Abstract:Despite the abundance of research on coral reef change detection, few studies have been conducted to assess the spatial generalization principles of a live coral cover classifier trained using remote sensing data from multiple locations. The aim of this study is to develop a machine learning classifier for coral dominated benthic cover-type class (CDBCTC) based on ground truth observations and Landsat images, evaluate the performance of this classifier when tested against new data, then deploy the classifier t… Show more
“…Therefore, if a pixel resembles that of sample bleached corals in the time series classification, it will be identified as a bleached coral. To achieve a higher accuracy based on the limited sample points, the support vector machine (SVM) classifier will be applied to the processed time series images because of its superior generalization properties and high performance (Gapper et al, 2019;. A radial basis function kernel method was used for each classification based on the optimal accuracy and generalization criteria.…”
Section: General Shemementioning
confidence: 99%
“…Brightness in a NIR band was utilized to deglint the visible wavelength bands based on the linear relationships between NIR and visible bands (Hedley et al, 2005). To facilitate further analysis, pixels containing boats, whitecaps (sea foam), clouds and their shadows, and land were masked (Gapper et al, 2019).…”
Section: Geo-registration Deglint and Maskingmentioning
Sentinel-2 mission has been shown to have promising applications in coral reef remote sensing because of its superior properties. It has a 5-day revisit time, spatial resolution of 10 m, free data, etc. In this study, Sentinel-2 imagery was investigated for bleaching detection through simulations and a case study over the Lizard Island, Australia. The spectral and image simulations based on the semianalytical (SA) model and the sensor spectral response function, respectively, confirmed that coral bleaching cannot be detected only using one image, and the change analysis was proposed for detection because there will be a featured change signal for bleached corals. Band 2 of Sentinel-2 is superior to its other bands for the overall consideration of signal attenuation and spatial resolution. However, the detection capability of Sentinel-2 is still limited by the water depth. With rapid signal attenuation due to the water absorption effect, the applicable water depth for bleaching detection was recommended to be less than 10 m. The change analysis was conducted using two methods: one radiometric normalization with pseudo invariant features (PIFs) and the other with multi-temporal depth invariant indices (DII). The former performed better than the latter in terms of classification. The bleached corals maps obtained using the PIFs and DII approaches had an overall accuracy of 88.9 and 57.1%, respectively. Compared with the change analysis based on two dated images, the use of a third image that recorded the spectral signals of recovered corals or corals overgrown by algae after bleaching significantly improved the detection accuracy. All the preliminary results of this article will aid in the future studies on coral bleaching detection based on remote sensing.
“…Therefore, if a pixel resembles that of sample bleached corals in the time series classification, it will be identified as a bleached coral. To achieve a higher accuracy based on the limited sample points, the support vector machine (SVM) classifier will be applied to the processed time series images because of its superior generalization properties and high performance (Gapper et al, 2019;. A radial basis function kernel method was used for each classification based on the optimal accuracy and generalization criteria.…”
Section: General Shemementioning
confidence: 99%
“…Brightness in a NIR band was utilized to deglint the visible wavelength bands based on the linear relationships between NIR and visible bands (Hedley et al, 2005). To facilitate further analysis, pixels containing boats, whitecaps (sea foam), clouds and their shadows, and land were masked (Gapper et al, 2019).…”
Section: Geo-registration Deglint and Maskingmentioning
Sentinel-2 mission has been shown to have promising applications in coral reef remote sensing because of its superior properties. It has a 5-day revisit time, spatial resolution of 10 m, free data, etc. In this study, Sentinel-2 imagery was investigated for bleaching detection through simulations and a case study over the Lizard Island, Australia. The spectral and image simulations based on the semianalytical (SA) model and the sensor spectral response function, respectively, confirmed that coral bleaching cannot be detected only using one image, and the change analysis was proposed for detection because there will be a featured change signal for bleached corals. Band 2 of Sentinel-2 is superior to its other bands for the overall consideration of signal attenuation and spatial resolution. However, the detection capability of Sentinel-2 is still limited by the water depth. With rapid signal attenuation due to the water absorption effect, the applicable water depth for bleaching detection was recommended to be less than 10 m. The change analysis was conducted using two methods: one radiometric normalization with pseudo invariant features (PIFs) and the other with multi-temporal depth invariant indices (DII). The former performed better than the latter in terms of classification. The bleached corals maps obtained using the PIFs and DII approaches had an overall accuracy of 88.9 and 57.1%, respectively. Compared with the change analysis based on two dated images, the use of a third image that recorded the spectral signals of recovered corals or corals overgrown by algae after bleaching significantly improved the detection accuracy. All the preliminary results of this article will aid in the future studies on coral bleaching detection based on remote sensing.
