River Water Quality Model Research Articles

Enhanced predictive modeling of dissolved oxygen concentrations in riverine systems using novel hybrid temporal pattern attention deep neural networks

Monitoring water quality and river ecosystems is vital for maintaining public health and environmental sustainability. Over the past decade, data-driven methods have been extensively used for river water quality modeling, including dissolved oxygen (DO) concentrations. Despite advancements, challenges persist regarding accuracy, scalability, and adaptability of data-driven models to diverse environmental conditions. Previous studies primarily employed singular models or basic combinations of machine learning techniques, lacking advanced integration of adaptive mechanisms to process complex and evolving datasets. The current study introduces innovative hybrid models that integrate temporal pattern attention (TPA) mechanisms with advanced neural networks, including feed-forward neural networks (FFNNs) and long short-term memory networks (LSTMs). This approach leverages the synergistic strengths of individual models, significantly enhancing the accuracy of DO predictions. The models were rigorously tested against water quality data obtained from two distinct riverine environments, the Illinois River (ILL) and Des Plaines River (DP). Daily measured water quality data, including DO, chlorophyll-a, nitrate plus nitrite, water temperature, specific conductance, and pH, from 2017 to 2024 provided a robust foundation for comprehensive analysis of DO dynamics in these rivers. We conducted 10 scenarios with different model inputs, wherein the hybrid TPACWRNN-LSTM-10 model particularly excelled, achieving coefficient of determination values of 0.993 and 0.965, and root mean squared errors of 0.241 mg/L and 0.450 mg/L for DO predictions at the ILL and DP stations, respectively. The model's reliability was further confirmed by Willmott's index values of 0.998 and 0.992 and Nash-Sutcliffe efficiency values of 0.990 and 0.961 at the ILL and DP stations, respectively. Additionally, Shapley additive explanations (SHAP) values were utilized to interpret each predictor's contribution, revealing key drivers of DO predictions. We believe the novel hybrid modeling approach presented in this study could benefit utilities and water resource management systems for predicting water quality in complex systems.

Comparative analysis of hydrodynamic flowrate sources as drivers of water quality models for nitrogenous compounds in complex ungauged South African rivers

ABSTRACT Water quality modelling is a critical tool for managing the health of river ecosystems, particularly in regions impacted by point source pollution activities. This study investigates the influence of different hydrodynamic data sources on the performance of two river water quality models, the Basic Model (BM) and the Water Quality Analysis Simulation Programme (WASP) for modelling nitrogenous compounds in a complex river system including wastewater treatment plant effluent discharges. Four diverse hydrodynamic data input types were considered. These included measured station data, altered station data, rainfall-generated flow, and the WRSM/Pitman model estimate. Findings revealed trends, analysis of variance (ANOVA), and t-test analyses consistently demonstrated significant disparities between model predictions and measured data in specific river segments, indicating a need for segment-specific modelling approaches. An increase in Root Mean Square Error (RMSE) and Mean Square Error (MSE) values in certain segments pointed to a decline in model accuracy when confronted with distinct hydrodynamic conditions. Additionally, application of four diverse hydrodynamic data input sources yielded similar performance for BM and WASP against measured data. The research findings indicated a complex interplay between river hydrodynamics and water quality modelling, resulting in a recommendation for tailored modelling strategies that account for unique characteristics of river segments.

River water quality modelling in South Africa: Considerations, sourcing and accessing of input data

River water quality modelling relies on a good dataset for model input, calibration and validation to develop a reliable model. Determination of data requirements, and data sourcing towards this purpose in South Africa, are not elementary. Data availability is key throughout the modelling processes, making the sourcing of good data equally imperative. This paper provides starting considerations, and compiles a list of available data sources applicable to river water quality modelling in South Africa. It also provides a background on the included data sources and a general overview of the extent of the databases.

Model parameter sensitivity and identifiability for urban river water quality: impact of domestic wastewater discharges from on-site treatment facilities

Abstract River water quality degradation is a risk to human health. Hence, many water quality models have been developed to predict the future states of water bodies and understand how the current water treatment systems will respond to future pollution loads and climatic drivers. A Japanese river was evaluated with the River Water Quality Model No.1 (RWQM1), and parameter sensitivity and identifiability analyses were executed on the model output using parameter sensitivity ranking, collinearity index, and Fisher Information Matrix-derived criterion. Among RWQM1 kinetic parameters, those related to hydrolysis, growth of aerobicheterotrophs, and first-stage nitrifiers were the most influential. Reactive soluble organic substances included in untreated gray waters, in addition to a prevalence ratio of the most advanced on-site treatment facility, strongly contributed to the model output variability. A remediation analysis revealed that a renewal to the most advanced on-site treatment facility by 20% increment was almost equivalent to the 70% decrease in the effluent concentration from an on-site treatment facility producing the highest pollutant load in terms of a BOD concentration decrease in the stream. This study provided baseline data assisting in policy implementation regarding the management of effluents from on-site treatment facilities.

