scholarly journals Deep Neural Network Analysis for Environmental Study of Coral Reefs in the Gulf of Eilat (Aqaba)

2021 ◽  
Vol 5 (2) ◽  
pp. 19
Author(s):  
Alina Raphael ◽  
Zvy Dubinsky ◽  
Nathan S. Netanyahu ◽  
David Iluz
Keyword(s):  
Deep Learning ◽  
Coral Reefs ◽  
Coral Species ◽  
Coral Cover ◽  
Environmental Study ◽  
Deep Convolutional Neural Networks ◽  
Main Research ◽  
Census Methods ◽  
Natural Sampling ◽  
Changes Over Time

Coral reefs are undergoing a severe decline due to ocean acidification, seawater warming and anthropogenic eutrophication. We demonstrate the applicability of Deep Learning (DL) for following these changes. We examined the distribution and frequency appearance of the eleven most common coral species at four sites in the Gulf of Eilat. We compared deep learning with conventional census methods. The methods used in this research were natural sampling units via photographing the coral reef, line transects for estimating the cover percentage at the four test sites and deep convolutional neural networks, which proved to be an efficient sparse classification for coral species using the supervised deep learning method. The main research goal was to identify the common coral species at four test sites in the Gulf of Eilat, using DL to detect differences in coral cover and species composition among the sites, and relate these to ecological characteristics, such as depth and anthropogenic disturbance. The use of this method will produce a vital database to follow changes over time in coral reefs, identify trend lines and recommend remediation measures accordingly. We outline future monitoring needs and the corresponding system developments required to meet these.

scholarly journals River Streamflow, Remotely Sensed Water Quality, and Benthic Composition of Previously Undescribed Nearshore Coral Reefs in Northern Puerto Rico

2021 ◽  
Vol 8 ◽  
Author(s):  
Juan L. Torres-Pérez ◽  
Carlos E. Ramos-Scharrón ◽  
William J. Hernández ◽  
Roy A. Armstrong ◽  
Maritza Barreto-Orta ◽  
...  
Keyword(s):  
Water Quality ◽  
Puerto Rico ◽  
Coral Reefs ◽  
Coral Species ◽  
Coral Cover ◽  
Remotely Sensed ◽  
North Coast ◽  
Acropora Palmata ◽  
Chl A ◽  
Benthic Composition

Land-based sediment stress represents a threat to many coral reefs in Puerto Rico primarily as a result of unrestricted land cover/land use changes and poor best management practices. The effects of such stresses have been documented along most coasts around the island. However, little attention has been paid to reefs located on the north coast, and very little is known about their composition and current state. Here, we present a study characterizing riverine inputs, water quality conditions, and benthic composition of two previously undescribed coral reefs (Tómbolo and Machuca reefs) located just eastward of the Río Grande de Manatí outlet in north-central Puerto Rico. This study utilizes a time series of remotely sensed ocean color products [diffuse vertical attenuation coefficient at 490 nm (Kd490) and chlorophyll-a concentration (Chl-a) estimated with data from the Visible Infrared Imaging Radiometer Suite (VIIRS)] to characterize water quality in this coastal region. In general, the months with relatively high mean daily river streamflow also coincide with months having the highest proportion of eastward wave direction, which can promote the eastward influence of river waters toward the two coral reefs sites. Kd490 and Chl-a showed a higher riverine influence closer to the watershed outlet. Kd490 and Chl-a monthly peaks also coincide with river streamflow highs, particularly at those pixels closer to shore. Tómbolo Reef, located farther eastward of the river outlet, shows a well-developed primary reef framework mainly composed of threatened reef-building species (Acropora palmata, Pseudodiploria) and high coral cover (19–51%). The benthos of Machuca Reef, located closer to the river outlet, is dominated by macroalgae with a significantly lower coral cover (0.2–2.7%) mainly composed of “weedy” coral species (Porites astreoides and Siderastrea radians). Cover of major benthic components correlates with distance from the river outlet, and with gradients in Kd490 and Chl-a, with higher coral cover and lower macroalgal cover farther from the river outlet. Coral cover at Tómbolo Reef is higher than what has been reported for similar sites around Puerto Rico and other Caribbean islands showing its ecological importance, and as up until now, an unrecognized potential refuge of reef-building threatened coral species.

