Machine Learning-Based Estimation of Suspended Sediment Concentration along Missouri River using Remote Sensing Imageries in Google Earth Engine

Dehkordi, Alireza Taheri; Ghasemi, Hani; Zoej, Mohammad Javad Valadan

doi:10.1109/icspis54653.2021.9729382

Cited by 10 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional SSC measurements are based on data from gauge stations and laboratory measurements (Choubey, 1998; Gao & O'Leary, 1997; Gray & Gartner, 2009; Milliman & Farnsworth, 2011; Walling & Fang, 2003). Although these methods are highly accurate, they are costly, time consuming and subject to locality, which hinders dynamic monitoring of the spatial distribution of SSC in rivers (Dehkordi et al., 2021; Gao & O'Leary, 1997; Gray & Gartner, 2009; Wang & Lu, 2010), as well as difficult to characterize the sediment exchange processes between river channels and floodplains (Park & Latrubesse, 2014). Owing to large spatial scale observation and short revisit time, remote sensing techniques become an important supplementary data source for ground‐based measurements (Beveridge, Hossain, Biswas, et al., 2020; Miller & McKee, 2004; Yepez et al., 2018).…”

Section: Introductionmentioning

confidence: 99%

“…The emergence of the GEE cloud computing platform has provided the possibility of rapid processing of large scale, high resolution, and long time series remote sensing data (Fu et al, 2021). Dehkordi et al (2021) used machine learning-based algorithms to quantify SSC in Missouri River and revealed that the short-wave infrared band and the near-infrared band have a strong correlation with SSC. Beveridge, Hossain, and Bonnema (2020) investigated the SSC distribution of the Mekong River Basin's 3S Tributaries in GEE platform and indicated the effects of dam construction and landcover on the SSC distribution.…”

mentioning

confidence: 99%

“…

Suspended sediment concentration (SSC) is closely related to total primary production and heavy metals in water bodies (Dekker et al, 2002;Gray & Gartner, 2009), and is one of the most important parameters for assessing water quality and the amount of organic and inorganic matter transported by rivers (Dehkordi et al, 2021). SSC surplus leads to a range of problems including obstruction of navigation, nutrient accumulation, algal blooms and reductions in aquatic populations (Henley et al, 2000;Welch et al, 2014); while SSC deficit results in reduction of biological habitats and damage to water infrastructure (Kondolf et al, 2014;Meade & Moody, 2009).

…”

mentioning

confidence: 99%

“…Previous studies attempted to estimate the spatial and temporal distribution patterns of SSC in rivers and lakes using remote sensing data, and further applied the derivative model to analyze sediment exchanges between floodplain and river channels (Mertes et al, 1993), the controlling factors on SSC distribution (Umar et al, 2018;Wu et al, 2015), as well as the morphodynamics of large fluvial systems (Park & Latrubesse, 2014) and the correlation between SSC patterns and their environment and geomorphology (Yepez et al, 2018). However, due to the data availability and atmospheric issues like cloud cover as well as unknown components in the waters that have impacts on surface reflectance, the remote sensing-based inversion of SSC is still challenging (Dehkordi et al, 2021). Additionally, traditional methods using remote sensing image processing platforms (e.g., The Environment for Visualizing Images, ENVI) are computationally slow and low efficient for data processing of remote sensing big data and dynamic monitoring of SSC (Baumann et al, 2016;Teluguntla et al, 2018;Wang et al, 2022).…”

mentioning

confidence: 99%

See 3 more Smart Citations

Google Earth Engine‐Based Estimation of the Spatio‐Temporal Distribution of Suspended Sediment Concentrations in a Multi‐Channel River System of the Yangtze River Basin

