COMPARATIVE AND MACHINE LEARNING-DRIVEN ANALYSIS OF REDUCED GRAPHENE OXIDE POLYMER GAS SENSORS: MATERIALS AND SENSITIVITY TRENDS

Gas sensors combining reduced grapheme oxide ( rGO )polymer have sparked a growing interest since past few years.Rgo polymers synergistically merge the high surface area and conductivity with the chemical affinity and tenability of polymers,often achieving superior room temperature gas sensing performance compared to either of the components alone.This review article collate recent advances in rGO polymer sensors, emphasizing material choices, fabrication techniques, gas detection performance (sensitivity, selectivity, and limits of detection), and specialized applications for nitroaromatic vapor detection. Conducting polymers like polyaniline (PANI), polypyrrole (PPy), polythiophene (PTh)and PEDOT:PSS have been widely incorporated with rGO for better operation and flexibility for sensing gases like NH, NO, HS, and volatile organic compounds. For these reasons, rGOpolymer sensors represent a rapidly progressing field, with significant steps in tracing toxic industrial gases and explosive compounds. Additionally, this work incorporates a data-driven section where statistical plots and machine learning were used to evaluate performance metrics from published studies. Results show that Limit of Detection (LOD) and gas type are the most influential features affecting sensitivity. Comparative radar charts and heatmaps support a holistic view of material-gas performance, strengthening the future design strategy of rGO polymer sensors. This interdisciplinary approach supports the transition from experimental sensing platforms to intelligent, application-specific devices for environmental and security applications.