Skip to content
DSML.KZ
Publications

Article · Journal of Earth Energy Science Engineering and Technology · December 14, 2025

Modeling and Prediction of Kappaphycus alvarezii Viscosity Using Artificial Neural Network and Adaptive Neuro-Fuzzy Inference System

Muhammad Taufiq Fathaddin, Onnie Ridaliani, Pri Agung Rakhmanto, Dwi Atty Mardiana, Wydhea Ayu Septianingrum, Sonny Irawan

Sonny Irawan
Open via DOIPDF

Abstract

This study examines the viscosity behavior of Kappaphycus alvarezii polymer solutions enhanced with TiO2 nanoparticles under varying concentrations, salinity, and temperature. Predictive models were developed using Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) approaches. The experimental work involved preparing Kappaphycus alvarezii solutions with polymer concentrations ranging from 2,000 to 6,000 ppm and TiO2 nanoparticle concentrations from 2,000 to 4,000 ppm at salinities of 6,000–30,000 ppm and temperatures between 30 °C and 80 °C. Results showed that increasing Kappaphycus alvarezii concentration enhanced viscosity by 1.04–21.12%, while TiO2 nanoparticles improved viscosity stability, especially under high-salinity conditions. In contrast, higher salinity and temperature reduced viscosity due to ionic screening and increased molecular motion, although a slight rise was observed at 30,000 ppm salinity. The optimized ANN model (18 neurons, one hidden layer) achieved a superior correlation coefficient (r = 0.9980) compared to ANFIS (r = 0.8769), confirming higher predictive accuracy. These findings demonstrate the potential of Kappaphycus alvarezii–TiO2 nanofluids as sustainable viscosity modifiers for enhanced oil recovery (EOR) and verify the reliability of ANN and ANFIS models in predicting viscosity under complex multivariable interactions.

Enhanced Oil Recovery TechniquesRheology and Fluid Dynamics StudiesNanofluid Flow and Heat TransferKappaphycus alvareziiseaweed polysaccharidesviscosity prediction

More by Sonny Irawan