[1]李爱民,王海隆,许有成.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):90-96.[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):90-96.[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:
90-96
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:
李爱民1;  王海隆2;  许有成2
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:
P237
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 spatialtemporal 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] EVANS C D, MONTEITH D T, COOPER D M. Longterm increases in surface water dissolved organic carbon: observations, possible causes and environmental impacts [ J ]. Environmental pollution, 2005, 137
(1): 55-71.
[2] PILLA R M, COUTURE R M. Attenuation of photosynthetically active radiation and ultraviolet radiation in response to changing dissolved organic carbon in browning lakes: modeling and parametrization [ J]. Limnology
and oceanography, 2021, 66(6): 2278-2289.
[3] 侯迪波, 张坚, 陈泠, 等. 基于紫外-可见光光谱的水质分析方法研究进展与应用[J]. 光谱学与光谱分析, 2013, 33(7): 1839-1844.
HOU D B, ZHANG J, CHEN L, et al. Water quality analysis by UV-vis spectroscopy: a review of methodology and application[J]. Spectroscopy and spectral analysis, 2013, 33(7): 1839-1844.
[4] 彭保发, 陈哲夫, 李建辉, 等. 基于GF-1 影像的洞庭湖区水体水质遥感监测[ J]. 地理研究, 2018,37(9): 1683-1691.
PENG B F, CHEN Z F, LI J H, et al. Monitoring water quality of Dongting Lake region based on GF-1 image[J]. Geographical research, 2018, 37(9): 1683-1691.
[5] CHERUKURU N, FORD P W, MATEAR R J, et al. Estimating dissolved organic carbon concentration in turbid coastal waters using optical remote sensing observations[J]. International journal of applied earth
observation and geoinformation, 2016, 52: 149-154.
[6] KUTSER T, VERPOORTER C, PAAVEL B, et al. Estimating Lake carbon fractions from remote sensing data[J]. Remote sensing of environment, 2015, 157:138-146.
[7] 徐良将, 黄昌春, 李云梅, 等. 基于高光谱遥感反射率的总氮总磷的反演[ J]. 遥感技术与应用,2013, 28(4): 681-688.
XU L J, HUANG C C, LI Y M, et al. Deriving concentration of TN, TP based on hyper spectral reflectivity[J]. Remote sensing technology and application, 2013, 28(4): 681-688.
[8] 蔡婉贞, 黄翰. 基于BP-RBF 神经网络的组合模型预测港口物流需求研究[J]. 郑州大学学报(工学版), 2019, 40(5): 85-91.
CAI W Z, HUANG H. A model based on the combination of BP and RBF neural network for port logistic demand forecasting[J]. Journal of Zhengzhou university (engineering science), 2019, 40(5): 85-91.
[9] 马丰魁, 姜群鸥, 徐藜丹, 等. 基于BP 神经网络算法的密云水库水质参数反演研究[J]. 生态环境学报, 2020, 29(3): 569-579.
MA F K, JIANG Q O, XU L D, et al. Retrieval of water quality parameters based on BP neural network algorithm in Miyun reservoir[J]. Ecology and environmental sciences, 2020, 29(3): 569-579.
[10] 夏晓芸, 解启蒙, 杨国范, 等. 大伙房水库叶绿素a浓度反演模型研究[J]. 节水灌溉, 2018(8): 39-42, 46.
XIA X Y, XIE Q M, YANG G F, et al. A study on remote sensing inversion model of chlorophyll-A in Dahuofang reservoir based on HJ - 1A/ 1B data [ J].Water saving irrigation, 2018(8): 39-42, 46.
[11] 张明慧, 苏华, 季博文. MODIS 时序影像的福建近岸叶绿素a 浓度反演[J]. 环境科学学报, 2018, 38(12): 4831-4839.
ZHANG M H, SU H, JI B W. Retrieving nearshorechlorophyll-a concentration using MODIS time-series images in the Fujian Province (China)[J]. Acta scientiae circumstantiae, 2018, 38(12): 4831-4839.
[12] 盛辉, 池海旭, 许明明, 等. 改进SVR 的内陆水体COD 高光谱遥感反演[ J]. 光谱学与光谱分析,2021, 41(11): 3565-3571.
SHENG H, CHI H X, XU M M, et al. Inland water chemical oxygen demand estimation based on improved SVR for hyperspectral data [ J]. Spectroscopy and spectral analysis, 2021, 41(11): 3565-3571.
[13] SHAHRIARI B, SWERSKY K, WANG Z Y, et al.Taking the human out of the loop: a review of Bayesian optimization[J]. Proceedings of the IEEE, 2016, 104(1): 148-175.
[14] 韩中含, 徐白山, 杨成林, 等. 基于Planet 多光谱影像的南海岛礁水深反演研究[J]. 测绘与空间地理信息, 2020, 43(12): 139-142, 146.
HAN Z H, XU B S, YANG C L, et al. Research on reef depth retrieval of South China Sea Island based on planet multispectral image[J]. Geomatics & spatial information technology, 2020, 43(12): 139-142, 146.
[15] 吴志明, 李建超, 王睿, 等. 基于随机森林的内陆湖泊水体有色可溶性有机物(CDOM) 浓度遥感估算[J]. 湖泊科学, 2018, 30(4): 979-991.
WU Z M, LI J C, WANG R, et al. Estimation of CDOM concentration in inland lake based on random forest using Sentinel-3A OLCI[J]. Journal of lake sciences,2018, 30(4): 979-991.
[16] 王奕森, 夏树涛. 集成学习之随机森林算法综述[J]. 信息通信技术, 2018, 12(1): 49-55.
WANG Y S, XIA S T. A survey of random forests algorithms[J]. Information and communications technologies,2018, 12(1): 49-55.
[17] 方馨蕊, 温兆飞, 陈吉龙, 等. 随机森林回归模型的悬浮泥沙浓度遥感估算[ J]. 遥感学报, 2019,23(4): 756-772.
FANG X R, WEN Z F, CHEN J L, et al. Remote sensing estimation of suspended sediment concentration based on random forest regression model[J]. Journal of remote sensing, 2019, 23(4): 756-772.

更新日期/Last Update: 2022-10-03