Machine learning trained poly (3,4-ethylenedioxythiophene) functionalized carbon matrix suspended Cu nanoparticles for precise monitoring of nitrite from pickled vegetables

Precise monitoring of nitrite from real samples has gained significant attention due to its detrimental impact on human health. Herein, we have fabricated poly(3,4-ethylenedioxythiophene) functionalized carbon matrix suspended Cu nanoparticles (PEDOT-C@Cu-NPs) through a facile green synthesis approach. Additionally, we have used machine learning (ML) to optimize experimental parameters such as pH, drying time, and concentrations to predict current of the designed electrochemical sensor. The ML optimized concentration of fabricated C@Cu-NPs was further functionalized by PEDOT (π-electron mediator). The designed PEDOT functionalized C@Cu-NPs (PEDOT-C@Cu-NPs) electrode has shown excellent electro-oxidation capability towards NO2− ions due to highly exposed Cu facets, defects rich graphitic C and high π-electron density. Additionally, the designed material has shown low detection limit (3.91 μM), high sensitivity (0.6372 μA/μM/cm2), and wide linear range (5–580 μM). Additionally, the designed electrode has shown higher electrochemical sensing efficacy against real time monitoring from pickled vegetables extract. •A simple and cost-effective green synthesis approach was used to fabricate C@Cu-NPs.•Fabricated PEDOT-C@Cu-NPs electrode offers fast shuttling of electrons/ions, thus results in precise monitoring of NO2−.•Machine learning was employed to optimize the experimental parameters to achieve high- sensitivity and selectivity.•Fabricated PEDOT-C@Cu-NPs sensor shows high sensitivity, selectivity, and reliable reproducibility in monitoring NO2 from pickled vegetables.