Browsing by Author "Shivam Gupta"

Now showing 1 - 5 of 5

A comparative survey between cascade correlation neural network (CCNN) and feedforward neural network (FFNN) machine learning models for forecasting suspended sediment concentration
(Nature Research, 2024) Bhupendra Joshi; Vijay Kumar Singh; Dinesh Kumar Vishwakarma; Mohammad Ali Ghorbani; Sungwon Kim; Shivam Gupta; V.K. Chandola; Jitendra Rajput; Il-Moon Chung; Krishna Kumar Yadav; Ehsan Mirzania; Nadhir Al-Ansari; Mohamed A. Mattar
Suspended sediment concentration prediction is critical for the design of reservoirs, dams, rivers ecosystems, various operations of aquatic resource structure, environmental safety, and water management. In this study, two different machine models, namely the cascade correlation neural network (CCNN) and feedforward neural network (FFNN) were applied to predict daily-suspended sediment concentration (SSC) at Simga and Jondhara stations in Sheonath basin, India. Daily-suspended sediment concentration and discharge data from 2010 to 2015 were collected and used to develop the model to predict suspended sediment concentration. The developed models were evaluated using statistical indices like Nash and Sutcliffe efficiency coefficient (NES), root mean square error (RMSE), Willmott’s index of agreement (WI), and Legates–McCabe’s index (LM), supplemented by a scatter plot, density plots, histograms and Taylor diagram for graphical representation. The developed model was evaluated and compared with CCNN and FFNN. Nine input combinations were explored using different lag-times for discharge (Qt-n) and suspended sediment concentration (St-n) as input variables, with the current suspended sediment concentration as the desired output, to develop CCNN and FFNN models. The CCNN4 model with 4 lagged inputs (St-1, St-2, St-3, St-4) outperformed the other developed models with the lowest RMSE = 95.02 mg/l and the highest NES = 0.0.662, WI = 0.890 and LM = 0.668 for the Jondhara Station while the same CCNN4 model secure as the best with the lowest RMSE = 53.71 mg/l and the highest NES = 0.785, WI = 0.936 and LM = 0.788 for the Simga Station. The result shows the CCNN model was better than the FFNN model for predicting daily-suspended sediment at both stations in the Sheonath basin, India. Overall, CCNN showed better forecasting potential for suspended sediment concentration compared to FFNN at both stations, demonstrating their applicability for hydrological forecasting with complex relationships. © The Author(s) 2024.
Crop Plants Develop Extracellular Signaling Products Against Salt Stress
(wiley, 2021) Santwana Tiwari; Nidhi Verma; Shikha Singh; Shivam Gupta; Madhulika Singh; Pratibha Singh; Jitendra Pandey; Sheo Mohan Prasad
Plant signaling is a usual phenomenon that facilitates the transduction of external and internal signals into physiological reactions such as modification of activity of various enzymes, cytoskeleton structure, and gene expression. This chapter aims to gather all the information about extracellular products secreted by crop plants as well as cyanobacteria with their working mechanisms under salt stress conditions and their role in economic values in agriculture and medicine. The biosynthesis of bioactive extracellular compounds in plants aimed to enhance crop tolerance to abiotic and biotic stresses and overcome stressful conditions. The level of antioxidants, enzymes, and proteins has fluctuated under salt stress. Salt stress often generates both ionic and osmotic stress in plants, resulting in a greater disturbance in signaling and accumulation or decrease of specific metabolites in plants. In agriculture, cyanobacterial and plant's secondary metabolites are key tools for enhancing crop production. © 2022 John Wiley & Sons Ltd. All rights reserved.
Diurnal oscillation in dissolved oxygen at sediment-water interface fuels denitrification-driven N removal in Ganga River
(Elsevier B.V., 2023) Deepa Jaiswal; Neha Naaz; Shivam Gupta; Ketan Madhav; Jitendra Pandey
Human activities have substantially enhanced riverine nitrogen loads in many parts of the world. The processes such as denitrification remove a large fraction of N added to the system, and thus, are very helpful in mitigating the effects of increasing human N loads in aquatic ecosystems. No systematic studies, so far, are available on current magnitude and factors regulating efficiency of N removal by the Ganga River. Using three sub-sets of studies- main river course, two tributary confluence trajectories and two point source trajectories along 520 km middle stretch, we generated high spatio-temporal resolution data to show that spatially targeted river reaches with higher nitrate concentrations are acting as ‘hotspots’ of N removal in the Ganga River. The static core method was used to measure the rate of denitrification. Intact sediment core samples were incubated in the laboratory condition and efficiency adjusted. Pollution-impacted point sources showed higher rates of denitrification (0.40 mg N/m2/hr to 2.48 mg N/m2/hr) relative to main stream sites (0.32 mg N/m2/hr to 2.09 mg N/m2/hr). Our results indicate that increased level of carbon (C) and phosphorus (P), which often accompany nitrogen (N) inputs from human activities, have enhanced N removal by the river. Periodic oxic-hypoxic cycle at sediment-water interface (DOsw), which might link nitrification with denitrification, has stimulated N removal at study sites in an opportunistic manner. These results suggest that data on this natural process of N removal (denitrification), and factors thereof, especially those accounting for interactive effects at spatially targeted locations, should be taken into account to formulate policies for the management of nutrient and organic pollution. © 2023 Elsevier B.V.
