Article

A Review of Computational Intelligence Techniques in Coral Reefs-related Applications

If you want to read the PDF, try requesting it from the authors.

Abstract

Studies on coral reefs increasingly combine aspects of science and technology to understand the complex dynamics and processes that shape these benthic ecosystems. Recently, the use of advanced computational algorithms has entered coral reefs science as new powerful tools that help solve complex coral reef related questions, which were unsolvable just a decade earlier. Some of these advanced algorithms consist of Computational Intelligence (CI) approaches, a branch of Artificial Intelligence that uses intelligent systems to address complex real-world problems yielding more robust, tractable and simpler solutions than those obtained by conventional mathematical techniques. This paper describes the most commonly used CI techniques related to coral reefs and the main improvements obtained with these methods over classical algorithms in this field. Some recommendations are given for the application of CI techniques to complex coral reef related problems, and vice-versa, for the application of novel coral reef dynamics concepts to improve the Coral Reefs Optimization (CRO) algorithm, an optimization method inspired by coral reef dynamics.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... The paper additionally contributes to some adjacent literatures. Prior studies have considered the application of AI for environmental protection [19][20], for climate change mitigation [21][22], and the energy consumption of AI systems [23]; these are relevant for environmental conceptions of sustainability. Also relevant are debates on the relative importance of near-term, medium-term, and long-term AI [24][25][26][27]; as this paper discusses, the future-orientation of sustainability can imply an emphasis on long-term AI. ...
Preprint
Full-text available
The paper is part of the conference AI for People: Towards Sustainable AI, CAIP’21.
... 96 An AI-based technique is being utilized to analyze shallow-water reef images, recognize the coral color-to track the effects of climate change, and to collect humidity, temperature, and CO 2 data-to grasp the health of our ecological environment. 97 Beyond AI's capabilities for meteorology, it can also play a critical role in decreasing greenhouse gas emissions originating from the electric-power sector. Comprised of production, transportation, allocation, and consumption of electricity, many opportunities exist in the electric-power sector for Al applications, including speeding up the development of new clean energy, enhancing system optimization and management, improving electricity-demand forecasts and distribution, and advancing system monitoring. ...
Article
Full-text available
Artificial Intelligence (AI) coupled with promising machine learning (ML) techniques well known from computer science is broadly affecting many aspects of various fields including science and technology, industry, and even our day to day life. The ML techniques have been developed to analyze high-throughput data with a view to obtaining useful insights, categorizing, predicting and making evidence-based decisions in novel ways, which will promote the growth of novel applications and fuel the sustainable booming of AI. This paper undertakes performs a comprehensive survey on the development and application of AI in different aspects of fundamental sciences, including information science, mathematics, medical science, materials science, geoscience, life science, physics and chemistry. The challenges that each discipline of science meets, and the potentials of AI techniques to handle these challenges, are discussed in detail. Moreover, we shed light on new research trends entailing the integration of AI into each scientific discipline. The goal of this paper is to provide a broad research guideline on fundamental sciences with potential infusion of AI, to help motivate researchers to deeply understand the state-of-the-art applications of AI-based fundamental sciences, and thereby to help promote the continuous development of these fundamental sciences.
... For example, Sperotto et al. (2017) and Landuyt et al. (2013) focused on a single method, reviewing the potential and limitations of BN for CCRA and ecosystem services evaluation. With a wider perspective, other authors compared the suitability of multiple ML techniques applied for modelling ecosystems (e.g, coral reefs: Salcedo-Sanz et al., 2016), pattern extraction (e.g. land use patterns), and insights from increasing streams of geospatial data (Reichstein et al., 2019), for predicting high-impact weather phenomena (McGovern et al., 2017), or for climate adaptation and mitigation (Rolnick et al., 2019). ...
Article
Global warming is exacerbating weather, and climate extremes events and is projected to aggravate multi-sectorial risks. A multiplicity of climate hazards will be involved, triggering cumulative and interactive impacts on a variety of natural and human systems. An improved understanding of risk interactions and dynamics is required to support decision makers in their ability to better manage current and future climate change risks. To face this issue, the research community has been starting to test new methodological approaches and tools, including the application of Machine Learning (ML) leveraging the potential of the large availability and variety of spatio-temporal big data for environmental applications. Given the increasing attention on the application of ML methods to Climate Change Risk Assessment (CCRA), this review mapped out the state of art and potential of these methods to this field of research. Scientometric and systematic analysis were jointly applied providing an in-depth review of publications across the 2000–2020 timeframe. The resulting output from the analysis showed that a huge variety of ML algorithms have been already applied within CCRA, among them, the most recurrent are Decision Tree, Random Forest, and Artificial Neural Network. These algorithms are often applied in an ensemble or hybridized way to analyze most of all floods and landslides risk events. Moreover, the application of ML to deal with remote sensing data is consistent and effective across reviewed CCRA applications, allowing the identification and classification of targets and the detection of environmental and structural features. On the contrary concerning future climate change scenarios, literature seems not to be very widespread into scientific production, compared to studies evaluating risks under current conditions. The same lack can be noted also for the assessment of cascading and compound hazards and risks, since these concepts are recently emerging in CCRA literature but not yet in combination with ML-based applications.
... Neural networks have been gaining popularity in the aquatic remote sensing and used to derive the diffuse attenuation coefficient (Jamet et al., 2012;Chen et al., 2014), uncouple constituents in optically complex waters (Doerffer and Helmut, 2000;Ioannou et al., 2013), map shallow-water benthic features (Sandidge and Holyer, 1998;Filippi, 2007;Liu et al., 2015), and to evaluate features across different scales (e.g., Hieronymi et al., 2017;Pahlevan et al., 2020). Salcedo-Sanz and colleagues, for example, implemented a neural network to map shallow benthic coral reef features and concluded that neural network approaches generally out perform traditional empirical approaches to the problem such as supervised and unsupervized classification and regression analysis (Salcedo-Sanz et al., 2016). ...