scholarly journals Coral Reef Degradation Due to ‘Ship Grounding’ in Indonesia: Case Study of Ship Aground in Bangka-Belitung Waters by Mother Vessel MV Lyric Poet

2020 ◽  
Vol 12 (2) ◽  
pp. 263
Author(s):  
Idris Idris ◽  
Neviaty P. Zamani ◽  
Suharsono Suharsono ◽  
Fakhrurrozi Fakhrurrozi
Keyword(s):  
Coral Reef ◽  
Coral Reefs ◽  
Coral Species ◽  
Coral Cover ◽  
Conservation Status ◽  
Three Dimensional ◽  
Live Coral ◽  
Hard Coral ◽  
Lyric Poet ◽  
Ship Grounding

HighlightDamage to coral reefs by ship aground is twice the area of a football fieldFound four zones of damage including runoff, dune, blow and dispersalMortality of live coral and other benthic biota ranges from 75-100% in the affected locationThe form of damaged live coral growth is predominantly slow growing.Eight hard coral species were found on the IUCN-Redlist list with a vulnerable status.AbstractShip grounding on coral reefs often results in physical and biological damage, including dislodging and removal of corals from reefs, destruction of coral skeletons, erosion and removal of sediment deposits, and loss of three-dimensional complexity. Indonesia, as an archipelagic country, is very vulnerable to various pressures; for example, the case of ship grounding is a great concern of scientists, managers, divers, and sailors themselves. Most of the damage is very severe. The purpose of the research conducted is to identify the condition of the live coral cover, mapping the type and extent of coral reef damage, affected coral species, their conservation status, and to quantify the extent of the area of coral reef damage. Measuring the extent of damage to coral reef ecosystems using the fishbone method, while the level of damage and its impact was measured using the Underwater Photo Transect (UPT) and belt transect method. The event of the grounding of the MV Lyric Poet on the Bangka Waters, Bangka-Belitung Province, has caused damage to the coral reef ecosystem. There are four damage zones identified, i.e., trajectory, mound, propeller, and dispersion zone. Corals are damaged with a total area of 13.540m2; equivalent to twice that of an international football field. Diversity of hard coral found as many as 49 species included in the CITES-Appendix II. A total of eight protected species are included in the IUCN Red List with extinction-prone status.

scholarly journals Dampak Snorkeling Terhadap Persen Tutupan Terumbu Karang Di Pulau Gili Labak Sumenep Madura

2021 ◽  
Vol 10 (2) ◽  
pp. 151-161
Author(s):  
Insafitri Insafitri ◽  
Eka Nurahemma Ning Asih ◽  
Wahyu Andy Nugraha
Keyword(s):  
Coral Reef ◽  
Coral Reefs ◽  
Coral Species ◽  
Coral Cover ◽  
Observation Time ◽  
Live Coral ◽  
Marine Tourism ◽  
Coral Reef Ecosystems ◽  
Potential Impact ◽  
The Impact

