EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Forecast of Winter Precipitation Type Based on Machine Learning Method

Zhang Lang iD, Qiuzi Han Wen, Bo Yu, Li Sang, Yao Wang

Entropy · 10.01.2023 · 25 (1) · 138

DOI: 10.3390/e25010138 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 10.01.2023. Verfasst von Zhang Lang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Chongqing Research Institute of Big Data, Peking University, Chongqing 400000, China. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Beijing Natural Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A winter precipitation-type prediction is a challenging problem due to the complexity in the physical mechanisms and computability in numerical modeling. In this study, we introduce a new method of precipitation-type prediction based on the machine learning approach LightGBM. The precipitation-type records of the in situ observations collected from 32 national weather stations in northern China during 1997–2018 are used as the labels. The features are selected from the conventional meteorological data of the corresponding hourly reanalysis data ERA5. The evaluation results of the model performance reflect that randomly sampled validation data will lead to an illusion of a better model performance. Extreme climate background conditions will reduce the prediction accuracy of the predictive model. A feature importance analysis illustrates that the features of the surrounding area with a –12 h offset time have a higher impact on the ground precipitation types. The exploration of the predictability of our model reveals the feasibility of using the analysis data to predict future precipitation types. We use the ECMWF precipitation-type (ECPT) forecast products as the benchmark to compare with our machine learning precipitation-type (MLPT) predictions. The overall accuracy (ACC) and Heidke skill score (HSS) of the MLPT are 0.83 and 0.69, respectively, which are considerably higher than the 0.78 and 0.59 of the ECPT. For stations at elevations below 800 m, the overall performance of the MLPT is even better.

Schlagwörter

Stichwörter der Autor:innen

machine learningmodel output statisticswinter precipitation-type prediction

Autor:innen und Institutionen

  • Chongqing Research Institute of Big Data, Peking University, Chongqing 400000, China.
  • China Huaneng Clean Energy Research Institute, Lab. Building A, Huaneng Innovation Base, Future Science Park, Beiqijia Town, Changping District, Beijing 102209, China.
  • Beijing Weather Forecast Center, Beijing 100097, China.
  • Academy for Advanced Interdisciplinary Studies, Peking University, Beijing 100871, China.

ORCID-Profile: Zhang Lang

Förderung

  • Beijing Natural Science Foundation

Zitieren

APA

Lang, Z., Wen, Q. H., Yu, B., Sang, L., & Wang, Y. (2023). Forecast of Winter Precipitation Type Based on Machine Learning Method. Entropy, 25(1), 138. https://doi.org/10.3390/e25010138

Vancouver

Lang Z, Wen QH, Yu B, Sang L, Wang Y. Forecast of Winter Precipitation Type Based on Machine Learning Method. Entropy. 2023;25(1):138. doi:10.3390/e25010138

BibTeX
@article{Lang2023,
  author = {Lang, Zhang and Wen, Qiuzi Han and Yu, Bo and Sang, Li and Wang, Yao},
  title = {Forecast of Winter Precipitation Type Based on Machine Learning Method},
  journal = {Entropy},
  year = {2023},
  volume = {25},
  number = {1},
  pages = {138},
  doi = {10.3390/e25010138}
}
Kostenlos starten →