According to the UNHCR (United Nations High Commissioner for Refugees), over 110 million people are currently displaced worldwide. With the intensification of conflicts and the impact of climate change, these numbers are expected to rise significantly in the future.
To gather information on the socio-economic and living conditions of refugees, the UNHCR runs a program called the Forced Displacement Survey (FDS) at regular intervals (approximately every 4 years). The cost of this program can exceed 4 billion dollars, which justifies the 4-year interval. However, this approach results in a loss of critical data on how refugee camps evolve over time, especially in areas where geopolitical factors can dramatically change living conditions overnight. In such cases, even after 4 years, the UNHCR may find itself needing to restart the entire process, leading to additional costs.
To address this challenge, the goal is to develop a function f(x, y, z) -> a, b, c, where:
x: Represents a refugee camp.y: Represents a series of satellite images.z: Represents the camp's geographical location.
From this input, we aim to predict:
- A: Socio-economic conditions such as access to energy, food, and nutrition.
- B: Sociocultural conditions like access to healthcare and housing.
- C: Civil and political conditions, including access to information and security.
Our project aims to use artificial intelligence and deep learning to analyze satellite imagery of a given region where a refugee camp is located. By extracting relevant socio-economic, sociocultural, and civil-political data from these images, we can:
- Reduce the operational costs of the FDS program.
- Equip the UNHCR with a real-time monitoring tool for refugee camps, enabling timely intervention and support.
With this approach, we aim to improve data collection accuracy, reduce survey costs, and enhance the ability to monitor refugee camps on an ongoing basis, addressing the dynamic nature of these environments.
Feel free to contribute by submitting issues, ideas, or code improvements to help the project achieve its mission.