- Projects 1
- Followers 1
Krish Goyal
Lavasa, Maharashtra
Green Spaces Mapping in Urban Areas and Predictions
This project uses geographic information system (GIS) data, satellite imagery, and clustering techniques to identify and map green spaces within urban areas. The primary goal is to combat global warming and address climate change by promoting efficient urban planning strategies prioritising regions ...learn more
Project status: Concept
Intel Technologies
oneAPI,
Intel Python,
Intel Integrated Graphics
Overview / Usage
This project uses geographic information system (GIS) data, satellite imagery, and clustering techniques to identify and map green spaces within urban areas. The primary goal is to combat global warming and address climate change by promoting efficient urban planning strategies prioritising regions with high vegetation coverage and better air quality.
Clone this repository to your local machine.
Install required dependencies using pip install -r requirements.txt.
Replace placeholder paths in the code with actual data files.
Run the code sequentially to execute each step of the methodology.
Explore the generated visualizations and insights to inform urban planning decisions.
Methodology / Approach
Step 1: Loading GIS Data and Satellite Imagery
The project leverages the power of the Intel oneAPI toolkit, particularly the GeoAnalytics module, to efficiently load and manipulate GIS data and satellite imagery. The GeoAnalytics module provides optimized tools for data preprocessing, handling spatial information, and managing geospatial datasets.
Step 2: Green Space Mapping and Urban Landscape Identification
With the Intel oneAPI toolkit, the project calculates the Normalized Difference Vegetation Index (NDVI) from the satellite imagery's red and near-infrared bands. The toolkit also facilitates K-Means clustering, powered by the scikit-learn library, applied to NDVI values. This process efficiently segments the urban landscape into clusters representing varying vegetation levels.
Step 3: Air Quality Analysis
Assuming Air Quality Index (AQI) data availability for different city areas, the project utilizes Intel's oneAPI toolkit to analyze air quality and identify regions with lower pollution levels. The toolkit's optimized data analysis capabilities streamline this process.
Step 4: Efficient Urban Planning
The project identifies areas with high vegetation coverage and low pollution levels by combining the outcomes of green space clustering and AQI analysis. These regions are earmarked for targeted urban planning initiatives, with guidance from the Intel oneAPI toolkit's performance-enhancing capabilities.
Technologies Used
Intel oneAPI Toolkit: The toolkit is integral for efficient data loading, processing, and analysis.
NDVI Calculation: Accurate vegetation mapping using optimized tools.
K-Means Clustering: Enhanced clustering facilitated by the oneAPI toolkit and scikit-learn.
AQI Analysis: Efficient air quality analysis using oneAPI's data capabilities.
Targeted Urban Planning: Data-driven decision-making for sustainable development.
Documents and Presentations
Repository
https://github.com/kp-Captain02/The_Game_Changers.git
Collaborators