Journal of Engineering, Project, and Production Management, 2026, 16(3), 2025-228
A Perceived Acoustic Landscape Model for Zhangjiajie National Forest Park
1
Teacher, School of Intelligent Construction, Jishou University, Jishou,
416000, China
2
Teacher, School of Liberal Arts, Zhangjiajie College, Zhangjiajie,
427000, China, E-mail: chenqni@outlook.com (corresponding author).
3
Teacher, School of Fine Arts, Jishou University, Jishou, 416000, China
4
Teacher, School of Intelligent Construction, Jishou University, Jishou,
416000, China
Project Management
Received October 4, 2025; revised November 26, 2025; accepted December 18, 2025
Available online April 8, 2026
Abstract: To explore tourist’s perception of soundscapes, this study selects the core scenic area of Zhangjiajie National Forest Park and takes a microphone array system to collect environmental sound data throughout the four seasons during both day and nighttime hours, while simultaneously collecting tourist’s subjective perception, evaluation, and behavioral data. By extracting and preprocessing acoustic features and combining rectangular and dilated convolution kernels, an environmental sound classification model is proposed. Subsequently, a soundscape perception model is constructed. The proposed environmental sound classification model achieved an average accuracy of 93.5% in natural sound source classification, demonstrating the best robustness across different signal-to-noise ratio levels. The parameter size was only 6.8M, and the average inference speed was 12.3ms. The sound landscape perception model demonstrated better predictive performance in dimensions such as pleasure and tranquility than the baseline model. The natural sound source area had high pleasure, naturalness, and tranquility, and low interference. The highest interference level in the traffic impact area was 4.39, with engine noise accounting for 58% of the total noise, and significant spatial and temporal differences between different regions. This model can effectively predict tourist’s perception and preferences of soundscapes, with significant differences in perception in different acoustic environments. The research provides a scientific acoustic basis for optimizing soundscapes, scenic area planning, and noise management, which helps to enhance tourist experience and promote the sustainable development of ecotourism.
Keywords: Acoustic environment modeling, ecotourism and sustainability, rectangular convolution kernel, self-distillation architecture, soundscape perception, spatiotemporal differences, visitor experience analysis.
Copyright © Journal of Engineering, Project, and Production Management (EPPM-Journal).
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported License.
Requests for reprints and permissions at eppm.journal@gmail.com.
Citation: Sun, Q., Cheng, Q., Tian, J., and Zhou, Y. (2026). A Perceived Acoustic Landscape Model for Zhangjiajie National Forest Park. Journal of Engineering, Project, and Production Management, 16(3), 2025-228.
