A Biologist’s Guide to the Galaxy: Leveraging Artificial Intelligence and Very High-Resolution Satellite Imagery to Monitor Marine Mammals from Space

Khan, Christin Brangwynne; Goetz, Kimberly T.; Cubaynes, Hannah C.; Robinson, Caleb; Murnane, Erin; Aldrich, Tyler; Sackett, Meredith; Clarke, Penny J.; LaRue, Michelle A.; White, Timothy P.; Leonard, Kathleen; Ortiz, Anthony; Ferres, Juan M. Lavista

doi:10.3390/jmse11030595

Cited by 10 publications

(4 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Satellite imagery offers a safe, effective method for estimating cetacean estuary abundance; however, ground-truthing with traditional aerial surveys would improve confidence in the estimate (Bamford et al, 2020). Crowd-counters offer one possible solution to handling the immense imagery reading task, but the future of abundance estimation with satellite imagery likely relies on automated detection algorithms that can be used to eliminate large areas with no features of interest and identify whales (Borowicz, 2019;Rodofili et al, 2022;Khan et al, 2023), while also eliminating the subjectivity of readers. Object or pixel based machine learning algorithms could greatly reduce the time required for analysis after imagery acquisition.…”

Section: Discussionmentioning

confidence: 99%

Eastern High Arctic–Baffin Bay beluga whale (Delphinapterus leucas) estuary abundance and use from space

et al. 2023

View full text Add to dashboard Cite

IntroductionThe Eastern High Arctic–Baffin Bay (EHA-BB) beluga whale (Delphinapterus leucas) population spends summer in estuaries around Somerset Island, Nunavut, Canada. A single abundance estimate from 1996 suggests an abundance >21,000 beluga whales; however, more information on abundance and distribution is needed to ensure effective management of this population, especially in estuaries where previous surveys provided minimal coverage. To assess the feasibility of using Very High Resolution (VHR) satellite imagery to obtain estuary abundance estimates for this beluga population, we evaluated a citizen science crowd counting initiative that was designed to monitor remote beluga whale populations and their estuary use.MethodsIn July and August 2020 the WorldView 2 and 3, and GeoEye 1 satellites were tasked to collect VHR imagery (30–41 cm) of estuaries previously known to be used by Eastern High Arctic–Baffin Bay beluga whales. The objectives were to obtain an estuary abundance estimate for this population from satellite imagery, and to evaluate the effectiveness of having imagery annotated using a crowd-source platform. Almost 3,800 km2 of ocean imagery was analyzed using Maxar’s Geospatial Human Imagery Verification Effort (GeoHIVE) Crowdsourcing platform. Expert readers then manually compared counts to those performed by crowd-counters to determine variance in observer counts.Results and DiscussionThe estuary abundance estimate from 11 core estuaries was 12,128 (CV 36.76%, 95% confidence interval 6,036–24,368) beluga whales. This represents an estuary abundance estimate only, as the greater Peel Sound and Prince Regent Inlet areas were not photographed. The estuaries with the largest abundance of beluga whales were Creswell Bay, Maxwell Bay, and Prince Whales Island, with over 2,000 crowd-counted whales in each estuary. Although VHR imagery has potential to assist with surveying and monitoring marine mammals, for larger estuaries it was not always possible to photograph the entire area in a single day, and cloud cover was an issue for sections of most images. This work will assist with planning large-scale aerial surveys for monitoring beluga whale populations, identifying high-use areas and important beluga habitat, and highlights the utility of using VHR imagery to enhance our understanding of estuary abundance and distribution of Arctic whales.

show abstract

Section: Discussionmentioning

confidence: 99%

Eastern High Arctic–Baffin Bay beluga whale (Delphinapterus leucas) estuary abundance and use from space

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Persistent target tracking, facilitated by the Automatic Radar Plotting Aid (ARPA), provides a continuous record of a unique vessel's trajectory, which is difficult to reconstruct from infrequent satellite images [56]. Some satellites can be tasked to a given area (albeit with limitations [57]) or revisit within minutes, but most have a longer revisit time [58,59]. Radar and AIS positions are both typically reported of the order of seconds, so association between the two is a common practice and helpful for providing identification information on radar-detected targets [60,61].…”

