Precipitation forecasting is an immensely significant aspect of meteorological prediction. Accurate weather predictions facilitate services in sectors such as transportation, agriculture, and tourism. In recent years, deep learning-based radar echo extrapolation techniques have found effective applications in precipitation forecasting. However, the ability of existing methods to extract and characterize complex spatiotemporal features from radar echo images remains insufficient, resulting in suboptimal forecasting accuracy. This paper proposes a novel extrapolation algorithm based on a dual-branch encoder–decoder and spatiotemporal Gated Recurrent Unit. In this model, the dual-branch encoder–decoder structure independently encodes radar echo images in the temporal and spatial domains, thereby avoiding interference between spatiotemporal information. Additionally, we introduce a Multi-Scale Channel Attention Module (MSCAM) to learn global and local feature information from each encoder layer, thereby enhancing focus on radar image details. Furthermore, we propose a Spatiotemporal Attention Gated Recurrent Unit (STAGRU) that integrates attention mechanisms to handle temporal evolution and spatial relationships within radar data, enabling the extraction of spatiotemporal information from a broader receptive field. Experimental results demonstrate the model’s ability to accurately predict morphological changes and motion trajectories of radar images on real radar datasets, exhibiting superior performance compared to existing models in terms of various evaluation metrics. This study effectively improves the accuracy of precipitation forecasting in radar echo images, provides technical support for the short-range forecasting of precipitation, and has good application prospects.

Evolutionary algorithms have been extensively utilized in practical applications. However, manually designed population updating formulas are inherently prone to the subjective influence of the designer. Genetic programming (GP), characterized by its tree-based solution structure, is a widely adopted technique for optimizing the structure of mathematical models tailored to real-world problems. This paper introduces a GP-based framework (GP-EAs) for the autonomous generation of update formulas, aiming to reduce human intervention. Partial modifications to tree-based GP have been instigated, encompassing adjustments to its initialization process and fundamental update operations such as crossover and mutation within the algorithm. By designing suitable function sets and terminal sets tailored to the selected evolutionary algorithm, and ultimately derive an improved update formula. The Cat Swarm Optimization Algorithm (CSO) is chosen as a case study, and the GP-EAs is employed to regenerate the speed update formulas of the CSO. To validate the feasibility of the GP-EAs, the comprehensive performance of the enhanced algorithm (GP-CSO) was evaluated on the CEC2017 benchmark suite. Furthermore, GP-CSO is applied to deduce suitable embedding factors, thereby improving the robustness of the digital watermarking process. The experimental results indicate that the update formulas generated through training with GP-EAs possess excellent performance scalability and practical application proficiency.

Human mobility, encompassing the movement of individuals and/or groups across space and time, significantly impacts various aspects of society, with intra-urban mobility being a major research focus of scholars in diverse disciplines. Bike-sharing systems have become an alternatives in cities for achieving more sustainable transportation. Hence, bike-sharing-related data are considered an important data source to study intra-urban human mobility. To better understand human mobility in cities, it is essential to characterize the typical patterns involved in intra-urban human mobility. This paper mainly focuses on characterizing the temporal patterns of intra-urban human mobility on bike-sharing based on the trip information of the acquired bike-sharing data. To achieve this, on the one hand, we adopted an exploratory data analysis (EDA) method to describe the temporal patterns by performing exploratory analyses of bike-sharing trips. On the other hand, we used the continuous triangular model (CTM) to conduct multi-temporal-scale analysis of bike-sharing trips for further explorations of the temporal patterns where necessary. The data of bike-sharing trips in Shanghai, China, were adopted as the dataset for the case study. Generally, the study was conducted at two different levels: the trip level and the bike level. Specifically, at each level, the explorations were conducted from varying perspectives. According to the analyses, numerous meaningful temporal patterns were discovered, and several distinctive findings were acquired. The results of this study show the effectiveness of the EDA and CTM methods in characterizing temporal patterns of intra-urban human mobility, based on which potentially insightful information and suggestions can be provided to assist related actions.

As the most significant interannual signal in the tropical Pacific, the influence of ENSO on the interannual variability in TC genesis location in the western North Pacific (WNP) has received much attention in previous studies. This paper mainly emphasizes the underlying SST factors independent of the ENSO signal and explores how they modulate interannual tropical cyclone genesis (TCG) latitude variability. Our study finds that the meridional sea temperature gradient (SSTG) between the Kuroshio Extension and the WNP still has a significant effect on the interannual variability in the TCG latitude after removing the effect of ENSO (r = 0.6). The interannual forecasts of the TCG latitude were effectively improved from 0.67 to 0.81 when the ENSO-independent SSTG and ENSO were regressed together in a multi-linear regression. We then propose an ENSO-independent physical mechanism affecting the TCG latitude. The equatorward (poleward) SSTG excited the positive (negative) Pacific–Japan telecorrelation pattern over the WNP, forming Rossby wave trains and propagating northward. A significant cyclonic vortex (anticyclonic vortex) with strong convective development (suppression) developed near 20° N, leading more TCs to the northern (southern) part of the WNP. These findings provide a new perspective for the prediction of the interannual variability in the TCG latitude.