Hyperspectral retrievals of suspended sediment using cluster-based machine learning regression in shallow waters

Kwon, Siyoon; Seo, Il Won; Noh, Hyoseob; Kim, Byunguk

doi:10.1016/j.scitotenv.2022.155168

Cited by 22 publications

(15 citation statements)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The empirical models designed in this study can be implemented in recently developed flow‐suspended sediment‐monitoring techniques to estimate Q t because the required input variables can be obtained by these techniques. For example, at the river scale, drone‐based remote‐sensing techniques have been applied to SSCs (Kwon et al., 2022a, 2022b; Kwon et al., 2023), bathymetry, and flows (Eltner et al., 2020; Legleiter & Harrison, 2019; Legleiter & Kinzel, 2021). ADCPs can be utilized for the simultaneous measurement of flow and suspended sediment (Noh et al., 2022, 2023; Son et al., 2021).…”

Section: Discussionmentioning

confidence: 99%

“…In particular, monitoring bed loads is costlier than monitoring suspending loads. Alternative methods to monitor suspended sediment have been proposed that utilize various equipment, such as optical sensors (Agrawal & Pottsmith, 2000) and hyperspectral cameras (Kwon et al., 2022a, 2022b), enabling high spatiotemporal resolution monitoring in the simplified monitoring process. Specifically, suspended loads can be easily calibrated with optical features using turbidity or reflectances, which are readily measured remotely.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Efficient Method of Estimating Suspended‐To‐Total Sediment Load Fraction in Natural Rivers

Noh,

Park,

Seo

2023

Water Resources Research

Self Cite

View full text Add to dashboard Cite

Sediment transport load monitoring is important in civil and environmental engineering fields. Monitoring the total load is difficult, especially because of the cost of the bed load transport measurement. This study proposes estimation models for the suspended‐to‐total load fraction using dimensionless hydro‐morphological variables. Two prominent variable combinations were identified using the recursive feature elimination for support vector regression (SVR): (1) width‐to‐depth ratio, dimensionless particle size, flow Reynolds number, densimetric Froude number, and falling particle Reynolds number, and (2) flow Reynolds number, Froude number, and densimetric Froude number. The explicit relations between the suspended‐to‐total load fraction and the two combinations were revealed by two modern symbolic regression methods: multi‐gene genetic programming and Operon. The five‐variable SVR model showed the best performance. Clustering analyses using a self‐organizing map and Gaussian mixture model, respectively, identified the underlying relationships between dimensionless variables. Subsequently, the one‐at‐a‐time sensitivity of the input variables of the empirical models was investigated. The suspended‐to‐total load fraction is positively related to the flow Reynolds number and is inversely related to the densimetric Froude number. The models developed in this study are practical and easy to implement in other suspended sediment monitoring methods because they only require basic measurable hydro‐morphological variables, such as velocity, depth, width, and median bed material size.This article is protected by copyright. All rights reserved.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Novel Efficient Method of Estimating Suspended‐To‐Total Sediment Load Fraction in Natural Rivers

Noh,

Park,

Seo

2023

Water Resources Research

Self Cite

View full text Add to dashboard Cite

show abstract

“…UAV systems, due to their flexibility, real-time capabilities, and efficiency, have overcome limitations associated with satellite images, namely the restricted revisit time and information losses in cloudy and rainy weather [11], providing higher spatial resolution images [12] and filling the gaps between ground-based and satellite monitoring. Compared with multispectral images, hyperspectral imagers can rapidly acquire tens or hundreds of high-resolution, narrow-band spectral images [13], offering abundant spectral information [14] and opportunities for the inversion of non-optically active WQPs such as the chemical oxygen demand [6]. UAV hyperspectral images have already found extensive applications in agriculture [15][16][17], with various strategies involving spectral preprocessing, feature selection, and regression modeling [18].…”

Section: Introductionmentioning

confidence: 99%

“…However, the utilization of UAV-borne hyperspectral images for water quality inversion has just witnessed gradual advancement in recent years [19,20]. Limited water quality samples, synchronized UAV images, and the complexity of spectral features in water bodies have emerged as obstacles [14,21,22].…”

Section: Introductionmentioning

confidence: 99%

A Machine-Learning-Based Framework for Retrieving Water Quality Parameters in Urban Rivers Using UAV Hyperspectral Images

