Restorative Evaluation of Rural Waterside Landscapes in Mountainous Areas Integrating Semantic Segmentation and Machine Learning
Open Access
Abstract
Rural waterfront landscapes connect ecological environments with residents’ recreational experiences, and assessing their perceived restorativeness can support improvements in rural living environments. However, complex terrain and limited data availability constrain the quantitative assessment of their visual characteristics. This study examined the Changjiang River waterfront in Jinzhai County, Anhui Province, China. Panoramic imagery, semantic segmentation, and random forest regression were integrated to derive 12 objective visual indicators of landscape composition and color characteristics and to predict four dimensions of perceived restorativeness: fascination, being away, coherence, and scope. The R2 values for the hold-out test set were 0.732, 0.730, 0.722, and 0.719, respectively (n = 200). The green view index, blue view index, contrast, color count, and color complexity showed significant positive correlations with perceived restorativeness, whereas the road visibility index, mountain visual ratio, and artificial structure visibility index showed significant negative correlations. Visible blue-green elements and visual richness were associated with higher perceived-restorativeness scores, whereas images with more visually dominant road surfaces, mountains, and artificial structures tended to receive lower perceived-restorativeness scores. These findings are specific to the dry-season, low-water-level conditions observed during the November survey and should not be generalized to other seasons or hydrological conditions.Keywords
Funding Information
- National Natural Science Foundation of China (52378001)
- Education and Teaching Reform Research Project of China’s National Steering Committee for Landscape Architecture Education (LAJGXM2025046)
- Anhui Provincial Undergraduate Teaching Quality Engineering Project (2024cxtd078 and 2025xnjys017)
This publication has 41 references indexed in Scilit:
- Assessing urban river landscape visual quality with extreme learning machines: A case study of the yellow river in ningxia hui autonomous region, chinaEcological Indicators, 2024
- Subjective and objective measures of streetscape perceptions: Relationships with property value in ShanghaiCities, 2022
- Visual quality evaluation model of an urban river landscape based on random forestEcological Indicators, 2021
- Development and application of indicators for visual landscape quality to include in life cycle sustainability assessment of Swiss agricultural farmsEcological Indicators, 2020
- Hyperparameters and tuning strategies for random forestWIREs Data Mining and Knowledge Discovery, 2019
- Semantic Understanding of Scenes Through the ADE20K DatasetInternational Journal of Computer Vision, 2018
- A random forest guided tourTEST, 2016
- The restorative benefits of nature: Toward an integrative frameworkJournal of Environmental Psychology, 1995
- Color indexingInternational Journal of Computer Vision, 1991
- A Mathematical Theory of CommunicationBell System Technical Journal, 1948