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.     

Novel integrated approaches for predicting the compressibility of clay using cascade forward neural networks optimized by swarm- and evolution-based algorithms

Acta Geotechnica - Soft soils are considered as disadvantages in construction, especially in clay layers. It requires many advanced techniques to treat the soft soils before construction, aiming to...     

Estimating Ore Production in Open-pit Mines Using Various Machine Learning Algorithms Based on a Truck-Haulage System and Support of Internet of Things

Natural Resources Research - This study aimed to develop and assess the feasibility of different machine learning algorithms for predicting ore production in open-pit mines based on a truck-haulage...     

Predicting Blast-Induced Air Overpressure: A Robust Artificial Intelligence System Based on Artificial Neural Networks and Random Forest

Natural Resources Research - Blasting is the most popular method for rock fragmentation in open-pit mines. However, the side effects caused by blasting operations include ground vibration, air...     

Computational Intelligence Model for Estimating Intensity of Blast-Induced Ground Vibration in a Mine Based on Imperialist Competitive and Extreme Gradient Boosting Algorithms

Natural Resources Research - In this paper, we developed a novel hybrid model ICA–XGBoost for estimating blast-produced ground vibration in a mine based on extreme gradient boosting (XGBoost)...     

Prediction of Blast-Induced Ground Vibration in an Open-Pit Mine by a Novel Hybrid Model Based on Clustering and Artificial Neural Network

Natural Resources Research - Ground vibration (PPV) is one of the hazard effects induced by blasting operations in open-pit mines, which can affect the surrounding structures, particularly the...     

Predicting Blast-Induced Ground Vibration in Open-Pit Mines Using Different Nature-Inspired Optimization Algorithms and Deep Neural Network

Natural Resources Research - Blast-induced ground vibration (GV) is a hazardous phenomenon in open-pit mines, and it has unquestionable effects, such as slope instability, deformation of...     

A study of the connection between tropical cyclone track and intensity errors in the WRF model

This study examines the dependence of the tropical cyclone (TC) intensity errors on the track errors in the Weather Research and Forecasting (WRF-ARW) model. By using the National Centers for Environmental Prediction global final analysis as the initial and boundary conditions for cloud-resolving simulations of TC cases that have small track errors, it is found that the 2- and 3-day intensity errors in the North Atlantic basin can be reduced to 15 and 19 % when the track errors decrease to 55 and 76 %, respectively, whereas the 1-day intensity error shows no significant reduction despite more than 30 % decrease of the 1-day track error. For the North-Western Pacific basin, the percentage of intensity reduction is somewhat similar with the 2- and 3-day intensity errors improved by about 15 and 19 %, respectively. This suggests that future improvement of the TC track forecast skill in the WRF-ARW model will be beneficial to the intensity forecast. However, the substantially smaller percentages of intensity improvement than those of the track error improvement indicate that ambient environment tends to play a less important role in determining the TC intensity as compared to other factors related to the vortex initialization or physics representations in the WRF-ARW model.     

Studying Transformations of the Hydrogeochemical Conditions of Pliocene Aquifer System (Mekong R. Delta,Vietnam) Using Thermodynamic Modeling

Water Resources - The results of earlier studies of stable and radioactive isotopes have shown that groundwater of the Middle Pliocene aquifer system form mostly due to the infiltration of meteoric...     

Simulating Groundwater-Streamflow Connections in the Upper Colorado River Basin

In mountain, snow driven catchments, snowmelt is supposed to be the primary contribution to river streamflows during spring. In these catchments the contribution of groundwater is not well documented because of the difficulty to monitor groundwater in such complex environment with deep aquifers. In this study we use an integrated hydrologic model to conduct numerical experiments that help quantify the effect of lateral groundwater flow on total annual and peak streamflow in predevelopment conditions. Our simulations focus on the Upper Colorado River Basin (UCRB; 2.8 × 10⁵ km²) a well-documented mountain catchment for which both streamflow and water table measurements are available for several important sub-basins. For the simulated water year, our results suggest an increase in peak flow of up to 57% when lateral groundwater flow processes are included—an unexpected result for flood conditions generally assumed independent of groundwater. Additionally, inclusion of lateral groundwater flow moderately improved the model match to observations. The correlation coefficient for mean annual flows improved from 0.84 for the no lateral groundwater flow simulation to 0.98 for the lateral groundwater flow one. Spatially we see more pronounced differences between lateral and no lateral groundwater flow cases in areas of the domain with steeper topography. We also found distinct differences in the magnitude and spatial distribution of streamflow changes with and without lateral groundwater flow between Upper Colorado River Sub-basins. A sensitivity test that scaled hydraulic conductivity over two orders of magnitude was conducted for the lateral groundwater flow simulations. These results show that the impact of lateral groundwater flow is as large or larger than an order of magnitude change in hydraulic conductivity. While our results focus on the UCRB, we feel that these simulations have relevance to other headwaters systems worldwide.