/SDG-SustainX

Sustainable development goals - carbon footprint score, ESG score for online stores through NLP and report generation

Primary LanguageHTMLMIT LicenseMIT

The Green Footprint | Track 3rd - Preserving the environment | 1st Position Winner

Blog post

Objective:

Challenge yourself and your team to develop innovative solutions for pressing issues in three critical areas: gender equality, food security, and environmental sustainability. Ideate and Pitch your ideas while networking with leading industrialists.

Problem Statement:

Preserving the Environment: Craft solutions for a sustainable future. Focus on renewable energy, waste management, and promoting eco-friendly practices. Address climate change, protect biodiversity, and empower communities to make a positive impact.

SDG-SustainX Logo

The Green Footprint is a multi-faceted platform designed to promote sustainability and awareness regarding energy consumption, product sustainability, and waste management. Our tools leverage the power of data analytics, natural language processing, and computer vision to provide users with actionable insights to make more eco-friendly decisions.

Features

  1. Energy Consumption Analysis (Data Analytics): Using big data analytics, this feature provides users with a personalized dashboard which identifies patterns, pinpoints inefficiencies, and encourages energy-saving habits.

  2. Amazon Product Sustainability Score (NLP+LLM, BERT Model): Our proprietary AI-driven scoring system analyzes product descriptions to calculate a sustainability score. The system utilizes state-of-the-art NLP techniques and BERT, a highly effective language representation model, for thorough examination.

  3. Brand Sustainability Profiles (LLM, Web Scraping): Utilizing advanced LLM capabilities, this feature compiles data on corporate practices obtained via web scraping to offer a concise profile highlighting brand sustainability efforts.

  4. Waste Classification Guide (Computer Vision, CNN, TensorflowJs): A user-friendly guide that incorporates a custom-trained Convolutional Neural Network (CNN) to identify and sort waste. It promulgates correct waste disposal procedures, assisting users in contributing to environmental conservation.

Tech Stack

  • HTML5
  • CSS3
  • JavaScript
  • Python
  • Streamlit
  • TensorFlow.js
  • Pandas
  • NumPy
  • Matplotlib
  • Gemini
  • BERT

Quick Links

Project Demo

The Green Footprint Demo

Usage

Clone the repository:

git clone https://github.com/Trident09/SDG-SustainX.git
cd SDG-SustainX

Data Analytics Dashboard

The dashboard can be accessed through the Streamlit app. Ensure you have all dependencies installed:

pip install -r requirements.txt
streamlit run Hello.py

Computer Vision Model

Please refer to the Google Colab notebook for the custom CNN implementation and its usage:

Image Detection Custom Model (Google Colab)

NLP BERT Model

For using the NLP model, navigate to the Google Colab notebook:

NLP Sustainability Model (BERT) Google Colab

Contributions

Contributions are welcome! Please feel free to submit a pull request or create an issue if you have suggestions for improvements.

Team
Trident09 error9098x

License

This project is licensed under the MIT License - see the LICENSE file for details.