Learning river water quality models by l1-weighted regularization

Abstract We investigate the problem of learning a water quality model (BOD-DO model) from given data. Assuming that all parameters in the model are constants, we reformulate the problem as a system of linear equations for the unknown terms. Since in practice the system is often under-determined or over-determined and the observed data are noisy, we use an $l^{1}$-weighted regularization method to find a stable approximate solution. Then, Nesterov’s algorithm is used to solve the regularized problem. Learning models with variable coefficients are also discussed. Numerical examples show that our approach works well with noisy data and has the ability to learn the BOD-DO model.

Decision Support Framework for Optimal Reservoir Operation to Mitigate Cyanobacterial Blooms in Rivers

Flow control flushing water from reservoirs has been imposed in South Korea for mitigating harmful cyanobacterial blooms (CyanoHABs) in rivers. This measure, however, can cause water shortage in reservoirs, as the measure adopting this flow control may require an additional amount of water which exceeds the water demand allocated to the reservoirs. In terms of sustainability, a trade-off between improving water quality and alleviating water shortage needs to be considered. This study aimed at establishing a practical framework for a decision support system for optimal joint operation of the upstream reservoirs (Andong and Imha) to reduce the frequency of CyanoHABs in the Nakdong River, South Korea. Methodologically, three models were introduced: (1) a machine learning model (accuracy 88%) based on the k-NN (k-Nearest Neighbor) algorithm to predict the occurrence of CyanoHABs at a selected downstream location (the Chilgok Weir located approximately 140 km downstream from the Andong Dam), (2) a multiobjective optimization model employing NSGA-II (Nondominated Sorting Genetic Algorithm II) to determine both the quantity and quality of water released from the reservoirs, and (3) a river water quality model (R2 0.79) using HEC-RAS to simulate the water quality parameter at Chilgok Weir according to given upstream boundary conditions. The applicability of the framework was demonstrated by simulation results using observational data from 2015 to 2019. The simulation results based on the framework confirmed that the frequency of CyanoHABs would be decreased compared with the number of days when CyanoHABs were observed at Chilgok Weir. This framework, with a combination of several models, is a novelty in terms of efficiency, and it can be a part of a solution to the problem of CyanoHABs without using an additional amount of water from a reservoir.

Application of best subset method for river water quality modeling: A study on Godavari River, India

AbstractThe utilization of water quality analysis to inform optimal decision‐making is imperative to achieve sustainable management of river water quality. A multitude of research works in the past has focused on river water quality modeling. Despite being a precise statistical regression technique that allows for fitting separate models for all potential combinations of predictors and selecting the optimal subset model, the application of best subset method in river water quality modeling is not widely adopted. The current research aims to validate the use of best subset method in evaluating the water quality parameters of the Godavari River, one of the largest rivers in India, by developing regression equations for different combinations of its physicochemical parameters. The study involves in formulating best subset regression equations to estimate the concentrations of river water quality parameters while also identifying and quantifying their variations. A total of 17 water quality parameters are analyzed at 13 monitoring sites using 13 years (1993–2005) of observed data for the monsoon (June–October) period and post‐monsoon (November–February) period. The final subset model is selected among model combinations that are developed for each year's dataset through widely used statistical criteria such as R2, F value, adjusted R2a, AICc, and RSS. The final best subset model across all parameters exhibits R2 values surpassing 0.8, indicating that the models possess the ability to account for over 80% of the variations in the concentrations of dependent parameters. Therefore, the findings demonstrated the appropriateness of this method in evaluating the water quality parameters in extensive rivers. This work is very useful for decision‐making and in the management of river water quality for its sustainable use in the study area.

