Artificial Intelligence for the Earth Systems: Recent submissions
Now showing items 161-170 of 170
-
This Looks Like That There: Interpretable Neural Networks for Image Tasks When Location Matters
(American Meteorological Society, 2022)We develop and demonstrate a new interpretable deep learning model specifically designed for image analysis in Earth system science applications. The neural network is designed to be inherently interpretable, rather than ... -
Application of Deep Learning to Understanding ENSO Dynamics
(American Meteorological Society, 2022)Many deep learning technologies have been applied to the Earth sciences. Nonetheless, the difficulty in interpreting deep learning results still prevents their applications to studies on climate dynamics. Here, we applied ... -
Detection of Bow Echoes in Kilometer-Scale Forecasts Using a Convolutional Neural Network
(American Meteorological Society, 2022)Bow echoes (BEs) are bow-shaped lines of convective cells that are often associated with swaths of damaging straight-line winds and small tornadoes. This paper describes a convolutional neural network (CNN) able to detect ... -
Global Mesoscale Ocean Variability from Multiyear Altimetry: An Analysis of the Influencing Factors
(American Meteorological Society, 2022)Sea surface slope (SSS) responds to oceanic processes and other environmental parameters. This study aims to identify the parameters that influence SSS variability. We use SSS calculated from multiyear satellite altimeter ... -
Archetypal Analysis of Geophysical Data Illustrated by Sea Surface Temperature
(American Meteorological Society, 2022)The ability to find and recognize patterns in high-dimensional geophysical data is fundamental to climate science and critical for meaningful interpretation of weather and climate processes. Archetypal analysis (AA) is one ... -
Accurate and Clear Quantitative Precipitation Nowcasting Based on a Deep Learning Model with Consecutive Attention and Rain-Map Discrimination
(American Meteorological Society, 2022)Deep learning models are developed for high-resolution quantitative precipitation nowcasting (QPN) in Taiwan up to 3 h ahead. Many recent works aim to accurately predict relatively rare high-rainfall events with the help ... -
On Variability due to Local Minima and K-Fold Cross Validation
(American Meteorological Society, 2022)Resampling methods such as cross validation or bootstrap are often employed to estimate the uncertainty in a loss function due to sampling variability, usually for the purpose of model selection. In models that require ... -
Hybrid Neural Network Models for Postprocessing Medium-Range Forecasts of Tropical Cyclone Tracks over the Western North Pacific
(American Meteorological Society, 2022)Tropical cyclone (TC) track forecasts derived from dynamical models inherit their errors. In this study, a neural network (NN) algorithm was proposed for postprocessing TC tracks predicted by the Global Ensemble Forecast ... -
Challenges and Benchmark Datasets for Machine Learning in the Atmospheric Sciences: Definition, Status, and Outlook
(American Meteorological Society, 2022)Benchmark datasets and benchmark problems have been a key aspect for the success of modern machine learning applications in many scientific domains. Consequently, an active discussion about benchmarks for applications of ... -
Probing the Explainability of Neural Network Cloud-Top Pressure Models for LEO and GEO Imagers
(American Meteorological Society, 2022)Satellite low-Earth-orbiting (LEO) and geostationary (GEO) imager estimates of cloud-top pressure (CTP) have many applications in both operations and in studying long-term variations in cloud properties. Recently, machine ...