收稿：2025-11-03，
网络首发：2026-06-17，
纸质出版：2026-06-07
移动端阅览
遥感反演技术为悬浮泥沙浓度（SSC）监测提供了高效手段，但对于高浓度宽范围河流SSC的适用性亟需验证。以黄河干流石嘴山水文站和吴堡水文站为测站，构建了基于交叉验证递归特征消除—随机森林（RFECV-RF）的机器学习模型，通过哨兵2号卫星多光谱反射率信息遥感反演测站高浓度悬沙。研究结果表明，RFECV-RF模型预测精度指标
R
2
大于0.8，总体上能够估算测站（0—44.5）kg/m
3
区间的SSC，但对高值SSC的估算偏低；高浓度宽范围SSC与光谱信息呈现明显的非线性关系，且可见光主导的特征对反演低浓度SSC较重要，红光—短波红外光谱区间主导的特征对反演高浓度SSC较重要；在关键光谱特征中，B8A、B7/B5、B8-B11波段光谱特征在SSC（0—44.5）kg/m
3
区间保持灵敏，而B3/B8、B4/B8、B5/B6随着SSC升高而渐趋饱和；数据输入以及机器学习模型结构的不确定性是反演模型不确定性的主要来源，且当反演的SSC范围变宽时，模型预测的95%置信宽度增大且低值SSC的相对偏差也增大。综上，RFECV-RF模型可用于定量反演高浓度宽范围SSC并估算河段SSC空间分布，为高含沙河流SSC自动监测方法提供技术参考。
Remote sensing inversion offers an efficient approach for monitoring Suspended Sediment Concentration (SSC). However
its applicability for rivers with high and wide-range SSC requires further validation. This study aims to develop a machine learning model based on recursive feature elimination with cross-validation and random forest (RFECV-RF) to retrieve SSC from multispectral imagery
using the Shizuishan and Wubu stations on the main stream of the Yellow River as study sites.
Sentinel-2 multispectral reflectance data were matched with in-situ daily SSC measurements from 2020 to 2024. After outlier removal using the isolation forest algorithm
datasets of 267 and 256 samples were obtained for the Shizuishan and Wubu Station
respectively. Spectral features
including single bands and band combinations (ratios and differences) from visible to shortwave infrared
were constructed. The RFECV method was applied to select optimal features
and a Random Forest model was subsequently built to establish the relationship between spectral features and SSC. Model performance was evaluated using
R
2
RMSE
and MAE. Spectral sensitivity was analyzed using regression fitting and slope decay ratios. Parameter sensitivity was assessed via the perturbation method by varying key parameters and evaluating corresponding changes in performance metrics using sensitivity coefficients. Uncertainty arising from data input
model parameters
and model structure was quantified using a Monte Carlo simulation framework with 500 iterations
and variance decomposition was applied to quantify the contributi
on of each uncertainty source.
The RFECV-RF model achieved
R
2
values greater than 0.8 for both stations
with RMSE below 1.6 kg/m
3
demonstrating reliable SSC estimation within the range of 0—44.5 kg/m
3
though with underestimation of extreme high SSC values. A strong nonlinear relationship was observed between spectral features and SSC. The B8A band
along with B7/B5 and B8-B11
remained sensitive across the entire SSC range
while features such as B3/B8
B4/B8
and B5/B6 tended to saturate as SSC increased. Parameter sensitivity analysis indicated that model performance was robust
with the most sensitive parameters being the subsampling rate and the number of features removed per iteration. Uncertainty analysis revealed that data input and model structure were the dominant sources of uncertainty
contributing over 98% of total variance
with larger uncertainties observed for low SSC values when modeling wide-range SSC. When applied to river reaches
the inversion model effectively captured temporal variations and spatial transport dynamics of SSC
with higher SSC values in the middle reaches than in the upper reaches
consistent with actual observations.
The RFECV-RF model provides a reliable and effective approach for retrieving high and wide-range SSC in sediment-laden rivers using multispectral remote sensing. The identified key spectral features and quantified uncertainties offer valuable insights for improving inversion accuracy and support the development of automated SSC monitoring methods for complex river systems.
Aires U R V , da Silva D D , Filho E I F , Fernandes Filho E I , Rodrigues L N , Uliana E M , Amorim R S S , Ribeiro C B D M and Campos J A . 2022 . Modeling of surface sediment concentration in the Doce River Basin using satellite remote sensing . Journal of Environmental Management , 323 : 116207 [ DOI: 10.1016/j.jenvman.2022.116207 http://dx.doi.org/10.1016/j.jenvman.2022.116207 ]
Balasubramanian S V , Pahlevan N , Smith B , Binding C , Schalles J , Loisel H , Gurlin D , Greb S , Alikas K , Randla M , Bunkei M , Moses W , Nguyễn H , Lehmann M K , O’Donnell D , Ondrusek M , Han T H , Fichot C G , Moore T and Boss E . 2020 . Robust algorithm for estimating total suspended solids (TSS) in inland and nearshore coastal waters . Remote Sensing of Environment , 246 : 111768 [ DOI: 10.1016/j.rse.2020.111768 http://dx.doi.org/10.1016/j.rse.2020.111768 ]
Bazzett D and Wang R Q . 2024 . Can surface water color accurately determine sediment concentration and grain size? A hyperspectral imaging study . Water , 16 ( 15 ): 2184 [ DOI: 10.3390/w16152184 http://dx.doi.org/10.3390/w16152184 ]
Chen T , Li W and Wu S C . 1994 . Correlation between suspended sediment concentration and red-shift of peak wavelength of spectral reflectance . Acta Oceanologica Sinica , 16 ( 1 ): 38 - 43
陈涛 , 李武 , 吴曙初 . 1994 . 悬浮泥沙浓度与光谱反射率峰值波长红移的相关关系 . 海洋学报 , 16 ( 1 ): 38 - 43
Dogliotti A I , Ruddick K G , Nechad B , Doxaran D and Knaeps E . 2015 . A single algorithm to retrieve turbidity from remotely-sensed data in all coastal and estuarine waters . Remote Sensing of Environment , 156 : 157 - 168 [ DOI: 10.1016/j.rse.2014.09.020 http://dx.doi.org/10.1016/j.rse.2014.09.020 ]
Fang X R , Wen Z F , Chen J L , Wu S J , Huang Y Y and Ma M H . 2019 . Remote sensing estimation of suspended sediment concentration based on Random Forest Regression Model . Journal of Remote Sensing (in Chinese) , 23 ( 4 ): 756 - 772
方馨蕊 , 温兆飞 , 陈吉龙 , 吴胜军 , 黄远洋 , 马茂华 . 2019 . 随机森林回归模型的悬浮泥沙浓度遥感估算 . 遥感学报 , 23 ( 4 ): 756 - 772 [ DOI: 10.11834/jrs.20197498 http://dx.doi.org/10.11834/jrs.20197498 ]
Fang X T , Zhang J H , Yu X , Zhang S C , Kong D L , Wang X P , Ali S , Ullah H and Xu N . 2025 . Accurate estimation of suspended sediment concentration integrated remote sensing information and a novel stacking machine learning model . Stochastic Environmental Research and Risk Assessment , 39 ( 4 ): 1517 - 1535 [ DOI: 10.1007/s00477-025-02930-4 http://dx.doi.org/10.1007/s00477-025-02930-4 ]
Ghorbani M A , Khatibi R , Singh V P , Kahya E , Ruskeepää H , Saggi M K , Sivakumar B , Kim S , Salmasi F , Kashani M H , Samadianfard S , Shahabi M and Jani R . 2020 . Continuous monitoring of suspended sediment concentrations using image analytics and deriving inherent correlations by machine learning . Scientific Reports , 10 ( 1 ): 8589 [ DOI: 10.1038/s41598-020-64707-9 http://dx.doi.org/10.1038/s41598-020-64707-9 ]
Hou Y Z , Xing Q G , Zheng X Y , Sheng D Z and Wang F T . 2023 . Monitoring suspended sediment concentration in the yellow river estuary and its vicinity waters on the basis of SDGSAT-1 multispectral imager . Water , 15 ( 19 ): 3522 [ DOI: 10.3390/w15193522 http://dx.doi.org/10.3390/w15193522 ]
