Skip to content
View djimrastephane's full-sized avatar
:electron:
:electron:
  • United Kingdom
  • 15:49 (UTC -12:00)

Block or report djimrastephane

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.

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
djimrastephane/README.md

πŸ‘‹ Hi, I'm Djimra Stephane Soulanoudjingar

Data Scientist | Well Intervention & Completions Engineer | MSc Data Science | Industrial AI & RAG Systems

Profile views LinkedIn

I combine 17+ years of operational experience in oil and gas with modern data science, machine learning, AI, and industrial analytics platforms to build practical decision-support systems for complex engineering environments.

My work focuses on transforming operational data, engineering reports, and technical knowledge into searchable, explainable, and actionable intelligence.


πŸ‘¨β€πŸ’» About Me

  • πŸŽ“ MSc Data Science
  • πŸ›’οΈ 17+ years in Completions, Well Intervention, Sand Control, Hydraulic Fracturing, and Production Enhancement
  • 🌍 International experience across multiple countries, operators, and operating environments
  • πŸ€– Building AI-powered operational intelligence systems for engineering workflows
  • πŸ“Š Experienced in machine learning, statistical analysis, RAG systems, and engineering analytics

πŸš€ Current Projects

DDR Intelligence Platform

AI-powered operational intelligence platform that transforms Daily Drilling Reports into structured engineering knowledge.

  • Semantic search across drilling campaigns
  • Well similarity analysis
  • Operational sequence mining
  • NPT identification and precursor analysis
  • Lessons learned extraction
  • Campaign planning support
  • Traceable evidence-backed recommendations

MSc Thesis β€” EvidenceRAG-Evaluation

Evaluating Hybrid Retrieval for Grounded Question Answering over Long-Form Reports.

  • BM25 retrieval
  • Dense retrieval
  • Reciprocal Rank Fusion
  • FAISS vector search
  • Retrieval evaluation
  • Hallucination reduction
  • Grounded AI systems

Completion Campaign Intelligence

Platform that converts completion and hydraulic fracturing spreadsheets into searchable operational intelligence.

  • Automated data ingestion
  • NLP-based engineering comment analysis
  • Delay and failure analysis
  • Fleet performance benchmarking
  • Lessons learned extraction
  • Natural language querying

πŸ› οΈ Technical Skills

Programming Languages

Python R SQL Wolfram

Data Science & Machine Learning

pandas NumPy scikit-learn

AI & LLM Engineering

FAISS RAG LLMs Vector_Search

Data Applications & Platforms

Dataiku Streamlit R Shiny Quarto Jupyter

Development Tools

Git GitHub PyCharm


πŸ“‚ Featured Projects

Project Description Access
EvidenceRAG-Evaluation Hybrid dense + BM25 retrieval-augmented generation pipeline with a reproducible evaluation harness, built on PDF annual reports (MSc thesis project) Public
Frac_Campaign_Planning Monte Carlo simulator for multi-pad hydraulic fracturing campaign planning, scheduling, risk, and scenario optimisation Public
GP_Screens_Analysis Computer vision pipeline for detecting, classifying, and quantifying failure modes on failed gravel pack screens Public
DDR Intelligence Platform AI-powered drilling report analytics, sequence mining, operational intelligence, and risk detection Private β€” available on request
Completion Campaign Intelligence NLP-driven intelligence platform for completion and stimulation campaigns Private β€” available on request
CCS Well Integrity Intelligence Data-informed risk assessment and intervention planning for CCS wells Private β€” available on request

🎯 Core Expertise

Oil & Gas

  • Well Intervention
  • Completions Engineering
  • Sand Control
  • Hydraulic Fracturing
  • Artificial Lift
  • Workovers
  • Well Integrity
  • Decommissioning
  • CCS Wells

Data Science & AI

  • Machine Learning
  • Statistical Analysis
  • Predictive Modelling
  • Time Series Analysis
  • Retrieval-Augmented Generation
  • Hybrid Search Systems
  • Knowledge Extraction
  • Information Retrieval
  • Operational Analytics

πŸ“ˆ GitHub Stats

GitHub stats Top languages


πŸ“« Connect With Me


Combining engineering expertise, data science, and AI to transform operational data into decision intelligence.

Popular repositories Loading

  1. djimrastephane djimrastephane Public

    Config files for my GitHub profile.

    1

  2. EvidenceRAG-Evaluation EvidenceRAG-Evaluation Public

    Hybrid dense + BM25 retrieval-augmented generation pipeline with a reproducible evaluation harness, built on PDF annual reports.

    Python 1

  3. GP_Screens_Analysis GP_Screens_Analysis Public

    Computer vision pipeline for detecting, classifying, and quantifying failure modes on failed gravel pack screens.

    Python 1

  4. Frac_Campaign_Planning Frac_Campaign_Planning Public

    Monte Carlo simulator for multi-pad hydraulic fracturing campaign planning, scheduling, risk, and scenario optimisation (R/Shiny).

    R 1

  5. industrial-telemetry-intelligence industrial-telemetry-intelligence Public

    Industrial asset monitoring and decision support system, prototyped on FastF1 telemetry as a public surrogate for ESP/SCADA/production sensor data.

    Python 1

  6. ProcessPath_AI ProcessPath_AI Public

    Process mining on the BPI Challenge 2020 Travel Permit dataset β€” bottleneck analysis, conformance checking, SHAP early warning model, temporal CV

    Jupyter Notebook 1