Browsing by Author "Mattar M.A."

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    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) Joshi B.; Singh V.K.; Vishwakarma D.K.; Ghorbani M.A.; Kim S.; Gupta S.; Chandola V.K.; Rajput J.; Chung I.-M.; Yadav K.K.; Mirzania E.; Al-Ansari N.; Mattar M.A.
    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.
  • Thumbnail Image
    Item
    Long-term application of agronomic management strategies effects on soil organic carbon, energy budgeting, and carbon footprint under rice�wheat cropping system
    (Nature Research, 2024) Naresh R.K.; Singh P.K.; Bhatt R.; Chandra M.S.; Kumar Y.; Mahajan N.C.; Gupta S.K.; Al-Ansari N.; Mattar M.A.
    In the plains of western North India, traditional rice and wheat cropping systems (RWCS) consume a significant amount of energy and carbon. In order to assess the long-term energy budgets, ecological footprint, and greenhouse gas (GHG) pollutants from RWCS with residual management techniques, field research was conducted which consisted of fourteen treatments that combined various tillage techniques, fertilization methods, and whether or not straw return was present in randomized block design. By altering the formation of aggregates and the distribution of carbon within them, tillage techniques can affect the dynamics of organic carbon in soil and soil microbial activity. The stability of large macro-aggregates (> 2 mm), small macro-aggregates (2.0�2.25 mm), and micro-aggregates in the topsoil were improved by 35.18%, 33.52%, and 25.10%, respectively, over conventional tillage (0�20 cm) using tillage strategies for conservation methods (no-till in conjunction with straw return and organic fertilizers). The subsoil (20�40 cm) displayed the same pattern. In contrast to conventional tilling with no straw returns, macro-aggregates of all sizes and micro-aggregates increased by 24.52%, 28.48%, and 18.12%, respectively, when conservation tillage with organic and chemical fertilizers was used. The straw return (aggregate-associated C) also resulted in a significant increase in aggregate-associated carbon. When zero tillage was paired with straw return, chemical, and organic fertilizers, the topsoil's overall aggregate-associated C across all aggregate proportions increased. Conversely, conventional tillage, in contrast to conservation tillage, included straw return as well as chemical and organic fertilizers and had high aggregate-associated C in the subsurface. This study finds that tillage techniques could change the dynamics of microbial biomass in soils and organic soil carbon by altering the aggregate and distribution of C therein. � 2024, The Author(s).
  • Thumbnail Image
    Item
    Publisher Correction: Long-term application of agronomic management strategies effects on soil organic carbon, energy budgeting, and carbon footprint under rice�wheat cropping system (Scientific Reports, (2024), 14, 1, (337), 10.1038/s41598-023-48785-z)
    (Nature Research, 2024) Naresh R.K.; Singh P.K.; Bhatt R.; Chandra M.S.; Kumar Y.; Mahajan N.C.; Gupta S.K.; Al-Ansari N.; Mattar M.A.
    In the original version of this Article, Mohamed Mattar was omitted as a corresponding author. Correspondence and requests for materials should also be addressed to mmattar@ksu.edu.sa. � The Author(s) 2024.