CNN-Based Model for 3D CME Parameter Prediction: A Proof of Concept

Accurate 3D reconstruction of coronal mass ejections (CMEs) is essential for understanding their propagation and improving space weather forecasts. In this study, we present a proof-of-concept deep learning framework that predicts seven parameters from synthetic multi-view coronagraph images. We generate 9250 synthetic CME events using a 3D wireframe model, each defined by randomly sampled values for CME's longitude, latitude, tilt-angle, and 3D propagation speed. The speed is used to compute heights at three timepoints aligned with SOHO/LASCO C3 and STEREO-A/COR2 and STEREO-B/COR2 cadences. These values are used to render time-resolved synthetic images, serving as inputs to a convolutional neural network (CNN). The CNN is trained using five-fold cross-validation to predict the sine and cosine of the longitude, latitude, tilt-angle, and apex heights at the three specified times. CNN achieves mean absolute errors (MAE) of 4.88°, 2.50°, and 13.35° for longitude, latitude, and tilt, and (Formula presented.) for heights. The predicted heights are used to derive CME speed via height-time fitting. Performance metrics include Pearson's (Formula presented.) for most parameters (tilt: (Formula presented.)), and (Formula presented.) values of 0.99 for longitude and latitude, with heights (Formula presented.), and 0.61 for tilt. The average test MAE across all outputs is 0.134 (Formula presented.) 0.004. When applied to a real CME event, the CNN's predictions fall within the typical uncertainties reported for standard geometric fitting approaches. While challenges remain in handling real data, our results indicate that the trained model can generalize beyond synthetic data, highlighting its potential for operational space weather forecasting.