基于粗糙集和BP神经网络的流域水资源脆弱性预测研究——以淮河流域为例

doi:10.11870/cjlyzyyhj201609002

长江流域资源与环境 >> 2016, Vol. 25 >> Issue (09): 1317-1327.doi: 10.11870/cjlyzyyhj201609002

基于粗糙集和BP神经网络的流域水资源脆弱性预测研究——以淮河流域为例

刘倩倩, 陈岩

南京林业大学经济管理学院, 江苏南京 210037

收稿日期:2015-12-21 修回日期:2016-02-19 出版日期:2016-09-20
通讯作者: 陈岩 E-mail:sanchen007@163.com
作者简介:刘倩倩(1991~),女,硕士研究生,主要研究方向为管理科学与工程、水资源管理.E-mail:dkjoy77@sina.com
基金资助:
国家自然基金青年项目“基于奈特不确定性理论的流域水资源脆弱性分析与适应性治理研究”（71403122）；江苏省自然基金青年项目“流域水资源关键脆弱性分析与适应性治理研究”；教育部人文社科基金青年项目“基于影响因素风险预测的流域水资源脆弱性分析与适应性治理研究”

VULNERABILITY PREDICTION OF BASIN WATER RESOURCES BASED ON ROUGH SET AND BP NEURAL NETWORK——A CASE OF HUAIHE BASIN

LIU Qian-qian, CHEN Yan

School of Economics and Management, Nanjing Forestry University, Nanjing 210037, China

Received:2015-12-21 Revised:2016-02-19 Online:2016-09-20
Supported by:
National Natural Foundation for young scholar (71403122)(BK20140980);Natural Foundation of Jiangsu Province for young scholar (BK20140980)(14YJC630018);Humanities and Social Science Foundation of Chinese Ministry of Education for young scholar (14YJC630018)

摘要/Abstract

摘要： 水资源是一种重要的自然资源和经济资源，对其未来的脆弱性进行预测可以预估研究区未来的水安全状况，对其脆弱性问题做出预警，从而及时采取治理措施。因此，合理科学的水资源脆弱性预测研究是缓解水资源脆弱性的有效手段。目前，水资源脆弱性研究主要是针对水资源现状进行评价，对其未来状况的预测较少。集成了粗糙集和BP神经网络两种方法，首先采用改进了的盲目删除法对构建的流域水资源脆弱性评价指标体系进行约简，其次通过BP神经网络拟合约简后的指标数据与脆弱度之间的映射关系，构建流域水资源脆弱性评价预测模型。基于之前研究的样本数据和脆弱性结果，探讨淮河流域未来的水资源脆弱性状况。结果表明：淮河流域2015年、2020年和2025年的水资源脆弱度分别为0.305、0.359和0.390，处于轻度脆弱和中度脆弱的状况，除2015年脆弱性状况有所好转以外，2020年和2025年的水资源脆弱性程度与近几年相比有所加剧，根据指标数据可知该现象主要是受年降水量、人均用水量、万元GDP废水排放量、垦殖指数、有效灌溉面积比和干旱面积受灾比6个指标的影响，为避免水资源脆弱性的加剧，应当有针对性的加强这几个方面的管理和控制。

关键词: 流域水资源, 脆弱性预测, 粗糙集, BP神经网络, 淮河流域

Abstract: Water is an important natural and economic resource. Predicting its vulnerability can forecast the water security and give an early warning of its vulnerability in given areas. Therefore, reasonable and scientific water resource vulnerability prediction research is an effective method to alleviate vulnerability. At present, water resource vulnerability studies mainly aimed at evaluating current situation of water resource vulnerability, while there is little work about forecasting. In this paper we combined the rough set and BP neural network to make attribute reduction of the evaluation indices system by using improved data analysis. Then, we established the forecast model by fitting functional relationship between index data and water vulnerability index based on the BP neural network. We discussed on Huaihe Basin's future water resource vulnerability situation based on the previous research. The results showed that, the WVI of Huaihe Basin in 2005, 2020 and 2025 were 0.305, 0.359 and 0.390, which were lightly and moderately vulnerable. Except for 2015, the water resource vulnerability in 2020 and 2025 was more seriously compared with recent years. According to the index data we revealed the main causes for this phenomenon to be annual precipitation, water per capita, GDP wastewater discharge, cultivation index, effective irrigation area ratio, and drought area ratio. In order to avoid the increasing water resource vulnerability the relevant departments should strengthen targeted management and control of these aspects.

Key words: Basin Water Resources, Vulnerability Prediction, Rough Set, BP neural network, Huaihe Basin

中图分类号:

TV213

刘倩倩, 陈岩. 基于粗糙集和BP神经网络的流域水资源脆弱性预测研究——以淮河流域为例[J]. 长江流域资源与环境, 2016, 25(09): 1317-1327.

LIU Qian-qian, CHEN Yan. VULNERABILITY PREDICTION OF BASIN WATER RESOURCES BASED ON ROUGH SET AND BP NEURAL NETWORK——A CASE OF HUAIHE BASIN[J]. RESOURCES AND ENVIRONMENT IN THE YANGTZE BASIN, 2016, 25(09): 1317-1327.

