Dynamic Graph Convolutional Network-Based Prediction of the Urban Grid-Level Taxi Demand–Supply Imbalance Using GPS Trajectories

• Published in: ISPRS international journal of geo-information Vol. 13; no. 2; p. 34
• Main Authors: Yang, Haiqiang, Li, Zihan
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.01.2024
• Subjects: Ablation; Algorithms; Artificial neural networks; Deep learning; dynamic graph convolution; Forecasting; gated recurrent unit; graph convolutional network; Impact analysis; Neural networks; prediction; Prediction models; Supply & demand; supply balance; taxi demand–supply imbalance; taxi trajectory data; Taxicabs; time series analysis; traffic; Traffic flow; travel; Trends

The objective imbalance between the taxi supply and demand exists in various areas of the city. Accurately predicting this imbalance helps taxi companies with dispatching, thereby increasing their profits and meeting the travel needs of residents. The application of Graph Convolutional Networks (GCN...