Corpus ID: 226306867

Hurricane Forecasting: A Novel Multimodal Machine Learning Framework

  title={Hurricane Forecasting: A Novel Multimodal Machine Learning Framework},
  author={L. Boussioux and Cynthia Zeng and Th'eo Gu'enais and D. Bertsimas},
  • L. Boussioux, Cynthia Zeng, +1 author D. Bertsimas
  • Published 2020
  • Computer Science, Physics
  • ArXiv
  • This paper describes a machine learning (ML) framework for tropical cyclone intensity and track forecasting, combining multiple distinct ML techniques and utilizing diverse data sources. Our framework, which we refer to as Hurricast (HURR), is built upon the combination of distinct data processing techniques using gradient-boosted trees and novel encoder-decoder architectures, including CNN, GRU and Transformers components. We propose a deep-feature extractor methodology to mix spatial-temporal… CONTINUE READING

    Figures and Tables from this paper


    Tropical Cyclone Track Forecasting Using Fused Deep Learning From Aligned Reanalysis Data
    • 6
    • Highly Influential
    • PDF
    A Novel Data-Driven Tropical Cyclone Track Prediction Model Based on CNN and GRU With Multi-Dimensional Feature Selection
    • 3
    • PDF
    Machine Learning in Tropical Cyclone Forecast Modeling: A Review
    • 2
    OMuLeT: Online Multi-Lead Time Location Prediction for Hurricane Trajectory Forecasting
    • 2
    Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
    • 2,446
    • PDF
    Deep-Hurricane-Tracker: Tracking and Forecasting Extreme Climate Events
    • 19
    • PDF
    MetNet: A Neural Weather Model for Precipitation Forecasting
    • 15
    • PDF
    A Sparse Recurrent Neural Network for Trajectory Prediction of Atlantic Hurricanes
    • 23
    Forecasts of Hurricanes Using Large-Ensemble Outputs
    • 2
    • PDF