Search Results (119)

Water quality monitoring is a fundamental element of sustainable aquaculture management, as changes in parameters of physicochemical and biological properties directly affect the health, growth performance, and productivity of the aquaculture systems. Although traditional machine learning (ML) methods have demonstrated effectiveness in water quality classification, their performance often depends on large amounts of labeled data, which can be challenging and expensive to collect in real-world aquaculture environments. This study explores a few-shot learning (FSL) framework for data-efficient water quality classification under limited supervision to address this limitation. Several FSL models, including prototypical networks (ProtoNet), Siamese Networks, and Matching Networks were developed and evaluated in a comparative experimental framework against the traditional machine learning classifiers logistic regression, random forest, support vector machine and extreme gradient boosting. Low-data learning scenarios were simulated using a structured episodic evaluation approach. Experimental results demonstrate FSL techniques outperform traditional machine learning methods across all evaluated scenarios. Among the tested methods, ProtoNet achieved the highest performance, attaining an accuracy of 94.46% and an ROC-AUC score of 98.65%, indicating superior discriminative capability and robustness. Siamese Networks also demonstrated competitive performance under highly constrained data conditions. Furthermore, latent-space visualization, confusion matrix analysis, paired t-test statistical analysis, and ablation studies confirmed that episodic meta-learning enables the learning of highly discriminative latent representations with strong generalization capability under limited labeled data conditions. The findings highlight that FSL provides a robust and scalable framework for intelligent water quality classification in aquaculture systems, particularly in scenarios where labeled data are scarce, offering significant potential for sustainable aquaculture monitoring applications. Full article

Woody breast (WB) myopathy is a major quality defect in modern broiler production, but its complex and heterogeneous pathophysiology continues to challenge objective and biologically meaningful detection. This review synthesizes 53 studies identified through a systematic search (January 2020 to May 2026), together with foundational pre-window works cited for context, organized across three main areas: physical and mechanical measurements, biochemical and physiological indicators, and imaging- and artificial intelligence-based approaches. Physical methods provide relatively interpretable measures of tissue properties, including stiffness, electrical behavior, and water mobility. Biochemical and physiological approaches offer greater insight into the mechanisms underlying WB development and may support earlier prediction, although their routine application remains limited. Imaging and AI-based methods appear to be the most scalable options for automated assessment, but their performance is still constrained by limited datasets and imperfect reference standards. Overall, no single modality fully captures the structural, functional, and metabolic complexity of WB. Future advances will require improved quantitative reference frameworks, more robust validation under commercial conditions, and multimodal strategies that better integrate biological relevance with practical applicability. Full article

Water quality monitoring remains a critical challenge for achieving Sustainable Development Goal 6, particularly in rural and resource-constrained environments where conventional laboratory-based methods are costly and slow. This study presents the development and field validation of an Artificial Intelligence of Things (AIoT) ecosystem for intelligent, low-cost, and real-time water quality assessment using edge computing and generative artificial intelligence. The system integrates a laboratory-developed multiparameter probe measuring temperature, pH, dissolved oxygen, and electrical conductivity with a mobile application and a cloud-based backend. Field validation was conducted in riverine environments in the municipality of Pueblo Bello (Cesar, Colombia), where the system was deployed for in situ data acquisition and real-time inference. A supervised Artificial Neural Network (ANN) was trained to classify water quality based on a Water Quality Index (WQI) ground truth derived from a public dataset, employing KNN-based missing data imputation, interquartile range outlier filtering, stratified balancing, and grid search hyperparameter optimization. The best-performing model achieved 85.1% accuracy and an AUC of 0.87 using only four physical parameters and was successfully deployed in TensorFlow Lite format on both the embedded probe and the mobile application with sub-millisecond inference time. Integration with a generative AI backend provides contextual natural-language interpretations of measurements. These results demonstrate that reduced-parameter edge AI systems can provide reliable environmental diagnostics while enhancing accessibility and citizen engagement for participatory water monitoring. Full article

Water pollution poses significant risks to human health and environmental sustainability, highlighting the need for accurate water quality assessment and prediction. This review examines the application of machine learning (ML) in Water Quality Index (WQI) assessments, focusing on WQI formulation, predictive modelling approaches, and explainable artificial intelligence (XAI) techniques. A structured literature review is conducted using major scientific databases, including ScienceDirect, Springer, and other relevant sources, following a systematic study selection process. The review analyzes commonly used water quality parameters and highlights how the deterministic structure of WQI influences machine learning modelling, often leading to high predictive performance that reflects predefined formulations rather than independent pattern learning. A comprehensive comparison of single, hybrid, and ensemble ML models is presented, showing that hybrid approaches generally provide improved robustness and accuracy in complex water quality scenarios. In addition, the role of XAI methods in enhancing model interpretability and supporting transparent decision-making is discussed. Key challenges, including limited generalization, model complexity, and interpretability constraints, are identified, and future research directions are proposed to develop more reliable and practical AI-based water quality monitoring systems. Overall, this review provides insights into the integration of machine learning and WQI, emphasizing the importance of balancing predictive accuracy with interpretability for sustainable water resource management. Full article

Freshwater ecosystems are increasingly affected by eutrophication, sediment loading, and other anthropogenic pressures, creating a growing need for monitoring frameworks that are spatially extensive, temporally consistent, and methodologically robust. Although in situ sampling remains essential, its limited spatial coverage and operational constraints have accelerated the use of satellite remote sensing combined with artificial intelligence (AI) and machine learning (ML) for water quality assessment. This review critically examines recent studies published between 2020 and March 2026 on the estimation of physicochemical water quality parameters in lakes and rivers using remote sensing, with particular attention to the methodological structure of image processing workflows rather than performance metrics alone. The synthesis shows that predictive performance is strongly conditioned by three interrelated stages: atmospheric correction (AC), spectral feature construction, and validation design. Across the reviewed studies, substantial variation is observed in atmospheric correction processors, spectral engineering strategies, and model architectures, leading to differences in the spectral inputs and analytical conditions used for model development. Validation approaches remain highly heterogeneous and often rely on internal data splits without geographically independent testing, which weakens claims of model generalizability. In addition, few studies explicitly distinguish algorithmic, matchup, and preprocessing uncertainties, revealing a persistent gap in uncertainty reporting. Overall, the review suggests that improvements attributed to newer ML models may partly reflect upstream preprocessing choices rather than algorithmic superiority alone. Future research should prioritize transparent reporting of atmospheric correction pipelines, structured uncertainty decomposition, standardized validation protocols, and cross-site transferability assessments. By synthesizing these methodological patterns, this review provides a consolidated methodological synthesis that supports improved reproducibility, comparability, and operational reliability of remote-sensing-based freshwater quality monitoring. Full article

The recirculating aquaculture system (RAS) marks a significant shift in global aquaculture, transitioning to controlled, land-based production. This review highlights technological advancements that enable the treatment and reuse of over 90% of water, thereby enhancing water quality and production efficiency. These features position RAS as a cornerstone of sustainable seafood production. This review introduces the RAS Readiness Level (RRL) framework which is a novel, structured approach to assess the commercial maturity of emerging RAS technologies. Applying the RRL to six key technological domains (from digital AI systems to biological PHB recovery) reveals a pervasive pilot-scale purgatory where most innovations stagnate at RRL 4–6. It further addresses advanced processes such as membrane bioreactors, denitrification reactors, and the conversion of waste into valuable products. Furthermore, this review addresses persistent challenges, including high energy demand, economic viability, and the accumulation of pathogens. Finally, it focuses on the emergent integration of the Internet of Things (IoT) and artificial intelligence (AI), which are revolutionizing RAS management through data-driven optimization. By synthesizing current innovations, this review envisions a future of intelligent, closed-loop RAS where advanced IoT- and AI-driven technologies optimize water quality and feeding strategies to minimize ecological impact while enhancing sustainability and productivity. Full article

