DecodeX
Home/Problem Statements/SIH26023
All 226 Statements
SIH26023SoftwareSmart Automation
₹1,50,000 Prize (₹75k Joint)
•
Deadline: 20 September 2026
•
Submitted Ideas: 0/500

AI-Powered Geological, Mining and other Reporting Solution for CMPDI/CIL subsidiaries

Ministry / Organization: Ministry of Coal
Department: Coal India Limited
SIH Official Portal
Technical Complexity
8/10
Dataset Accessibility
6/10
36h Hackathon Viability
8/10
Step 0 • Zero-Jargon Layman Summary

“Coal India and CMPDI spend massive manual effort searching through decades of paper maps, scanned PDFs, and complex spreadsheets to create reports and answer urgent ministry queries. This solution builds an intelligent software system that automatically reads these messy documents, extracts key geological data with high accuracy, builds instant reports, and provides an AI assistant to answer complex government questions.”

The DecodeX PS Decoder™

Deconstructed Problem Blueprint

Step 1

WHAT TO BUILD?

An enterprise AI-driven Document Processing (IDP), Retrieval-Augmented Generation (RAG), and Automated Reporting Platform tailored specifically for geological and coal mining datasets.

Step 2

WHO IS IT FOR?

Central Mine Planning & Design Institute (CMPDI) engineers, Coal India Limited (CIL) subsidiary officers, Ministry of Coal officials, and teams handling parliamentary inquiry responses.

Step 3

WHY DOES IT EXIST?

Decades of critical mining data are trapped in unstructured legacy scanned PDFs, borehole logs, and scattered spreadsheets, leading to slow report generation, manual errors, and delayed responses to high-priority parliamentary questions.

Step 4

INPUT → PROCESS → OUTPUT ARCHITECTURE PIPELINE

01 • Inputs & Telemetry

Scanned legacy geological PDFs, scanned borehole logs, production spreadsheets (Excel/CSV), handwritten field notes, and text queries from officials.

02 • Processing & AI Core

Layout-aware OCR parsing, tabular structure extraction, vector embedding generation, domain-tuned RAG pipeline, automated topic modeling (BERTopic), and template-driven PDF report generation.

03 • Actionable Deliverables

Automated PDF/Word report generation, dynamic word cloud and topic trend analytics dashboard, and an interactive query assistant providing cited answers with exact PDF page highlight references.

Step 5

CONSTRAINTS

  • Must support on-premise deployment capabilities due to sensitive national energy and mineral reserve data.
  • High resilience against heavily degraded, skewed, or low-resolution scanned documents from legacy archives.
  • Strict precision required when parsing complex nested tables and multi-column geological layouts.
Step 6

JURY METRICS

  • Data extraction accuracy from complex scanned tables (>95%)
  • Report preparation time reduction (aiming for >80% reduction)
  • Query response latency (<3 seconds)
  • RAG response groundedness with zero hallucinations on coal production metrics
Step 7

CORE BOTTLENECK

Accurately extracting and preserving structural context from decades-old scanned geological tables and handwritten borehole logs without losing data lineage.

Why You Should Choose This PS (Pros)

  • High impact and clear government pain point with direct adoption potential by Ministry of Coal.
  • Rich problem scope allowing teams to demonstrate computer vision, advanced RAG, NLP, and UI/UX in one cohesive platform.
  • Well-defined deliverables (Report Generator, Topic Identification Module, Query-Response System) making evaluation criteria straightforward.

Challenges & Risks to Watch (Cons)

  • No official dataset provided, requiring teams to curate/scrape sample geological reports and synthesize legacy scans.
  • High vulnerability to OCR failure on bad quality scans during live evaluation.
Hackathon Blueprint

Recommended Tech Stack & Grand Finale Features

Frontend & Mobile
Next.jsTailwind CSSPDF.js for visual document annotation and bounding box highlighting
Backend & APIs
FastAPICeleryRedis
AI / ML & Models
Surya OCR / DocTR for layout-aware OCRTable Transformer / Camelot for table parsingBERTopic for word cloud and topic modelingLlama-3-8B-Instruct / Qwen-2.5-7B fine-tuned via UnslothBGE-Large-EN for vector embeddings
Database & Cloud
PostgreSQL + pgvectorQdrant Vector DatabaseMinIO Object Storage

Killer Features to Impress the SIH Jury

Visual Citation & Bounding Box Highlighting: Clicking any AI answer or extracted table cell instantly opens and highlights the exact region on the original scanned PDF.
Automated Parliamentary Query Response Generator: Single-click generator that drafts formal parliamentary replies formatted according to official Ministry templates with supporting source tables.
Domain-Specific Data Validation Guardrails: Automated sanity checks that flag mathematical anomalies or impossible reserve depth/tonnage values before final report rendering.
Spatiotemporal Topic Drift Analysis: Interactive dynamic word clouds and topic maps tracking emerging operational and safety discussions across CIL subsidiaries over time.
View Official SIH 2026 Portal Raw Text
▼
BACKGROUND

CMPDI/CIL subsidiaries play a key role in providing geological and mining information to the Ministry of Coal and responding to parliamentary and high-priority administrative inquiries. These reports require compilation of data from scanned PDFs, digital documents, spreadsheets, images, and historical archives. The current workflow is largely manual, resulting in:

•High dependence on individual expertise
•Delay in generating reports and analytics
•Higher probability of manual errors
•Limited ability to quickly retrieve insights when required Objectives:
•Deploy an automated platform for AI-assisted geological, mining and any other production figures document processing and reporting.
•Enhance data validation, consistency, and traceability across historical and contemporary datasets.
•Build an efficient, scalable foundation for future digital transformation initiatives within each CIL subsidiary and the Ministry of Coal.

Desired Outcomes: The solution should be implemented in structured phases, including requirement analysis, data digitization and pre-processing, platform development, system testing, integration with CIL subsidiary workflows, training, and continuous enhancement to ensure scalability and long-term adoption.

1.Automated Report Generation Platform
2.Automated Word Cloud and Topic Identification Module
3.AI-Based Query and Response System Expected Benefits:
•Reduction in report preparation time as less as it can be, quantified in percentage.
•Maximum accuracy, calculated in percentage in structured extraction and report generation.
•Maximum automation, calculated in percentage of repetitive reporting and response workflows.
•Faster response to high-level inquiries and parliamentary questions
•Improved data accessibility, transparency, and standardization
•Strengthened operational efficiency and informed decision-making using historical insights and AI-generated recommendations Impact:

The proposed system should significantly modernize CMPDI/CIL subsidiaries reporting ecosystem, reduce dependency on manual processes, improve response timelines, and strengthen the coal sector’s capability to support governance, policy planning, and operational excellence.