参考文献

[1] 夏军, 邱冰, 潘兴瑶, 等.气候变化影响下水资源脆弱性评估方法及其应用[J].地球科学进展, 2012, 27(4):443-451. [XIA J, QIU B, PAN X Y, et al. Assessment of water resources vulnerability under climate change and human activities[J]. Advances in Earth Science, 2012, 27(4):443-451.]
[2] 夏军, 雒新萍, 曹建廷, 等.气候变化对中国东部季风区水资源脆弱性的影响评价[J].气候变化研究进展, 2015, 11(1):8-14. [XIA J, LUO X P, CAO J T, et al. Impact and assessment of climate change on the water resources vulnerability in the Eastern China monsoon region[J]. Progressus Inquisitiones de Mutatione Climatis, 2015, 11(1):8-14.]
[3] 夏军, 石卫, 陈俊旭, 等.变化环境下水资源脆弱性及其适应性调控研究-以海河流域为例[J].水利水电技术, 2015, 46(6):27-33. [XIA J, SHI W, CHEN J X, et al. Study on vulnerability of water resources and its adaptive regulation under changing environment-A case of Haihe River Basin[J]. Water Resources and Hydropower Engineering, 2015, 46(6):27-33.]
[4] 邓慧平, 赵明华.气候变化对莱州湾地区水资源脆弱性的影响[J].自然资源学报, 2001, 16(1):9-15. [DENG H P, ZHAO M H. Impacts of climate change on water resource vulnerability in Laizhou Bay region[J]. Journal of Natural Resources, 2001, 16(1):9-15.]
[5] 郝璐, 王静爱.基于SWAT-WEAP联合模型的西辽河支流水资源脆弱性研究[J].自然资源学报, 2012, 27(3):468-479. [HAO L, WANG J A. Evaluate to water resources vulnerability using SWAT-WEAP model in tributary of Xiliaohe River[J]. Journal of Natural Resources, 2012, 27(3):468-479.]
[6] GOGU R C, DASSARGUES A. Current trends and future challenges in groundwater vulnerability assessment using overlay and index methods[J]. Environmental Geology, 2000, 39(6):549-559.
[7] VÖRÖSMARTY C J, GREEN P, SALISBURY J, et al. Global water resources:vulnerability from climate change and population growth[J]. Science, 2000, 289(5477):284-288.
[8] SULLIVAN C A. Quantifying water vulnerability:a multi-dimensional approach[J]. Stochastic Environmental Research and Risk Assessment, 2011, 25(4):627-640.
[9] 吕彩霞, 仇亚琴, 贾仰文, 等.海河流域水资源脆弱性及其评价[J].南水北调与水利科技, 2012, 10(1):55-59. [LV C X, QIU Y Q, JIA Y W, et al. Water Resources vulnerability and its assessment of Haihe River Basin[J]. South-to-North Water Transfers and Water Science & Technology, 2012, 10(1):55-59.]
[10] 李智飞, 门宝辉, 张士锋, 等.河西走廊地区狭义/广义水资源脆弱性对比研究[J].干旱区地理, 2014, 37(5):939-947. [LI Z F, MEN B H, ZHANG S F, et al. A comparative study of narrow/general water resources vulnerability in Hexi Corridor region[J]. Arid Land Geography, 2014, 37(5):939-947.]
[11] 陈康宁, 董增川, 崔志清.基于分形理论的区域水资源系统脆弱性评价[J].水资源保护, 2008, 24(3):24-26, 34. [CHEN K N, DONG Z C, CUI Z Q. Evaluation of vulnerability of regional water resources system based on the fractal theory[J]. Water Resources Protection, 2008, 24(3):24-26, 34.]
[12] 马冬梅, 陈大春.基于欧式贴近度的模糊物元模型在水资源脆弱性评价中的应用[J].南水北调与水利科技, 2015, 13(5):1003-1007. [MA D M, CHEN D C. Application of fuzzy matter element model based on Euclid approach degree on vulnerability assessment of water resources[J]. South-to-North Water Transfers and Water Science & Technology, 2015, 13(5):1003-1007.]
[13] 董四方, 董增川, 陈康宁.基于DPSIR概念模型的水资源系统脆弱性分析[J].水资源保护, 2010, 26(4):1-3, 25. [DONG S F, DONG Z C, CHEN K N, et al. Analysis of water resources system vulnerability based on DPSIR conceptual model[J]. Water Resources Protection, 2010, 26(4):1-3, 25.]
[14] PAWLAK Z. Rough sets[J]. International Journal of Computer & Information Sciences, 1982, 11(5):341-356.
[15] 张文修.粗糙集理论与方法[M].北京:科学出版社, 2001. [ZHANG W X. Rough set theory and method[M]. Beijing:Science Press, 2001.]
[16] FENG C X, GOWRISANKAR A C, SMITH A E, et al. Practical guidelines for developing BP neural network models of measurement uncertainty data[J]. Journal of Manufacturing Systems, 2006, 25(4):239-250.
[17] 邓少波, 黎敏, 关素洁, 等.一种非相容决策表的属性值与属性约简方法术[J].计算机应用研究, 2011, 28(4):1308-1310. [DENG S B, LI M, GUAN S J, et al. Attribute value and attribute reduction method based on inconsistent decision tables[J]. Application Research of Computers, 2011, 28(4):1308-1310.]
[18] 张晓峒.EViews使用指南与案例[M].北京:机械工业出版社, 2007. [ZHANG X T. Guide to using EViews[M]. Beijing:Machine Press, 2007.]
[19] 翁建武, 夏军, 陈俊旭.黄河上游水资源脆弱性评价研究[J].人民黄河, 2013, 35(9):15-20. [WENG J W, XIA J, CHEN J X. Water resources vulnerability assessment of the upper Yellow River[J]. Yellow River, 2013, 35(9):15-20.]

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed