A5000315193- Flood Risk Assessment and Management
- Landslides and related hazards
- Tree Root and Stability Studies
- Geotechnical Engineering and Analysis
- Hydrology and Watershed Management Studies
- Dam Engineering and Safety
- Groundwater and Watershed Analysis
- Hydrological Forecasting Using AI
- Cryospheric studies and observations
- Grouting, Rheology, and Soil Mechanics
- Hydrology and Sediment Transport Processes
- Fire effects on ecosystems
- Infrastructure Maintenance and Monitoring
- Soil and Unsaturated Flow
- Tropical and Extratropical Cyclones Research
- Hydrology and Drought Analysis
- Soil erosion and sediment transport
- Water Quality Monitoring and Analysis
- SARS-CoV-2 and COVID-19 Research
- Hydraulic flow and structures
- Seismic Imaging and Inversion Techniques
- Geological Modeling and Analysis
- COVID-19 epidemiological studies
- Rangeland Management and Livestock Ecology
- Karst Systems and Hydrogeology
Hanoi University of Mining and Geology
2016-2024
Ton Duc Thang University
2020
Shallow landslides damage buildings and other infrastructure, disrupt agriculture practices, can cause social upheaval loss of life. As a result, many scientists study the phenomenon, some them have focused on producing landslide susceptibility maps that be used by land-use managers to reduce injury damage. This paper contributes this effort comparing power effectiveness five machine learning, benchmark algorithms—Logistic Model Tree, Logistic Regression, Naïve Bayes Artificial Neural...
We used AdaBoost (AB), alternating decision tree (ADTree), and their combination as an ensemble model (AB-ADTree) to spatially predict landslides in the Cameron Highlands, Malaysia. The models were trained with a database of 152 compiled using Synthetic Aperture Radar Interferometry, Google Earth images, field surveys, 17 conditioning factors (slope, aspect, elevation, distance road, river, proximity fault, road density, river normalized difference vegetation index, rainfall, land cover,...
We generated high-quality shallow landslide susceptibility maps for Bijar County, Kurdistan Province, Iran, using Random Forest (RAF), an ensemble computational intelligence method and three meta classifiers—Bagging (BA, BA-RAF), Subspace (RS, RS-RAF), Rotation (RF, RF-RAF). Modeling validation were done on 111 locations 20 conditioning factors tested by the Information Gain Ratio (IGR) technique. assessed model performance with statistically based indexes, including sensitivity,...
Gully erosion destroys agricultural and domestic grazing land in many countries, especially those with arid semi-arid climates easily eroded rocks soils. It also generates large amounts of sediment that can adversely impact downstream river channels. The main objective this research is to accurately detect predict areas prone gully erosion. In paper, we couple hybrid models a commonly used base classifier (reduced pruning error tree, REPTree) AdaBoost (AB), bagging (Bag), random subspace...
The objective of this research is to propose and confirm a new machine learning approach Best-First tree (BFtree), AdaBoost (AB), MultiBoosting (MB), Bagging (Bag) ensembles for potential groundwater mapping assessing role influencing factors. Yasuj-Dena area (Iran) selected as case study. For regard, database was established with 362 springs locations 12 groundwater-influencing factors (slope, aspect, elevation, stream power index (SPI), length slope (LS), topographic wetness (TWI),...
We used remote sensing techniques and machine learning to detect map landslides, landslide susceptibility in the Cameron Highlands, Malaysia. located 152 landslides using a combination of interferometry synthetic aperture radar (InSAR), Google Earth (GE), field surveys. Of total slide locations, 80% (122 landslides) were utilized for training selected algorithms, remaining 20% (30 applied validation purposes. employed 17 conditioning factors, including slope angle, aspect, elevation,...
Groundwater is an important natural resource in arid and semi-arid environments, where discharge from karst springs utilized as the principal water supply for human use. The occurrence of over large areas often poorly documented, interpolation strategies are to map distribution potential springs. This study develops a novel method delineate spring zones on basis various hydrogeological factors. A case Bojnourd Region, Iran, measurements available 359 sites, used demonstrate application new...
