Advancing Urban Planning with Deep Learning: Intelligent Traffic Flow Prediction and Optimization for Smart Cities

This study introduces the MSTA-GNet (Multi-Scale Spatiotemporal Attention Graph Network), a novel deep learning model which integrates spatiotemporal self-attention mechanisms to model heterogeneous dependencies in traffic networks. The primary objective of the study is to improve existing traffic flow prediction models to address the inadequacies of traditional models in complex big data environments. Key innovations of the MSTA-GNet model include positional encoding and global and local self-attention mechanisms to capture long-term and short-term dependencies. Using the PeMS (Performance Measurement System) dataset, the study conducted performance comparison experiments among various deep learning models, including LSTM (Long Short-Term Memory), GCN (Graph Convolutional Network), DCRNN (Diffusion Convolutional Recurrent Neural Network), STGCN (Spatiotemporal Graph Convolutional Network), STMetaNet (Spatiotemporal Meta Network), and MSTA-GNet. The results showed that MSTA-GNet significantly outperformed other models with improvements of 13.4%, 11.8%, and 9.7% in Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) metrics, respectively. Ablation studies further validated the significance of attention mechanisms, feature extraction, convolutional layers, and graph networks, confirming the effectiveness and practical application of MSTA-GNet in traffic flow prediction. This research provides important insights for AI-based congestion management, support for low-carbon traffic networks, and optimization of local traffic operations, demonstrating its significant practical value in intelligent transportation systems.

This paper proposes the application of artificial intelligence to forecast the generation capacity of wind power plants by processing data through noise reduction and filtering. It subsequently employs Long-Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) neural networks for training, testing, and evaluation. Processing the initial data will help minimize noise and reduce the data space. The study focuses on preprocessing methods and selecting the appropriate neural network between LSTM and GRU. The initial data processing will assess the similarity through the Spearman rank correlation coefficient. The data used in the paper is taken from local wind turbines. The processed data will be input into the neural network for evaluation based on Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Percent Error (PE), and training time. The entire network simulation and evaluation process is performed using MATLAB software. The simulation results show the feasibility and suitability of the GRU network model combined with noise filtering methods, bringing high accuracy and less training time compared to the LSTM network. Specifically, the analysis contrasting the GRU network with the optimized dataset and the LSTM with the unprocessed dataset is more effective than a difference in RMSE of 15.592 and MAPE of 611.047%. Moreover, the time difference between the GRU and LSTM networks with the same dataset has a much earlier time difference from 6 to 28 seconds.

Globally, wind energy if properly harnessed, could serve as a source of energy generation in Africa. This study compared the performance of two Machine Learning (ML) algorithms (Linear regression and Random Forest) in predicting wind speed in five major cities in Africa (Yaoundé, Pretoria, Nairobi, Cairo and Abuja). Wind data were collected between January 1, 2000, and December 31, 2022, using the Solar Radiation Data Archive. The data preprocessing was carried out with 80% of the data used for training and 20% for validation. The performance of these ML algorithms was evaluated using Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and coefficient of determination (R2). The result shows that Nairobi (3.814795 m/s) closely followed by Cairo (3.606453 m/s) has the highest mean wind speed while Yaoundé (1.090512 m/s) has the lowest. Based on the performance metrics used, the two Machine Learning algorithms were competitive. Still, the Linear Regression (LR) algorithm outperformed the Random Forest Algorithm in predicting wind speed in all the selected major African cities. In Yaoundé (RMSE = 0.3892, MAE= 0.3001, MAPE =0.5030), Pretoria (RMSE=1.2339, MAE=0.9480, MAPE=0.7450) Nairobi (RMSE= 0.4223, MAE =0.6499, MAPE =0.1872), Nairobi (RMSE=0.6499, MAE=0.5171, MAPE =0.1872), Cairo (RMSE =1.0909, MAE =0.8544, MAPE =0.3541) and Abuja (RMSE = 0.70245, MAE =0.5441, MAPE= 0.4515) the Linear regression algorithms was found to outperformed Random Forest Regression. Therefore, the Linear regression algorithm is more reliable in predicting wind speed compared with the Random Forest regression.