“…The remote sensing analysis was implemented as an "objective" processing chain that could be consistently and repeatedly applied free from potential bias due to data or operator choices. This excluded commonly used habitat classification or machine learning approaches for seagrass mapping (Knudby and Nordlund, 2011;Lyons et al, 2013;Roelfsema et al, 2014;Gapper et al, 2019) since the location and time points of training data could not be excluded as spatial or temporal bias factors (and in any case training data appropriate for the scale of the analysis was lacking). Instead, we used a radiative transfer model inversion method to simultaneously estimate LAI and depth (Hedley et al, 2016(Hedley et al, , 2017.…”
The seagrass Thalassia testudinum is the dominant habitat-builder in coastal reef lagoons of the Caribbean, and provides vital ecosystem services including coastal protection and carbon storage. We used a remote sensing methodology to map T. testudinum canopies over 400 km of coastline of the eastern Yucatán Peninsula, comparing the depth distribution of canopy density, in terms of leaf area index (LAI), to a previously established ecological model of depth and LAI for this species in oligotrophic conditions. The full archive of Sentinel-2 imagery from 2016 to 2020 was applied in an automated model inversion method to simultaneously estimate depth and LAI, covering ∼900 km2 of lagoon with approximately 800 images. Data redundancy allowed for statistical tests of change detection. Achieved accuracy was sufficient for the objectives: LAI estimates compared to field data had mean absolute error of 0.59, systematic error of 0.04 and r2 > 0.67 over a range of 0–5. Bathymetry compared to 46,000 ICESat-2 data points had a mean absolute error of 1 m, systematic error less than 0.5 m, and r2 > 0.88 over a range of 0–15 m. The estimated total area of seagrass canopy was consistent with previously published estimates of ∼580 km2, but dense canopies (LAI > 3), which are the primary contributors to below-ground carbon storage, comprise only ∼40 km2. Within the year-to-year variation there was no change in overall seagrass abundance 2017–2020, but localised statistically significant (p < 0.01) patches of canopy extension and retraction occurred. 2018 and 2019 were affected by beaching of pelagic Sargassum and dispersion as organic matter into the lagoon. The multi-year analysis enabled excluding this influence and provided an estimate of its extent along the coast. Finally, the distribution of LAI with depth was consistent with the ecological model and showed a gradient from north to south which mirrored a well-established gradient in anthropogenic pressure due to touristic development. Denser canopies were more abundant in developed areas, the expected growth response to nutrient enrichment. This increase in canopy density may be a useful early bio-indicator of environmental eutrophication, detectable by remote sensing before habitat deterioration is observed.
“…According to the difference of micro-Doppler effects [45] of rotating parts due to the difference in structure and rotating speed, features of the amplitude deviation coefficient, time domain waveform entropy and frequency domain waveform entropy are extracted to classify targets. Finally, features extracted from multi-wave gates sparse echo data are weighted and fused to train and test the support vector machine (SVM) [46][47][48] model for classification. Experimental results show that the proposed algorithm can improve the classification probability, and four wave gates echo data in weighted features fusion used to extract features is the optimal wave gate number for target classification.…”
For a conventional narrow-band radar system, the detectable information of the target is limited, and it is difficult for the radar to accurately identify the target type. In particular, the classification probability will further decrease when part of the echo data is missed. By extracting the target features in time and frequency domains from multi-wave gates sparse echo data, this paper presents a classification algorithm in conventional narrow-band radar to identify three different types of aircraft target, i.e., helicopter, propeller and jet. Firstly, the classical sparse reconstruction algorithm is utilized to reconstruct the target frequency spectrum with single-wave gate sparse echo data. Then, the micro-Doppler effect caused by rotating parts of different targets is analyzed, and the micro-Doppler based features, such as amplitude deviation coefficient, time domain waveform entropy and frequency domain waveform entropy, are extracted from reconstructed echo data to identify targets. Thirdly, the target features extracted from multi-wave gates reconstructed echo data are weighted and fused to improve the accuracy of classification. Finally, the fused feature vectors are fed into a support vector machine (SVM) model for classification. By contrast with the conventional algorithm of aircraft target classification, the proposed algorithm can effectively process sparse echo data and achieve higher classification probability via weighted features fusion of multi-wave gates echo data. The experiments on synthetic data are carried out to validate the effectiveness of the proposed algorithm.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.