Long-lead forecasts of wintertime air stagnation index in Southern China using oceanic memory effects

Chenhong Zhou; Xiaorui Zhang; Meng Gao; Shanshan Liu; Yi-Ke Guo; Jie Chen

Long-lead forecasts of wintertime air stagnation index in Southern China using oceanic memory effects

Chenhong Zhou, Xiaorui Zhang, Meng Gao, Shanshan Liu, Yi-Ke Guo, Jie Chen^*

^*Corresponding author for this work

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

Abstract

Stagnant weather condition is one of the major contributors to air pollution as it is favorable for the formation and accumulation of pollutants. To measure the atmosphere's ability to dilute air pollutants, Air Stagnation Index (ASI) has been introduced as an important meteorological index. Therefore, making long-lead ASI forecasts is vital to make plans in advance for air quality management. In this study, we found that autumn Niño indices derived from sea surface temperature (SST) anomalies show a negative correlation with wintertime ASI in southern China, offering prospects for a prewinter forecast. We developed an LSTM-based model to predict the future wintertime ASI. Results demonstrated that multivariate inputs (past ASI and Niño indices) achieve better forecast performance than univariate input (only past ASI). The model achieves a correlation coefficient of 0.778 between the actual and predicted ASI, exhibiting a high degree of consistency.

Original language	English
Title of host publication	International Conference on Learning Representations Workshops, ICLR 2023
Subtitle of host publication	Tackling Climate Change with Machine Learning
Publisher	International Conference on Learning Representations Workshops
Pages	1-6
Number of pages	6
Publication status	Published - May 2023
Event	International Conference on Learning Representations, ICLR 2023 Workshop - Kigali, Rwanda Duration: 4 May 2023 → … https://www.climatechange.ai/events/iclr2023 https://www.climatechange.ai/events/iclr2023#accepted-works

Workshop

Workshop	International Conference on Learning Representations, ICLR 2023 Workshop
Country/Territory	Rwanda
City	Kigali
Period	4/05/23 → …
Internet address	https://www.climatechange.ai/events/iclr2023 https://www.climatechange.ai/events/iclr2023#accepted-works

Access to Document

Cite this

Zhou, C., Zhang, X., Gao, M., Liu, S., Guo, Y.-K., & Chen, J. (2023). Long-lead forecasts of wintertime air stagnation index in Southern China using oceanic memory effects. In International Conference on Learning Representations Workshops, ICLR 2023: Tackling Climate Change with Machine Learning (pp. 1-6). International Conference on Learning Representations Workshops. https://www.climatechange.ai/papers/iclr2023/13

@inproceedings{8a8f619a4fe1494f82b8b2ce1264a017,

title = "Long-lead forecasts of wintertime air stagnation index in Southern China using oceanic memory effects",

abstract = "Stagnant weather condition is one of the major contributors to air pollution as it is favorable for the formation and accumulation of pollutants. To measure the atmosphere's ability to dilute air pollutants, Air Stagnation Index (ASI) has been introduced as an important meteorological index. Therefore, making long-lead ASI forecasts is vital to make plans in advance for air quality management. In this study, we found that autumn Ni{\~n}o indices derived from sea surface temperature (SST) anomalies show a negative correlation with wintertime ASI in southern China, offering prospects for a prewinter forecast. We developed an LSTM-based model to predict the future wintertime ASI. Results demonstrated that multivariate inputs (past ASI and Ni{\~n}o indices) achieve better forecast performance than univariate input (only past ASI). The model achieves a correlation coefficient of 0.778 between the actual and predicted ASI, exhibiting a high degree of consistency.",

author = "Chenhong Zhou and Xiaorui Zhang and Meng Gao and Shanshan Liu and Yi-Ke Guo and Jie Chen",

year = "2023",

month = may,

language = "English",

pages = "1--6",

booktitle = "International Conference on Learning Representations Workshops, ICLR 2023",

publisher = "International Conference on Learning Representations Workshops",

note = "International Conference on Learning Representations, ICLR 2023 Workshop ; Conference date: 04-05-2023",

url = "https://www.climatechange.ai/events/iclr2023, https://www.climatechange.ai/events/iclr2023#accepted-works",

}

Zhou, C, Zhang, X, Gao, M, Liu, S, Guo, Y-K & Chen, J 2023, Long-lead forecasts of wintertime air stagnation index in Southern China using oceanic memory effects. in International Conference on Learning Representations Workshops, ICLR 2023: Tackling Climate Change with Machine Learning. International Conference on Learning Representations Workshops, pp. 1-6, International Conference on Learning Representations, ICLR 2023 Workshop, Kigali, Rwanda, 4/05/23. <https://www.climatechange.ai/papers/iclr2023/13>

Long-lead forecasts of wintertime air stagnation index in Southern China using oceanic memory effects. / Zhou, Chenhong; Zhang, Xiaorui; Gao, Meng et al.
International Conference on Learning Representations Workshops, ICLR 2023: Tackling Climate Change with Machine Learning. International Conference on Learning Representations Workshops, 2023. p. 1-6.

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Long-lead forecasts of wintertime air stagnation index in Southern China using oceanic memory effects

AU - Zhou, Chenhong

AU - Zhang, Xiaorui

AU - Gao, Meng

AU - Liu, Shanshan

AU - Guo, Yi-Ke

AU - Chen, Jie

PY - 2023/5

Y1 - 2023/5

N2 - Stagnant weather condition is one of the major contributors to air pollution as it is favorable for the formation and accumulation of pollutants. To measure the atmosphere's ability to dilute air pollutants, Air Stagnation Index (ASI) has been introduced as an important meteorological index. Therefore, making long-lead ASI forecasts is vital to make plans in advance for air quality management. In this study, we found that autumn Niño indices derived from sea surface temperature (SST) anomalies show a negative correlation with wintertime ASI in southern China, offering prospects for a prewinter forecast. We developed an LSTM-based model to predict the future wintertime ASI. Results demonstrated that multivariate inputs (past ASI and Niño indices) achieve better forecast performance than univariate input (only past ASI). The model achieves a correlation coefficient of 0.778 between the actual and predicted ASI, exhibiting a high degree of consistency.

AB - Stagnant weather condition is one of the major contributors to air pollution as it is favorable for the formation and accumulation of pollutants. To measure the atmosphere's ability to dilute air pollutants, Air Stagnation Index (ASI) has been introduced as an important meteorological index. Therefore, making long-lead ASI forecasts is vital to make plans in advance for air quality management. In this study, we found that autumn Niño indices derived from sea surface temperature (SST) anomalies show a negative correlation with wintertime ASI in southern China, offering prospects for a prewinter forecast. We developed an LSTM-based model to predict the future wintertime ASI. Results demonstrated that multivariate inputs (past ASI and Niño indices) achieve better forecast performance than univariate input (only past ASI). The model achieves a correlation coefficient of 0.778 between the actual and predicted ASI, exhibiting a high degree of consistency.

M3 - Conference proceeding

SP - 1

EP - 6

BT - International Conference on Learning Representations Workshops, ICLR 2023

PB - International Conference on Learning Representations Workshops

T2 - International Conference on Learning Representations, ICLR 2023 Workshop

Y2 - 4 May 2023

ER -

Long-lead forecasts of wintertime air stagnation index in Southern China using oceanic memory effects

Abstract

Workshop

Access to Document

Fingerprint

Cite this