Seagrass Depth Distribution Mirrors Coastal Development in the Mexican Caribbean – An Automated Analysis of 800 Satellite Images

Hedley, John D.; Velázquez-Ochoa, Roberto; Enríquez, Susana

doi:10.3389/fmars.2021.733169

Cited by 6 publications

(4 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study by Hedley et al (2021) carried out in the same system supposed a T. testudinum dominated vegetation, which is still correct, but may be changing in the future due to continuing pressures on this system. This only exemplifies the need for continuous ground truthing, as already proposed by Neckles et al (2012).…”

Section: Discussionmentioning

confidence: 94%

“…The lagoon floor is usually composed of calcareous sand, and seagrass meadows are interspersed with underwater dunes consisting of loose calcareous sands devoid of vegetation. The dominant seagrass species is Thalassia testudinum, which is considered the climax species in the Caribbean, along with Syringodium filiforme, Halodule wrightii and rhizophytic algae (van Tussenbroek, 2011;Hedley et al, 2021).…”

Section: Study Areamentioning

confidence: 99%

See 1 more Smart Citation

Mapping the structure of mixed seagrass meadows in the Mexican Caribbean

et al. 2022

View full text Add to dashboard Cite

The physical and ecological importance of seagrass meadows in coastal processes is widely recognized, and the development of tools facilitating characterization of their structure and distribution is important for improving our understanding of these processes. Mixed (multi-specific) meadows in a Mexican Caribbean reef lagoon were mapped employing a multiparameter approach, using PlanetScope remote sensing images, and supervised classification based on parameters related to the structure of the seagrasses meadows, including the cover percentages of seagrass/algae/sediment, algae thalli and seagrass shoot densities, canopy heights and estimated leaf area index (LAI). The cover, seagrass and algae densities, and seagrass canopy heights were obtained using ground truth sampling, while the LAI was estimated using data obtained from long-term monitoring programs. The maps do not show the differentiation of seagrass species, but ground truthing contemplated characterization of the density of Thalassia testudinum, Syringodium filiforme and Halodule wrightii and their respective LAIs. S. filiforme was the dominant species in terms of shoot density, and T. testudinum was dominant in terms of LAI. In the multiparameter-based map four classes were defined, based on the cover and structural characteristics, and its overall accuracy was very high (~90%). Maps based on sediment cover and LAI alone also had 4 classes, but they were less accurate than the multiparameter-based map (~70% and ~80%, respectively). The multiparameter-based seagrass map provided spatially-explicit data on the abundance and structure of seagrasses, useful for future monitoring of the changes in the meadows, and also for studies of that require data of large-scale meadow structure, such as inventories of associated biota, blue carbon storage, or modelling of the local hydrodynamics.

show abstract

Section: Discussionmentioning

confidence: 94%

Section: Study Areamentioning

confidence: 99%

Mapping the structure of mixed seagrass meadows in the Mexican Caribbean

et al. 2022

View full text Add to dashboard Cite

show abstract

“…A correction is also required to remove the underwater scattering and absorption in order to correctly detect seagrasses [22]. Complicated radiative transfer models are used to retrieve seagrass information [35][36][37][38]. Lastly, machine learning algorithms are readily available, and many studies have adopted various machine learning algorithms to map seagrass distribution [22,25,[27][28][29].…”

Section: Remote Sensing Of Seagrassmentioning

confidence: 99%

Quantifying Seagrass Density Using Sentinel-2 Data and Machine Learning

Meister,

2024

Remote Sensing

View full text Add to dashboard Cite

Seagrasses, rooted aquatic plants growing completely underwater, are extremely important for the coastal ecosystem. They are an important component of the total carbon burial in the ocean, they provide food, shelter, and nursery to many aquatic organisms in coastal ecosystems, and they improve water quality. Due to human activity, seagrass coverage has been rapidly declining, and there is an urgent need to monitor seagrasses consistently. Seagrass coverage has been closely monitored in the Chesapeake Bay since 1970 using air photos and ground samples. These efforts are costly and time-consuming. Many studies have used remote sensing data to identify seagrass bed outlines, but few have mapped seagrass bed density. This study used Sentinel-2 satellite data and machine learning in Google Earth Engine and the Chesapeake Bay Program field data to map seagrass density. We used seagrass density data from the Chincoteague and Sinepuxent Bay to train machine learning algorithms and evaluate their accuracies. Out of the four machine learning models tested (Naive Bayes (NB), Classification and Regression Trees (CART), Support Vector Machine (SVM), and Random Forest (RF)), the RF model outperformed the other three models with overall accuracies of 0.874 and Kappa coefficients of 0.777. The SVM and CART models performed similarly and NB performed the poorest. We tested two different approaches to assess the models’ accuracy. When we used all the available ground samples to train the models, whereby our analysis showed that model performance was associated with seagrass density class, and that higher seagrass density classes had better consumer accuracy, producer accuracy, and F1 scores. However, the association of model performance with seagrass density class disappeared when using the same training data size for each class. Very sparse and dense seagrass classes had replacedhigherbetter accuracies than the sparse and moderate seagrass density classes. This finding suggests that training data impacts machine learning model performance. The uneven training data size for different classes can result in biased assessment results. Selecting proper training data and machine learning models are equally important when using machine learning and remote sensing data to map seagrass density. In summary, this study demonstrates the potential to map seagrass density using satellite data.

show abstract

“…Seagrass is a critically important food source for dugong and sea turtles (Short et al, 2016) where the species are fully protected marine biota in Indonesia. That makes condition of seagrass habitats also be useful as a bio-indicator of another ecosystems (Hedley et al, 2021). In addition, the seagrass ecosystem also has an important function as a carbon sink, that sequestration in seagrass biomass will be flowed into the sediment.…”

mentioning

confidence: 99%

Association Analysis of Seagrass Coverage and Human Activities in Nusa Lembongan

et al. 2022

View full text Add to dashboard Cite

Nusa Lembongan has high marine biodiversity, including seagrass. Seagrass is a plant that lives submerged in a marine or estuary water that functions as a nursery ground, trapping sediment, and beach protector, so it is important to know the condition of seagrass coverage, especially in Nusa Lembongan for managing the Nusa Penida Marine Protected Area. This study aimed to understand the condition of seagrass coverage and the factors influencing the existence of its ecosystem in Nusa Lembongan. According to reslut in two stations, it was found that six of the twelve types of seagrasses in Indonesia, namely Enhalus acoroides, Thalassia hemprichii, Cymodocea serrulata, Cymodocea rotundata, Halodule pinifolia, and Halophila ovalis. From the two stations (LMB01 and LMB02), the total seagrass coverage was 38.10±30.98% or the medium category. The seagrass communities in the station areas were generally formed by 3 types of seagrasses; Thalassia hemprichii, Cymodocea serrulata, and Cymodocea rotundata. LMB02 has higher seagrass coverage than LMB01. The seagrass coverage is inversely proportional to the intensity of human activity.

show abstract

Seagrass Depth Distribution Mirrors Coastal Development in the Mexican Caribbean – An Automated Analysis of 800 Satellite Images

Cited by 6 publications

References 77 publications

Mapping the structure of mixed seagrass meadows in the Mexican Caribbean

Mapping the structure of mixed seagrass meadows in the Mexican Caribbean

Quantifying Seagrass Density Using Sentinel-2 Data and Machine Learning

Association Analysis of Seagrass Coverage and Human Activities in Nusa Lembongan

Contact Info

Product

Resources

About