Impact of hypoxia coupled elevated salinity on sediment metal release along Ganga–Hooghly River Estuary gradient
(Taylor and Francis Ltd., 2025) Shivam Gupta; Jitendra P. Pandey
Intense anthropogenic activities have increased the frequency of benthic hypoxic patches in the Ganga River. We investigated the synergistic effects of elevated salinity and benthic hypoxia on sediment-metal release along a 150-km gradient of the Ganga–Hooghly River estuary. Also, we tested toxicological implications of metal pollutants in terms of changes in microbial extracellular enzyme activities (β-D-glucosidase, fluorescein diacetate hydrolase (FDAase) and alkaline phosphatase) and eco-toxicological indices. We found synergistic effects of salinity and hypoxia on sediment-metal release and sediment-P release. We found 3.5–7.73% (p < 0.001) increase in the concentrations of metal pollutants in the overlaying water at low levels of dissolved oxygen (DO ≤ 2 mgL−1) under controlled experiment. At high salinity and low DO, the sediment release of study metals enhanced by 5.8–20.25%. Total heavy metal concentration (⅀THM) above 350 µg g−1 decreased the activities of extracellular enzymes (18.6–47.8%; p < 0.001). Contamination factor, geo-accumulation index and ecological risk index showed concordance except at sites where salinity counterbalanced toxicological effects. Our study suggests that the synergism between hypoxia and salinity, which are expected to increase in future, will continue to increase the sediment-metal release with toxicological implications along the Ganga–Hooghly River estuarine gradient. © 2025 Informa UK Limited, trading as Taylor & Francis Group.
Multi-ahead electrical conductivity forecasting of surface water based on machine learning algorithms
(Springer Science and Business Media Deutschland GmbH, 2023) Deepak Kumar; Vijay Kumar Singh; Salwan Ali Abed; Vinod Kumar Tripathi; Shivam Gupta; Nadhir Al-Ansari; Dinesh Kumar Vishwakarma; Ahmed Z. Dewidar; Ahmed A. Al‑Othman; Mohamed A. Mattar
The present research work focused on predicting the electrical conductivity (EC) of surface water in the Upper Ganga basin using four machine learning algorithms: multilayer perceptron (MLP), co-adaptive neuro-fuzzy inference system (CANFIS), random forest (RF), and decision tree (DT). The study also utilized the gamma test for selecting appropriate input and output combinations. The results of the gamma test revealed that total hardness (TH), magnesium (Mg), and chloride (Cl) parameters were suitable input variables for EC prediction. The performance of the models was evaluated using statistical indices such as Percent Bias (PBIAS), correlation coefficient (R), Willmott’s index of agreement (WI), Index of Agreement (PI), root mean square error (RMSE) and Legate-McCabe Index (LMI). Comparing the results of the EC models using these statistical indices, it was observed that the RF model outperformed the other algorithms. During the training period, the RF algorithm has a small positive bias (PBIAS = 0.11) and achieves a high correlation with the observed values (R = 0.956). Additionally, it shows a low RMSE value (360.42), a relatively good coefficient of efficiency (CE = 0.932), PI (0.083), WI (0.908) and LMI (0.083). However, during the testing period, the algorithm’s performance shows a small negative bias (PBIAS = − 0.46) and a good correlation (R = 0.929). The RMSE value decreases significantly (26.57), indicating better accuracy, the coefficient of efficiency remains high (CE = 0.915), PI (0.033), WI (0.965) and LMI (− 0.028). Similarly, the performance of the RF algorithm during the training and testing periods in Prayagraj. During the training period, the RF algorithm shows a PBIAS of 0.50, indicating a small positive bias. It achieves an RMSE of 368.3, R of 0.909, CE of 0.872, PI of 0.015, WI of 0.921, and LMI of 0.083. During the testing period, the RF algorithm demonstrates a slight negative bias with a PBIAS of − 0.06. The RMSE reduces significantly to 24.1, indicating improved accuracy. The algorithm maintains a high correlation (R = 0.903) and a good coefficient of efficiency (CE = 0.878). The index of agreement (PI) increases to 0.035, suggesting a better fit. The WI is 0.960, indicating high accuracy compared to the mean value, while the LMI decreases slightly to − 0.038. Based on the comparative results of the machine learning algorithms, it was concluded that RF performed better than DT, CANFIS, and MLP. The study recommended using the current month’s total hardness (TH), magnesium (Mg), and chloride (Cl) parameters as input variables for multi-ahead forecasting of electrical conductivity (ECt+1, ECt+2, and ECt+3) in future studies in the Upper Ganga basin. The findings also indicated that RF and DT models had superior performance compared to MLP and CANFIS models. These models can be applied for multi-ahead forecasting of monthly electrical conductivity at both Varanasi and Prayagraj stations in the Upper Ganga basin. © 2023, The Author(s).