Abstract

Hailstorms have caused damages in billions of dollars to industrial, electronic, and mechanical properties such as automobiles, buildings, roads, and aircrafts, as well as life threats to crop and cattle populations, due to their hazardous nature. Hence, the relevance of predicting hailstorms in the future has significant scientific, economic, and societal benefits. However, climate models do not have adequate resolutions to explicitly resolve these subscale phenomena. One solution is to estimate the probability of these storms by using large-scale atmospheric thermodynamic environment variables from climate model outputs, but the existing methods only carried out experiments on small datasets limited to a region, country, or location and a large number of input features. Using one year of Tropical Rainfall Measuring Mission (TRMM) observations and European Center for Medium-Range Weather Forecasts (ECMWF) Re-Analysis Interim (ERA-Interim) reanalysis on a global scale, this paper develops two deep-learning-based models (an autoencoder and convolutional neural network (CNN)) as well as a machine learning approach (random forest) for hailstorm prediction by using only four attributes—convective potential energy, convective inhibition, 1–3 km wind shear, and warm cloud depth. In the experiments, the random forest approach produces the best hailstorm prediction performance compared to the other two methods.

Highlights

  • In the context of climatic conditions, the term precipitation refers to a natural phenomenon where objects such as rain, hail, or snow precipitate from clouds

  • This paper developed two deep learning models and a machine learning model that can be applied to large-scale thermodynamic environment variables in the diagnosis of hailstorms globally

  • The AE and convolutional neural network (CNN) models can predict a good number of true negatives, but both models made predictions with low precision and, with high error rates

Read more

Summary

Introduction

In the context of climatic conditions, the term precipitation refers to a natural phenomenon where objects such as rain, hail, or snow precipitate from clouds. Water droplets collectively freeze to produce larger masses of ice called hailstones (or hail) in high-altitude regions with temperatures of less than 0 ◦C. The hail size grows when more super-cooled water drops merge and freeze on the hail core in strong updrafts in these clouds [1]. From the time a hailstone is formed in a storm, its size grows or shrinks based on various physical processes that it encounters during its route towards the Earth from the storm [2]. The diameter of a hailstone can range from 0.2 to 6 inches. Hailstones falling on the Earth move with different velocities based on their size. A hailstone with a diameter of 1 cm drops down to Earth at 20 mph, whereas an 8 cm hail plunges at 110 mph towards the Earth

Objectives
Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call