Cabo Delgado, Mozambique

AI for Coral Reef Conservation

A computer vision non-intrusive mechanism to collect images and give real-time insights about animals behaviour on coral reefs in Mozambican waters

The project

Motivation

Mozambique has the fourth-longest coastline in Africa, stretching over 2700 kilometres along the Indian Ocean. Traditional coral reef monitoring efforts involve few Mozambican human divers manually collecting images and footage underwater to be analysed subsequently. These methods are widely trusted and employed, however, the analysis remains entirely manual, which is both time-consuming and error-prone especially when multiple human observers are involved. To positively influence and support decision-making actions, accurate large scale monitoring systems need to be in place.

Goals

We want to develop a non-intrusive deep learning mechanism to collect images to give insights about coral reefs in the Vamizi Island. This will allow biologists to analyze data in real-time and infer on animals’ life story, behaviour, population, and survivorship in Mozambican waters. Initially, the coral reef will be located between 10-15 meters depth and 90 – 100 meters from the central power supply site on Vamizi Island. In particular, we will deploy an artificial reef to study the development of a fish community around a newly introduced structure to gain insight on the potential for ecosystem improvement in the context of coral reef restoration.

Long-term Vision

This project is an opportunity to pioneer the development of new technologies that will ultimately support conservation effort through enhanced data collection and processing. It will help gain insight on the ecological processes around artificial reefs. This is particularly important in the context of the oil and gas developments occurring in Mozambique and which will warrant the implementation of reef restoration measures. Additionally, this project will create capacity in the young Mozambican research community regarding the application of Artificial Intelligence technologies to tackle marine conservation issues.

Stay tuned for news in the near future!

Sponsors

HPI Future SOC Lab

the team

Erwan Sola

Project Lead, Centre for Environmental Investigation and Conservation, Lúrio University, Mozambique

Luís Pina

Project Manager, Centre of Engineering Studies and Projects, Lúrio University, Mozambique​

Kenneth Ezukwoke

AI4D Mentor, Institute Henri FAYOL, France

Natu Lauchande

External Collaborator, Data Engineer, Jumo, South Africa

Tiago Azevedo

External Collaborator, University of Cambridge, United kingdom

Bania Fonseca

Software Engineer, Mozambique

Emerson Cardoso

DevOps Engineer, Mozambique

Boaventura Manhique

Internal Collaborator, Networking Engineer, Lúrio University, Mozambique

Lourenço Matandire

Internal Collaborator, Mechatronics Engineer, Lúrio University, Mozambique