A prompt and precise estimation of traffic conditions on the scale of a few minutes by analyzing past data is crucial for establishing an effective intelligent traffic management system. Nevertheless, because of the irregularity and nonlinear features of traffic flow data, developing a prediction model with excellent robustness poses a significant obstacle. Therefore, we propose genetic-search-algorithm-improved kernel extreme learning machine, termed GA-KELM, to unleash the potential of improved prediction accuracy and generalization performance. By substituting the inner product with a kernel function, the accuracy of short-term traffic flow forecasting using extreme learning machines is enhanced. The genetic algorithm evades manual traversal of all possible parameters in searching for the optimal solution. The prediction performance of GA-KELM is evaluated on eleven benchmark datasets and compared with several state-of-the-art models. There are four benchmark datasets from the A1, A2, A4, and A8 highways near the ring road of Amsterdam, and the others are D1, D2, D3, D4, D5, D6, and P, close to Heathrow airport on the M25 expressway. On A1, A2, A4, and A8, the RMSEs of the GA-KELM model are 284.67 vehs/h, 193.83 vehs/h, 220.89 vehs/h, and 163.02 vehs/h, respectively, while the MAPEs of the GA-KELM model are 11.67%, 9.83%, 11.31%, and 12.59%, respectively. The results illustrate that the GA-KELM model is obviously superior to state-of-the-art models.

Short-term traffic flow forecasting, an essential enabler for intelligent transportation systems, is a fundamental and challenging task for dramatically changing traffic flow over time. In this paper, we present a gravitational search optimized kernel extreme learning machine, named GSA-KELM, to avoid manually traversing all possible parameters to improve the potential performance. Furthermore, with the interference of heavy-tailed impulse noise, the performance of KELM may be seriously deteriorated. Based on the Kalman filter that cleverly combines observed data and estimated data to perform the closed-loop management of errors and limit the errors within a certain range, we propose a combined model, termed GSA-KELM-KF. The experimental results of two real-world datasets demonstrate that GSA-KELM-KF outperforms the state-of-the-art parametric and non-parametric models.

Accurate traffic flow forecasting is vital for intelligent transportation systems, especially with urbanization worsening traffic congestion, which affects daily life, economic growth, and the environment. Precise forecasts aid in managing and optimizing transportation systems, reducing congestion, and improving air quality by cutting emissions. However, predicting outcomes is difficult due to intricate spatial relationships, nonlinear temporal patterns, and the challenges associated with long-term forecasting. Current research often uses static graph structures, overlooking dynamic and long-range dependencies. To tackle these issues, we introduce the spatiotemporal dynamic multi-hop network (ST-DMN), a Seq2Seq framework. This model incorporates spatiotemporal convolutional blocks (ST-Blocks) with residual connections in the encoder to condense historical traffic data into a fixed-dimensional vector. A dynamic graph represents time-varying inter-segment relationships, and multi-hop operation in the encoder’s spatial convolutional layer and the decoder’s diffusion multi-hop graph convolutional gated recurrent units (DMGCGRUs) capture long-range dependencies. Experiments on two real-world datasets METR-LA and PEMS-BAY show that ST-DMN surpasses existing models in three metrics.

With global warming, coastal areas are exposed to multiple climate-related hazards. Understanding the facts and attribution of regional climate change in coastal communities is a frontier science challenge. In this study, we focus on fact analysis of multi-scale climate changes in the Guangdong–Hong Kong–Macao Greater Bay area (GBA) and around the Baltic Sea area (BSA). We selected three Asian stations from the GBA in South China (Guangzhou, Hong Kong, and Macao) and five European stations around the Baltic Sea (Stockholm, Haparanda A, Vestervig, Poznan, and Frankfurt) from four countries in the BSA as representative stations, which have more than 100- or 150-year datasets. Based on the ensemble empirical mode decomposition (EEMD) and Mann–Kendall methods, this study focuses on the multi-scale temperature and precipitation fluctuation and mutation analysis in the past. The multi-scale analyses show that there are four time-scale changes in both areas. They are the inter-annual scale, inter-decadal scale, centennial scale, and trend, but the lengths of different timescales vary in both regions, especially the inter-decadal scale and centennial scale. For temperature, the inter-annual scales show the same results, with 2–4 and 7–9 a in both the GBA and BSA. In the GBA, the inter-decadal scales are 10–14, 30–50, and 55–99 a, while in the BSA, they are 13–20, 26–50, and 66–99 a. For centennial scales, there are 143–185 and 200–264 a in the BSA and about 100–135 a in the GBA. Temperature trends in the GBA reveal that the coastal area has experienced an upward trend (Hong Kong and Macao), but in the inland area (Guangzhou), the trend fluctuated. Temperature trends in the BSA have risen since 1756. For precipitation, the inter-annual scales are 2–4 and 6–9 a in both the GBA and BSA. The inter-decadal scales are 11–29 and 50–70 a in the GBA and 11–20, 33–50, and 67–86 a in the BSA. For centennial scales, there are about 100 a in the GBA and 100–136 a in the BSA. In the GBA, the precipitation trends show stronger local characteristics, with three different fluctuation types. In the BSA, most stations had a fluctuating trend except Haparanda A and Vestervig station, which experienced an upward trend throughout the whole time range. Overall, there are no unified trends for precipitation in both areas. Temperature mutation tests show that only Vestervig in the BSA changed abruptly in 1987, while the mutation point of Macao in the GBA was 1991. Precipitation mutation points of Stockholm and Vestervig were 1878 and 1918 in the BSA, while only Macao in the GBA changed abruptly in 1917. The results reveal that the regional climate mutation of both areas is not obvious, but the temperature changes with an upward trend as a whole.