Article
Full-text available
Intensifying pressure on global aquatic resources and services due to population growth and climate change is inspiring new surveying technologies to provide science-based information in support of management and policy strategies. One area of rapid development is hyperspectral remote sensing: imaging across the full spectrum of visible and infrared light. Hyperspectral imagery contains more environmentally meaningful information than panchromatic or multispectral imagery and is poised to provide new applications relevant to society, including assessments of aquatic biodiversity, habitats, water quality, and natural and anthropogenic hazards. To aid in these advances, we provide resources relevant to hyperspectral remote sensing in terms of providing the latest reviews, databases, and software available for practitioners in the field. We highlight recent advances in sensor design, modes of deployment, and image analysis techniques that are becoming more widely available to environmental researchers and resource managers alike. Systems recently deployed on space- and airborne platforms are presented, as well as future missions and advances in unoccupied aerial systems (UAS) and autonomous in-water survey methods. These systems will greatly enhance the ability to collect interdisciplinary observations on-demand and in previously inaccessible environments. Looking forward, advances in sensor miniaturization are discussed alongside the incorporation of citizen science, moving toward open and FAIR (findable, accessible, interoperable, and reusable) data. Advances in machine learning and cloud computing allow for exploitation of the full electromagnetic spectrum, and better bridging across the larger scientific community that also includes biogeochemical modelers and climate scientists. These advances will place sophisticated remote sensing capabilities into the hands of individual users and provide on-demand imagery tailored to research and management requirements, as well as provide critical input to marine and climate forecasting systems. The next decade of hyperspectral aquatic remote sensing is on the cusp of revolutionizing the way we assess and monitor aquatic environments and detect changes relevant to global communities.
... 被证明在仅有少量物种出现记录的情况下依然 能够取得良好的拟合效果甚至优于其他模型 [31] , 因此可适用于调查数据获取难度较大的珊瑚礁. 目前国外已有研究利用 MaxEnt 模型创建生态系 统监测和管理所需的珊瑚分布图 [32] ,探索深海珊 瑚的潜在适生区分布 [33][34][35] ,以及用于预测珊瑚栖 息地应对气候变化的响应 [36][37] .模型模拟方法正 在逐渐成为珊瑚礁研究中的重要工具之一 [38] [39] ,其中广西涠洲岛和广东徐闻的造 礁石珊瑚能成礁,再往北分布的则形成造礁石珊 瑚群落 [40] ,通常认为福建东山是我国大陆沿岸造 礁石珊瑚成片分布的最北缘 [41] .本研究主要覆盖 中国大陆东南部沿岸海域,将有造礁石珊瑚分布 记录的海南、广西、广东、福建四省及其邻近海 域纳入适生区研究范围.据文献检索结果,目前中 ...
Article
Full-text available
Predicting their potential habitat distribution and suitable environmental conditions is essential to achieve effective conservation and coral reef restoration of scleractinia corals. Here, for the first time, we adopted the Maximum Entropy Model and spatial analysis approach to predict the potential habitat suitability of scleractinia corals along the southeast coast of mainland China, as well as quantitatively evaluated the relationships between coral distribution and multiple environmental factors. The results showed that the distribution of scleractinia corals in China was mainly affected by environmental variables such as precipitation and sea surface temperature. The most suitable environmental interval include annual precipitation (between 1136~2051mm), precipitation seasonality (coefficient of variation, 66~83mm), mean SST in the coldest season (18.6~23.3℃), and annual mean SST(20.9~25.8℃). The simulated potential suitable areas are mainly distributed along the coasts of Hainan Island-Weizhou Island-Leizhou Peninsula, Pearl River Mouth-Daya Bay, Nan'ao-Dongshan-Liu Au, and Xiamen Bay-Pingtan Island, where the most suitable area is about 138km². By comparing the distribution hotspots of scleractinia corals and current marine protected areas, it was identified that the potential conservation gaps may occur at the Pearl River Estuary, Daya Bay and the southern coast of Fujian Province, as well as Lingao and Lingshui around Hainan Island. © 2021, Editorial Board of China Environmental Science. All right reserved.
... The CRO [31] is an evolutionary meta-heuristic algorithm which has high convergence rate. CRO-based optimization methods have been utilized in several applications [32,33]. This technique has been also used in some areas of cloud computing. ...
Article
Full-text available
Resource management is the process of task scheduling and resource provisioning to provide requirements of cloud users. Since cloud resources are often heterogeneous, task scheduling and resource provisioning are major challenges in this area. Various methods have been introduced to improve resource utilization and thus increase the efficiency of cloud computing. Existing methods can be divided into several categories, including mathematical and statistical methods, heuristic- and meta-heuristic-based methods, and machine-learning-based methods. Since the resource management problem is NP-complete, several optimization methods have been also exploited in this area. Coral reefs algorithm is an evolutionary method that has showed appropriate convergence and response time for some problems, and thus is used in this paper to combine with reinforcement learning to improve efficiency of resource management in cloud environments. The proposed method of this paper consists of two phases. The initial allocation of resources to ready-to-perform tasks is done using the coral reefs algorithm in the first phase. The tasks are considered as corals and the resources are considered reefs in this method. The second phase utilizes reinforcement learning to avoid falling into the local optima and to make optimal use of resources using a long-term approach. The proposed model of this paper, called MO-CRAML, introduces a new hybrid algorithm for improving utilization and load balancing of cloud resources using the combination of coral reefs optimization algorithm and reinforcement learning. The results of the experiments show that the proposed algorithm has better performance in cloud resource utilization and load balancing in comparison with some other important methods of the literature.
... Artificial intelligent techniques have emerged as an attractive approach for modeling and predicting the performance of complex systems found in numerous areas of science and engineering [1]. In particular, artificial neural networks (ANNs) are reliable and flexible black box models capable of identifying and fitting the nonlinear relationships between a set of input and output variables. ...
... Although subjective manual mapping is the most common approach for identifying areas of potential coral habitats (Davies et al. 2008;Ross and Howell 2013), more objective and automated approaches have been published (Salcedo-Sanz et al. 2016). However, the semi-automated mapping approach presented in this study uses a fast and consistent automatic method and allows inclusion of additional data sets that have been developed within a GIS environment. ...
