Ganga River in the Himalayas at sunrise

Environmental Analytics & Documentary

The Ganga More Than a River

A sacred river. A growing crisis. A story that must be told.

Scroll
Ganga River
15+
Data Sources
24+
Years of Data
50+
Pollution Hotspots

About the Project

Echoes of the Ganga

Echoes of the Ganga is a data-driven environmental initiative focused on analyzing pollution trends and identifying key contamination patterns in the Ganga River using long-term datasets.

Data has been collected from official government sources including the Namami Gange Programme, Central Pollution Control Board (CPCB), and the Ministry of Jal Shakti, along with supporting research and environmental reports.

The dataset spans from 2000 to 2024, covering the entire river from Gangotri (origin) to West Bengal (end point).

Project Includes

Pollution trend analysis across 24+ years
Comparison with other major rivers in India
Identification of key pollution factors
Machine learning predictions till 2030

Research Findings

What the Data Reveals

Years of data analysis uncovered clear patterns in how and why the Ganga is being polluted.

Seasonal Patterns

Analysis of data (2000–2024) shows a consistent rise in pollution levels during monsoon months, driven by increased agricultural runoff and urban discharge entering the river system.

Industrial Impact

Industrial discharge significantly contributes to organic load and chemical contamination, with several high-density industrial zones consistently exceeding safe limits.

Urban Pollution

Urban sewage and untreated wastewater remain major pollution sources, with multiple cities showing sustained high pollution levels due to inadequate treatment infrastructure.

Agricultural Runoff

Runoff from agricultural activities introduces nutrients and chemicals into the river, contributing to eutrophication and increased biological contamination levels.

Critical Hotspots

Data analysis identifies key pollution hotspots along the Ganga where BOD and COD levels frequently exceed permissible limits, requiring targeted intervention and monitoring.

Treatment Infrastructure Gap

Data analysis (2000–2024) reveals a significant gap between sewage generation and treatment capacity, resulting in large volumes of untreated wastewater entering the river system.

Data Sources & Validation

This analysis is based on verified government datasets collected from:

  • Namami Gange Programme
  • Central Pollution Control Board (CPCB)
  • Ministry of Jal Shakti

Based on government-verified datasets (2000–2024), ensuring accuracy, reliability, and real-world environmental insights.

Research

Thesis SectionsData-Driven Research & Predictive Analysis (2000–2030)

Ganga River Analysis

Ganga River Analysis

Core pollution trends & ML predictions

Comprehensive analysis of the Ganga river using real-world datasets from 2000 onwards. Includes pollution trends, hotspot identification, and machine learning-based forecasting of water quality and risk levels up to 2030.

Key Insights

  • Pollution trend analysis (2000–2024)
  • High-risk hotspot identification
  • ML-based prediction till 2030
  • BOD, COD & DO parameter analysis
Ganga Basin

Ganga Basin

River system overview

Geographical and ecological analysis of the Ganga basin, including tributary networks, regional distribution, and environmental significance influencing pollution patterns.

Key Insights

  • Basin geography & tributary mapping
  • Regional ecological significance
  • Pollution pattern distribution
  • Hydrological flow analysis
Drains & Treatment Systems

Drains & Treatment Systems

Pollution flow & infrastructure analysis

Evaluation of drainage networks, sewage treatment plants (STPs), and inefficiencies in treatment systems contributing to untreated discharge into the river.

Key Insights

  • STP capacity vs. actual treatment
  • Untreated sewage discharge volumes
  • Drain network mapping
  • Infrastructure efficiency gaps
Other Rivers & Tributaries

Other Rivers & Tributaries

Impact of connected water systems

Analysis of tributaries and connected rivers, examining their role in amplifying or reducing pollution levels in the main Ganga river.

Key Insights

  • Tributary pollution contribution
  • Cross-river contamination flow
  • Seasonal variation analysis
  • Comparative water quality data
Industrial Pollution

Industrial Pollution

Industrial discharge & impact analysis

Study of industrial pollution sources, effluent discharge patterns, and their impact on river health using data-driven insights.

Key Insights

  • Industry-wise effluent profiling
  • Heavy metal contamination mapping
  • Regulatory compliance analysis
  • Impact on aquatic biodiversity
Final Report

Final Report

Integrated findings & recommendations

Complete synthesis of findings, combining all analyses with machine learning predictions and actionable recommendations for river restoration and policy improvement.