Huang H , Li M Y , Chen Y H , Chen G , Liu H L , Xing Q G and Cai J N . 2021 . Water quality retrieval by hyperspectral for city rivers in Pearl River Estuary based on partial least squares regression . Water Resources Protection , 37 ( 5 ): 36 - 42
黄华 , 李茂亿 , 陈吟晖 , 陈耿 , 刘海龙 , 刑前国 , 蔡建楠 . 2021 . 基于PLSR的珠江口城市河流水质高光谱反演 . 水资源保护 , 37 ( 5 ): 36 - 42 [ DOI: 10.3880/j.issn.1004-6933.2021.05.006 http://dx.doi.org/10.3880/j.issn.1004-6933.2021.05.006 ]
Jiang D L , Matsushita B , Pahlevan N , Gurlin D , Lehmann M K , Fichot C G , Schalles J , Loisel H , Binding C , Zhang Y L , Alikas K , Kangro K , Uusõue M , Ondrusek M , Greb S , Moses W J , Lohrenz S and O’Donnell D . 2021 . Remotely estimating total suspended solids concentration in clear to extremely turbid waters using a novel semi-analytical method . Remote Sensing of Environment , 258 : 112386 [ DOI: 10.1016/j.rse.2021.112386 http://dx.doi.org/10.1016/j.rse.2021.112386 ]
Jiji G W . 2021 . An estimation and analysis method for suspended sediment and depth map of Gulf of Mannar . The Imaging Science Journal , 69 ( 1-4 ): 92 - 102 [ DOI: 10.1080/13682199.2022.2149382 http://dx.doi.org/10.1080/13682199.2022.2149382 ]
Jung S H , Kwon S , Seo I W and Kim J S . 2024 . Comparison between hyperspectral and multispectral retrievals of suspended sediment concentration in rivers . Water , 16 ( 9 ): 1275 [ DOI: 10.3390/w16091275 http://dx.doi.org/10.3390/w16091275 ]
Kwon S , Seo I W and Lyu S W . 2023 . Investigating mixing patterns of suspended sediment in a river confluence using high-resolution hyperspectral imagery . Journal of Hydrology , 620 : 129505 [ DOI: 10.1016/j.jhydrol.2023.129505 http://dx.doi.org/10.1016/j.jhydrol.2023.129505 ]
Kwon S , Seo I W , Noh H and Kim B . 2022a . Hyperspectral retrievals of suspended sediment using cluster-based machine learning regression in shallow waters . Science of the Total Environment , 833 : 155168 [ DOI: 10.1016/j.scitotenv.2022.155168 http://dx.doi.org/10.1016/j.scitotenv.2022.155168 ]
Kwon S , Shin J , Seo I W , Noh H , Jung S H and You H . 2022b . Measurement of suspended sediment concentration in open channel flows based on hyperspectral imagery from UAVs . Advances in Water Resources , 159 : 104076 [ DOI: 10.1016/j.advwatres.2021.104076 http://dx.doi.org/10.1016/j.advwatres.2021.104076 ]
Li W and Wang X M . 2024 . Application research of photoelectric sediment concentration meter in Luokou Hydrological Station of the Lower Yellow River // Proceedings of 2024 (3rd) Urban Water Conservancy and Flood Control Academic Seminar . Hangzhou : Hohai University, Zhejiang University of Water Resources and Electric Power, Hebei University of Engineering, Zhejiang Hydraulic Society
厉玮 , 王向明 . 2024 . 光电测沙仪在黄河下游泺口水文站的应用研究 // 2024(第三届)城市水利与洪涝防治学术研讨会论文集 . 杭州 : 河海大学, 浙江水利水电学院, 河北工程大学, 浙江省水利学会 [ DOI: 10.26914/c.cnkihy.2024.055005 http://dx.doi.org/10.26914/c.cnkihy.2024.055005 ]
Li Z Y , Dai J Q , Huang D , Zhang W , Li H M , Wang Z and Kang R . 2023 . Application and prospects of satellite remote sensing monitoring technology in water conservancy projects . Advances in Water Science , 34 ( 5 ): 798 - 811
李子阳 , 戴济群 , 黄对 , 张文 , 李涵曼 , 王喆 , 康芮 . 2023 . 水利工程卫星遥感监测技术应用与展望 . 水科学进展 , 34 ( 5 ): 798 - 811 [ DOI: 10.14042/j.cnki.32.1309.2023.05.014 http://dx.doi.org/10.14042/j.cnki.32.1309.2023.05.014 ]
