Please wait a minute...
img

官方微信

遥感技术与应用  2010, Vol. 25 Issue (2): 257-262    DOI: 10.11873/j.issn.1004-0323.2010.2.257
研究与应用     
基于GA-LSSVR的渭河水质参数遥感反演研究
谢屹鹏,汪西莉
陕西师范大学计算机科学学院,陕西 西安 710062
Study on GA-LSSVR for Weihe River Quality Parameters Retrieving by Remote Sensing
XIE Yi-peng,WANG Xi-li
School of Computer Sciences,Shannxi Normal University,Xi’an 710062,China
 全文: PDF(668 KB)  
摘要:

针对渭河水质参数遥感反演这一典型的非线性、小样本回归估计问题,引入最小二乘支持向量回归(LSSVR)方法来解决,它将SVR中的二次规划问题转化为线性方程组求解,在保证精度的同时极大地降低了计算复杂性,加快了求解速度;针对其参数难以选择的问题,利用遗传算法(GA)来优选模型参数。采用提出的方法对标准数据集进行了实验,并建模对渭河的4种水质参数CODmn(高锰酸盐指数)、NH3-N(氨氮)、 DO(溶解氧)、COD(化学需氧量)进行了遥感反演,结果表明GA-LSSVR模型可用于解决复杂的回归问题并具有较好的预测性能。

关键词: 遗传算法最小二乘支持向量回归渭河遥感反演水质参数    
Abstract:

In order to solve Weihe River water quality retrieving by remote sensing,which is regression estimation problem characterized by non-linear and small sample,least squares support vector regression (LSSVR) is introduced in this paper.It transforms the quadratic programming problems into linear equations,which reduce the computational complexity greatly,increase the speed of computing,and meanwhile assure the accuracy.To overcome difficulties in selecting the parameters of the model,genetic algorithm (GA) is used to optimize the parameters of the model.The proposed methods are used to carry on experiments to the standard data sets,and retrieve four water quality parameters CODmn (potassium permanganate index),NH3-N(ammonia nitrogen),DO (dissolved oxygen),COD(chemical oxygen demand) for Weihe River.The results show that GA-LSSVR model can be used to solve complex regression problems and has better prediction performance.

Key words: Genetic algorithm    Least squares support vector regression    Weihe river    Retrieve    Remote sensing    Water quality parametersd
收稿日期: 2009-08-17 出版日期: 2010-10-19
基金资助:

国家自然科学基金项目(40671133)资助。

作者简介: 谢屹鹏(1984-),男,硕士研究生,主要研究方向为智能信息处理、模式识别。E-mail:xieyipeng@stu.snnu.edu.cn。
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
谢屹鹏
汪西莉

引用本文:

谢屹鹏, 汪西莉. 基于GA-LSSVR的渭河水质参数遥感反演研究[J]. 遥感技术与应用, 2010, 25(2): 257-262.

XIE Yi-peng, WANG Xi-li. Study on GA-LSSVR for Weihe River Quality Parameters Retrieving by Remote Sensing. Remote Sensing Technology and Application, 2010, 25(2): 257-262.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2010.2.257        http://www.rsta.ac.cn/CN/Y2010/V25/I2/257

