Compressive strength is one of the important property of concrete and depends on many factors. Most of the concrete compressive strength predictive models mainly rely on available literature data, which are too simple to consider all the contributing factors. This study adopted a new approach to predict the compressive strength of sugarcane bagasse ash concrete (SCBAC). A vast amount of data from the literature study and fifteen laboratory tested concrete samples with different dosage of bagasse ash, were respectively used to calibrate and validate the models. The novel Gene Expression Programming, Multiple Linear Regression and Multiple Non-Linear Regression were used to model SCBAC compressive strength. The water cement ratio, bagasse ash percent replacement, quantity of fine and coarse aggregate and cement content were used as an input for models development. Various statistical indicators, i.e., NSE, R² and RMSE were used to assess the performance of the models. The results indicated a strong correlation between observed and predicted values with NSE and R² both above 0.8 during calibration and validation for the Gene Expression Programming (GEP). The outcomes from GEP outclassed all the models to predict SCBAC compressive strength. The validity of the model is further verified using data of fifteen tests conducted in the laboratory. Moreover, the cement content in the mix was revealed as the most sensitive parameter followed by water cement ratio form sensitivity analysis. The GEP fulfilled all the criteria for external validity. The simple formulae derived in this study could be used reliably for the prediction of SCBAC compressive strength.

Water pollution is an increasing global issue that societies are facing and is threating human health, ecosystem functions and agriculture production. The distinguished features of artificial intelligence (AI) based modeling can deliver a deep insight pertaining to rising water quality concerns. The current study investigates the predictive performance of gene expression programming (GEP), artificial neural network (ANN) and linear regression model (LRM) for modeling monthly total dissolved solids (TDS) and specific conductivity (EC) in the upper Indus River at two outlet stations. In total, 30 years of historical water quality data, comprising 360 TDS and EC monthly records, were used for models training and testing. Based on a significant correlation, the TDS and EC modeling were correlated with seven input parameters. Results were evaluated using various performance measure indicators, error assessment and external criteria. The simulated outcome of the models indicated a strong association with actual data where the correlation coefficient above 0.9 was observed for both TDS and EC. Both the GEP and ANN models remained the reliable techniques in predicting TDS and EC. The formulated GEP mathematical equations depict its novelty as compared to ANN and LRM. The results of sensitivity analysis indicated the increasing trend of input variables affecting TDS as HCO₃⁻ (22.33%) > Cl⁻ (21.66%) > Mg²⁺ (16.98%) > Na⁺ (14.55%) > Ca²⁺ (12.92%) > SO₄²⁻ (11.55%) > pH (0%), while, in the case of EC, it followed the trend as HCO₃⁻ (42.36%) > SO₄²⁻(25.63%) > Ca²⁺ (13.59%) > Cl⁻ (12.8%) > Na⁺ (5.01%) > pH (0.61%) > Mg²⁺ (0%). The parametric analysis revealed that models have incorporated the effect of all the input parameters in the modeling process. The external assessment criteria confirmed the generalized outcome and robustness of the proposed approaches. Conclusively, the outcomes of this study demonstrated that the formulation of AI based models are cost effective and helpful for river water quality assessment, management and policy making.

Using biomass waste as supplementary cementing material (SCM) in concrete has attracted researchers’ attention for efficient waste utilization and reducing cement demand. Sugarcane bagasse ash (SCBA) is one such example of biomass waste. It is an agricultural waste obtained when sugarcane bagasse from the sugar industry is used for power generation and disposed of in open-air dumping sites. Its waste disposal causes the generation of particulate matter, degrading air quality. In this study, the effect of processed SCBA as SCM in concrete has been investigated. The processing of the SCBA involved the removal of fibrous and carbon-containing particles by sieving followed by grinding. The SCBA was ground for 45 min until the surface area was comparable to that of cement and was then used for further characterization and incorporation into concrete. The 45 min grinding time resulted in 2.92 times higher pozzolanic reactivity of the SCBA. The SCBA was incorporated by replacing cement in different weight fractions (10%, 20%, 30%, 40%) in concrete. Test results showed that the concrete workability increased with SCBA incorporation, whereas the resulting concrete density was reduced. The results of the mechanical properties, including compressive sstrength and hardened density, were enhanced upon the cement replacement by SCBA. Concrete containing 30% SCBA can be used for structural applications as its 28 days compressive strength was 21 MPa, which complies with ACI 318-16 specifications. Concrete resistance against scaling and leaching due to adverse effects of sulfuric and hydrochloric acid considerably increased with SCBA addition and was due to microstructure densification by secondary hydrates formation as lower portlandite content was detected by thermogravimetric analysis. Hence, SCBA processing increases its reactivity, as reflected by the improved mechanical properties and greater durability of SCBA-incorporated concrete.

