Abstract
Due to its complex and diverse terrain, precipitation gauges in the Tibetan Plateau (TP) are sparse, making it difficult to obtain reliable precipitation data for environmental studies. Data merging is a method that can integrate precipitation data from multiple sources to generate high-precision precipitation data. However, the more commonly used methods, such as regression and machine learning, do not usually consider the local correlation of precipitation, so that the spatial pattern of precipitation cannot be reproduced, while deep learning methods do incorporate spatial correlation. To explore the ability of using deep learning methods in merging precipitation data for the TP, this study compared three methods: a deep learning method—a convolutional neural network (CNN) algorithm, a machine learning method—an artificial neural network (ANN) algorithm, and a statistical method based on Extended Triple Collocation (ETC) in merging precipitation from multiple sources (gauged, grid, satellite and dynamic downscaling) over the TP, as well as their performance for hydrological simulations. Dynamic downscaling data driven by global reanalysis data centered on the TP were introduced in the merging process to better reflect the spatial variability of precipitation. The results show that: (1) in terms of the meteorological metrics, the merged data perform better than the gauge interpolation data. By using data merging, the error between the raw multi-source and gauged precipitation can be reduced, and the precipitation detection capability can be greatly improved; (2) The merged precipitation data also perform well in the hydrological evaluation. The Xin’anjiang (XAJ) model parameter calibration experiments at the source of the Yangtze River (SYR) and the source of the Yellow River (SHR) were repeated 300 times to remove uncertainty in the model parameter results. The median Kling-Gupta Efficiency Coefficients (KGE) of simulated runoff from the merged data of the ANN, CNN and ETC methods for the SYR and the SHR are 0.859, 0.864, 0.838 and 0.835, 0.835, 0.789, respectively. Except for the ETC merging data at the SHR, the performance of other merged data was improved compared to the simulation results of the gauged precipitation (KGE=0.807 at the SYR, KGE=0.828 at the SHR); and (3) In contrast to the machine learning ANN method and the statistical ETC method, the deep learning method, CNN, consistently showed better performance.
Similar content being viewed by others
References
Beck H E, Westra S, Tan J, Pappenberger F, Huffman G J, McVicar T R, Gründemann G J, Vergopolan N, Fowler H J, Lewis E, Verbist K, Wood E F. 2020. PPDIST, global 0.1° daily and 3-hourly precipitation probability distribution climatologies for 1979–2018. Sci Data, 7: 302
Bitew M M, Gebremichael M. 2011a. Assessment of satellite rainfall products for streamflow simulation in medium watersheds of the Ethiopian Highlands. Hydrol Earth Syst Sci, 15: 1147–1155
Bitew M M, Gebremichael M. 2011b. Evaluation of satellite rainfall products through hydrologic simulation in a fully distributed hydrologic model. Water Resour Res, 47: W06526
Bukovsky M S, Karoly D J. 2007. A brief evaluation of precipitation from the north american regional reanalysis. J Hydrometeorol, 8: 837–846
Chen J. 2013. Water Cycle Mechanism in the Source Region of Yangtze River (in Chinese). J Yangtze River Sci Res Inst, 30: 1–5
Chen F, Li X. 2016. Evaluation of IMERG and TRMM 3B43 monthly precipitation products over mainland China. Remote Sens, 8: 472
Chen J, Chen H, Guo S. 2018. Multi-Site precipitation downscaling using a stochastic weather generator. Clim Dyn, 50: 1975–1992
Chen Y, Sharma S, Zhou X, Yang K, Li X, Niu X, Hu X, Khadka N. 2021. spatial performance of multiple reanalysis precipitation datasets on the southern slope of Central Himalaya. Atmos Res, 250: 105365
Duan Q, Sorooshian S, Gupta V. 1992. Effective and efficient global optimization for conceptual rainfall-runoff models. Water Resour Res, 28: 1015–1031
Fang K, Shen C, Kifer D, Yang X. 2017. Prolongation of SMAP to spatiotemporally seamless coverage of continental U.S. using a deep learning neural network. Geophys Res Lett, 44: 11,030–11,039
