A revolutionary tool for automatic detection and counting of bats using artificial intelligence, transforming hours of manual work into instant analysis.

• Improving data reliability – Our AI is trained to handle different lighting conditions, bat species, roost types and provides accurate counts in minutes.
• Supporting conservation efforts – Better data means better protection for bat populations.

Interactive mapping application of bee food availability across Réunion island, combining connected hive data, land cover, urbanisation and open source weather data.

• Multi-source data integration: hive sensors, open geospatial & cartographic data.
• Monitorun interactive map of food availability across the island

Analysis of migration trajectories of hundreds of migratory birds using over 40 million GPS points to understand their movements between France and North Africa.

• Which stopover areas do they rest in?
• How long do they stay there?
• What migration corridors are used?
• How do their trajectories vary based on weather conditions?

A 2024-2025 project delivered for the Coeur de Forêt association to move forest plot management from spreadsheets to a PostgreSQL/PostGIS database and design dedicated business interfaces.

• Transition from tabular management to PostgreSQL/PostGIS
• Business interface design for plot monitoring

Training ISA Lille students in the basics of image analysis applied to ecology, with hands-on practice of annotation, learning and results interpretation workflows.

• ISA Lille students discovering how image analysis can be applied to life science use cases.
• Data preparation, annotation, result reading, model evaluation and implementation best practices.

A 2025-2026 training project delivered for the BCA of Annecy (French Army) to teach the basics of geospatial image analysis for operational use cases.

• Introduction to geospatial image analysis methods
• Support for teams on concrete use cases

Mission delivered in 2025 for Epigreen to analyze health data related to the Ebola outbreak in Africa using machine learning methods, to improve identification of epidemic dynamics and monitoring of critical indicators.

• Machine learning model development on epidemiological datasets
• Visualization and interpretation of spread indicators for decision support