https://ojs.luminescience.cn/CER <p><em>Civil and Energy Research</em> (CER) aims to provide a high-level academic exchange platform for academic researchers, engineers and practitioners in the fields of civil engineering and energy around the world, and publish the latest scientific research results and technological advances. This journal pays special attention to the intersection and integration of civil engineering and energy, and welcomes original research, review articles, technical reports, case studies in related fields.</p> Luminescience Press Ltd en-US Civil and Energy Research <p>Copyright licenses detail the rights for publication, distribution, and use of research. Open Access articles published by Luminescience do not require transfer of copyright, as the copyright remains with the author. In opting for open access, the author(s) should agree to publish the article under the CC BY license (Creative Commons Attribution 4.0 International License). The CC BY license allows for maximum dissemination and re-use of open access materials and is preferred by many research funding bodies. Under this license, users are free to share (copy, distribute and transmit) and remix (adapt) the contribution, including for commercial purposes, providing they attribute the contribution in the manner specified by the author or licensor.</p> https://ojs.luminescience.cn/CER/article/view/357 <p>The accuracy of surface settlement predictions, which aim to limit theoretical, numerical and experimental simulation errors, is influenced by several factors, including parameter values, assumption conditions and other limitations. However, the recent introduction of machine learning (ML) and deep learning (DL) has provided new ideas for surface settlement prediction. In this paper, the advances of ML and DL in surface settlement prediction are systematically reviewed. The classification of surface settlement prediction methods is first conducted based on the principles of commonly used ML and DL algorithms, including maximum surface settlement prediction and surface settlement time series prediction. Existing studies are then analysed, and common methods for improving prediction accuracy are presented. Finally, the performance of common ML and DL algorithms in predicting surface settlement is compared using the Kunming dataset. The study then draws conclusions based on the results of the comparative studies and literature research, highlighting the impact of dataset quality and feature selection on the generalisation ability of prediction models and the real-time prediction ability of existing studies.</p> Zekun Zhu Chang Liu Copyright © 2025 Zekun Zhu, Chang Liu https://creativecommons.org/licenses/by/4.0 2025-11-04 2025-11-04 2 20 https://ojs.luminescience.cn/CER/article/view/400 <p>Structural health monitoring (SHM) of composite materials is critical for ensuring the reliability and longevity of high-performance engineering systems. This review comprehensively examines the advancements, challenges, and applications of flat optical fibre sensors (FOFS) for real-time strain monitoring in composite structures. Traditional electrical strain gauges and piezoelectric sensors face limitations in multiplexing, electromagnetic interference (EMI), and integration within composite layups. In contrast, FOFS offer unique advantages, including high spatial resolution, compatibility with composite manufacturing processes, and immunity to EMI. This paper analyses the working principles of FOFS, their fabrication techniques, integration methodologies, and signal interrogation systems. Case studies from aerospace, civil engineering, and renewable energy sectors underscore their practical efficacy. Challenges such as signal attenuation, temperature cross-sensitivity, and long-term durability are critically evaluated. The review concludes with future directions, including nanotechnology-enhanced sensors and machine learning-driven data analytics. </p> Elias Randjbaran Darya Khaksari Hamid Mehrabi Rizal Zahari Dayang L. Majid Mohamed T. H. Sultan Norkhairunnisa Mazlan Mehdi Granhemat Copyright © 2025 Elias Randjbaran, Darya Khaksari, Hamid Mehrabi, Rizal Zahari, Dayang L. Majid, Mohamed T. H. Sultan, Norkhairunnisa Mazlan, Mehdi Granhemat https://creativecommons.org/licenses/by/4.0 2025-11-07 2025-11-07 21 28 https://ojs.luminescience.cn/CER/article/view/456 Yong Yuan Copyright © 2025 Yong Yuan https://creativecommons.org/licenses/by/4.0 2025-09-03 2025-09-03 1 1