Remote sensing-enabled machine learning for river water quality modeling under multidimensional uncertainty

Two fundamental problems have inhibited progress in the simulation of river water quality under climate (and other) uncertainty: 1) insufficient data, and 2) the inability of existing models to account for the complexity of factors (e.g., hydro-climatic, basin characteristics, land use features) affecting river water quality. To address these concerns this study presents a technique for augmenting limited ground-based observations of water quality variables with remote-sensed surface reflectance data by leveraging a machine learning model capable of accommodating the multidimensionality of water quality influences. Total Suspended Solids (TSS) can serve as a surrogate for chemical and biological pollutants of concern in surface water bodies. Historically, TSS data collection in the United States has been limited to the location of water treatment plants where state or federal agencies conduct regularly-scheduled water sampling. Mathematical models relating riverine TSS concentration to the explanatory factors have therefore been limited and the relationships between climate extremes and water contamination events have not been effectively diagnosed. This paper presents a method to identify these issues by utilizing a Long Short-Term Memory Network (LSTM) model trained on Moderate Resolution Imaging Spectroradiometer (MODIS) satellite reflectance data, which is calibrated to TSS data collected by the Ohio River Valley Water Sanitation Commission (ORSANCO). The methodology developed enables a thorough empirical analysis and data-driven algorithms able to account for spatial variability within the watershed and provide effective water quality prediction under uncertainty.

Pollution source identification and abatement for water quality sections in Huangshui River basin, China

Accurately obtaining the pollution sources and their contribution rates is the basis for refining watershed management. Although many source analysis methods have been proposed, a systematic framework for watershed management is still lacking, including the complete process of pollution source identification to control. We proposed a framework for identification and abatement of pollutants and applied in the Huangshui River Basin. A newer contaminant flux variation method based on a one-dimensional river water quality model was used to calculate the contribution of pollutants. The contributions of various factors to the over-standard parameters of water quality sections at different spatial and temporal scales were calculated. Based on the calculation results, corresponding pollution abatement projects were developed, and the effectiveness of the projects was evaluated through scenario simulation. Our results showed that the large scale livestock and poultry farms and sewage treatment plants were the largest sources of total nitrogen (TP) in Xiaoxia bridge section, with contribution rates of 46.02% and 36.74%, respectively. Additionally, the largest contribution sources of ammonia nitrogen (NH3–N) were sewage treatment plants (36.17%) and industrial sewage (26.33%). Three towns that contributed the most to TP were Lejiawan Town (14.4%), Ganhetan Town (7.3%) and Handong Hui Nationality town (6.6%), while NH3–N mainly from the Lejiawan Town (15.9%), Xinghai Road Sub-district (12.4%) and Mafang Sub-district (9.5%). Further analysis found that point sources in these towns were the main contributor to TP and NH3–N. Accordingly, we developed abatement projects for point sources. Scenario simulation indicated that the TP and NH3–N could be significantly improved by closing down and upgrading relevant sewage treatment plants and building facilities for large scale livestock and poultry farms. The framework adopted in this study can accurately identify pollution sources and evaluate the effectiveness of pollution abatement projects, which is conducive to the refined water environment management.

REVIEW PAPER ON PREDICTION OF WATER QUALITY PARAMETER USING MACHINE LEARNING

Surface water pollution become a nuisance for humankind as river water fulfill requirement of a major population and traditional method of water quality assessment and evaluation is inadequate in this era. So using advance method of machine learning in prediction of surface water proves to be helpful to prevent future water accident. As we seen many recent studies of water quality prediction and river water assessment using machine learning approach for better accuracy and less labor and to optimize its overall results. It’s become essential to review the recent studies which used Machine Learning algorithms for prediction, analysis, evaluation and assessment of river water quality and different models used in these studies for different environmental conditions. Machine learning models are superior to handle such complex and non linear data such as water quality parameters with greater accuracy, reliability, cost-effectiveness and efficiency as considered as great tool for surface Water Quality monitoring, prediction, future projects and help lawmakers in policy. In this report we reviewed around 17 research papers which uses machine learning approach from different journal and concise it to covers the structure of study, datasets used, methodology analysis, models performance, environment susceptibility, comparative analysis and assessments of Machine Learning models progress in river water quality research. For better management and control of surface water quality and its treatment, this study will help in understanding and analyzing the studies reviewed in this paper and its future application. We can conclude that research on Water Quality prediction using Machine Learning model are inadequate in the context future vulnerability, observing increasing pollution in recent years we require more research in this field. Finally, this study provides breakthrough in Surface Water Engineering and Management to give a new direction to fore coming studies and fortified it scope also gives a comparative approach for its implementation in new studies.

