A Machine Learning Approach for the Estimation of Total Dissolved Solids Concentration in Lake Mead Using Electrical Conductivity and Temperature

Abstract

Total dissolved solids (TDS) concentration determination in water bodies is sophisticated, time-consuming, and involves expensive field sampling and laboratory processes. TDS concentration has, however, been linked to electrical conductivity (EC) and temperature. Compared to monitoring TDS concentrations, monitoring EC and temperature is simpler, inexpensive, and takes less time. This study, therefore, applied several machine learning (ML) approaches to estimate TDS concentration in Lake Mead using EC and temperature data. Standalone models including the support vector machine (SVM), linear regressors (LR), K-nearest neighbor model (KNN), the artificial neural network (ANN), and ensemble models such as bagging, gradient boosting machine (GBM), extreme gradient boosting (XGBoost), random forest (RF), and extra trees (ET) models were used in this study. The models’ performance were evaluated using several performance metrics aimed at providing a holistic assessment of each model. Metrics used include the coefficient of determination (R2), mean absolute error (MAE), percent mean absolute relative error (PMARE), root mean square error (RMSE), the scatter index (SI), Nash–Sutcliffe model efficiency (NSE) coefficient, and percent bias (PBIAS). Results obtained showed varying model performance at the training, testing, and external validation stage of the models, with obtained R2 of 0.77–1.00, RMSE of 2.28–37.68 mg/L, an MAE of 0.14–22.67 mg/L, a PMARE of 0.02–3.42%, SI of 0.00–0.06, NSE of 0.77–1.00, and a PBIAS of 0.30–0.97 across all models for the three datasets. We utilized performance rankings to assess the model performance and found the LR to be the best-performing model on the external validation datasets among all the models (R2 of 0.82 and RMSE of 33.09 mg/L), possibly due to the established existence of a relationship between TDS and EC, although this may not always be linear. Similarly, we found the XGBoost to be the best-performing ensemble model based on the external validation with R2 of 0.81 and RMSE of 34.19 mg/L. Assessing the overall performance of the models across all the datasets, however, revealed GBM to produce a superior performance based on the ranks, possibly due to its ability to reduce overfitting and improve generalizations. The findings from this study could be employed in assisting water resources managers and stakeholders in effective monitoring and management of water resources to ensure their sustainability.

Changes in Surface Water Quality of the El Salvador River in La Joya de los Sachas, Ecuadorian Amazon Region

“…In the Puyo River, located in the central Ecuadorian Amazon Region, dissolved oxygen and nitrates were also found to be correlated [52]. The relationship between temperature and conductivity and TDS is corroborated by Adjovu et al and Dewangan et al [53,54], who maintain that as the water temperature increases, the ions present in the water become more active and move rapidly, which leads to an increase in conductivity and TDS. For this reason, the evaluation of temperature must be considered in these water quality studies.…”

“…Its development involves four main processes: the selection of relevant parameters, normalization of the data to a uniform scale, assignment of weights, and aggregation of sub-indices [12,13]. The final value obtained is given a rating from excellent (91-100) to good (71-90), average (51)(52)(53)(54)(55)(56)(57)(58)(59)(60)(61)(62)(63)(64)(65)(66)(67)(68)(69)(70), bad , or very bad (0-25) [13,17].…”

Measurement of Total Dissolved Solids and Total Suspended Solids in Water Systems: A Review of the Issues, Conventional, and Remote Sensing Techniques

“…In this approach, the spectral radiance is recalculated to above the surface irradiance reflectance and subsequently, through regression techniques related to the TDS and TSS. Over the years, studies have developed and improved these approaches leading to more recent use in the state-of-art artificial intelligence (AI) approaches such as machine learning (ML) models and deep learning which uses implicit algorithms to capture both linear and nonlinear relationships compared with the conventional statistical methods [2,124,[141][142][143][144][145].…”

“…Observed or ground-truth data from conventional field sampling should be used to complement RS measurements: this is important to ensure proper calibration and validation of RS models. Statistical or evaluation metrics such as the R 2 , Percent Bias (PBIAS), MAE, NSE, RMSE, and the ratio of the RMSE to standard deviation which have been widely used should be utilized to evaluate developed models to improve their accuracy and robustness [2,128,145,[271][272][273][274][275][276][277]. 4.…”

Rapid and Green Classification Method of Bacteria Using Machine Learning and NIR Spectroscopy

“…It is a square matrix (n × n), where n is the number of classes in which the columns express the prediction errors and successes, and the lines are the classifiers. The main diagonal lists the samples correctly classified [27,[30][31][32][33].…”