Wisata snorkeling terumbu karang di perairan pulau Gili Labak merupakan salah satu sektor wisata bahari yang sedang dikembangkan oleh pemerintah kebupaten Sumenep Madura sejak tahun 2014 hingga saat ini. Peningkatan jumlah wisatawan yang terjadi pada beberapa tahun terakhir dapat menimbulkan resiko tekanan dan kerusakan ekosistem terumbu karang di area snorkeling secara berkala. Penelitian ini bertujuan untuk mengetahui dampak kegiatan wisatawan sebelum, selama dan sesudah snorkeling terhadap ekosistem terumbu karang yang dikaji dengan mengetahui jenis karang yang mendominasi, status persentase tutupan terumbu karang serta potensi Dampak Wisata Bahari (DWB) snorkeling di lokasi wisata snorkeling pulau Gili Labak Sumenep. Persentase penutupan lifeform karang pulau Gili Labak khususnya di area snorkelling didominasi oleh karang hidup sebanyak 74% dan unsur abiotik sebesar 22%. Jenis karang yang mendominasi pulau Gili Labak adalah Acropora Branching sebesar 19,88% dan Coral Foliose sebesar 10,25%. Selama waktu 6 minggu pengamatan terjadi penurunan total karang sebesar 0,64% yang termasuk kategori rusak ringan, dimana sebagian besar kerusakan terjadi pada karang dengan bentuk pertumbahan branching misalnya Acropora Submassive dan Coral Submassive. Penurunan persen tutupan karang yang tinggi terjadi setelah kegiatan snorkeling (after) yang dilakukan oleh wisatawan. Analisa potensi Dampak Wisata Bahari (DWB) snorkeling pada terumbu karang di perairan Gili Labak selama 6 minggu pengamatan masuk dalam kategori rendah yaitu berkisar 0,052% hingga 0,085%. Faktor penyebab kecilnya nilai presentase Dampak Wisata Bahari (DWB) ini diduga karena waktu pengamatan cenderung pendek dan jenis karang yang mendominasi yaitu Acropora. Acropora memiliki kemampuan regenerasi lebih cepat dibandingkan jenis lainnya.  The snorkeling activity around coral reefs in the waters of Gili Labak is one of the marine tourism sectors that is being developed by the Sumenep Madura district government since 2014. Increasing number of tourists that occurs in recent years pose a risk of pressure and damage to coral reef ecosystems in the snorkeling area. This study aims to determine the impact of tourist activities before, during and after snorkeling on coral reef ecosystems that are studied by knowing the type of dominated coral, the percentage status of coral cover and the potential Impact of snorkeling at the snorkeling sites of the island of Gili Labak Sumenep. The percentage of coral cover in the island of Gili Labak especially in the snorkelling area is dominated by live coral ( 74%) and abiotic elements by 22%. Coral species that dominate the island of Gili Labak are Acropora Branching at 19.88% and Coral Foliose at 10.25%. During the 6-week observation there was a decrease in live coral cover by 0.64% which was categorized as minor damage, most of the damage occurred to branching   Acropora, sub-massive Acropora and Coral Sub-massive. The high percent decrease in coral cover occurred after snorkeling conducted by tourists. Analysis of the potential impact of snorkeling on coral reefs in the waters of Gili Labak for 6 weeks of observation is in the low category, ranging from 0.052% to 0.085%. The factor causing the small impact of Marine Tourism is presumably because the observation time tends to be short and the dominant coral species is Acropora. Acropora has the ability to regenerate faster than other types.

scholarly journals Adaptive responses and local stressor mitigation drive coral resilience in warmer, more acidic oceans

2019 ◽  
Vol 286 (1902) ◽  
pp. 20190614 ◽  
Author(s):  
Christopher P. Jury ◽  
Robert J. Toonen
Keyword(s):  
Coral Reefs ◽  
Human Disturbance ◽  
Coral Species ◽  
Human Impacts ◽  
Coral Cover ◽  
Control Site ◽  
Low Ph ◽  
Adaptive Responses ◽  
Catastrophic Loss ◽  
Effective Conservation

Coral reefs have great biological and socioeconomic value, but are threatened by ocean acidification, climate change and local human impacts. The capacity for corals to adapt or acclimatize to novel environmental conditions is unknown but fundamental to projected reef futures. The coral reefs of Kāne‘ohe Bay, Hawai‘i were devastated by anthropogenic insults from the 1930s to 1970s. These reefs experience naturally reduced pH and elevated temperature relative to many other Hawaiian reefs which are not expected to face similar conditions for decades. Despite catastrophic loss in coral cover owing to human disturbance, these reefs recovered under low pH and high temperature within 20 years after sewage input was diverted. We compare the pH and temperature tolerances of three dominant Hawaiian coral species from within Kāne‘ohe Bay to conspecifics from a nearby control site and show that corals from Kāne‘ohe are far more resistant to acidification and warming. These results show that corals can have different pH and temperature tolerances among habitats and understanding the mechanisms by which coral cover rebounded within two decades under projected future ocean conditions will be critical to management. Together these results indicate that reducing human stressors offers hope for reef resilience and effective conservation over coming decades.