Key Insights

  • Integrated multi-source findings
  • ML-driven future projections
  • Policy & restoration recommendations
  • Actionable intervention roadmap
Public Access

Thesis Preview – Public Access Coming Soon

A structured preview of the complete thesis. Full access to detailed research, datasets, and machine learning models will be available after final publication.

Publication in Progress

Research Paper

The complete research paper based on this thesis, including methodology, data analysis, and machine learning models, will be published soon.

Watch

Project Experience Through Video

Experience the journey of Echoes of the Ganga through presentation, storytelling, and real-world documentary visuals.

Academic

IIT Roorkee Presentation

A glimpse of the project presentation delivered at IIT Roorkee, showcasing the data analysis, methodology, and key findings.

Trailer

Documentary Trailer

A short preview of the documentary highlighting the story, field visits, and data-driven insights behind the Ganga pollution analysis.

Film

Documentary Experience

Part 1 — Live

Echoes of the Ganga — Part 1: The Reality

This documentary explores pollution using data and real-world observations. Shot across the most sacred stretches of the Ganga, it reveals the ground reality behind the numbers.

Shot across: Devprayag, Rishikesh, Haridwar
Documentary Part 2
Coming Soon
Part 2 — Coming Soon

Echoes of the Ganga Part 2: The Path to Solutions

The journey continues beyond the problem exploring real solutions, ongoing efforts, and what data reveals about the future of the Ganga.

We return to the same locations — this time to uncover solutions and real change.

The Team

The People Behind the Project

A dedicated team combining data science expertise with a passion for environmental impact.

Sarthak Bobade
Project Lead

Sarthak Bobade

Data Scientist | Environmental Analytics

Led and executed data collection, analysis, machine learning modeling, documentary creation, and end-to-end platform development.

Data ScienceMachine LearningEnvironmental AnalyticsDocumentary
Pavan Khandare
Mentor

Pavan Khandare

Lead Data Scientist | AI Architect

Provided guidance in machine learning, system design, and real-world implementation of data-driven solutions for environmental analysis. Supported project architecture and practical deployment decisions.

AI & MLData StrategyMentorshipEnvironmental Impact

This is Part 1 of the journey — understanding the reality.

Project Submission at IIT Roorkee | Echoes of the Ganga Proud to share that I had the opportunity to present and submit my project “Echoes of the Ganga” during the workshop at IIT Roorkee. This project is a data-driven environmental analytics initiative aimed at uncovering hidden pollution patterns in the Ganga River using data science and machine learning. By analyzing multi-year datasets, the project highlights pollution trends, identifies high-risk zones, and supports sustainable river management. Presenting this work at IIT Roorkee was an enriching experience, interacting with faculty, coordinating with participants, and contributing to meaningful discussions on environmental sustainability and data-driven solutions. Grateful for the guidance, collaboration, and recognition received during the workshop. Moments like these strengthen my commitment to using data science for social and environmental impact. #EchoesOfTheGanga #IITRoorkee #DataScienceForGood #EnvironmentalAnalytics #WaterQuality #MachineLearning #Sustainability #PublicHealth #AIForImpact Indian Institute of Technology, Roorkee Ethical Edufabrica Pvt. Ltd® Pavan Khandare
Sarthak Bobade
Data Scientist | AI & Machine Learning | Healthcare & Environmental Analytics | Generative AI
🌊 Echoes of the Ganga Trailer Release I’m proud to share the trailer of Echoes of the Ganga, a data-driven documentary and research project that explores pollution trends across the Ganga River basin. Using real-world datasets and environmental indicators, this project analyzes historical patterns and predicts pollution trends up to 2030, offering insights into the future health of Maa Ganga. The analysis revealed several high-risk pollution hotspots that highlight the urgent need for sustainable action and responsible environmental management. This work aims to transform data into awareness and inspire informed action for river conservation. 🎬 Trailer below | Full documentary & thesis coming soon #EchoesOfTheGanga #NamamiGange #JalShakti #CleanGanga #PollutionControl #WaterQuality #Sustainability #EnvironmentalData #IITRoorkee #SaveGanga #EnvironmentalAwareness #DataScience #MachineLearning #AIforGood Indian Institute of Technology, Roorkee Central Pollution Control Board (CPCB) Pavan Khandare
Sarthak Bobade
Data Scientist | AI & Machine Learning | Healthcare & Environmental Analytics | Generative AI