基于云推理和模糊逻辑关系模型的干旱等级预测方法研究

doi:10.11870/cjlyzyyhj201608014

长江流域资源与环境 >> 2016, Vol. 25 >> Issue (08): 1273-1278.doi: 10.11870/cjlyzyyhj201608014

基于云推理和模糊逻辑关系模型的干旱等级预测方法研究

龚艳冰^1,2, 戴靓靓¹, 胡娜¹, 刘高峰^1,2, 张继国^1,2

1. 河海大学水利信息统计与管理研究所, 江苏常州 213022;
2. 江苏省"世界水谷"与水生态文明协同创新中心, 江苏南京 211100

收稿日期:2015-11-25 修回日期:2016-01-19 出版日期:2016-08-20
作者简介:龚艳冰(1979~),男,副教授,博士,主要研究方向为水旱灾害管理.E-mail:yanbg78@163.com
基金资助:
国家自然科学基金项目（71303074）；江苏省社会科学基金项目（14GLC004）；江苏省自然科学基金项目（BK20130242）；中央高校基本科研业务费项目（2015B23914，2015B28014）

STUDY ON DROUGHT CLASS PREDICTION METHOD BASED ON THE CLOUD REASONING AND FUZZY LOGIC RELATION MODEL

GONG Yan-bing^1,2, DAI Liang-liang¹, HU Na¹, LIU Gao-feng^1,2, ZHANG Ji-guo^1,2

1. Institute of Hydraulic Information Statistic and Management, Hohai University, Changzhou 213022, China;
2. Jiangsu Provincial Collaborative Innovation Center of World Water Valley and Water Ecological Civilization, Nanjing 211100, China

Received:2015-11-25 Revised:2016-01-19 Online:2016-08-20
Supported by:
National Nature Science Foundation of China (No. 71303074);Social Science Foundation of Jiangsu Province of China (No. 14GLC004);Natural Science Foundation of Jiangsu Province of China (No. BK20130242);Fundamental Research Fund for the Central University of China (Nos. 2015B23914, 2015B28014)

摘要/Abstract

摘要： 针对月平均降水量时间序列存在模糊性和随机性的特点，给出一种结合云推理和模糊逻辑关系的干旱等级预测方法。采用徐州站1951～2014年逐月降水量数据，通过计算标准化降水指数（SPI），得到实测干旱等级序列，以1952～2013年SPI指数数据作为样本数据，并提取样本模糊时间序列的52条模糊逻辑推理规则，将某月份的SPI指数数据作为输入变量，利用云发生器进行云推理，得到未来相应月份的干旱等级预测结果。结果表明，研究方法对干旱发生具有一定预测能力，尤其是对无旱的预测比较准确，但是对于干旱状态突变的预测能力较弱，主要是由于发生严重旱灾的可能性较少，导致模糊推理规则较少。因此，对于江苏省以轻旱为主的苏北地区，可以作为早期干旱预警的参考。

关键词: 标准化降水指数, 云推理, 模糊逻辑关系, 干旱预测

Abstract: For the monthly average precipitation time series having the features of the fuzziness and randomness, a drought class prediction combination method based on the cloud reasoning and fuzzy logic relation are given. By calculating the standardized precipitation index (SPI) of Xuzhou station monthly precipitation data from 1951 to 2014, we get the measured drought grade sequence. We use SPI data from1952 to 2013 as the sample data, and extract 52 fuzzy logic inference rules of the fuzzy time series. The SPI data of a month is used as the input variable, and the cloud generator is used to obtain the forecast result of the drought level in the future. The results show that this method has certain prediction ability for drought occurrence, especially for no drought prediction, which is more accurate. But it is weak for the drought state mutations prediction, mainly due to the possibility of a severe drought is less, resulting in a less fuzzy inference rules. Therefore, it can be used as a reference for early warning of drought in northern Jiangsu Province, which is given priority to the light drought.

Key words: SPI, cloud reasoning, fuzzy logic relation, drought class prediction

中图分类号:

P338

龚艳冰, 戴靓靓, 胡娜, 刘高峰, 张继国. 基于云推理和模糊逻辑关系模型的干旱等级预测方法研究[J]. 长江流域资源与环境, 2016, 25(08): 1273-1278.

GONG Yan-bing, DAI Liang-liang, HU Na, LIU Gao-feng, ZHANG Ji-guo. STUDY ON DROUGHT CLASS PREDICTION METHOD BASED ON THE CLOUD REASONING AND FUZZY LOGIC RELATION MODEL[J]. RESOURCES AND ENVIRONMENT IN THE YANGTZE BASIN, 2016, 25(08): 1273-1278.

