Cetacean Strandings From Space: Challenges and Opportunities of Very High Resolution Satellites for the Remote Monitoring of Cetacean Mass Strandings

Abstract

The study of cetacean strandings was globally recognised as a priority topic at the 2019 World Marine Mammal Conference, in recognition of its importance for understanding the threats to cetacean communities and, more broadly, the threats to ecosystem and human health. Rising multifaceted anthropogenic and environmental threats across the globe, as well as whale population recovery from exploitation in some areas, are likely to coincide with an increase in reported strandings. However, the current methods to monitor strandings are inherently biased towards populated coastlines, highlighting the need for additional surveying tools in remote regions. Very High Resolution (VHR) satellite imagery offers the prospect of upscaling monitoring of mass strandings in minimally populated/unpopulated and inaccessible areas, over broad spatial and temporal scales, supporting and informing intervention on the ground, and can be used to retrospectively analyse historical stranding events. Here we (1) compile global strandings information to identify the current data gaps; (2) discuss the opportunities and challenges of using VHR satellite imagery to monitor strandings using the case study of the largest known baleen whale mass stranding event (3) consider where satellites hold the greatest potential for monitoring strandings remotely and; (4) outline a roadmap for satellite monitoring. To utilise this platform to monitor mass strandings over global scales, considerable technical, practical and environmental challenges need to be addressed and there needs to be inclusivity in opportunity from the onset, through knowledge sharing and equality of access to imagery.

Remote sensing techniques for automated marine mammals detection: a review of methods and current challenges

“…Automated studies on toothed whales and mustelids are also due. Here we focused on automated detection of living marine mammal individuals in VHR satellite and UAS imagery, but it is noteworthy that other promising satellite and UAS image analysis applications (automated and manual) exist and focus for example on detecting marine mammal groups ( e.g ., Burn & Cody, 2005 ; Fischbach & Douglas, 2021 ), traces and holes ( e.g ., Platonov, Mordvintsev & Rozhnov, 2013 ), carcasses ( e.g ., Fretwell et al, 2019 ; Clarke et al, 2021 ), and on comparing detection success from imagery of different spatial resolutions ( e.g ., Fischbach & Douglas, 2021 ; Corrêa et al, 2022 ).…”

“…The literature cited in these studies was then explored further if relevant to image analysis for marine mammal detection, either through Primo or Google Scholar. We excluded studies of detection of marine mammal groups ( e.g ., Burn & Cody, 2005 ; Fischbach & Douglas, 2021 ), traces and holes ( e.g ., Platonov, Mordvintsev & Rozhnov, 2013 ), carcasses ( e.g ., Fretwell et al, 2019 ; Clarke et al, 2021 ), and works that compared automated detection in separate datasets of different spatial resolutions ( e.g ., Fischbach & Douglas, 2021 ; Corrêa et al, 2022 ).…”

Annotating very high-resolution satellite imagery: A whale case study

“…The workflow for ESRI ArcMap 10.8 was developed and used by several studies [3 , 17 , 19 , 31] with updates for ArcMap 10.8. None of these studies offered a step-by-step guide.…”

“…Research using VHR satellite images to monitor cetaceans has increased since Abileah (2002) [13] and Fretwell et al. (2014) [14] pioneering studies, highlighting how VHR satellite imagery may help gather missing information about whales, and complement boat and aircraft surveys [3 , [15] , [16] , [17] , [18] , [19] , [20] , [21] , [22] , [23] . There have been developments in using this technology in remote regions to estimate whale density [17] , detect strandings [21 , 24 , 25] , and count cetaceans [18] .…”

“…Our aim is to share a detailed step-by-step workflow for annotating VHR satellite images and for creating datasets of annotations as points, bounding boxes, and image chips in a png format, which will facilitate collaboration across research groups towards the development of an operational system for marine animal detection in VHR satellite imagery. Here we provide a general outline of the steps required to annotate satellite images, and create datasets, alongside detailed protocols for ESRI ArcMap 10.8 (Supplemental 1) [32] and ESRI ArcGIS Pro 2.5 (Supplemental 2) [33] , as used by several studies detecting wildlife in VHR satellite imagery [3 , 17 , 19 , 26 , 31] but with more details to allow reproducibility and transferability. We use cetaceans as a case study to explain the steps, which are transferable to other objects that can be individually labelled in VHR optical satellite imagery.…”