Water quality prediction using SWAT-ANN coupled approach

Noori, Navideh; Kalin, Latif; Işık, Sabahattin

doi:10.1016/j.jhydrol.2020.125220

Cited by 111 publications

(50 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, ANN was combined with PSO to create a new model in the prediction of laser metal deposition process [42]. Moreover, to enhance the water quality predictions, Noori et al [43] developed a hybrid model by combining a process-based watershed model and ANN. In terms of structural failure, Mangalathu et al [44] contributed to the critical need of failure mode prediction for circular reinforced concrete bridge columns by using several AI algorithms, including nearest neighbors, decision trees, random forests, Naïve Bayes, and ANN.…”

Section: Literature Reviewmentioning

confidence: 99%

Metaheuristic Optimized Multi-Level Classification Learning System for Engineering Management

Chou

Pham

2021

Applied Sciences

View full text Add to dashboard Cite

Multi-class classification is one of the major challenges in machine learning and an ongoing research issue. Classification algorithms are generally binary, but they must be extended to multi-class problems for real-world application. Multi-class classification is more complex than binary classification. In binary classification, only the decision boundaries of one class are to be known, whereas in multiclass classification, several boundaries are involved. The objective of this investigation is to propose a metaheuristic, optimized, multi-level classification learning system for forecasting in civil and construction engineering. The proposed system integrates the firefly algorithm (FA), metaheuristic intelligence, decomposition approaches, the one-against-one (OAO) method, and the least squares support vector machine (LSSVM). The enhanced FA automatically fine-tunes the hyperparameters of the LSSVM to construct an optimized LSSVM classification model. Ten benchmark functions are used to evaluate the performance of the enhanced optimization algorithm. Two binary-class datasets related to geotechnical engineering, concerning seismic bumps and soil liquefaction, are then used to clarify the application of the proposed system to binary problems. Further, this investigation uses multi-class cases in civil engineering and construction management to verify the effectiveness of the model in the diagnosis of faults in steel plates, quality of water in a reservoir, and determining urban land cover. The results reveal that the system predicts faults in steel plates with an accuracy of 91.085%, the quality of water in a reservoir with an accuracy of 93.650%, and urban land cover with an accuracy of 87.274%. To demonstrate the effectiveness of the proposed system, its predictive accuracy is compared with that of a non-optimized baseline model, single multi-class classification algorithms (sequential minimal optimization (SMO), the Multiclass Classifier, the Naïve Bayes, the library support vector machine (LibSVM) and logistic regression) and prior studies. The analytical results show that the proposed system is promising project analytics software to help decision makers solve multi-level classification problems in engineering applications.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Metaheuristic Optimized Multi-Level Classification Learning System for Engineering Management

Chou

Pham

2021

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…A few studies (El-Khoury et al 2015;Zhou et al 2015;C ̌erkasova et al 2018) have also obtained better performance for streamflow calibration. The reason for the low performance in predicting water quality parameters is the limited available data for a large number of parameters, highlighted in Hoang et al (2019) and Noori et al (2020). There are also greater uncertainties in nutrient data associated with errors in streamflow measurements, sample collection, storage, and analysis (Harmel & Smith 2007).…”

Section: Model Performancementioning

confidence: 99%

Impacts of urbanization and climate change on water quantity and quality in the Carp River watershed

Zango

Seidou

Sartaj

et al. 2021

Journal of Water and Climate Change

View full text Add to dashboard Cite

Pressure on water resources has reached unprecedented levels during the last decades because of climate change, industrialization, and population growth. As a result, vulnerability to inappropriate water availability and/or quality is increasing worldwide. In this paper, a Soil & Water Assessment Tool (SWAT) model of the Carp river watershed located in the city of Ottawa, Ontario was calibrated and validated. The model was then used to evaluate the individual and coupled impacts of urbanization and climate change on water quantity (discharge) and quality (nitrogen and phosphorus loads). While most of the watershed is currently rural, the headwaters will undergo rapid urbanization in the future, and there are concerns about possible negative impacts on water quantity and quality. Seven scenarios were developed to represent various watershed configurations in terms of land use and climate regime. Future climate time series were obtained by statistically downscaling the outputs of nine regional climate models, ran under representative concentration pathways (RCP)4.5 and RCP8.5. The impacts were evaluated at the main outlet and at the outlet of an upstream sub-watershed that would be most affected by urbanization. Results show that climate change and urbanization's impacts vary greatly depending on the spatial scale and geographic location. Globally, the annual average discharge will increase between 6.75 and 9.34% by 2050, while changes in annual average nitrogen and phosphorus loads will vary between −1.20 and 24.84%, and 19.15 and 23.81%, respectively. Local impacts in sub-watersheds undergoing rapid urbanization would be often much larger than watershed-scale impacts.

show abstract

“…The opposite effect was broadly observed in the case of forested buffer zones, as their presence limited nitrate concentration [14,39], although such influence was seasonally differentiated [14]. Another common research issue was the prediction of nutrient concentration as an effect of non-point pollution with the use of the hydrological models, such as the SWAT model, or even with the use of an artificial neural network [40][41][42]. Such investigations related to landscape dependence of nutrient dynamics were mainly focused on areas with the dominance of cereal crops [43,44], rice [45], and livestock farming, especially dominated by cattle, sheep, and poultry [27,28,44,46].…”

Section: Introductionmentioning

confidence: 99%

Spatial and Seasonal Dynamics of Inorganic Nitrogen and Phosphorous Compounds in an Orchard-Dominated Catchment with Anthropogenic Impacts

Stępniewski

Łaszewski

2021

Sustainability

View full text Add to dashboard Cite

The influence of various types of agricultural activities on the dynamics of biogenic compounds of flowing water was broadly recognized in many spatial and temporal scales. However, relatively minor attention was paid to the hydrochemical functioning of horticultural catchments despite their importance and dominance in some regions of Europe. Thus, the current study investigated spatial and seasonal variations in inorganic nitrogen and phosphorous compounds in stream water in the Mogielanka River catchment, with 72% covered by apple orchards. Water samples were collected from fifteen sites distributed across the catchment in the monthly timescale from March 2020 to February 2021. Concentrations of NO3−, NO2−, NH4+, and PO43− were determined photometrically, while in situ water temperature, oxygen saturation, electrical conductivity, and pH, were measured with the use of portable devices. The impact of horticulture was mainly documented in the higher concentration of NO3− during the winter months; however, maximum values did not exceed 15 mg·dm−3 and were relatively low in comparison to catchments dominated by arable lands. The authors also found a clear impact of unstratified reservoirs and inflows from wastewater treatment plants on the dynamics of biogenic compounds. The correlations of PO43− with the sums of precipitation suggested, in turn, that increased PO43− concentration mainly results from poor sewage management. The results provided preliminary but unique and spatially extensive insight into the functioning of an orchard-dominated lowland catchment and allowed the researchers to point out the main recommendations for improving water quality in similar regions.

show abstract

Water quality prediction using SWAT-ANN coupled approach

Cited by 111 publications

References 37 publications

Metaheuristic Optimized Multi-Level Classification Learning System for Engineering Management

Metaheuristic Optimized Multi-Level Classification Learning System for Engineering Management

Impacts of urbanization and climate change on water quantity and quality in the Carp River watershed

Spatial and Seasonal Dynamics of Inorganic Nitrogen and Phosphorous Compounds in an Orchard-Dominated Catchment with Anthropogenic Impacts

Contact Info

Product

Resources

About