
World Research Map
A Perceived Acoustic Landscape Model for Zhangjiajie National Forest Park
Qing Sun; Qianni Cheng; Jianlin Tian; Yanan Zhou · Journal of Engineering, Project, and Production Management · 2026
Article
- Authors
- Qing Sun; Qianni Cheng; Jianlin Tian; Yanan Zhou
- Year
- 2026
- Citation
- Vol. 16 · Issue 3
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.
Venue
- Publisher
- Engineering, Project, and Production Management (EPPM)
- Country
- US (US)
- ISSN
- 2221-6529 / eISSN 2223-8379
Keywords
acoustic environment modeling, ecotourism and sustainability, rectangular convolution kernel, self-distillation architecture, soundscape perception, spatiotemporal differences, visitor experience analysis
