Quantifying the Intra-Habitat Variation of Seagrass Beds with Unoccupied Aerial Vehicles (UAVs)

Price, David M.; Felgate, Stacey L.; Huvenne, Veerle; Strong, James Asa; Carpenter, Stephen; Barry, C.; Lichtschlag, Anna; Sanders, Richard J.; Carrias, Abel; Young, Arlene; Andrade, Valdemar; Cobb, Eliceo; Bas, Tim Le; Brittain, Hannah; Evans, Claire

doi:10.3390/rs14030480

Cited by 11 publications

(7 citation statements)

References 73 publications

(78 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RFs have been widely applied for a number of classification tasks in remote sensing (Pal 2005;Rodriguez-Galiano et al, 2012;Belgiu and Drăgu 2016) and specifically, in marine and coastal studies (Seiler et al, 2012;Gauci et al, 2016;Robert et al, 2016;Misiuk et al, 2019;Zelada Leon et al, 2020;Price et al, 2022). In our study, the RF was among the top four classifiers.…”

Section: Classifier Performancementioning

confidence: 59%

“…Predictions are generated as an ensemble estimate from a number of decision trees from bootstrap samples (termed bagging) (Hengl et al, 2018). RF classifications have been successfully applied in a number of marine (Robert et al, 2016;Misiuk et al, 2019;Shang et al, 2021;Price et al, 2022) and terrestrial studies (Schratz et al, 2019). Comparison performance studies in land cover suggest that RF has provided the best performance in object-based classification tasks (Ma et al, 2017).…”

Section: Random Forestmentioning

confidence: 99%

See 1 more Smart Citation

High-resolution 3D mapping of cold-water coral reefs using machine learning

Oliveira

Lim

Conti

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

Structure-from-Motion (SfM) photogrammetry is a time and cost-effective method for high-resolution 3D mapping of cold-water corals (CWC) reefs and deep-water environments. The accurate classification and analysis of marine habitats in 3D provide valuable information for the development of management strategies for large areas at various spatial and temporal scales. Given the amount of data derived from SfM data sources such as Remotely-Operated Vehicles (ROV), there is an increasing need to advance towards automatic and semiautomatic classification approaches. However, the lack of training data, benchmark datasets for CWC environments and processing resources are a bottleneck for the development of classification frameworks. In this study, machine learning (ML) methods and SfM-derived 3D data were combined to develop a novel multiclass classification workflow for CWC reefs in deep-water environments. The Piddington Mound area, southwest of Ireland, was selected for 3D reconstruction from high-definition video data acquired with an ROV. Six ML algorithms, namely: Support Vector Machines, Random Forests, Gradient Boosting Trees, k-Nearest Neighbours, Logistic Regression and Multilayer Perceptron, were trained in two datasets of different sizes (1,000 samples and 10,000 samples) in order to evaluate accuracy variation between approaches in relation to the number of samples. The Piddington Mound was classified into four classes: live coral framework, dead coral framework, coral rubble and sediment and dropstones. Parameter optimisation was performed with grid search and cross-validation. Run times were measured to evaluate the trade-off between processing time and accuracy. In total, eighteen variations of ML algorithms were created and tested. The results show that four algorithms yielded f1-scores >90% and were able to discern between the four classes, especially those with usually similar characteristics, e.g., coral rubble and dead coral. The accuracy variation among them was 3.6% which suggests that they can be used interchangeably depending on the classification task. Furthermore, results on sample size variations show that certain algorithms benefit more from larger datasets whilst others showed discrete accuracy variations (<5%) when trained in datasets of different sizes.

show abstract

Section: Classifier Performancementioning

confidence: 59%

Section: Random Forestmentioning

confidence: 99%

High-resolution 3D mapping of cold-water coral reefs using machine learning

Oliveira

Lim

Conti

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…The first results of our work were typically maps of the presence or absence of seagrass and its spatial extent. Quantitative information on density and biomass cannot be achieved using the classification results alone (Price et al 2022). The empirical relationship between field data and vegetation indices revealed by high hyperspectral or multispectral satellite imagery can provide biomass and density maps (Barillé et al 2010;Bargain et al 2013;Roelfsema et al 2014;Benmokhtar et al 2021), and the biomass of the Z. noltei beds in Merja Zerga lagoon was estimated using the quantitative experimental NDVI -Z. noltei biomass relationship created by Barillé et al (2010), whereby biomass = 610.61 (NDVI)^1.88 (n = 31, r2 = 0.97).…”

