基于极限学习机的干旱区潜在蒸发量模拟

doi:10.7522/j.issn.1000-694X.2017.00097

摘要/Abstract

摘要： 准确地模拟干旱区潜在蒸发量，对区域水资源的合理开发利用与生态环境保护具有十分重要的意义。以极限学习机（ELM）模型为基础，以古浪河流域的乌鞘岭、古浪两个典型气象观测站点为对象，将气象因子的不同组合作为输入参数，构建了适合当地的潜在蒸发量模型。利用构建的模型对乌鞘岭、古浪气象观测站点的月潜在蒸发量进行了模拟，将模拟结果与支持向量机（SVM）模型模拟结果进行了对比，发现ELM模型在干旱区月潜在蒸发量模拟中有更好的适用性，可为干旱地区潜在蒸发量的估算提供新方法和思路，是资料有限条件下潜在蒸发估算的有效方法。

关键词: 干旱区, 潜在蒸发, 模拟, 极限学习机

Abstract: The simulated accurately evaporation at the arid regions was essential to rationally develop and utilize water resources and the ecosystem protection. The meteorological data at Wushaoling and Gulang weather stations in Shiyang River Basin were used in this study. Based on the extreme learning machine (ELM) model, the varying combination of meteorological factors were inputted to the model. An evaporation model also was established to simulate monthly evaporation at the two weather stations, and the results were compared with support vector machine (SVM) model to evaluate the simulation ability of ELM model. Our study demonstrated that the ELM model had better applicability in simulating monthly evaporation at arid regions. It can provide a new method and idea for calculating evaporation, and it is a desirable and effective method to calculate evaporation at the arid regions with insufficient data.

Key words: arid region, evaporation, numerical simulation, extreme learning machine

中图分类号:

P332.2

王婷婷, 冯起, 温小虎, 郭小燕. 基于极限学习机的干旱区潜在蒸发量模拟[J]. 中国沙漠, 2017, 37(6): 1219-1226.

Wang Tingting, Feng Qi, Wen Xiaohu, Guo Xiaoyan. Numerical Simulation of Evaporation of Arid Region Based on Extreme Learning Machine[J]. JOURNAL OF DESERT RESEARCH, 2017, 37(6): 1219-1226.

参考文献

[1] 廖杰,王涛,薛娴,等.黑河调水以来额济纳盆地湖泊蒸发量[J].中国沙漠,2015,35(1):228-232.
[2] 柯珂,金晓媚,高萌萌,等.以改进SEBS模型估算苏木吉林南湖的水面蒸发[J].中国沙漠,2015,35(1):233-239.
[3] Raziei T,Pereira L S.Estimation of ET₀ with Hargreaves-Samani and FAO-PM temperature methods for a wide range of climates in Iran[J].Agricultural Water Management,2013,121:1-18.
[4] Falamarzi Y,Palizdan N,Huang Y F,et al.Estimating evapotranspiration from temperature and wind speed data using artificial and wavelet neural networks (WNNs)[J].Agricultural Water Management,2014,140:26-36.
[5] Tang R S,Etzion Y.Comparative studies on the water evaporation rate from a wetted surface and that from a free water surface[J].Building and Environment,2004,39(1):77-86.
[6] 陈伯龙,左洪超,高晓清,等.20 cm蒸发皿蒸发量的数学物理模型研究[J].地球物理学报,2013,56(2):422-430.
[7] Guven A,Kisi O.Monthly pan evaporation modeling using linear genetic programming[J].Journal of Hydrology,2013,503:178-185.
[8] Kisi Ö.Pan evaporation modeling using least square support vector machine,multivariate adaptive regression splines and M5 model tree[J].Journal of Hydrology,2015,528:312-320.
[9] Kişi Ö.Evolutionary neural networks for monthly pan evaporation modeling[J].Journal of Hydrology,2013,498:36-45.
[10] Kişi Ö,Tombul M.Modeling monthly pan evaporations using fuzzy genetic approach[J].Journal of Hydrology,2013,477:203-212.
[11] Wang L,Kisi O,Zounemat-Kermani M,et al.Pan evaporation modeling using six different heuristic computing methods in different climates of China[J].Journal of Hydrology,2017,544:407-427.
[12] 侯志强,杨培岭,苏艳平,等.基于最小二乘支持向量机的ET₀模拟计算[J].水利学报,2011,42(6):743-749.
[13] 冯禹,王守光,崔宁博,等.基于遗传算法优化神经网络的参考作物蒸散量预测模型[J].资源科学,2014,12:2624-2630.
[14] 张育斌,魏正英,张磊,等.耦合模拟退火优化最小二乘支持向量机的日参照蒸散量模拟计算[J].节水灌溉,2016,9:133-138.
[15] Goyal M K,Bharti B,Quilty J,et al.Modeling of daily pan evaporation in sub tropical climates using ANN,LS-SVR,Fuzzy Logic,and ANFIS[J].Expert Systems with Applications,2014,41(11):5267-5276.
[16] Huang G B,Zhu Q Y,Siew C K.Extreme learning machine:theory and applications[J].Neurocomputing,2006,70(1):489-501.
[17] Deo R C,Şahin M.Application of the extreme learning machine algorithm for the prediction of monthly Effective Drought Index in eastern Australia[J].Atmospheric Research,2015,153:512-525.
[18] Lima A R,Cannon A J,Hsieh W W.Nonlinear regression in environmental sciences using extreme learning machines:a comparative evaluation[J].Environmental Modelling & Software,2015,73:175-188.
[19] Yuan P,Chen H,Zhou Y,et al.Generalization ability of extreme learning machine with uniformly ergodic Markov chains[J].Neurocomputing,2015,167:528-534.
[20] 赵福年,王莺,张龙,等.1960-2009年石羊河流域气候变化特征[J].气象与环境学报,2014,5:131-140.
[21] Chang C C,Lin C J.LIBSVM:a library for support vector machines[J].ACM Transactions on Intelligent Systems and Technology,2011,27:1-27.