Marinho R R , Harmel T , Martinez J M and Filizola Junior N P . 2021 . Spatiotemporal dynamics of suspended sediments in the Negro River, Amazon Basin, from in situ and Sentinel-2 remote sensing data . ISPRS International Journal of Geo-Information , 10 ( 2 ): 86 [ DOI: 10.3390/ijgi10020086 http://dx.doi.org/10.3390/ijgi10020086 ]
Mohsen A , Kovács F and Kiss T . 2022 . Remote sensing of sediment discharge in rivers using Sentinel-2 images and machine-learning algorithms . Hydrology , 9 ( 5 ): 88 [ DOI: 10.3390/hydrology9050088 http://dx.doi.org/10.3390/hydrology9050088 ]
Pan H Z , Yang L Z , Liu C Q and Fu Q H . 2019 . Muti-model collaborative retrieval of suspend sediment concentration in the estuary of Pearl River based on data assimilation . Journal of Sediment Research , 44 ( 4 ): 47 - 53
潘洪洲 , 杨留柱 , 刘超群 , 扶卿华 . 2019 . 基于数据同化的珠江河口悬沙浓度多模型协同反演 . 泥沙研究 , 44 ( 4 ): 47 - 53 [ DOI: 10.16239/j.cnki.0468-155x.2019.04.008 http://dx.doi.org/10.16239/j.cnki.0468-155x.2019.04.008 ]
Pham Q V , Ha N T T , Pahlevan N , Oanh L T , Nguyen T B and Nguyen N T . 2018 . Using Landsat-8 images for quantifying suspended sediment concentration in Red River (northern Vietnam) . Remote Sensing , 10 ( 11 ): 1841 [ DOI: 10.3390/rs10111841 http://dx.doi.org/10.3390/rs10111841 ]
Qiu Z Q , Liu D , Yan N X , Yang C , Chen P P , Zhang C X and Duan H T . 2024 . Improving the observations of suspended sediment concentrations in rivers from Landsat to Sentinel-2 imagery . International Journal of Applied Earth Observation and Geoinformation , 134 : 104209 [ DOI: 10.1016/j.jag.2024.104209 http://dx.doi.org/10.1016/j.jag.2024.104209 ]
Song H S , Li D G , Chen B H and Liu P W . 2019 . Research on ADCP multi-line depth-integrating flow measurements . Yellow River , 41 ( 1 ): 18 - 22
宋海松 , 李德贵 , 陈宝华 , 刘培旺 . 2019 . ADCP多线积深式流量测验技术应用研究 . 人民黄河 , 41 ( 1 ): 18 - 22 [ DOI: 10.3969/j.issn.1000-1379.2019.01.005 http://dx.doi.org/10.3969/j.issn.1000-1379.2019.01.005 ]
Sun X H , Tian L Q , Fang H W , Walling D E , Huang L , Park E , Li D R , Zheng C M and Feng L . 2025 . Changes in global fluvial sediment concentrations and fluxes between 1985 and 2020 . Nature Sustainability , 8 ( 2 ): 142 - 151 [ DOI: 10.1038/s41893-024-01476-7 http://dx.doi.org/10.1038/s41893-024-01476-7 ]
Wackerman C , Hayden A and Jonik J . 2017 . Deriving spatial and temporal context for point measurements of suspended-sediment concentration using remote-sensing imagery in the Mekong Delta . Continental Shelf Research , 147 : 231 - 245 [ DOI: 10.1016/j.csr.2017.08.007 http://dx.doi.org/10.1016/j.csr.2017.08.007 ]
Wang J Y , Zhang W , Yang Y L and Wang Z S . 2025 . Study on hysteresis characteristics between flood peaks and sediment peaks and their Causes in the Tongguan-Xiaolangdi reach of the middle Yellow River ( 2002 — 2024 ). Advanced Engineering Sciences , 1 - 13
王江瑜 , 张为 , 杨泱柳 , 王治森 . 2025 . 2002~2024年黄河中游潼关-小浪底河段洪峰沙峰异步特性及成因研究 . 工程科学与技术 , 1 - 13 [ DOI: 10.12454/j.jsuese.202500751 http://dx.doi.org/10.12454/j.jsuese.202500751 ]
Wang Y P , Hu X K , Li J G , Jiang S , Chen X F , Zhao L M and Chen H Z . 2024 . Research on suspended matter concentration retrieval of SDGSAT-1 Satellite in Lake Taihu based on Hydrolight model . Spacecraft Recovery and Remote Sensing , 45 ( 1 ): 174 - 186
