The effect of uncertainties in reproducing the ambient solar wind at Earth on forecasting CME arrival times

Coronal Mass Ejections (CMEs) are the major drivers of Space Weather (SWx), so predicting their arrival at Earth is a major aspect of SWx forecasting. Despite increasingly complex models proposed over the past decades, the mean absolute error (MAE) for predictions of CME arrival still surpasses 10 hours. In this study, we use machine learning (ML) techniques trained on the discrepancies between observed and modeled solar wind (SW) at the L1 point, upstream of CMEs, to quantify and ''correct'' the errors in CME Time of Arrival (TOA) associated with these discrepancies. We use CME data from the Database Of Notifications, Knowledge, Information (DONKI) developed by the NASA Community Coordinated Modeling Center (CCMC) for our investigation. The WSA-ENLIL-Cone (WEC) model inputs and outputs are available on DONKI for each CME, along with the associated forecast errors. The dataset consists of 122 CME events observed between March 2012 and March 2023. SW properties at L1 and publicly available simulation results based on the WEC model are obtained. Three machine learning (ML) models are employed: 1) k-nearest neighbors (KNN), 2) support vector machine (SVM), and 3) linear regression (LR). Univariate and multivariate ML schemes were developed to examine how individual features and their combinations contribute to reducing the MAE in CME TOA forecasts. The best univariate and multivariate models improved the forecast by 36.6 and 45 minutes, respectively.