Search Results (130)

Habitat complexity plays a critical role in coral reef ecosystems by enhancing habitat availability, increasing ecological resilience, and offering coastal protection. Structure-from-motion (SfM) photogrammetry has become a standard approach for quantifying habitat complexity in reef monitoring programs. However, a major bottleneck remains in the two-dimensional (2D) classification of benthic cover in three-dimensional (3D) models, where experts are required to manually annotate individual colonies and identify coral species or taxonomic groups. With recent advances in deep learning and computer vision, automated classification of benthic habitats is possible. While some semi-automated tools exist, they are often limited in scope or do not provide semantic segmentation. In this investigation, we trained a convolutional neural network with the ResNet101 architecture on three years (2015, 2017, and 2019) of human-annotated 2D orthomosaics from Kiritimati, Kiribati. Our model accuracy ranged from 71% to 95%, with an overall accuracy of 84% and a mean intersection of union of 0.82, despite highly imbalanced training data, and it demonstrated successful generalizability when applied to new, untrained 2023 plots. Successful automation depends on training data that captures local ecological variation. As coral monitoring efforts move toward standardized workflows, locally developed models will be key to achieving fully automated, high-resolution classification of benthic communities across diverse reef environments. Full article

This study proposes a lightweight classification framework for anomaly traffic detection in edge computing environments. Thirteen packet- and flow-level features extracted from the CIC-IDS2017 dataset were compressed into 4-dimensional latent vectors using a Sparse Autoencoder (SAE). Two classifiers were compared under the same pipeline: a Feed-Forward network (SAE-FF) and a Deep Neural Network (SAE-DNN). To ensure generalization, all experiments were conducted with 5-fold cross-validation. Performance evaluation revealed that SAE-DNN achieved superior classification performance, with an average accuracy of 99.33% and an AUC of 0.9993. The SAE-FF model, although exhibiting lower performance (average accuracy of 93.66% and AUC of 0.9758), maintained stable outcomes and offered significantly lower computational complexity (~40 FLOPs) compared with SAE-DNN (~8960 FLOPs). Device-level analysis confirmed that SAE-FF was the most efficient option for resource-constrained platforms such as Raspberry Pi 4, whereas SAE-DNN achieved real-time inference capability on the Coral Dev Board by leveraging Edge TPU acceleration. To quantify this trade-off between accuracy and efficiency, we introduce the Edge Performance Efficiency Score (EPES), a composite metric that integrates accuracy, latency, memory usage, FLOPs, and CPU performance into a single score. The proposed EPES provides a practical and comprehensive benchmark for balancing accuracy and efficiency and supporting device-specific model selection in practical edge deployments. These findings highlight the importance of system-aware evaluation and demonstrate that EPES can serve as a valuable guideline for efficient anomaly traffic classification in resource-limited environments. Full article

Accurate and rapid detection of Plasmodium falciparum parasites in blood smears is critical for the timely diagnosis and treatment of malaria, particularly in resource-constrained field settings. This paper presents a proof-of-concept solution demonstrating the feasibility of the Google Coral Edge Tensor Processing Unit (TPU) for real-time screening of thin blood smears for P. falciparum infection. We develop and deploy a lightweight deep learning model optimized for edge inference using transfer learning and training data supplied by the NIH. This model is capable of detecting individual parasitized red blood cells (RBCs) with high sensitivity and specificity. In a final deployment, the system will integrate a portable digital microscope and low-power color display with the Coral TPU to perform on-site image capture and classification without reliance on cloud connectivity. We detail the model training process using a curated dataset of annotated smear images, potential future hardware integration for field deployment, and performance benchmarks. Initial tests show that the Coral TPU-based solution achieves an accuracy of 92% in detecting P. falciparum parasites in thin-smear microscopy images, with processing times under 50 ms per identified RBC. This work illustrates the potential of edge AI devices to transform malaria diagnostics in low-resource settings through efficient, affordable, and scalable screening tools. Full article