Article
Full-text available
Cold-water corals form substantial biogenic habitats on continental shelves and in deep-sea areas with topographic highs, such as banks and seamounts. In the Atlantic, many reef and mound complexes are engineered by Lophelia pertusa, the dominant framework-forming coral. In this study, a variety of mapping approaches were used at a range of scales to map the distribution of both cold-water coral habitats and individual coral colonies at the Mingulay Reef Complex (west Scotland). The new ArcGIS-based British Geological Survey (BGS) seabed mapping toolbox semi-automatically delineated over 500 Lophelia reef ‘mini-mounds’ from bathymetry data with 2-m resolution. The morphometric and acoustic characteristics of the mini-mounds were also automatically quantified and captured using this toolbox. Coral presence data were derived from high-definition remotely operated vehicle (ROV) records and high-resolution microbathymetry collected by a ROV-mounted multibeam echosounder. With a resolution of 0.35 × 0.35 m, the microbathymetry covers 0.6 km² in the centre of the study area and allowed identification of individual live coral colonies in acoustic data for the first time. Maximum water depth, maximum rugosity, mean rugosity, bathymetric positioning index and maximum current speed were identified as the environmental variables that contributed most to the prediction of live coral presence. These variables were used to create a predictive map of the likelihood of presence of live cold-water coral colonies in the area of the Mingulay Reef Complex covered by the 2-m resolution data set. Predictive maps of live corals across the reef will be especially valuable for future long-term monitoring surveys, including those needed to understand the impacts of global climate change. This is the first study using the newly developed BGS seabed mapping toolbox and an ROV-based microbathymetric grid to explore the environmental variables that control coral growth on cold-water coral reefs.
Article
Artificial Intelligence (AI) has become an important area to tackle most environmental sustainability issues such as biodiversity, energy, transportation and water management. Biodiversity research has developed machine learning or natural language processing solutions to predict ecosystem services. Artificial intelligence applications and machine learning models have been increasingly used for predicting and optimizing water resource conservation. Area neural network, expert systems, pattern recognition, and fuzzy logic models are the main focus areas in energy. Applications of computer vision and decision support were found in transportation. Timely monitoring of interventions is required to improve environmental sustainability.
Article
Artificial intelligence (AI) will transform business practices and industries and has the potential to address major societal problems, including sustainability. Degradation of the natural environment and the climate crisis are exceedingly complex phenomena requiring the most advanced and innovative solutions. Aiming to spur groundbreaking research and practical solutions of AI for environmental sustainability, we argue that AI can support the derivation of culturally appropriate organizational processes and individual practices to reduce the natural resource and energy intensity of human activities. The true value of AI will not be in how it enables society to reduce its energy, water, and land use intensities, but rather, at a higher level, how it facilitates and fosters environmental governance. A comprehensive review of the literature indicates that research regarding AI for sustainability is challenged by (1) overreliance on historical data in machine learning models, (2) uncertain human behavioral responses to AI-based interventions, (3) increased cybersecurity risks, (4) adverse impacts of AI applications, and (5) difficulties in measuring effects of intervention strategies. The review indicates that future studies of AI for sustainability should incorporate (1) multilevel views, (2) systems dynamics approaches, (3) design thinking, (4) psychological and sociological considerations, and (5) economic value considerations to show how AI can deliver immediate solutions without introducing long-term threats to environmental sustainability.
Article
In requirements elicitation process, different stakeholder participates to find out the requirements of software. In practical applications, different stakeholders have dissimilar view for the same requirements; and they may also use linguistic terminologies in describing the importance of their requirements. Based on literature review, we identify that stakeholder identification methods do not support that how to prioritize the stakeholders on the basis of the importance of software requirements. Therefore, to address the above issue, we propose a method for the prioritization of stakeholders on the basis of the importance of software requirements using fuzzy-based approach. There are three steps in the proposed method, i.e., (1) “specify stakeholder types and their roles” (2) “select and classify requirements”; and (3) “stakeholder's analysis”. Finally, the application of the proposed method is explained with the help of a case study, which is based on Institute Examination System.
Article
Full-text available
Swarm intelligence is a relatively new approach to problem solving that takes inspiration from the social behaviors of insects and of other animals. In particular, ants have inspired a number of methods and techniques among which the most studied and the most successful is the general purpose optimization technique known as ant colony optimization. Ant colony optimization (ACO) takes inspiration from the foraging behavior of some ant species. These ants deposit pheromone on the ground in order to mark some favorable path that should be followed by other members of the colony. Ant colony optimization exploits a similar mechanism for solving optimization problems. From the early nineties, when the first ant colony optimization algorithm was proposed, ACO attracted the attention of increasing numbers of researchers and many successful applications are now available. Moreover, a substantial corpus of theoretical results is becoming available that provides useful guidelines to researchers and practitioners in further applications of ACO. The goal of this article is to introduce ant colony optimization and to survey its most notable applications
Article
Full-text available
Mangrove forests are one of the world's most threatened tropical ecosystems with global loss exceeding 35% (ref. 1). Juvenile coral reef fish often inhabit mangroves, but the importance of these nurseries to reef fish population dynamics has not been quantified. Indeed, mangroves might be expected to have negligible influence on reef fish communities: juvenile fish can inhabit alternative habitats and fish populations may be regulated by other limiting factors such as larval supply or fishing. Here we show that mangroves are unexpectedly important, serving as an intermediate nursery habitat that may increase the survivorship of young fish. Mangroves in the Caribbean strongly influence the community structure of fish on neighbouring coral reefs. In addition, the biomass of several commercially important species is more than doubled when adult habitat is connected to mangroves. The largest herbivorous fish in the Atlantic, Scarus guacamaia, has a functional dependency on mangroves and has suffered local extinction after mangrove removal. Current rates of mangrove deforestation are likely to have severe deleterious consequences for the ecosystem function, fisheries productivity and resilience of reefs. Conservation efforts should protect connected corridors of mangroves, seagrass beds and coral reefs.
Article
Full-text available
There are more coral species in deep, cold-waters than in tropical coral reefs. This broad-ranging treatment is the first to synthesise current understanding of all types of cold-water coral, covering their ecology, biology, palaeontology and geology. Beginning with a history of research in the field, the authors describe the approaches needed to study corals in the deep sea. They consider coral habitats created by stony scleractinian as well as octocoral species. The importance of corals as long-lived geological structures and palaeoclimate archives is discussed, in addition to ways in which they can be conserved. Topic boxes explain unfamiliar concepts, and case studies summarize significant studies, coral habitats or particular conservation measures. Written for professionals and students of marine science, this text is enhanced by an extensive glossary, online resources, and a unique collection of color photographs and illustrations of corals and the habitats they form. © J. Roberts, A. Wheeler, A. Freiwald and S. Cairns 2009 and Cambridge University Press, 2009.