Fractional-order models (FOMs) have been recognized as superior tools for capturing the complex electrochemical dynamics of lithium-ion batteries, outperforming integer-order models in accuracy, robustness, and adaptability. Parameter identification (PI) is essential for FOMs, as its accuracy directly affects the model’s ability to predict battery behavior and estimate critical states such as state of charge (SOC) and state of health (SOH). In this study, a hybrid deep learning approach has been introduced for FOM PI, representing the first application of deep learning in this domain. A simulation platform was developed to generate datasets using Sobol and Monte Carlo sampling methods. Five deep learning models were constructed: long short-term memory (LSTM), gated recurrent unit (GRU), one-dimensional convolutional neural network (1DCNN), and hybrid models combining 1DCNN with LSTM and GRU. Hyperparameters were optimized using Optuna, and enhancements such as Huber loss for robustness to outliers, stochastic weight averaging, and exponential moving average for training stability were incorporated. The primary contribution lies in the hybrid architectures, which integrate convolutional feature extraction with recurrent temporal modeling, outperforming standalone models. On a test set of 1000 samples, the improved 1DCNN + GRU model achieved an overall root mean square error (RMSE) of 0.2223 and a mean absolute percentage error (MAPE) of 0.27%, representing nearly a 50% reduction in RMSE compared to its baseline. This performance surpasses that of the improved LSTM model, which yielded a MAPE of 9.50%, as evidenced by tighter scatter plot alignments along the diagonal and reduced error dispersion in box plots. Terminal voltage prediction was validated with an average RMSE of 0.002059 and mean absolute error (MAE) of 0.001387, demonstrating high-fidelity dynamic reconstruction. By advancing data-driven PI, this framework is well-positioned to enable real-time integration into battery management systems.

Compressive strength is an important mechanical property of high-strength concrete (HSC), but testing methods are usually uneconomical, time-consuming, and labor-intensive. To this end, in this paper, a long short-term memory (LSTM) model was proposed to predict the HSC compressive strength using 324 data sets with five input independent variables, namely water, cement, fine aggregate, coarse aggregate, and superplasticizer. The prediction results were compared with those of the conventional support vector regression (SVR) model using four metrics, root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and correlation coefficient (R2). The results showed that the prediction accuracy and reliability of LSTM were higher with R2 = 0.997, RMSE = 0.508, MAE = 0.08, and MAPE = 0.653 compared to the evaluation metrics R2 = 0.973, RMSE = 1.595, MAE = 0.312, MAPE = 2.469 of the SVR model. The LSTM model is recommended for the pre-estimation of HSC compressive strength under a given mix ratio before the laboratory compression test. Additionally, the Shapley additive explanations (SHAP)-based approach was performed to analyze the relative importance and contribution of the input variables to the output compressive strength.

This study proposed a hybrid modelling framework that integrates Random Forest (RF), Vector Error Correction Model (VECM), and Regression Analysis to enhance macroeconomic forecasting in Nigeria. Addressing challenges such as oil price volatility, structural shocks, and sparse high-frequency data, this approach combines RF’s ability to capture non-linear patterns, VECM’s cointegration of non- stationary variables, and Regression’s parametric efficiency through residual correction and ensemble averaging. Using macroeconomic data from 1993–2022, the hybrid model achieved a 23.4% reduction in Mean Absolute Error (MAE) for GDP (from 15.23 to 11.67) and a 28.5% reduction in Root Mean Squared Error (RMSE) (from 20.45 to 14.62), alongside significant improvements for other variables: 17.6% MAE (exchange rate), 15.2% MAE (inflation), 12.1% MAE (unemployment), and 20.3% RMSE (exchange rate), 18.5% RMSE (inflation), 15.6% RMSE (unemployment). The optimized integration weights ( α = 0.61 for RF, β = 0.17 for VECM, γ = 0.23 for RA in GDP forecasting) highlight machine learning’s dominance in modeling non-linearities, while VECM anchors predictions to long-term equilibria and RA stabilizes parametric relationships. Residual correction and ensemble averaging further reduced systematic biases, as evidenced by tighter error distributions. By bridging machine learning and econometrics, this integrated approach provided policymakers with a robust tool for economic stabilization in resource-dependent economies. While data granularity influenced performance, it highlighted its potential for emerging markets facing structural constraints.

