Effective Mitigation Research Articles

The impact of town planning on direct residential CO2 emissions in rural China

China's commitment to carbon neutrality by 2060 has made decarbonization a key principle for spatial planning (also referred to as urban/city/town planning). Although the mitigation effect of spatial planning in urban areas has been well documented, its significance in rural development has yet to be investigated. This paper addresses this research gap by empirically examining the influence of town planning on rural direct residential CO2 emissions (DRCEs) across 30 provinces in China. Based on various quantitative models, this study not only confirms the significant impact of town planning on rural DRCEs and the moderation effect of plan implementation capacity but also discloses that different dimensions of town planning have disparate roles in rural DRCE reduction. Additionally, regional variations in the mitigation effects of town planning on rural DRCEs were observed. The study also reveals spatial spillover effects, indicating that the influence of town planning on rural DRCEs extends beyond individual areas. Overall, China's experiences demonstrate that well-managed town planning could play an essential role in low-carbon rural revitalization or, otherwise, it may augment rural DRCEs per capita. Consequently, governments should ascribe great importance to low-carbon town planning and allocate sufficient resources to towns, especially those in the central and western regions, so that they can afford professional planning consultation and adequate staffing in plan implementation. Moreover, governments should cooperate to promote knowledge sharing and transferring of low-carbon planning.

Carbon mitigation effect of emission trading product: Perspective from intra-industry carbon leakage

Carbon mitigation within key industries has become a paramount concern in China, yet research focusing on industry-level emissions remains limited despite comprehensive validation of the efficacy of emission trading schemes (ETS) at both enterprise and regional levels. This paper addresses this gap by examining the intra-industry carbon leakage. Firstly, applying multi-period DID method to the industry-level data from 2000 to 2018 in Guangdong province, we empirically find a counterintuitive increase in carbon emissions in the compliance industries despite mitigation efforts by compliance enterprises in the same industries. Secondly, we build a Stackelberg quantity leadership model incorporating ETS and theoretically find that, the intra-industry carbon leakage results in this increased industry-level emissions, notably through the cost crowding-in mechanism. Further theoretical analysis underscores the pivotal role of enhancing ETS coverage ratios for enterprises within compliance industries and bolstering the carbon price mechanism's capacity to accurately reflect enterprises' demand for carbon allowances. Such enhancements are anticipated to effectively mitigate intra-industry carbon leakage and facilitate reductions in industry-level carbon emissions.

Evil and allies: Opportunistic gulls as both spreaders and sentinels of antibiotic‐resistant bacteria in human‐transformed landscapes

Abstract Human‐transformed residuals, especially those derived from human waste (dumps), farmland, and livestock are involved in the emergence of antibiotic‐resistant bacteria (ARB) in the environment. Wildlife can act as vectors of ARB dispersal through different environments, but also as sentinels to detect the early spread and determine ARB sources. The development of integrated monitoring programmes focused on wildlife would help to anticipate the risks of ARB to humans and livestock. We used the yellow‐legged gull (Larus michahellis) as a model species to investigate and monitor the spatial patterns of ARB dispersal across an extensive farmland region located in northeastern Spain (Lleida). By integrating GPS tracking data and ARB clinical testing for 26 individuals within a network analysis framework, we modelled the risk of spatial pathogen spread through faeces during the bacteria‐transmission latency period (16 days after sample collection). Additionally, we created a connectivity network to determine the main sources of ARB in the area, focusing on three main habitats of special risk for infection: dumps, livestock facilities, and irrigation ponds. Seven individuals were infected by Escherichia coli, with one also co‐infected with Listeria monocytogenes and Salmonella spp. Potential pathogen dispersal distances ranged from 1.13 km to 23.13 km from the breeding colony. Our network analyses revealed 54 main nodes (i.e. high‐risk habitats recurrently visited by tracked gulls) and 1182 links among them. Our findings revealed a high degree of connectivity between the breeding area, located in a shallow lake, and nearby dumps, highlighting them as significant contributors to ARB dispersal. Synthesis and applications: The integration of GPS data, pathogen testing and network analyses can shed further light on pathogen dynamics by creating spatial risk maps and identifying ARB sources. In combination with complementary molecular epidemiology techniques within a One Health framework, our approach can emerge as an important tool for monitoring ARB dynamics within highly human‐transformed ecosystems. This may empower managers for the development of targeted ARB monitoring programmes and effective mitigation strategies, ultimately improving both animal and public health.

