Search

Predicting short-term passenger flow accurately is of great significance for daily management and for a timely emergency response of rail transit networks. In this paper, we propose an attention-based Graph–Temporal Fused Neural Network (GTFNN) that can make online predictions of origin–destination (OD) flows in a large-scale urban transit network. In order to solve the key issue of the passenger hysteresis in online flow forecasting, the proposed GTFNN takes finished OD flow and a series of features, which are known or observable, as the input and performs multi-step prediction. The model is constructed from capturing both spatial and temporal characteristics. For learning spatial characteristics, a multi-layer graph neural network is proposed based on hidden relationships in the rail transit network. Then, we embedded the graph convolution into a Gated Recurrent Unit to learn spatial–temporal features. For learning temporal characteristics, a sequence-to-sequence structure embedded with the attention mechanism is proposed to enhance its ability to capture both local and global dependencies. Experiments based on real-world data collected from Chongqing's rail transit system show that the metrics of GTFNN are better than other methods, e.g., the SMAPE (Symmetric Mean Absolute Percentage Error) score is about 14.16%, with a range from 5% to 20% higher compared to other methods. [ABSTRACT FROM AUTHOR]

House price is closely associated with the development of the national economy and people's daily life. Understanding the spatial distribution characteristics and influencing factors of the house price is of great practical significance. Although a lot of attention has been paid to modeling the house price from structure and location attributes, limited work has considered the impact of visual attributes. Intuitively, a better visual environment may raise the surrounding house price. When aggregating multiple factors that influence house price, the multiscale geographically weighted regression (MGWR) provides a suitable solution. Specifically, the MGWR assigns each factor a bandwidth to model the spatial heterogeneity, e.g., a factor may have different influences at different places. In this paper, we introduce the visual environment factors into the MGWR method. In detail, we extract ten visual elements, e.g., sky, vegetation, road, from the Baidu street view (BSV) images, using a deep learning framework. We further define six visual environment factors to investigate their influence on house price. Based on the data from two representative Chinese cities, i.e., Beijing and Chongqing, we reveal the influence degree and spatial scale difference of six visual indexes on the house price in two cities. Results show that: (1) the influence intensity of our proposed six visual environment factors on the house price in different regions of the city can be identified, and the green view index (GVI) is the most important visual environmental factor; and (2) the influence of these view indexes changes significantly or even reversely depends on different areas. [ABSTRACT FROM AUTHOR]

It is difficult for a single model to simultaneously capture the nonlinear, correlation, and periodicity of data series in the passenger flow prediction of urban rail transit (URT). To better predict the short-term passenger flow of URT, based on the long short-term memory network (LSTM) model, a deep learning model prediction method combining the time convolution network (TCN) and the long short-term memory network (LSTM) based on machine learning is proposed. The model couples the external factors such as date attributes, weather conditions, and air quality, to improve the overall prediction performance and solve the difficulty of accurate prediction due to the large fluctuation and randomness of short-term passenger flow in rail transit. Using the swiping data and related weather information of some stations of Chongqing Rail Transit Line 3, the TCN-LSTM model is verified by an example, and the prediction results of the single LSTM model are given for comparison. The results show that the TCN-LSTM model can better predict the passenger flow characteristics of different stations at different times. Compared with the single LSTM model, the TCN-LSTM model has better prediction accuracy and data generalization ability. [ABSTRACT FROM AUTHOR]

Land use/cover change (LUCC) refers to the phenomenon of changes in the Earth's surface over time. Accurate prediction of LUCC is crucial for guiding policy formulation and resource management, contributing to the sustainable use of land, and maintaining the health of the Earth's ecosystems. LUCC is a dynamic geographical process involving complex spatiotemporal dependencies. Existing LUCC simulation models suffer from insufficient spatiotemporal feature learning, and traditional cellular automaton (CA) models exhibit limitations in neighborhood effects. This study proposes a cellular automaton model based on spatiotemporal feature learning and hotspot area pre-allocation (VST-PCA). The model utilizes the video swin transformer to acquire transformation rules, enabling a more accurate capture of the spatiotemporal dependencies inherent in LUCC. Simultaneously, a pre-allocation strategy is introduced in the CA simulation to address the local constraints of neighborhood effects, thereby enhancing the simulation accuracy. Using the Chongqing metropolitan area as the study area, two traditional CA models and two deep learning-based CA models were constructed to validate the performance of the VST-PCA model. Results indicated that the proposed VST-PCA model achieved Kappa and FOM values of 0.8654 and 0.4534, respectively. Compared to other models, Kappa increased by 0.0322–0.1036, and FOM increased by 0.0513–0.1649. This study provides an accurate and effective method for LUCC simulation, offering valuable insights for future research and land management planning. [ABSTRACT FROM AUTHOR]

One of the focal points in Geographic Information Science (GIS) is to uncover the spatial distribution patterns of geographical phenomena. In response to the insufficient spatial feature learning concerning neighborhoods in traditional machine learning-based Cellular Automata (CA) models for land use change, this study couples the Random Forest (RF) model and the Spatially Non-Stationary Convolutional Neural Network (SNSCNN) model to the CA model. The resulting RF-SNSCNN-CA model considers the issue of spatial non-stationarity by incorporating attention mechanisms. Using observed urban land change data from 2010 to 2017 in the 21 districts of Chongqing's main city as an example, two sets of experiments comprising eight scenarios were designed to verify the neighborhood effects. The results demonstrate that the proposed RF-SNSCNN-CA model achieves an Overall Accuracy (OA) of 97.82%, Kappa of 0.7683, and Figure of Merit (FoM) of 0.3836. The study reveals the following findings. Firstly, the RF-SNSCNN-CA model integrates the dual advantages of traditional machine learning and deep learning models, in which SNSCNN improves by the combined effect of channel and spatial attention mechanisms improves the learning of neighborhood features; secondly, the machine learning-like urban sprawl CA modeling process, regardless of the approach taken to obtain development suitability, cannot completely replace the learning of the neighborhood part; lastly, the use of traditional neighborhood modeling methods may produce suppression of simulation results and make the model inadequately learn spatial features. [ABSTRACT FROM AUTHOR]