NORMA eResearch @NCI Library

A Novel Approach for Predicting the Tropical Storm Trajectories using Gridbased Recurrent Neural Networks

Jagadale, Rohit (2020) A Novel Approach for Predicting the Tropical Storm Trajectories using Gridbased Recurrent Neural Networks. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (2MB) | Preview


Tropical storms have wreaked havoc in the past on humanity and pose a great threat to disrupt the civilizations in future considering rapid global warming. Different statistical forecasting algorithms have slowly evolved over the past decades to mitigate this problem, but precise prediction still continues to be a difficult task. The present study proposes the novel approach for prediction of storm trajectory by implementing Grid-based recurrent neural networks model. LSTM and BiLSTM models are implemented and compared in this research as they perform better for sequence data inputs. The models are applied on HURDAT2 dataset by National Hurricane Center (NHC). Grid points are generated using latitude and longitude features and integrated with the neural networks. The research improves the previously applied LSTM model and also implements BiLSTM model which outperforms LSTM model with accuracy of 74%. With this model, the storm trajectory can be predicted well in advance which can save human lives and property damage. Storm prediction centers across the coastal regions will benefit from this analysis to provide reliable results for storm tracking.
Keywords — Tropical Storm Trajectory, Climatology, Recurrent Neural Networks, Long Short-Term Memory, Deep learning, BiLSTM

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 20 Jan 2021 15:24
Last Modified: 20 Jan 2021 15:24

Actions (login required)

View Item View Item