Microplastics pose a growing environmental concern, necessitating accurate and scalable methods for their detection and classification. This study presents a novel deep learning framework that integrates a transformer-based architecture with domain adaptation techniques to classify microplastics using reflectance micro-FTIR spectroscopy. A key challenge addressed in this work is the domain shift between laboratory-prepared reference spectra and environmentally sourced spectra, which can significantly degrade model performance. To overcome this, three domain-adaptation strategies—Domain Adversarial Neural Networks (DANN), Deep Subdomain-Adaptation Networks (DSAN), and Deep CORAL—were evaluated for their ability to enhance cross-domain generalization. Experimental results show that while DANN was unstable, DSAN and Deep CORAL improved target domain accuracy. Deep CORAL achieved 99% accuracy on the source and 94% on the target, offering balanced performance. DSAN reached 95% on the target but reduced source accuracy. Overall, statistical alignment methods outperformed adversarial approaches in transformer-based spectral adaptation. The proposed model was integrated into a reflectance micro-FTIR workflow, accurately identifying PE and PP microplastics from unlabelled spectra. Predictions closely matched expert-validated results, demonstrating practical applicability. This first use of a domain-adaptive transformer in microplastics spectroscopy sets a benchmark for high-throughput, cross-domain analysis. Future work will extend to more polymers and enhance model efficiency for field use. Full article

Corals exhibit complex and diverse relationships with dinoflagellates of the family Symbiodiniaceae. Montiporid corals within Norfolk Island’s shallow water lagoonal reef systems have been observed to turn a deep fluorescent blue during winter, suggesting potential environmentally driven changes to their photoendosymbiosis. Here, we investigate the photoendosymbiosis of blue Montipora sp. corals over a year-long study, demonstrating that photosynthetic yield and Symbiodiniaceae densities vary seasonally, with the lowest photosynthetic yield occurring within winter periods. We also provide the first characterisation of Symbiodiniaceae species associated with corals from Norfolk Island, identifying blue Montipora sp. as predominantly associating with Cladocopium (formerly Clade C) genotypes (C3aap, C3ig, and C3aao). Finally, we also report on the impact of recent bleaching conditions (March 2024) on blue Montipora sp. photoendosymbiosis and find the genera is susceptible to increasing sea surface temperatures. Our findings provide insight into the unique biology of subtropical corals within this remote reef and the susceptibility of corals in the region to increasing sea surface temperatures. Full article

With the rising adoption of machine learning (ML) and deep learning (DL) applications, the demand for deploying these algorithms closer to sensors has grown significantly, particularly in sensor-driven use cases such as predictive maintenance (PM) and condition monitoring (CM). This study investigated a novel application-oriented approach to representing interpretable ML inference as deep neural networks (DNNs) regarding the latency and energy efficiency on the edge, to tackle the problem of inefficient, high-effort, and uninterpretable-implementation ML algorithms. For this purpose, the interpretable deep neural network representation (IDNNRep) was integrated into an open-source interpretable ML toolbox to demonstrate the inference time and energy efficiency improvements. The goal of this work was to enable the utilization of generic artificial intelligence (AI) accelerators for interpretable ML algorithms to achieve efficient inference on edge hardware in smart sensor applications. This novel approach was applied to one regression and one classification task from the field of PM and validated by implementing the inference on the neural processing unit (NPU) of the QXSP-ML81 Single-Board Computer and the tensor processing unit (TPU) of the Google Coral. Different quantization levels of the implementation were tested against common Python and C++ implementations. The novel implementation reduced the inference time by up to 80% and the mean energy consumption by up to 76% at the lowest precision with only a 0.4% loss of accuracy compared to the C++ implementation. With the successful utilization of generic AI accelerators, the performance was further improved with a 94% reduction for both the inference time and the mean energy consumption. Full article