Prediction of dissolved oxygen in a fishery pond based on gated recurrent unit (GRU)

Stocks have become one of the largest and most intricate financial markets globally due to their high popularity, making them very challenging to predict as they can process millions of transactions rapidly. The objective of this study is to enhance the field by creating a dependable and accurate model for predicting the stock price of Amazon. This will be achieved via the use of advanced algorithms such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). This research utilised historical data on Amazon's stock price from the past five years, which was acquired from Yahoo Finance. The data was partitioned using a hold-out validation technique, allocating 80% for training and 20% for testing. The model underwent training using different optimizers (Adam, SGD, RMSprop), batch sizes (8, 16, 32), and learning rates (0.001, 0.0001). The evaluation criteria comprised of mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). The results suggest that the GRU model, when trained with the RMSprop optimizer using a batch size of 16 and a learning rate of 0.0001, as well as with the SGD optimizer using a batch size of either 16 or 32 and a learning rate of either 0.001 or 0.0001, produced the lowest error metrics, indicating superior performance. This study enables more precise forecasts of stock prices and more efficient investment techniques.

With the in-depth implementation of China’s “National Strategy for Building a Strong Transportation Network,” the scale of expressway construction has continued to expand. As a result, the number of high-fill and deep-cut subgrade projects under complex geological conditions has increased significantly, leading to a surge in landslide-related issues. Consequently, accurate prediction of slope displacement is of critical importance for early warning and prevention of landslide disasters. This study proposes a hybrid prediction model, VMD-MPA-LSSVM-LSTM (VMLL), which integrates Variational Mode Decomposition (VMD), Marine Predators Algorithm (MPA), Least Squares Support Vector Machine (LSSVM), and Long Short-Term Memory (LSTM) networks. Using monitoring data from the high-fill embankment slope at Hongtuyao as the research subject, the VMLL model is employed to predict slope displacement based on small-sample data. The objective is to provide a more accurate method for early warning of slope displacement. Firstly, the original monitoring data are decomposed into trend displacement components and fluctuation displacement components using Variational Mode Decomposition (VMD). Subsequently, the trend component and the fluctuation component are predicted using Least Squares Support Vector Machine (LSSVM) and Long Short-Term Memory (LSTM) networks, respectively. Finally, the Marine Predators Algorithm (MPA) is employed to optimize the hyperparameters of the predictive models. Based on this framework, a VMLL-based slope displacement prediction model is constructed. To verify the superiority of the VMLL model, a comparative analysis was conducted against LSSVM, LSTM, and the VMD-LSSVM-LSTM models. The results demonstrate that the VMLL model achieves the highest prediction accuracy, with a Mean Absolute Percentage Error (MAPE) of 0.4022%, a Mean Absolute Error (MAE) of 0.016 mm, a Root Mean Square Error (RMSE) of 0.0206 mm, a coefficient of determination (R²) of 94.08%, and a Variance Accounted For (VAF) of 96.5%. Compared with the other three models, the VMLL model reduces the MAPE, MAE, and RMSE by 30.41–67.62%, 30.38–67.40%, and 27.32–71.00%, respectively. Meanwhile, it improves the R² and VAF by 5.95–217.51% and 0.38–11.48%, respectively. These improvements clearly demonstrate that the VMLL model outperforms the other models, indicating its significant advantage over single prediction models. Furthermore, three additional datasets were used to evaluate the model’s performance. The average values of the performance evaluation metrics for these datasets were 0.6207% (MAPE), 0.0238 mm(MAE), 0.0273 mm(RMSE), 90.33%(R²), and 96.81%(VAF), respectively. These results demonstrate the high accuracy and strong robustness of the proposed model in predicting both horizontal displacement and vertical settlement of slopes, providing a reliable methodological framework for slope stability assessment and landslide disaster early warning.