scholarly journals The Status of the Coral Reefs of the Jaffna Peninsula (Northern Sri Lanka), with 36 Coral Species New to Sri Lanka Confirmed by DNA Bar-Coding

Oceans ◽  
2021 ◽  
Vol 2 (3) ◽  
pp. 509-529
Author(s):  
Ashani Arulananthan ◽  
Venura Herath ◽  
Sivashanthini Kuganathan ◽  
Anura Upasanta ◽  
Akila Harishchandra
Keyword(s):  
Sri Lanka ◽  
Coral Reefs ◽  
Coral Species ◽  
Diversity Index ◽  
Coral Cover ◽  
Northern Region ◽  
Live Coral ◽  
Northern Coast ◽  
Acropora Digitifera ◽  
The Status

Sri Lanka, an island nation located off the southeast coast of the Indian sub-continent, has an unappreciated diversity of corals and other reef organisms. In particular, knowledge of the status of coral reefs in its northern region has been limited due to 30 years of civil war. From March 2017 to August 2018, we carried out baseline surveys at selected sites on the northern coastline of the Jaffna Peninsula and around the four largest islands in Palk Bay. The mean percentage cover of live coral was 49 ± 7.25% along the northern coast and 27 ± 5.3% on the islands. Bleaching events and intense fishing activities have most likely resulted in the occurrence of dead corals at most sites (coral mortality index > 0.33). However, all sites were characterised by high values of diversity (H’ ≥ 2.3) and evenness (E ≥ 0.8). The diversity index increased significantly with increasing coral cover on the northern coast but showed the opposite trend on the island sites. One hundred and thirteen species of scleractinian corals, representing 16 families and 39 genera, were recorded, as well as seven soft coral genera. Thirty-six of the scleractinian coral species were identified for the first time on the island of Sri Lanka. DNA barcoding using the mitochondrial cytochrome oxidase subunit I gene (COI) was employed to secure genetic confirmation of a few difficult-to-distinguish new records: Acropora aspera, Acropora digitifera, Acropora gemmifera, Montipora flabellata, and Echinopora gemmacea.

scholarly journals Deep convolutional neural networks for cardiovascular vulnerable plaque detection

2019 ◽  
Vol 277 ◽  
pp. 02024 ◽  
Author(s):  
Lincan Li ◽  
Tong Jia ◽  
Tianqi Meng ◽  
Yizhe Liu
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Vulnerable Plaque ◽  
Recall Rate ◽  
Superior Performance ◽  
Learning Approaches ◽  
Deep Convolutional Neural Networks ◽  
Vulnerable Plaques ◽  
Plaque Detection

In this paper, an accurate two-stage deep learning method is proposed to detect vulnerable plaques in ultrasonic images of cardiovascular. Firstly, a Fully Convonutional Neural Network (FCN) named U-Net is used to segment the original Intravascular Optical Coherence Tomography (IVOCT) cardiovascular images. We experiment on different threshold values to find the best threshold for removing noise and background in the original images. Secondly, a modified Faster RCNN is adopted to do precise detection. The modified Faster R-CNN utilize six-scale anchors (122,162,322,642,1282,2562) instead of the conventional one scale or three scale approaches. First, we present three problems in cardiovascular vulnerable plaque diagnosis, then we demonstrate how our method solve these problems. The proposed method in this paper apply deep convolutional neural networks to the whole diagnostic procedure. Test results show the Recall rate, Precision rate, IoU (Intersection-over-Union) rate and Total score are 0.94, 0.885, 0.913 and 0.913 respectively, higher than the 1st team of CCCV2017 Cardiovascular OCT Vulnerable Plaque Detection Challenge. AP of the designed Faster RCNN is 83.4%, higher than conventional approaches which use one-scale or three-scale anchors. These results demonstrate the superior performance of our proposed method and the power of deep learning approaches in diagnose cardiovascular vulnerable plaques.

