长江流域资源与环境 >> 2020, Vol. 29 >> Issue (11): 2406-2416.doi: 10.11870/cjlyzyyhj202011008

• 自然资源 • 上一篇    下一篇

基于五种模型比较的湖南省生态旅游需求预测研究

邹伏霞1, 邹冬生2   

  1. ( 1.湖南农业大学生物科学技术学院,湖南 长沙 410128;2. 湖南农业大学生态经济研究所,湖南 长沙 410128)
  • 出版日期:2020-11-20 发布日期:2020-12-17

A Study on Forecast of Ecotourism Demand in Hunan Province Based on the Comparison of Five Models

ZOU  Fu-xia 1 , ZOU Dong-sheng 2   

  1. (1.Biological Science and Technology College, Hunan Agricultural University, Changsha 410128,China;2. Institute of ecological economics,Hunan Agricultural University, Changsha 410128, China )
  • Online:2020-11-20 Published:2020-12-17

摘要: 从供求关系视角对湖南省生态旅游需求预测有利于生态旅游资源的优化配置与生态旅游产业的可持续发展。为了进一步了解湖南省生态旅游市场需求,以2008~2017年生态旅游相关数据为样本数据,运用GM(1,1)预测模型、线性回归预测模型、非参数模型、BP神经网络预测模型、时间序列预测模型(2)五种预测模型对湖南省生态旅游需求进行预测,得到线性回归模型的模拟精度最高。因此,采用线性回归模型对湖南省生态旅游总收入和生态接待旅游总人数进行预测。结果显示:2021~2025年期间,湖南省生态旅游总收入和接待生态旅游总人数呈中低速曲线递增趋势,其中生态旅游总收入名列前5强的市州是长沙、张家界、岳阳、湘潭和益阳市;生态旅游接待人数名列前5强的市州是长沙、常德、衡阳、郴州、益阳市。在各市州之间,存在生态旅游总收入与生态旅游人数不对等现象,尤以常德和张家界两市最为典型。

Abstract: Forecast of ecotourism demand in Hunan Province from the perspective of supply and demand is conducive to the optimal allocation of eco-tourism resources and the sustainable development of eco-tourism industry. In order to further understand the demand of eco-tourism market in Hunan Province, this study uses the relevant data of eco-tourism from 2008 to 2017 as sample data, and uses GM (1,1) prediction model, linear regression prediction model, nonparametric model, BP neural network prediction model and time series prediction model (2) to predict the demand of eco-tourism in Hunan Province, and obtains the highest simulation accuracy of linear regression model.Therefore, the linear regression model is used to predict the total ecological tourism revenue and the total number of ecological tourists in Hunan Province.The results show that the total ecological tourism revenue and total number of ecological tourists received in Hunan Province are in curve growth at medium-low speed: from 2021 to 2025, Top 5 cities and prefectures in total ecological tourism revenue are Changsha, Zhangjiajie, Yueyang, Changde, Xiangtan andYiyang ; Top5 cities and prefectures in the total number of ecological tourists received are Changsha, Changde, Hengyang, Chenzhou, Yiyang. Different cities and prefectures are unequal in total revenue and number of tourists, represented by Changde and Zhangjiajie.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 黄金川,方创琳,冯仁国. 三峡库区城市化与生态环境耦合关系定量辨识[J]. 长江流域资源与环境, 2004, 13(2): 153 -158 .
[2] 闫东升, 杨槿, 陈雯. 失地农民生活满意度测度及影响因素研究——以南京市仙林新村为例[J]. 长江流域资源与环境, 2018, 27(07): 1450 .
[3] 张婷, 王学雷, 耿军军, 班璇, 杨超, 吕晓蓉. 基于MIKE21和灰色模式识别模型的洪湖水质模拟与评价[J]. 长江流域资源与环境, 2018, 27(09): 2090 -2100 .
[4] 陈叶华, 李志威, 沈小雄, . 芭蕉湖-南湖连通工程的连通性评价[J]. 长江流域资源与环境, 2019, 28(03): 731 -738 .
[5] 高艳丽, 董 捷, 李 璐, 李红波. 碳排放权交易政策的有效性及作用机制研究——基于建设用地碳排放强度省际差异视角[J]. 长江流域资源与环境, 2019, 28(04): 783 -793 .
[6] 黄隆杨, 刘胜华, 李健. 城市生态用地时空动态及其相关驱动力——以武汉市为例[J]. 长江流域资源与环境, 2019, 28(05): 1059 -1069 .
[7] 魏小芳, 赵宇鸾, 李秀彬, 薛朝浪, 夏四友. 基于“三生功能”的长江上游城市群国土空间特征及其优化[J]. 长江流域资源与环境, 2019, 28(05): 1070 -1079 .
[8] 邹润彦, 周宏冀, 郭熙, 但承龙, 吕添贵, 李洪义. 环鄱阳湖区农田土壤有机碳影响因素空间分布格局分析及制图研究[J]. 长江流域资源与环境, 2019, 28(05): 1121 -1131 .
[9] 秦 腾, 章恒全, 佟金萍. 安徽省用水网络管理与关键区域界定[J]. 长江流域资源与环境, 2019, 28(06): 1304 -1313 .
[10] 郭强, 孟元可, 樊龙凤, 叶许春. 基于IHA/RVA法的近年来鄱阳湖生态水位变异研究[J]. 长江流域资源与环境, 2019, 28(07): 1691 -1701 .