Solofoarisoa Rakotoniaina
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Solofoarisoa Rakotoniaina has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Christophe Révillion
University of Reunion, UMR 228 Espace-Dev (IRD, UA, UG, UM, UR), Saint-Pierre, La Réunion, France
2 shared publications - Cyprien Alexandre
French National Research Institute for Sustainable Development, Research Lab Espace-dev, Montpellier, France
2 shared publications - Gwenaëlle Pennober
UMR 228 Espace Dev, Université de La Réunion, 97400 Saint-Denis, Reunion Island, France
2 shared publications - Pascal Mouquet
UMR 228 Espace Dev, IRD, SEAS-OI, 97410 Saint-Pierre, Reunion Island, France
2 shared publications - Rosa Johary
Institut et Observatoire de Géophysique d’Antananarivo, Université d’Antananarivo, Antananarivo 101, Madagascar
2 shared publications - Solofo Rakotondraompiana
Institut et Observatoire de Géophysique d’Antananarivo, Université d’Antananarivo, Antananarivo 101, Madagascar
2 shared publications
Latest Publications
- Open Access
Mapping Coastal Marine Habitats with RGB and Multispectral UAS Imagery to Support Seaweed Aquaculture Management and Ecosystem Conservation
Madagascar’s expanding blue economy is largely underpinned by seaweed aquaculture, particularly Kappaphycus alvarezii (Cottonii), which offers an alternative to declining small-scale fisheries and strengthens the resilience of coastal socio-ecosystems. Ensuring the sustainability of this economic activity requires effective ecological monitoring of aquaculture sites and surrounding habitats. This study examines and compares the performance of two imaging configurations—an RGB composite derived from a subset of multispectral images capturing red (650 nm), green (560 nm), and blue (450 nm) bands; and a five-band multispectral (MS) image encompassing blue, green, red, red-edge (730 nm), and near-infrared (840 nm) bands—combined with a Random Forest (RF) classification model, for benthic habitat mapping in a seaweed cultivation context. High-resolution orthomosaics (2 cm/pixel) enabled the discrimination of Kappaphycus cultivation plots from three shallow-water habitats: (i) ‘benthic macrophytes’, which comprise: seagrass meadows and benthic macroalgal; (ii) ‘sandy bottom’ and (iii) ‘green algae’. The RF classification achieved an overall accuracy of 87% (Kappa = 0.82) across ~10 hectares. Producer’s accuracy exceeded 80% for Kappaphycus cultivation, green algae, and sandy bottom for both the RGB and MS datasets, indicating strong classification performance. However, early-stage seaweed was occasionally misclassified as benthic macrophytes, likely due to its low biomass and weak spectral signature. This UAS-based approach provided a robust and cost-effective framework for monitoring off-bottom seaweed farms and associated natural habitats. This approach supports sustainable aquaculture development and integrated coastal management in Madagascar and comparable tropical reef socio-ecosystems.
Open AccessMapping Coastal Marine Habitats with RGB and Multispectral UAS Imagery to Support Seaweed Aquaculture Management and Ecosystem Conservation
Madagascar’s expanding blue economy is largely underpinned by seaweed aquaculture, particularly Kappaphycus alvarezii (Cottonii), which offers an alternative to declining small-scale fisheries and strengthens the resilience of coastal socio-ecosystems. Ensuring the sustainability of this economic activity requires effective ecological monitoring of aquaculture sites and surrounding habitats. This study examines and compares the performance of two imaging configurations—an RGB composite derived from a subset of multispectral images capturing red (650 nm), green (560 nm), and blue (450 nm) bands; and a five-band multispectral (MS) image encompassing blue, green, red, red-edge (730 nm), and near-infrared (840 nm) bands—combined with a Random Forest (RF) classification model, for benthic habitat mapping in a seaweed cultivation context. High-resolution orthomosaics (2 cm/pixel) enabled the discrimination of Kappaphycus cultivation plots from three shallow-water habitats: (i) ‘benthic macrophytes’, which comprise: seagrass meadows and benthic macroalgal; (ii) ‘sandy bottom’ and (iii) ‘green algae’. The RF classification achieved an overall accuracy of 87% (Kappa = 0.82) across ~10 hectares. Producer’s accuracy exceeded 80% for Kappaphycus cultivation, green algae, and sandy bottom for both the RGB and MS datasets, indicating strong classification performance. However, early-stage seaweed was occasionally misclassified as benthic macrophytes, likely due to its low biomass and weak spectral signature. This UAS-based approach provided a robust and cost-effective framework for monitoring off-bottom seaweed farms and associated natural habitats. This approach supports sustainable aquaculture development and integrated coastal management in Madagascar and comparable tropical reef socio-ecosystems.