Article
Full-text available
Millions of people rely on the ecosystem services provided by coral reefs, but sustaining these benefits requires an understanding of how reefs and their biotic communities are affected by local human-induced disturbances and global climate change. Ecosystem-based management that explicitly considers the indirect and cumulative effects of multiple disturbances has been recommended and adopted in policies in many places around the globe. Ecosystem models give insight into complex reef dynamics and their responses to multiple disturbances and are useful tools to support planning and implementation of ecosystem-based management. We adapted the Atlantis Ecosystem Model to incorporate key dynamics for a coral reef ecosystem around Guam in the tropical western Pacific. We used this model to quantify the effects of predicted climate and ocean changes and current levels of current land-based sources of pollution (LBSP) and fishing. We used the following six ecosystem metrics as indicators of ecosystem state, resilience and harvest potential: 1) ratio of calcifying to non-calcifying benthic groups, 2) trophic level of the community, 3) biomass of apex predators, 4) biomass of herbivorous fishes, 5) total biomass of living groups and 6) the end-to-start ratio of exploited fish groups. Simulation tests of the effects of each of the three drivers separately suggest that by mid-century climate change will have the largest overall effect on this suite of ecosystem metrics due to substantial negative effects on coral cover. The effects of fishing were also important, negatively influencing five out of the six metrics. Moreover, LBSP exacerbates this effect for all metrics but not quite as badly as would be expected under additive assumptions, although the magnitude of the effects of LBSP are sensitive to uncertainty associated with primary productivity. Over longer time spans (i.e., 65 year simulations), climate change impacts have a slight positive interaction with other drivers, generally meaning that declines in ecosystem metrics are not as steep as the sum of individual effects of the drivers. These analyses offer one way to quantify impacts and interactions of particular stressors in an ecosystem context and so provide guidance to managers. For example, the model showed that improving water quality, rather than prohibiting fishing, extended the timescales over which corals can maintain high abundance by at least 5-8 years. This result, in turn, provides more scope for corals to adapt or for resilient species to become established and for local and global management efforts to reduce or reverse stressors.
Article
Full-text available
Coverage control is one of the most fundamental issues in directional sensor networks. In this paper, the coverage optimization problem in a directional sensor network is formulated as a multi-objective optimization problem. It takes into account the coverage rate of the network, the number of working sensor nodes and the connectivity of the network. The coverage problem considered in this paper is characterized by the geographical irregularity of the sensed events and heterogeneity of the sensor nodes in terms of sensing radius, field of angle and communication radius. To solve this multi-objective problem, we introduce a learning automata-based coral reef algorithm for adaptive parameter selection and use a novel Tchebycheff decomposition method to decompose the multi-objective problem into a single-objective problem. Simulation results show the consistent superiority of the proposed algorithm over alternative approaches.
Thesis
Full-text available
Autonomous repair of deep-sea coral reefs is a recent proposed idea to support the oceans ecosystem in which is vital for commercial fishing, tourism and other species. This idea can be operated through using many small autonomous underwater vehicles (AUVs) and swarm intelligence techniques to locate and replace chunks of coral which have been broken off, thus enabling re-growth and maintaining the habitat. The aim of this project is developing machine vision algorithms to enable an underwater robot to locate a coral reef and a chunk of coral on the seabed and prompt the robot to pick it up. Although there is no literature on this particular problem, related work on fish counting may give some insight into the problem. The technical challenges are principally due to the potential lack of clarity of the water and platform stabilization as well as spurious artifacts (rocks, fish, and crabs). We present an efficient sparse classification for coral species using supervised deep learning method called Convolutional Neural Networks (CNNs). We compute Weber Local Descriptor (WLD), Phase Congruency (PC), and Zero Component Analysis (ZCA) Whitening to extract shape and texture feature descriptors, which are employed to be supplementary channels (feature-based maps) besides basic spatial color channels (spatial-based maps) of coral input image, we also experiment state-of-art preprocessing underwater algorithms for image enhancement and color normalization and color conversion adjustment. Our proposed coral classification method is developed under MATLAB platform, and evaluated by two different coral datasets (University of California San Diego's Moorea Labeled Corals, and Heriot-Watt University's Atlantic Deep Sea).
Article
Full-text available
Extreme learning machine (ELM) is a novel and fast learning method to train single layer feed-forward networks. However due to the demand for larger number of hidden neurons, the prediction speed of ELM is not fast enough. An evolutionary based ELM with differential evolution (DE) has been proposed to reduce the prediction time of original ELM. But it may still get stuck at local optima. In this paper, a novel algorithm hybridizing DE and metaheuristic coral reef optimization (CRO), which is called differential evolution coral reef optimization (DECRO), is proposed to balance the explorative power and exploitive power to reach better performance. The thought and the implement of DECRO algorithm are discussed in this article with detail. DE, CRO and DECRO are applied to ELM training respectively. Experimental results show that DECRO-ELM can reduce the prediction time of original ELM, and obtain better performance for training ELM than both DE and CRO.
Article
Full-text available
Understanding how communities respond to natural disturbances is fundamental to assess the mechanisms of ecosystem resistance and resilience. However, ecosystem responses to natural disturbances are rarely monitored both through space and time, while the factors promoting ecosystem stability act at various temporal and spatial scales. Hence, assessing both the spatial and temporal variations in species composition is important to comprehensively explore the effects of natural disturbances. Here, we suggest a framework to better scrutinize the mechanisms underlying community responses to disturbances through both time and space. Our analytical approach is based on beta diversity decomposition into two components, replacement and biomass difference. We illustrate this approach using a 9-year monitoring of coral reef fish communities off Moorea Island (French Polynesia), which encompassed two severe natural disturbances: a crown-of-thorns starfish outbreak and a hurricane. These disturbances triggered a fast logistic decline in coral cover, which suffered a 90% decrease on all reefs. However, we found that the coral reef fish composition remained largely stable through time and space whereas compensatory changes in biomass among species were responsible for most of the temporal fluctuations, as outlined by the overall high contribution of the replacement component to total beta diversity. This suggests that, despite the severity of the two disturbances, fish communities exhibited high resistance and the ability to reorganize their compositions to maintain the same level of total community biomass as before the disturbances. We further investigated the spatial congruence of this pattern and showed that temporal dynamics involved different species across sites; yet, herbivores controlling the proliferation of algae that compete with coral communities were consistently favored. These results suggest that compensatory changes in biomass among species and spatial heterogeneity in species responses can provide further insurance against natural disturbances in coral reef ecosystems by promoting high levels of key species (herbivores). They can also allow the ecosystem to recover more quickly.
