Water contamination is indeed a worldwide problem that threatens public health, environmental protection, and agricultural productivity. The distinctive attributes of machine learning (ML)-based modelling can provide in-depth understanding into increasing water quality challenges. This study presents the development of a multi-expression programming (MEP) based predictive model for water quality parameters, i.e., electrical conductivity (EC) and total dissolved solids (TDS) in the upper Indus River at two different outlet locations using 360 readings collected on a monthly basis. The optimized MEP models were assessed using different statistical measurements i.e., coefficient-of-determination (R2), root-mean-square error (RMSE), mean-absolute error (MAE), root-mean-square-logarithmic error (RMSLE) and mean-absolute-percent error (MAPE). The results show that the R2 in the testing phase (subjected to unseen data) for EC-MEP and TDS-MEP models is above 0.90, i.e., 0.9674 and 0.9725, respectively, reflecting the higher accuracy and generalized performance. Also, the error measures are quite lower. In accordance with MAPE statistics, both the MEP models shows an “excellent” performance in all three stages. In comparison with traditional non-linear regression models (NLRMs), the developed machine learning models have good generalization capabilities. The sensitivity analysis of the developed MEP models with regard to the significance of each input on the forecasted water quality parameters suggests that Cl and HCO3 have substantial impacts on the predictions of MEP models (EC and TDS), with a sensitiveness index above 0.90, although the influence of the Na is the less prominent. The results of this research suggest that the development of intelligence models for EC and TDS are cost effective and viable for the evaluation and monitoring of the quality of river water.
The conventional disposal of green straws through burning can be eliminated in a biorefinery that converts them into a range of sustainable commercial products. However, this leads to the generation of green straw biorefinery effluent (GSBE). Green straw biorefineries discharge wastewater into the ecosystem that contains high concentrations of COD and NH4+−N. It is one of the most notable sources of visual pollution and disruption of aquatic life as well as public health that requires treatment prior to discharge. To improve the GSBE quality for environmental sustainability, the attainment of sustainable development goals 6, 9, and 14, “clean water and sanitation”, “inorganic and organic waste utilization for added values from material”, and “life below water” is very important. Therefore, the effectiveness of the continuous mode activated sludge (CMAS) system and the biocomposite-based–continuous mode activated sludge (SB-CMAS) system in the treatment of GSBE was investigated in this study. Response surface methodology (RSM) was used to optimize the process variables. At their optimized conditions, the performances of CMAS and SB-CMAS were analyzed in terms of COD and NH4+−N. Findings showed 81.21% and 95.50% COD and 78.31% and 87.34% NH4+−N reduction in concentration for CMAS and SB-CMAS, respectively. The high COD and NH4+−N removal efficiencies indicate the better performance of CMAS and SB-CMAS. The first- and second-order models and the modified Stover–Kincannon biokinetic models were utilized to analyze substrate removal rates. It was discovered that the modified Stover models were ideal for the measured data with R2 values 0.99646 and 0.91236 attained for COD and NH4+−N, respectively, in CMAS. The SB-CMAS had 0.99932 and 0.99533 for COD and NH4+−N, respectively. Maximum contaminant elimination was attained at 60% GSBE and 2-day HRT. Thus, to achieve the UN SDGs for 2030, findings from this study have the potential to answer goals 6, 9, and 14.
This study evaluated multiple aspects of flood risks and effects on the Cinan Feizuo flood protection area in the Huaihe River basin. Flooding remains a leading problem for infrastructure, especially in urban, residential areas of the region. Effective flood modeling for urbanized floodplains is challenging, but MIKE (ID-2D) is paramount for analyzing and quantifying the risk in the vulnerable region. The Saint-Venant equation and a one-dimensional (1D) MIKE 11 model were used to understand the flood dynamics in the Huaihe River, and a two-dimensional (2D) MIKE 21 model was applied to assess the risk in the Cinan Feizuo flood protection area. The finite volume method (FVM) was used for discrete grid problems, and the models were coupled through the weir equation to find the flow volume from the 1D domain to the 2D domain to investigate water level changes. Flood inundation maps were generated for the flood protection area. The maximum discharge, velocity, and submerged depth for 50- and 100-year flood events were assessed with flood risk. Chenbei indicated a high flood risk level in 50 to 100 years in which the water level exceeds a high level and inundates the maximum area with minimum time. Conversely, the 100-year flood inundation in the flood protection area was comparatively higher than the 50-year flood, with a lower time step. The risk analysis identified significant damage caused by the flood over the target regions. The findings of this study provide technical support for flood risk analysis and loss assessment within the flood protection area and have important reference values for regional flood control, disaster reduction decision making, and constructive planning.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.