Section: Discussionmentioning

confidence: 99%

Monitoring the Spatial and Interannual Dynamic of Zostera noltei

et al. 2023

View full text Add to dashboard Cite

Seagrass is a vital structural and functional element of the marine environment worldwide and is highly valued for its ecological benefits. Monitoring the evolution of the seagrass habitat is essential to understand how this coastal ecosystem changes, and to develop good environmental management practices. For the present study, two remote sensing methods were used to map and monitor Zostera noltei Hornemann, 1832 ( Z. noltei ), in the Merja Zerga lagoon from 2010 to 2020. These methods which are the random forest algorithm and the object-oriented classification, were convenient to provide significant results. The first approach employed Sentinel-2 images from 2018 to 2020, which were used to extract information on changes in Z. noltei (commonly called dwarf eelgrass) distribution and aboveground biomass estimation. The second involved three orthophotography (orthophoto) mosaics from the years 2010, 2016, and 2018, which were analyzed to map the distribution of the species. It was revealed that Z. noltei coverage has increased by 212 ha since 2010, with most of the growth occurring in the center and upstream part of the lagoon. The mean aboveground biomass of dwarf eelgrass in the lagoon was 78.5 DW/m² in 2018, 92.6 DW/m² in 2019, and 115.2 g DW/m² in 2020. The approach used in this study has provided important insights into the dynamic and mean biomass of Z. noltei in the Merja Zerga lagoon. It is therefore a valuable, non-destructive method that uses freely-available Sentinel-2 satellite data.

show abstract

“…UAV surveys were conducted using a Phantom 4 drone with an onboard GPS for georeferencing and a 20-megapixel camera attached to a 3-axis gimbal on its base. Collection, pre-processing and classification of the UAV data are reported in Price et al [34]). In brief, at each location, low-altitude UAV surveys were taken between 14:30 and 17:30 (local time) to ensure maximum illumination while minimising sun glint.…”

Section: Uav Data Collection Processing and Classificationmentioning

confidence: 99%

Using Unoccupied Aerial Vehicles (UAVs) to Map Seagrass Cover from Sentinel-2 Imagery

et al. 2022

Self Cite

View full text Add to dashboard Cite

Seagrass habitats are ecologically valuable and play an important role in sequestering and storing carbon. There is, thus, a need to estimate seagrass percentage cover in diverse environments in support of climate change mitigation, marine spatial planning and coastal zone management. In situ approaches are accurate but time-consuming, expensive and may not represent the larger spatial units collected by satellite imaging. Hence, there is a need for a consistent methodology that uses accurate point-based field surveys to deliver high-quality mapping of percentage seagrass cover at large spatial scales. Here, we develop a three-step approach that combines in situ (quadrats), aerial (unoccupied aerial vehicle—UAV) and satellite data to map percentage seagrass cover at Turneffe Atoll, Belize, the largest atoll in the northern hemisphere. First, the optical bands of four UAV images were used to calculate seagrass cover, in combination with in situ data. The seagrass cover calculated from the UAV was then used to develop training and validation datasets to estimate seagrass cover in Sentinel-2 pixels. Next, non-seagrass areas were identified in the Sentinel-2 data and removed by object-based classification, followed by a pixel-based regression to calculate seagrass percentage cover. Using this approach, percentage seagrass cover was mapped using UAVs (R2 = 0.91 between observed and mapped distributions) and using Sentinel-2 data (R2 = 0.73). This work provides the first openly available and explorable map of seagrass percentage cover across Turneffe Atoll, where we estimate approximately 242 km2 of seagrass above 10% cover is located. We estimate that this approach offers 30 times more data for training satellite data than traditional methods, therefore presenting a substantial reduction in cost-per-point for data. Furthermore, the increase in data helps deliver a high-quality seagrass cover map, suitable for resolving trends of deteriorating, stable or recovering seagrass environments at 10 m2 resolution to underpin evidence-based management and conservation of seagrass.

show abstract

Quantifying the Intra-Habitat Variation of Seagrass Beds with Unoccupied Aerial Vehicles (UAVs)

Cited by 11 publications

References 73 publications

High-resolution 3D mapping of cold-water coral reefs using machine learning

High-resolution 3D mapping of cold-water coral reefs using machine learning

Monitoring the Spatial and Interannual Dynamic of Zostera noltei

Using Unoccupied Aerial Vehicles (UAVs) to Map Seagrass Cover from Sentinel-2 Imagery

Contact Info

Product

Resources

About