Low-cost sensors have revolutionized air quality monitoring, however, precision is questioned compared to reference instruments. Hence, the performance of two widely used PM_2.5 Sensors, Purple Air (PA) and ATMOS, were evaluated over a 10-month period in the North Western-Indo Gangetic Plains (NW-IGP). In-field collocation with Beta Attenuation Monitor found low R² values; 0.40 for ATMOS and 0.43 for PA. To calibrate and improve the accuracy of sensors, five Machine Learning (ML) models and an empirical relative humidity correction methodology were used separately for both sensors. Out of these, the Decision Tree outperformed others, and R² values improved to 0.996 for ATMOS and 0.999 for PA. Root mean square error reduced from 34.6 µg/m³ to 0.731 µg/m³ for ATMOS and from 77.7 µg/m³ to 0.61 µg/m³ for PA, while using DT as a calibrating model. The study reveals the best-performing ML model for correcting PM_2.5 sensor data, enhancing the accuracy of air quality monitoring systems.

低成本传感器彻底改变了空气质量监测，然而，与参考仪器相比，其精度受到质疑。因此，在西北印度恒河平原 （NW-IGP） 对两种广泛使用的 PM_2.5 传感器 Purple Air （PA） 和 ATMOS 的性能进行了为期 10 个月的评估。与 Beta 衰减监视器的现场搭配发现 R² 值较低;ATMOS 为 0.40，PA 为 0.43。为了校准和提高传感器的精度，两个传感器分别使用了五个机器学习 （ML） 模型和经验相对湿度校正方法。其中，决策树的性能优于其他决策树，ATMOS 的 R² 值提高到 0.996 和 PA 的 0.999。当使用 DT 作为校准模型时，ATMOS 的均方根误差从 34.6 μg/m³ 降低到 0.731 μg/m^3，PA 从 77.7 μg/m³ 降低到 0.61 μg/m³。该研究揭示了用于校正 PM_2.5 传感器数据的性能最佳的 ML 模型，从而提高了空气质量监测系统的准确性。