AI based prediction of daily rainfall from satellite observation for disaster management

Kuldeep Chaurasia; Unnam Tarun; Guddanti V. S. Sarala; Komal Soni

doi:10.1117/12.2580628

8 November 2020 AI based prediction of daily rainfall from satellite observation for disaster management

Kuldeep Chaurasia, Unnam Tarun, Guddanti V. S. Sarala, Komal Soni

Proceedings Volume 11525, SPIE Future Sensing Technologies; 115250W (2020) https://doi.org/10.1117/12.2580628
Event: SPIE Future Sensing Technologies, 2020, Online Only

Abstract

We are all well aware of the fact that heavy rainfall is one of the major sources of causing disasters. Be it flood or drought, landslide or erosion rainfall is the prime factor to be causing these calamities. Timely prediction of rainfall is important to be ready for facing upcoming disasters. In this research work, an attempt has been made to predict daily rainfall from satellite observation for disaster management using Artificial Intelligence (AI). A multi-stacked LSTM based model has been used for prediction of daily rainfall. The model uses 40 years of dataset provided by the National Aeronautics and Space Administration (NASA) / Goddard Space Flight Center through MERRA-2 portal. The dataset belongs to Yamuna Nagar district in Haryana, India during the period 1980 - 2020 for the training purpose. The outcome of the research proves that LSTM based neural networks are better alternative to forecast general weather conditions when compared with traditional methods. The outcome of the model can further be improved by including more parameters and better hyper parameter tuning.

Conference Presentation

Citation Download Citation

Kuldeep Chaurasia, Unnam Tarun, Guddanti V. S. Sarala, and Komal Soni "AI based prediction of daily rainfall from satellite observation for disaster management", Proc. SPIE 11525, SPIE Future Sensing Technologies, 115250W (8 November 2020); https://doi.org/10.1117/12.2580628

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available