Article
Full-text available
As hotspots of local biodiversity in the deep sea, preservation of cold-water coral reef communities is of great importance. In European waters the most extensive reefs are found at depths of 300 - 500 m on the continental margin. In Norwegian waters many of these reefs are located in areas of interest for oil and gas exploration and production. In this study drilling was carried out in the Morvin drill field in proximity to a number of small Lophelia pertusa coral reefs (closest reefs 100 m upstream and 350 m downstream of point of waste drill material release). In a novel monitoring study, ROV video surveys of 9 reefs were conducted prior, during, immediately after and >1 year after drilling operations. Behavior of coral polyps inhabiting reefs exposed to differing concentrations of drill cuttings and drilling fluids (waste drilling material) were compared. Levels of expected exposure to these waste materials were determined for each reef by modelling drill cutting transport following release, using accurate in-situ hydrodynamic data collected during the drilling period and drill cutting discharge data as parameters of a dispersal model. The presence / absence of associate reef species (Acesta excavata, Paragorgia arborea and Primnoa resedaeformis) were also determined from each survey video. There were no significant differences in Lophelia pertusa polyp behavior in corals modelled to have been exposed to pulses of >25 ppm drill cutting material and those modelled to be exposed to negligible concentrations of material. From the video data collected, there were no observed degradations of reef structure over time, nor reductions of associate fauna abundance, regardless of modelled exposure concentration at any of the surveyed reefs. This study focused exclusively on adult fauna, and did not assess the potential hazard posed by waste drilling material to coral or other larvae. Video data was collected by various ROV's, using different camera and lighting setups throughout the survey campaign, making comparison of observations prior, during and post drilling problematic. A standardization of video monitoring in future monitoring campaigns is recommended.
Article
Full-text available
In this article a new algorithm for multi-objective optimization is presented, the Multi-Objective Coral Reefs Optimization (MO-CRO) algorithm. The algorithm is based on the simulation of processes in coral reefs, such as corals' reproduction and fight for space in the reef. The adaptation to multi-objective problems is a process based on domination or non-domination during the process of fight for space in the reef. The final MO-CRO is an easily-implemented and fast algorithm, simple and robust, since it is able to keep diversity in the population of corals (solutions) in a natural way. The experimental evaluation of this new approach for multi-objective optimization problems is carried out on different multi-objective benchmark problems, where the MO-CRO has shown excellent performance in cases with limited computational resources, and in a real-world problem of wind speed prediction, where the MO-CRO algorithm is used to find the best set of features to predict the wind speed, taking into account two objective functions related to the performance of the prediction and the computation time of the regressor.
Article
Full-text available
Ocean and coastal ecosystems provide critical fisheries, coastal protection, and cultural benefits to communities worldwide, but these services are diminishing due to local and global threats. In response, place-based strategies involve communities and resource users in management have proliferated. Here, we present a transferable community-based approach to assess the social and ecological factors affecting resource sustainability and food security in a small-scale, coral reef fishery. Our results show that this small-scale fishery provides large-scale benefits to communities, including 7,353 ± 1547 kg yr-1 (mean ± SE) of seafood per year, equating to >30,000 meals with an economic value of $78,432. The vast majority of the catch is used for subsistence, contributing to community food security: 58% is kept, 33.5% is given away, and 8.5% is sold. Our spatial analysis assesses the geographic distribution of community beneficiaries from the fishery (the "food shed" for the fishery), and we document that 20% of seafood procured from the fishery is used for sociocultural events that are important for social cohesion. This approach provides a method for assessing social, economic, and cultural values provided by small-scale food systems, as well as important contributions to food security, with significant implications for conservation and management. This interdisciplinary effort aims to demonstrate a transferable participatory research approach useful for resource-dependent communities as they cope with socioeconomic, cultural, and environmental change.
Conference Paper
Full-text available
Several clustering algorithms have been developed and applied to a great variety of problems in different fields. However, some of these algorithms have limitations. Bio-inspired algorithms have been applied to clustering problems aiming to overcome some of these limitations. In this paper, we apply the Coral Reefs Optimization (CRO) algorithm to clustering problems. The CRO algorithm has been originally proposed for classical optimization problems. In this paper, this algorithm will be adjusted to provide a good clustering partition for a dataset. In addition, we also propose three new modifications of this algorithm and an index to be used as objective function for the optimization techniques. In order to evaluate the effectiveness of the CRO algorithm and the proposed extensions when dealing with real data, we conduct a comparison analysis with another bio-inspired algorithm, a hybrid genetic algorithm proposed for solving clustering problems. In this analysis, two clustering validiity measures are employed to measure the generated clusters by the bio-inspired algorithms. We also use two objective functions (TWCV and MX index) in the reproduction process of the analysed algorithms.
Article
Full-text available
Monitoring coral reef, seagrass, and sand features using contemporary remotely sensed data may prove to be a cost-effective and time-efficient tool for reef surveys, change detection, and management. Previous attempts at subsurface feature discrimination with satellite remote sensing have been limited in accuracy due to the effects of pixel mixing associated with poor spatial resolutions. While aerial reconnaissance may offer higher spatial resolutions than satellite sensors, it is often limited by the high costs of planning and implementing the missions, image rectification, area that can be covered, and repeat coverage. In this study, the Ikonos satellite with a 4- by 4-m spatial resolution in the multispectral bands was used as a tool for subsurface feature identification. The Single-Image Normalization Using Histogram Adjustment was used for atmospheric corrections on the imagery. Classification was performed using bands 1, 2, and 3 (blue, green, and red) to maximize the water-penetration capabilities of the sensor. An accuracy assessment of the classification results was performed using in situ data collected at 62 points one day prior to the image being acquired. It was concluded that the Ikonos data were useful for discriminating sand, coral reef (at two depth intervals), and seagrass features (providing overall accuracies of 89 percent each for the two study areas). However, error still remained in discriminating small, diverse patch-reef features. This error (producers accuracy 67 percent) was found in the "Reef ≤ 5 m" class and was primarily attributed to the diversity of this spectral class, which may lead to a spectral signature based on the dominant cover type in a given pixel.