A high-resolution comprehensive water quality model based on GPU acceleration techniques

The study of the temporal and spatial evolution of pollutants in modern water bodies and river water quality management largely depend on river water quality models. These models are usually constructed based on detailed hydrodynamic models but cannot satisfy the high precision and efficiency requirement of model simulations in high-resolution terrain. To solve this problem, we developed a high-resolution comprehensive water quality model based on the graphics processing unit (GPU) acceleration techniques in which hydrodynamics and accompanying contaminants were perfectly coupled. The performance and functionality of the model were improved by using the Compute Unified Device Architecture (CUDA) parallel computing architecture and robust model algorithms. A simulation function of the transport attenuation and interaction among multicomponent pollutants was stablished by solving mass conservation, momentum and chemical concentration equations of the flow process. The simulation results of the pure pollutant reaction process and the transport and reaction process were validated against an analytical solution and the results of a two-dimensional steady water quality model by using the Nash-Sutcliffe efficiency (NSE) coefficient. The coefficients were 0.996 and 0.984, respectively. The water quality of the Xidagou River in Yinchuan was evaluated and analyzed by using the validated high-resolution comprehensive water quality model, and the numerical results of two-dimensional pollutant transport were explored. On the adopted RTX3070d computer, only 0.12 h were needed to simulate the hydrodynamic and water quality evolution process involving 350.000 cells with 5-h model settings. The model achieved a high operation speed and high calculation accuracy and could effectively simulate, predict and evaluate various complex water environment problems. This study provides a reliable tool for further research on the water environment and water ecology and the treatment of black and odorous water bodies.

How do inorganic nitrogen processing pathways change quantitatively at daily, seasonal, and multiannual scales in a large agricultural stream?

Abstract. Large agricultural streams receive excessive inputs of nitrogen. However, quantifying the role of these streams in nitrogen processing remains limited because continuous direct measurements of the interacting and highly time-varying nitrogen processing pathways in larger streams and rivers are very complex. Therefore, we employed a monitoring-driven modelling approach with high-frequency in situ data and the river water quality model Water Quality Analysis Simulation Program (WASP) 7.5.2 in the 27.4 km reach of the sixth-order agricultural stream called Lower Bode (central Germany) for a 5-year period (2014–2018). Paired high-frequency sensor data (15 min interval) of discharge, nitrate, dissolved oxygen, and chlorophyll a at upstream and downstream stations were used as model boundaries and for setting model constraints. The WASP model simulated 15 min intervals of discharge, nitrate, and dissolved oxygen with Nash–Sutcliffe efficiency values higher than 0.9 for calibration and validation, enabling the calculation of gross and net dissolved inorganic nitrogen uptake and pathway rates on a daily, seasonal, and multiannual scale. Results showed daily net uptake rate of dissolved inorganic nitrogen ranged from −17.4 to 553.9 mgNm-2d-1. The highest daily net uptake could reach almost 30 % of the total input loading, which occurred at extreme low flow in summer 2018. The growing season (spring and summer) accounted for 91 % of the average net annual uptake of dissolved inorganic nitrogen in the measured period. In spring, both the DIN gross and net uptake were dominated by the phytoplankton uptake pathway. In summer, benthic algae assimilation dominated the gross uptake of dissolved inorganic nitrogen. Conversely, the reach became a net source of dissolved inorganic nitrogen with negative daily net uptake values in autumn and winter, mainly because the release from benthic algae surpassed uptake processes. Over the 5 years, average gross and net uptake rates of dissolved inorganic nitrogen were 124.1 and 56.8 mgNm-2d-1, which accounted for only 2.7 % and 1.2 % of the total loadings in the Lower Bode, respectively. The 5-year average gross DIN uptake decreased from assimilation by benthic algae through assimilation by phytoplankton to denitrification. Our study highlights the value of combining river water quality modelling with high-frequency data to obtain a reliable budget of instream dissolved inorganic nitrogen processing which facilitates our ability to manage nitrogen in aquatic systems. This study provides a methodology that can be applied to any large stream to quantify nitrogen processing pathway dynamics and complete our understanding of nitrogen cycling.