Fu Y, Liu Q, Zi Y, Feng S, Li Y, Liu G. 2008. Summer precipitation and latent heating over the Tibetan Plateau based on TRMM measurements (in Chinese). Plateau Mountain Meteorol Res, 28: 8–18
Gao Y C, Liu M F. 2013. Evaluation of high-resolution satellite precipitation products using rain gauge observations over the Tibetan Plateau. Hydrol Earth Syst Sci, 17: 837–849
Gao Y, Xu J, Chen D. 2015. Evaluation of WRF mesoscale climate simulations over the Tibetan Plateau during 1979–2011. J Clim, 28: 2823–2841
Gao Y, Chen F, Jiang Y. 2020. Evaluation of a convection-permitting modeling of precipitation over the Tibetan Plateau and its influences on the simulation of snow-cover fraction. J Hydrometeorol, 21: 1531–1548
Gu J, Wang Z, Kuen J, Ma L, Shahroudy A, Shuai B, Liu T, Wang X, Wang G, Cai J, Chen T. 2018. Recent advances in convolutional neural networks. Pattern Recognition, 77: 354–377
Hong Z, Han Z, Li X, Long D, Tang G, Wang J. 2021. Generation of an improved precipitation data set from multisource information over the Tibetan Plateau. J Hydrometeorol, 22: 1275–1295
Hou A Y, Kakar R K, Neeck S, Azarbarzin A A, Kummerow C D, Kojima M, Oki R, Nakamura K, Iguchi T. 2014. The global precipitation measurement mission. Bull Amer Meteorol Soc, 95: 701–722
Hou Y K, Chen H, Xu C Y, Chen J, Guo S L. 2017. Coupling a markov chain and support vector machine for at-site downscaling of daily precipitation. J Hydrometeorol, 18: 2385–2406
Immerzeel W W, van Beek L P H, Bierkens M F P. 2010. Climate change will affect the Asian water towers. Science, 328: 1382–1385
Jiang L, Bauer-Gottwein P. 2019. How do GPM IMERG precipitation estimates perform as hydrological model forcing? Evaluation for 300 catchments across mainland China. J Hydrol, 572: 486–500
Jiang T, Chen Y D, Xu C, Chen X, Chen X, Singh V P. 2007. Comparison of hydrological impacts of climate change simulated by six hydrological models in the Dongjiang Basin, South China. J Hydrol, 336: 316–333
Jiang Y, Yang K, Shao C, Zhou X, Zhao L, Chen Y, Wu H. 2021. A downscaling approach for constructing high-resolution precipitation dataset over the Tibetan Plateau from ERA5 reanalysis. Atmos Res, 256: 105574
Koster R D, Liu Q, Reichle R H, Huffman G J. 2021. Improved estimates of pentad precipitation through the merging of independent precipitation data sets. Water Resources Res, 57: e2021W
Li Q, Zhang W, Yi L, Liu J, Chen H. 2018. Accuracy evaluation and comparison of GPM and TRMM precipitation product over Mainland China (in Chinese). Adv Water Sci, 29: 303–313
Li D, Yang K, Tang W, Li X, Zhou X, Guo D. 2020. Characterizing precipitation in high altitudes of the western Tibetan Plateau with a focus on major glacier areas. Int J Climatol, 40: 5114–5127
Li K, Tian F, Khan M Y A, Xu R, He Z, Yang L, Lu H, Ma Y. 2021. A high-accuracy rainfall dataset by merging multiple satellites and dense gauges over the southern Tibetan Plateau for 2014–2019 warm seasons. Earth Syst Sci Data, 13: 5455–5467
Li W, Chen J, Li L, Orsolini Y J, Xiang Y, Senan R, de Rosnay P. 2022. Impacts of snow assimilation on seasonal snow and meteorological forecasts for the Tibetan Plateau. The Cryosphere Discuss. 1–31
Lin Q, Chen J, Chen D, Wang X, Li W, Scherer D. 2021. Impacts of bias-orrected ERA5 initial snow depth on dynamical downscaling simulations for the Tibetan Plateau. J Geophys Res-Atmos, 126: e2021JD035625
Liu X, Yin Z Y. 2001. Spatial and temporal variation of summer precipitation over the eastern Tibetan Plateau and the north Atlantic oscillation. J Clim, 14: 2896–2909
Liu Z, Liu Y, Wang S, Yang X, Wang L, Baig M H A, Chi W, Wang Z. 2018. Evaluation of spatial and temporal performances of ERA-interim precipitation and temperature in mainland China. J Clim, 31: 4347–4365
Lu D, Yong B. 2018. Evaluation and hydrological utility of the latest GPM IMERG V5 and GSMaP V7 precipitation products over the Tibetan Plateau. Remote Sens, 10: 2022
Lundquist J, Hughes M, Gutmann E, Kapnick S. 2019. Our skill in modeling mountain rain and snow is bypassing the skill of our observational networks. Bull Am Meteorol Soc, 100: 2473–2490