Article
Full-text available
Coral reef ecosystems are under dual threat from climate change. Increasing sea surface temperatures and thermal stress create environmental limits at low latitudes, and decreasing aragonite saturation state creates environmental limits at high latitudes. This study examines the response of unique coral reef habitats to climate change in the remote Pacific, using the National Center for Atmospheric Research Community Earth System Model version 1 alongside the species distribution algorithm Maxent. Narrow ranges of physico-chemical variables are used to define unique coral habitats and their performance is tested in future climate scenarios. General loss of coral reef habitat is expected in future climate scenarios and has been shown in previous studies. This study found exactly that for most of the predominant physico-chemical environments. However, certain coral reef habitats considered marginal today at high latitude, along the equator and in the eastern tropical Pacific were found to be quite robust in climate change scenarios. Furthermore, an environmental coral reef refuge previously identified in the central south Pacific near French Polynesia was further reinforced. Studying the response of specific habitats showed that the prevailing conditions of this refuge during the 20 th century shift to a new set of conditions, more characteristic of higher latitude coral reefs in the 20 th century, in future climate scenarios projected to 2100.
Article
Full-text available
Understanding the temporal dynamics of present thermal and pH exposure on coral reefs is crucial for elucidating reef response to future global change. Diel ranges in temperature and carbonate chemistry parameters coupled with seasonal changes in the mean conditions define periods during the year when a reef habitat is exposed to anomalous thermal and/or pH exposure. Anomalous conditions are defined as values that exceed an empirically estimated threshold for each variable. We present a 200-day time series from June through December 2010 of carbonate chemistry and environmental parameters measured on the Heron Island reef flat. These data reveal that aragonite saturation state, pH, and pCO2 were primarily modulated by biologically-driven changes in dissolved organic carbon (DIC) and total alkalinity (TA), rather than salinity and temperature. The largest diel temperature ranges occurred in austral spring, in October (1.5 - 6.6°C) and lowest diel ranges (0.9 - 3.2°C) were observed in July, at the peak of winter. We observed large diel total pH variability, with a maximum range of 7.7 - 8.5 total pH units, with minimum diel average pH values occurring during spring and maximum during fall. As with many other reefs, the nighttime pH minima on the reef flat were far lower than pH values predicted for the open ocean by 2100. DIC and TA both increased from June (end of Fall) to December (end of Spring). Using this high-resolution dataset, we developed exposure metrics of pH and temperature individually for intensity, duration, and severity of low pH and high temperature events, as well as a combined metric. Periods of anomalous temperature and pH exposure were asynchronous on the Heron Island reef flat, which underlines the importance of understanding the dynamics of co-occurrence of multiple stressors on coastal ecosystems.
Article
Full-text available
Animal-derived nutrients play an important role in structuring nutrient regimes within and between ecosystems. When animals undergo repetitive, aggregating behavior through time, they can create nutrient hotspots where rates of biogeochemical activity are higher than those found in the surrounding environment. In turn, these hotspots can influence ecosystem processes and community structure. We examined the potential for reef fishes from the family Haemulidae (grunts) to create nutrient hotspots and the potential impact of these hotspots on reef communities. To do so, we tracked the schooling locations of diurnally migrating grunts, which shelter at reef sites during the day but forage off reef each night, and measured the impact of these fish schools on benthic communities. We found that grunt schools showed a high degree of site fidelity, repeatedly returning to the same coral heads. These aggregations created nutrient hotspots around coral heads where nitrogen and phosphorus delivery was roughly 10 and 7 times the respective rates of delivery to structurally similar sites that lacked schools of these fishes. In turn, grazing rates of herbivorous fishes at grunt-derived hotspots were approximately 3 times those of sites where grunts were rare. These differences in nutrient delivery and grazing led to distinct benthic communities with higher cover of crustose coralline algae and less total algal abundance at grunt aggregation sites. Importantly, coral growth was roughly 1.5 times greater at grunt hotspots, likely due to the important nutrient subsidy. Our results suggest that schooling reef fish and their nutrient subsidies play an important role in mediating community structure on coral reefs and that overfishing may have important negative consequences on ecosystem functions. As such, management strategies must consider mesopredatory fishes in addition to current protection often offered to herbivores and top-tier predators. Furthermore, our results suggest that restoration strategies may benefit from focusing on providing structure for aggregating fishes on reefs with low topographic complexity or focusing the restoration of nursery raised corals around existing nutrient hotspots.
Article
Full-text available
Remote sensing shows potential for assessing biodiversity of coral reefs. Important steps in achieving this objective are better understanding the spectral variability of various reef components and correlating these spectral characteristics with field-based ecological assessments. Here we analyze >9400 coral reef field spectra from southwestern Puerto Rico to evaluate how spectral variability and, more specifically, spectral similarity between species influences estimates of biodiversity. Traditional field methods for estimating reef biodiversity using photoquadrats are also included to add ecological context to the spectral analysis. Results show that while many species can be distinguished using in situ field spectra, the addition of the overlying water column significantly reduces the ability to differentiate species, and even groups of species. This indicates that the ability to evaluate biodiversity with remote sensing decreases with increasing water depth. Due to the inherent spectral similarity amongst many species, including taxonomically dissimilar species, remote sensing underestimates biodiversity and represents the lower limit of actual species diversity. OPEN ACCESS J. Mar. Sci. Eng. 2015, 3 2 The overall implication is that coral reef ecologists using remote sensing need to consider the spatial and spectral context of the imagery, and remote sensing scientists analyzing biodiversity need to define confidence limits as a function of both water depth and the scale of information derived, e.g., species, groups of species, or community level.
Article
Full-text available
The objective of this research focused on the utility of QuickBird multispectral data for identifying and classifying tropical-marine benthic habitats after applying atmospheric and water-column corrections for an area around Roatan Island, Honduras. Atmospheric (Rayleigh and aerosol path radiance) and water column corrections (water depth and water column attenuation) were applied to the imagery, making it an effective method for mapping benthic habitats. Water depth for each pixel was calculated based on a linear model by regressing transformed radiance over known homogenous benthos against measured depths. Water column correction was achieved by deriving absorption and backscattering coefficients for each band of the image using a 50 × 50 window of clear water pixels. Corrections for water path radiance and water column attenuation of the bottom reflected radiance were made for the entire scene, allowing the bottom albedo to be determined for shallow coastal areas. An image of the bottom (i.e., an albedo image), minus the water column, was produced. Albedos were 8 percent for seagrass benthos, approximately 8 to 18 percent for coral areas, and 18 percent for sand dominated areas. An unsupervised classification algorithm was applied to the bottom albedo image, generating a classified map of benthic habitats. Accuracy assessment based on 383 reference points revealed an overall accuracy of 81 percent, with an overall Kappa value of 0.774.
