Process-based Modeling
Hydrologic Modeling
Hydraulic Routing Simulations
Water Systems Analysis & Modeling
Data-driven Techniques
Data Analytics and Data Science
Machine Learning and Deep Learning
Tools Development
GIS & Geospatial Tool Development
Skills References
Software and Tools: Watershed Modeling System (WMS), HEC-HMS, Gridded Surface Subsurface Hydrologic Analysis (GSSHA), Lisem Integrated Spatial Earth Modeller (openLISEM)
Abilities:
Develop lumped and distributed models in HEC-HMS and GSSHA to solve analysis and design problems.
Formulate combinations of hydrologic modeling components and suitable equations to match a specific case.
Calibrate models through stochastic or optimization runs with an understanding of objective functions and error metrics.
Apply physical principles of hydrology in hydrologic modeling and refer back to the principles in interpreting results.
Collect digital elevation model, precipitation, land-use, soil-type, etc., data from publicly available sources and process and analyze these data to compute necessary inputs and parameters.
Software and tools: WANDA · SIMSEN · ALLIEVI · AFT Impulse · InfoWater Pro · Bentley HAMMER · Open-source transient-flow tools
Abilities developed:
Understand the basic theory and assumptions behind hydraulic modeling software for pressurized transient flows.
Recognize transient-flow problems in hydraulic systems, including water hammer, pressure surges, pump operations, hydropower schemes, water-supply systems, and industrial flows.
Compare commercial, non-commercial, open-access, freeware, and payware software for transient-flow modeling.
Develop critical thinking in selecting suitable modeling software according to the hydraulic system, engineering objective, available data, and model limitations.
Interpret transient-flow simulation results in relation to hydraulic-system design, protection, operation, and maintenance.
Identify when specialized expertise is required for complex transient phenomena beyond standard engineering practice.
MOOC: Modelling Software for Transient Flows
Software and tools: HydroBlox · HydroSuite · Web APIs · Python/pandas · Interactive dashboards · Maps and charts · Hydrological data workflows
Abilities:
Retrieve and process hydrological, meteorological, and spatial datasets from web-based data sources and APIs.
Clean, standardize, and transform time-series, spatial, and tabular hydrological datasets.
Develop interactive dashboards combining maps, charts, and data-processing workflows.
Apply web-based tools to support hydrological analysis, flood-disaster exploration, and water-resources communication.
Communicate results through visual dashboards designed for research, education, and decision-making.
Water Systems Analysis & Modeling
Software and Tools: EPANET, MS Excel
Abilities:
Perform the balance analysis between capacity and demand for water distribution systems, along with the level of service considerations and design components, including pumps and emergency storage.
Analyze the capacity of existing distribution systems to suggest expansions in line with the projected demand.
Data Analytics and Data Science
Software and Tools: pandas, SciPy, NumPy, Statsmodels, Matplotlib, R Programming, SQL, MS Excel
Abilities:
Explore data with numerical and statistical summaries and visualizations.
Identify random sampling and randomized assignments for their implications on inference and causality.
Choose and implement hypothesis tests and create confidence intervals for inference about the population.
Fit data to statistical regression models for prediction and inference about relationships between variables.
Create custom Python and R data processing and analysis scripts for unique workflows using built-in, third-party, and user-defined datatypes and packages.
Parse web data in HTML, XML, JSON, etc. data formats.
Construct database tables and extract and manipulate data with queries.
Machine Learning and Deep Learning
Software and Tools: scikit-learn, Keras, Tensorflow, PyTorch, SHAP
Abilities:
Prepare (bring to desired format), clean (address missing values), and pre-process (encoding and feature engineering) large datasets to train machine learning (ML) models.
Select model features using statistical filter and subset-based wrapper methods and reduce dimensionality by extraction and aggregation techniques (e.g., principal component analysis).
Possess an understanding of optimization algorithms, such as gradient descent, stochastic gradient descent, adaptive gradient algorithm, root mean square propagation, adaptive moment estimation, etc., and hyperparameter tuning searches.
Construct and deploy tree-based, support vector-based, and neural network ML models of standard practices and customized variations.
Produce Shapley-based insights and interpretations of the trained ML models for explainability.
MOOC: 3 months Course-Factual Analytics Nigeria
GIS and Geospatial Tool Development
Software and Tools: ArcGIS Pro, QGIS, Google Earth Engine, Leaflet, GeoPandas, GDAL, Shapely, Rasterio, Folium
Abilities:
Retrieve, process, store, and manage diverse forms of spatial data and understand data formats.
Analyze geospatial data to identify patterns and extract meaningful relationships among variables.
Create professional-level layout maps and technical reports to present solutions to geospatial problems.
Perform GIS-based multi-criteria decision analysis (MCDA) to generate composite risk maps.
Build custom geospatial workflows by combining available and custom tools in the graphical interface of ArcGIS Model Builder or in the programmatic interface of Python and/or QGIS.
Use web mapping tools like Leaflet to share geospatial information interactively.