{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T07:07:40Z","timestamp":1777446460563,"version":"3.51.4"},"reference-count":35,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T00:00:00Z","timestamp":1673308800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Beijing Natural Science Foundation","award":["8192019"],"award-info":[{"award-number":["8192019"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>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\u20132018 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 \u201312 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.<\/jats:p>","DOI":"10.3390\/e25010138","type":"journal-article","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T01:57:48Z","timestamp":1673315868000},"page":"138","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Forecast of Winter Precipitation Type Based on Machine Learning Method"],"prefix":"10.3390","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0019-9032","authenticated-orcid":false,"given":"Zhang","family":"Lang","sequence":"first","affiliation":[{"name":"Chongqing Research Institute of Big Data, Peking University, Chongqing 400000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuzi Han","family":"Wen","sequence":"additional","affiliation":[{"name":"China Huaneng Clean Energy Research Institute, Lab. Building A, Huaneng Innovation Base, Future Science Park, Beiqijia Town, Changping District, Beijing 102209, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Yu","sequence":"additional","affiliation":[{"name":"Beijing Weather Forecast Center, Beijing 100097, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Sang","sequence":"additional","affiliation":[{"name":"Beijing Weather Forecast Center, Beijing 100097, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Wang","sequence":"additional","affiliation":[{"name":"Academy for Advanced Interdisciplinary Studies, Peking University, Beijing 100871, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,1,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"821","DOI":"10.5194\/tc-6-821-2012","article-title":"Greenland ice sheet albedo feedback: Thermodynamics and atmospheric drivers","volume":"6","author":"Box","year":"2012","journal-title":"Cryosphere"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"104928","DOI":"10.1016\/j.atmosres.2020.104928","article-title":"An improved forecast of precipitation type using correlation-based feature selection and multinomial logistic regression","volume":"240","author":"Moon","year":"2020","journal-title":"Atmos. Res."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"185","DOI":"10.3354\/cr015185","article-title":"Relationships between road slipperiness, traffic accident risk and winter road maintenance activity","volume":"15","author":"Norrman","year":"2000","journal-title":"Clim. Res."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"584","DOI":"10.1175\/1520-0477-38.10.584","article-title":"Mean temperature from 1000 mb to 500 mb as a predictor of precipitation type","volume":"38","author":"Wagner","year":"1957","journal-title":"Bull. Am. Meteorol. Soc."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"596","DOI":"10.1175\/1520-0493(1980)108<0596:TOUOUA>2.0.CO;2","article-title":"The objective use of upper air soundings to specify precipitation type","volume":"108","author":"Bocchieri","year":"1980","journal-title":"Mon. Weather Rev."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1175\/1520-0434(1996)011<0591:APBNPF>2.0.CO;2","article-title":"A physically based, nondimensional parameter for discriminating between locations of freezing rain and ice pellets","volume":"11","author":"Czys","year":"1996","journal-title":"Weather Forecast."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1185","DOI":"10.1175\/1520-0450(2000)039<1185:TRIOWR>2.0.CO;2","article-title":"The relative importance of warm rain and melting processes in freezing precipitation events","volume":"39","author":"Rauber","year":"2000","journal-title":"J. Appl. Meteorol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"700","DOI":"10.1175\/1520-0434(2000)015<0700:TMEAAF>2.0.CO;2","article-title":"The melting effect as a factor in precipitation-type forecasting","volume":"15","author":"Kain","year":"2000","journal-title":"Weather Forecast."},{"key":"ref_9","first-page":"D18","article-title":"On the simulation of winter precipitation types","volume":"111","author":"Stewart","year":"2006","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_10","unstructured":"Glickman, T.S., and Zenk, W. (2000). Glossary of Meteorology, AMS (American Meteorological Society)."},{"key":"ref_11","unstructured":"Olsen, A. (2016, August 22). Snow or Rain?\u2014A Matter of Wet-Bulb Temperature. Available online: http:\/\/www.divaportal.se\/smash\/get\/diva2:968860\/FULLTEXT01.pdf."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/0169-8095(94)00004-W","article-title":"Some characteristics of the precipitation formed within winter storms over eastern Newfoundland","volume":"36","author":"Stewart","year":"1995","journal-title":"Atmos. Res."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1619","DOI":"10.1175\/BAMS-86-11-1619","article-title":"Improving short-term (0\u201348 h) cool-season quantitative precipitation forecasting: Recommendations from a USWRP workshop","volume":"86","author":"Ralph","year":"2005","journal-title":"Bull. Am. Meteorol. Soc."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1175\/WAF-D-17-0114.1","article-title":"Improving predictions of precipitation type at the surface: Description and verification of two new products from the ECMWF ensemble","volume":"33","author":"Hewson","year":"2018","journal-title":"Weather Forecast."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1175\/1520-0493(1979)107<0637:ANOSFF>2.0.CO;2","article-title":"A new operational system for forecasting precipitation type","volume":"107","author":"Bocchieri","year":"1979","journal-title":"Mon. Weather Rev."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"456","DOI":"10.1175\/1520-0434(1991)006<0456:TOUOOA>2.0.CO;2","article-title":"The objective use of observed and forecast thickness values to predict precipitation type in North Carolina","volume":"6","author":"Keeter","year":"1991","journal-title":"Weather Forecast."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1175\/1520-0434(2000)015<0583:AMTDPT>2.0.CO;2","article-title":"A method to determine precipitation types","volume":"15","author":"Bourgouin","year":"2000","journal-title":"Weather Forecast."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1175\/JHM-D-13-073.1","article-title":"Sensitivity of precipitation phase over the Swiss Alps to different meteorological variables","volume":"15","author":"Froidurot","year":"2014","journal-title":"J. Hydrometeorol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"151","DOI":"10.14191\/Atmos.2014.24.2.151","article-title":"A method for the discrimination of precipitation type using thickness and improved matsuo\u2019s scheme over South Korea","volume":"24","author":"Lee","year":"2014","journal-title":"Atmosphere"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1747","DOI":"10.1175\/JAMC-D-16-0044.1","article-title":"Discrimination between winter precipitation types based on spectral-bin microphysical modeling","volume":"55","author":"Reeves","year":"2016","journal-title":"J. Appl. Meteorol. Climatol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1002\/qj.3240","article-title":"On distinguishing snowfall from rainfall using near-surface atmospheric information: Comparative analysis, uncertainties and hydrologic importance","volume":"144","author":"Behrangi","year":"2018","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-018-03629-7","article-title":"Spatial variation of the rain\u2013snow temperature threshold across the Northern Hemisphere","volume":"9","author":"Jennings","year":"2018","journal-title":"Nat. Commun."},{"key":"ref_23","first-page":"1","article-title":"The construction and comparison of high resolution precipitation type prediction models based on three machine leanrning methods","volume":"79","author":"Yang","year":"2021","journal-title":"Acta Meteorol. Sin."},{"key":"ref_24","first-page":"31","article-title":"Decision tree for the weather forecasting","volume":"76","author":"Kumar","year":"2013","journal-title":"Int. J. Comput. Appl."},{"key":"ref_25","first-page":"1","article-title":"Machine learning applied to weather forecasting","volume":"10","author":"Holmstrom","year":"2016","journal-title":"Environ. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Singh, N., Chaturvedi, S., and Akhter, S. (2019, January 7\u20139). Weather forecasting using machine learning algorithm. Proceedings of the 2019 International Conference on Signal Processing and Communication (ICSC), Noida, India.","DOI":"10.1109\/ICSC45622.2019.8938211"},{"key":"ref_27","unstructured":"Jakaria, A., Hossain, M.M., and Rahman, M.A. (2020). Smart weather forecasting using machine learning: A case study in tennessee. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"e2020MS002203","DOI":"10.1029\/2020MS002203","article-title":"WeatherBench: A benchmark data set for data-driven weather forecasting","volume":"12","author":"Rasp","year":"2020","journal-title":"J. Adv. Model. Earth Syst."},{"key":"ref_29","first-page":"91","article-title":"Preliminarily assessment of ERA5 reanalysis data","volume":"38","author":"Meng","year":"2018","journal-title":"J. Mar. Meteorol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1007\/s10462-007-9052-3","article-title":"Machine learning: A review of classification and combining techniques","volume":"26","author":"Kotsiantis","year":"2006","journal-title":"Artif. Intell. Rev."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1007\/s00376-020-0165-9","article-title":"Determination of Surface Precipitation Type Based on the Data Fusion Approach","volume":"38","author":"Kolendowicz","year":"2021","journal-title":"Adv. Atmos. Sci."},{"key":"ref_32","first-page":"3146","article-title":"Lightgbm: A highly efficient gradient boosting decision tree","volume":"30","author":"Ke","year":"2017","journal-title":"Proc. Nips"},{"key":"ref_33","first-page":"301","article-title":"Calculation of the success and goodness of strong wind forecasts in the storm warning service","volume":"8","author":"Heidke","year":"1926","journal-title":"Geogr. Ann."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1175\/WAF-D-13-00103.1","article-title":"A probabilistic derivation of Heidke skill score","volume":"29","year":"2014","journal-title":"Weather Forecast."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1002\/qj.49707833705","article-title":"The evaluation of vertical velocity and thickness tendency from Sutcliffe\u2019s theory","volume":"78","author":"Bushby","year":"1952","journal-title":"Q. J. R. Meteorol. Soc."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/1\/138\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:05:14Z","timestamp":1760119514000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/1\/138"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,10]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,1]]}},"alternative-id":["e25010138"],"URL":"https:\/\/doi.org\/10.3390\/e25010138","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,10]]}}}