In this study, a low-cost AS7265x-based multispectral electronic tongue system was developed for estimating milk composition and adulteration indicators and supported with an explainable artificial intelligence (XAI) framework. Experimental analyses were conducted on 190 augmented commercial milk samples, where fat, protein, solids-not-fat (SNF), density, freezing point, and added water ratio were treated as target variables. Sensor data were modeled as RAW, DERIVED, and FUSION feature sets, and regression performance was compared using Random Forest, Gradient Boosting, AdaBoost, KNN, and XGBoost. Model validation was carried out with both five-fold cross-validation and Leave-One-Out (LOO) strategies to assess field-level generalizability. Results showed that a narrow-band, low-cost optical sensor platform can estimate not only fat and protein but also SNF, density, and freezing point with high accuracy. Within the XAI framework, permutation-based importance analysis and SHAP were used to identify critical spectral bands for each target parameter, enabling data-driven recommendations for band-oriented sensor design optimization. The study presents a scalable methodology that integrates low-cost sensor design, multi-parameter quality estimation, and explainable modeling beyond traditional fat–protein-focused approaches. Across all six targets, the XAI analysis consistently identified the near-infrared channel at 860 nm (asIR_3) as the most informative band, reflecting the combined effect of water absorption and Mie scattering by fat globules; the visible channel at 680 nm (asVIS_4) emerged as a secondary band, reflecting dissolved-matter scattering. These bands are therefore the natural starting point for cost-reduced versions of the sensor. Among the compared feature sets (RAW, DERIVED, FUSION), the 18-band RAW configuration provided the most balanced performance across all six targets. Full article

Safe and sustainable water sources are a serious global concern because of growing population, urbanization, industrialization, and climate change. The conventional water surveillance systems that rely on periodic sampling and laboratory analysis fail to provide time-sensitive and high-resolution data utilized for proactive water management. Artificial Intelligence of Things (AIoT) offers a viable solution, as they can provide tools of constant active monitoring and predictive analytics. The integration of IoT sensor networks with machine learning (ML) methods enables real-time data-driven water resource monitoring and intelligent decision-making, enhances water quality assessment, supports early detection of anomalies, improves predictive capabilities for floods and droughts, and facilitates efficient irrigation and reservoir management, ultimately leading to sustainable and resilient water management systems. The paper presents an extensive overview of AIoT solutions for water quality monitoring and water resource management, including IoT sensor networks for real-time data acquisition, machine learning methods for prediction, classification, anomaly detection, and edge computing platforms for data processing and decision support. This study also highlights existing possibilities, obstacles, and research gaps identified through a review of the recent literature. Key challenges reported across multiple studies include limited data availability, sensor calibration bias, integration of heterogeneous data, and insufficient model interpretability. Advanced paradigms such as digital twin systems, TinyML, federated learning, and explainable AI (XAI) are examined as enabling technologies to enhance system efficiency, flexibility, and transparency. Future research directions are outlined to develop scalable, interpretable, and real-time water management solutions. Full article

Medium voltage induction motors (MVIM) are a key component of numerous industries, such as water treatment plants, sewage discharge stations, and chilled water systems. The starting process for these MV motors is critical as it is associated with a major impact on both motor lifetime and power grid quality. In this article, a proposed modified and comprehensive starting scheme of MV three-phase induction motors driving pumps for water stations is introduced. Firstly, the starting performance and its impact on power grid quality will be discussed when all motors are normally started with direct on line connection (DOL), which is already the normal established status. A modified starting scheme based on an optimized coordination of motor starting methods in addition to variable voltage variable frequency drive (VVVFD) drive and control implementation will be discussed. A transition between the starting of variant MV induction motors as well as the starting event coordination principle will be discussed to improve the power quality relative to the obligatory time shift required for the operation. The coordination is based on an algorithm implementation which is achieved using different optimization concepts based on artificial intelligence techniques, properly conducting the transition time in addition to the power delivered by the inverter unit rather than determining the number of DOL and VVVF-implemented motors. A comparison between using the optimized VVVFD soft-starting and the proposed modified scheme is performed, focusing on the power quality improvement rather than optimizing the cost function. The modified scheme is simulated using ETAP power station for brief analysis and study of load flow rather than the complete inspection and power quality assessment. Full article

