Page 212 - 《高原气象》2026年第2期
P. 212
高 原 气 象 45 卷
512
tering and exploration of large and high-dimensional geodata[J]. cold air and return flow of dust air masses[J]. Atmospheric Re‐
GeoInformatica, 7: 229-253. search, 220: 81-91. DOI: 10. 1016/j. atmosres. 2019. 01. 007.
Han L, Chen M, Chen K, et al, 2021. A deep learning method for bi‐ Zhong X, Du F, Chen L, et al, 2024. Investigating transformer‐based
as correction of ECMWF 24-240 h forecasts[J]. Advances in At‐ models for spatial downscaling and correcting biases of near‐sur‐
mospheric Sciences, 38(9): 1444-1459. face temperature and wind‐speed forecasts[J]. Quarterly Journal
Hartigan J A, Wong M A, 1979. Algorithm AS 136: A K-means clus‐ of the Royal Meteorological Society, 150(758): 275-289.
tering algorithm[J]. Journal of the Royal Statistical Society: Se‐ Zhou L, Chen H, Xu L, et al, 2024. Deep learning‐based postpro‐
ries C (Applied Statistics), 28(1): 100-108. cessing for hourly temperature forecasting[J]. Meteorological Ap‐
Jiang Q, Cioffi F, Li W, et al, 2024. Hybrid multilayer perceptron plications, 31(2): e2194.
and convolutional neural network model to predict extreme re‐ 陈新明, 盘钰春, 徐勇, 等, 2023. 西南地区植被覆盖度时空演变及
gional precipitation dominated by the large-scale atmospheric cir‐ 其与气候和地形的相关性[J]. 西南农业学报, 36(6): 1307-
culation[J]. Atmospheric Research, 304: 107362. 1317. Chen X M, Pan Y C, Xu Y, et al, 2023. Spatio-temporal
Li J W, Han X Q, Jiang J W, et al, 2020. An efficient clustering variation of fractional vegetation cover and its relationship with
method for DBSCAN geographic spatio-temporal large data with climate and topographic factors in Southwest China[J]. South‐
improved parameter optimization[J]. The International Archives west China Journal of Agricultural Sciences, 36(6): 1307-1317.
of the Photogrammetry, Remote Sensing and Spatial Information 管筝, 印涌强, 张晓祥, 等, 2024. 基于 K-means聚类与集成学习算
Sciences, 42: 581-584. 法的小流域山洪灾害易发性评估[J]. 应用科学学报, 42(3):
Lian J, Huang S, Shao J, et al, 2024. Terra Wind: a deep learning‐ 388-404. DOI: 10. 3969/j. issn. 0255-8297. 2024. 03. 002. Guan
based near‐surface winds downscaling model for complex terrain Z, Yin Y Q, Zhang X X, et al, 2024. Estimating flash flood di‐
region[J]. Geophysical Research Letters, 51(23): e2024GL11 saster susceptibility based on K-means clustering and ensemble
2124. learning approaches[J]. Journal of Applied Sciences, 42(3):
Liu Q, Lou X, Yan Z, et al, 2023. Deep-learning post-processing of 388-404. DOI: 10. 3969/j. issn. 0255-8297. 2024. 03. 002.
short-term station precipitation based on NWP forecasts[J]. At‐ 郭小芹, 李光明, 孙占峰, 等, 2022. 祁连山及周边降水分布聚类检
mospheric Research, 295: 107032. 验和典型流域增雨效果评价[J]. 干旱区地理, 45(3): 706-
Murtagh F, Contreras P, 2012. Algorithms for hierarchical clustering: 714. Guo X Q, Li G M, Sun Z F, et al, 2022. Cluster analysis
an overview[J]. Wiley Interdisciplinary Reviews Data Mining with statistical test of precipitation distribution in Qilian Moun‐
and Knowledge Discovery, 2(1), 86-97. tains and its surrounding area and evaluation of artificial precipita‐
Qin Y, Liu Y, Jiang X, et al, 2023. Grid-to-point deep-learning error tion enhancement in typical watershed[J]. Arid Land Geography,
correction for the surface weather forecasts of a fine-scale numeri‐ 45(3): 706-714.
cal weather prediction system[J]. Atmosphere, 14(1): 145. 胡莹莹, 庞林, 王启光, 2023. 基于深度学习的 7~15d温度格点预报
Schubert E, Sander J, Ester M, et al, 2017. DBSCAN revisited, re‐ 偏差订正[J]. 应用气象学报, 34(4): 426-437. Hu Y Y, Pang
visited: why and how you should (still) use DBSCAN[J]. ACM L, Wang Q G, 2023. Application of deep learning bias correction
Transactions on Database Systems (TODS), 42(3): 1-21. method to temperature grid forecast of 7-15 days[J]. Journal of
Sønderby C K, Espeholt L, Heek J, et al, 2020. MetNet: a neural Applied Meteorological Science, 34(4): 426-437.
weather model for precipitation forecasting[J]. arXiv: 2003. 金荣花, 代刊, 赵瑞霞, 等, 2019. 我国无缝隙精细化网格天气预报
12140v2. 技术进展与挑战[J]. 气象, 45(4): 445-457. Jin R H, Dai K,
Vatsavai R R, Symons C T, Chandola V, et al, 2011. GX-Means: A Zhao R X, et al, 2019. Progress and challenge of seamless fine
model-based divide and merge algorithm for geospatial image gridded weather forecasting technology in China[J]. Meteorologi‐
clustering[J]. Procedia Computer Science, 4: 186-195. cal Monthly, 45(4): 445-457.
Wu P Y, Takemi T, 2023. Impacts of mountain topography and back‐ 李浙华, 肖安, 郑丽君, 2024. 基于高分辨率数值预报和深度学习
ground flow conditions on the predictability of thermally induced 的地面气温预报研究[J]. 高原气象, 43(2): 464-477. DOI:
thunderstorms and the associated error growth[J]. Journal of the 10. 7522/j. issn. 1000-0534. 2023. 00073. Li Z H, Xiao A,
Atmospheric Sciences, 80(4): 1177-1199. Zheng L J, 2024. Research on surface temperature prediction
Xu L, Zhou L, Chen H, et al, 2024. A deep learning network for im‐ based on high-resolution numerical prediction products and deep
proving predictions of maximum and minimum temperatures over learning[J]. Plateau Meteorology, 43(2): 464-477. DOI: 10.
complex terrain[J]. Theoretical and Applied Climatology, 155 7522/j. issn. 1000-0534. 2023. 00073.
(7): 6949-6963. 潘留杰, 薛春芳, 王建鹏, 等, 2017. 一个简单的格点温度预报订正
Zhang T, Liang Z, Li W, et al, 2023. Statistical post-processing of 方法[J]. 气象, 43(12): 1584-1593. Pan L J, Xue C F, Wang J
precipitation forecasts using circulation classifications and spatio‐ P, et al, 2017. A simple grid temperature forecast correction
temporal deep neural networks[J]. Hydrology and Earth System method[J]. Meteorological Monthly, 43(12): 1584-1593.
Sciences, 27(10): 1945-1960. 邱贵强, 时少英, 王洪霞, 等, 2023. 2m 气温集成订正方法及在冬
Sun Z B, Wang H, Guo C, et al, 2019. Barrier effect of terrain on 奥延庆赛区的应用[J]. 应用气象学报, 34(4): 400-412. Qiu G

