Skip to content

Hybrid model combining 3D-CNN and LSTM networks to predict snow over Lake Michigan

Notifications You must be signed in to change notification settings

krishna-aditi/Lake-Effect-Snow-Prediction

Repository files navigation

SnowCast: Lake-Effect Snow Prediction with Hybrid Multimodal CNN-LSTM Network May 2023

  • Developed a hybrid model combining 3D-CNN and LSTM networks to predict snow with 97.7% accuracy
  • Designed a multimodal architecture processing both - radar images and numerical meteorological data for snow prediction
  • Created a novel data preparation function to transform the numerical data into sliding window of observations to predict snow 3 days in advance based on 5 days of historical data
  • Boosted the overall accuracy of Lake-effect snow prediction by 43%, surpassing the baseline decision tree model

Reference

About

Hybrid model combining 3D-CNN and LSTM networks to predict snow over Lake Michigan

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published