Chuong Dang TA
Hi! My name is Chuong Dang Ta. [translate:Chương] is my Vietnamese name, and yes, it’s tough for foreigners to pronounce (but no hard feelings toward my parents for that 😅).
Currently, I am pursuing a Master’s degree in Decentralised Smart Energy Systems (DENSYS), studying at Université de Lorraine, Nancy, France and Politecnico di Torino, Italy. I expect to graduate in September 2026. I am currently working as a Research Intern at rebase.energy in Stockholm, developing power forecasting models for Wave Energy Converters. Previously, from February to July 2026, I carried out my Master’s thesis here, building on IEA Wind Task 19 to develop machine-learning models (LightGBM, Quantile Regression Forests, deep learning architectures) to forecast icing-related power losses for wind farms. Professionally, I’m driven by challenges in Offshore Wind, Wave Energy, and Power-to-X, a passion amplified by the time I worked as Junior Researcher at VPI - Vietnam’s Petroleum Institute — contributing to Vietnam’s national hydrogen roadmap. My goal is to return and help advance this transformation.
Recently, I watched a great video on how to learn machine learning, and it made me realize that most people skip the fundamentals and jump straight into a bootcamp. Here’s a meme that captures this tendency. Personally, I really enjoy learning from textbooks on topics that interest me, it’s one of the best ways to build a concrete foundation of understanding!
Many learners leap straight to tools like Ansys/Comsol in CFD, skipping mathematics and core fundamentals.
Most people rush into ML bootcamps without core concepts; textbook learning helps reach true expertise.
I have hands-on experience with PyWake, an open-source, Python-based wind farm simulation tool developed at DTU, which computes flow fields, power production of individual turbines, and Annual Energy Production (AEP) for entire wind farms. I modeled a project using PyWake that gave me practical insights into wind farm aerodynamics. I also intend to learn TOPFARM, a Python package from DTU Wind Energy that wraps PyWake with OpenMDAO, enabling wind farm optimization for both onshore and offshore projects.
In terms of machine learning, I am currently strengthening my foundational mathematical skills in Linear Algebra, Calculus, Statistics, Probability, and Statistical Learning through the book Mathematics for Machine learning. In the coming months, I plan to focus more deeply on Data Science applications relevant to Wind Energy, beginning with two initial books and progressing to An Introduction to Statistical Learning with Applications in Python and Data Science in Wind Energy.
Education
Université de Lorraine, Nancy and Politecnico di Torino, Turin
MSc in Decentralised Smart Energy Systems (DENSYS)
France & Italy
Selected Coursework: Wind and Ocean Energy Plants, Data and Forecasting in Microgrids, Optimal Local Design Energy Networks, Smart Electricity Systems, Chemical and Electrochemical Processes
Key Projects: ML-Enhanced LCA of a North Sea Offshore Wind Farm (12,600× computational acceleration, R²=98.5%); Techno-economic and environmental assessment of algae-based SAF pathways.
Master's Thesis: Icing and power loss forecasting for cold-climate wind farms using SCADA and NWP data (rebase.energy, Stockholm, Feb–Jul 2026)
Hanoi University of Science and Technology (HUST)
BSc in Thermal Engineering
Hanoi, Vietnam
Thesis: Techno-economic analysis of internal combustion engines using Diesel and LNG (Grade: 9.5/10)
Honors: Merit Scholarship and JNED Award for nuclear research, Japan (2023)
Selected Research Experience
Research Intern, rebase.energy
Jul 2026 – Present, Stockholm, Sweden
Developing power forecasting models for Wave Energy Converters, benchmarking multiple ridge-regularised and tree-based models (Ridge Regression, Random Forest, LightGBM) against deep learning architectures (BiLSTM, TCN) for time-series power prediction.
Master Thesis Student, rebase.energy
Feb 2026 – Jul 2026, Stockholm, Sweden
Established wind turbine icing labels on multi-year Swedish SCADA data using an extended IEA Wind Task 19 framework, correcting biases via Quantile Mapping and LightGBM. Built a two-stage LightGBM classifier-regressor to forecast wind power icing losses at 1-36 hour lead times using SCADA and NWP meteorological inputs.
Junior Researcher, Vietnam Petroleum Institute (VPI)
Feb 2024 – Aug 2024, Hanoi, Vietnam
Contributed to national hydrogen roadmap by conducting feasibility studies for green hydrogen integration into thermal power plants. Focused on techno-economic modeling, cost benchmarking, and policy analysis for power sector decarbonization.
Research Intern, Vietnam Initiative for Energy Transition (VIETSE)
May 2023 – Sep 2023, Hanoi, Vietnam
Modeled solar/wind/BESS hybrid power systems using HOMER Pro and Python. Analyzed performance and policy impacts in Vietnam and Thailand, contributing to stakeholder reports on renewable integration and energy security.
Publications
Wind Farm-Scale Forecasting of Turbine Icing Power Losses Using Multi-Ridge Regression Models [Ongoing]
Dang-Chuong Ta et al.
Based on MSc thesis research at rebase.energy, extending the turbine-level classifier-regressor framework with multi-ridge regression models and upscaling to wind farm-level forecasts.
Feasibility Analysis of Hydrogen Co-Firing in Vietnam's Gas Power Plants for the Period 2035–2050 [Journal Article]
Dang-Chuong Ta, Thanh-Hoang Le, Long Van Phan, Hoang-Luong Pham
Energy Conversion and Management, Impact Factor: 11.8, 2025
DOI: 10.1016/j.enconman.2025.120192
An Assessment of the Potential for Large-Scale Hydrogen Export from Vietnam to Asian Countries: Techno-Economic Analysis, Transport Options, and Energy Carrier Comparison [Journal Article]
Dang-Chuong Ta, Thanh-Hoang Le, Hoang-Luong Pham
International Journal of Hydrogen Energy, Impact Factor: 9.2, 2024
DOI: 10.1016/j.ijhydene.2024.04.033
Technical Skills
- Data Science & Optimisation: Developing hybrid, physics-informed ML models for energy system forecasting and predictive maintenance; applied MILP, MINLP, and heuristic algorithms (e.g., genetic algorithms) in Pyomo to optimize renewable energy systems.
- Technical Toolset: Python (PyTorch, Scikit-learn, TensorFlow, Pyomo, PyWake), MATLAB/Simulink, Modelica, QBlade, HOMER Pro, GIS, Aspen Plus, Typst, LaTeX.
Honors & Awards
- Erasmus Mundus Scholarship (DENSYS, EU)
- JNED Award, with site visits to nuclear power plants and research facilities in Japan, 2023
- Merit Scholarship (BSc at HUST, Vietnam)
Languages
- Vietnamese (Native)
- English (IELTS 7.5, full professional proficiency)
- German (A2), French (A1)
Referees
Prof. Fabrice Lemoine — Chair of the DENSYS Erasmus Mundus Joint Master Degree, Université de Lorraine
fabrice.lemoine@univ-lorraine.fr
Marta Gandiglio — Associate Professor, Department of Energy (DENERG), Politecnico di Torino
marta.gandiglio@polito.it