参考文献

[1] MCKEE T B, DOESKEN N J, KLEIST J. The relationship of drought frequency and duration to time scales[C]//Proceedings of the 8th Conference on Applied Climatology. California: American Meteorological Society, 1993.
[2] 韩萍, 王鹏新, 王彦集, 等. 多尺度标准化降水指数的ARIMA模型干旱预测研究[J]. 干旱地区农业研究, 2008, 26(2): 212-218.[HAN P, WANG P X, WANG Y J, et al. Drought forecasting based on the standardized precipitation index at different temporal scales using ARIMA models[J]. Agricultural Research in the Arid Areas, 2008, 26(2): 212-218.]
[3] 田苗, 王鹏新, 韩萍, 等. 基于SARIMA模型和条件植被温度指数的干旱预测[J]. 农业机械学报, 2013, 44(2): 109-116.[TIAN M, WANG P X, HAN P, et al. Drought forecasts based on SARIMA models and vegetation temperature condition index[J]. Transactions of the Chinese Society for Agricultural Machinery, 2013, 44(2): 109-116.]
[4] 王彦集, 刘峻明, 王鹏新, 等. 基于加权马尔可夫模型的标准化降水指数干旱预测研究[J]. 干旱地区农业研究, 2007, 25(5): 198-203.[WANG Y J, LIU J M, WANG P X, et al. Prediction of drought occurrence based on the standardized precipitation index and the Markov Chain Model with weights[J]. Agricultural Research in the Arid Areas, 2007, 25(5): 198-203.]
[5] 吕小俊, 谢海平, 木绍良. 基于灰色灾变理论的云南省干旱气候预测研究[J]. 数学的实践与认识, 2015, 45(1): 164-168.[LV X J, XIE H P, MU S L. Study drought climate in Yunnan province based on gray system theory[J]. Mathematics in Practice and Theory, 2015, 45(1): 164-168.]
[6] 田苗, 王鹏新, 侯姗姗, 等. 基于相空间重构与RBF神经网络模型的面上干旱预测研究[J]. 干旱地区农业研究, 2013, 31(6): 164-168, 180.[TIAN M, WANG P X, HOU S S, et al. Research of regional drought forecasting based on phase space reconstruction and RBF neural network model[J]. Agricultural Research in the Arid Areas, 2013, 31(6): 164-168, 180.]
[7] 冯平, 胡荣, 李建柱. 基于三维对数线性模型的气象干旱等级预测研究[J]. 水利学报, 2014, 45(5): 505-512.[FENG P, HU R, LI J Z. Meteorological drought grade prediction using three-dimensional log-linear models[J]. Journal of Hydraulic Engineering, 2014, 45(5): 505-512.]
[8] 胡荣, 冯平, 李一兵. 流域水文干旱等级预测问题的研究[J]. 自然灾害学报, 2015, 24(2): 147-156.[HU R, FENG P, LI Y B. Study on drought class prediction problem in basin[J]. Journal of Natural Disasters, 2015, 24(2): 147-156.]
[9] 彭高辉, 张振伟, 马建琴. 基于可公度理论的安徽省干旱预测[J]. 水电能源科学, 2012, 30(9): 6-8.[PENG G H, ZHANG Z W, MA J Q. Drought prediction in Anhui province based on commensurability theory[J]. Water Resources and Power, 2012, 30(9): 6-8.]
[10] 李德毅, 杜鹢. 不确定性人工智能[M]. 北京: 国防工业出版社, 2005.[LI D Y, DU Y. Artificial intelligence with uncertainty[M]. Beijing: National Defense Industry Press, 2005.]
[11] SONG Q, CHISSOM B S. Forecasting enrollments with fuzzy time series-part 1[J]. Fuzzy Sets and Systems, 1993, 54(1): 1-9.
[12] CHEN S M. Forecasting enrollments based on fuzzy time series[J]. Fuzzy Sets and Systems, 1996, 81(3): 311-319.
[13] 龚艳冰, 张继国. 基于正态云模型和熵权的人口发展现代化程度综合评价[J]. 中国人口·资源与环境, 2012, 22(1): 138-143.[GONG Y B, ZHANG J G. Comprehensive assessment on population development degree of modernization based on normal cloud model and entropy weight[J]. China Population, Resources and Environment, 2012, 22(1): 138-143.]

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed