Research

Earth, Atmosphere & Environment Sciences

Title :

Development of a machine learning method for classification and nowcasting of rainfall using Doppler Weather Radar.

Area of research :

Earth, Atmosphere & Environment Sciences

Focus area :

Atmospheric Science

Principal Investigator :

PI: Dr. Saurabh Das, Indian Institute of Technology Indore, Madhya Pradesh, Khandwa Road, Simrol Indore, Madhya Pradesh 453552 India

Timeline Start Year :

2022

Details

Executive Summary :

The problem of issuing a nowcasting warning is difficult task for meteorologists, mainly because of the extremely large set of data, which has to be analyzed in a short period of time. Therefore, ML based methods are useful for offering effective solutions for nowcasting by learning relevant patterns from the large amount of weather data and thus improving decision making for high impact weather. Most of the existing operational and semi-operational methods for nowcasting are using the extrapolation of radar data and algorithms mainly based on cell tracking. However, existence of varied rain type and topographic influence are major limiting factor in such prediction methods. Hence, the present proposal aims to introduce machine learning (ML) based methods ( particularly the Deep learning methods) for obtaining effective solutions for the nowcasting problem.

Co-PI:

Dr. Abhirup Datta, Indian Institute of Technology Indore, Madhya Pradesh, Khandwa Road, Simrol Indore, Madhya Pradesh 453552, India

Total Budget (INR):

71,79,930

Organizations involved