Detecting active sinkholes through combination of morphometric-cluster assessment and deformation precursors

Sinkhole hazards pose considerable challenges in the west-central region of Texas. This study integrates multisource datasets and innovative techniques to detect early sinkhole development and identify the processes governing their formation. The techniques employed encompass feature extraction, cluster analysis, and deformation process monitoring. Potential sinkholes were initially mapped using high-resolution elevation data, and a circularity index (CI) threshold value of 0.85 was applied to filter out depressions with noncircular shapes. Subsequently, Persistent Scatterer Interferometry (PSInSAR) followed by the Getis-Ord Gi* statistic methods were used to identify statistically significant subsidence clusters with rates of <−2 mm/yr, indicating active sinkhole formation. The findings reveal the following: (1) surface deformation analysis revealed significant subsidence hotspots, particularly in areas underlain by units containing significant sequences of evaporites, which nominally belong to the Clear Fork Group and the Blaine Formation, compared with those dominated by carbonates; (2) potential sinkholes are undergoing displacement up to a rate of −11.31 mm/yr, and (3) extreme groundwater pumping of karst aquifers and the subsequent decline in groundwater levels are found to be the leading causes of the susceptibility of the region to sinkhole hazards. In such cases, the decline of the water table deprives the overlying bedrock of buoyant support provided by the groundwater in the cavity. The bedrock will undergo sagging subsidence under the influence of gravity and eventually form a sinkhole. Extensive oil and gas activity in the study area, including extreme withdrawal rates and the injection of fluids associated with the activity, are other potential causes of the observed sinkhole susceptibility in several parts of the study area. This study underscores the importance of understanding the geologic, hydrologic, and anthropogenic factors driving sinkhole hazards for effective mitigation strategies to protect public safety, infrastructure, and the environment.

The TELCoMB Protocol for High-Sensitivity Detection of ARG-MGE Colocalizations in Complex Microbial Communities.

Understanding the genetic basis of antimicrobial resistance is crucial for developing effective mitigation strategies. One necessary step is to identify the antimicrobial resistance genes (ARGs) within a microbial population, referred to as the resistome, as well as the mobile genetic elements (MGEs) harboring ARGs. Although shotgun metagenomics has been successful in detecting ARGs and MGEs within a microbiome, it is limited by low sensitivity. Enrichment using cRNA biotinylated probes has been applied to address this limitation, enhancing the detection of rare ARGs and MGEs, especially when combined with long-read sequencing. Here, we present the TELCoMB protocol, a Snakemake workflow that elucidates resistome and mobilome composition and diversity and uncovers ARG-MGE colocalizations. The protocol supports both short- and long-read sequencing and does not require enrichment, making it versatile for various genomic data types. TELCoMB generates publication-ready figures and CSV files for comprehensive analysis, improving our understanding of antimicrobial resistance mechanisms and spread. © 2024 The Author(s). Current Protocols published by Wiley Periodicals LLC. Basic Protocol 1: Installing TELCOMB Locally Alternate Protocol: Installing TELCOMB on a SLURM Cluster Basic Protocol 2: Data Preprocessing Basic Protocol 3: Calculation of Resistome Distribution and Composition Basic Protocol 4: Identification of ARG-MGE Colocalizations.