Ma Y, Hong Y, Chen Y, Yang Y, Tang G, Yao Y, Long D, Li C, Han Z, Liu R. 2018. Performance of optimally merged multisatellite precipitation products using the dynamic Bayesian model averaging scheme over the Tibetan Plateau. J Geophys Res-Atmos, 123: 814–834
Ma Y, Sun X, Chen H, Hong Y, Zhang Y. 2021. A two-stage blending approach for merging multiple satellite precipitation estimates and rain gauge observations: An experiment in the northeastern Tibetan Plateau. Hydrol Earth Syst Sci, 25: 359–374
McColl K A, Vogelzang J, Konings A G, Entekhabi D, Piles M, Stoffelen A. 2014. Extended triple collocation: Estimating errors and correlation coefficients with respect to an unknown target. Geophys Res Lett, 41: 6229–6236
Min X Y, Yang C G, Li Y, Cheng G. 2020. Accuracy analysis of flood forecasting based on the fusion data of satellite and gauge rainfalls in humid region (in Chinese). Water Resour Power, 38: 1–5
Muñoz-Díaz D, Rodrigo F S. 2006. Seasonal Rainfall Variations in Spain (1912–2000) and their Links to Atmospheric Circulation. Atmos Res, 81: 94–110
Nan S, Zhao P, Yang S, Chen J. 2009. Springtime tropospheric temperature over the Tibetan Plateau and evolutions of the tropical Pacific SST. J Geophys Res, 114: D10104
Ou T, Chen D, Chen X, Lin C, Yang K, Lai H W, Zhang F. 2020. Simulation of summer precipitation diurnal cycles over the Tibetan Plateau at the gray-zone grid spacing for cumulus parameterization. Clim Dyn, 54: 3525–3539
Pan B, Hsu K, AghaKouchak A, Sorooshian S. 2019. Improving precipitation estimation using convolutional neural network. Water Resources Res, 55: 2301–2321
Qi W, Chen J, Li L, Xu C Y, Li J, Xiang Y, Zhang S. 2022. Regionalization of catchment hydrological model parameters for global water resources simulations. Hydrol Res, 53: 441–466
Qiu J. 2008. China: The Third Pole. Nature, 454: 393–396
Shen C, Laloy E, Elshorbagy A, Albert A, Bales J, Chang F J, Ganguly S, Hsu K L, Kifer D, Fang Z, Fang K, Li D, Li X, Tsai W P. 2018. HESS opinions: Incubating deep-learning-powered hydrologic science advances as a community. Hydrol Earth Syst Sci, 22: 5639–5656
Sui Y, Jiang D, Tian Z. 2013. Latest update of the climatology and changes in the seasonal distribution of precipitation over China. Theor Appl Climatol, 113: 599–610
Sun H, Su F, He Z, Ou T, Chen D, Li Z, Li Y. 2021. Hydrological evaluation of high-resolution precipitation estimates from the WRF model in the Third Pole River Basins. J Hydrometeorol, 22: 2055–2071
Tang G, Ma Y, Long D, Zhong L, Hong Y. 2016. Evaluation of GPM Day-1 IMERG and TMPA Version-7 legacy products over mainland China at multiple spatiotemporal scales. J Hydrol, 533: 152–167
Tang G, Long D, Hong Y, Gao J, Wan W. 2018. Documentation of multifactorial relationships between precipitation and topography of the Tibetan Plateau Using spaceborne precipitation radars. Remote Sens Environ, 208: 82–96
Tian B, Chen H, Wang J, Xu C Y. 2021. Accuracy assessment and error cause analysis of GPM (V06) in Xiangjiang River catchment. Hydrol Res, 52: 1048–1065
Tong K, Su F, Yang D, Hao Z. 2014. Evaluation of satellite precipitation retrievals and their potential utilities in hydrologic modeling over the Tibetan Plateau. J Hydrol, 519: 423–437
Valéry A, Andréassian V, Perrin C. 2014. ‘As simple as possible but not simpler’: What is useful in a temperature-based snow-accounting routine? Part 2—Sensitivity analysis of the Cemaneige snow accounting routine on 380 catchments. J Hydrol, 517: 1176–1187
Venkatesh K, Maheswaran R, Devacharan J. 2022. Framework for developing IDF curves using satellite precipitation: A Case Study Using GPM-IMERG V6 Data. Earth Sci Inform, 15: 671–687
Wang X, Pang G, Yang M. 2018. Precipitation over the Tibetan Plateau during recent decades: A review based on observations and simulations. Int J Climatol, 38: 1116–1131
Wang H M, Chen J, Xu C Y, Zhang J, Chen H. 2020. A framework to quantify the uncertainty contribution of GCMs over multiple sources in hydrological impacts of climate change. Earths Future, 8: e2020EF001602
