Artificial intelligence tools for AgNP-SSB-SN and AgNP-CSS-SN biosynthesis from Synechococcus PCC 11901 and Chlorella sorokiniana MSP1 for hazardous dyes remediation

Abstract In response to concerns of environmental pollution caused by hazardous dyes, remediating these dyes is a challenge. Herein, we developed a genetic algorithm-artificial neural network (GA-ANN) based optimization process for phyco-synthesis of silver nanoparticles (AgNPs) from fast growing Synechococcus sp. PCC 11901 and Chlorella sorokiniana MSP1 bioextract (named SSB-SN and CSS-SN). The developed GA-ANN model predicted the most suitable process variables with excellent correlation coefficients of 0.97 and 0.98 for SSB-SN and CSS-SN, respectively. The existence of the potential functional groups and compositional aspects of AgNPs were studied using fourier transform infrared spectroscopy and field-emission scanning electron microscopy-energy-dispersive x-ray spectroscopy. Further, the Transmission electron microscopy analysis revealed the average size of 10.66 and 26.03 nm of SSB-SN and CSS-SN, respectively. Thermogravimetry analysis and X-ray diffraction analysis revealed a higher thermal stability and crystallinity of the phyco-synthesised AgNPs. The SSB-SN and CSS-SN nanoparticles showed 99.79 ± 1.18% and 73.13 ± 0.82% of Orange-II dye degradation. Whereas, 98.17 ± 0.07% and 97.76 ± 0.08% for Sudan black dye. These results followed pseudo-second-order kinetics. Finally, the present findings reveal that efficient phyco-synthesis process for AgNPs, offering a promising solution for hazardous dyes remediation.