The Tibetan Plateau (TP) is one of the highest plateaus globally, with an average altitude of over 4,000 meters, and is known as the Asian water tower. Large amounts of terrestrial water are stored in this "Asian water towers" in glaciers, snow, lakes, and rivers. It's the source of over 12 important Asian rivers, including the Indus, Ganges, Brahmaputra, Yangtze, and Yellow Rivers, which provide essential water resources for more than two billion people (
The variation of polar vortex intensity is a significant factor affecting the atmospheric conditions and weather in the Northern Hemisphere (NH) and even the world. However, previous studies on the prediction of polar vortex intensity are insufficient. This paper establishes a deep learning (DL) model for multi-day and long-time intensity prediction of the polar vortex. Focusing on the winter period with the strongest polar vortex intensity, geopotential height (GPH) data of NCEP from 1948 to 2020 at 50 hPa are used to construct the dataset of polar vortex anomaly distribution images and polar vortex intensity time series. Then, we propose a new convolution neural network with long short-term memory based on Gaussian smoothing (GSCNN-LSTM) model which can not only accurately predict the variation characteristics of polar vortex intensity from day to day, but also can produce a skillful forecast for lead times of up to 20 days. Moreover, the innovative GSCNN-LSTM model has better stability and skillful correlation prediction than the traditional and some advanced spatiotemporal sequence prediction models. The accuracy of the model suggests important implications that DL methods have good applicability in forecasting the nonlinear system and vortex spatial–temporal characteristics variation in the atmosphere.
The intensity variation of the South Asian high (SAH) plays an important role in the formation and extinction of many kinds of mesoscale systems, including tropical cyclones, southwest vortices in the Asian summer monsoon (ASM) region, and the precipitation in the whole Asia Europe region, and the SAH has a vortex symmetrical structure; its dynamic field also has the symmetry form. Not enough previous studies focus on the variation of SAH daily intensity. The purpose of this study is to establish a day-to-day prediction model of the SAH intensity, which can accurately predict not only the interannual variation but also the day-to-day variation of the SAH. Focusing on the summer period when the SAH is the strongest, this paper selects the geopotential height data between 1948 and 2020 from NCEP to construct the SAH intensity datasets. Compared with the classical deep learning methods of various kinds of efficient time series prediction model, we ultimately combine the Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) method, which has the ability to deal with the nonlinear and unstable single system, with the Permutation Entropy (PE) method, which can extract the SAH intensity feature of IMF decomposed by CEEMDAN, and the Convolution-based Gated Recurrent Neural Network (ConvGRU) model is used to train, test, and predict the intensity of the SAH. The prediction results show that the combination of CEEMDAN and ConvGRU can have a higher accuracy and more stable prediction ability than the traditional deep learning model. After removing the redundant features in the time series, the prediction accuracy of the SAH intensity is higher than that of the classical model, which proves that the method has good applicability for the prediction of nonlinear systems in the atmosphere.
In July 2021, an extreme precipitation event occurred in Henan, China, causing tremendous damage and deaths; so, it is very important to study the observation technology of extreme precipitation. Surface rain gauge precipitation observations have high accuracy but low resolution and coverage. Satellite remote sensing has high spatial resolution and wide coverage, but has large precipitation accuracy and distribution errors. Therefore, how to merge the above two kinds of precipitation observations effectively to obtain heavy precipitation products with more accurate geographic distributions has become an important but difficult scientific problem. In this paper, a new information fusion method for improving the position accuracy of satellite precipitation estimations is used based on the idea of registration and warping in image processing. The key point is constructing a loss function that includes a term for measuring two information field differences and a term for a warping field constraint. By minimizing the loss function, the purpose of position error correction of quantitative precipitation estimation from FY-4A and Integrated Multisatellite Retrievals of GPM are achieved, respectively, using observations from surface rain gauge stations. The errors of different satellite precipitation products relative to ground stations are compared and analyzed before and after position correction, using the ‘720’ extreme precipitation in Henan, China, as an example. The experimental results show that the final run has the best performance and FY-4A has the worse performance. After position corrections, the precipitation products of the three satellites are improved, among which FY-4A has the largest improvement, IMERG final run has the smallest improvement, and IMERG late run has the best performance and the smallest error. Their mean absolute errors are reduced by 23%, 14%, and 16%, respectively, and their correlation coefficients with rain gauge stations are improved by 63%, 9%, and 16%, respectively. The error decomposition model is used to examine the contributions of each error component to the total error. The results show that the new method improves the precipitation products of GPM primarily in terms of hit bias. However, it does not significantly reduce the hit bias of precipitation products of FY-4A while it reduces the total error by reducing the number of false alarms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.