Page 123 - 《高原气象》2025年第6期
P. 123
6 期 刘 杰等:基于决策树算法的青海省高原地区冰雹预报及关键特征因子分析 1531
Kim M H, Lee J, Lee S J, 2023. Hail: Mechanisms, monitoring, Glaciology, 52(58): 81-88.
forecasting, damages, financial compensation systems, and pre‐ Zheng Y G, Tao Z Y, Yu X D, 2017. Some essential issues of severe
vention[J]. Atmosphere, 14(11): 1642. convective weather forecasting[J]. Meteorological Monthly, 43
Martius O, Hering A, Kunz M, et al, 2018. Challenges and recent ad‐ (6): 641-652. DOI: 10. 7519/j. issn. 1000-0526. 2017. 06. 001.
vances in hail research[J]. Bulletin of the American Meteorologi‐ 曹艳察, 田付友, 郑永光, 等, 2018. 中国两级阶梯地势区域冰雹天
cal Society, 99(3): ES51-ES54. 气的环境物理量统计特征[J]. 高原气象, 37(1): 185-196.
McGovern A, Elmore K L, Gagne D J, et al, 2017. Using artificial DOI: 10. 7522/j. issn. 1000-0534. 2017. 00044. Cao Y C, Tian
intelligence to improve real-time decision-making for high-impact F Y, Zheng Y G, et al, 2018. Statistical characteristics of envi‐
weather[J]. Bulletin of the American Meteorological Society, 98 ronmental physical quantities in hail weather over China's Two-
(10): 2073-2090. Tiered Terrain Regions [J]. Plateau Meteorology, 37(1): 185-
McGovern A, Gagne D J, Williams J K, et al, 2014. Enhancing un‐ 196. DOI: 10. 7522/j. issn. 1000-0534. 2017. 00044.
derstanding and improving prediction of severe weather through 匡秋明, 杨雪冰, 张文生, 等, 2017. 多源数据融合高时空分辨率晴
spatiotemporal relational learning[J]. Machine Learning, 95: 雨分类[J]. 软件学报, 28(11): 2925-2939. DOI: 10. 13328/j.
27-50. cnki. jos. 005336. Kuang Q M, Yang X B, Zhang W S, et al,
Meifang Q U, Xiaoding Y U, Mengsong N, et al, 2021. Develop‐ 2017. High spatiotemporal resolution rainfall classification
ment and maintenance of squall line in a weak vertical wind shear through multi-source data fusion[J]. Journal of Software, 28
environment[J]. Torrential Rain and Disasters, 40(5): 466-473. (11): 2925-2939. DOI: 10. 13328/j. cnki. jos. 005336.
Noor N M, Al Bakri A M M, Yahaya A S, et al, 2015. Comparison of 李典, 白爱娟, 薛羽君, 等, 2014. 青藏高原和四川盆地夏季对流性
linear interpolation method and mean method to replace the miss‐ 降水特征的对比分析[J]. 气象, 40(3): 280-289. DOI: 10.
ing values in environmental data set[C]//Materials science forum. 7519/j. issn. 1000-0526. 2014. 03. 003. Li D, Bai A J, Xue Y J,
Trans Tech Publications Ltd, 803: 278-281. et al, 2014. Comparative analysis on characteristics of summer
Otchere D A, Ganat T O A, Gholami R, et al, 2021. Application of convective precipitation over Tibetan Plateau and Sichuan Basin
supervised machine learning paradigms in the prediction of petro‐ [J]. Meteorological Monthly, 40(3): 280-289. DOI: 10. 7519/
leum reservoir properties: comparative analysis of ANN and j. issn. 1000-0526. 2014. 03. 003.
SVM models[J]. Journal of Petroleum Science and Engineering, 李文娟, 赵放, 郦敏杰, 等, 2018. 基于数值预报和随机森林算法的
200: 108182. 强对流天气分类预报技术[J]. 气象, 44(12): 1555-1564.
Prein A F, Holland G J, 2018. Global estimates of damaging hail haz‐ DOI: 10. 7519/j. issn. 1000-0526. 2018. 12. 005. Li W J, Zhao
ard[J]. Weather and Climate Extremes, 22: 10-23. F, Li M J, et al, 2018. Forecasting and classification of severe
Punge H J, Kunz M, 2016. Hail observations and hailstorm character‐ convective weather based on numerical forecast and random for‐
istics in Europe: a review[J]. Atmospheric Research, 176: est algorithm[J]. Meteorological Monthly, 44(12): 1555-1564.
159-184. DOI: 10. 7519/j. issn. 1000-0526. 2018. 12. 005.
Qu M F, Yu X D, Nong M S, et al, 2021. Development and mainte‐ 刘莲, 王迎春, 陈明轩, 2015. 京津冀一次飑线过程的精细时空演
nance of squall line in a weak vertical wind shear environment 变特征分析[J]. 气象, 41(12): 1433-1446. DOI: 10. 7519/j.
[J]. Torrential Rain and Disasters, 40(5): 466-473. issn. 1000-0526. 2015. 12. 001. Liu L, Wang Y C, Chen M X,
Rana V S, Sharma S, Rana N, et al, 2022. Management of hailstorms 2015. Spatio-temporal evolution characteristics of a squall line in
under a changing climate in agriculture: a review[J]. Environ‐ Beijing-Tianjin-Hebei Region[J]. Meteorological Monthly, 41
mental Chemistry Letters, 20(6): 3971-3991. (12): 1433-1446. DOI: 10. 7519/j. issn. 1000-0526. 2015.
Reichstein M, Camps-Valls G, Stevens B, et al, 2019. Deep learning 12. 001.
and process understanding for data-driven Earth system science 刘新伟, 黄武斌, 蒋盈沙, 等, 2021. 基于 LightGBM 算法的强对流
[J]. Nature, 566(7743): 195-204. 天气分类识别研究[J]. 高原气象, 40(4): 909-918. DOI: 10.
Sarker I H, 2021. Machine learning: algorithms, real-world applica‐ 7522/j. issn. 1000-0534. 2020. 00075. Liu X W, Huang W B, Ji‐
tions and research directions[J]. SN Computer Science, 2 ang Y S, et al, 2021. Research on the classification and identifi‐
(3): 160. cation of severe convective weather based on the LightGBM Algo‐
Sui X, He S, Vilsen S B, et al, 2021. A review of non-probabilistic rithm[J]. Plateau Meteorology, 40(4): 909-918. DOI: 10. 7522/
machine learning-based state of health estimation techniques for j. issn. 1000-0534. 2020. 00075.
Lithium-ion battery[J]. Applied Energy, 300: 117346. 马晓玲, 李德帅, 胡淑娟, 2020. 青海地区雷暴, 冰雹空间分布及时
Yao H, Li X, Pang H, et al, 2020. Application of random forest algo‐ 间变化特征的精细化分析[J]. 气象, 46(3): 301-312. DOI:
rithm in hail forecasting over Shandong Peninsula[J]. Atmospher‐ 10. 7519/j. issn. 1000-0526. 2020. 03. 002. Ma X L, Li D S, Hu
ic Research, 244: 105093. S J, 2020. Refined analysis of spatio-temporal characteristics of
Zhang Y, Guo Y, 2011. Variability of atmospheric freezing-level thunderstorm and hail over Qinghai Province[J]. Meteorological
height and its impact on the cryosphere in China[J]. Annals of Monthly, 46(3): 301-312. DOI: 10. 7519/j. issn. 1000-0526.

