Mixed traffic flow, consisting of human-driven vehicles (HDVs) and connected autonomous vehicles (CAVs), is expected to dominate future roadways. This study develops a heterogeneous traffic flow model in an intelligent connected environment to analyze macroscopic characteristics, including traffic capacity, critical density, and fundamental diagrams, under varying CAV penetration rates. Three car-following modes are considered: HDVs following HDVs, HDVs following CAVs, and CAVs following CAVs, modeled respectively by the Intelligent Driver Model (IDM), Adaptive Cruise Control (ACC), and Cooperative Adaptive Cruise Control (CACC). Model parameters are calibrated using genetic algorithms based on publicly available autonomous driving datasets. Calibration results demonstrate high predictive accuracy, with mean absolute percentage errors of 0.009% (distance) and 2.37% (speed) for IDM, 0.27% and 3.67% for ACC, and near-zero errors for CACC. Analysis of fundamental diagrams shows that increasing CAV penetration significantly enhances traffic flow efficiency, improves stability, and mitigates congestion. The findings provide theoretical guidance for optimizing mixed traffic operations and support the development of intelligent and connected transportation systems.

The increasing frequency and intensity of extreme weather events, coupled with rapid urbanization, are placing unprecedented pressure on urban environments. The Three-Point Sponge Policy Approach (3PSPa) integrates the Three-Point Approach (3PA) with Sponge City principles to enhance urban flood resilience through design-driven, adaptive, and multifunctional solutions. This paper applies the 3PSPa framework to Zhengzhou, China, which experienced devastating flooding in 2021, to assess its current flood resilience measures and explore pathways for improvement. Two contrasting urban districts in Zhengzhou were analysed: B1, a newly developed, low-density district offering high potential for implementing large-scale blue-green-grey infrastructure (BGGI); and B2, a dense, older district where  interventions are limited, typically emerging incrementally through targeted retrofitting associated with urban renewal activities. By applying the 3PSPa’s five-step design process, this study identifies resilience gaps and proposes tailored interventions, balancing short-term, localized strategies with long-term, catchment-wide transformations. It emphasizes the importance of shifting from a conveyance-based water management approach to a diversified strategy that integrates infrastructure with natural hydrological processes.

Despite the continued success of machine learning (ML), its indiscriminate use may not always yield the expected benefits, can waste resources, introduce unforeseen complexities, and even lead to failure. From this lens, this paper systematically addresses the following elemental questions: When should we integrate ML, and which problem-solving workflows benefit the most? Thus, this paper critically examines existing decision making frameworks and guidelines to identify their strengths and limitations in defining ML applicability. Then, through a comprehensive literature review and analysis, we outline explicit suitability criteria to assess when ML should be favored over traditional engineering methods. Based on this analysis, we propose a conceptual structured decision making framework that incorporates practical steps and checklists to guide engineers in method selection, model development, validation, and deployment. Additionally, this paper highlights critical challenges and potential future research questions.

Vehicular Ad Hoc Networks (VANETs) are critical for transportation safety and efficiency but face serious security challenges due to limitations of traditional cryptography and emerging cyber threats. This paper proposes a novel reconciliation-free Physical Layer Key Generation (PKG) framework based on dynamic Received Signal Strength (RSS) measurements and Triplet Networks (TN). Unlike conventional PKG schemes, the proposed approach eliminates reconciliation overhead while maintaining high entropy and strong resistance to eavesdropping. Realistic RSS is generated by integrating SUMO-based vehicular mobility with NS-3 network simulations, capturing spatiotemporal channel dynamics. The TN architecture extracts reciprocal channel features through hierarchical convolutional layers and optimized embedding spaces for secure key extraction. Experimental results show near-zero bit error rates between legitimate vehicles, high key entropy (0.69 bits/bit), and complete failure of eavesdroppers to reconstruct keys. Among 3,200 generated keys, 74.1% achieved perfect agreement without reconciliation, while eavesdroppers achieved 0% success. The proposed framework demonstrates a scalable, and robust security solution for VANET communications.

Transverse cracking is a major distress mechanism in Continuously Reinforced Concrete Pavement (CRCP), affecting ride smoothness, service life, and maintenance strategies. This research introduces a hybrid predictive framework that couples Particle Swarm Optimization (PSO) with Gradient Boosting Machine (GBM) to enhance the accuracy of transverse crack prediction in CRCP. The analysis utilized 395 records from 33 pavement sections obtained from the Long-Term Pavement Performance (LTPP) program, encompassing structural, environmental, traffic, and performance-related parameters. PSO was applied to fine-tune critical GBM hyperparameters, namely the number of iterations, learning rate, and tree depth. The optimized PSO–GBM model demonstrated excellent performance, yielding an average RMSE of 1.62 and an R² of 0.99 under 5-fold cross-validation, surpassing benchmark models such as conventional GBM, Random Forest, Support Vector Regression (SVR), Artificial Neural Networks (ANN), and Linear Regression. Sensitivity analysis revealed that L3 thickness, L4 thickness, and Annual Average Daily Traffic (AADT) were the most significant contributors, consistent with engineering knowledge of crack development. Validation through residual distribution and equality line plots confirmed the robustness and stability of the proposed approach across varying severity levels.

Centrifugal compressors are commonly employed for pressure compensation in long-distance natural gas pipelines. Accurate prediction of compressor performance is essential for safety and economic considerations. However, due to the invariance of process requirements over time, operational data is usually insufficient to establish a comprehensive model that covers varying operating conditions. This paper presents a prediction method based on the long short-term memory (LSTM) network and transfer learning technique, integrating similarity laws to expand the feature domain and address the issue of limited data. In the case study, the constructed TransLSTM model, a fusion of transfer learning and LSTM, is compared with pure LSTM, Gaussian Process (GP), Gradient Boosting Decision Tree (GBDT), Random Forest (RF), and Support Vector Machine (SVM) models. Results indicate that TransLSTM achieves the highest prediction accuracy, with deviations from actual values of only 2.9% for power and 0.971% for compressor ratio. Verification through comparisons between the training and test sets demonstrates its excellent generalization ability, which is particularly crucial when operational data spans a limited range of working conditions. Additionally, its stability is significantly superior to that of benchmark models.