An AI-powered web application that analyzes urban climate reports and provides insights to mitigate the Urban Heat Island (UHI) effect using Natural Language Processing (NLP) techniques.
- 📌 Text Summarization – Extracts key points from environmental reports
- 🌍 Topic Modeling (LDA) – Identifies major climate-related themes
- 📊 Sentiment Analysis (VADER) – Detects public/environmental sentiment
- 🌳 Word Cloud Visualization – Highlights important terms
- 💡 AI Recommendations – Suggests green infrastructure solutions
- 🔍 Relevance Detection – Filters non-environmental inputs
- Python
- Flask (Web Framework)
- NLTK (Text Processing)
- Scikit-learn (LDA Topic Modeling)
- VADER Sentiment Analysis
- Matplotlib (Charts)
- WordCloud
Urban-Heat-Island-Mitigation-Analyzer/
│
├── app.py # Main Flask application
├── preprocess.py # Text cleaning functions
├── model.py # NLP models (topics, sentiment, summary)
├── insight_engine.py # Recommendation engine
├── requirements.txt # Dependencies
│
├── static/
│ └── style.css
│
├── templates/
│ └── index.html
│
└── README.md
1️⃣ Clone the repository
git clone https://github.com/Keerthana-webdev/Urban-Heat-Island-Mitigation-Analyzer.git
cd Urban-Heat-Island-Mitigation-Analyzer
2️⃣ Install dependencies
pip install -r requirements.txt
3️⃣ Run the Application
python app.py
- User inputs climate or urban heat-related text
- System checks if the content is relevant
- Text is cleaned and processed
- NLP models perform:
- Topic extraction (LDA)
- Sentiment analysis (VADER)
- Summarization
- Visual outputs are generated:
- Word cloud
- Sentiment chart
- AI suggests mitigation strategies
- Use Transformer models (BERT, GPT) for better summarization
- Add real-time datasets (API integration)
- Improve UI/UX design
- Deploy on cloud (AWS / Render / Heroku)