A timely and accurate assessment of the spatial precipitation distribution holds great significance to the development of the national economy. At present, most remote sensing-based precipitation products improve their accuracy using multiple regression models and physical models rather than deep learning models. This study improved a long short-term memory neural network (LSTM) deep learning model, yielding an optimized LSTM deep learning model. With the Fujian-Zhejiang-Jiangxi area as the study area, this study conducted downscaling for an integrated multi-satellite retrievals for global precipitation measurement (IMERG) product based on the daily precipitation data of 69 meteorological stations from 2015 to 2019 by introducing multiple factors controlling precipitation such as vegetation, slope aspect, slope gradient. Finally, this study assessed the reliability of the optimized model through verifications based on high-density meteorological stations and individual years. The results show that the downscaling results are consistent with the spatio-temporal distribution of precipitation measured at meteorological stations and, thus, can better reflect the spatial distribution of precipitation in the study area than the original IMERG. Furthermore, underestimated and overestimated precipitation data of the study area from the GPM product were corrected. As indicated by the verification based on high-density meteorological stations, the downscaled model yielded correlation coefficients of 0.9 or above for July and October, which were followed by April. The correlation coefficient was the lowest of 0.7 in January. As shown by the verification based on individual year data, the correlation coefficient between the daily precipitation downscaling results and the measurement results in 2020 was above 0.8, with a root mean square error of 5.23 mm and an average relative error of 9.43%. Therefore, the deep learning-based downscaling model enjoys high accuracy on both daily and monthly scales and can be widely applied in the assessment of both spatial and temporal precipitation distributions.
李新同, 史岚, 陈多妍. 基于深度学习的闽浙赣GPM降水产品降尺度方法[J]. 自然资源遥感, 2023, 35(4): 105-113.
LI Xintong, SHI Lan, CHEN Duoyan. A deep learning-based study on downscaling of GPM products in Fujian-Zhejiang-Jiangxi area. Remote Sensing for Natural Resources, 2023, 35(4): 105-113.
Wang Q X, Wang M B, Fan X H, et al. Trends of temperature and precipitation extremes in the Loess Plateau region of China,1961—2010[J]. Theoretical and Applied Climatology, 2017, 129(3):949-963.
doi: 10.1007/s00704-016-1820-z
[2]
Xu C, Luo Y, Xu Y. Projected changes of precipitation extremes in river basins over China[J]. Quaternary International, 2011, 244(2):149-158.
doi: 10.1016/j.quaint.2011.01.002
[3]
Yu S, Xia J, Yan Z, et al. Changing spring phenology dates in the Three-Rivers Headwater region of the Tibetan Plateau during 1960—2013[J]. Advances in Atmospheric Sciences, 2018, 35(1):116-126.
doi: 10.1007/s00376-017-6296-y
[4]
Huang L, Liu J, Shao Q, et al. Changing inland lakes responding to climate warming in Northeastern Tibetan Plateau[J]. Climatic Change, 2011, 109(3):479-502.
doi: 10.1007/s10584-011-0032-x
Zhang H L, Xiao L S, Chen S, et al. Characteristics and evaluation of diurnal rainfall variation in rainy seasons in Guangdong based on GPM satellite[J]. Journal of Tropical Meteorology, 2020, 36(3):335-346.
[6]
Hou A Y, Kakar R K, Neeck S, et al. The global precipitation measurement mission[J]. Bulletin of the American Meteorological Society, 2014, 95(5):701-722.
doi: 10.1175/BAMS-D-13-00164.1
[7]
Sodunke M A, Ojo J S, Adedayo K D, et al. Performance evaluation of metric measures for converting 30-min GPM rain data to 1-min for microwave applications in Tropical region of Nigeria:A multivariate approach[J]. Advances in Space Research, 2022, 69(8):3117-3129.
doi: 10.1016/j.asr.2022.01.040
[8]
Lu X, Tang G, Wang X, et al. Correcting GPM IMERG precipitation data over the Tianshan Mountains in China[J]. Journal of Hydrology, 2019, 575:1239-1252.
doi: 10.1016/j.jhydrol.2019.06.019
Shi L, He Q Q, Yang J, et al. Downscaling modeling of the GPM IMERG precipitation product and comparative analysis in the Fujian-Zhejiang-Jiangxi region[J]. Journal of Geo-Information Science, 2019, 21(10):1642-1652.
