PROGRESS IN GEOGRAPHY ›› 2023, Vol. 42 ›› Issue (8): 1541-1555.doi: 10.18306/dlkxjz.2023.08.008

• Rural Tourism, Rural Recreational Agriculture, and Forest-based Health andWellness Tourism • Previous Articles     Next Articles

Evaluation of rural tourism competitiveness based on multi-source data and machine learning: A case study of Lin’an District in Hangzhou, China

ZHAO Qiuhao1(), JIN Pingbin1, WANG Bingbing1, XU Pengfei2,*()   

  1. 1. School of Earth Sciences, Zhejiang University, Hangzhou 310058, China
    2. College of Landscape Architecture, Zhejiang A&F University, Hangzhou 311300, China
  • Received:2022-10-09 Revised:2023-02-19 Online:2023-08-28 Published:2023-08-25
  • Contact: XU Pengfei;
  • Supported by:
    Soft Science Research Project of Zhejiang Province(2022C35090);Social Science Federation Project of Zhejiang Province(2023N043);Research Development Fund Project of Zhejiang Agriculture and Forestry University(2022LFR031)


Evaluating tourism competitiveness is important for ensuring the sustainable development of rural tourism. In the digital information era, multi-source data and machine learning methods can efficiently reveal the characteristics of relevant elements from a geospatial perspective, providing a new method for scientific evaluation of rural tourism competitiveness. Based on multi-source remote sensing and Internet data at the village level from 2019 to 2022, this study identified the rural tourism competitiveness in Lin'an District of Hangzhou City using four machine learning models, including logistic regression (LR), support vector machine (SVM), random forest (RF), and extreme gradient boosting tree (XGB), and the optimal model was selected to reveal the spatial pattern of competitiveness and analyze the critical indicators of identification. The results show that: 1) The accuracy of the rural tourism competitiveness evaluation using the random forest (RF) model is better than the other three machine learning models. 2) Tourism resources, service facilities, accessibility, and policy conditions are the main factors affecting the rural tourism competitiveness. 3) Villages in the high tourism competitiveness category are distributed in strips in the northern and western areas of Lin'an District, with superior development conditions. The medium competitiveness villages are distributed in clumps in the eastern and central-western areas of the district, which have lower quality of tourism resources and service facilities. Low-competitiveness villages are distributed in patches in the central and western areas of the district, with superior ecological environment and land endowment, but lacking resource development and policy support. The study results may provide some policy references and technical supports for promoting the sustainable development of rural tourism.

Key words: tourism competitiveness, machine learning, rural tourism, regional tourism, rural revitalization