ERISNet: deep neural network for <i>Sargassum</i> detection along the coastline of the Mexican Caribbean

Arellano‐Verdejo, Javier; Lazcano-Hernandez, Hugo-Enrique; Cabañillas-Terán, Nancy

doi:10.7717/peerj.6842

Cited by 49 publications

(33 citation statements)

References 41 publications

(60 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, there are often high levels of environmental complexities in marine environments which can interfere with clear footage, including variable water clarity, complex background structures, decreased light at depth, and obstruction due to schooling fish (Mandal et al, 2018;Salman et al, 2019). Although these factors may affect the quality of images and videos, deep learning methods have proven successful in a range of marine applications (Galloway et al, 2017;Arellano-Verdejo et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

Automating the Analysis of Fish Abundance Using Object Detection: Optimizing Animal Ecology With Deep Learning

et al. 2020

View full text Add to dashboard Cite

Aquatic ecologists routinely count animals to provide critical information for conservation and management. Increased accessibility to underwater recording equipment such as action cameras and unmanned underwater devices has allowed footage to be captured efficiently and safely, without the logistical difficulties manual data collection often presents. It has, however, led to immense volumes of data being collected that require manual processing and thus significant time, labor, and money. The use of deep learning to automate image processing has substantial benefits but has rarely been adopted within the field of aquatic ecology. To test its efficacy and utility, we compared the accuracy and speed of deep learning techniques against human counterparts for quantifying fish abundance in underwater images and video footage. We collected footage of fish assemblages in seagrass meadows in Queensland, Australia. We produced three models using an object detection framework to detect the target species, an ecologically important fish, luderick (Girella tricuspidata). Our models were trained on three randomized 80:20 ratios of training:validation datasets from a total of 6,080 annotations. The computer accurately determined abundance from videos with high performance using unseen footage from the same estuary as the training data (F1 = 92.4%, mAP50 = 92.5%) and from novel footage collected from a different estuary (F1 = 92.3%, mAP50 = 93.4%). The computer's performance in determining abundance was 7.1% better than human marine experts and 13.4% better than citizen scientists in single image test datasets, and 1.5 and 7.8% higher in video datasets, respectively. We show that deep learning can be a more accurate tool than humans at determining abundance and that results are consistent and transferable across survey locations. Deep learning methods provide a faster, cheaper, and more accurate alternative to manual data analysis methods currently used to monitor and assess animal abundance and have much to offer the field of aquatic ecology.

show abstract

Section: Introductionmentioning

confidence: 99%

Automating the Analysis of Fish Abundance Using Object Detection: Optimizing Animal Ecology With Deep Learning

et al. 2020

View full text Add to dashboard Cite

show abstract

“…There has been much effort expended over the last few years to understand pelagic Sargassum arrival and transport throughout the Wider Caribbean (e.g., Wang and Hu 2016, Brooks et al 2018, Putman et al 2018, 2019, Johns et al 2020. New and experimental products have been developed, which provide valuable insight into the comparative presence of pelagic Sargassum blooms across the Caribbean and GOM, and visual assessment of the probability of inundation (e.g., Webster and Linton 2013, Wang and Hu 2017, Arellano-Verdejo et al 2019. Some of these products are freely accessible (e.g., USF's Optical Ocean Laboratory, Satellite-based Sargassum Watch System (SaWS) [https://optics.…”

