地理学

上海市水资源生态足迹分析与SVR预测

  • 曹 坤 ,
  • 刘素霞
展开
  • 华东师范大学 计算机科学技术系, 上海 200241

收稿日期: 2015-09-15

  网络出版日期: 2016-09-29

Analysis and SVR predication of water resources ecological footprint in Shanghai

  • CAO Kun ,
  • LIU Su-xia
Expand
  • Department of Computer Science and Technology, East China Normal University, Shanghai 200241, China

Received date: 2015-09-15

  Online published: 2016-09-29

摘要

根据水资源生态足迹模型, 以北京市2001---2013年水资源生态足迹和生态承载力为参照, 对上海市同年份的水资源生态足迹和生态承载力进行计算并对比分析了利用现状;引入机器学习中的支持向量回归机 SVR, 对上海市 2014---2016 年生态足迹进行了预测, 并给出可能的影响因素. 研究结果表明, 2001---2010 年上海市历年水生态足迹基本持平且数值较大, 2011---2013 年较往年出现明显下降. 2001---2013 年一直表现为生态赤字, 水资源差值生态压力指数年均值为 -3.083 11, 说明本地的水资源无法自给自足, 需要过境水的补给来满足生产生活的需求. 上海市万元GDP和万元工业GDP生态足迹呈下降趋势, 说明产业结构在优化, 水资源经济效益在提高, 但其年均值都高于北京市, 仍存在改善空间. 预测2014---2016年生态足迹总体呈上升趋势, 水危机形势日益严峻, 保护水资源, 促进可持续发展已刻不容缓.

本文引用格式

曹 坤 , 刘素霞 . 上海市水资源生态足迹分析与SVR预测[J]. 华东师范大学学报(自然科学版), 2016 , 2016(4) : 139 -149 . DOI: 10.3969/j.issn.1000-5641.2016.04.016

Abstract

Based on the ecological footprint model and the carrying capacities of water resources from 2001 to 2013 in Beijing, the ecological footprint and the carrying capacities in Shanghai at the same year were calculated and the current situation was analyzed. Furthermore, using the techniques of Support Vector Regression (SVR) in machine learning, the ecological footprints in Shanghai from 2014 to 2016 were predicted, and the possible influencing factors were discussed. The results show that the ecological footprints of water from 2001 to 2010 keep steady, while from 2011 to 2013 there are significant reductions
compared with previous years. The status of water resources from 2001 to 2013 have been characterized by ecological deficit, and the annual average of difference of water resources ecological pressure index is −3.083 11, which demonstrates that the local water resources cannot be self-sufficient, so as to need transit water resources to meet the needs of normal production and living. In spite of the industrial structure in the optimization and economic benefits of water resources in improving, the ecological footprint of ten thousand yuan GDP and ten thousand yuan industrial GDP in Shanghai is on the decline, and the average
is higher than Beijing, and therefore there is still improve space. The predicted results show that the ecological footprint from 2014 to 2016 will present a rising trend every year. The situation of water crisis will be increasingly serious, thus measures of protection of water resources and promoting the sustainable development should be put into effect.

参考文献

[1] WILLIAM E R. Ecological footprints and appropriated carrying capacity: What urban economics leaves out [J]. Environment and Urbanization. 1992, 4(2): 121-130.
[2] WACKERNAGEL M, REES W. Our ecological footprint: Reducing human impact on the earth [M]. Gabriola Island: New Society Publishers, 1998.
[3] 黄林楠, 张伟新, 姜翠玲, 等. 水资源生态足迹计算方法[J]. 生态学报, 2008, 28(3): 1279-1286.
[4] 李培月, 钱会, 吴健华, 等. 银川市 2008 年水资源生态足迹研究与分析[J]. 南水北调与水利科技, 2010, 8(1): 69-71.
[5] 徐珊, 夏丽华, 陈智斌, 等. 基于生态足迹法的广东省水资源可持续利用分析[J]. 南水北调与水利科技, 2013, 11(5): 11-15.
[6] 谭秀娟, 郑钦玉. 我国水资源生态足迹分析与预测[J]. 生态学报, 2009, 29(7): 3559-3568.
[7] 周悦, 谢屹. 基于生态足迹模型的辽宁省水资源可持续利用分析[J]. 生态学杂志, 2014, 33(11): 3157-3163.
[8] 方伟成, 孙成访. 基于水资源生态足迹模型的东莞市水资源可持续性研究[J]. 水电能源科学, 2014, 32(1): 25-28.
[9] 于冰, 徐琳瑜. 城市水生态系统可持续发展评价:以大连市为例[J]. 资源科学, 2014, 36(12): 2578-2583.
[10] 王文国, 何明雄, 潘科, 等. 四川省水资源生态足迹与生态承载力的时空分析[J]. 自然资源学报, 2011, 26(9): 1555-1565.
[11] 胡永红, 吴志峰, 李定强. 基于 ARIMA 模型的区域水生态足迹时间序列分析[J]. 生态环境, 2006, 15(1): 94-98.
[12] 罗娜. 辽宁省水资源生态足迹动态变化与时间序列预测分析研究[D]. 大连: 辽宁师范大学, 2012.
[13] 李玉平, 王晓妍, 朱琛, 等. 邢台市水资源生态足迹核算与预测研究[J]. 水土保持研究, 2014, 21(3): 227-230.
[14] 张勃, 刘秀丽. 基于ARIMA模型的生态足迹动态模拟和预测:以甘肃省为例[J]. 生态学报, 2011, 31(20): 6251-6260.
[15] 龚国勇. ARIMA模型在深圳GDP预测中的应用[J]. 数学的实践与认识, 2008, 38(4): 53-57
[16] 同小军, 陈绵云. 基于级差格式的灰色 Logistic 模型[J]. 控制与决策, 2002, 17(5): 554-558.
[17] 陈果, 周伽. 小样本数据的支持向量机回归模型参数及预测区间研究[J]. 计量学报, 2008, 29(1): 92-96.
[18] VAPNIK V N. 统计学习理论的本质[M]. 张学工~~译. 北京: 清华大学出版社, 2000.
[19] MEYER D, LEISCH F, HORNIK K. Benchmarking support vector machines [R]. Austria: Vienna University of Economics and Business Administration, 2002.
[20] BRERETON R G, LLOYD G R. Support vector machines for classification and regression [J]. Analyst, 2010, 135(2): 230-267.
[21] GUNN S R. Support vector machines for classification and regression [R]. United Kingdom: University of Southampton, 1998.
[22] BASAK D, PAL S, PATRANABIS D C. Support vector regression[J]. Neural Information Processing-Letters and Reviews, 2007, 11(10): 203-224.
[23] SMOLA A J, SCH\"{O]LKOPF B. A tutorial on support vector regression [J]. Statistics and computing, 2004, 14(3): 199-222.
[24] 赵莹. 支持向量机中高斯核函数的研究[D]. 上海:华东师范大学, 2007.
[25] 鞠鲁峰, 王群京, 李国丽, 等. 永磁球形电机的支持向量机模型的参数寻优[J]. 电工技术学报, 2014, 29(1): 85-90.
[26] 吴景龙, 杨淑霞, 刘承水. 基于遗传算法优化参数的支持向量机短期负荷预测方法[J]. 中南大学学报(自然科学版), 2009, 40(1): 180-184.
[27] 雷开友. 粒子群算法及其应用研究[D]. 重庆: 西南大学, 2006.
文章导航

/