Section: Related Workmentioning

confidence: 99%

Building a Practical Multi-Sensor Platform for Monitoring Vessel Activity near Marine Protected Areas: Case Studies from Urban and Remote Locations

Cope¹,

Tougher²,

Zetterlind³

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Monitoring vessel activity is an important part of managing marine protected areas (MPAs), but small-scale fishing and recreational vessels that do not participate in cooperative vessel traffic systems require additional monitoring strategies. Marine Monitor (M2) is a shore-based, multi-sensor platform that integrates commercially available hardware, primarily X-band marine radar and optical cameras, with custom software to autonomously track and report on vessel activity regardless of participation in other tracking systems. By utilizing established commercial hardware, the radar system is appropriate for supporting the management of coastal, small-scale MPAs. Data collected in the field are transferred to the cloud to provide a continuous record of activity and identify prohibited activities in real-time using behavior characteristics. To support the needs of MPA managers, both hardware and software improvements have been made over time, including ruggedizing equipment for the marine environment and powering systems in remote locations. Case studies are presented comparing data collection by both radar and the Automatic Identification System (AIS) in urban and remote locations. At the South La Jolla State Marine Reserve near San Diego, CA, USA, 93% of vessel activity (defined as the cumulative time vessels spent in the MPA) was identified exclusively by radar from November 2022 through January 2023. At the Caye Bokel Conservation Area, within the Turneffe Atoll Marine Reserve offshore of Belize, 98% was identified exclusively by radar from April through October 2022. Spatial and temporal patterns of radar-detected and AIS activity also differed at both sites. These case study site results together demonstrate the common and persistent presence of small-scale vessel activity near coastal MPAs that is not documented by cooperative systems. Therefore, an integrated radar system can be a useful tool for independent monitoring, supporting a comprehensive understanding of vessel activity in a variety of areas.

show abstract

“…Object detection with deep learning has been successful in identifying whales in VHR satellite imagery (Houegnigan et al., 2022; Kapoor et al., 2023; Khan et al., 2023). Training of CNNs has been previously performed using aerial imagery or a mixture of VHR satellite and aerial imagery (Borowicz et al., 2019; Guirado et al., 2019), due to the lack of labelled VHR satellite imagery, which takes time to acquire and must be manually requested and annotated by users (Cubaynes & Fretwell, 2022; Höschle et al., 2021).…”

Section: Introductionmentioning

confidence: 99%

Gray whale detection in satellite imagery using deep learning

Green

Virdee

Cubaynes

et al. 2023

Remote Sens Ecol Conserv

Self Cite

View full text Add to dashboard Cite

The combination of very high resolution (VHR) satellite remote sensing imagery and deep learning via convolutional neural networks provides opportunities to improve global whale population surveys through increasing efficiency and spatial coverage. Many whale species are recovering from commercial whaling and face multiple anthropogenic threats. Regular, accurate population surveys are therefore of high importance for conservation efforts. In this study, a state‐of‐the‐art object detection model (YOLOv5) was trained to detect gray whales (Eschrichtius robustus) in VHR satellite images, using training data derived from satellite images spanning different sea states in a key breeding habitat, as well as aerial imagery collected by unoccupied aircraft systems. Varying combinations of aerial and satellite imagery were incorporated into the training set. Mean average precision, whale precision, and recall ranged from 0.823 to 0.922, 0.800 to 0.939, and 0.843 to 0.889, respectively, across eight experiments. The results imply that including aerial imagery in the training data did not substantially impact model performance, and therefore, expansion of representative satellite datasets should be prioritized. The accuracy of the results on real‐world data, along with short training times, indicates the potential of using this method to automate whale detection for population surveys.

show abstract

A Biologist’s Guide to the Galaxy: Leveraging Artificial Intelligence and Very High-Resolution Satellite Imagery to Monitor Marine Mammals from Space

Cited by 10 publications

References 63 publications

Eastern High Arctic–Baffin Bay beluga whale (Delphinapterus leucas) estuary abundance and use from space

Eastern High Arctic–Baffin Bay beluga whale (Delphinapterus leucas) estuary abundance and use from space

Building a Practical Multi-Sensor Platform for Monitoring Vessel Activity near Marine Protected Areas: Case Studies from Urban and Remote Locations

Gray whale detection in satellite imagery using deep learning

Contact Info

Product

Resources

About