Abnormal climate events have demonstrated an increasing trend with global warming in recent years. Continuous abnormal climate events refer to the phenomenon that weather/climate state constantly deviates from the average status. Compared with the traditional definition of abnormal events, continuity and overrun of continuous abnormal climate events have been often overlooked, but they also seriously affect the production and life of the society. Aiming at filling the gap that traditional anomaly monitoring methods can not detect continuous abnormal weather, this paper firstly presents a probability-percentile algorithm that adopts the continuous abnormal monitoring idea with continuous large deviation from suitable value. On this foundation, gated recurrent unit (GRU) neural network was applied to predict continuous abnormal meteorological value. The model was applied to daily meteorological data of precipitation, temperature, and wind speed at 166 stations in mainland China from 1951 to 2020, and the results suggest that as the duration increases, continuous abnormal meteorological value presents a fluctuating pattern in most regions, rather than a hypothetical downward trend. Therefore, significant attention should be paid to continuous abnormal weather with high duration and average daily meteorological value based on our model. The method proposed in this paper can be used to monitor and predict continuous abnormal climate events, and is a valuable supplement to traditional anomaly detection methods.
[1] O'neill B C, Oppenheimer M, Warren R, et al. IPCC reasons for concern regarding climate change risks[J]. Nature Climate Change, 2017, 7(1):28-37. DOI:10.1038/nclimate3179.
[2] United Nations Office for Disaster Risk Reduction. The human cost of disasters:an overview of the last 20 years (2000-2019)[R/OL]. Estados Unidos:Naciones Unidas. (2020-10-12)[2021-07-08]. https://reliefweb.int/report/world/human-cost-disasters-overview-last-20-years-2000-2019.
[3] Krnhuber K, Osprey S, Coumou D, et al. Extreme weather events in early summer 2018 connected by a recurrent hemispheric wave-7 pattern[J]. Environmental Research Letters, 2019, 14(5):1-7. DOI:10.1088/1748-9326/ab13bf.
[4] 仇逸. 上海今年夏天已有10余人非职业性中暑死亡[EB/OL]. 搜狐新闻, (2013-07-30)[2021-07-08]. http://news.sohu.com/20130730/n382965724.shtml.
[5] 人民日报. 京广线列车脱轨原因公布[EB/OL]. (2020-04-30)[2021-07-08]. https://baijiahao.baidu.com/s?id=1665404798084280501&wfr=spider&for=pc.
[6] 张小玲, 唐宜西, 熊亚军, 等. 华北平原一次严重区域雾霾天气分析与数值预报试验[J]. 中国科学院大学学报, 2014, 31(3):337-344. DOI:10.7523/j.issn.2095-6134.2014.03.007.
[7] 宁文晓, 刘旭阳, 王振亭. 巴丹吉林沙漠气温和降水特征及空间分层异质性[J]. 中国科学院大学学报, 2021, 38(1):103-113. DOI:10.7523/j.issn.2095-6134.2021. 01.013.
[8] Dong L J, Tang Z, Li X B, et al. Discrimination of mining microseismic events and blasts using convolutional neural networks and original waveform[J]. Journal of Central South University, 2020, 27(10):3078-3089. DOI:10.1007/s11771-020-4530-8.
[9] 赵瑞星, 翟宇梅. 极端降水广义帕累托分布参数的Pickands自助矩估计研究[J]. 水力发电学报, 2015, 34(10):42-50. DOI:10.11660/slfdxb.20151006.
[10] Gao L, Huang J, Chen X W, et al. Contributions of natural climate changes and human activities to the trend of extreme precipitation[J]. Atmospheric Research, 2018, 205:60-69. DOI:10.1016/j.atmosres.2018.02.006.
[11] 周小康, 李靖, 赵昕奕. 基于小时温度数据的北京市热岛时空变化与土地利用分析[J]. 北京大学学报(自然科学版), 2020, 56(5):939-949. DOI:10.13209/j.0479-8023.2020.068.
[12] 黄建风, 陆文聪. 基于小波-NAR神经网络的气象要素时间序列预测与天气指数彩虹期权估值[J]. 系统工程理论与实践, 2016, 36(5):1146-1155. DOI:10.12011/1000-6788(2016)05-1146-10.
[13] Niu W J, Feng Z K, Feng B F, et al. Comparison of multiple linear regression, artificial neural network, extreme learning machine, and support vector machine in deriving operation rule of hydropower reservoir[J]. Water, 2019, 11(1):88-104. DOI:10.3390/w11010088.
[14] Sulaiman J, Wahab S H. Heavy rainfall forecasting model using artificial neural network for flood prone area[M]//IT convergence and security 2017. Springer, Singapore, 2018:68-76. DOI:10.1007/978-981-10-6451-7_9.
[15] Scher S. Toward data-driven weather and climate forecasting:approximating a simple general circulation model with deep learning[J]. Geophysical Research Letters, 2018, 45(22):12616-12622. DOI:10.1029/2018GL080704.