Section: Introductionmentioning

confidence: 99%

Pelagic Sargassum Prediction and Marine Connectivity in the Tropical Atlantic

Johnson¹,

Franks²,

Oxenford³

et al. 2020

GCR

View full text Add to dashboard Cite

Since 2011, pelagic Sargassum has experienced extraordinary blooms in the Tropical Atlantic where a system of persistent but seasonally variable currents has retained and consolidated it in large masses. Although beneficial at sea, principally as a unique pelagic habitat, when Sargassum inundates the nearshore environment it can have catastrophic effects on tourism, fisheries, health, and local ecosystems. Providing advanced warning of arrival dates of large masses of Sargassum is critical for enabling preparations and planning for its removal, use, and mitigation. Predictions of arrival time and location involve satellite identification of Sargassum at sea together with ocean current data for forward model tracking. However, forecast ocean current data are generally valid for only 5—7 days. In this study, ocean currents from 2 models (HYCOM and OSCAR) are validated against satellite tracked drifters from the Global Drifter Program with vector correlation and with skill in replicating a drifter pathway. Various wind additions to the models are also tested. Although both models capture the surface current systems in the Tropical Atlantic, they are mediocre in performance along both boundaries. In contrast, a drifter based current data model with 0.5% wind addition had high skill levels. This skill—tested drifter—based model was then used to determine marine connectivity across the Tropical Atlantic and suggests a much broader spread of Sargassum in the eastern Tropical Atlantic than is presently observed by satellites, conforming to earlier hypotheses. This model forms the basis for seasonal scale Sargassum forecasting.

show abstract

“…This approach achieves state-of-the-art results in different applications in remote sensing digital image processing [5]: pan-sharpening [6][7][8][9]; image registration [10][11][12][13], change detection [14][15][16][17], object detection [18][19][20][21], semantic segmentation [22][23][24][25], and time series analysis [26][27][28][29]. The classification algorithms applied in remote sensing imagery uses spatial, spectral, and temporal information to extract characteristics from the targets, where a wide variety of targets show significant results: clouds [30][31][32][33], dust-related air pollutant [34][35][36][37] land-cover/land-use [38][39][40][41], urban features [42][43][44][45], and ocean [46][47][48][49], among others.…”

Section: Introductionmentioning

confidence: 99%

Instance Segmentation for Large, Multi-Channel Remote Sensing Imagery Using Mask-RCNN and a Mosaicking Approach

et al. 2020

View full text Add to dashboard Cite

Instance segmentation is the state-of-the-art in object detection, and there are numerous applications in remote sensing data where these algorithms can produce significant results. Nevertheless, one of the main problems is that most algorithms use Red, Green, and Blue (RGB) images, whereas Satellite images often present more channels that can be crucial to improve performance. Therefore, the present work brings three contributions: (a) conversion system from ground truth polygon data into the Creating Common Object in Context (COCO) annotation format; (b) Detectron2 software source code adaptation and application on multi-channel imagery; and (c) large scene image mosaicking. We applied the procedure in a Center Pivot Irrigation System (CPIS) dataset with ground truth produced by the Brazilian National Water Agency (ANA) and Landsat-8 Operational Land Imager (OLI) imagery (7 channels with 30-m resolution). Center pivots are a modern irrigation system technique with massive growth potential in Brazil and other world areas. The round shapes with different textures, colors, and spectral behaviors make it appropriate to use Deep Learning instance segmentation. We trained the model using 512 × 512-pixel sized patches using seven different backbone structures (ResNet50- Feature Pyramid Network (FPN), Resnet50-DC5, ResNet50-C4, Resnet101-FPN, Resnet101-DC5, ResNet101-FPN, and ResNeXt101-FPN). The model evaluation used standard COCO metrics (Average Precision (AP), AP50, AP75, APsmall, APmedium, and AR100). ResNeXt101-FPN had the best results, with a 3% advantage over the second-best model (ResNet101-FPN). We also compared the ResNeXt101-FPN model in the seven-channel and RGB imagery, where the multi-channel model had a 3% advantage, demonstrating great improvement using a larger number of channels. This research is also the first with a mosaicking algorithm using instance segmentation models, where we tested in a 1536 × 1536-pixel image using a non-max suppression sorted by area method. The proposed methodology is innovative and suitable for many other remote sensing problems and medical imagery that often present more channels.

show abstract

ERISNet: deep neural network for Sargassum detection along the coastline of the Mexican Caribbean

Cited by 49 publications

References 41 publications

Automating the Analysis of Fish Abundance Using Object Detection: Optimizing Animal Ecology With Deep Learning

Automating the Analysis of Fish Abundance Using Object Detection: Optimizing Animal Ecology With Deep Learning

Pelagic Sargassum Prediction and Marine Connectivity in the Tropical Atlantic

Instance Segmentation for Large, Multi-Channel Remote Sensing Imagery Using Mask-RCNN and a Mosaicking Approach

Contact Info

Product

Resources

About