Data-Driven Analysis and Optimization of Container Terminal Operations: A Digital Yard Feature Model With Deep-Tree Cascaded Regression

With the rapid expansion of global logistics networks, container terminals, as critical nodes in the logistics chain, exert significant influence on the overall performance of supply chains. In terminal operations, container stacking strategies and equipment configuration are core factors determining operational efficiency. However, due to the complexity of terminal operations and the existence of multi-layered feedback mechanisms, there is currently a lack of systematic and quantitative evaluation methods to analyze the advantages and disadvantages of stacking strategies and equipment configurations. To address this gap, this study proposes a data-driven analytical framework. By processing real-world terminal operation data, the framework constructs a digital yard feature model, extracts key spatiotemporal operational features, and integrates the spatial feature extraction capability of 3D Convolutional Neural Networks (3DCNN) with the advantages of Boosting algorithms in handling non-linear relationships and feature importance. The study introduces a novel Deep-Tree Cascaded Regression (DTCR) algorithm to predict vessel handling efficiency, a highly uncertain and nonlinear indicator, to quantitatively assess the practical impact of different stacking strategies and equipment configurations. Experimental results demonstrate that the proposed model accurately captures the key correlations between container stacking and terminal operations, predicts vessel handling efficiency within a reasonable accuracy range, and realistically reflects the terminal’s operational processes. These findings provide a scientific basis for optimizing yard stacking strategies and equipment operation workflows, effectively improving overall terminal operational efficiency. Additionally, this research offers technical support and practical insights for the development of smart ports.