Energy Data Scientist | Renewable Energy Systems Modeller | PhD Researcher

I am a Glasgow-based researcher transitioning into Data Science and AI. With a PhD in Renewable Energy, I specialize in bridging the gap between theoretical physics and commercial application through predictive modelling, simulation, and machine learning.

• 🔭 I’m currently working on Subsurface Thermal Energy Storage simulations (STEaM Project).
• 🐍 I use Python and MATLAB to optimize energy efficiency and reduce LCOH.
• ⚡ I’m looking to collaborate on Energy Data Analysis and Decarbonization AI projects.

I am a Glasgow-based Ph.D. Researcher and Data Scientist bridging the gap between theoretical physics and commercial AI applications. My work focuses on optimizing renewable energy systems (STEaM, PVT) using advanced simulation and Deep Learning workflows.

• 🔭 Currently working on: Integrating Deep Learning with Subsurface Thermal Energy Storage (STEaM) simulations to predict long-term thermal behavior.
• ⚡ Core Expertise: Renewable Energy Systems, Thermodynamics, Systems Modelling, and Predictive Analytics.
• 👯 Looking to collaborate on: AI-driven energy decarbonization projects and predictive maintenance models.
• 🇬🇧 Status: Global Talent Visa Holder (No Visa Sponsorship Required for UK work)

Languages & Frameworks

Visualization

Domain & Research

• ⚡ Domain: Energy Systems Modelling, Thermodynamics, Optimization Algorithms
• 🔬 Research: Experiment Design, Technical Writing, Scenario Analysis

I am a Glasgow-based Ph.D. Researcher and Data Scientist bridging the gap between theoretical physics and commercial AI applications. My work focuses on Physics-Informed Machine Learning, utilizing TensorFlow and LSTMs to solve complex energy challenges.

• 🔭 Currently working on: Integrating Deep Learning with Subsurface Thermal Energy Storage (STEaM) simulations to predict long-term thermal behavior.
• ⚡ Core Expertise: Renewable Energy Systems, Thermodynamics, Systems Modelling, and Predictive Analytics.
• 👯 Looking to collaborate on: AI-driven energy decarbonization projects and predictive maintenance models.
• 🇬🇧 Status: Global Talent Visa Holder (UK).

Predicting subsurface thermal behavior using Long Short-Term Memory (LSTM) networks.

• The Problem: Legacy physical simulations were computationally expensive for long-term forecasting.
• The Solution: Built a TensorFlow LSTM model to predict temperature fluctuations based on historical training data.
• The Result: Reduced prediction time by 90% compared to numerical simulation while maintaining high accuracy.
• Stack: Python TensorFlow Keras Pandas

Data-driven optimization of Photovoltaic-Thermal collectors.

• The Problem: Optimizing energy capture in variable weather conditions.
• The Solution: Designed genetic algorithms to analyze experimental data and identify optimal collector configurations.
• The Result: Identified configurations yielding 30% higher energy capture.
• Stack: MATLAB Optimization Algorithms Data Visualization

Predictive modeling for public health resources.

• The Work: Utilized data science techniques to model patient intake trends during the pandemic for the Scottish Government.
• Stack: Python Data Science Scikit-Learn

Domain	Tools & Frameworks
Machine Learning
Data Science
Languages
Research Domain	Thermodynamics Renewable Energy Experiment Design Technical Writing

I am a Glasgow-based Ph.D. Researcher and Data Scientist bridging the gap between theoretical physics and commercial AI applications. My work focuses on Physics-Informed Machine Learning, utilizing TensorFlow and LSTMs to solve complex energy challenges.

• 🔭 Currently working on: Integrating Deep Learning with Subsurface Thermal Energy Storage (STEaM) simulations to predict long-term thermal behavior.
• ⚡ Core Expertise: Renewable Energy Systems, Thermodynamics, Systems Modelling, and Predictive Analytics.
• 👯 Looking to collaborate on: AI-driven energy decarbonization projects and predictive maintenance models.
• 🇬🇧 Status: Global Talent Visa Holder (UK).

Predicting subsurface thermal behavior using Long Short-Term Memory (LSTM) networks.

• The Problem: Legacy physical simulations were computationally expensive for long-term forecasting.
• The Solution: Built a TensorFlow LSTM model to predict temperature fluctuations based on historical training data.
• The Result: Reduced prediction time by 90% compared to numerical simulation while maintaining high accuracy.
• Stack: Python TensorFlow Keras Pandas

Data-driven optimization of Photovoltaic-Thermal collectors.

• The Problem: Optimizing energy capture in variable weather conditions.
• The Solution: Designed genetic algorithms to analyze experimental data and identify optimal collector configurations.
• The Result: Identified configurations yielding 30% higher energy capture.
• Stack: MATLAB Optimization Algorithms Data Visualization

Predictive modeling for public health resources.

• The Work: Utilized data science techniques to model patient intake trends during the pandemic for the Scottish Government.
• Stack: Python Data Science Scikit-Learn

Category	Stack
Languages
Machine Learning
Data Processing
Visualization
Dev Tools
Research Domain	Thermodynamics Renewable Energy Technical Writing Experiment Design

I am a Data Scientist & Machine Learning Specialist transitioning from advanced research to industry. I combine the mathematical rigor of a Physics PhD with practical Deep Learning skills to solve complex data problems.

• Role: Data Scientist, Machine Learning Engineer, AI Researcher.
• Top Skills: Python, TensorFlow (Deep Learning), Time-Series Forecasting, Mathematical Modelling.
• Business Value: I don't just build models; I use Physics-Informed ML to optimize systems, reduce operational costs, and drive decarbonization.
• Visa: UK Global Talent Visa (I can work for any employer immediately without sponsorship).

Industry Application: Predictive Maintenance & Energy Grid Optimization

• The Challenge: Predicting heat retention in subsurface storage was too slow using traditional physics engines.
• The Solution: Developed a TensorFlow LSTM (Recurrent Neural Network) to learn from historical sensor data.
• The Impact: Reduced simulation runtime by 90%, enabling real-time decision-making for energy storage.
• Stack: Python TensorFlow Keras Pandas Google Colab

Industry Application: System Efficiency Improvement

• The Challenge: Solar collectors were underperforming due to static configuration parameters.
• The Solution: Wrote custom Genetic Algorithms (Optimization) to cycle through thousands of design variables.
• The Impact: Identified a configuration that increased energy capture by 30%.
• Stack: MATLAB Optimization Data Visualization

Industry Application: Healthcare Analytics & Resource Planning

• The Challenge: The Scottish Government needed rapid projections of ICU bed usage.
• The Solution: Applied statistical modelling to patient intake data to forecast demand spikes.
• The Impact: Directly supported public health resource planning during a critical crisis.
• Stack: Python Scikit-Learn Data Analysis

Area	Technologies
Deep Learning
Data Stack
Visualization
Development
Soft Skills	Technical Writing Stakeholder Management Complex Problem Solving