DecodeX
Home/Problem Statements/SIH26121
All 226 Statements
SIH26121SoftwareSmart Automation
₹1,50,000 Prize (₹75k Joint)
•
Deadline: 20 September 2026
•
Submitted Ideas: 0/500

eRTMAC-NWIS (Nearby Wells Intelligence System): An AI-Powered Offset Well Knowledge and Decision Support Platform for Drilling Operations

Ministry / Organization: Oil India Limited
SIH Official Portal
Technical Complexity
8/10
Dataset Accessibility
7/10
36h Hackathon Viability
9/10
Step 0 • Zero-Jargon Layman Summary

“Oil drilling teams currently waste time manually reading thousands of old paper reports to guess what might go wrong when drilling a new well. This system acts as a 'digital memory' that uses AI to read those old files and warn engineers in real-time about potential dangers based on what happened in nearby wells.”

The DecodeX PS Decoder™

Deconstructed Problem Blueprint

Step 1

WHAT TO BUILD?

An AI-powered Knowledge Management and Predictive Decision Support Platform that integrates historical drilling data with real-time operational streams.

Step 2

WHO IS IT FOR?

Primary: Drilling Engineers, Wellsite Supervisors, and Geologists at Oil India Limited. Secondary: Operations Managers and Safety Officers.

Step 3

WHY DOES IT EXIST?

Institutional knowledge is trapped in unstructured PDFs and physical reports. Human memory is fallible, and the lack of a unified, searchable, and predictive system leads to costly operational delays, safety incidents, and 'stuck pipe' scenarios.

Step 4

INPUT → PROCESS → OUTPUT ARCHITECTURE PIPELINE

01 • Inputs & Telemetry

PDF/Scanned Well Completion Reports (WCRs), Daily Drilling Reports (DDRs), real-time sensor streams (eRTMAC), geological survey data, and well trajectory coordinates.

02 • Processing & AI Core

OCR/NLP pipeline for document digitization, RAG (Retrieval-Augmented Generation) for knowledge querying, geospatial indexing of well coordinates, and time-series anomaly detection models.

03 • Actionable Deliverables

Interactive geospatial dashboard, proactive risk alerts (push/SMS), automated 'Lessons Learned' summaries, and predictive trend visualizations.

Step 5

CONSTRAINTS

  • Must handle unstructured, messy, and heterogeneous historical document formats.
  • Low-latency inference for real-time drilling alerts.
  • Data privacy and security for sensitive oil field operational data.
  • Must function as a standalone system that integrates with existing eRTMAC infrastructure.
Step 6

JURY METRICS

  • Retrieval accuracy (Precision/Recall) of historical drilling events.
  • Latency of risk alert generation (must be sub-second).
  • User interface intuitiveness for field-based personnel.
  • Reduction in manual search time for engineers.
Step 7

CORE BOTTLENECK

The 'Data Silo' problem: Converting decades of inconsistent, non-standardized, and handwritten/scanned PDF reports into a structured, queryable database.

Why You Should Choose This PS (Pros)

  • High industrial impact with clear ROI for the organization.
  • Excellent opportunity to showcase advanced RAG and LLM integration.
  • Strong potential for scalability across other oil and gas sectors.

Challenges & Risks to Watch (Cons)

  • Requires high-quality synthetic data generation to demonstrate the model before real data is provided.
  • Complex domain knowledge required to understand drilling terminology.
  • Risk of 'hallucinations' in AI-generated risk alerts.
Hackathon Blueprint

Recommended Tech Stack & Grand Finale Features

Frontend & Mobile
React.jsMapbox GL JSTailwind CSSRecharts
Backend & APIs
FastAPIPythonCelery for background tasks
AI / ML & Models
Llama-3 or Mistral for RAGLangChainTesseract/DocTR for OCRXGBoost for time-series anomaly detection
Database & Cloud
PostgreSQL with PostGIS for geospatial dataChromaDB or Pinecone for vector storageRedis

Killer Features to Impress the SIH Jury

Semantic Search: 'Show me all wells where mud loss occurred at 2000m depth' using natural language.
Predictive 'Risk Heatmap': A visual overlay on the map showing high-risk zones based on historical incidents.
Automated 'Briefing Generator': One-click summary of all offset well risks before starting a new drilling phase.
Human-in-the-loop feedback: Allow engineers to verify/correct AI alerts to improve model accuracy over time.
View Official SIH 2026 Portal Raw Text
▼
•Background Oil India Limited has a digital real-time monitoring system (eRTMAC) that provides real-time drilling data, mud logging information, and wellsite analytics across operational areas. However, drilling decisions, particularly in geologically complex formations, require not only real-time data from the active well but also insights from nearby and historical wells drilled in the same reservoir or formation. Historical drilling knowledge currently resides across numerous well completion reports, drilling reports, PDF documents, and individual experience, making retrieval time-consuming and dependent on individual experience &
memory.This often results in delays in decision-making and missed opportunities to proactively mitigate drilling risks.
•Problem Description Currently, drilling teams do not have a unified platform that can:
i.Display nearby wells on a geospatial map relative to the active well.
ii.Provide instant access to historical drilling experiences and operational events from offset wells.
iii.Correlate drilling parameters, reservoir characteristics, mud losses, kicks, stuck pipe incidents, casing programs, cementing practices, and formation-specific risks across wells.
iv.Generate proactive alerts when current drilling operations approach depths or formations where similar challenges were encountered in nearby wells.

As a result, engineers often spend significant time manually searching through historical reports and databases, limiting the ability to make fast, informed, and data-driven operational decisions.

•Expected Outcome / Solution Develop an AI/ML-enabled Nearby Wells Intelligence System (NWIS) that acts as a standalone decision-support platform alongside eRTMAC that has institutional memory.

The solution should:

i.Use AI, NLP, OCR, and data analytics to automatically extract and structure information from historical drilling reports and well documents.
ii.Provide an interactive map-based visualization of nearby wells within a user-defined radius.
iii.Create a searchable knowledge repository of drilling events, lessons learned, operational challenges, and mitigation measures.
iv.Correlate geological, drilling, and reservoir data across wells based on depth and formation.
v.Develop predictive analytics models that can identify potential drilling risks such as mud losses, stuck pipe, overpressure zones, torque spikes, or cementing issues based on historical offset-well behaviour.
vi.Generate real-time alerts and recommendations to assist drilling engineers in proactive decision-making.
vii.Present information through a user-friendly dashboard for field and office-based personnel.
•Relevant Data Availability (if any)

Potential data sources available within OIL may include:

i.Well Completion Reports (WCRs)
ii.Daily Drilling Reports (DDRs)
iii.Drilling and mud logging databases iv. Historical well parameters and drilling records
v.Reservoir and geological data vi. eRTMAC data streams vii. Well trajectory and survey data viii. Casing, cementing, and mud program records ix. Historical operational event records including mud losses, kicks, stuck pipe incidents, fishing operations, and NPT events.