Article
Full-text available
An analysis of fish declines in coral reefs shows that simple fishing limits and implementation of marine protected areas can be enough to support recovery of coral ecosystem resilience. See Letter p.341
Article
Full-text available
Object-based classification technique (OBIA) in Landsat image analysis is assumed to be able to increase classification accuracy result compared with a pixel-based classification technique. Most of the previous research was conducted using conventional (pixel-based) classification technique such as maximum likelihood algorithm. The objective of this research was to determine accuracy values of coral reef habitat classification based on OBIA algorithms such as Support Vector Machine (SVM), Random Tree, Decision Tree (DT), Bayesian, and k-Nearest Neighbour (KNN). The Landsat 8 OLI satellite imagery acquired on 17 October 2013 on coral reef area in Morotai island, North Maluku Province, Indonesia was analysed in this study. Field data was obtained in October 2012 using transect photo technique. The field data was then classified employing OBIA classification within 7 (seven) classes i.e., sand-rubble, rubble, coral, sand, sand-algae, seagrass, and rubble-sand. Results showed that the highest values of overall accuracy and Kappa on coral reef habitat mapping was produced by SVM algorithm which reached 73% and 0.64 followed by RT, KNN, Bayesian, and DT algorithms of 68% and 0.59, 67% and 0.56, 66% and 0.53, and 56% and 0.46, respectively. Those results showed that the classification methods based OBIA approach within > 6 classes produced better accuracy than the pixel based classification technique.
Article
It is clear that the learning speed of feedforward neural networks is in general far slower than required and it has been a major bottleneck in their applications for past decades. Two key reasons behind may be: (1) the slow gradient-based learning algorithms are extensively used to train neural networks, and (2) all the parameters of the networks are tuned iteratively by using such learning algorithms. Unlike these conventional implementations, this paper proposes a new learning algorithm called extreme learning machine (ELM) for single-hidden layer feedforward neural networks (SLFNs) which randomly chooses hidden nodes and analytically determines the output weights of SLFNs. In theory, this algorithm tends to provide good generalization performance at extremely fast learning speed. The experimental results based on a few artificial and real benchmark function approximation and classification problems including very large complex applications show that the new algorithm can produce good generalization performance in most cases and can learn thousands of times faster than conventional popular learning algorithms for feedforward neural networks.1
Book
Remote sensing stands as the defining technology in our ability to monitor coral reefs, as well as their biophysical properties and associated processes, at regional to global scales. With overwhelming evidence that much of Earth’s reefs are in decline, our need for large-scale, repeatable assessments of reefs has never been so great. Fortunately, the last two decades have seen a rapid expansion in the ability for remote sensing to map and monitor the coral reef ecosystem, its overlying water column, and surrounding environment. Remote sensing is now a fundamental tool for the mapping, monitoring and management of coral reef ecosystems. Remote sensing offers repeatable, quantitative assessments of habitat and environmental characteristics over spatially extensive areas. As the multi-disciplinary field of coral reef remote sensing continues to mature, results demonstrate that the techniques and capabilities continue to improve. New developments allow reef assessments and mapping to be performed with higher accuracy, across greater spatial areas, and with greater temporal frequency. The increased level of information that remote sensing now makes available also allows more complex scientific questions to be addressed. As defined for this book, remote sensing includes the vast array of geospatial data collected from land, water, ship, airborne and satellite platforms. The book is organized by technology, including: visible and infrared sensing using photographic, multispectral and hyperspectral instruments; active sensing using light detection and ranging (LiDAR); acoustic sensing using ship, autonomous underwater vehicle (AUV) and in-water platforms; and thermal and radar instruments. Emphasis and Audience This book serves multiple roles. It offers an overview of the current state-of-the-art technologies for reef mapping, provides detailed technical information for coral reef remote sensing specialists, imparts insight on the scientific questions that can be tackled using this technology, and also includes a foundation for those new to reef remote sensing. The individual sections of the book include introductory overviews of four main types of remotely sensed data used to study coral reefs, followed by specific examples demonstrating practical applications of the different technologies being discussed. Guidelines for selecting the most appropriate sensor for particular applications are provided, including an overview of how to utilize remote sensing data as an effective tool in science and management. The text is richly illustrated with examples of each sensing technology applied to a range of scientific, monitoring and management questions in reefs around the world. As such, the book is broadly accessible to a general audience, as well as students, managers, remote sensing specialists and anyone else working with coral reef ecosystems.
Book
Swarm Intelligence and bio-inspired computation have become increasing popular in the last two decades. Bio-inspired algorithms such as ant colony algorithms, bat algorithms, bee algorithms, firefly algorithms, cuckoo search and particle swarm optimization have been applied in almost every area of science and engineering with a dramatic increase of number of relevant publications. This book reviews the latest developments in swarm intelligence and bio-inspired computation from both the theory and application side, providing a complete resource that analyzes and discusses the latest and future trends in research directions. It can help new researchers to carry out timely research and inspire readers to develop new algorithms. With its impressive breadth and depth, this book will be useful for advanced undergraduate students, PhD students and lecturers in computer science, engineering and science as well as researchers and engineers. Focuses on the introduction and analysis of key algorithms Includes case studies for real-world applications Contains a balance of theory and applications, so readers who are interested in either algorithm or applications will all benefit from this timely book.
Article
Half Title Series Information Title Copyright Dedication Contents Preface
Chapter
A fuzzy logic algorithm was used to model coral bleaching events around Magnetic Island, North Queensland, Australia. Most events during the 80’s and 90’s did not coincide with the strong ENSO (El-Niño Southern Oscillation) phenomenon. The model uses monthly Air Temperature (AT) data obtained from the Townsville Bureau of Meteorology and monthly IGOSS-NMC and Geoffrey Bay Sea Surface Temperature (SST) data sets. Four separate model inputs were considered. They were: (a) raw temperature, (b) a temperature for a particular year is taken by subtracting the value of one year before from the value of that year, (c) a temperature for a particular year is taken by subtracting the 2-year running average from the value of that year, and (d) a temperature for a particular year is taken by subtracting the 3-year running average from the value of that year. Using the difference in seawater temperature with that of the previous year as a model input (case b) gave a better fit to bleaching events than using seawater temperature alone. This indicates that some form of acclimatisation may influence the response of corals to some form of bleaching event. It was also found that when the maximum sea temperature in a particular year exceeds 0.37 °C of the previous one year, coral bleaching occurs.