Hu S, Han J, Zhan C S, et al. Spatial downscaling of remotely sensed precipitation in Taihang Mountains[J]. Geographical Research, 2020, 39 (7):1680-1690.
doi: 10.11821/dlyj020190545
[11]
Brocca L, Massari C, Pellarin T, et al. River flow prediction in data scarce regions:Soil moisture integrated satellite rainfall products outperform rain gauge observations in West Africa[J]. Scientific Reports, 2020, 10(1):12517.
doi: 10.1038/s41598-020-69343-x
pmid: 32719498
[12]
Hinton G E, Osindero S, Teh Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7):1527-1554.
doi: 10.1162/neco.2006.18.7.1527
pmid: 16764513
[13]
Afshin S, Fahmi H, Alizadeh A, et al. Long term rainfall forecasting by integrated artificial neural network-fuzzy logic-wavelet model in Karoon basin[J]. Scientific Research and Essays, 2011, 6(6): 1200-1208.
[14]
Bonnet S M, Evsukoff A, Morales R C A. Precipitation nowcasting with weather Radar images and deep learning in São Paulo,Brasil[J]. Atmosphere, 2020, 11(11):1157.
doi: 10.3390/atmos11111157
[15]
王慧媛. 基于深度学习的短时定量降水预测研究[D]. 金华: 浙江师范大学, 2020.
Wang H Y. Short-term quantitative precipitation prediction based on deep learning[D]. Jinhua: Zhejiang Normal University, 2020.
Zhou K H, Zheng Y G, Han L, et al. Advances in application of machine learning to severe convective weather monitoring and forecasting[J]. Meteorological Monthly, 2021, 47(3):274-289.
Guo H Y, Chen M X, Han L, et al. High resolution nowcasting experiment of severe convections based on deep learning[J]. Acta Meteorologica Sinica, 2019, 77(4):715-727.
Xu H L, Qiao S B, Lin J L. Prediction of length-of-day variations by long short-term memory network[J]. Journal of Geomatics Science and Technology, 2020, 37 (5):474-478.
Yuan J G, Li W, liu S N. A global ionospheric NmF2 model developed by deep learning[J]. Journal of Geomatics Science and Technology, 2020, 37(1):15-20.
[20]
Xiang L, Xiang J, Guan J, et al. A novel reference-based and gradient-guided deep learning model for daily precipitation downscaling[J]. Atmosphere, 2022, 13(4):511.
doi: 10.3390/atmos13040511
Wu H P, Huang S C. Research on new construction land information extraction based on deep learning:Innovation exploration of the national project of land use monitoring via remote sensing[J]. Remote Sensing for Land and Resources, 2019, 31(4):159-166.doi:10.6046/gtzyyg.2019.04.21.
Xu J, Yuan C Q, Cheng Y E, et al. Active deep learning based polarimetric SAR image classification[J]. Remote Sensing for Land and Resources, 2018, 30(1):72-77.doi:10.6046/gtzyyg.2018.01.10.
Wang Y Q, Li Q Q, Wang C S, et al. Tethered UAVs-based applications in emergency surveying and mapping[J]. Remote Sensing for Land and Resources, 2020, 32(1):1-6.doi:10.6046/gtzyyg.2020.01.01.
Cai X, Li Q, Luo Y, et al. Surface features extraction of mining area image based on object-oriented and deep-learning method[J]. Remote Sensing for Land and Resources, 2021, 33(1):63-71.doi:10.6046/gtzyyg.2020111.
Cui L L, Shi J, Yang Y M, et al. Ten-day response of vegetation NDVI to the variations of temperature and precipitation in Eastern China[J]. Acta Geographica Sinica, 2009, 64(7):850-860.
doi: 10.11821/xb200907009
Shu S J, Wang Y, Xiong A Y. Estimation and analysis for geographic and orographic influences on precipitation distribution in China[J]. Chinese Journal of Geophysics, 2007, 50(6):1703-1712.
[27]
Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780.
doi: 10.1162/neco.1997.9.8.1735
pmid: 9377276
[28]
Yu Y, Si X, Hu C, et al. A review of recurrent neural networks:LSTM cells and network architectures[J]. Neural Computation, 2019, 31(7):1235-1270.
doi: 10.1162/neco_a_01199
Jin X L, Shao H, Zhang C, et al. The applicability evaluation of three satellite products in Tianshan Mountains[J]. Journal of Natural Resources, 2016, 31(12):2074-2085.
[30]
Tan J, Petersen W A, Tokay A. A novel approach to identify sources of errors in IMERG for GPM ground validation[J]. Journal of Hydrometeorology, 2016, 17(9):2477-2491.
doi: 10.1175/JHM-D-16-0079.1