王雅萍 , 胡雪可 , 李家国 , 姜晟 , 陈兴峰 , 赵利民 , 陈洪真 . 2024 . 基于Hydrolight模型的太湖SDGSAT-1卫星悬浮物浓度反演研究 . 航天返回与遥感 , 45 ( 1 ): 174 - 186 [ DOI: 10.3969/j.issn.1009-8518.2024.01.015 http://dx.doi.org/10.3969/j.issn.1009-8518.2024.01.015 ]
Wu X S and Feng X Q . 2024 . Analysis of sand content distribution pattern of Yellow River Shizuishan Hydrological Stat // Proceedings of 2024 (12th) China Water Ecology Conference . Jiaxing : Hohai University, Zhejiang Institute of Hydraulics and Estuary, Zhejiang Hydraulic Society
吴小爽 , 冯晓强 . 2024 . 黄河石嘴山水文站含沙量分布规律分析研究 // 2024(第十二届)中国水生态大会论文集 . 嘉兴 : 河海大学, 浙江省水利河口研究院(浙江省海洋规划设计研究院), 浙江省水利学会 [ DOI: 10.26914/c.cnkihy.2024.039867 http://dx.doi.org/10.26914/c.cnkihy.2024.039867 ]
Xu H Q . 2005 . A study on information extraction of water body with the modified normalized difference water index ( MNDWI ) . Journal of Remote Sensing (in Chinese) , ( 5 ): 589 - 595
徐涵秋 . 2005 . 利用改进的归一化差异水体指数( MNDWI )提取水体信息的研究 . 遥感学报 , ( 5 ): 589 - 595 [ DOI: 10.11834/jrs.20050586 http://dx.doi.org/10.11834/jrs.20050586 ]
Yang X P , Sokoletsky L , Wei X D and Shen F . 2017 . Suspended sediment concentration mapping based on the MODIS satellite imagery in the East China inland, estuarine, and coastal waters . Chinese Journal of Oceanology and Limnology , 35 ( 1 ): 39 - 60 [ DOI: 10.1007/s00343-016-5060-y http://dx.doi.org/10.1007/s00343-016-5060-y ]
Yao R , Cai L N , Liu J Q and Zhou M R . 2020 . GF-1 satellite observations of suspended sediment injection of yellow river estuary, China . Remote Sensing , 12 ( 19 ): 3126 [ DOI: 10.3390/rs12193126 http://dx.doi.org/10.3390/rs12193126 ]
Ying Z X , Li N G , Guo L L and Bao J Y . 2023 . Development history and prospects of sediment monitoring technology at home and abroad // Proceedings of 2023 China Hydraulic Academic Conference (Part I) . Zhengzhou : China Hydraulic Academic Conference
应周箫 , 李聂贵 , 郭丽丽 , 鲍金玉 . 2023 . 国内外泥沙监测技术的发展历程及展望 // 2023中国水利学术大会论文集(第一分册) . 郑州 : 中国水利学术大会 [ DOI: 10.26914/c.cnkihy.2023.087933 http://dx.doi.org/10.26914/c.cnkihy.2023.087933 ]
Yu D F , Bian X D , Yang L , Zhou Y , An D Y , Zhou M S , Chen S L and Pan S Q . 2023 . Monitoring suspended sediment concentration in the Yellow River Estuary from 1984 to 2021 using Landsat imagery and Google Earth Engine . International Journal of Remote Sensing , 44 ( 10 ): 3122 - 3145 [ DOI: 10.1080/01431161.2023.2216849 http://dx.doi.org/10.1080/01431161.2023.2216849 ]
Zeng Q Z , Cao M S , Feng X Z , Liang F X , Chen X Z and Sheng W K . 1984 . A study on spectral reflection characteristics of snow, ice and water in Northwest China . Scientia Sinica (Chemica, Biologica, Agricultural, Medica, Sinica) (Series B) , 14 ( 4 ): 370 - 377
曾群柱 , 曹梅盛 , 冯学智 , 梁凤仙 , 陈贤章 , 盛文坤 . 1984 . 我国西北若干种冰、雪及水体反射光谱特性的研究 . 中国科学(B辑 化学 生物学 农学 医学 地学) , 14 ( 4 ): 370 - 377 [ DOI: 10.1360/zb1984-14-4-370 http://dx.doi.org/10.1360/zb1984-14-4-370 ]
Zheng Z , Li L W , Xue C J , Wu S Y and Wang Y . 2025 . Inversion method of offshore total suspended matter concentration based on SDGSAT-1 satellite . Remote Sensing Information , 40 ( 3 ): 172 - 180
郑直 , 李连伟 , 薛存金 , 吴世玉 , 王宇 . 2025 . 基于SDGSAT-1卫星的近海总悬浮物浓度反演方法 . 遥感信息 , 40 ( 3 ): 172 - 180 [ DOI: 10.20091/j.cnki.1000-3177.2025.03.020 http://dx.doi.org/10.20091/j.cnki.1000-3177.2025.03.020 ]
相关作者
相关机构
京公网安备11010802024621
