Natural gas pipeline leak monitoring suffers from severe environmental noise, non-stationary signals, and complex multi-source variable couplings, limiting prediction accuracy and robustness. Inspired by biological perceptual systems, particularly their multimodal integration and dynamic attention allocation, we propose GL-TransLSTM, a biomimetic hybrid deep learning model. It synergistically combines Transformer’s global self-attention (emulating selective focus) and LSTM’s gated memory (mimicking neural temporal retention). The architecture incorporates a multimodal fusion pipeline; raw sensor data are first decomposed via CEEMDAN to extract multi-scale features, then processed by an enhanced LSTM-Transformer backbone. A novel physics-informed gated attention mechanism embeds gas diffusion dynamics into attention weights, while an adaptive sliding window adjusts temporal granularity. This study makes evaluations on an industrial dataset with methane concentration, temperature, and pressure, GL-TransLSTM achieves 99.93% accuracy, 99.86% recall, and 99.89% F1-score, thereby significantly outperforming conventional LSTM and Transformer-LSTM baselines. Experimental results demonstrate that the proposed biomimetic framework substantially enhances modeling capacity and generalization for non-stationary signals in noisy and complex industrial environments through multi-scale fusion, physics-guided learning, and bio-inspired architectural synergy.

Global urbanization has promoted to an increasing scale of construction projects, thereby making the optimization of construction project organization design a critical task in engineering management. However, conventional methods relying on empirical decision-making suffer from issues like low resource allocation efficiency, many difficulties in coordinating multi-objective conflicts and insufficient dynamic adjustment capabilities. To address these issues, we propose the first multi-objective extension of the Animated Oat Optimization algorithm (MOAOO), which represents a pioneering contribution in transforming the single-objective AOO into a multi-objective optimizer for construction project organization design. The developed algorithm fundamentally extends the biological mechanism of Animated Oat Optimization introducing several key innovations: (a) a novel hybrid position update rule combining Elite Reference Points and stochastic perturbations to prevent premature convergence; (b) an innovative three-layer constraint processing mechanism ensuring the generation of feasible solutions; and (c) a dual-threshold convergence monitoring system for early termination. Notably, we establish MOAOO as the inaugural multi-objective variant of AOO, integrating dynamic elite retention strategies, non-dominated sorting, and dynamic archive mechanisms to enable effective collaborative optimization of three conflicting goals. Enough experiments on ZDT test functions demonstrate that the designed MOAOO method shows competitive performance compared to advanced algorithms such as Pre-DEMO, MOEA/D-OED, and Pi-MOEA in terms of hypervolume inverted generational distance and the Spacing metrics. The indicator is improved in certain configurations. In an engineering case study, MOAOO reduces resource fluctuation by 72.7% in the compromise solution while achieving a balanced duration (279 days) and cost ($1.34 M). Moreover, the proposed algorithm converges in 118 iterations on average, thereby verifying its practical value in construction scheduling.

Accurate traffic flow prediction plays a critical role in intelligent transportation systems, supporting traffic management, congestion mitigation, and efficient utilization of road resources. Advances in neural network-based methods, particularly graph neural networks (GNNs) and attention-based models, have demonstrated strong capability in modeling spatio-temporal traffic dynamics. However, existing approaches still face notable challenges: GNN-based models often rely on static adjacency matrices, limiting their ability to capture dynamic and long-range spatial dependencies, while attention-based models usually involve complex architectures and heavy reliance on large-scale pre-training data. To address these limitations, this study proposes a novel traffic flow prediction model that integrates a learnable memory tensor into an attention-based framework. The introduced memory mechanism provides persistent global context for modeling long-term temporal dependencies in an end-to-end manner, enabling efficient and dynamic spatio-temporal representation learning with a lightweight architecture. Extensive experiments on multiple real-world traffic datasets demonstrate that the proposed model achieves superior prediction accuracy and robustness compared with existing baselines. The proposed approach offers a new perspective for memory-enhanced spatio-temporal modeling and provides valuable insights for traffic forecasting and related intelligent transportation applications.

The accuracy of numerical model outputs strongly depends on the quality of the initial wind field, yet ground observation data are typically sparse and provide incomplete spatial coverage. More importantly, many current mainstream correction models rely on reanalysis grid datasets like ERA5 as the true value, which relies on interpolation calculation, which directly affects the accuracy of the correction results. To address these issues, we propose a new deep learning model, PPWNet. The model directly uses sparse and discretely distributed observation data as the true value, which integrates observation point positions and a physical consistency term to achieve a high-precision corrected wind field. The model design is inspired by biological intelligence. First, observation point positions are encoded as input and observation values are included in the loss function. Second, a parallel dual-branch DenseInception network is employed to extract multi-scale grid features, simulating the hierarchical processing of the biological visual system. Meanwhile, PPWNet references the PointNet architecture and introduces an attention mechanism to efficiently extract features from sparse and irregular observation positions. This mechanism reflects the selective focus of cognitive functions. Furthermore, this paper incorporates physical knowledge into the model optimization process by adding a learned physical consistency term to the loss function, ensuring that the corrected results not only approximate the observations but also adhere to physical laws. Finally, hyperparameters are automatically tuned using the Bayesian TPE algorithm. Experiments demonstrate that PPWNet outperforms both traditional and existing deep learning methods. It reduces the MAE by 38.65% and the RMSE by 28.93%. The corrected wind field shows better agreement with observations in both wind speed and direction, confirming the effectiveness of incorporating position information and a physics-informed approach into deep learning-based wind field correction.