The prediction accuracies of machine learning (ML) models may not only be dependent on the input parameters and training dataset, but also on whether an ensemble or individual learning model is selected. The present study is based on the comparison of individual supervised ML models, such as gene expression programming (GEP) and artificial neural network (ANN), with that of an ensemble learning model, i.e., random forest (RF), for predicting river water salinity in terms of electrical conductivity (EC) and dissolved solids (TDS) in the Upper Indus River basin, Pakistan. The projected models were trained and tested by using a dataset of seven input parameters chosen on the basis of significant correlation. Optimization of the ensemble RF model was achieved by producing 20 sub-models in order to choose the accurate one. The goodness-of-fit of the models was assessed through well-known statistical indicators, such as the coefficient of determination (R²), mean absolute error (MAE), root mean squared error (RMSE), and Nash–Sutcliffe efficiency (NSE). The results demonstrated a strong association between inputs and modeling outputs, where R² value was found to be 0.96, 0.98, and 0.92 for the GEP, RF, and ANN models, respectively. The comparative performance of the proposed methods showed the relative superiority of the RF compared to GEP and ANN. Among the 20 RF sub-models, the most accurate model yielded the R² equal to 0.941 and 0.938, with 70 and 160 numbers of corresponding estimators. The lowest RMSE values of 1.37 and 3.1 were yielded by the ensemble RF model on training and testing data, respectively. The results of the sensitivity analysis demonstrated that HCO₃⁻ is the most effective variable followed by Cl⁻ and SO₄²⁻ for both the EC and TDS. The assessment of the models on external criteria ensured the generalized results of all the aforementioned techniques. Conclusively, the outcome of the present research indicated that the RF model with selected key parameters could be prioritized for water quality assessment and management.

The Upper Indus Basin (UIB) is a major source of supplying water to different areas because of snow and glaciers melt and is also enduring the regional impacts of global climate change. The expected changes in temperature, precipitation and snowmelt could be reasons for further escalation of the problem. Therefore, estimation of hydrological processes is critical for UIB. The objectives of this paper were to estimate the impacts of climate change on water resources and future projection for surface water under different climatic scenarios using soil and water assessment tool (SWAT). The methodology includes: (i) development of SWAT model using land cover, soil and meteorological data; (ii) calibration of the model using daily flow data from 1978 to 1993; (iii) model validation for the time 1994–2003; (iv) bias correction of regional climate model (RCM), and (v) utilization of bias-corrected RCM for future assessment under representative concentration pathways RCP4.5 and RCP8.5 for mid (2041–2070) and late century (2071–2100). The results of the study revealed a strong correlation between simulated and observed flow withR²and Nash–Sutcliff efficiency (NSE) equal to 0.85 each for daily flow. For validation,R²and NSE were found to be 0.84 and 0.80, respectively. Compared to baseline period (1976–2005), the result of RCM showed an increase in temperature ranging from 2.36°C to 3.50°C and 2.92°C to 5.23°C for RCP4.5 and RCP8.5 respectively, till the end of the twenty-first century. Likewise, the increase in annual average precipitation is 2.4% to 2.5% and 6.0% to 4.6% (mid to late century) under RCP4.5 and RCP8.5, respectively. The model simulation results for RCP4.5 showed increase in flow by 19.24% and 16.78% for mid and late century, respectively. For RCP8.5, the increase in flow is 20.13% and 15.86% during mid and late century, respectively. The model was more sensitive towards available moisture and snowmelt parameters. Thus, SWAT model could be used as effective tool for climate change valuation and for sustainable management of water resources in future.