[1]Zhang Rongzhen,Zhang Xing.The Evolution of the Ecological Environment in Shaanxi Part of Weihe River Basin in Recent 50 Years[J].Journal of Arid Land Resources and Environment,2008,22(2):37-42.[张蓉珍,张幸.渭河流域陕西段近50年生态环境演变[J].干旱区资源与环境,2008,22(2):37-42.]
[2]Giardino C,Pepe M.Detecting Chlorophyll,Secchi Disk Depth and Surface Temperature in a Sub-alpine Lake Using Landsat Imagery[J].The Science of the Total Environment,2001,268:19-29.
[3]DallOlmo G,Gitelson A A,Rundquist D C,et al.A Assessing the Potential of SeaWiFS and MODIS for Estimating Chlorophyll Concentration in Turbid Productive Waters Using Red and Near-infrared Bands[J].Remote Sensing of Enviroment,2005,96:176-187.
[4]Gu Liang,Zhang Yuchao,Qian Xin,et al.Study on Retrieval of Chlorophyll-a Concentration by Remote Sensing in Taihu Lake[J].Science and Management,2007,32(6): 5-29.[顾亮,张玉超,钱新,等.太湖水域叶绿素a浓度的遥感反演研究[J].环境科学与管理,2007,32(6):25-29.]
[5]Cherkassky V,Ma Y Q.Practical Selection of SVM Parameters and Noise Estimation for SVM Regression[J].Neural Networks(S0893-6080),2004,17(1):113-126.
[6]Chang Yuqing,Zou Wei,Wang Fuli,et al.Research on Soft Sensing Method Based on Support Vector Machines[J].Control and Decision,2005,20(11):1307-1310.[常玉清,邹伟,王福利,等.基于支持向量机的软测量方法研究[J].控制与决策,2005,20(11):1307-1310.]
[7]Suykens J A K,Vandewall J.Least Squares Support Vector Machine Classifiers[J].Neural Processing Letters,1999,9(3):293-300.
[8]Han Liwei,Li Zongkun,Wang Jianyou,et al.Study and Application of Inverse Method for Determining Parameters in Least Squares Support Vector Machine[J].Advances in Science and Technology of Water Resources,2009,29(1):8-11.[韩立炜,李宗坤,王建有,等.最小二乘支持向量机参数反演方法及其应用[J].水利水电科技进展,2009,29(1):8-11.]
[9]Cristianini N,Shawe-taylor J.An Introduction to Support Vector Machines and Other Kernel-based Learning Methods[M].Beijing:Publishing House of Electronics Industry,2004.
[10]Zhou ZhiHua,Wu Jianxin,Tang Wei,et al.Ensembling Neural Networks:Many Could Be Better than All [J].Artificial Intelligence,2002,137(1-2):239-263.
[11]Jiang Sai,Wang Xili,Zhao Yuqin,et al.Study on the Effect of Atmospheric Correction in the Weihe River Quality Quantitative Retrieving of Remote Sensing[J].Remote Sensing Technology and Application,2009,24(2):204-209.[蒋赛,汪西莉,赵玉琴,等.渭河定量遥感水质反演中的大气校正作用研究[J].遥感技术与应用,2009,24(2):204-209.]
[12]Zhao Yuqin,Wang Xili,Jiang Sai,et al.Study on Neural Network Model for Weihe River Water Quality Retrieving Using Remote Sensing Image[J].Remote Sensing Technology and Application,2009,24(1):63-67.[赵玉芹,汪西莉,蒋赛,等.渭河水质遥感反演的人工神经网络模型研究[J].遥感技术与应用,2009,24(1):63-67.]

 

[1] 王卷乐, 程凯, 边玲玲, 韩雪华, 王明明. 面向SDGs和美丽中国评价的地球大数据集成框架与关键技术[J]. 遥感技术与应用, 2018, 33(5): 775-783.
[2] 王恺宁,王修信,黄凤荣,罗涟玲. 喀斯特城市地表温度遥感反演算法比较[J]. 遥感技术与应用, 2018, 33(5): 803-810.
[3] 金点点,宫兆宁. 基于Landsat 系列数据地表温度反演算法对比分析—以齐齐哈尔市辖区为例[J]. 遥感技术与应用, 2018, 33(5): 830-841.
[4] 张晓峰,吕晓琪,张信雪,张继凯,王月明,谷宇,樊宇. 多时刻海色遥感数据融合及其可视化[J]. 遥感技术与应用, 2018, 33(5): 873-880.
[5] 谢旭,陈芸芝. 基于PSO-RBF神经网络模型反演闽江下游水体悬浮物浓度[J]. 遥感技术与应用, 2018, 33(5): 900-907.
[6] 迟文峰,匡文慧,贾静,刘正佳. 京津风沙源治理工程区LUCC及土壤风蚀强度动态遥感监测研究[J]. 遥感技术与应用, 2018, 33(5): 965-974.
[7] 胡云锋,商令杰,张千力,王召海. 基于GEE平台的1990年以来北京市土地变化格局及驱动机制分析[J]. 遥感技术与应用, 2018, 33(4): 573-583.
[8] 李晨伟,张瑞丝,张竹桐,曾敏 . 基于多源遥感数据的构造解译与分析—以西藏察隅吉太曲流域为例[J]. 遥感技术与应用, 2018, 33(4): 657-665.
[9] 李生生,王广军,梁四海,彭红明,董高峰,罗银飞. 基于Landsat-8 OLI数据的青海湖水体边界自动提取[J]. 遥感技术与应用, 2018, 33(4): 666-675.
[10] 廖凯涛,齐述华,王成,王点. 结合GLAS和TM卫星数据的江西省森林高度和生物量制图[J]. 遥感技术与应用, 2018, 33(4): 713-720.
[11] 张震,刘时银,魏俊锋,蒋宗立. 1974~2012年珠穆朗玛峰地区冰川物质平衡遥感监测研究[J]. 遥感技术与应用, 2018, 33(4): 731-740.
[12] 康文慧,宋晓谕,李洁,邓晓红,王宏伟,孙栋元. 基于GIS技术的流域生态补偿方案设计[J]. 遥感技术与应用, 2018, 33(4): 766-774.
[13] 王琳,徐涵秋,李胜. 重钢重工业区迁移对区域生态的影响研究[J]. 遥感技术与应用, 2018, 33(3): 387-397.
[14] 任浙豪,周坚华. 增大特征空间复杂度的方法——以城镇下垫面遥感分类为[J]. 遥感技术与应用, 2018, 33(3): 408-417.
[15] 王宝刚,晋锐,赵泽斌,亢健. 被动微波遥感在地表冻融监测中的应用研究进展[J]. 遥感技术与应用, 2018, 33(2): 193-201.