Life Cycle Data Research Articles

The advent of artificial intelligence is transforming business intelligence, reshaping the roles of data professionals, and offering unprecedented capabilities across the data lifecycle. This article examines how AI technologies are revolutionizing data engineering through automated pipeline construction, intelligent data quality management, and seamless data integration while simultaneously enhancing data science with automated feature engineering, democratized machine learning, and explainable decision support. Current trends in real-time analytics, cloud-native architectures, edge intelligence, and federated learning illustrate the evolving landscape. Despite these advancements, significant challenges persist in data governance, algorithmic bias, model explainability, and workforce transformation. By exploring both opportunities and limitations, the article provides a balanced perspective on how organizations can harness AI to elevate their business intelligence capabilities while addressing ethical and practical concerns.

The proliferation of wearable health sensors and remote patient monitoring (RPM) systems has transformed healthcare delivery by enabling continuous health tracking and proactive care. However, the transmission of sensitive biometric data through intricate edge-to-cloud pipelines introduces critical security and privacy challenges. This article examines cutting-edge advancements in secure data architectures for RPM systems, emphasizing encryption-in-transit protocols, adaptive data masking techniques, and robust audit trail mechanisms designed to meet stringent regulatory standards, including HIPAA, GDPR, and Joint Commission requirements. As RPM systems evolve from basic data collection tools to complex, multi-layered ecosystems, the need for advanced security measures across the entire data lifecycle becomes paramount. Through detailed case studies, this work highlights how comprehensive security frameworks can be seamlessly integrated into real-world clinical environments, achieving significant reductions in security incidents while enhancing monitoring capabilities. Looking ahead, the article explores emerging innovations such as edge intelligence with low-overhead encryption, localized anonymization strategies, and federated learning models that preserve data privacy while unlocking actionable insights across distributed systems.

The efficient maintenance and optimization of solar modules are critical for sustaining high energy yields over their operational lifetimes. This research introduces a comprehensive system designed to enhance lifecycle traceability and defect detection in solar modules using a combination of advanced image analysis and machine learning techniques. By leveraging Convolutional Neural Networks (CNN), You Only Look Once (YOLO) object detection, and deep learning, the system analyzes thermal and normal imaging data as well as current-voltage (IV) characteristics and curves. The proposed framework enables the detection of common faults, such as hotspots, cell cracks, and degradation patterns, which can impact performance and safety. Integrated data management and tracking capabilities facilitate end-to-end lifecycle monitoring, providing accessible, organized insights for stakeholders involved in solar module maintenance and diagnostics. The model shows an accuracy of 90%. The results show that the system not only improves accuracy in fault identification but also allows efficient storage and retrieval of diagnostic data, presenting a robust solution for advancing photovoltaic asset management

Environmental regulations are forcing certain industrial sectors to quantify their environmental impact, using environmental analysis tools. Currently, there is a lack of appropriation of these tools in industrial sectors. Participative approaches are relevant to tackle this issue. This article proposes an approach for co-creating an environmental analysis tool based on Life cycle assessment (LCA). To this day, there is no academic initiative to develop this type of tool in a participatory way. This approach suggests using a combination of a generic methodology (result 1) and a cocreation framework (result 2). It is then illustrated using the example of the competitive sailing sector in Brittany (France). The generic methodology is adapted from the recommendations of the International Life Cycle Data system guide and the usual steps of a software development. Some values of the methodology need to be cocreated. To do so, a cocreation framework is suggested, adapted from a generic framework from Durugbo and Pawar. The generic methodology proposed comprises twelve steps. The cocreation framework comprises three steps. Three values cocreated in the competitive sailing sector have been illustrated: a choice of functional unit, a perimeter for the sector, and software specifications adapted to the sector. The article discusses the approach in a broad context (regarding participatory approaches in the environmental sciences, co-creation linked to LCA and co-creation), as well as its advantages and disadvantages. The results of the article have implications at the level of industrial sectors, helping them to respond to future environmental policies.

