Machine learning for subseasonal-to-seasonal prediction

Kirsten J. Mayer; Sebastian Lerch; Catherine de Burgh-Day; Marybeth C. Arcodia

doi:10.1016/B978-0-443-31538-1.00003-8

Machine learning for subseasonal-to-seasonal prediction

Kirsten J. Mayer
, Sebastian Lerch
, Catherine de Burgh-Day
, Marybeth C. Arcodia

National Science Foundation
Karlsruhe Institute of Technology
Bureau of Meteorology Australia
University of Miami

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

1 Scopus citations

Abstract

In this chapter, we cover the current state of machine learning (ML) applied to subseasonal-to-seasonal (S2S) prediction and predictability. This includes ML applications for postprocessing and online bias correction, data-driven forecasting, and scientific discovery. We detail best practices, community efforts, as well as previous research and future directions for ML applications to S2S prediction and predictability.

Original language	English
Title of host publication	Subseasonal to Seasonal Prediction
Subtitle of host publication	The Gap Between Weather and Climate Forecasting
Publisher	Elsevier
Pages	539-589
Number of pages	51
ISBN (Electronic)	9780443315381
ISBN (Print)	9780443315398
DOIs	https://doi.org/10.1016/B978-0-443-31538-1.00003-8
State	Published - Jan 1 2025
Externally published	Yes

Keywords

Machine learning
artificial intelligence
bias correction
data-driven forecasting
explainability
interpretability
postprocessing

Access to Document

10.1016/B978-0-443-31538-1.00003-8

Cite this

@inbook{8d4083e936ce4e638ddff35ec4274155,

title = "Machine learning for subseasonal-to-seasonal prediction",

abstract = "In this chapter, we cover the current state of machine learning (ML) applied to subseasonal-to-seasonal (S2S) prediction and predictability. This includes ML applications for postprocessing and online bias correction, data-driven forecasting, and scientific discovery. We detail best practices, community efforts, as well as previous research and future directions for ML applications to S2S prediction and predictability.",

keywords = "Machine learning, artificial intelligence, bias correction, data-driven forecasting, explainability, interpretability, postprocessing",

author = "Mayer, \{Kirsten J.\} and Sebastian Lerch and \{de Burgh-Day\}, Catherine and Arcodia, \{Marybeth C.\}",

note = "Publisher Copyright: {\textcopyright} 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.",

year = "2025",

month = jan,

day = "1",

doi = "10.1016/B978-0-443-31538-1.00003-8",

language = "English",

isbn = "9780443315398",

pages = "539--589",

booktitle = "Subseasonal to Seasonal Prediction",

publisher = "Elsevier",

address = "Netherlands",

}

TY - CHAP

T1 - Machine learning for subseasonal-to-seasonal prediction

AU - Mayer, Kirsten J.

AU - Lerch, Sebastian

AU - de Burgh-Day, Catherine

AU - Arcodia, Marybeth C.

PY - 2025/1/1

Y1 - 2025/1/1

N2 - In this chapter, we cover the current state of machine learning (ML) applied to subseasonal-to-seasonal (S2S) prediction and predictability. This includes ML applications for postprocessing and online bias correction, data-driven forecasting, and scientific discovery. We detail best practices, community efforts, as well as previous research and future directions for ML applications to S2S prediction and predictability.

AB - In this chapter, we cover the current state of machine learning (ML) applied to subseasonal-to-seasonal (S2S) prediction and predictability. This includes ML applications for postprocessing and online bias correction, data-driven forecasting, and scientific discovery. We detail best practices, community efforts, as well as previous research and future directions for ML applications to S2S prediction and predictability.

KW - Machine learning

KW - artificial intelligence

KW - bias correction

KW - data-driven forecasting

KW - explainability

KW - interpretability

KW - postprocessing

UR - https://www.scopus.com/pages/publications/105040290268

U2 - 10.1016/B978-0-443-31538-1.00003-8

DO - 10.1016/B978-0-443-31538-1.00003-8

M3 - Chapter

AN - SCOPUS:105040290268

SN - 9780443315398

SP - 539

EP - 589

BT - Subseasonal to Seasonal Prediction

PB - Elsevier

ER -

Machine learning for subseasonal-to-seasonal prediction

Abstract

Keywords

Access to Document

Other files and links

Cite this