Data Science & Computational Engineering

I apply machine learning, simulation‑driven modeling, and statistical analysis to accelerate design, predict material behavior, and extract insights from engineering datasets.

1. Machine Learning for Materials & Structures

I develop predictive models that link geometry, process parameters, and material behavior. These models help reduce experimental cost and guide design decisions in additive manufacturing and metamaterials.

Key Topics

  • Supervised learning for mechanical property prediction
  • Feature engineering for lattice and metamaterial geometries
  • Regression, classification, and surrogate modeling
  • Model interpretability and sensitivity analysis

2. Simulation‑Driven Data & Hybrid Modeling

I integrate finite element simulations with data‑driven methods to create hybrid models that combine physics‑based understanding with statistical learning.

Key Topics

  • FEA‑based dataset generation
  • Physics‑informed ML models
  • Design space exploration and optimization
  • Uncertainty quantification

3. Statistical Analysis & Experimental Data Processing

I analyze mechanical testing data, extract trends, and build statistical models to understand structure–property relationships and experimental variability.

Key Topics

  • Data cleaning and preprocessing
  • Curve fitting and regression analysis
  • ANOVA and hypothesis testing
  • Signal processing for mechanical test data

Tools & Technologies

  • Python · NumPy · Pandas · SciPy · scikit‑learn
  • MATLAB · Statistics Toolbox
  • TensorFlow / PyTorch (basic workflows)
  • FEA tools: Abaqus, ANSYS, COMSOL
  • Visualization: Matplotlib · Seaborn · Plotly