Humanitywatch is aimed at assistance actors (humanitarian and development), and institutional actors, all over the world thanks to AI and Earth Observation technologies.
What is the challenge that is being addressed?
Humanitarian partners are operating in increasingly complex environments. Prolonged, multifaceted crises marked by volatile security conditions, rapidly growing needs and severe access constraints are today prevailing in the humanitarian sector, yet greatly challenging the effectiveness of the response. In challenging operational environments such as the Central Sahel, strategic information management is pivotal to allow humanitarian partners to adapt to rapidly changing dynamics and safely navigate through difficult security conditions to deliver assistance where most needed.
What is the AI solution the project has implemented?
"The EO Data is processed by the remote sensing processor which is based on the Pixstart QuantEO platform. It includes atmospheric or speckle correction valid anywhere over Earth, feature engineering including Sentinel 1 and 2 combinations, and the application of Artificial Neural Networks (ANN). We also proceed a supervised learning phase for the detection of desired objects like harvest field via classical machine learning on radiometric information."
Who helped implement the AI solution?
This solution is implemented in the context of HumanityWatch, a winning project from the AI4Copernicus 1st Open Call. The consortium consists of Pixstart and Keyaid Consulting, while the results of the project are available here.