This paper aims to apply and compare the performance of three machine learning algorithms–support vector (SVM), bayesian logistic regression (BLR), alternating decision tree (ADTree)–to map landslide susceptibility along mountainous road Salavat Abad saddle, Kurdistan province, Iran. We identified 66 shallow locations, based on field surveys, by recording locations landslides a global position System (GPS), Google Earth imagery black-and-white aerial photographs (scale 1: 20,000) 19...
Abstract The safety operation and management of hydropower dam play a critical role in social‐economic development ensure people's many countries; therefore, modeling forecasting the dam's deformations with high accuracy is crucial. This research aims to propose validate new model based on deep learning long short‐term memory (LSTM) coronavirus optimization algorithm (CVOA), named CVOA‐LSTM, for dam. second‐largest Vietnam, located Hoa Binh province, focused. Herein, we used LSTM establish...
Zrebar Lake is one of the largest freshwater lakes in Iran and it plays an important role ecosystem environment, while its desiccation has a negative impact on surrounded ecosystem. Despite this, this lake provides interesting recreation setting terms ecotourism. The prediction forecasting water level through simple but practical methods can provide reliable tool for future resource management. In present study, we predict daily well-known decision tree-based algorithms, including M5 pruned...
Flash flood is one of the most dangerous natural phenomena because its high magnitudes and sudden occurrence, resulting in huge damages for people properties. Our work aims to propose a state-of-the-art model susceptibility mapping flash using decision tree random subspace ensemble optimized by hybrid firefly–particle swarm optimization (HFPS), namely HFPS-RSTree model. In this work, we used data from inventory map consisting 1866 polygons derived Sentinel-1 C-band synthetic aperture radar...
The declining water level in Lake Urmia has become a significant issue for Iranian policy and decision makers. This lake been experiencing an abrupt decrease is at real risk of becoming complete saline land. Because its position, assessment changes the essential. study aims to evaluate using space-borne remote sensing GIS techniques. Therefore, multispectral Landsat 7 ETM+ images years 2000, 2010, 2017 were acquired. In addition, precipitation temperature data 31 between 1986 collected...
Corona viruses are a large family of that not only restricted to causing illness in humans but also affect animals such as camels, cattle, cats, and bats, thus affecting group living species. The outbreak virus late December 2019 (also known COVID-19) raised major concerns when the started getting tremendous. While first case was discovered Wuhan, China, it did take long for disease travel across globe infect every continent (except Antarctica), killing thousands people. Since has become...
Frequent forest fires are causing severe harm to the natural environment, such as decreasing air quality and threatening different species; therefore, developing accurate prediction models for fire danger is vital mitigate these impacts. This research proposes evaluates a new modeling approach based on TensorFlow deep neural networks (TFDeepNN) geographic information systems (GIS) modeling. Herein, TFDeepNN was used create model, whereas adaptive moment estimation (ADAM) optimization...
This paper proposes and implements an early warning monitoring system for rainfall-induced landslide (named as EWMRIL) with a case study at the Nam Dan (northern Vietnam). The proposed consists of six sensor nodes one rainfall station that are used to sense large amounts data in real-time such soil moisture, pore-water pressure (PWP), movement status, rainfall. In addition, new flexible configuration wireless communication is capable not only save energy consuming but also ensure reliability...
Flash floods induced by torrential rainfalls are considered one of the most dangerous natural hazards, due to their sudden occurrence and high magnitudes, which may cause huge damage people properties. This study proposed a novel modeling approach for spatial prediction flash based on tree intelligence-based CHAID (Chi-square Automatic Interaction Detector)random subspace, optimized biogeography-based optimization (the CHAID-RS-BBO model), using remote sensing geospatial data. In this...
The predictive capability of a new artificial intelligence method, random subspace (RS), for the prediction suspended sediment load in rivers was compared with commonly used methods: forest (RF) and two support vector machine (SVM) models using radial basis function kernel (SVM-RBF) normalized polynomial (SVM-NPK). Using river discharge, rainfall stage data from Haraz River, Iran, results revealed: (a) RS model provided superior accuracy (NSE = 0.83) to SVM-RBF 0.80), SVM-NPK 0.78) RF 0.68),...