Continuous monitoring of suspended sediment concentrations using image analytics and deriving inherent correlations by machine learning

Ghorbani, Mohammad Ali; Khatibi, Rahman; Singh, Vijay P.; Kahya, Ercan; Ruskeepää, Heikki; Saggi, Mandeep Kaur; Sivakumar, Bellie; Kim, Sung-Won; Salmasi, Farzin; Kashani, Mahsa H.; Samadianfard, Saeed; Shahabi, Mahmoud; Jani, Rasoul

doi:10.1038/s41598-020-64707-9

Cited by 15 publications

(8 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Higher SSC values are not captured by modeling alone [51]. Examination at extreme sediment transport instances and correlation plots reveals that the peak SSC events moderately correlated with consecutive 3-day precipitation.…”

Section: Discussionmentioning

confidence: 87%

Insights on the Impacts of Hydroclimatic Extremes and Anthropogenic Activities on Sediment Yield of a River Basin

Talchabhadel

Panthi

Sharma

et al. 2021

Earth

View full text Add to dashboard Cite

Streamflow and sediment flux variations in a mountain river basin directly affect the downstream biodiversity and ecological processes. Precipitation is expected to be one of the main drivers of these variations in the Himalayas. However, such relations have not been explored for the mountain river basin, Nepal. This paper explores the variation in streamflow and sediment flux from 2006 to 2019 in central Nepal’s Kali Gandaki River basin and correlates them to precipitation indices computed from 77 stations across the basin. Nine precipitation indices and four other ratio-based indices are used for comparison. Percentage contributions of maximum 1-day, consecutive 3-day, 5-day and 7-day precipitation to the annual precipitation provide information on the severity of precipitation extremeness. We found that maximum suspended sediment concentration had a significant positive correlation with the maximum consecutive 3-day precipitation. In contrast, average suspended sediment concentration had significant positive correlations with all ratio-based precipitation indices. The existing sediment erosion trend, driven by the amount, intensity, and frequency of extreme precipitation, demands urgency in sediment source management on the Nepal Himalaya’s mountain slopes. The increment in extreme sediment transports partially resulted from anthropogenic interventions, especially landslides triggered by poorly-constructed roads, and the changing nature of extreme precipitation driven by climate variability.

show abstract

Section: Discussionmentioning

confidence: 87%

Insights on the Impacts of Hydroclimatic Extremes and Anthropogenic Activities on Sediment Yield of a River Basin

Talchabhadel

Panthi

Sharma

et al. 2021

Earth

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 99%

“…In this figure, the SVM-AF optimization algorithm has lower error than the SVM-wavelet such that the relative error values of the latter model are higher for all of the studied stations. 34,35 Taylor diagrams were used to analyze and evaluate the models used in the study, as shown in Figure 7. A clear advantage of Taylor's diagram is that it uses 2 common correlation statistics: the correlation coefficient and the standard deviation.…”

Section: Comparison Of the Performances Of The Modelsmentioning

confidence: 99%

Forecasting Daily River Flow Using an Artificial Flora–Support Vector Machine Hybrid Modeling Approach (Case Study: Karkheh Catchment, Iran)

Dehghani

Poudeh

Younesi

et al. 2020

Air, Soil and Water Research

View full text Add to dashboard Cite

In this study, the hybrid support vector machine–artificial flora algorithm method was developed and the obtained results were compared with those of the support vector–wave vector machine model. Karkheh catchment area was considered as a case study to estimate the flow rate of rivers using the daily discharge statistics taken from hydrometric stations located upstream of the dam in the statistical period of 2008 to 2018. Necessary criteria including coefficient of determination, root mean square error (RMSE), mean absolute error (MAE), and Nash–Sutcliffe coefficient were used to evaluate and compare the models. The results illustrated that the combined structures provided acceptable results in terms of river flow modeling. Also, a comparison of the models based on the evaluation criteria and Taylor’s diagram demonstrated that the proposed hybrid method with the correlation coefficient of R2 = 0.924 to 0.974, RMSE = 0.022 to 0.066 m3/s, MAE = 0.011 to 0.034 m3/s, and Nash-Sutcliffe (NS) coefficient = 0.947 to 0.986 outperformed other methods in terms of estimating the daily flow rates of rivers.

show abstract

“…However, this segmentation method is not ideal for complex images. The introduction of DL improves the effectiveness of the segmentation of high-dimensional complex images [ 11 , 12 ]. The image segmentation system based on the DC-Unet network model of DL is studied, and it is introduced from the structure design, the preparation for training datasets, model construction, and model training.…”

Section: Methodsmentioning

confidence: 99%

Image Segmentation under the Optimization Algorithm of Krill Swarm and Machine Learning

Geng¹,

Yan

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

This study aims to improve the efficiency and accuracy of image segmentation, and to compare and study traditional threshold-based image segmentation methods and machine learning model-based image segmentation methods. The krill herb optimization algorithm is combined with the traditional maximum between-class variance function to form a new graph segmentation algorithm. The pet dataset is used to train the algorithm model and build an image semantic segmentation system. The results show that when the traditional Ostu algorithm performs image single-threshold segmentation, the number of iterations is about 256. When double-threshold segmentation is performed, the number of iterations increases exponentially, and the execution time is about 2 s. The number of iterations of the improved Krill Herd algorithm in single-threshold segmentation is 6.95 times, respectively. The execution time for double-threshold segmentation is about 0.24 s. The number of iterations is only improved by a factor of 0.19. The average classification accuracy of the Unet network model and the SegNet network model is 86.3% and 91.9%, respectively. The average classification accuracy of the DC-Unet network model reaches 93.1%. This shows that the proposed fusion algorithm has high optimization efficiency and stronger practicability in multithreshold image segmentation. The DC-Unet network model can improve the image detail segmentation effect. The research provides a new idea for finding an efficient and accurate image segmentation method.

show abstract

Continuous monitoring of suspended sediment concentrations using image analytics and deriving inherent correlations by machine learning

Cited by 15 publications

References 19 publications

Insights on the Impacts of Hydroclimatic Extremes and Anthropogenic Activities on Sediment Yield of a River Basin

Insights on the Impacts of Hydroclimatic Extremes and Anthropogenic Activities on Sediment Yield of a River Basin

Forecasting Daily River Flow Using an Artificial Flora–Support Vector Machine Hybrid Modeling Approach (Case Study: Karkheh Catchment, Iran)

Image Segmentation under the Optimization Algorithm of Krill Swarm and Machine Learning

Contact Info

Product

Resources

About