Interplanetary Shock Predictor

Visual of interplanetary shock
Correlation
Final fit of power law model

Inspiration

Forecasting interplanetary shocks driven by Coronal Mass Ejections (CMEs) is crucial for understanding space weather and its impact on spacecraft, satellites, and planetary environments. The goal is to model and predict shock propagation times.

What it does

The project links CME events with observed interplanetary shocks (IPS) and predicts the time difference between CME launches and subsequent shocks using a power law model. It provides visualizations and evaluation metrics to assess prediction accuracy.

How we built it

Historical CME and IPS data are processed to create lookup tables and clean datasets. A power law model of the form $$ \text{Time_diff} = a \cdot (\text{CME_speed})^b $$ is fitted using SciPy's curve_fit. Python libraries like pandas, NumPy, matplotlib, and seaborn handle data manipulation, modeling, and plotting.

Challenges we ran into

Sparse and inconsistent event linkages made matching CMEs to shocks difficult. Selecting the most accurate CME speed from multiple analyses and cleaning the data required careful handling to ensure reliable predictions.

Accomplishments that we're proud of

A predictive model was created that quantifies CME-to-shock time differences and visualizes both fits and residuals. Evaluation metrics such as RMSE and R² demonstrate robust model performance.

What we learned

Linking heterogeneous datasets requires careful preprocessing. Power law modeling effectively captures the inverse relationship between CME speed and shock propagation time. Residual analysis is key to validating model assumptions.

What's next for Interplanetary Shock Predictor

Future work includes integrating additional CME properties, improving model accuracy on rare events, and testing alternative predictive models to enhance generalization.