Supervised Machine Learning for Estimation of Total Suspended Solids in Urban Watersheds

Moeini, Mohammadreza; Shojaeizadeh, Ali; Geza, Mengistu

doi:10.3390/w13020147

Cited by 18 publications

(20 citation statements)

References 77 publications

(82 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…L.R. can be used with single or multiple variable datasets [35]. With a single variable, the method minimizes a single objective function based on that variable.…”

Section: Linear Regression (Lr)mentioning

confidence: 99%

“…Literature reviews showed that despite numerous studies focused on using specific ML methods on predicting air temperature, few studies are comparing and evaluating the application of multiple ML methods in the same study [35]. Since, temperature has a direct effect on precipitation, which will create drought event, so different ML approaches would help in forecasting drought event [36].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of Machine Learning Methods Application in Temperature Prediction

Azari¹,

Hassan²,

Pierce³

et al. 2022

CRPASE

View full text Add to dashboard Cite

Machine Learning (ML) techniques for time series prediction are becoming increasingly accurate and helpful, particularly in considering climate change. As more methods are developed, it follows that differentiating between them is becoming increasingly more important as well. This work took a local temperature time series as a dependent variable and a collection of relevant climatology time series as independent variables and applied leading Machine Learning methods to them. The six methods tested included four simple models: Linear Regression (L.R.), k-Nearest Neighbor (kNN), Support Vector Machine (SVM), and Artificial Neural Network (ANN), In addition of two ensemble model methods: Random Forest (R.F.) and Adaptive Boosting (AdB). Results compared all the method's training and predictive performances to evaluate the method's overall effectiveness in forecasting the average daily temperature value. Actual data was used to train each of the mentioned ML methods, and then they were used to predict the future temperature in the study area. The analysis revealed that out of the six methods tested, the Artificial Neural Network outperformed the others in both training and prediction of temperature values in the Memphis, TN climate.

show abstract

“…L.R. can be used with single or multiple variable datasets [35]. With a single variable, the method minimizes a single objective function based on that variable.…”

Section: Linear Regression (Lr)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Evaluation of Machine Learning Methods Application in Temperature Prediction

Azari¹,

Hassan²,

Pierce³

et al. 2022

CRPASE

View full text Add to dashboard Cite

show abstract

“…Adaptive Boosting is a boosting machine learning technique in which strong learning algorithms augment weak learning algorithms. AdaBoost must define the number of beginning students (n) as a parameter [25]. During the training phase, AdaBoost develops learners with low accuracy who improve based on their predecessors [26].…”

Section: Adaptive Boosting (Adaboost)mentioning

confidence: 99%

Extreme Gradient Boosting Algorithm for Predicting Shear Strengths of Rockfill Materials

et al. 2022

View full text Add to dashboard Cite

For the safe and economical construction of embankment dams, the mechanical behaviour of the rockfill materials used in the dam’s shell must be analyzed. The characterization of rockfill materials with specified shear strength is difficult and expensive due to the presence of particles greater than 500 mm in diameter. This work investigates the feasibility of using an extreme gradient boosting (XGBoost) computing paradigm to estimate the shear strength of rockfill materials. To train and validate the proposed XGBoost model, a total of 165 databases obtained from the literature are chosen. The XGBoost model was compared against support vector machine (SVM), adaptive boosting (AdaBoost), random forest (RF), and K-nearest neighbor (KNN) models described in the literature. XGBoost beats SVM, RF, AdaBoost, and KNN models in terms of performance evaluation metrics such as coefficient of determination (R2), Nash–Sutcliffe coefficient (NSE), and error in the root mean square ratio (RMSE) to the standard deviation of the measured data (RSR). The results demonstrated that the XGBoost model has the highest prediction performance with (R2 = 0.9707, NSE = 0.9701, and RSR = 0.1729), followed by the SVM model with (R2 = 0.9655, NSE = 0.9639, and RSR = 0.1899), RF (R2 = 0.9545, NSE = 0.9542, and RSR = 0.2140), the AdaBoost model with (R2 = 0.9390, NSE = 0.9388, and RSR = 0.2474) and the KNN model with (R2 = 0.6233, NSE = 0.6180, and RSR = 0.6181). A sensitivity analysis has been conducted to ascertain the impact of each investigated input parameter. This study demonstrates that the established XGBoost model for estimating the shear strength of rockfill materials is reliable.

show abstract

“…Although the suspended matter is not toxic, excessive amounts will have an impact on aquatic ecosystems, which can disrupt the balance of aquatic ecosystems [12]. The high concentration of suspended solids in the waters causes a reduction in water brightness [20,21], increases turbidity [17] and decreases the clarity of the waters [22].…”

Section: Introductionmentioning

confidence: 99%

“…In addition, suspended solids have the potential to lead to oxygen depletion [25,18,22] due to the increase in surface water temperature caused by the higher absorption of solar energy by these solids [23,25,22]. TSS results in fish death through clogging of the gills and TSS that settles to the bottom of the stream, potentially smothering fish eggs or other benthos [18].…”

Section: Introductionmentioning

confidence: 99%

Influence of Rainfall and Spatial Temporal Distribution Analysis of Total Suspended Solid in Laut Tawar Lake

Adhar

Lukman²,

Khalil

et al. 2022

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Total Suspended Solid (TSS) is a solid particle suspended in the water column of organic and inorganic materials, sized more than two micrometers. The high concentration of TSS in the waters causes a decrease in water clarity and potentially reduces dissolved oxygen that can threaten the life of aquatic biota. This study aims to analyze the spatial and temporal distribution of TSS and analyze the influence of rainfall on TSS in Laut Tawar Lake waters. The lake TSS ranged from 44 – 91 mg/L with an average of 68.67 ± 11.23 mg/L. Spatially TSS ranged from 63.17 - 73.67 mg/L and temporally ranged from 51.14 - 81.43 mg/L. The distribution of TSS was not spatially different because the lake waters are perfectly agitated. The difference in TSS was obtained temporally due to the influence of rainfall. The catchment area can be eroded by only 100 mm of rain/month. It leads to high production of TSS loading into the lake waters. It was indicated by the difference in TSS of Dry Months with TSS of Wet and Moist Months. The determinant coefficient of influence of rainfall on the TSS concentration of the lake waters is 0.62.

show abstract

Supervised Machine Learning for Estimation of Total Suspended Solids in Urban Watersheds

Cited by 18 publications

References 77 publications

Evaluation of Machine Learning Methods Application in Temperature Prediction

Evaluation of Machine Learning Methods Application in Temperature Prediction

Extreme Gradient Boosting Algorithm for Predicting Shear Strengths of Rockfill Materials

Influence of Rainfall and Spatial Temporal Distribution Analysis of Total Suspended Solid in Laut Tawar Lake

Contact Info

Product

Resources

About