[1]元成方,陈 阳,王世博,等.优化随机森林算法的城市湖泊DOC浓度遥感反演[J].郑州大学学报(工学版),2022,43(06):97-103.[doi:10.13705/j.issn.1671-6833.2022.06.007]
　LI Aimin,WANG Hailong,XU Youcheng.Remote Sensing Retrieval of Urban Lake DOC Concentration Based on Optimized Random Forest Algorithm[J].Journal of Zhengzhou University (Engineering Science),2022,43(06):97-103.[doi:10.13705/j.issn.1671-6833.2022.06.007]
点击复制

优化随机森林算法的城市湖泊DOC浓度遥感反演()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
43
期数:
2022年06期
页码:
97-103
栏目:
出版日期:
2022-09-02

文章信息/Info

Title:
Remote Sensing Retrieval of Urban Lake DOC Concentration Based on Optimized Random Forest Algorithm
作者:
元成方1 ;  陈 阳1 ;  王世博2 ;  魏逸然1
1.郑州大学地球科学与技术学院;2.郑州大学水利科学与工程学院;

Author(s):
LI Aimin 1;  WANG Hailong2;  XU Youcheng 2
1.School of Geo-science and Technology, Zhengzhou University, Zhengzhou 450001, China; 
2.School of Water Conservancy Engineering, Zhengzhou University, Zhengzhou 450001, China
关键词:
Keywords:
dissolved organic carbon;  remote sensing inversion;  Planet;  random forest;  Bayesian optimization
分类号:
TU528. 1；X798
DOI:
10.13705/j.issn.1671-6833.2022.06.007
文献标志码:
A
摘要:
在城市湖泊的可溶性有机碳( DOC)含量的遥感监测问题中,传统回归模型难以描述非线性关系而不能满足精度的要求,因此,将贝叶斯优化算法引入到随机森林模型的参数优化中,提出一种贝叶斯优化随机森林模型( BO-RF)的城市湖泊 DOC 质量浓度反演方法。 以郑州市天德湖水域为例,基于高时空分辨率的 Planet 卫星影像数据和实测的 DOC 水质数据,开展城市湖泊 DOC 质量浓度的遥感反演方法研究。 PEARSON 相关性分析结果表明:反演 DOC 质量浓度的 Planet 卫星影像波段最佳波段 组合为B2 / B4。 利用传统回归方法得到的波段比值模型决定系数 R2 = 0. 466,均方根误差 RMSE = 0. 515 mg / L,无法满足精度要求。 利用支持向量机和 BP 神经网络建模精度有所提升,拟合度 R2 分别为 0. 772 和0. 806,均方根误差 RMSE 分别为 0. 328 mg / L 和 0. 302 mg / L。 引入贝叶 斯优化算法对随机森林模型进行优化得到BO-RF 模型,其拟合度 R2 = 0. 865,均方根误差 RMSE = 0. 253 mg / L。 优化后的模型 BO-RF拟合度较好,模型精度显著提高。 贝叶斯优化后的随机森林 BO-RF 算法更适合反演天德湖水体 DOC 质量浓度,为城市湖泊水质的遥感监测提供参考。
Abstract:
In remote sensing monitoring of dissolved organic carbon (DOC) content in urban lakes, the traditional regression model is difficult to describe the nonlinear relationship and can not meet the accuracy requirements. In this study, Bayesian optimization algorithm was introduced into the parameter optimization of random forest model, and a DOC concentration inversion method of urban lakes based on Bayesian optimization random forest model (BO-RF) was proposed. Taking the water area of Tiande Lake in Zhengzhou city as an example, the remote sensing inversion method of DOC concentration in urban lakes was studied based on high spatial-temporal resolution Planet satellite image data and measured DOC water quality data. Through PEARSON correlation analysis, the results showed that the best band combination of Planet satellite image band for retrieving DOC concentration was B2/B4. The determination coefficient R2 of the band ratio model obtained by the traditional regression method was 0.466, and the root mean square error RMSE was 0.515 mg/L, which could not meet the accuracy requirements. The modeling accuracy was improved by using support vector machine and BP neural network, the fitting R2 was 0.772 and 0.806, respectively, and the root mean square error RMSE was 0.328 mg/L and 0.302 mg/L, respectively. Bayesian optimization algorithm was introduced to optimize the random forest model to obtain the BO-RF model, and its fitting degree R2 was 0.865 and root mean square error RMSE was 0.253 mg/L. The BO-RF fit of the optimized model was good, and the accuracy of the model was significantly improved. The Bayesian optimized random forest BO-RF algorithm was more suitable for retrieving DOC concentration in Tiande lake, which could provide a reference for remote sensing monitoring of urban lake water quality.

参考文献/References:

[1] 元成方, 魏逸然, 李爽. 聚丙烯纤维混合再生骨料 混凝土 力 学 性 能 研 究 [ J] . 郑 州 大 学 学 报 ( 工 学 版) , 2021, 42(2) : 49-53. 