Examining the factors that impact the formation of barite scale in water injection operations: experimental study and quantification of scale formation

Barium sulfate (BaSO4) scale formation in oilfield operations is a significant problem that leads to severe operational challenges, including reduced production efficiency and increased maintenance costs. Understanding the factors that influence BaSO4 scale formation, such as injection rate and temperature, is crucial for developing effective mitigation strategies. In this study, we systematically investigated the effects of injection rate and temperature on BaSO4 scale formation using a series of controlled laboratory experiments. The injection rates varied between 1 and 5 mL/min and temperatures between 25 and 75 °C, simulating realistic field conditions. Our findings indicate that higher injection rates and elevated temperatures significantly increase the amount of BaSO4 scale formed. Specifically, the scale formation increased from 15.2 mg/L at 1 mL/min and 25 °C to 22.3 mg/L at 5 mL/min and the same temperature. Similarly, at a constant injection rate of 3 mL/min, the scale formation increased from 18.1 mg/L at 25 °C to 26.5 mg/L at 75 °C. The study employed Scanning Electron Microscopy (SEM) and X-ray Diffraction (XRD) to analyze the crystal morphology and structure of the formed scales. SEM images revealed a transition from dendritic structures at lower temperatures and slower injection rates to spherical crystals at higher temperatures and faster injection rates. XRD patterns indicated variations in crystallinity and phase purity corresponding to the experimental conditions. Our results align with previous studies that report increased nucleation rates and reduced solubility of BaSO4 at higher temperatures and injection rates. These findings highlight the critical role of controlling operational parameters to mitigate scale formation in oil and gas operations. By optimizing injection rates and temperatures, it is possible to reduce scale deposition, thereby improving production efficiency and reducing maintenance costs. This study provides valuable insights for the development of scale management strategies and underscores the importance of a comprehensive understanding of the physicochemical factors affecting BaSO4 scale formation.

Enhancing aspect category detection in imbalanced online reviews: An integrated approach using Select-SMOTE and LightGBM

Aspect category detection (ACD) is a pivotal subtask within the field of sentiment analysis in natural language processing, aiming to identify implicit aspect category information in online review texts. In real-world scenarios of online review category detection tasks, data imbalance often arises, leading to skewed distributions among distinct review categories. This phenomenon poses substantial challenges for accurately recognizing minority categories through modeling. To address this, we propose a method for detecting imbalanced aspect categories by combining the selective synthetic over-sampling (Select-SMOTE) algorithm with the light gradient boosting machine (LightGBM). Our approach commences with text data representation through features, followed by a strategy involving joint sample partitioning and boundary optimization within the feature space to generate minority class samples. This partitioning strategy aligns generated data more closely with the original distribution, while the boundary optimization module enhances classification performance by eliminating samples near boundaries. Subsequently, the balanced dataset is input to the LGB model, enabling the extraction of aspect category information through parameter optimization and class weight assignment. Finally, our method is evaluated using the SemEval and SentiHood datasets and compared with prevailing sampling methods and classification models. Empirical results manifestly demonstrate the method’s superiority across diverse metrics, reflecting robustness and effective mitigation of imbalanced data challenges in ACD.

Turbulence effects mitigation for twin-photons generated by high order transverse modes

Turbulence presents challenges for free-space light-based protocols. In this work, we investigated the effect of turbulence on the correlations of twin photons prepared in Spontaneous Parametric Down Conversion (SPDC) by a pump beam with different transverse modes. We demonstrate that the strategy of coordinate inversion for mitigating turbulence-induced distortions on transverse coincidence profiles is effective for twin photons generated by HG/LG modes. The conservation of orbital angular momentum in SPDC enables us to encode information in the transverse degrees of freedom of the down-converted photon pairs. This information can have its correlation protected by the coordinate inversion technique against weak turbulence effects in free-space links.

Impact of dyke and vegetation on fluid force and moment reduction under sub and supercritical flow conditions

Flooding is the most common natural disaster throughout the world and requires efficient management. Therefore, the current investigation aimed to explore the impact of a composite defense system comprising dyke and vegetation on flow dynamics and velocity reduction. Experiments were conducted in an open channel setup with an adjustable bed slope and transparent sidewalls, and the vegetation model was replicated as real trees such as Eucalyptus trees. The study involved calculating several parameters, including flow velocity, reduction of fluid force index (RFI%), reduction in moment index (RMI%), and hydrostatic and hydrodynamic forces. These calculations were done by changing the channel bed slope and keeping the flow rate (discharge) constant while considering both subcritical and supercritical flow conditions. Moreover, regression analysis was performed for the prediction of RFI% and RMI% under various flow conditions. Also, statistical analyses were performed to assess the effectiveness of the defense system in reducing fluid force and moment indices. The result of the current investigation indicates that the highest values of RFI% and RMI% under subcritical flow conditions were 79% and 88%, while under supercritical flow conditions they were 94% and 78%, respectively. Moreover, a velocity reduction of 69% was observed under subcritical flow, while 84% was observed under supercritical flow conditions. Under subcritical flow conditions, RFI% and RMI% enhanced by enhancing Froude number (Fr) because of an increase in velocity reduction and hydraulic jump formation. Similar trends were observed under supercritical flow conditions, with effective mitigation of high-velocity flows by the composite system. The finding of current research helps in providing effective techniques for flood management.

Urban Groundwater in the cities of Europe: hidden challenges in a changing climate

In European cities, groundwater remains an issue of significant concern, largely because it is “out of sight and out of mind.” The general public, and even decision-makers, possess only a limited understanding of the state and characteristics of this vital resource. As a consequence, problems related to groundwater quality or changing water tables/piezometric surfaces may persist for years, or even decades, without being adequately addressed-or worse, without being noticed at all before resulting in land subsidence,saltwater intrusion, deep migration of persistent organic contaminants like PFAS (Le monde, 2023) or other irreversible consequences. The urban water cycle is central to ensuring the supply of clean, safe drinking water, effective sanitation, and wellfunctioning drainage systems for millions of residents. The impacts of human activities, such as land use change, excessive water abstraction and mismanagement, and the discharge of wastewater can exert a far greater influence on groundwater systems and hydrogeology than climate change. These activities alter the quantity and quality of both surface and groundwater, raising complex scientific, technical, socio-economic, cultural, and ethical challenges in urban water management. It is important to address the many challenges associated with ensuring water security and safety in cities (Quevauviller et al., 2024), as well as for development of effective climate change mitigation and adaptation strategies for urban areas (IPCC, 2024). Groundwater plays a critical role in the green transition and is an integral component of most climate change mitigation and adaptation strategies (Ingemarsson et al., 2022), and for meeting the increasing demand for freshwater in cities due to accelerating urbanization (United Nations, 2022). Many urbanized areas in Europe already face poor chemical and quantitative status (EEA, 2024; Sentek et al., 2024), and global change including increasing populations and sea level rise pose a tremendous challenge for safe and secure water supply especially in coastal European cities. Open access to digital subsurface data e.g. through the European Geological Data Infrastructure supports societal needs and UN sustainable development goals (Hinsby et al., 2024). This special issue demonstrates some of the important issues that the water supply of European cities are facing in times of increasing competing use of the subsurface (Volckko et al., 2020), projected climate change impacts on the hydrological cycle (Henriksen et al., 2023) and with freshwater now being among the transgressed planetary boundaries (Richardsson et al., 2023). [...]

A global synthesis of nitrous oxide emissions across cotton-planted soils

Globally, acquiring information on region- and crop-specific nitrous oxide (N2O) emissions is vital for establishing effective N2O mitigation strategies. Soil cultivated with cotton (Gossypium hirsutum L.) is an important source of N2O in agricultural production. However, little is known about the magnitudes and main drivers of soil N2O emissions from cotton fields worldwide. In this meta-analysis, we were the first to synthesize 34 peer-reviewed papers (298 observational datasets) to quantify the magnitudes and controlling factors of area-scaled N2O emissions (N2Oarea), direct N2O emission factors (EFd), and yield-scaled N2O emissions (N2Oyield) from the soils of cotton fields and to explore associated potential mitigation strategies. On average, the N2Oarea from global cotton-planted soils was 2.10 kg N ha−1, with a mean EFd of 0.92 %, which is comparable to those reported for cereal crops (e.g., maize, 1.02 %) and the Intergovernmental Panel on Climate Change default value of 1 % for global croplands. The global mean N2Oyield estimated here was 622 g N Mg−1. At the global scale, the variations in all N2O-related indices in the soils of cotton fields were demonstrated to be primarily controlled by climatic conditions (e.g. climate type) and soil properties (e.g., bulk density, pH, C/N or soil texture) rather than by well-recognized management practices (e.g., N fertilization rate). Furthermore, our analysis showed that the application of urease and/or nitrification inhibitors significantly reduced soil N2O emissions while maintaining seed cotton yields. These findings emphasize that cotton production has an obvious climate footprint and provide potential N2O mitigation options for the sustainable intensification of cotton production.

Response of wheat to arbuscular mycorrhizal fungi inoculation and biochar application: Implications for soil carbon sequestration

The sequestration of atmospheric CO₂ in soil is suggested as an effective climate change mitigation strategy. Biochar application shows promise in this regard, while the role of fungi in soil carbon cycling and sequestration is also under investigation. Using a novel high-throughput plant phenomics approach, we explore the impact of arbuscular mycorrhizal fungi (AMF) inoculation and biochar application on wheat growth and soil carbon, guided by one of the leading global carbon credit schemes. Wheat was successfully colonised by AMF, achieving an average root length colonisation of 35.9%. We uncover an indirect fungal-mediated pathway to soil carbon sequestration, with mycorrhizal plants generating more biomass across all soil treatments without yield penalties, suggesting colonised plants deliver more plant derived carbon to the soil, potentially leading to long-term soil carbon gains. Conversely, fungal-driven carbon loss occurred, significantly reducing soil carbon accumulation in unamended soil, but not in biochar-amended soil, suggesting that biochar moderates fungal activity and positively impacts the soil carbon balance. While both biochar and AMF enhance plant growth, their direct effects on soil carbon are complex. Although biochar did not significantly increase soil carbon stocks beyond its own contribution, its ability to regulate fungal activity could play an important role in influencing soil carbon sequestration.

Focal Causal Temporal Convolutional Neural Networks: Advancing IIoT Security with Efficient Detection of Rare Cyber-Attacks

The Industrial Internet of Things (IIoT) deals with vast amounts of data that must be safeguarded against tampering or theft. Identifying rare attacks and addressing data imbalances pose significant challenges in the detection of IIoT cyberattacks. Innovative detection methods are important for effective cybersecurity threat mitigation. While many studies employ resampling methods to tackle these issues, they often face drawbacks such as the use of artificially generated data and increased data volume, which limit their effectiveness. In this paper, we introduce a cutting-edge deep binary neural network known as the focal causal temporal convolutional neural network to address imbalanced data when detecting rare attacks in IIoT. The model addresses imbalanced data challenges by transforming the attack detection into a binary classification task, giving priority to minority attacks through a descending order strategy in the tree-like structure. This approach substantially reduces computational complexity, surpassing existing methods in managing imbalanced data challenges in rare attack detection for IoT security. Evaluation of various datasets, including UNSW-NB15, CICIDS-2017, BoT-IoT, NBaIoT-2018, and TON-IIOT, reveals an accuracy of over 99%, demonstrating the effectiveness of FCTCNNs in detecting attacks and handling imbalanced IoT data with efficiency.

The Changing Hydrology of an Irrigated and Dammed Yangtze River: Streamflow, Extremes, and Lake Hydrodynamics

AbstractUnderstanding the role of anthropogenic activities in the hydrological cycle is critical to support sustainable water management for the Yangtze River Basin (YRB), which experiences extensive dam operation, irrigation and water withdrawal. However, this remains challenging due to insufficient accuracies of existing process‐based models for fully depicting anthropogenic activities as part of the hydrological cycle. To this end, this study enhances a national‐scale coupled land surface‐hydrologic‐hydrodynamic model (CLHMS) with a dynamic irrigation scheme for distinct crops, an extended reservoir operation scheme incorporating both water storage anomalies and water demand anomalies, and a cost‐function‐based approach to link water demands with reservoir operation. The enhanced model is extensively validated against historical streamflow, water storage of 90 reservoirs, and irrigation water withdrawal in the YRB, and the water level and storage of the Poyang Lake (PYL). By setting up controlled experiments in the YRB, we show that the streamflow decreases by 2%–6% due to irrigation and water withdrawal, and manifests an attenuated seasonality due to reservoir operation. At the basin scale, the increasing trend of extreme flood peaks exhibits a reversal under human activities, with the flood mitigation effect of irrigation and water withdrawal accounting for up to 50% of that of reservoir operation. The hydrodynamics of the PYL also exhibits considerable human‐induced alterations, with a 1.79 m‐decrease in the water level at the end of flood season. Our study sheds light on quantifying anthropogenic hydrologic impacts at basin scales, with important implications for understanding the co‐evolution between anthropogenic activities and the hydrological cycle.

Effect of Structure and Wearing Modes on the Protective Performance of Industrial Safety Helmet.

This study aims to explore the effects of helmet structure designs and wearing modes on the protective performance of safety helmets under the impact of falling objects. Four helmet types (no helmet, V-shaped, dome-shaped, and motorcycle helmets) and five wearing modes (left and right tilt by 5 deg, backward tilt by 15 deg, 0 deg without chin strap, 0 deg with chin strap) were included in this study. The axial impact of a concrete block under various impact velocities was simulated. The results indicate that the energy absorption and shock mitigation effects of the foam cushion are superior to those of the suspension system in traditional industrial safety helmets. The structure of the top of V-shaped helmets is designed to withstand greater impact. Regarding the wearing mode, the helmet strap's deflection angle increases stress in the brain tissue and skull, heightens intracranial pressure, and causes pressure diffusion toward the forehead.

The adverse consequences of technostress on strain and turnover intentions among auditors: the mitigating effect of segmentation mindset

The adverse consequences of technostress on strain and turnover intentions among auditors: the mitigating effect of segmentation mindset

Optimization of methylene blue dye degradation using heterogeneous Fenton-like reaction with Fe3O4 nanoparticles/PVDF macrospheres: A response surface methodology approach

Microplastics (MPs) are increasingly recognised for their significant impact on the environment and human health. Understanding MPs is crucial to grasp their widespread presence in various environmental areas. The unique properties of MPs, such as their small size, durability, and potential to adsorb and transport environmental pollutants, underscore the necessity of studying their characteristics. This study aims to investigate the physical and chemical characteristics of polypropylene microplastics (PPMPs) and address the dispersion stability issues associated with them. The PPMPs were characterised using scanning electron microscopy (SEM), revealing a surface structure marked by cracks, fractures, and a rough texture. The PPMPs were observed as irregularly shaped, white particles. Their size distribution spans from 14 to 96 µm, with a mean size of 50.00 µm. Fourier Transform Infrared Spectroscopy (FTIR) confirmed the presence of polypropylene functional groups, specifically identifying characteristic peaks at 2952-2846 cm-1 and 1456 -1376 cm-1, indicating C-H stretching and bending vibrations, respectively, with additional peaks suggesting degradation. The effect of different concentrations of sodium lauryl sulfate (SLS) on PPMPs dispersion indicated that 5% SLS led to superior dispersion of PPMPs, thereby addressing the stability issue. These findings provide comprehensive insights into the physical and chemical attributes of PPMPs and their dispersion stability, offering a foundation for informed environmental assessments and the development of effective mitigation strategies.

