92 respectively. The results showed that under two RCPs, spatial distribution of high flood risk areas will change in the future and the trends will be different from the current. These results could provide valuable insights in simulating, predicting and reducing future flood risk. [ABSTRACT FROM AUTHOR]

Delineation of the groundwater's potential zones is a growing phenomenon worldwide due to the high demand for fresh groundwater. Therefore, the identification of potential groundwater zones is an important tool for groundwater occurrence, protection, and management purposes. More specifically, in arid and semi-arid regions, groundwater is one of the most important natural resources as it supplies water during the drought period. The present research study focused on the delineation of potential groundwater zones in Saveh City, the northern part of the Markazi Province in Iran. The groundwater potential mapping was prepared using hybrid deep learning and machine learning algorithm of the boosted tree (BT), artificial neural network (ANN), deep learning neural network (DLNN), deep learning tree (DLT), and deep boosting (DB). This study was carried out by using fourteen groundwater potential conditioning factors and 349 each for springs and non-springs points. The performance of each model was validated through statistical analysis of sensitivity, specificity, positive predictive values (PPV), negative predictive values (NPV), and receiver operating characteristic (ROC)-area under curve (AUC) analysis. The validation result showed that the success rate of AUC is very good for the DB model (0.87–0.99) and other models are also good i.e. BT (0.81–0.90), ANN (0.77–0.82), DLNN (0.84–0.86), and DLT (0.83–0.91). Among the several factors used in this study altitude, rainfall, distance to fault and soil types are the more important conditioning factors for groundwater potential modeling. Finally, all the models in this study had high efficiency in groundwater potential mapping, but it is recommended to use the Deep Boost model due to the better results in future studies. The result of this work will be useful to planners for optimal use and future planning of groundwater. [ABSTRACT FROM AUTHOR]

Piping erosion is one of the water erosions that cause significant changes in the landscape, leading to environmental degradation. To prevent losses resulting from tube growth and enable sustainable development, developing high-precision predictive algorithms for piping erosion is essential. Boosting is a classic algorithm that has been successfully applied to diverse computer vision tasks. Therefore, this work investigated the predictive performance of the Boosted Linear Model (BLM), Boosted Regression Tree (BRT), Boosted Generalized Linear Model (Boost GLM), and Deep Boosting models for piping erosion susceptibility mapping in Zarandieh Watershed located in the Markazi province of Iran. A piping inventory map including 152 piping erosion locations was prepared for algorithm training and testing. 18 initial predisposing factors (altitude, slope, plan curvature, profile curvature, distance from river, drainage density, distance from road, rainfall, land use, soil type, bulk density, CEC, pH, clay, silt, sand, topographical position index (TPI), topographic wetness index (TWI)) was derived from multiple remote sensing (RS) sources to determine the piping erosion prone areas. The most significant predisposing factors were selected using multi-collinearity analysis which indicates linear correlations between predisposing factors. Finally, the results were evaluated for Sensitivity, Specificity, Positive predictive values (PPV) and Negative predictive value (NPV), and Receiver Operation characteristic (ROC) curve. The best Sensitivity (0.80), Specificity (0.84), PPV (0.85), NPV (0.79), and ROC (0.93), were obtained by Deep Boosting model. The results of the piping erosion susceptibility study in agricultural land use showed that 41% of agricultural lands are very sensitive to piping erosion. This outcome will enable natural resource managers and local planners to assess and take effective decisions to minimize damages to agricultural land use by accurately identifying the most vulnerable areas. Hence, this research proved Deep Boosting model's ability for piping erosion susceptibility mapping in comparison to other popular methods such as BLM, BRT, and Boost GLM. [ABSTRACT FROM AUTHOR]

The mountainous watersheds are increasingly challenged with extreme erosions and devastating floods due to climate change and human interventions. Hazard mapping is essential for local policymaking for prevention, planning the mitigation actions, and also adaptation to extremes. This study proposes novel predictive models for susceptibility mapping for flood and erosion. Furthermore, this study elaborates on prioritizing the existing sub-basins in terms of erosion and flood susceptibility. A comparative analysis of generalized linear model (GLM), flexible discriminate analyses (FDA), multivariate adaptive regression spline (MARS), random forest (RF), and their ensemble is performed to ensure highest predictive performance. Furthermore, the priority of the sub-basins in terms of sensitivity to erosion and flood was determined based on the best model. The results showed that the GLM, FDA, MARS, RF, and ensemble models had an area under curve (AUC) 0.91, 0.92, 0.89, 0.93 and 0.94, respectively, in modeling the flood susceptibility. Also, the GLM, FDA, MARS, RF, and ensemble models had an AUC of 0.93, 0.92, 0.89, 0.96, and 0.97, respectively, in determining erosion susceptibility. Priority assessment based on the best model, the ensemble approach, indicated that the sub-basins SW3 and SW5 were found to have high sensitivity to the flood and soil erosion, respectively. [ABSTRACT FROM AUTHOR]