Intelligent assessment of industrial green total factor productivity based on multimodal data fusion
Year: 2025
Type: conference-paper
Abstract: An intelligent assessment model that fuses different types of data for the assessment of industrial green productivity is described in this article. This model solves the problems of missing data and temporal and spatial dependencies by using a cross-modal attention network and a spatio-temporal graph convolutional network. The results show that the model is much more accurate than traditional assessment techniques, that it can accurately recover from missing data, and that it can capture the impact of policy changes on production efficiency and technology spillovers between different areas. The results also show that technological innovation, the use of clean energy and the reduction of environmental pollution are the most important factors influencing the green productivity of industries. Based on the evaluation results of this model, it provides an effective data support tool for promoting the green transformation of industries, as the adjustment of industrial layout has led to a significant increase in green production efficiency in industrial parks in one province.
Author: Jianying Huang
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W4413812507