A5051623706- Flood Risk Assessment and Management
- Landslides and related hazards
- Hydrology and Watershed Management Studies
- Groundwater and Watershed Analysis
- Hydrology and Drought Analysis
- Soil erosion and sediment transport
- Geotechnical Engineering and Analysis
- Dam Engineering and Safety
- Fire effects on ecosystems
- Hydrology and Sediment Transport Processes
- Geochemistry and Geologic Mapping
- Tree Root and Stability Studies
- Synthetic Aperture Radar (SAR) Applications and Techniques
- Soil and Water Nutrient Dynamics
- Climate variability and models
- Climate change impacts on agriculture
- Grouting, Rheology, and Soil Mechanics
- Land Use and Ecosystem Services
- Groundwater and Isotope Geochemistry
- Rock Mechanics and Modeling
- Karst Systems and Hydrogeology
- Soil and Unsaturated Flow
- Hydrological Forecasting Using AI
- Water Resources and Management
- Constructed Wetlands for Wastewater Treatment
University of Kurdistan
2012-2022
University of Guelph
2015
This study presents three new hybrid artificial intelligence optimization models—namely, adaptive neuro-fuzzy inference system (ANFIS) with cultural (ANFIS-CA), bees (ANFIS-BA), and invasive weed (ANFIS-IWO) algorithms—for flood susceptibility mapping (FSM) in the Haraz watershed, Iran. Ten continuous categorical conditioning factors were chosen based on 201 locations, including topographic wetness index (TWI), river density, stream power (SPI), curvature, distance from river, lithology,...
The main objective of this research was to introduce a novel machine learning algorithm alternating decision tree (ADTree) based on the multiboost (MB), bagging (BA), rotation forest (RF) and random subspace (RS) ensemble algorithms under two scenarios different sample sizes raster resolutions for spatial prediction shallow landslides around Bijar City, Kurdistan Province, Iran. evaluation modeling process checked by some statistical measures area receiver operating characteristic curve...
Floods are some of the most dangerous and frequent natural disasters occurring in northern region Iran. Flooding this area frequently leads to major urban, financial, anthropogenic, environmental impacts. Therefore, development flood susceptibility maps used identify zones catchment is necessary for improved management decision making. The main objective study was evaluate performance an Evidential Belief Function (EBF) model, both as individual model combination with Logistic Regression...
Landslides cause a considerable amount of damage around the world every year. Landslide susceptibility assessments are useful for mitigation associated potential risks to local economic development, land use planning, and decision makers. The main aim this study was present novel hybrid approach bagging (B)-based kernel logistic regression (KLR), named BKLR model, spatial prediction landslides in Shangnan County, China. We first selected 15 conditioning factors landslide modeling. Then,...
Adaptive neuro-fuzzy inference system (ANFIS) includes two novel GIS-based ensemble artificial intelligence approaches called imperialistic competitive algorithm (ICA) and firefly (FA). This combination could result in ANFIS-ICA ANFIS-FA models, which were applied to flood spatial modelling its mapping the Haraz watershed Northern Province of Mazandaran, Iran. Ten influential factors including slope angle, elevation, stream power index (SPI), curvature, topographic wetness (TWI), lithology,...
Since landslide detection using the combination of AIRSAR data and GIS-based susceptibility mapping has been rarely conducted in tropical environments, aim this study is to compare validate support vector machine (SVM) index entropy (IOE) methods for assessment Cameron Highlands area, Malaysia. For purpose, ten conditioning factors observed landslides were detected by data, WorldView-1 SPOT 5 satellite images. A spatial database was generated including a total 92 locations encompassing same...
In this study, land subsidence susceptibility was assessed for a study area in South Korea by using four machine learning models including Bayesian Logistic Regression (BLR), Support Vector Machine (SVM), Model Tree (LMT) and Alternate Decision (ADTree). Eight conditioning factors were distinguished as the most important affecting on of Jeong-am area, slope angle, distance to drift, drift density, geology, lineament, lineament use rock-mass rating (RMR) applied modelling. About 24 previously...
A novel artificial intelligence approach of Bayesian Logistic Regression (BLR) and its ensembles [Random Subspace (RS), Adaboost (AB), Multiboost (MB) Bagging] was introduced for landslide susceptibility mapping in a part Kamyaran city Kurdistan Province, Iran. spatial database generated which includes total 60 locations set conditioning factors tested by the Information Gain Ratio technique. Performance these models evaluated using area under ROC curve (AUROC) statistical index-based...
We used a novel hybrid functional machine learning algorithm to predict the spatial distribution of landslides in Sarkhoon watershed, Iran. developed new ensemble model which is combination algorithm, stochastic gradient descent (SGD) and an AdaBoost (AB) Meta classifier namely ABSGD landslides. The incorporates 20 landslide conditioning factors, we ranked using least-square support vector (LSSVM) technique. For modeling, considered 98 locations, 70% (79) were for training 30% (19)...
This study describes the application of logistic regression to rock-fall susceptibility mapping along 11 km a mountainous road on Salavat Abad saddle, in southwest Kurdistan, Iran. To determine factors influencing rock-falls, data layers slope degree, aspect, curvature, elevation, distance road, fault, lithology, and land use were analyzed by analysis. The results are shown as maps. A spatial database, which included 68 sites (34 point cells with value 1 34 no 0) was developed using...
In this study, we introduced a novel hybrid artificial intelligence approach of rotation forest (RF) as Meta/ensemble classifier based on alternating decision tree (ADTree) base called RF-ADTree in order to spatially predict gully erosion at Klocheh watershed Kurdistan province, Iran. A total 915 locations along with 22 conditioning factors were used construct database. Some soft computing benchmark models (SCBM) including the ADTree, Support Vector Machine by two kernel functions such...
In this study, the main goal is to compare predictive capability of Support Vector Machines (SVM) with four Bayesian algorithms namely Naïve Bayes Tree (NBT), network (BN), (NB), Decision Table (DTNB) for identifying landslide susceptibility zones in Pauri Garhwal district (India). First, inventory map was built using 1295 historical data, then total sixteen influencing factors were selected and tested modelling. Performance model evaluated compared Statistical based index methods, Area...
This research aims at proposing a new artificial intelligence approach (namely RVM-ICA) which is based on the Relevance Vector Machine (RVM) and Imperialist Competitive Algorithm (ICA) optimization for landslide susceptibility modeling. A Geographic Information System (GIS) spatial database was generated from Lang Son city in province (Vietnam). GIS includes inventory map fourteen conditioning factors. The suitability of these factors modeling study area verified by Gain Ratio (IGR)...