Transitional water ecosystems exhibit pronounced spatio-temporal variability and increasing anthropogenic pressures, posing substantial challenges for ecological monitoring and management. Artificial Intelligence (AI), particularly Machine Learning (ML) and Deep Learning (DL), has emerged as a powerful framework for addressing the structural complexity of these systems. This systematic review synthesizes peer-reviewed studies applying ML and DL to ecological research and monitoring in transitional waters. A structured search of the Scopus^® database was conducted up to 31 December 2024, and studies were screened according to predefined eligibility criteria and PRISMA 2020 guidance; methodological quality was appraised using a structured assessment framework. Ninety-six studies met the inclusion criteria. Regression was the most frequent analytical task (44.1%), followed by classification (36.2%) and clustering (19.7%), with water quality monitoring representing the dominant thematic domain. Tree-based and kernel-based ML models prevailed overall, whereas DL architectures increased markedly after 2020, particularly in remote sensing and high-dimensional applications. Despite methodological heterogeneity and variable validation practices, the evidence indicates that ML and DL approaches effectively accommodate non-linearity, data heterogeneity, and scale mismatches typical of transitional waters. Standardized validation strategies and improved model interpretability remain essential for robust ecological inference and operational implementation. Full article

Water accumulation in goafs in Chinese coal mines is a major hidden hazard that can trigger water inrush accidents and may also affect aquifer integrity and regional water security. Reliable delineation of goaf water distribution and identification of water-source types are therefore essential for mine water-hazard control and groundwater protection. This paper reviews the main technical routes for goaf groundwater investigation, including geophysical prospecting, hydrogeochemical and isotopic identification, direct inspection tools, and data-driven intelligent workflows. For geophysical detection, the mechanisms, engineering applicability, and key constraints of the Transient Electromagnetic Method (TEM), Surface Nuclear Magnetic Resonance (NMR), the High-Density Resistivity Method (HDRM), and the Coherent Frequency Component (CFC) electromagnetic wave reflection coherence method are synthesized, with emphasis on interpretation boundaries and uncertainty sources under complex geological conditions. For source identification, conventional hydrochemistry, stable isotopes, and laser-induced fluorescence are summarized, and intelligent recognition models such as neural networks and support vector machines are discussed in terms of workflow positioning and practical performance limits. A unified evaluation rationale is established and a semi-quantitative method–metric matrix is constructed to compare techniques in terms of reliability, deployability, cost level, environmental adaptability, and information value, thereby clarifying their functional roles and complementarities within staged engineering workflows. The synthesis indicates that major bottlenecks include limited deep capability under strong interference, pronounced interpretational non-uniqueness caused by complex geology and irregular goaf geometries, and constrained timeliness and generalization for mixed-source identification. Future directions are summarized as multi-method integration with fusion-driven interpretation, intelligent and quantitative decision support with quality control, and sensor–platform advances enabling more practical three-dimensional investigation, aiming to improve the reliability and engineering usability of goaf groundwater hazard assessment. Full article

Postharvest dehydration is a major determinant of cucumber freshness and marketability, yet early reductions in internal water status are difficult to detect using conventional quality assessment methods. This study presents a non-destructive, physiology-informed deep learning approach that links cucumber surface color and texture patterns to internal hydration level for automated freshness classification. A time-resolved dataset comprising 4160 RGB images of cucumber fruits was paired with gravimetrically determined relative water content (RWC), used as an objective indicator of internal hydration status. Based on RWC, fruits were classified into four freshness categories: Very Fresh (≥98%), Moderately Fresh (95–98%), Low Freshness (90–95%), and Spoiled (<90%). A custom convolutional neural network (CNN) was trained using standardized RGB images and evaluated on an independent test set. The model achieved an overall classification accuracy of 91.35% and a Cohen’s Kappa coefficient of 0.875, indicating strong agreement between predicted and actual freshness classes. Classification performance was highest for the extreme freshness states, with F1-scores exceeding 0.94 for Very Fresh and Spoiled fruits, while intermediate classes showed greater overlap, reflecting the gradual nature of postharvest water loss. Model interpretability analyses revealed that the CNN consistently focused on physiologically meaningful surface color and texture features associated with dehydration. Overall, these findings highlight the potential of physiology-informed deep learning to advance non-destructive freshness assessment in cucumbers, offering a realistic pathway toward hydration-based sorting, improved shelf-life management, and intelligent quality monitoring in modern postharvest supply chains. Full article