Zhao,

Huang,

et al. 2023

Water Resources Research

View full text Add to dashboard Cite

Lowland multi‐channel alluvial river systems are highly variable in frequency and magnitude of floodplain inundation and are vulnerable to human activities such as damming. In the Yangtze River Basin, the Three Gorges Dam (TGD) has trapped >80% of upstream sediment supply, causing downstream scouring and rapid geomorphic changes in river and its floodplain lakes. Suspended sediment concentration (SSC) is widely used to monitor river morphodynamics, but traditional measurements of SSC are time consuming, costly and difficult to quantify SSC in a large spatial scale. Using Google Earth Engine and in situ observed hydrological data, we created a multiple linear regression model to map SSC in the multi‐channel system Songzi River of the Yangtze. The new SSC predictive model achieved high accuracy (R2: 0.87) and showed opposite downstream trends in SSC during peak flood years and normal flood years. For the first time, we found that in the peak flood year of 1998 the study rivers exhibit a downstream increase trend of SSC with an abrupt increase in their middle reach, while SSC in normal flood years experiences a downstream decline with minimal changes. A prominent difference in SSC is also revealed after the TGD with a reduction of 60%. Furthermore, SSC in the closely hydrologically connected lakes is more dynamic than the less connected lakes. Our study demonstrates that the proposed method enables to rapidly quantify the spatio‐temporal SSC distribution in the multi‐channel systems on the floodplain of large alluvial rivers and highlights the importance of connectivity in regulating SSC dynamics.

show abstract

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

“…

…”

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Google Earth Engine‐Based Estimation of the Spatio‐Temporal Distribution of Suspended Sediment Concentrations in a Multi‐Channel River System of the Yangtze River Basin

Zhao,

Huang,

et al. 2023

Water Resources Research

View full text Add to dashboard Cite

show abstract

“…Today, with the development of cloud-based platforms such as Google Earth Engine (GEE), it has been possible to process remote sensing data online without downloading [20]. Various studies showed the effectiveness of GEE in different remote sensing applications such as landcover classification [21,22], wetland detection [23], water quality monitoring [24], flood mapping [19], and impact analysis of drought and floods on croplands [25].…”

Section: Introductionmentioning

confidence: 99%

A New Clustering Method to Generate Training Samples for Supervised Monitoring of Long-Term Water Surface Dynamics Using Landsat Data through Google Earth Engine

et al. 2022

Self Cite

View full text Add to dashboard Cite

Water resources are vital to the survival of living organisms and contribute substantially to the development of various sectors. Climatic diversity, topographic conditions, and uneven distribution of surface water flows have made reservoirs one of the primary water supply resources in Iran. This study used Landsat 5, 7, and 8 data in Google Earth Engine (GEE) for supervised monitoring of surface water dynamics in the reservoir of eight Iranian dams (Karkheh, Karun-1, Karun-3, Karun-4, Dez, UpperGotvand, Zayanderud, and Golpayegan). A novel automated method was proposed for providing training samples based on an iterative K-means refinement procedure. The proposed method used the Function of the Mask (Fmask) initial water map to generate final training samples. Then, Support Vector Machines (SVM) and Random Forest (RF) models were trained with the generated samples and used for water mapping. Results demonstrated the satisfactory performance of the trained RF model with the samples of the proposed refinement procedure (with overall accuracies of 95.13%) in comparison to the trained RF with direct samples of Fmask initial water map (with overall accuracies of 78.91%), indicating the proposed approach’s success in producing training samples. The performance of three feature sets was also evaluated. Tasseled-Cap (TC) achieved higher overall accuracies than Spectral Indices (SI) and Principal Component Transformation of Image Bands (PCA). However, simultaneous use of all features (TC, SI, and PCA) boosted classification overall accuracy. Moreover, long-term surface water changes showed a downward trend in five study sites. Comparing the latest year’s water surface area (2021) with the maximum long-term extent showed that all study sites experienced a significant reduction (16–62%). Analysis of climate factors’ impacts also revealed that precipitation (0.51 ≤ R2 ≤ 0.79) was more correlated than the temperature (0.22 ≤ R2 ≤ 0.39) with water surface area changes.

show abstract

Deep learning-based mapping of total suspended solids in rivers across South Korea using high resolution satellite imagery

Moon,

Suh,

Jung

et al. 2024

GIScience & Remote Sensing

View full text Add to dashboard Cite

Machine Learning-Based Estimation of Suspended Sediment Concentration along Missouri River using Remote Sensing Imageries in Google Earth Engine

Cited by 10 publications

References 13 publications

Google Earth Engine‐Based Estimation of the Spatio‐Temporal Distribution of Suspended Sediment Concentrations in a Multi‐Channel River System of the Yangtze River Basin

Google Earth Engine‐Based Estimation of the Spatio‐Temporal Distribution of Suspended Sediment Concentrations in a Multi‐Channel River System of the Yangtze River Basin

A New Clustering Method to Generate Training Samples for Supervised Monitoring of Long-Term Water Surface Dynamics Using Landsat Data through Google Earth Engine

Deep learning-based mapping of total suspended solids in rivers across South Korea using high resolution satellite imagery

Contact Info

Product

Resources

About