Predictive Analytics of Black Carbon in High-Concentration Region Using Machine Learning Models

PRATIMA GUPTA, Pau Ferrer-Cid, Jose M. Barcelo-Ordinasb, Jorge Garcia-Vidal, Mar Viana, Mira L. Pöhlker, Ajit Ahlawat, Indian Institute of Technology Delhi

     Abstract Number: 59
     Working Group: Instrumentation and Methods

Abstract
Black carbon (BC) is emitted into the atmosphere during combustion processes, often in conjunction with emissions such as NOx and O3, which are also by-products of combustion. In highly polluted regions, combustion processes are one of the main sources of aerosols and particulate matter (PM) concentrations, which affect the radiative budget. In this study we use machine learning approaches to estimate BC from NOx, O3, PM2.5, relative humidity (RH), and solar radiation (SR). We assess the effectiveness of various machine learning models, such as random forest (RF), support vector regression (SVR), and multilayer perceptron (MLP) artificial neural network, for predicting black carbon (BC) mass concentrations in areas with high BC levels such as Northern Indian cities (Delhi and Agra), across different seasons. This study evaluates the performance of models in Delhi using data from 2018-19, including NOx, O3, PM2.5, relative humidity (RH), and solar radiation as input variables and Agra. The results demonstrate comparable effectiveness among the models, with the multilayer perceptron (MLP) showing the most promising results. In Delhi, the MLP shows high correlations between measured and modelled concentrations during winter (R2: 0.85) and post-monsoon (R2: 0.83) seasons, and notable metrics in the pre-monsoon (R2: 0.72). The results from Agra are consistent with those from Delhi, highlighting the consistency of the neural network's performance. These results highlight the usefulness of machine learning, particularly MLP, as a valuable tool for predicting BC concentrations. This approach provides critical new opportunities for urban air quality management and mitigation strategies and may be especially valuable for megacities in medium- and low-income regions.