A global coral reef probability map generated using convolutional neural networks

Li, Jiwei; Knapp, David; Fabina, Nicholas S.; Kennedy, Emma; Larsen, Kirk; Lyons, Mitchell; Murray, Nicholas J.; Phinn, Stuart; Roelfsema, Chris; Asner, Gregory P.

doi:10.1007/s00338-020-02005-6

Cited by 59 publications

(48 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Otsu's method (Otsu, 1979) was applied on SPM-transformed S2 L2A blue (SPM B2), green (SPM B3), red (SPM B4), red edge bands (SPM B5) (Nechad et al, 2010), normalized red-blue band difference [ND(B4/B2)] (Li et al, 2020), and normalized red-green band difference [ND(B4/B3)]. This method works for single-band images with bimodal pixel distribution by defining a minimum threshold value that separates two classes.…”

Section: Otsu's Methods For Bimodal Thresholdingmentioning

confidence: 99%

Cloud-Native Coastal Turbid Zone Detection Using Multi-Temporal Sentinel-2 Data on Google Earth Engine

2021

View full text Add to dashboard Cite

The lack of clarity in turbid coastal waters interferes with light attenuation and hinders remotely sensed studies in aquatic ecology such as benthic habitat mapping and bathymetry estimation. Although turbid water column corrections can be applied on regions with seasonal turbidity by performing multi-temporal analysis, different approaches are needed in regions where the water is constantly turbid or only exhibits subtle turbidity variations through time. This study aims to detect these turbid zones (TZs) in optically shallow coastal waters using multi-temporal Sentinel-2 surface reflectance datasets to improve the aforementioned studies. The herein framework can be paired with other aquatic ecology remote sensing studies to establish the clear water focus area and can also be used by decision makers to identify rehabilitation areas. We selected the coastlines of Guinea-Bissau, Tunisia, and west Madagascar as our case studies which feature wide-ranging turbidity intensities across tropical, subtropical, and Mediterranean waters and applied three different methods for the TZ detection: Otsu’s method for bimodal thresholding, linear spectral unmixing, and Random Forest (RF) machine learning method on Google Earth Engine as an end-to-end process. Based on our experiments, the RF method yields good results in all study regions with overall accuracies ranging between 88 and 96% and F1-scores between 0.87 and 0.96. TZ detection is highly site-specific due to the inter-class variability that is mainly affected by the nature of the suspended materials and the environmental characteristics of the site.

show abstract

Section: Otsu's Methods For Bimodal Thresholdingmentioning

confidence: 99%

Cloud-Native Coastal Turbid Zone Detection Using Multi-Temporal Sentinel-2 Data on Google Earth Engine

2021

View full text Add to dashboard Cite

show abstract

“…By compositing several classifications of the same year, we can gain a more nuanced picture of seagrass extent by attaching probability estimates to each pixel. Previous studies found temporal composite approaches useful for mapping of terrestrial vegetation [44,45], as well as coral reefs and other marine benthic habitats [43]. A drawback of the approach presented herein is that both classification error and seasonal growth dynamics reduce seagrass detection probability.…”

Section: Temporal Composite Of Satellite Imagery For Eelgrass Probability Mappingmentioning

confidence: 96%

“…This and the typically turbid waters at San Quintín require imagery taken at low tidal stage, however, no such imagery was available for summer, because of regular cloud cover. Large-scale benthic habitat mapping efforts that rely on Planet imagery have used a cloud-free satellite scene composite [43], but our attempt of seasonal mapping required imagery to be acquired in close temporal proximity to field sampling, narrowing the choice of satellite scenes. Tidal stage, cloud cover, and imagery acquisition timing are well described constrains for benthic habitat mapping [12] and these are not fully alleviated by daily satellite revisits.…”