- Open Access
- 15 November 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (22) , 5368
Detection of Large-Scale Floods Using Google Earth Engine and Google Colab
This paper presents an operational approach for detecting floods and establishing flood extent using Sentinel-1 radar imagery with Google Earth Engine. The methodology relies on change detection, comparing pre-event and post-event images. The change-detection method is based on the normalised difference ratio. Additionally, the HAND model is employed to delineate zones for processing only in flood-prone areas. The approach was tested and calibrated at a small scale to optimise parameters. In these calibration tests, an accuracy of 85% is achieved. The approach was then applied to the whole of the island of Madagascar after Cyclone Batsirai in 2022. The proposed method is enabled by the computing power and data availability of Google Earth Engine and Google Colab. The results show satisfactory accuracy in delineating flooded areas. The advantages of this approach are its rapidity, online availability and ability to detect floods over a wide area. The approach relying on Google Tools thus offers an effective solution for generating a large-scale synoptic picture to inform hazard management decision making. However, one of the method’s drawbacks is that it depends to a large extent on frequent radar imagery being available at the time of flood events and on free access to the platform. These drawbacks will need to be taken into account in an operational scenario.
- 15 November 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (22) , 5368
Open AccessDetection of Large-Scale Floods Using Google Earth Engine and Google Colab
This paper presents an operational approach for detecting floods and establishing flood extent using Sentinel-1 radar imagery with Google Earth Engine. The methodology relies on change detection, comparing pre-event and post-event images. The change-detection method is based on the normalised difference ratio. Additionally, the HAND model is employed to delineate zones for processing only in flood-prone areas. The approach was tested and calibrated at a small scale to optimise parameters. In these calibration tests, an accuracy of 85% is achieved. The approach was then applied to the whole of the island of Madagascar after Cyclone Batsirai in 2022. The proposed method is enabled by the computing power and data availability of Google Earth Engine and Google Colab. The results show satisfactory accuracy in delineating flooded areas. The advantages of this approach are its rapidity, online availability and ability to detect floods over a wide area. The approach relying on Google Tools thus offers an effective solution for generating a large-scale synoptic picture to inform hazard management decision making. However, one of the method’s drawbacks is that it depends to a large extent on frequent radar imagery being available at the time of flood events and on free access to the platform. These drawbacks will need to be taken into account in an operational scenario.
- Open Access
- 20 September 2023
- Published by MDPI AG in Preprints.org
Detection of Large-Scale Floods Using Google Earth Engine and Google Colab
This paper presents an operational approach for detecting floods and establishing flood extent using Sentinel-1 radar imagery with Google Earth Engine. Flooded areas are identified using a change-detection method based on the normalized difference. The HAND algorithm is used to delineate zones for processing. The approach was tested and calibrated at small scale to identify optimal parameters for flood detection. It was then applied to the whole of the island of Madagascar after the cyclone Batsirai in 2022. The proposed method is enabled by the computing power and data availability of Google Earth Engine and Google Colab. The results show satisfactory accuracy in delineating flooded areas. The advantages of this approach are its rapidity, online availability and ability to detect floods over a wide area. The approach relying on Google tools thus offers an effective solution for generating a large-scale synoptic picture to inform hazard management decision-making. However, one of the method’s drawbacks is that it depends to a large extent on frequent radar imagery being available at the time of flood events and on free access to the platform. These drawbacks will need to be taken into account in an operational scenario.
- 20 September 2023
- Published by MDPI AG in Preprints.org
Open AccessDetection of Large-Scale Floods Using Google Earth Engine and Google Colab
This paper presents an operational approach for detecting floods and establishing flood extent using Sentinel-1 radar imagery with Google Earth Engine. Flooded areas are identified using a change-detection method based on the normalized difference. The HAND algorithm is used to delineate zones for processing. The approach was tested and calibrated at small scale to identify optimal parameters for flood detection. It was then applied to the whole of the island of Madagascar after the cyclone Batsirai in 2022. The proposed method is enabled by the computing power and data availability of Google Earth Engine and Google Colab. The results show satisfactory accuracy in delineating flooded areas. The advantages of this approach are its rapidity, online availability and ability to detect floods over a wide area. The approach relying on Google tools thus offers an effective solution for generating a large-scale synoptic picture to inform hazard management decision-making. However, one of the method’s drawbacks is that it depends to a large extent on frequent radar imagery being available at the time of flood events and on free access to the platform. These drawbacks will need to be taken into account in an operational scenario.