Conference Paper
In this paper we detail a new algorithm for multi-objective optimization, the Multi-Objective Coral Reefs Optimization (MO-CRO) algorithm. The algorithm is based on the simulation of the coral reefs processes, including corals’ reproduction and fight for the space in the reef. The adaptation to multi-objective problems is an easy process based on domination or non-domination during the process of fight for the space in the reef. The final MO-CRO is an easily implementing and fast algorithm, quite simple, but able to keep diversity in the population of corals (solutions) in a natural way. Experiments in different multi-objective benchmark problems have shown the good performance of the proposed approach in cases with limited computational resources, where we have compared it with the well known NSGA-II algorithm as reference.
Chapter
Coral reefs are the most diverse marine ecosystems, at least on a per-area basis if not overall, with perhaps millions of species. They are also among the most threatened ecosystems. Outbreaks of coral eaters, smothering by seaweed, coral bleaching, and coral disease have all decimated reefs globally. The underlying anthropogenic causes are direct destruction, poor water quality, overfishing, introduction of invasive species, and the multiple effects of increasing concentrations of carbon dioxide (CO2) in the atmosphere due to burning of fossil fuels. Successful conservation of coral reefs and their biodiversity will depend on aggressive reduction of local stressors and ultimately on the stabilization and lowering of CO2 emissions.
Chapter
Introduction Effects on Inference Effects on Forecasting Detection of Multicollinearity Centering and Scaling Principal Components Approach Imposing Constraints Searching for Linear Functions of the β's Computations Using Principal Components Bibliographic Notes Exercises Appendix: Principal Components
Book
see website http://www.springer.com/us/book/9780387772417
Chapter
In the history of research of the learning problem one can extract four periods that can be characterized by four bright events: (i) Constructing the first learning machines, (ii) constructing the fundamentals of the theory, (iii) constructing neural networks, (iv) constructing the alternatives to neural networks.
Article
Extreme learning machines (ELMs) basically give answers to two fundamental learning problems: (1) Can fundamentals of learning (i.e., feature learning, clustering, regression and classification) be made without tuning hidden neurons (including biological neurons) even when the output shapes and function modeling of these neurons are unknown? (2) Does there exist unified framework for feedforward neural networks and feature space methods? ELMs that have built some tangible links between machine learning techniques and biological learning mechanisms have recently attracted increasing attention of researchers in widespread research areas. This paper provides an insight into ELMs in three aspects, viz: random neurons, random features and kernels. This paper also shows that in theory ELMs (with the same kernels) tend to outperform support vector machine and its variants in both regression and classification applications with much easier implementation.
Article
Mobile technology is currently one of the main pillars of worldwide economy. The constant evolution that mobile communications have undergone in the last decades, due to the appearance of new services and new technologies such as Universal Mobile Telecommunication Systems/High Speed Data Access and Long Term Evolution, has contributed to achieve this position in global economy. However, because of the crisis of the sector in the last 5years, mobile operator's revenues and investments have been reduced. Thus, mobile network operators tend to exploit the existing infrastructure at maximum possible, trying to use the existing network in the most efficient way. In this paper, a novel bio-inspired algorithm, the coral reef optimization algorithm (CRO) is introduced to minimise a network deployment investment cost problem. This is carried out by means of optimising the user demand of different services offered by mobile operators over the available technologies in the market, namely the optimal service distribution problem. The CRO is a recently proposed meta-heuristic based on the computer simulation of corals reproduction and reefs' formation. In this paper, this algorithm has been tested on several optimal service distribution problem scenarios in Spain, observing a significant reduction (up to 400 MEuro) on the total investment costs associated to the radio access network deployment. We compare the performance of the CRO approach with that of a classical (experience-based) services distribution, and with alternative meta-heuristics techniques, obtaining good results in all cases. Copyright (c) 2013 John Wiley & Sons, Ltd.
Article
Accurate mapping and effective monitoring of benthic habitat in the Florida Keys are critical in developing management strategies for this valuable coral reef ecosystem. For this study, a framework was designed for automated benthic habitat mapping by combining multiple data sources (hyperspectral, aerial photography, and bathymetry data) and four contemporary imagery processing techniques (data fusion, Object-based Image Analysis (OBIA), machine learning, and ensemble analysis). In the framework, 1-m digital aerial photograph was first merged with 17-m hyperspectral imagery and 10-m bathymetry data using a pixel/feature-level fusion strategy. The fused dataset was then preclassified by three machine learning algorithms (Random Forest, Support Vector Machines, and k-Nearest Neighbor). Final object-based habitat maps were produced through ensemble analysis of outcomes from three classifiers. The framework was tested for classifying a group-level (3-class) and code-level (9-class) habitats in a portion of the Florida Keys. Informative and accurate habitat maps were achieved with an overall accuracy of 88.5% and 83.5% for the group-level and code-level classifications, respectively.
Article
Continuing degradation of coral reef ecosystems has generated substantial interest in how management can support reef resilience. Fishing is the primary source of diminished reef function globally, leading to widespread calls for additional marine reserves to recover fish biomass and restore key ecosystem functions. Yet there are no established baselines for determining when these conservation objectives have been met or whether alternative management strategies provide similar ecosystem benefits. Here we establish empirical conservation benchmarks and fish biomass recovery timelines against which coral reefs can be assessed and managed by studying the recovery potential of more than 800 coral reefs along an exploitation gradient. We show that resident reef fish biomass in the absence of fishing (B0) averages ∼1,000 kg ha(-1), and that the vast majority (83%) of fished reefs are missing more than half their expected biomass, with severe consequences for key ecosystem functions such as predation. Given protection from fishing, reef fish biomass has the potential to recover within 35 years on average and less than 60 years when heavily depleted. Notably, alternative fisheries restrictions are largely (64%) successful at maintaining biomass above 50% of B0, sustaining key functions such as herbivory. Our results demonstrate that crucial ecosystem functions can be maintained through a range of fisheries restrictions, allowing coral reef managers to develop recovery plans that meet conservation and livelihood objectives in areas where marine reserves are not socially or politically feasible solutions.