Section: Planetscope-daily Revisits But Mixed Image Qualitymentioning

confidence: 99%

Emerging Sensor Platforms Allow for Seagrass Extent Mapping in a Turbid Estuary and from the Meadow to Ecosystem Scale

et al. 2021

View full text Add to dashboard Cite

Seagrass meadows are globally important habitats, protecting shorelines, providing nursery areas for fish, and sequestering carbon. However, both anthropogenic and natural environmental stressors have led to a worldwide reduction seagrass habitats. For purposes of management and restoration, it is essential to produce accurate maps of seagrass meadows over a variety of spatial scales, resolutions, and at temporal frequencies ranging from months to years. Satellite remote sensing has been successfully employed to produce maps of seagrass in the past, but turbid waters and difficulty in obtaining low-tide scenes pose persistent challenges. This study builds on an increased availability of affordable high temporal frequency imaging platforms, using seasonal unmanned aerial vehicle (UAV) surveys of seagrass extent at the meadow scale, to inform machine learning classifications of satellite imagery of a 40 km2 bay. We find that object-based image analysis is suitable to detect seasonal trends in seagrass extent from UAV imagery and find that trends vary between individual meadows at our study site Bahía de San Quintín, Baja California, México, during our study period in 2019. We further suggest that compositing multiple satellite imagery classifications into a seagrass probability map allows for an estimation of seagrass extent in turbid waters and report that in 2019, seagrass covered 2324 ha of Bahía de San Quintín, indicating a recovery from losses reported for previous decades.

show abstract

“…Heat stress, disease outbreaks, sedimentation, and increased storms have resulted in dramatic loss of warm-water coral reefs in increasingly widespread locations (Häussermann & Försterra 2014 , Hughes et al 2018 , GBRMPA 2019 , Li et al 2020 ). Poleward expansion of light-dependent coral species has been limited (with few exceptions; e.g.…”

Section: Alternative Future Narrative 1: Business-as-usual 2030mentioning

confidence: 99%

Warming world, changing ocean: mitigation and adaptation to support resilient marine systems

Trebilco

Fleming

Hobday

et al. 2021

Rev Fish Biol Fisheries

View full text Add to dashboard Cite

Proactive and coordinated action to mitigate and adapt to climate change will be essential for achieving the healthy, resilient, safe, sustainably harvested and biodiverse ocean that the UN Decade of Ocean Science and sustainable development goals (SDGs) seek. Ocean-based mitigation actions could contribute 12% of the emissions reductions required by 2030 to keep warming to less than 1.5 ºC but, because substantial warming is already locked in, extensive adaptation action is also needed. Here, as part of the Future Seas project, we use a “foresighting/hindcasting” technique to describe two scenarios for 2030 in the context of climate change mitigation and adaptation for ocean systems. The “business-as-usual” future is expected if current trends continue, while an alternative future could be realised if society were to effectively use available data and knowledge to push as far as possible towards achieving the UN SDGs. We identify three drivers that differentiate between these alternative futures: (i) appetite for climate action, (ii) handling extreme events, and (iii) climate interventions. Actions that could navigate towards the optimistic, sustainable and technically achievable future include: proactive creation and enhancement of economic incentives for mitigation and adaptation; supporting the proliferation of local initiatives to spur a global transformation; enhancing proactive coastal adaptation management; investing in research to support adaptation to emerging risks; deploying marine-based renewable energy; deploying marine-based negative emissions technologies; developing and assessing solar radiation management approaches; and deploying appropriate solar radiation management approaches to help safeguard critical ecosystems. Supplementary Information The online version contains supplementary material available at 10.1007/s11160-021-09678-4.

show abstract

A global coral reef probability map generated using convolutional neural networks

Cited by 59 publications

References 41 publications

Cloud-Native Coastal Turbid Zone Detection Using Multi-Temporal Sentinel-2 Data on Google Earth Engine

Cloud-Native Coastal Turbid Zone Detection Using Multi-Temporal Sentinel-2 Data on Google Earth Engine

Emerging Sensor Platforms Allow for Seagrass Extent Mapping in a Turbid Estuary and from the Meadow to Ecosystem Scale

Warming world, changing ocean: mitigation and adaptation to support resilient marine systems

Contact Info

Product

Resources

About