APPLICATION OF CLASSIFICATION ALGORITHM OF MACHINE LEARNING AND BUFFER ANALYSIS IN TORISM REGIONAL PLANNING

TianYu Zhang, Hongfei Ji, Yang Hu, Q. Ye, Yi Lin2018 · DOI

Abstract

Remote Sensing (RS) and Geography Information System (GIS) technologies are widely used in ecological analysis and regional planning. In this study, support vector machine (SVM) classification algorithm is used to monitor the land use and land cover change (LUCC), and then to perform the ecological evaluation for Chaohu lake tourism area quantitatively. The automatic classification and the quantitative spatial-temporal analysis for the Chaohu Lake basin are realized by the analysis of multi-temporal and multispectral satellite images, DEM data and slope information data. Furthermore, the ecological buffer zone analysis is also studied to set up the buffer width for each catchment area surrounding Chaohu Lake. The results of LUCC monitoring from 1992 to 2015 has shown obvious affections by human activities. Since the construction of the Chaohu Lake basin is in the crucial stage of the rapid development of urbanization, the application of RS and GIS technique can effectively provide scientific basis for land use planning, ecological management, environmental protection and tourism resources development in the Chaohu Lake Basin.

Introduction

The Chaohu Lake basin, a major region for tourism and urban expansion in China’s Anhui Province, faces intense pressure from human activity. Rapid urbanization often leads to "Land Use and Land Cover Change" (LUCC)—the conversion of forests and wetlands into concrete and farmland—which can degrade water quality and destroy habitats. This research explores the intersection of machine learning and environmental management, applying Support Vector Machines (SVM) and Geographic Information Systems (GIS) to track 23 years of land-use changes and proposing a data-driven framework for ecological buffer zones to support sustainable tourism.

Methodology

The researchers employed a two-pronged technical approach to map the urbanization of the Chaohu Lake basin and establish protection zones.

  1. Machine Learning Classification (SVM): To categorize land use (e.g., forest, water, construction land), the team used a Support Vector Machine (SVM) algorithm. SVM is particularly effective for remote sensing because it handles non-linear data well and maintains high accuracy even with relatively small training samples. Visual signatures like color and texture were used to train the model to recognize eight distinct ground objects.
  2. Hydrological Buffer Analysis: Using ArcGIS and Digital Elevation Models (DEM), the team conducted a hydrological analysis to divide the basin into sub-catchments. They synthesized data on relative distance, elevation, and slope to calculate the optimal width for ecological buffer zones—strips of vegetation designed to filter pollutants before they reach the lake.
Methodological flowchart showing the integration of Landsat imagery and DEM data for buffer zone analysis.

Key Insights and Results

The study relies on a multi-source longitudinal dataset, including Landsat series images from 1992 to 2015. Key findings include:

  • The Urban Explosion: Construction land skyrocketed from roughly 263 km² in 1992 to over 2,149 km² in 2015. This growth was concentrated northwest of the lake, near the city of Hefei.
  • Land Use Trends: While construction land surged, cultivated land and forest land followed a "bell curve" trend—increasing initially before declining as urban sprawl took over. Algae coverage also increased (from 47.43 km² to 83.52 km²), highlighting declining lake health.
  • Classification Accuracy: SVM improved land-use classification accuracy by 3–6% compared to traditional Maximum Likelihood Classification (MLC) methods.
Area statistics of the Chaohu Lake Basin showing land use changes from 1992 to 2015.

Conclusion

The study successfully mapped 10 catchment units, providing specific meter-by-meter requirements for forest and wetland buffers. Rather than a uniform buffer, the researchers calculated widths (e.g., 80m to 180m) based on local topography and contamination risk. While challenges like spectral confusion between wetlands and cultivated land remain, this work provides a scientific basis for land use planning and environmental protection in the rapidly developing Chaohu Lake Basin.

Summary updated

Abstract

Remote Sensing (RS) and Geography Information System (GIS) technologies are widely used in ecological analysis and regional planning. With the advantages of large scale monitoring, combination of point and area, multiple time-phases and repeated observation, they are suitable for monitoring and analysis of environmental information in a large range. In this study, support vector machine (SVM) classification algorithm is used to monitor the land use and land cover change (LUCC), and then to perform the ecological evaluation for Chaohu lake tourism area quantitatively. The automatic classification and the quantitative spatial-temporal analysis for the Chaohu Lake basin are realized by the analysis of multi-temporal and multispectral satellite images, DEM data and slope information data. Furthermore, the ecological buffer zone analysis is also studied to set up the buffer width for each catchment area surrounding Chaohu Lake. The results of LUCC monitoring from 1992 to 2015 has shown obvious affections by human activities. Since the construction of the Chaohu Lake basin is in the crucial stage of the rapid development of urbanization, the application of RS and GIS technique can effectively provide scientific basis for land use planning, ecological management, environmental protection and tourism resources development in the Chaohu Lake Basin.
BibTeX
@inproceedings{zhang2018application,
  author = {TianYu ZHANG and Hongfei Ji and Yang Hu and Q. Ye and Yi Lin},
  title = {{APPLICATION OF CLASSIFICATION ALGORITHM OF MACHINE LEARNING AND BUFFER ANALYSIS IN TORISM REGIONAL PLANNING}},
  booktitle = {˜The},
  year = {2018},
  doi = {10.5194/isprs-archives-xlii-3-2297-2018},
}
Figure