FazBrowse GitHub Viewer | Trending |
URL:
| Home
Tools: [Original HTTPS Page]

marblehub (Goodfriend Whyte) · GitHub

Overview Repositories 14 Projects Packages Stars 18
3 followers · 14 following

Achievements

x2

Achievements

x2

Block or report marblehub

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Close all issues, pull requests, and discussions opened by this user Content in all repositories owned by your account will be closed.
Add an optional note
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
marblehub/README.md

Whyte Goodfriend M.

Scientific Researcher | Computational Physics | Machine Learning | Knowledge Graphs | Energy and Materials Informatics

Profile

Machine learning researcher with a physics background and doctoral research focused on data-driven modeling of energy systems. My work spans time-series analysis, anomaly detection, and unsupervised learning techniques, including UMAP, HDBSCAN, and LOF. I develop Python-based workflows that combine machine learning, large language models, and knowledge graphs for structured analysis and decision support. My research focuses on building scalable, interpretable, and explainable solutions for real-world scientific and engineering challenges.

Focus Areas

  • Machine learning for solar energy systems
  • PV anomaly detection and performance analytics
  • Thermal modeling for outdoor PV operation
  • Forecasting, data quality, and decision-support workflows
  • Domain-specific AI tools with provenance and citations

Featured Work

Project What it shows Links
Research Portfolio A clean portfolio for PV, ML, and data science work.
Trustworthy Energy RAG Chatbot Document-grounded technical-support chatbot with provenance, citations, OCR, and fault-code lookup.
SolarGraph AI LLM-powered knowledge graph exploration for PV solar energy and materials-science research.
PV Power Predictor Machine-learning workflow for predicting photovoltaic power output.

Technical stack

Python | scikit-learn | FastAPI | Flask | Streamlit | SQL | MATLAB | Linux | Git | MLFlow

Current Direction

I develop research-oriented prototypes that connect solar-energy domain knowledge with machine learning, knowledge graphs, explainable analytics, and practical interfaces for scientific insight.

Contact

Pinned Loading

  1. portfolio portfolio Public

    Research portfolio for solar PV, machine learning, and data science

    TypeScript 1

  2. s26-redi-ml-ai/provenance-energy-rag-chatbot s26-redi-ml-ai/provenance-energy-rag-chatbot Public

    A trustworthy document-grounded RAG chatbot for solar and energy technical support, with manual upload, provenance, citations, fault-code lookup, and hallucination-aware answers.

    Python 3

  3. solargraph-ai solargraph-ai Public

    LLM Agent & Knowledge Graph for PV Solar Materials Science — RDF/OWL · SPARQL · ReAct · Groq

    HTML 3

  4. PV-Power-Predictor PV-Power-Predictor Public

    End-to-end ML system for PV power prediction with MLflow tracking and Flask deployment

    Python 1

  5. marblehub marblehub Public

    Machine learning engineer with a physics background, specializing in time-series modeling, anomaly detection, and energy systems. Building scalable, production-ready ML solutions.

    1

Back | FazBrowse Home | New Git URL