Insight into the physical and chemical attributes of polypropylene microplastics

Microplastics (MPs) are increasingly recognised for their significant impact on the environment and human health. Understanding MPs is crucial to grasp their widespread presence in various environmental areas. The unique properties of MPs, such as their small size, durability, and potential to adsorb and transport environmental pollutants, underscore the necessity of studying their characteristics. This study aims to investigate the physical and chemical characteristics of polypropylene microplastics (PPMPs) and address the dispersion stability issues associated with them. The PPMPs were characterised using scanning electron microscopy (SEM), revealing a surface structure marked by cracks, fractures, and a rough texture. The PPMPs were observed as irregularly shaped, white particles. Their size distribution spans from 14 to 96 µm, with a mean size of 50.00 µm. Fourier Transform Infrared Spectroscopy (FTIR) confirmed the presence of polypropylene functional groups, specifically identifying characteristic peaks at 2952-2846 cm-1 and 1456 -1376 cm-1, indicating C-H stretching and bending vibrations, respectively, with additional peaks suggesting degradation. The effect of different concentrations of sodium lauryl sulfate (SLS) on PPMPs dispersion indicated that 5% SLS led to superior dispersion of PPMPs, thereby addressing the stability issue. These findings provide comprehensive insights into the physical and chemical attributes of PPMPs and their dispersion stability, offering a foundation for informed environmental assessments and the development of effective mitigation strategies.

Evaluating the Impact of Artificial Intelligence in Managing Construction Engineering Projects

This study evaluates the impact of utilizing artificial intelligence (AI) in managing construction engineering projects. With the increasing complexity and scale of construction projects, AI offers promising solutions to enhance efficiency, accuracy, and decision-making processes. The study investigates the potential benefits, challenges, and practical applications of AI through detailed case studies. The study employs a mixed-methods approach, combining qualitative and quantitative research methods. Data was collected through literature reviews and case studies where AI had been successfully implemented. The analyses included comparisons between projects that used AI and those that did not. The findings demonstrated significant improvements in project efficiency, cost estimation accuracy, and risk management. For instance, AI-powered systems reduced scheduling errors by 35%, leading to more accurate timelines. Additionally, the integration led to a 20% reduction in project durations due to improved resource allocation and proactive risk management. Furthermore, AI-supported systems contributed to a 25% improvement in stakeholder satisfaction. In terms of cost estimation, AI-powered estimation tools improved the accuracy of cost estimates by 30%, helping to reduce budget overruns by 40%. In risk management, AI-supported tools enhanced the accuracy of risk identification by 45%, leading to the early detection of potential issues and the development of effective mitigation strategies that reduced the impact of risks by 30%. Thanks to these improvements, project success rates increased by 20%. These results demonstrate that integrating AI into the management of engineering construction projects can lead to tangible improvements in project efficiency, cost accuracy, and risk management, thereby enhancing stakeholder satisfaction and contributing to more successful project outcomes.

End-to-end deep learning on classification of neutral-to-ground voltage in secondary distribution systems

Neutral-to-ground voltage (NTGV) abnormalities in secondary distribution systems (SDS) pose significant power quality (PQ) challenges, including safety hazards, power losses, and equipment damage. Despite their importance, these abnormalities remain relatively understudied. Accurate classification of NTGV events is crucial for effective mitigation strategies. Existing research primarily relies on machine learning (ML) models trained on manually extracted features from simulated or real-world signals. This paper introduces a novel end-to-end deep learning approach that leverages Gate Recurrent Units (GRU) to bypass manual feature extraction, directly utilizing real-world signals from three NTGV event categories: ground fault, lightning strike, and normal conditions. This is first time that GRU has been used for NTGV classification using raw data. The model's generalizability is assessed through 5-fold cross-validation. A comparative analysis with baseline models and traditional ML techniques demonstrates the proposed model's superior performance and computational efficiency due to its ability to directly process raw data.