This paper presents WaveCORAL-DCCA, an unsupervised domain adaptation (UDA) framework specifically developed to address data distribution shifts and operational variabilities (OVs) in rotor fault diagnosis. The framework introduces the novel integration of discrete wavelet transformation for robust time–frequency feature extraction and an enhanced deep canonical correlation analysis (DCCA) network with correlation alignment (CORAL) loss for superior domain-invariant representation learning. This combination enables more effective alignment of source and target feature distributions without requiring any labelled data from the target domain. Comprehensive validation on both experimental and numerically simulated rotor datasets across three health conditions—i.e., normal, unbalanced, and misaligned—demonstrates that WaveCORAL-DCCA achieves an average diagnostic accuracy of 95%. Notably, it outperforms established UDA benchmarks by at least 5–17% in cross-domain scenarios. These results confirm that WaveCORAL-DCCA provides robust generalisation across machines, fault severities, and operational conditions, even with scarce target domain samples, offering a scalable and practical solution for industrial rotor fault diagnosis. Full article

Cold-water soft corals are a known habitat for juvenile basket stars (Gorgonocephalus sp.), but the role of this relationship in the earliest life stages of basket stars warrants further investigation. Here, basket stars and colonies of the soft coral Gersemia rubiformis were collected together from the Funk Island Deep Marine Refuge (NW Atlantic) and maintained in a laboratory setting for observation. During this time, two developing (<1 mm disc diameter) basket stars were discovered on coral colonies and could be seen retracting with the coral polyp into the colony. The basket stars were recorded unharmed once the polyps were expanded again and continued to retract within the colony over the period of observation. The results of this study show that developing basket stars can spend time inside the coral colony, which could be a form of protection. Full article

Hydrogen energy is a pivotal carrier for achieving carbon neutrality, requiring green and efficient production via water electrolysis. However, the anodic oxygen evolution reaction (OER) involves a sluggish four-electron transfer process, resulting in high overpotentials, while the prohibitive cost and complex preparation of precious metal catalysts impede large-scale commercialization. In this study, we develop a FeCo-based bimetallic deep eutectic solvent (FeCo-DES) as a multifunctional reaction medium for engineering a three-dimensional (3D) coral-like FeOOH-Co₂(OH)₃Cl/NF composite via a mild one-step impregnation approach (70 °C, ambient pressure). The FeCo-DES simultaneously serves as the solvent, metal source, and redox agent, driving the controlled in situ assembly of FeOOH-Co₂(OH)₃Cl hybrids on Ni(OH)₂/NiOOH-coated nickel foam (NF). This hierarchical architecture induces synergistic enhancement through geometric structural effects combined with multi-component electronic interactions. Consequently, the FeOOH-Co₂(OH)₃Cl/NF catalyst achieves a remarkably low overpotential of 197 mV at 100 mA cm⁻² and a Tafel slope of 65.9 mV dec⁻¹, along with 98% current retention over 24 h chronopotentiometry. This study pioneers a DES-mediated strategy for designing robust composite catalysts, establishing a scalable blueprint for high-performance and low-cost OER systems. Full article

This paper systematically reviews the progress of remote-sensing technology in coastal-ecosystem health assessment. Coastal ecosystems, as transitional zones between land and ocean, play vital roles in maintaining biodiversity, carbon sequestration, and coastal protection, but currently face severe challenges from climate change and human activities. Remote-sensing technology, with its capability for large-scale, long time-series observations, has become a key tool for coastal-ecosystem health assessment. This paper analyzes the technical characteristics and advantages of optical remote sensing, radar remote sensing, and multi-source data fusion in coastal monitoring; constructs a health-assessment framework that includes water-quality indicators, vegetation and ecosystem function indicators, and human disturbance and landscape change indicators; discusses the application of advanced technologies from traditional methods to machine learning and deep learning in data processing; and demonstrates the role of multi-temporal analysis in revealing coastal-ecosystem change trends through typical case studies of mangroves, salt marshes, and coral reefs. Research indicates that, despite the enormous potential of remote-sensing technology in coastal monitoring, it still faces challenges such as sensor limitations, environmental interference, and data processing and validation. Future development should focus on advanced sensor technology, platform innovation, data-processing method innovation, and multi-source data fusion, while strengthening the effective integration of remote-sensing technology with management practices to provide scientific basis for the protection and sustainable management of coastal ecosystems. Full article

