Optimization and prediction of Rhodamine B uptake onto alkali-functionalized sugarcane bagasse biochar: Krill Herd algorithm-based ANN modelling approach

The present research work accentuates the utilization of sodium hydroxide-functionalized sugarcane bagasse biochar (NaOH-SBB) for the decolorization of Rhodamine B (RhB) dye from effluents, for fostering the UN Sustainable Development Goals (SDGs) of pure water and robust health. The physicochemical...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Environmental science and pollution research international
Hlavní autoři: Mayilswamy, Neelaambhigai, Kandasubramanian, Balasubramanian, Warjurkar, Tushar, Chame, Satkirti, Shirin, Saleega
Médium: Journal Article
Jazyk:angličtina
Vydáno: Germany 02.07.2025
Témata:
Krill Herd algorithm optimization
Rhodamine B
ANN modelling
Adsorption mechanism
Adsorption isotherm
Alkali functionalized biochar
ISSN:1614-7499, 1614-7499
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The present research work accentuates the utilization of sodium hydroxide-functionalized sugarcane bagasse biochar (NaOH-SBB) for the decolorization of Rhodamine B (RhB) dye from effluents, for fostering the UN Sustainable Development Goals (SDGs) of pure water and robust health. The physicochemical characteristics of the as-prepared biochar were examined using advanced characterization techniques, and a maximum mono-layered Langmuir adsorption capacity (q ) of 4.8309 mg/g was attained at adsorbate concentrations of 15 ppm. The dye decolorization phenomenon using NaOH-SBB adsorbent was modelled using the Krill Herd algorithm-optimized via the Levenberg Marquardt Backpropagation (LM) algorithm through Artificial Neural Network (ANN) modelling, for optimizing and predicting the dye adsorption capacity values. The configured Artificial Neural Network (ANN) model demonstrated a strong predictive performance, reflected by a high coefficient of correlation (R = 0.9531), and determination coefficient (R  = 0.9726), along with low error metrics (mean square error: 0.5669, mean absolute error: 0.3884, root mean square error: 0.7542). These results indicated a strong correlation between the empirical and ANN-prognosticated results, validating the effectiveness, and reliability of the developed model.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1614-7499
1614-7499
DOI:10.1007/s11356-025-36680-1