Exploring the relationship between tourism development and environmental pollution using an LSTM-based time series model

With the rapid development of tourism, understanding its relationship with environmental pollution has become a critical issue. Traditional research methods often struggle to effectively capture complex time series data and nonlinear associations, limiting their ability to accurately analyze and predict the interactions between tourism development and environmental changes. In response to these challenges, this research introduces a time series modeling framework leveraging LSTM-Attention-Random Forest (LARF). The LSTM model captures the temporal dynamics in tourism and environmental data, the Attention mechanism enhances the focus on critical time steps, and the Random Forest improves prediction accuracy by leveraging nonlinear relationships through ensemble learning. Experimental results demonstrate that the LARF model significantly outperforms traditional methods in prediction accuracy and generalization ability across multiple datasets, with an average improvement of 18.2% in MSE and 16.5% in MAPE compared to baseline models like LSTM, GRU, and Random Forest. Specifically, the LARF model achieves an MSE of 30.0 on the Global Tourism Data and 35.0 on the China City Air Quality Data, highlighting its robustness and reliability. Furthermore, the model provides innovative insights for pollutant risk quantification and environmental management, offering actionable recommendations for sustainable tourism and environmental governance. This study contributes not only to advancing methodologies for analyzing tourism and environmental systems but also offers a versatile framework that can be applied to other complex systems for predictive modeling and decision support in the future.