Wang J, Cao J, Zhao S, Qi Q. 2022. S-wave velocity inversion and prediction using a deep hybrid neural network. Sci China Earth Sci, 65: 724–741
Whelan E, Gleeson E, Hanley J. 2018. An evaluation of MÉRA, a high-resolution mesoscale regional reanalysis. J Appl Meteor Climatol, 57: 2179–2196
Wu G, Liu Y, He B, Bao Q, Duan A, Jin F F. 2012. Thermal controls on the Asian Summer Monsoon. Sci Rep, 2: 404
Wu J, Gao X J. 2013. A Gridded daily observation dataset over China region and comparison with the other datasets (in Chinese). Chin J Geophys, 56: 1151–1169
Xiong L H, Guo S L. 1998. Three Layers Coupled Watershed Hdrological Model (I) Model Structure and Equation (in Chinese). J Wuhan Univ Hydr Elec Eng, 31: 28–31
Xiong L H, Liu C K, Chen S L, Zha X, Ma Q. 2021. Review of postprocessing research for remote-sensing precipitation products (in Chinese). Adv Water Sci, 32: 627–637
Xu X, Lu C, Shi X, Gao S. 2008. World water tower: An atmospheric perspective. Geophys Res Lett, 35: L20815
Xu R, Tian F, Yang L, Hu H, Lu H, Hou A. 2017. Ground validation of GPM IMERG and TRMM 3B42V7 rainfall products over Southern Tibetan Plateau based on a high-density rain gauge network. J Geophys Res-Atmos, 122: 910–924
Xu Z, Han Y, Yang Z. 2019. Dynamical downscaling of regional climate: A review of methods and limitations. Sci China Earth Sci, 62: 365–375
Xu W, Chen J, Su T, Kim J S, Gu L, Lee J H. 2022. Cascading model-based framework for the sustainability assessment of a multipurpose reservoir in a changing climate. J Water Resour Plann Manage, 148: 5021029
Yao T, Thompson L, Yang W, Yu W, Gao Y, Guo X, Yang X, Duan K, Zhao H, Xu B, Pu J, Lu A, Xiang Y, Kattel D B, Joswiak D. 2012. Different glacier status with atmospheric circulations in Tibetan Plateau and surroundings. Nat Clim Change, 2: 663–667
Yin Z Y, Zhang X, Liu X, Colella M, Chen X. 2008. An assessment of the biases of satellite rainfall estimates over the Tibetan Plateau and correction methods based on topographic analysis. J Hydrometeorol, 9: 301–326
Yu H, Liang Z, Yan Y. 2020. Review on multi-source and multi-modal data fusion and integration (in Chinese). Inform Stud Theory Appl, 43: 169–178
Zhao R J, Zhuang Y L, Fang L R, Liu X R, Zhang Q S. 1980. The Xinanjiang Model. In: Hydrological Forecasting, IAHS Publication No. 129. Wallingford: IAHS Press. 351–356
Zhao R J, Wang P L. 1988. Analysis of XAJ model parameters (in Chinese). J China Hydrol, (6): 2–9
Zhao R J. 1992. The Xinanjiang model applied in China. J Hydrol, 135: 371–381
Zhang C F, Liu C S, Wang G D, Jin J, Guan X. 2020. Attribution of Runoff Variation for the Yellow River Source Region Based on the Budyko Hypothesis (in Chinese). China Rural Water Hydropower, (9): 90–94
Zhang L, Li X, Zheng D, Zhang K, Ma Q, Zhao Y, Ge Y. 2021. Merging multiple satellite-based precipitation products and gauge observations using a novel double machine learning approach. J Hydrol, 594: 125969
Zhou X J, Zhao P, Chen J M, Chen L X, Li W L. 2009. Impacts of thermodynamic processes over the Tibetan Plateau on the northern hemispheric climate. Sci China Ser D-Earth Sci, 52: 1679–1693
Acknowledgements
We thank Prof. Deliang CHEN and Dr. Tinghai OU from the Regional Climate Group of the University of Gothenburg, Sweden, for providing the TPReanalysis dynamic downscaling dataset. Also, we thank Professor Xuejie GAO from the Laboratory for Climate Studies, China Meteorological Administration, for providing the CN05.1 gridded daily meteorological forcing dataset. Especially, we thank the responsible editor and four anonymous reviewers for constructive comments that helped improve the manuscript. This work was supported by the National Natural Science Foundation of China (Grant No. 52079093) and the National Natural Science Foundation of Hubei Province of China (Grant No. 2020CFA100).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Nan, T., Chen, J., Ding, Z. et al. Deep learning-based multi-source precipitation merging for the Tibetan Plateau. Sci. China Earth Sci. 66, 852–870 (2023). https://doi.org/10.1007/s11430-022-1050-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11430-022-1050-2