Development of chemometrics-based neurocomputing paradigm for simulation of manganese extraction using solid-phase tea waste

Salihu Ismail, R. A. Abdulkadir, A. G. Usman*, S. I. Abba

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

5 Scopus citations

Abstract

Manganese (Mn) is a trace mineral that is present in tiny amounts in the body. It is found mostly in bones, the liver, kidneys, and pancreas. Manganese helps the body form connective tissue, bones, and blood clotting factors. It also plays a role in fat and carbohydrate metabolism, calcium absorption, and blood sugar regulation. Manganese is also necessary for normal brain and nerve function. Therefore, the current study explored the application of two different neurocomputing techniques, including adaptive neuro-fuzzy inference system (ANFIS) and Hammerstein wiener (HW) models, for the prediction of the efficiency of tea waste as a sorbent for manganese extraction using a solid-phase (SP) approach. The pH, eluent concentration (mol/L), extraction time (min), and mass of sorbent (g) were used as the corresponding predictors. The models were evaluated using six different performance indices, including mean absolute percentage error (MAPE), root mean square error (RMSE), mean absolute error (MAE), mean square error (MSE), correlation coefficient (R) and determination coefficient (R2). Graphical illustrations such as radar chart, time series, and scatter plots were applied to demonstrate the comparative performance of each of the models. The obtained data-driven results showed the promising ability of ANFIS over HW in modeling the extraction performance of manganese using solid-phase tea waste sorbent in both the calibration and verification phases. Overall, the results proved the satisfactory reliability of non-linear models in solid-phase extraction.

Original languageEnglish
Pages (from-to)5031-5040
Number of pages10
JournalModeling Earth Systems and Environment
Volume8
Issue number4
DOIs
StatePublished - Nov 2022

Bibliographical note

Publisher Copyright:
© 2022, The Author(s), under exclusive licence to Springer Nature Switzerland AG.

Keywords

  • Adaptive neuro-fuzzy inference system
  • Chemometrics-based models
  • Manganese
  • Solid-phase extraction
  • Tea waste sorbent

ASJC Scopus subject areas

  • General Environmental Science
  • General Agricultural and Biological Sciences
  • Computers in Earth Sciences
  • Statistics, Probability and Uncertainty

Fingerprint

Dive into the research topics of 'Development of chemometrics-based neurocomputing paradigm for simulation of manganese extraction using solid-phase tea waste'. Together they form a unique fingerprint.

Cite this