As fundamental geophysical information, the high-precision detection of shallow water bathymetry is critical data support for the utilization of island resources and coral reef protection delimitation. In recent years, the combination of active and passive remote sensing technologies has led to a revolutionary breakthrough in satellite-derived bathymetry (SDB). Optical SDB extracts bathymetry by quantifying light–water–bottom interactions. Therefore, the apparent differences in the reflectance of different bottom types in specific wavelength bands are a core component of SDB. In this study, refined classification was performed for complex seafloor sediment and geomorphic features in coral reef habitats. A multi-model synergistic SDB fusion approach constrained by coral reef habitat classification based on the deep learning framework Mamba was constructed. The dual error of the global single model was suppressed by exploiting sediment and geomorphic partitions, as well as the accuracy complementarity of different models. Based on multispectral remote sensing imagery Sentinel-2 and the Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2) active spaceborne lidar bathymetry data, wide-range and high-accuracy coral reef habitat classification results and bathymetry information were obtained for the Yuya Shoal (0–23 m) and Niihau Island (0–40 m). The results showed that the overall Mean Absolute Errors (MAEs) in the two study areas were 0.2 m and 0.5 m and the Mean Absolute Percentage Errors (MAPEs) were 9.77% and 6.47%, respectively. And R² reached 0.98 in both areas. The estimated error of the SDB fusion strategy based on coral reef habitat classification was reduced by more than 90% compared with classical SDB models and a single machine learning method, thereby improving the capability of SDB in complex geomorphic ocean areas. Full article

Accurately simulating wave breaking is crucial for modeling hydrodynamics over steep coral reef slopes, yet it remains a challenge for Boussinesq-type models like FUNWAVE-TVD. The model’s standard hybrid breaking mechanism, triggered by a fixed free surface elevation-to-depth ratio ($\eta /d>0.8$), often lacks physical sensitivity to local slope and wave conditions prevalent in reef environments and suffers from inaccuracies associated with using η as a direct proxy for wave height (H). This study introduces and validates a novel, enhanced hybrid breaking module within FUNWAVE-TVD, specifically designed to overcome these limitations on steep slopes. The core novelty lies in the synergistic implementation of two key components: (1) replacing the fixed threshold with a dynamic, physically-based criterion derived from the Modified Goda formula (MGO) by Rattanapitikon and Shibayama, which calculates the breaking wave height ($H_b$) based on local depth, slope, and deep-water wavelength; and (2) developing and applying a practical method, using the wave vertical asymmetry relationship proposed by Yu and Li, to dynamically convert the calculated $H_b$ into an equivalent breaking surface elevation threshold (${\eta }_b$). This derived dynamic threshold (${\eta }_b/d$) is then used to trigger the model’s existing switch from Boussinesq to Nonlinear Shallow Water Equations (NSWE), allowing for energy dissipation via shock-capturing while retaining the physical basis of the MGO criterion. The performance of this enhanced module was rigorously evaluated against five laboratory experiments of regular waves breaking on impermeable slopes ranging from mild (1:10) to extremely steep (1:1), contrasting results with the original FUNWAVE-TVD. The modified model demonstrates significantly improved accuracy (model skill increases ranging from 10.16% to 42.49%) compared to the original model for breaking location and wave height prediction on steeper slopes ($m\ge 1:6$). Conversely, tests on the 1:1 slope confirmed the inherent limitations of the MGO criterion itself under surging breaker conditions ($m\ge 1:2.3$), highlighting the applicability range. This work provides a validated methodology for incorporating slope-aware, dynamic breaking criteria effectively into hybrid Boussinesq models, offering a more robust tool for simulating wave processes on steep reef topographies. Full article