scholarly journals Nitrogen enrichment in macroalgae following mass coral mortality

Coral Reefs ◽  
2021 ◽  
Author(s):  
Eleanor J. Vaughan ◽  
Shaun K. Wilson ◽  
Samantha J. Howlett ◽  
Valeriano Parravicini ◽  
Gareth J. Williams ◽  
...  
Keyword(s):  
Coral Reefs ◽  
Coral Cover ◽  
Strong Association ◽  
French Polynesia ◽  
Mass Mortality ◽  
Transplant Experiment ◽  
Bleaching Event ◽  
Coral Mortality ◽  
Absolute Increase ◽  
Inorganic Matter

AbstractScleractinian corals are engineers on coral reefs that provide both structural complexity as habitat and sustenance for other reef-associated organisms via the release of organic and inorganic matter. However, coral reefs are facing multiple pressures from climate change and other stressors, which can result in mass coral bleaching and mortality events. Mass mortality of corals results in enhanced release of organic matter, which can cause significant alterations to reef biochemical and recycling processes. There is little known about how long these nutrients are retained within the system, for instance, within the tissues of other benthic organisms. We investigated changes in nitrogen isotopic signatures (δ15N) of macroalgal tissues (a) ~ 1 year after a bleaching event in the Seychelles and (b) ~ 3 months after the peak of a bleaching event in Mo’orea, French Polynesia. In the Seychelles, there was a strong association between absolute loss in both total coral cover and branching coral cover and absolute increase in macroalgal δ15N between 2014 and 2017 (adjusted r2 = 0.79, p = 0.004 and adjusted r2 = 0.86, p = 0.002, respectively). In Mo’orea, a short-term transplant experiment found a significant increase in δ15N in Sargassum mangarevense after specimens were deployed on a reef with high coral mortality for ~ 3 weeks (p < 0.05). We suggest that coral-derived nutrients can be retained within reef nutrient cycles, and that this can affect other reef-associated organisms over both short- and long-term periods, especially opportunistic species such as macroalgae. These species could therefore proliferate on reefs that have experienced mass mortality events, because they have been provided with both space and nutrient subsidies by the death and decay of corals.

scholarly journals Implementation of a deep learning model for automated classification of Aedes aegypti (Linnaeus) and Aedes albopictus (Skuse) in real time

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Song-Quan Ong ◽  
Hamdan Ahmad ◽  
Gomesh Nair ◽  
Pradeep Isawasan ◽  
Abdul Hafiz Ab Majid
Keyword(s):  
Deep Learning ◽  
Aedes Aegypti ◽  
Real Time ◽  
Aedes Albopictus ◽  
Automated Classification ◽  
Expert Performance ◽  
Deep Convolutional Neural Networks ◽  
Significant Difference ◽  
Set Up

AbstractClassification of Aedes aegypti (Linnaeus) and Aedes albopictus (Skuse) by humans remains challenging. We proposed a highly accessible method to develop a deep learning (DL) model and implement the model for mosquito image classification by using hardware that could regulate the development process. In particular, we constructed a dataset with 4120 images of Aedes mosquitoes that were older than 12 days old and had common morphological features that disappeared, and we illustrated how to set up supervised deep convolutional neural networks (DCNNs) with hyperparameter adjustment. The model application was first conducted by deploying the model externally in real time on three different generations of mosquitoes, and the accuracy was compared with human expert performance. Our results showed that both the learning rate and epochs significantly affected the accuracy, and the best-performing hyperparameters achieved an accuracy of more than 98% at classifying mosquitoes, which showed no significant difference from human-level performance. We demonstrated the feasibility of the method to construct a model with the DCNN when deployed externally on mosquitoes in real time.

scholarly journals Multimodal Deep Learning and Visible-Light and Hyperspectral Imaging for Fruit Maturity Estimation

