Climate Artificial Intelligence


Title of the project

The project title is Clim-AI
Tackling the communication of financial data to the public challenge

Project idea (elevator pitch)

Our platform aims at showing climate data to the public in an intelligent way and to better communicate the effects of climate change projects funded by developed countries on the citizens. we are focusing on identifying key metrics that shows which projects has great impact on the country’s vulnerability. We are identifying those keys and patterns using AI

The story behind the project

We have seen that the public from the developed countries doesn’t see the impact climate change projects is making. The data is open and available however, it’s grandiose, hard to understand and raw. We are creating a simplified and efficient data representation

We are using these data below:

Team Members:

  • Ameera Tag
  • Ayomide Faleye
  • Dele Bakare
  • Ryme Kabak
  • Segun Adeniyi
  • Yasmine Hajjem


Link to our project:


Link to our PPT:


Firstly, we have thought about choosing the data that would more speak to an ordinary public and represent them in a map. We thought that this would me be more interactive. So, the data that we decided to keep were for instance:


Secondly, we tried to see the impact of climate finance on some indicators; the CO2 gas emission for instance. For that, we considered the classification of countries based on their income level (Low-income economies, Lower-middle-income economies, Upper-middle-income economies, High-income economies). The aim was that, given a group of countries, we see the impact of climate financing on a given country within the same group compared to a country where there was less climate finance.
To better present the idea, let’s take an example and consider the Low-income economies. Within this group, we chose Guinea and Ethiopia to bette illustrate the impact. And we tracked the CO2 gas emission over time. And in order to be able to interpret the results, we are assuming both countries had same CO2 gas emission starting point.
We get the figure below:

We can see that from 2003 and 2015, both countries start to have different CO2 emissions. In the same period, we found out that Guinea has started its first project and got 8 projects completed at the end spending around 8 millions dollars in total; while in Ethiopia, in which only 2 projects have got completed in 2015.
So using AI, we can predict in the future how much money should be invested in order to reach a certain level of CO2 gas emission. The impact could be this way more tangible and visible to donors and therefore our platform will push to change.