Performance Analysis of Neural Network Architecture in Developing Real-Time Malaysian River Water Quality Model

According to the world health organization, 485,000 people died each year due to water-related health diseases which are mainly contributed by poor river water quality. As a result, water quality monitoring stations have been deployed across the world. Unfortunately, due to the complex nature of the off-site water quality parameters, the water quality index (WQI) cannot be assessed in real-time. This has led to a significant push for the scientific community to develop an accurate and robust water quality prediction model. The dynamic and nonlinear nature of water quality parameters are major challenges for traditional machine learning algorithms such as multi linear regression to capture. In this study, the water quality index prediction model was developed using the feedforward artificial neural network (FANN) algorithms utilizing only on-site parameters. The performance of different nonlinear activation functions in the hidden neurons was thoroughly analysed which includes rectified linear unit (ReLU), scaled exponential linear unit (SELU), and exponential linear unit (ELU). Additionally, various initialization and optimization algorithms were also evaluated for maximum performance and efficiency. The results shows that FANN-ELU model coupled with Glorot initialization technique and AdaGrad optimizer outperformed other model combinations with an R2 value of 0.88 and mean squared error (MSE) value of 22.74.

Application of synthetic data to establish the working framework for multivariate statistical analysis of river pollution traceability - the heavy metals in Nankan River, Taiwan.

This study applied multivariate statistical analysis (MSA) to synthetic data simulated by a river water quality model to verify whether the MSA can correctly infer the pollution scenario assigned in the river water quality model. The results showed that when assessing the number and possible locations of pollution sources based on the results of cluster analysis (CA), two instead of three pollution point source were identified when considering the hydraulic variations of surface water. When discussing the principal component analysis (PCA) result, the second principal component (PC2) and the Pearson correlation coefficients among the pollutants should also be considered, which can infer that Cu, Pb, Cr, and Ni are contributed by the same pollutant point source, and Cu is also influenced by another pollutant point source. This result also implies that the solid and liquid partition coefficients (Kd) of pollutants can affect the interpretation of the PCA results, so the Kd values should be determined before tracing the pollution sources to facilitate the evaluation of the source characteristics and potential targets. This study established a working framework for surface water pollution traceability to enhance the effectiveness of pollution traceability.

Tuning fuzzy logic controller with SGWO for river water quality modelling

Particle Swarm Optimization (PSO) algorithm is amongst the prominent population dependent search procedure and was originally established on the communal conduct and intelligence of birds inside a swarm. Further, PSO algorithm is used as a prominent tuning tool for fuzzy logic controllers. Nevertheless, it still experiences abundant difficulties while dealing with Mamdani’s fuzzy logic controller. In the present work, we are analyzing the water quality of river Yamuna for the years 2018–2019 using Mamdani’s fuzzy logic controller and an adjustable hybrid variant, Swarmed Grey Wolf Optimizer has been employed to tune membership function’s parameters of the fuzzy logic controller. We validate our proposed approach by comparing similar fuzzy systems tuned with PSO and Grey Wolf Optimizer in terms of Root Mean Square Error. The outcomes of the investigation revealed that the proposed model is effective and promising in the field of water quality modelling.

Using Arc GIS to explore the impact of environmental and ecological factors on water body

As water pollution is more and more serious, ArcGIS is proposed to explore the impact of environmental and ecological factors on water. Taking the river water quality as the research object, this paper simulates and analyzes the endogenous and non-point source pollution and water quality through indoor physical model experiment, hydrological and water quality numerical model and water quality numerical model, and analyzes the impact of different environmental changes on river water quality and pollution sources from micro and macro perspectives. The main contents include: experimental study on the influence mechanism of overlying water velocity, disturbance and water temperature on sediment endogenous release, construction and simulation of watershed non-point source pollution model, construction and simulation of watershed river water quality model, as well as the impact of environmental change on river water quality and quantitative analysis of river pollution sources.

DETERMINATION OF DEOXYGENATION RATE OF URBAN RIVER USING MODIFICATION METHODS FOR CITEPUS RIVER WATER, BANDUNG, INDONESIA

River water quality modeling needs appropriate and suitable coefficients especially in application for specific river like urban river. Aim: This study aims to determine the value of the coefficient with a short term duration and a variable test time span. Several ways and methods of determining the rate of deoxygenation are developed according to the characteristics of the river and the environment. Modification method was applied in this research in which the test time span was unequal. The river chosen in this study is the Citepus River, Bandung, Indonesia representing an urban river in a tropical country. Methodology and Results: Sampling was carried out in the dry season. The laboratory analysis method used in determining the rate of deoxygenation uses the Slope Method of data from the short term incubation, which is ten days. The results showed that the Thomas Slope method's deoxygenation rate (K1) was 0.095 per day in the upstream segment, 0.917 per day in the middle segment, and 0.180 per day in the downstream segment. While the Ultimate BOD (La) value is 46.95 mg/l in the upstream segment, 38.70 mg/l in the middle segment, and 37.60 mg/l in the downstream segment. Conclusion, significance, and impact of study: The results of this study show that the value of the deoxygenation rate is similar to the theoretical surface water conditions. However, in the upstream segment, there is still a low deoxygenation rate value due to non-optimal activity of microorganisms. This findings will be very useful both in water quality modeling and river management.