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1288
Author(s):  
Cinmayii A. Garillos-Manliguez ◽  
John Y. Chiang
Keyword(s):  
Deep Learning ◽  
Visible Light ◽  
Hyperspectral Imaging ◽  
Morphological Changes ◽  
Consumer Preference ◽  
Hyperspectral Data ◽  
Sensitivity Analyses ◽  
Deep Convolutional Neural Networks ◽  
Fruit Maturity ◽  
Learning Architectures

Fruit maturity is a critical factor in the supply chain, consumer preference, and agriculture industry. Most classification methods on fruit maturity identify only two classes: ripe and unripe, but this paper estimates six maturity stages of papaya fruit. Deep learning architectures have gained respect and brought breakthroughs in unimodal processing. This paper suggests a novel non-destructive and multimodal classification using deep convolutional neural networks that estimate fruit maturity by feature concatenation of data acquired from two imaging modes: visible-light and hyperspectral imaging systems. Morphological changes in the sample fruits can be easily measured with RGB images, while spectral signatures that provide high sensitivity and high correlation with the internal properties of fruits can be extracted from hyperspectral images with wavelength range in between 400 nm and 900 nm—factors that must be considered when building a model. This study further modified the architectures: AlexNet, VGG16, VGG19, ResNet50, ResNeXt50, MobileNet, and MobileNetV2 to utilize multimodal data cubes composed of RGB and hyperspectral data for sensitivity analyses. These multimodal variants can achieve up to 0.90 F1 scores and 1.45% top-2 error rate for the classification of six stages. Overall, taking advantage of multimodal input coupled with powerful deep convolutional neural network models can classify fruit maturity even at refined levels of six stages. This indicates that multimodal deep learning architectures and multimodal imaging have great potential for real-time in-field fruit maturity estimation that can help estimate optimal harvest time and other in-field industrial applications.

scholarly journals Interpretable deep learning for the remote characterisation of ambulation in multiple sclerosis using smartphones

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Andrew P. Creagh ◽  
Florian Lipsmeier ◽  
Michael Lindemann ◽  
Maarten De Vos
Keyword(s):  
Multiple Sclerosis ◽  
Deep Learning ◽  
Inertial Sensor ◽  
Heterogeneous Data ◽  
Fine Tuning ◽  
Sensor Data ◽  
Support Vector ◽  
Deep Convolutional Neural Networks ◽  
Healthcare Applications ◽  
Feature Based

AbstractThe emergence of digital technologies such as smartphones in healthcare applications have demonstrated the possibility of developing rich, continuous, and objective measures of multiple sclerosis (MS) disability that can be administered remotely and out-of-clinic. Deep Convolutional Neural Networks (DCNN) may capture a richer representation of healthy and MS-related ambulatory characteristics from the raw smartphone-based inertial sensor data than standard feature-based methodologies. To overcome the typical limitations associated with remotely generated health data, such as low subject numbers, sparsity, and heterogeneous data, a transfer learning (TL) model from similar large open-source datasets was proposed. Our TL framework leveraged the ambulatory information learned on human activity recognition (HAR) tasks collected from wearable smartphone sensor data. It was demonstrated that fine-tuning TL DCNN HAR models towards MS disease recognition tasks outperformed previous Support Vector Machine (SVM) feature-based methods, as well as DCNN models trained end-to-end, by upwards of 8–15%. A lack of transparency of “black-box” deep networks remains one of the largest stumbling blocks to the wider acceptance of deep learning for clinical applications. Ensuing work therefore aimed to visualise DCNN decisions attributed by relevance heatmaps using Layer-Wise Relevance Propagation (LRP). Through the LRP framework, the patterns captured from smartphone-based inertial sensor data that were reflective of those who are healthy versus people with MS (PwMS) could begin to be established and understood. Interpretations suggested that cadence-based measures, gait speed, and ambulation-related signal perturbations were distinct characteristics that distinguished MS disability from healthy participants. Robust and interpretable outcomes, generated from high-frequency out-of-clinic assessments, could greatly augment the current in-clinic assessment picture for PwMS, to inform better disease management techniques, and enable the development of better therapeutic interventions.

Sign in / Sign up

Export Citation Format

Share Document