Improving the Accuracy of Subseasonal Forecasting of China Precipitation With a Machine Learning Approach
Precipitation change, which is closely related to drought and flood disasters in China, affects billions of people every year, and the demand for subseasonal forecasting of precipitation is even more urgent. Subseasonal forecasting, which is more difficult than weather forecasting, however, has rema...
Published in: | Frontiers in Earth Science |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Frontiers Media S.A.
2021
|
Subjects: | |
Online Access: | https://doi.org/10.3389/feart.2021.659310 https://doaj.org/article/d56329fc3aa94b6cb1fe509df08c5c84 |
id |
ftdoajarticles:oai:doaj.org/article:d56329fc3aa94b6cb1fe509df08c5c84 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:d56329fc3aa94b6cb1fe509df08c5c84 2023-05-15T15:16:03+02:00 Improving the Accuracy of Subseasonal Forecasting of China Precipitation With a Machine Learning Approach Cen Wang Zhaoying Jia Zhaohui Yin Fei Liu Gaopeng Lu Jianqiu Zheng 2021-05-01T00:00:00Z https://doi.org/10.3389/feart.2021.659310 https://doaj.org/article/d56329fc3aa94b6cb1fe509df08c5c84 EN eng Frontiers Media S.A. https://www.frontiersin.org/articles/10.3389/feart.2021.659310/full https://doaj.org/toc/2296-6463 2296-6463 doi:10.3389/feart.2021.659310 https://doaj.org/article/d56329fc3aa94b6cb1fe509df08c5c84 Frontiers in Earth Science, Vol 9 (2021) subseasonal forecasting machine learning MultiLLR China precipitation intraseasonal variability seasonal cycle Science Q article 2021 ftdoajarticles https://doi.org/10.3389/feart.2021.659310 2022-12-31T10:19:43Z Precipitation change, which is closely related to drought and flood disasters in China, affects billions of people every year, and the demand for subseasonal forecasting of precipitation is even more urgent. Subseasonal forecasting, which is more difficult than weather forecasting, however, has remained as a blank area in meteorological service for a long period of time. To improve the accuracy of subseasonal forecasting of China precipitation, this work introduces the machine learning method proposed by Hwang et al. in 2019 to predict the precipitation in China 2–6 weeks in advance. The authors used a non-linear regression model called local linear regression together with multitask feature election (MultiLLR) model and chosen 21 meteorological elements as candidate predictors to integrate diverse meteorological observation data. This method automatically eliminates irrelevant predictors so as to establish the forecast equations using multitask feature selection process. The experiments demonstrate that the pressure and Madden–Julian Oscillation (MJO) are the most important physical factors. The average prediction skill is 0.11 during 2011–2016, and there are seasonal differences in forecasting skills, evidenced by higher forecast skills of winter and spring seasons than summer and autumn seasons. The proposed method can provide effective and indicative guidance for the subseasonal prediction of precipitation in China. By adding another three factors, Arctic Oscillation (AO) index, Western North Pacific Monsoon (WNPM) index and Western North Pacific Subtropical High (WNPSH) index into the MultiLLR model, the authors find that AO can improve the forecast skill of China precipitation to the maximum extent from 0.11 to 0.13, followed by WNPSH. Moreover, the ensemble skill of our model and CFSv2 is 0.16. This work shows that our subseasonal prediction of China precipitation should be benefited from the MultiLLR model. Article in Journal/Newspaper Arctic Directory of Open Access Journals: DOAJ Articles Arctic Pacific Frontiers in Earth Science 9 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
subseasonal forecasting machine learning MultiLLR China precipitation intraseasonal variability seasonal cycle Science Q |
spellingShingle |
subseasonal forecasting machine learning MultiLLR China precipitation intraseasonal variability seasonal cycle Science Q Cen Wang Zhaoying Jia Zhaohui Yin Fei Liu Gaopeng Lu Jianqiu Zheng Improving the Accuracy of Subseasonal Forecasting of China Precipitation With a Machine Learning Approach |
topic_facet |
subseasonal forecasting machine learning MultiLLR China precipitation intraseasonal variability seasonal cycle Science Q |
description |
Precipitation change, which is closely related to drought and flood disasters in China, affects billions of people every year, and the demand for subseasonal forecasting of precipitation is even more urgent. Subseasonal forecasting, which is more difficult than weather forecasting, however, has remained as a blank area in meteorological service for a long period of time. To improve the accuracy of subseasonal forecasting of China precipitation, this work introduces the machine learning method proposed by Hwang et al. in 2019 to predict the precipitation in China 2–6 weeks in advance. The authors used a non-linear regression model called local linear regression together with multitask feature election (MultiLLR) model and chosen 21 meteorological elements as candidate predictors to integrate diverse meteorological observation data. This method automatically eliminates irrelevant predictors so as to establish the forecast equations using multitask feature selection process. The experiments demonstrate that the pressure and Madden–Julian Oscillation (MJO) are the most important physical factors. The average prediction skill is 0.11 during 2011–2016, and there are seasonal differences in forecasting skills, evidenced by higher forecast skills of winter and spring seasons than summer and autumn seasons. The proposed method can provide effective and indicative guidance for the subseasonal prediction of precipitation in China. By adding another three factors, Arctic Oscillation (AO) index, Western North Pacific Monsoon (WNPM) index and Western North Pacific Subtropical High (WNPSH) index into the MultiLLR model, the authors find that AO can improve the forecast skill of China precipitation to the maximum extent from 0.11 to 0.13, followed by WNPSH. Moreover, the ensemble skill of our model and CFSv2 is 0.16. This work shows that our subseasonal prediction of China precipitation should be benefited from the MultiLLR model. |
format |
Article in Journal/Newspaper |
author |
Cen Wang Zhaoying Jia Zhaohui Yin Fei Liu Gaopeng Lu Jianqiu Zheng |
author_facet |
Cen Wang Zhaoying Jia Zhaohui Yin Fei Liu Gaopeng Lu Jianqiu Zheng |
author_sort |
Cen Wang |
title |
Improving the Accuracy of Subseasonal Forecasting of China Precipitation With a Machine Learning Approach |
title_short |
Improving the Accuracy of Subseasonal Forecasting of China Precipitation With a Machine Learning Approach |
title_full |
Improving the Accuracy of Subseasonal Forecasting of China Precipitation With a Machine Learning Approach |
title_fullStr |
Improving the Accuracy of Subseasonal Forecasting of China Precipitation With a Machine Learning Approach |
title_full_unstemmed |
Improving the Accuracy of Subseasonal Forecasting of China Precipitation With a Machine Learning Approach |
title_sort |
improving the accuracy of subseasonal forecasting of china precipitation with a machine learning approach |
publisher |
Frontiers Media S.A. |
publishDate |
2021 |
url |
https://doi.org/10.3389/feart.2021.659310 https://doaj.org/article/d56329fc3aa94b6cb1fe509df08c5c84 |
geographic |
Arctic Pacific |
geographic_facet |
Arctic Pacific |
genre |
Arctic |
genre_facet |
Arctic |
op_source |
Frontiers in Earth Science, Vol 9 (2021) |
op_relation |
https://www.frontiersin.org/articles/10.3389/feart.2021.659310/full https://doaj.org/toc/2296-6463 2296-6463 doi:10.3389/feart.2021.659310 https://doaj.org/article/d56329fc3aa94b6cb1fe509df08c5c84 |
op_doi |
https://doi.org/10.3389/feart.2021.659310 |
container_title |
Frontiers in Earth Science |
container_volume |
9 |
_version_ |
1766346364837429248 |