[16] Abduliah N H, Adnan R, Samad A M, et al. Lightning forecasting modelling using artificial neural network (ANN):case study Sultan Abdul Aziz Shah Airport or Skypark Subang[C]//2018 IEEE Conference on Systems, Process and Control (ICSPC). December 14-15, 2018, Melaka, Malaysia. IEEE, 2018:1-4. DOI:10.1109/SPC.2018. 8704147.
[17] Gessang O M, Lasminto U. The flood prediction model using artificial neural network (ANN) and weather application programming interface (API) as an alternative effort to flood mitigation in the Jenelata Sub-watershed[C]//IOP Conference Series:Materials Science and Engineering. IOP Publishing, 2020, 930(1):012080. DOI:10.1088/1748-9326/ab13bf.
[18] 任芝花, 邹凤玲, 余予, 等. 中国地面国际交换站气候资料日值数据集(V3.0)[EB/OL]. 国家气象科学数据中心. (2021-02-01)[2021-07-08]. http://data.cma.cn/data/cdcdetail/dataCode/SURF_CLI_CHN_MUL_DAY_CES_V3.0.html.
[19] Liu Z, Yang M, Wan G, et al. The spatial and temporal variation of temperature in the Qinghai-Xizang (Tibetan) Plateau during 1971-2015[J]. Atmosphere, 2017, 8(11):214-228. DOI:10.3390/atmos8110214.
[20] 《第三次气候变化国家评估报告》编写委员会. 第三次气候变化国家评估报告[M]. 北京:科学出版社, 2015.
[21] 孙军, 张福青. 中国日极端降水和趋势[J]. 中国科学:地球科学, 2017, 47(12):1469-1482. DOI:10.1360/N072016-00360.
[22] Chen Y C. A tutorial on kernel density estimation and recent advances[J]. Biostatistics & Epidemiology, 2017, 1(1):161-187. DOI:10.1080/24709360.2017.1396742.
[23] Vincent P, Bengio Y. Manifold parzen windows[C]//Proceedings of the 15th International Conference on Neural Information Processing Systems (NIPS'02):Cambridge, MA, USA:MIT Press, 2002:849-856. DOI:10.5555/2968618.2968724.
[24] Sheather S J, Jones M C. A reliable data-based bandwidth selection method for kernel density estimation[J]. Journal of the Royal Statistical Society:Series B (Methodological), 1991, 53(3):683-690. DOI:10.1111/j.2517-6161.1991.tb01857.x.
[25] 陈海山, 范苏丹, 张新华. 中国近50a极端降水事件变化特征的季节性差异[J]. 大气科学学报, 2009, 32(6):744-751.
[26] Yosedzadeh S, Ghazavi R, Dokhani S. Study the effect of meteorological droughts on the quantity and continuity of the surface runoff in an arid region (a case study:Kerman Province)[J]. Journal of Arid Regions Geographics Studies, 2019, 9(35):29-43.
[27] Khan F, Saeed A, ALI S. Modelling and forecasting of new cases, deaths and recover cases of COVID-19 by using vector autoregressive model in Pakistan[J]. Chaos, Solitons & Fractals, 2020, 140:110189. DOI:10.1016/j.chaos.2020.110189.
[28] Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780. DOI:10.1162/neco.1997.9.8.1735.
[29] Zhao Z, Chen W H, Wu X M, et al. LSTM network:a deep learning approach for short-term traffic forecast[J]. IET Intelligent Transport Systems, 2017, 11(2):68-75. DOI:10.1049/iet-its.2016.0208.
[30] Chung J, Gulcehre C, Cho K H, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling[EB/OL]. arXiv:1412.3555. (2014-12-11)[2021-07-08]. https://arxiv.org/abs/1412.3555.
[31] Dai Z F, Zhu H, Wen F H. Two nonparametric approaches to mean absolute deviation portfolio selection model[J]. Journal of Industrial & Management Optimization, 2020, 16(5):2283-2303. DOI:10.3934/jimo.2019054.
[32] Ali M M, Hashim N, Hamid A S A. Combination of laser-light backscattering imaging and computer vision for rapid determination of oil palm fresh fruit bunches maturity[J]. Computers and Electronics in Agriculture, 2020, 169:105235. DOI:10.1016/j.compag.2020.105235.
[33] 高丽, 陈静, 郑嘉雯, 等. 极端天气的数值模式集合预报研究进展[J]. 地球科学进展, 2019, 34(7):706-716. DOI:10.11867/j.issn.1001-8166.2019.07.0706.
[34] Yu J H, Liu Y M, Ma T T, et al. Impact of surface potential vorticity density forcing over the Tibetan Plateau on the South China extreme precipitation in January 2008. part Ⅱ:numerical simulation[J]. Journal of Meteorological Research, 2019, 33(3):416-432. DOI:10.1007/s13351-019-8606-z.
[35] Jia Z, Ren F M, Zhang D L, et al. An application of the LTP_DSEF model to heavy precipitation forecasts of landfalling tropical cyclones over China in 2018[J]. Science China Earth Sciences, 2020, 63(1):27-36. DOI:10.1007/s11430-019-9390-6.