This study proposes an enhanced deep learning framework for accurately estimating the state of health (SOH) of lithium-ion batteries (LIBs), leveraging a refined Convolutional Neural Network (CNN)-Long Short-Term Memory (LSTM)-Attention architecture. To improve prediction accuracy and robustness, a novel Multi-Scale Adaptive Wasserstein-Huber Loss (MSAWH Loss) is introduced, which combines the strengths of Huber loss and multi-scale Wasserstein distance to effectively handle outliers and capture complex degradation patterns. Furthermore, an Uncertainty-Guided Adaptive Bayesian Optimization (UGABO) algorithm is employed to optimize model hyperparameters, achieving efficient convergence in high-dimensional and noisy parameter spaces while maintaining a balance between exploration and exploitation. To enhance generalization, four complementary data augmentation techniques—linear interpolation, data slicing, sequence flipping, and cross-sample mixing—are applied to the National Aeronautics and Space Administration (NASA) charge-discharge dataset, significantly enriching the training data. Additionally, a Model Predictive Control (MPC) mechanism is integrated to correct long-horizon prediction errors, dynamically refining outputs based on recent deviations and maintaining consistency with real-world battery constraints. Experimental results demonstrate that the proposed framework outperforms baseline models, achieving a 20.6% reduction in mean absolute error (MAE), an 18.6% reduction in root mean squared error (RMSE), and a 0.1% improvement in R-squared (R 2 ). These findings highlight the effectiveness of integrating adaptive loss design, automated hyperparameter optimization, strategic data augmentation, and feedback-based error correction in advancing SOH prediction performance for lithium-ion batteries.

Given the substantial volatility and non-stationarity of cryptocurrency prices, forecasting them has become a complex task within the realm of financial time series analysis. This study introduces an innovative hybrid prediction model, VMD-AGRU-RESVMD-LSTM, which amalgamates the disintegration–integration framework with deep learning techniques for accurate cryptocurrency price prediction. The process begins by decomposing the cryptocurrency price series into a finite number of subseries, each characterized by relatively simple volatility patterns, using the variational mode decomposition (VMD) method. Next, the gated recurrent unit (GRU) neural network, in combination with an attention mechanism, predicts each modal component’s sequence separately. Additionally, the residual sequence, obtained after decomposition, undergoes further decomposition. The resultant residual sequence components serve as input to an attentive GRU (AGRU) network, which predicts the residual sequence’s future values. Ultimately, the long short-term memory (LSTM) neural network integrates the predictions of modal components and residuals to yield the final forecasted price. Empirical results obtained for daily Bitcoin and Ethereum data exhibit promising performance metrics. The root mean square error (RMSE) is reported as 50.651 and 2.873, the mean absolute error (MAE) stands at 42.298 and 2.410, and the mean absolute percentage error (MAPE) is recorded at 0.394% and 0.757%, respectively. Notably, the predictive outcomes of the VMD-AGRU-RESVMD-LSTM model surpass those of standalone LSTM and GRU models, as well as other hybrid models, confirming its superior performance in cryptocurrency price forecasting.

