A5017929974- Hydrology and Watershed Management Studies
- Flood Risk Assessment and Management
- Soil and Water Nutrient Dynamics
- Hydrological Forecasting Using AI
- Hydrology and Drought Analysis
- Urban Stormwater Management Solutions
- Water resources management and optimization
- Groundwater flow and contamination studies
- Tropical and Extratropical Cyclones Research
- Water Systems and Optimization
- Land Use and Ecosystem Services
- Dam Engineering and Safety
- Anomaly Detection Techniques and Applications
- Scientific Computing and Data Management
- Plant Water Relations and Carbon Dynamics
- Groundwater and Watershed Analysis
- Climate variability and models
- Hydrology and Sediment Transport Processes
- Water Quality and Pollution Assessment
- Fire Detection and Safety Systems
- Climate change impacts on agriculture
- Infrastructure Resilience and Vulnerability Analysis
- Data Stream Mining Techniques
- Optimal Power Flow Distribution
- Clinical Nutrition and Gastroenterology
Florida A&M University - Florida State University College of Engineering
2020-2025
Florida State University
2023-2024
ORCID
2018-2024
Northeastern University
2023
Chesapeake Public Schools
2023
Water Research Foundation
2023
Oregon State University
2023
Virginia Tech
2016-2020
ETH Zurich
2020
Sharif University of Technology
2015
Floods are some of the most destructive and catastrophic disasters worldwide. Development management plans needs a deep understanding likelihood magnitude future flood events. The purpose this research was to estimate flash susceptibility in Tafresh watershed, Iran, using five machine learning methods, i.e., alternating decision tree (ADT), functional (FT), kernel logistic regression (KLR), multilayer perceptron (MLP), quadratic discriminant analysis (QDA). A geospatial database including...
Floods can severely impact the economy, environment and society. These impacts be direct indirect. Past research has focused more on former impacts. Of indirect impacts, those mold growth in indoor environments that affect human respiratory health (e.g. asthma) have received limited attention. Models used to predict these support development of mitigation preventive actions. Despite presence models for some other flooding, quantitative estimating flooding spores are lacking. In this article,...
Watershed models are widely used in total maximum daily load (TMDL) studies to predict the impacts of pollutant discharges on biochemical functioning and assimilative capacity water bodies. The reliability a TMDL is therefore tightly linked with predictive capability these models. While there has been an increasing availability application watershed for studies, guidelines model evaluation, including recommendations appropriate selection implementation calibration, validation, uncertainty...
This study presents an innovative approach for the integration of flood hazard into site selection detention basins. The process is conducted by taking account multiple criteria and disciplines. Hydraulic modeling results derived from stormwater management model are employed Technique Order Prioritization Similarity to Ideal Solution (TOPSIS) determine score. score generated TOPSIS used in a spatial multi-criteria decision-making framework. Applying framework, suitability map which primary...
In this study, a new hybridized machine learning algorithm for urban flood susceptibility mapping, named MultiB-MLPNN, was developed using multi-boosting technique and MLPNN. The model tested in Amol City, Iran, data-scarce city an ungauged area which is prone to severe inundation events currently lacks prevention infrastructure. Performance of the compared with that standalone MLPNN model, random forest boosted regression trees. Area under curve, efficiency, true skill statistic, Matthews...
Soil moisture, a key hydrologic variable that determines hydroclimatic extremes including catastrophic flooding, is generally considered less important in cities compared to natural, agricultural and rural areas due the prevalence of impervious surfaces. However, recent empirical studies on stormwater runoff reduction by turfgrass lawns (which cover nearly half cumulative urban area USA), have demonstrated soil moisture highly significant factor flooding. Yet, remains uncertain high...
Abstract In the absence of adequate observations on off‐channel areas, flood models are typically trained and validated against stream water depths. This approach can be efficient for physics‐based models, which incorporate underlying physical processes, but efficiency data‐driven like machine learning (ML) algorithms is unclear. The existing high‐water marks (HWMs) also subject to uncertainty. paper addressed three research questions: (a) how useful ML with gauges, hindcasting depths in...
This paper reviews 14 prevalent watershed models for their capabilities, credibility, and suitability in total maximum daily load (TMDL) development implementation. Brief descriptions of the models, including sources, applicability are presented. General information such as intended simulation types, simulated outputs, uncertainty analysis graphical user interface, availability also Mathematical bases hydrologic water quality simulations, which indicate expected performance, accuracy,...
Prediction of design hydrographs is key in floodplain mapping using hydraulic models, which are either steady state or unsteady. The former, require only an input peak, substantially overestimate the volume water entering compared to more realistic dynamic case simulated by unsteady models that full hydrograph. Past efforts account for uncertainty boundary conditions modeling have been based largely on a joint flood frequency–shape analysis, with very limited number studies hydrological...
A total maximum daily load (TMDL) is required for water bodies in the U.S. that do not meet applicable quality standards. Computational watershed models are often used to develop TMDL pollutant reduction scenarios. Uncertainty inherent modeling process. An explicit uncertainty analysis would improve model performance and result more robust decision making when comparing alternative This paper presents a risk-based framework evaluating allocation scenarios considering reliability achieving...
Non-point source pollution is a major factor in excessive nutrient that can result the eutrophication. Land use/land cover (LULC) change, as of urbanization and agricultural intensification (e.g., increase consumption fertilizers), intensify this pollution. An informed LULC planning needs to consider negative impacts such anthropogenic activities minimize impact on water resources. The objective study was inform future land use by considering reduction goals. We modeled dynamics determined...
This study presents a probabilistic framework that considers both the water quality improvement capability and reliability of alternative total maximum daily load (TMDL) pollutant allocations. Generalized likelihood uncertainty estimation Markov chain Monte Carlo techniques were used to assess relative two TMDL allocations developed address fecal coliform (FC) bacteria impairment in rural watershed western Virginia. The allocation alternatives, using Hydrological Simulation Program—FORTRAN,...
Abstract Projecting future climate variables is essential for comprehending the potential impacts on hydroclimatic hazards like floods and droughts. Evaluating these challenging due to coarse spatial resolution of global models (GCMs); therefore, bias correction widely used. Here, we applied two statistical methods—standard empirical quantile mapping (EQM) a hybrid approach, EQM with linear (EQM‐LIN)—to correct precipitation air temperature simulated by nine GCMs. We used historical...