YUAN C F, WEI Y R, LI S. Study on mechanical properties of polypropylene fiber mixed recycled aggregate concrete [ J ] . Journal of Zhengzhou university ( engineering science) , 2021, 42(2) : 49-53.
[2] 高嵩, 郭远新, 吴本清, 等. 再生细骨料品质的分 形学特征研究[ J] . 混凝土, 2019(6) : 78-83. 
GAO S, GUO Y X, WU B Q, et al. Research on fractal characteristic of recycled fine aggregate [ J] . Concrete, 2019(6) : 78-83.
[3] YAN K Z, LI G K, YOU L Y, et al. Performance assessments of open-graded cement stabilized macadam containing recycled aggregate [ J ] . Construction and building materials, 2020, 233: 117326. 
[4] WANG J G, ZHANG J X, CAO D D, et al. Comparison of recycled aggregate treatment methods on the performance for recycled concrete [ J] . Construction and building materials, 2020, 234: 117366.
[5] 张璐, 李海洲, 任皎龙. 100%再生黏土砖骨料混凝 土抗压强度的试验研究[ J] . 混凝土, 2020 ( 11) : 79-82, 88. 
ZHANG L, LI H Z, REN J L. Experimental study on compressive strength of the concrete with 100% recycled clay brick aggregates[ J] . Concrete, 2020( 11) : 79-82, 88.
[6] SHAO J H, GAO J M, ZHAO Y S, et al. Study on the pozzolanic reaction of clay brick powder in blended cement pastes [ J] . Construction and building materials, 2019, 213: 209-215.
[7] LIN K L, CHEN B Y, CHIOU C S, et al. Waste brick′s potential for use as a pozzolan in blended Portland cement[ J] . Waste management & research: the journal for a sustainable circular economy, 2010, 28 (7) : 647-652.
[8] KARTINI, ROHAIDAH, ZURAINI, et al. Performance of ground clay bricks as partial cement replacement in grade 30 concrete [ J]. International journal of environmental monitoring and analysis, 2012, 6: 569-572. 
[9] 李炜, 孙南屏, 何健恒. 废砖粉水泥胶砂基本性能 试验研究[ J] . 砖瓦, 2014(2) : 3-6.
 LI W, SUN N P, HE J H. Experimental study on the basic properties of cement mortar added some recycled brick powder[ J] . Block-brick-tile, 2014(2) : 3-6.
[10] 李述俊, 赵霄龙, 李秋义, 等. 再生微粉基本性能 及活性试验研究[ J] . 硅酸盐通报, 2019, 38( 10) : 3314-3319, 3325. 
LI S J, ZHAO X L, LI Q Y, et al. Experimental study on basic properties and activity of recycled fine powder [ J] . Bulletin of the Chinese ceramic society, 2019, 38(10) : 3314-3319, 3325.
[11] 张平,古龙龙,王琴,等. 激发再生微粉活性的方法 研究[ J] . 混凝土与水泥制品,2019(2) :90-93. 
ZHANG P, GU L L, WANG Q, et al. Study on the method of stimulating the activity of regenerated micro powder [ J] . Bulletin of the chinese ceramic society, 2019(2) : 90-93.
[12] 李琴, 张春红, 孙可伟. 不同激发剂激发建筑垃圾 再生微 粉 活 性 研 究 [ J ] . 硅 酸 盐 通 报, 2016, 35 (7) : 2187-2192, 2197. 
LI Q, ZHANG C H, SUN K W. Preliminary study on micronized active regeneration experiment with different activator excitation construction waste[ J] . Bulletin of the Chinese ceramic society, 2016, 35( 7) : 2187- 2192, 2197. 
[13] 刘栋, 张鹏宇, 刘彤, 等. 建筑垃圾中再生微粉材 性表征及潜在活性的激发[ J] . 硅酸盐通报, 2016, 35(8) : 2635-2641. 
LIU D, ZHANG P Y, LIU T, et al. Material properties characterization and the excitation of potential activity on construction waste recycled powder[ J] . Bulletin of the Chinese ceramic society, 2016, 35 ( 8) : 2635-2641. 
[14] 康晓明, 李滢, 樊耀虎. 不同激发方式对再生微粉 性能的影响研究[ J] . 硅酸盐通报, 2019, 38( 4) : 1135-1139.
 KANG X M, LI Y, FAN Y H. Effect of different excitation methods on the properties of recycled concrete powder[ J] . Bulletin of the Chinese ceramic society, 2019, 38(4) : 1135-1139.
[15] 何健恒. 废弃混凝土中砂浆组分的性能及利用研 究[D] . 广州: 广东工业大学, 2015. 
HE J H. Study on the properties of the mortar components and use in waste concrete [ D ] . Guangzhou: Guangdong University of Technology, 2015.

更新日期/Last Update: 2022-10-03