Solar energy has become a promising renewable energy source, offering significant opportunities for photovoltaic (PV) systems. Accurate and reliable PV generation forecasts are crucial for efficient grid integration and optimized system planning. However, the complexity of environmental factors, including seasonal and daily patterns, as well as social behaviors and user habits, presents significant challenges. Traditional prediction models often struggle with capturing the complex nonlinear dynamics in multivariate time series, leading to low prediction accuracy. To address this issue, this paper proposes a new PV power prediction method that considers factors such as light, air pressure, wind direction, and social behavior, assigning different weights to them to accurately extract nonlinear feature relationships. The framework integrates long short-term memory (LSTM) and gated recurrent units (GRU) to capture local time features, while bidirectional LSTM (BiLSTM) and an attention mechanism extract global spatiotemporal relationships, effectively capturing key features related to historical output. This improves the accuracy of multi-step predictions. To verify the feasibility of the method for multivariate time series, we conducted experiments using PV power prediction as a scenario and compared the results with LSTM, CNN, BiLSTM, CNN-LSTM and GRU models. The experimental results show that the proposed method outperforms these models, with a mean absolute error (MAE) of 12.133, root mean square error (RMSE) of 14.234, mean absolute percentage error (MAPE) of 2.1%, and a coefficient of determination (R2) of 0.895. These results indicate the effectiveness and potential of the method in PV prediction tasks.

Abstract. Rainfall time series prediction is essential for monitoring urban hydrological systems, but it is challenging and complex due to the extreme variability of rainfall. A hybrid deep learning model (VMD-RNN) is used in order to improve prediction performance. In this study, variational mode decomposition (VMD) is first applied to decompose the original rainfall time series into several sub-sequences according to the frequency domain, where the number of decomposed sub-sequences is determined by power spectral density (PSD) analysis. To prevent the disclosure of forthcoming data, non-training time series are sequentially appended for generating the decomposed testing samples. Following that, different recurrent neural network (RNN) variant models are used to predict individual sub-sequences, and the final prediction is reconstructed by summing the prediction results of sub-sequences. These RNN variants are long short-term memory (LSTM), gated recurrent unit (GRU), and bidirectional LSTM (BiLSTM) and bidirectional GRU (BiGRU), which are optimal for sequence prediction. In addition to three common evaluation criteria, mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE), the framework of universal multifractals (UMs) is also introduced to assess the performance of predictions, which enables the extreme variability of predicted rainfall time series to be characterized. The study employs two rainfall time series with daily and hourly resolutions, respectively. The results indicate that the hybrid VMD-RNN model provides a reliable one-step-ahead prediction, with better performance in predicting high and low values than the pure LSTM model without decomposition.

Short term traffic flow prediction of expressway service area based on STL-OMS

Accurate traffic congestion estimation and prediction are critical building blocks for smart trip planning and rerouting decisions in transportation systems. Over the decades, there have been many studies focusing on traffic congestion estimation and prediction with different statistical approaches (e.g., Markov chain) and machine learning models (e.g., clustering, Bayesian networks, and artificial neural networks). However, there is a lack of a unified framework to address the mechanisms of different models and integrate the advantages of different methods through combinations. This paper introduces the FD-Markov-LSTM model, a hybrid interpretable approach that combines the fundamental diagram (FD), Markov chain, and long short-term memory (LSTM). The aim is to estimate and predict traffic states by integrating statistical data in both congested and uncongested scenarios. The FD-Markov-LSTM model leverages the FD to identify hierarchical traffic states and utilizes the Markov process to capture the probabilistic transitions between these states. We employ the LSTM model to further capture the residual time series produced by the Markov chain model (assuming a memoryless property) to enhance the estimation and prediction performance. The proposed model's accuracy in estimating and predicting traffic flow is evaluated using empirical data from three case studies conducted in Beijing and Los Angeles. The results highlight a significant improvement in accuracy compared to classical benchmark models such as the Markov model, ARIMA model, k-Nearest Neighbor model, Random Forest model, and LSTM. Specifically, the FD-Markov-LSTM model achieves reductions of over 39% in mean absolute error, 35% in root mean squared error, and 7.4% in mean absolute percentage error. These results clearly demonstrate that the FD-Markov-LSTM model outperforms the benchmark models, enabling more precise predictions of traffic flow.