This survey is an integrated and complete summary of the strategies and technological systems of surveying environmental hazard in marine, freshwater, and brackish environments. Contrary to the previous articles where the separate parts of the monitoring chain are investigated or certain environments/enabling technologies are considered, the given work has a cross-domain approach that unites sensing modalities, data acquisition schemes, communication schemes, operational platforms, data analytics, energy management schemes, and regulatory compliance into one consistent framework. The survey systematically examines the entire sensing-to-cloud pipeline, which includes sensor technologies, data acquisition systems, telecommunication infrastructures, and a variety of monitoring platforms such as buoy-based systems, Unmanned Surface Vehicles (USVs), Autonomous Underwater Vehicles (AUVs), and Unmanned Aerial Vehicles (UAVs). In addition, it touches on the administration and examination of mass environmental data, including cloud-based systems and AI-based methods of automated feature identification, anomaly recognition and predictive modeling. The key points of the autonomy of the system, including power supply solutions and energy-conscious management, are also mentioned, as well as the relevant regulations on the environmental monitoring nationally, at the European level, and globally. This paper presents a systematic six-step design process of aquatic environmental monitoring systems: (1) risk categorization, (2) physical data acquisition systems, (3) monitoring platforms, (4) data management & analytics, (5) energy autonomy strategies, and (6) regulatory compliance. The systematic framework offers researchers and practitioners practical guidelines to follow when designing end-to-end systems, thus completing the gaps in the historically disjointed research strands and going beyond the traditional domain- and technology-based studies. Full article

This systematic review analyzes the evolution of Machine Learning and Big Data applications in agriculture from 2021 to 2025, with particular emphasis on how recent technological advances facilitate the transition from precision agriculture to Intelligent Agricultural Ecosystems. A comprehensive literature search was conducted across Scopus, Web of Science, IEEE Xplore, the ACM Digital Library, SpringerLink, and MDPI, following the PRISMA 2020 guidelines. After duplicate removal and a two-stage screening process (title/abstract screening followed by full-text assessment), eligible peer-reviewed studies were systematically extracted using a structured coding matrix encompassing six analytical domains: crops, soil, weather and water, land use, animal systems, and farmer decision-making. The findings reveal a substantial increase in ML-driven agricultural analytics. Although Random Forest and Convolutional Neural Networks remain widely adopted, recent studies demonstrate a marked shift toward advanced Deep Learning architectures, integrated cloud–edge–device infrastructures, Federated Learning frameworks for privacy-preserving collaboration, Explainable AI techniques to enhance transparency, and governance-oriented mechanisms to ensure interoperability. Notwithstanding these advances, several persistent challenges remain, including limited generalizability across diverse agroclimatic contexts, the high costs associated with high-quality data annotation, the integration of heterogeneous and multimodal datasets, and infrastructural constraints related to connectivity. These developments are synthesized within the IAE conceptual framework, underscoring governance- and lifecycle-aware orchestration MLOps as a critical differentiator that transcends purely technology-centric approaches. Full article

Biopolymers from renewable sources are increasingly explored to reduce the carbon footprint of materials and mitigate plastic pollution. This review synthesizes the last five years of progress across the biopolymer value chain, comparing plant, microbial/fermentation, fungal, and marine/algal resources and critically assessing greener extraction and fractionation routes (ultrasound and microwave intensification, subcritical water, supercritical CO₂ with co-solvents, ionic liquids, deep eutectic solvents including natural deep eutectic solvents, and enzymatic or bio-mediated processes). We emphasize yield-selectivity trade-offs, scalability, energy demand, and solvent recovery. Downstream, we summarize purification and performance tuning via crosslinking, derivatization, blending/plasticization, and nanocomposites, and we map advanced characterization to targeted functional properties to bridge processing choices with end-use performance. Applications are organized across food and agriculture, biomedical and pharmaceutical technologies, packaging, and cosmetics, with cross-cutting attention to safety and regulatory compliance, quality-by-design, techno-economics, and life-cycle assessment. Key bottlenecks are feedstock variability, viscosity and recyclability limitations of designer solvents, and persistent gaps in barrier and thermal properties versus petrochemical benchmarks, compounded by uneven composting and recycling infrastructure. Promising directions include low-viscosity or switchable solvents, data- and artificial intelligence (AI)-guided process optimization, engineered biopolymers, and circular end-of-life strategies that align material design with realistic recovery routes. Full article