The accurate evaluation of rock mass quality and competent roadway-support decision-making requires the rapid and accurate acquisition of the distribution of structural planes in rocks. To address this need, a program was developed that uses deep learning to automatically recognize the structural plane in-borehole images. First, borehole images from 30 mines in China were collected during field tests, and the structural planes in the images were categorized into five types. Second, a deep Coral architecture based on a convolutional neural network (CNN) was established to automatically extract features from the borehole images and classify the structural planes therein. The experimental results indicate that the CNN model classifies the structural planes in the borehole images with an overall accuracy of 86%. Validation tests in field applications demonstrated recognition accuracies ranging from 0.76 to 1.0 compared to manual markings, meeting engineering requirements. Finally, based on the proposed method, an intelligent system to recognize surrounding rock fracture was developed. Engineering application cases are presented and discussed to demonstrate the method and confirm the accuracy of this approach. Compared with traditional classification methods, the proposed method rapidly recognizes and classifies structural planes in borehole images at low cost, with precision, and in a non-destructive and automated manner. Full article

Coral reefs are well known for their diversity and value, providing habitats for a third of marine species within just 0.2% of the ocean. However, these natural habitats face significant threats and degradation, leading to unresolved issues related to coral loss inventory, coral protection, and the implementation of long-term conservation policies. In this study, we examined two decades of changes in coral spatial distribution within the Nha Trang Bay Marine Protected Area (MPA) using remote sensing and machine learning (ML) approaches. We identified various factors contributing to coral reef loss and analyzed the effectiveness of management policies over the past 20 years. By employing the Light Gradient Boosting Machine (LGBM) and Deep Forest (DF) models on Landsat (2002, κ = 0.83, F₁ = 0.85) and Planet (2016, κ = 0.89, F₁ = 0.82; 2024, κ = 0.92, F₁ = 0.86) images, we achieved high confidence in our inventory of coral changes. Our findings revealed that 191.38 hectares of coral disappeared from Nha Trang Bay MPA between 2002 and 2024. The 8-year period from 2016 to 2024 saw a loss of 66.32 hectares, which is in linear approximation to the 125.06 hectares lost during the 14-year period from 2002 to 2016. It is concluded that the key factors contributing to coral loss include land-use dynamics, global warming, and the impact of starfish. To address these challenges, we propose next a modern community-based management paradigm to enhance the conservation of existing coral reefs and protect potential habitats within Nha Trang Bay MPA. Full article

Vibroflotation has proven to be an effective method for treating loose and unevenly graded coral sand foundations formed through hydraulic filling. In this study, a series of model tests were conducted to investigate the effects of particle gradations on the response of coral sand foundation reinforced by vibroflotation. The main focus was on analyzing the changes in excess pore water pressure (EPWP) and horizontal earth pressure. Cone penetration tests (CPTs) were then used to evaluate the effectiveness of vibroflotation. The results indicate that the maximum settlement occurs after the first vibroflotation, with surface settlement significantly increasing as the distance to the vibro-point decreases. The reinforcement range expands radially, and the foundation can achieve a medium or dense state after vibroflotation. During the penetration stage, the EPWP rapidly peaks and increases with depth. Shallow foundations exhibit a higher excess pore pressure ratio compared to deep foundations. Foundations with lower coarse particle content show higher EPWPs compared to those with higher coarse particle content. Lower vibration frequency results in diminished reinforcement effects in foundations with high coarse particle content and increases the difficulty of penetration. Additionally, the residual soil pressure in foundations with high coarse particle content significantly rises after three vibroflotation reinforcements. The increase in strength after reinforcement is more pronounced because the foundation has a greater coarse particle content. The reinforcement effect diminishes with increasing distance from the vibrator. Full article