- Determining the poverty levels of various regions throughout the world is crucial in identifying interventions for poverty reduction initiatives and directing resources fairly.
- However, reliable data on global economic livelihoods is hard to come by, especially for areas in the developing world, hampering efforts to both deploy services and monitor/evaluate progress.
- This project proposes to use satellite images to detect economic activity and, as a result, estimate poverty in a location.
- A Recurrent neural network is trained to learn various developmental parameters like rooftop type, source of lighting and proximity to water sources, Agriculture Areas, Road Structure, and Industrial Areas.
- Currently, poverty is formally calculated by numerous philanthropic agencies including the World Bank.
- One of the reasons why data on poverty is sparse in the developing world is because it is infrequently collected due to the high cost associated with on-the-ground surveys.
- Only after this step does the country realize where it stands with respect to the income levels.
- The current challenge in this domain is that agencies across the world who predict income levels take a huge amount of time to do the same.
- Once done this topic is not raised until the next decennial census comes up.
- Not only does it take a big chunk of time but also staggering amounts of money is invested into these kinds of projects.
- This is a real headache for agencies and governments all around the world.
- Recent advancements in deep learning present an exciting opportunity for application to poverty prediction.
- More specifically, both daytime and nighttime satellite imagery of regions can be used to estimate poverty in certain regions.
- Deep learning has been a main factor behind recent breakthroughs in numerous computer vision tasks such as image classification, segmentation, and object detection.
- In this project, we test the hypothesis that deep learning can leverage satellite imagery to reliably predict the poverty level of a region.
- We assemble a dataset of 88,386 images from 44,193 cities spanning Africa, South America, Asia, Europe, and the Caribbean.
- For each city, we obtain a daytime satellite image, a nighttime satellite image, and the city’s wealth index.
- I then train Recurrent neural networks (RNNs) to predict a city’s wealth index, given a satellite image.
- Front End – Anaconda IDE
- Backend – SQL
- Language – Python 3.8
- Hard Disk: Greater than 500 GB
- RAM: Greater than 4 GB
- Processor: I3 and Above
* Base Paper
* Complete Source Code
* Complete Documentation
* Complete Presentation Slides
* Flow Diagram
* Database File
* Execution Procedure
* Readme File
* Video Tutorials