Impact of Nitro Substituents on Dopamine Sensing and Nanostructure Morphology: A Machine Learning Approach for PANI:2- and 3-Nitro-1H-Pyrrole Nanocomposite Sensors

In this study, we explore the effects of nitro substituents on the morphology and dopamine (DOP) sensing performance of polyaniline (PANI) nanocomposites (NCs). The novelty of the study is the unique integration of 2-nitro-1H-pyrrole (D9A) and 3-nitro-1H-pyrrole (D9B) into PANI to develop advanced non-enzymatic voltammetric sensors, combined with machine learning for DOP sensitivity and morphology analysis. Structural and morphological insights were obtained through comprehensive characterization techniques including ¹H NMR, 13 C NMR, Fourier transform infrared spectroscopy, scanning electron microscopy, and artificial intelligence-enhanced SEM analysis. The PANI: D9B NCs sensor demonstrated superior DOP detection in the range of 0.625–5 μM, with exceptional sensitivity (329.72 μAμM −1 cm −2 ) and an ultra-low limit of detection of 0.078 μM. Its rapid sensing capability within 1 min indicates potential for use in biomedical diagnostics. In contrast, the PANI NCs sensor exhibited lower sensitivity, which was linked to higher Zreel values and space charge effects. To further enhance DOP prediction accuracy, we employed machine learning (ML) models—ANN, SVM, XGBoost, and Linear Regression—to analyze sensor outputs, with a focus on feature extraction and multivariate data analysis. Our combined approach provides a robust framework for optimizing nitro-substituted PANI NCs for high-performance sensing applications.