Preprints
https://doi.org/10.5194/egusphere-2023-763
https://doi.org/10.5194/egusphere-2023-763
05 Jun 2023
 | 05 Jun 2023

Identifying Atmospheric Rivers and their Poleward Latent Heat Transport with Generalizable Neural Networks: ARCNNv1

Ankur Mahesh, Travis O'Brien, Burlen Loring, Abdelrahman Elbashandy, William Boos, and William Collins

Abstract. Atmospheric rivers (ARs) are extreme weather events that can alleviate drought or cause billions of dollars in flood damage. By transporting significant amounts of latent energy towards the poles, they are crucial to maintaining the climate system’s energy balance. Since there is no first-principles definition of an AR grounded in geophysical fluid mechanics, AR identification is currently performed by a multitude of expert-defined, threshold-based algorithms. The variety of AR detection algorithms has introduced uncertainty into the study of ARs, and the algorithms' thresholds may not generalize to new climate datasets and resolutions. We train convolutional neural networks (CNNs) to detect ARs while representing this uncertainty; we name these models ARCNNs. To detect ARs without requiring new labeled data and labor-intensive AR detection campaigns, we present a semi-supervised learning framework based on image style transfer. This framework generalizes ARCNNs across climate datasets and input fields. Using idealized and realistic numerical models, together with observations, we assess the performance of the ARCNNs. We test the ARCNNs in an idealized simulation of a shallow water fluid, in which nearly all the tracer transport can be attributed to AR-like filamentary structures. In reanalysis and a high-resolution climate model, we use ARCNNs to calculate the contribution of ARs to meridional latent heat transport, and we demonstrate that this quantity varies considerably due to AR detection uncertainty.

Ankur Mahesh, Travis O'Brien, Burlen Loring, Abdelrahman Elbashandy, William Boos, and William Collins

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Ankur Mahesh, Travis O'Brien, Burlen Loring, Abdelrahman Elbashandy, William Boos, and William Collins
Ankur Mahesh, Travis O'Brien, Burlen Loring, Abdelrahman Elbashandy, William Boos, and William Collins

Viewed

Total article views: 499 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
271 204 24 499 20 16
  • HTML: 271
  • PDF: 204
  • XML: 24
  • Total: 499
  • BibTeX: 20
  • EndNote: 16
Views and downloads (calculated since 05 Jun 2023)
Cumulative views and downloads (calculated since 05 Jun 2023)

Viewed (geographical distribution)

Total article views: 505 (including HTML, PDF, and XML) Thereof 505 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 28 Mar 2024
Download
Short summary
Atmospheric rivers (ARs) are extreme weather events that can alleviate drought or cause billions of dollars in flood damage. We train convolutional neural networks (CNNs) to detect ARs with an estimate of uncertainty. We present a framework to generalize these CNNs to a variety of datasets of past, present, and future climate. Using a simplified simulation of the Earth's atmosphere, we validate the CNNs. We explore ARs' role in maintaining energy balance in the earth system.