This study analyzes electric, hydrogen fuel cell, hybrid, and biofuel vehicles in terms of energy efficiency, environmental impact, and economic viability. Drawing on life cycle data, it evaluates costs, emissions, and infrastructure needs across diverse contexts to identify the most effective solutions for sustainable and equitable transport decarbonization.

With rapid urbanization exacerbating the challenges in resource allocation, environmental sustainability, and infrastructure management, City Information Modeling (CIM) has emerged as an indispensable digital solution for smart city development. CIM represents an advanced urban management paradigm that integrates Geographic Information Systems (GISs), Building Information Modeling (BIM), and the Internet of Things (IoT) to establish a multidimensional digital framework for comprehensive urban data management and intelligent decision making. While the existing research has primarily focused on technical architectures, governance models, and application scenarios, a systematic exploration of CIM’s data-driven characteristics remains limited. This paper reviews the evolution of CIM from a data-centric view introducing a research framework that systematically examines the data lifecycle, including acquisition, processing, analysis, and decision support. Furthermore, it explores the application of CIM in key areas such as smart transportation and digital twin cities, emphasizing its deep integration with big data, artificial intelligence (AI), and cloud computing to enhance urban governance and intelligent services. Despite its advancements, CIM faces critical challenges, including data security, privacy protection, and cross-sectoral data sharing. This survey highlights these limitations and points out the future research directions, including adaptive data infrastructure, ethical frameworks for urban data governance, intelligent decision-making systems leveraging multi-source heterogeneous data, and the integration of CIM with emerging technologies such as AI and blockchain. These innovations will enhance CIM’s capacity to support intelligent, resilient, and sustainable urban development. By establishing a theoretical foundation for CIM as a data-intensive framework, this survey provides valuable insights and forward-looking guidance for its continued research and practical implementation.

Lithium-ion batteries (LIBs) are widely utilized in consumer electronics, electric vehicles, and large-scale energy storage systems due to their high energy density and long lifespan. Accurately estimating the state of health (SOH) and predicting the remaining useful life (RUL) of cells is crucial to ensuring their safety and preventing potential risks. Existing state estimation methodologies primarily rely on electrical signal measurements, which predominantly capture electrochemical reaction dynamics but lack sufficient integration of thermomechanical process data critical to holistic system characterization. In this study, relevant thermal and mechanical features collected during the formation process are extracted and incorporated as additional data sources for battery state estimation. By integrating diverse datasets with advanced algorithms and models, we perform correlation analyses of parameters such as capacity, voltage, temperature, pressure, and strain, enabling precise SOH estimation and RUL prediction. Reliable predictions are achieved by considering the interaction mechanisms involved in the formation process from a mechanistic perspective. Full lifecycle data of batteries, gathered under varying pressures during formation, are used to predict RUL using convolutional neural networks (CNN) and Gaussian process regression (GPR). Models that integrate all formation-related data yielded the lowest root mean square error (RMSE) of 2.928% for capacity estimation and 16 cycles for RUL prediction, highlighting the significant role of surface-level physical features in improving accuracy. This research underscores the importance of formation features in battery state estimation and demonstrates the effectiveness of deep learning in performing thorough analyses, thereby guiding the optimization of battery management systems.

Customer behavior analysis remains a cornerstone of strategic decision-making in the telecommunications industry. In this study, we present a complete, Python-based data science pipeline focused on predicting customer dependency status a proxy indicator for household-related churn or service needs. Using a real-world telecom dataset, our approach covers the full data lifecycle: from data cleaning and preprocessing to supervised classification and unsupervised segmentation. We evaluate a diverse set of machine learning models, including Linear and Logistic Regression, Support Vector Machines (SVM), Decision Trees, Random Forests, and XGBoost. Each model is carefully assessed through accuracy metrics, confusion matrices, and ROC curves to ensure both robustness and interpretability. Additionally, we apply K-Means clustering to explore customer segmentation patterns and reveal underlying group structures within the data. Our results indicate that ensemble-based models, particularly Random Forest and XGBoost, consistently outperform simpler classifiers in predictive accuracy. The integration of interpretability tools and feature importance analyses further highlights the relevance of variables such as tenure and monthly charges in customer behavior modeling. This work provides a hands-on and reproducible guide for telecom analysts and data scientists aiming to translate raw customer data into actionable business intelligence using well-established machine learning practices.

Smart cities rely on torrents of sensor, device, and citizen data to optimize transport, energy, safety, health and other urban services. Converting that raw stream into actionable insight hinges on data engineering. This paper surveys global smart‑city domains and maps their technical demands—IoT networks, edge‑to‑cloud pipelines, big‑data platforms, and real‑time stream engines. We trace the full data lifecycle (collection to visualisation) and show how data engineers design scalable, quality‑controlled, and secure pipelines while enforcing privacy and ethical‑AI safeguards. Case studies from Barcelona, New York, and other cities demonstrate tangible gains—lower energy use, faster emergency response, improved transparency—achieved through well‑architected data systems. We conclude that robust, interoperable data‑engineering practices are the decisive factor in realising safe, sustainable, AI‑driven smart‑city services.

A generic physics-informed machine learning framework for battery remaining useful life prediction using small early-stage lifecycle data

PurposeThe notion of efficiency in business operations generally focuses on both operational and ecological impacts. Individual assessments are critical considering the mutual dependence of both these impacts. Traditional evaluative techniques often produce erratic results when undesirable outputs (UOs), such as emissions and pollutants, are directly included to evaluate efficiency. To provide a comprehensive assessment of performance efficiency, this study applies a proposed framework in seafood pre-processing centres in India.Design/methodology/approachA framework comprising life cycle assessment (LCA) and data envelopment analysis (DEA) is developed and applied to assess performance efficiency comprising both ecological and operational efficiency. To assess the inclusion of UOs generated, four standalone integrative models identified from literature are examined, using the case addressed in this study.FindingsAnalysis reveals (1) the average carbon footprint of pre-processed seafood. (2) Better performance of the slack-based measure of efficiency model (SBM) with UO using the nonlinear approach compared to other models. (3) Influence of electricity consumption and operation costs on efficiency scores, as determined through sensitivity analysis.Research limitations/implicationsOutcomes highlight significant improvements in operational efficiency and reductions in greenhouse gas emissions. The outcomes highlight the need for enhanced waste management, energy efficiency and cold chain infrastructure. The outcomes also contribute to sustainability development goals (SDG) emphasizing the need for adequate policies.Originality/valueConclusions highlight the uniqueness of the framework, which integrates LCA and DEA. The results provide a valuable reference for policymakers and stakeholders, enabling them to adopt the proposed framework and minimise resource consumption and environmental impacts.

The copper life cycle comprises numerous stages from the alloy production to the manufacturing and usage of engineered parts until recycling. At each step, valuable data are generated and stored; some are transferred to the subsequent stations. A thorough understanding of the materials’ behavior during manufacturing processes or throughout their product lifetime is highly dependent on a reliable data transfer. If, for example, a failure occurs during the service life, information about the manufacturing route can be of decisive importance for detecting the root cause of the failure. Additionally, the life cycle assessment hinges on the availability of data. Recording and storing interoperable structured data is, therefore, a thriving research field with huge implications for the economic strength of the manufacturing industry. In the KupferDigital project, it is demonstrated how an ontology‐based data space can be utilized not only as an innovative method for storing and providing interoperable life cycle data but also as a means to enable automated data analysis and evaluation, leading to new insights and the creation of new knowledge using semantic data and technologies. This work illustrates how data recorded at different research facilities can be integrated into one single data space, allowing queries across heterogeneous sources.

The field of research data management librarianship has grown significantly in past years but continues to face the challenges of knowledge gaps, frequent changes to policy and guidance, and the complexity and context that comes from data that varies both in type and format. As a research data librarian, I face these issues on a daily basis and have adopted an adaptive approach that combines multiple styles to balance the individual needs of researchers while complying with policies and best practices. This approach was adopted from my past experience in data governance at a corporation in which we faced the same core challenges. Incorporating the four styles of data governance as laid out by Gartner provides a framework for librarians and data governance specialists alike to prioritize competing needs and guide researchers through the data lifecycle. The benefits of this approach include increased flexibility in data management practices, continuous improvement of services and resources, efficiency, and empowerment of researchers and related stakeholders.

The ocean plays a vital role in our society and represents a constantly changing landscape that is not well understood and therefore needs continuous monitoring and research. Sustainable monitoring is essential to assess both the current and future state of our oceans. However, conventional monitoring faces significant challenges, including issues of accessibility, and spatial and temporal constraints. The development of digital twins of the ocean (DTO) offers an emerging technology that could revolutionise our understanding of marine and coastal environments. Current DTO have shown effectiveness in monitoring marine and coastal environments in the European context. However, there is a need for a DTO for the Southern African and Western Indian Ocean regions that addresses specific concerns that are relevant to these regions. Successful development of a DTO depends on the availability of high-quality data. Therefore, various data inputs are necessary to build an accurate digital twin. This paper explores the data that can be utilised in a DTO, detailing how different ocean variables are collected and integrated into the digital twin. As a first step towards the development of a DTO in these regions, the paper proposes a data management plan and its implementation in the development of DTO. The data management plan is based on the phases of data in a geospatial data life cycle. Challenges regarding the management of data in this DTO and possible solutions are presented in the conclusion.

Abstract Design for circular economy (DfCE) aims to systematically incorporate circular economy (CE) considerations during the design phase. In this article, we introduce an integrated quantitative framework that concurrently assesses product functionality, CE, and sustainability performance to enable a more holistic DfCE. This framework enables coupling multiple life-cycle phase simulation models for estimating the effects of parameterized changes in a product’s design or life-cycle behavior on its CE and sustainability performance. We showcase the ability of the proposed framework to support CE- and sustainability-centric design optimization and design space exploration using a case study on a commercial flange coupling. Results show that geometric optimization, to a certain extent, can compensate for material substitution. Furthermore, we show the existence of trade-offs between the above three indicators and that optimizing the flange coupling design to reduce global warming potential results in an increase in energy intensity for the same material composition. The case study shows the potential of the presented modeling framework to provide meaningful insights for DfCE. We demonstrate that the developed framework supports DfCE by highlighting interdependencies between product life-cycle data and their influence on CE and sustainability performance, which can be difficult to assess through other means. This research facilitates the integration of circularity considerations into simulation-based design by leveraging existing engineering simulation models and provides concrete design guidance on how products can be redesigned for CE.

This paper proposed a digital twin modeling method based on digital twin technology to improve the operational stability of rolling bearings and the accuracy of fault diagnosis methods. A comprehensive digital twin model for the entire lifecycle of rolling bearings was constructed using Modelica language. This model included a multi-state rolling bearing digital twin and integrated twin models for both the bearing drive and load ends. The model employed hybrid noise component to simulate the bearing's actual operating state and degradation process with high fidelity. Based on experimental lifecycle data from the laboratory, the rolling bearing full-life digital twin integrated model parameters were updated. Through the degradation components of the digital twin, the twin data of the rolling bearing was generated. By combining the twin data with actual measurement data, this approach addresses the limitations of traditional methods in the absence of data for bearings, providing reliable technical support for intelligent maintenance and fault diagnosis methods for rolling bearings.

The AEC’s resource consumption and environmental impact necessitate a shift towards sustainable, circular practices. Building information modeling, powered by information technology, serves as a key enabler in this transition, offering life cycle data management capabilities from design to deconstruction. However, current BIM models lack embedded life cycle and circularity data, limiting their effectiveness for sustainability integration. This study addresses this gap by proposing a BIM object library framework that embeds life cycle, cost, and circularity data into objects and aims at enabling informed, sustainability-driven decision making. Through a proof of concept, this research demonstrates how embedding LCA and CE metrics into BIM objects enhances environmental and circular impact assessments. The framework aligns with standards such as ISO 14040 and EN 15804, EU Level(s), and United Nations’ 2030 Agenda for Sustainable Development. Limitations such as manual data integration and the need for specialized expertise occurred. However, this framework provides a scalable foundation for future research, including automating data integration, enhancing metric calculations, and developing interactive circularity dashboards to improve as a decision-support tool. This study advances circular BIM adoption, integrating sustainability principles into digital design workflows from the object level, while serving as a centralized repository for sustainability-driven decision making.

ABSTRACTThe evolution of data journals and the increase in data papers call for associated peer review, which is intricately linked yet distinct from traditional scientific paper review. This study investigates the data paper review guidelines of 22 scholarly journals that publish data papers and analyses 131 data papers' review reports from the journal Data. Peer review is an essential part of scholarly publishing. Although the 22 data journals employ disparate review models, their review purposes and requirements exhibit similarities. Journal guidelines provide authors and reviewers with comprehensive references for reviewing, which cover the entire life cycle of data. Reviewer attitudes predominantly encompass Suggestion, Inquiry, Criticism and Compliment during the specific review process, focusing on 18 key targets including manuscript writing, diagram presentation, data process and analysis, references and review and so forth. In addition, objective statements and other general opinions are also identified. The findings show the distinctive characteristics of data publication assessment and summarise the main concerns of journals and reviewers regarding the evaluation of data papers.

Introduction. This paper examines the transformation of university data culture in the age of AI. AI and big data are reshaping how universities manage data, make decisions, and interact with stakeholders, raising both opportunities and challenges. Method. The study explores the concept of university data culture, proposing a four-layer conceptual framework: the data layer, user layer, organizational layer, and societal layer. Analysis. The four-layer framework captures the lifecycle of data, stakeholder behaviours and competencies, institutional policies, and societal influences. It emphasizes how AI transforms data usage and governance within universities, as well as the ethical and social considerations that arise. Results. AI is driving a shift from traditional data management to structured data governance, fostering greater data-informed decision-making, and encouraging bottom-up participation among faculty and students. However, challenges related to ethics, privacy, and inequality persist. Conclusions. The transformation of university data culture is not just technological but cultural, requiring universities to address ethical and social issues. Ensuring inclusivity, fairness, and responsibility in data practices is critical for fostering a balanced and sustainable data culture in higher education.

To enhance the maintenance efficiency and operational stability of rolling bearings, this work establishes a methodology for bearing life prediction, employing digital twin systems to evaluate the remaining useful life of rolling bearings. A comprehensive digital twin-integrated model for the entire lifecycle of rolling bearings is constructed using the Modelica language. This model generates sufficient and reliable lifecycle twin data for the bearings. Due to the symmetrical physical structure of the bearings, the generated twin data also have symmetry. Based on this characteristic of bearings, a remaining useful life (RUL) prediction algorithm is developed using a recurrent neural network (RNN), specifically an improved gated recurrent unit (GRU) model. An optimization algorithm is employed to adjust the hyperparameters and determine the initial fault point of the bearing. A multi-feature dataset is constructed, effectively enhancing the precision and reliability of lifespan estimation. Based on existing measured data of the bearing’s entire lifecycle, the rolling bearing’s digital twin-integrated model parameters are updated. Through the parameter degradation component of the twin, the lifecycle twin data of the rolling bearing are generated. By combining twin data with actual measurement data, this method addresses the limitations of traditional approaches in situations where complete lifecycle data of bearings are scarce, providing reliable technical support for the intelligent maintenance and optimization of rolling bearings.