Hierarchical systems integration for coordinated urban-rural water quality management at a catchment scale

Managing river quality is important for sustainable catchment development. In this study, we present how catchment management strategies benefit from a coordinated implementation of measures that are based on understanding key drivers of pollution. We develop a modelling approach that integrates environmental impacts, human activities, and management measures as three hierarchical levels. We present a catchment water management model (CatchWat) that achieves all three hierarchical levels and is applied to the Cherwell Catchment, UK. CatchWat simulations are evaluated against observed river flow and pollutant data including suspended solids, total nitrogen, and total phosphorus. We compare three competing hypotheses, or framings, of the catchment representation (integrated, urban-only, and rural-only framings) to test the impacts of model boundaries on river water quality modelling. Scenarios are formulated to simulate separate, combined and coordinated implementation of fertiliser application reduction and enhanced wastewater treatment. Results show that models must represent both urban and rural pollution emissions to accurately estimate river quality. Agricultural activities are found to drive river quality in wet periods because runoff is the main pathway for rural pollutants. Meanwhile, urban activities are the key source of pollution in dry periods because effluent constitutes a larger percentage of river flow during this time. Based on this understanding, we identify a coordinated management strategy that implements fertiliser reduction measures to improve river quality during wet periods and enhanced wastewater treatment to improve river quality during dry periods. The coordinated strategy performs comparably to the combined strategy but with higher overall efficiency. This study emphasises the importance of systems boundaries in integrated water quality modelling and simulating the mechanisms of seasonal water quality behaviour. Our key recommendation is that incorporating these mechanisms is required to develop coordinated strategies for river water quality management, that can ultimately lead to more efficient and sustainable catchment management.

Modeling Biological Oxygen Demand Load Capacity in a Data-Scarce Basin with Important Anthropogenic Interventions

Most water bodies are currently used as receptors for pollutants coming mainly from the industrial and domestic sectors. The Biobío river is subjected to multiple anthropogenic pressures such as industrial water supply, drinking water, hydroelectric power generation, agriculture, and the final receptor body of a large amount of industrial and urban waste, pressures that will intensify due to the decrease in water flow as a result of climate change. In this context, organic contamination has been found mainly from sewage discharges and oxidizable waste discharges generated by industrial processes. In this sense, the objective of this research is to determine the Biological Oxygen Demand Loading Capacity (LC) in a basin with a low density of water quality data subjected to strong anthropogenic pressures. To estimate the carrying capacity in a section of the Biobío River, the water quality model River and Stream Water Quality Model- Qual2K version 2.11b8, developed by Chapra, was used. This model solves the Streeter–Phelps equation, proposing an analytical expression to relate the dissolved oxygen (DO) and biochemical oxygen demand (BOD5) variables. These variables were modeled for different critical scenarios of minimum flows in return periods of 5, 50, and 100 years, determining that the studied section of the Biobío river would have a high carrying capacity to not be affected by its organic matter pollution.

Application of fuzzy logic in river water quality modelling for analysis of industrialization and climate change impact on Sabarmati river

Abstract Rivers are critical to human life because they are strategically significant in the world, providing primary water supplies for various purposes. Rivers are the prime importance of any country as most of the cities are settled near the river. Due to developmental activities and increase in population, it will result in huge waste generation. Surface water quality is affected because of increasing urbanization and industrialization. The aim of this research is to examine the effect of climate change and industrialization on the water quality of the Sabarmati river using a mathematical model. For this study, four important towns along the lower Sabarmati River have been considered and water quality data was considered from 2005 to 2015. In this study, different water quality parameters were considered to derive a water quality model. Results show the water quality downstream after Ahmedabad city is worse compared to the other location where the Maximum WQI is 0.71 at Rasikapur and average WQI is 0.50 for the same location for the last 15 years. It has been observed that the effect of the monsoon and also by comparing time scale water quality model the role of regulations for industrialization also plays an important role in the quality of Sabarmati river.