Advection-Free Convolutional Neural Network for Convective Rainfall Nowcasting

Nowcasts (i.e., short-term forecasts from 5 min to 6 h) of heavy rainfall are important for applications such as flash flood predictions. However, current precipitation nowcasting methods based on the extrapolation of radar echoes have a limited ability to predict the growth and decay of rainfall. W...

Full description

Saved in:
Bibliographic Details
Main Authors: Jenna Ritvanen, Bent Harnist, Miguel Aldana, Terhi Makinen, Seppo Pulkkinen
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10021317/
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Nowcasts (i.e., short-term forecasts from 5 min to 6 h) of heavy rainfall are important for applications such as flash flood predictions. However, current precipitation nowcasting methods based on the extrapolation of radar echoes have a limited ability to predict the growth and decay of rainfall. While deep learning applications have recently shown improvement compared to extrapolation-based methods, they still struggle to correctly nowcast small-scale high-intensity rainfall. To address this issue, we present a novel model called the Lagrangian convolutional neural network (L-CNN) that separates the growth and decay of rainfall from motion using the advection equation. In the model, differences between consecutive rain rate fields in Lagrangian coordinates are fed into a U-Net-based CNN, known as RainNet, that was trained with the root-mean-squared-error loss function. This results in a better representation of rainfall temporal evolution compared to the RainNet and the extrapolation-based LINDA model that were used as reference models. On Finnish weather radar data, the L-CNN underestimates rainfall less than RainNet, demonstrated by greater POD (29&#x0025; at 30 min at 1 mm&#x00B7;h<inline-formula><tex-math notation="LaTeX">$^{-1}$</tex-math></inline-formula> threshold) and smaller bias (98&#x0025; at 15 min). The increased ETS values over LINDA for leadtimes under 15 min, with maximum increases of 7&#x0025; (5 mm&#x00B7;h<inline-formula><tex-math notation="LaTeX">$^{-1}$</tex-math></inline-formula> threshold) and 10&#x0025; (10 mm&#x00B7;h<inline-formula><tex-math notation="LaTeX">$^{-1}$</tex-math></inline-formula>), show that the L-CNN represents the growth and decay of heavy rainfall more accurately than LINDA. This implies that nowcasting of heavy rainfall is improved when growth and decay are predicted using a deep learning model.
ISSN:1939-1404
2151-1535