Liu,

2024

Remote Sensing

View full text Add to dashboard Cite

Efficient monitoring of water quality parameters (WQPs) is crucial for environmental health. Drone hyperspectral images have offered the potential for the flexible and accurate retrieval of WQPs. However, a machine learning (ML)-based multi-process strategy for WQP inversion has yet to be established. Taking a typical urban river in Guangzhou city, China, as the study area, this paper proposes a machine learning-based strategy combining spectral preprocessing and ML regression models with ground truth WQP data. Fractional order derivation (FOD) and discrete wavelet transform (DWT) methods were used to explore potential spectral information. Then, multiple methods were applied to select sensitive features. Three modeling strategies were constructed for retrieving four WQPs, including the Secchi depth (SD), turbidity (TUB), total phosphorus (TP), and permanganate index (CODMn). The highest R2s were 0.68, 0.90, 0.70, and 0.96, respectively, with corresponding RMSEs of 13.73 cm, 6.50 NTU, 0.06 mg/L, and 0.20 mg/L. Decision tree regression (DTR) was found to have the potential with the best performance for the first three WQPs, and eXtreme Gradient Boosting Regression (XGBR) for the CODMn. Moreover, tailored feature selection methods emphasize the importance of fitting processing strategies for specific parameters. This study provides an effective framework for WQP inversion that combines spectra mining and extraction based on drone hyperspectral images, supporting water quality monitoring and management in urban rivers.

show abstract

“…UAV platforms offer operational flexibility and the ability to record short-to long-term algal bloom events at the centimeter scale [17]. Numerous studies have demonstrated that UAV platforms can contribute valuable hydrology [18,19] and water quality information [20,21], regarding algae [17,[22][23][24] and other optically active constituents [25][26][27]. The photogrammetry technique is widely employed in constructing orthomosaics for many of these applications.…”

Section: Introductionmentioning

confidence: 99%

Comparing Unmanned Aerial Multispectral and Hyperspectral Imagery for Harmful Algal Bloom Monitoring in Artificial Ponds Used for Fish Farming

Olivetti

Cicerelli

Martinez

et al. 2023

Drones

View full text Add to dashboard Cite

This work aimed to assess the potential of unmanned aerial vehicle (UAV) multi- and hyper-spectral platforms to estimate chlorophyll-a (Chl-a) and cyanobacteria in experimental fishponds in Brazil. In addition to spectral resolutions, the tested platforms differ in the price, payload, imaging system, and processing. Hyperspectral airborne surveys were conducted using a push-broom system 276-band Headwall Nano-Hyperspec camera onboard a DJI Matrice 600 UAV. Multispectral airborne surveys were conducted using a global shutter-frame 4-band Parrot Sequoia camera onboard a DJI Phantom 4 UAV. Water quality field measurements were acquired using a portable fluorometer and laboratory analysis. The concentration ranged from 14.3 to 290.7 µg/L and from 0 to 112.5 µg/L for Chl-a and cyanobacteria, respectively. Forty-one Chl-a and cyanobacteria bio-optical retrieval models were tested. The UAV hyperspectral image achieved robust Chl-a and cyanobacteria assessments, with RMSE values of 32.8 and 12.1 µg/L, respectively. Multispectral images achieved Chl-a and cyanobacteria retrieval with RMSE values of 47.6 and 35.1 µg/L, respectively, efficiently mapping the broad Chl-a concentration classes. Hyperspectral platforms are ideal for the robust monitoring of Chl-a and CyanoHABs; however, the integrated platform has a high cost. More accessible multispectral platforms may represent a trade-off between the mapping efficiency and the deployment costs, provided that the multispectral cameras offer narrow spectral bands in the 660–690 nm and 700–730 nm ranges for Chl-a and in the 600–625 nm and 700–730 nm spectral ranges for cyanobacteria.

show abstract

Hyperspectral retrievals of suspended sediment using cluster-based machine learning regression in shallow waters

Cited by 22 publications

References 73 publications

A Novel Efficient Method of Estimating Suspended‐To‐Total Sediment Load Fraction in Natural Rivers

A Novel Efficient Method of Estimating Suspended‐To‐Total Sediment Load Fraction in Natural Rivers

A Machine-Learning-Based Framework for Retrieving Water Quality Parameters in Urban Rivers Using UAV Hyperspectral Images

Comparing Unmanned Aerial Multispectral and Hyperspectral Imagery for Harmful Algal Bloom Monitoring in Artificial Ponds Used for Fish Farming

Contact Info

Product

Resources

About