Integrative Approach for Operational Sargassum Stranding Forecasts – SargAlert

Algal index calculation, radiative model inversion and deep learning (AI) methods are applied to satellite data corrected for atmospheric transfer (VIIRS, OLCI, MSI, ABI, MODIS) to detect and quantify the presence of Sargassum rafts, in order to deduce surfaces and biomasses.

Aggregation velocities and directions are obtained from algal index maps obtained with 3-hour intervals during the day and using keypoint or optical flow tracking methods.

To validate the measurements obtained from satellite data, a field campaign was carried out from June 24 to July 4, 2024 in Martinique Island) to measure the aggregation velocities (using SPOT trackers), 2) the spectral reflectance of Sargassum (using a field spectrometer), 3) the aggregation depth (using underwater images), 4) the biomass of Sargassum corresponding to a given surface (by weighing 1 m² samples) and 5) the aggregation coverage (using aerial images).

Interviews with local stakeholders (municipalities, fishermen, prefecture, Ministry of the Sea, Sargassum collectors, etc.) in Martinique are conducted to fully understand their needs in terms of bulletins. Based on the coverage fraction maps, new quantitative indicators of Sargassum presence and evolution are developed in targeted areas.

A 3-year satellite data archive on the Caribbean Sea and the Atlantic Ocean is currently being developed (OLCI, MSI, MODIS). Products for detecting rafts, algal indices (dAFAI type) and cover fractions (to deduce surfaces and biomasses) are already available, obtained from MODIS, OLCI and MSI images, and radiative model inversion or deep learning (artificial intelligence) methods.

Comparison of Sargassum aggregation rates obtained from satellite data (MODIS and GOES) with co-occurring drifters has proven the reliability of the keypoint and optical flow methods.

The new activity and evolution indicators have been integrated into the bulletin that Météo-France publishes every 3 days, to indicate two-week trends.

The satellite data archive must be completed with VIIRS and GOES geostationary data. This archive will be accessible via a web server for the development of algorithms and data exploitation.

The method for estimating raft speeds will now be extended to all possible satellite detections at a few hours interval. These speeds will then be integrated into transport models to predict the location and dates of strandings.

The analysis of interviews with local stakeholders will make it possible to develop and distribute bulletins specific to each user.

Laval, M., Belmouhcine, A., Courtrai, L., Descloitres, J., Salazar-Garibay, A., Schamberger, L., Minghelli A. Thibaut T., Dorville R., Mazoyer C., Zongo P., & Chevalier, C. (2023). Detection of Sargassum from Sentinel Satellite Sensors Using Deep Learning Approach. Remote Sensing, 15(4), 1104 [link]

Podlejski, W., Berline, L., Nerini, D., Doglioli, A., & Lett, C. (2023). A new Sargassum drift model derived from features tracking in MODIS images. Marine Pollution Bulletin, 188, 114629

The objective of the SargAlert project is to significantly improve the forecasts of the strandings of the invasive algal species Sargassum in the tropical Atlantic Ocean, in the Caribbean Sea and on the Brazilian coast. The synergy between satellite data / ocean transport modeling / in-situ measurements will be used for that purpose. SargAlert will provide alert bulletins to end-users such as territorial authority, tourism, fishers. The challenges that will be addressed by SargAlert are as follows:
- detection and monitoring of at different time (hour to daily) and spatial (20 m to 5 km) scales using a multi-sensor satellite data analysis (Low Earth and GEOstationary orbits),
- improvement of Sargassum stranding forecasts by combining physical transport models with artificial intelligence approaches,
- validation of satellite data products and forecast models using in-situ measurements,
- production of alert bulletins to address societal issues.

The innovative developments of the project will enable an integrative approach of the Sargassum stranding issues: synergy between satellite data, understanding of Sargassum spatio-temporal distribution, transport forecast. Improvements of ocean modeling of dynamics will benefit societal authorities to better respond to the risks induced by the more frequent and intense Sargassum blooms in the Atlantic Ocean. The operational Sargassum forecast center will thus have all required inputs to provide reliable forecasts in near real time.

This federative and interdisciplinary project includes complementary partners from academic laboratories, including a human science team (AEM, IRISA, LATMOS, LC2S, LIS, Marbec, MIO, UFPE/UFRPE), from an operational forecast center (Météo-France) and from a national satellite data center (AERIS/ICARE).