All Issue

2026 Vol.59, Issue 8 Preview Page
Spatio-temporal bias correction of multi-source near-real-time satellite precipitation products using double machine learning

이중기계학습을 활용한 다중 준실시간 위성강수자료의 시공간 편의 보정

Sungho Jungab
,
Younghun Kimc
,
Giha Leed*
정 성호ab
,
김 영훈c
,
이 기하d*
aPost-doctoral Researcher, Disaster Safety ADX Research Section, Electronics and Telecommunications Research Institute, Daejeon, Korea
bPost-doctoral Researcher, Climate Crisis Disaster Response Institute, Kyungpook National University, Sangju, Korea
cPh.D Student, School of Advanced Science and Technology Convergence, Kyungpook National University, Sangju, Korea
dProfessor, School of Advanced Science and Technology Convergence, Kyungpook National University, Sangju, Korea
a한국전자통신연구원 재난안전ADX연구실 박사후연구원
b경북대학교 기후위기재난대응연구소 박사후연구원
c경북대학교 미래과학기술융합학부 박사과정
d경북대학교 미래과학기술융합학부 교수
*Corresponding Author
31 August 2026. pp. 921-935
PDF XML Citation
Abstract

This study developed a LightGBM-based double machine learning (DML) framework to correct the spatio-temporal bias of three near-real-time satellite precipitation products (IMERG-Early, GSMaP-Gauge-NRT, and PERSIANN-V3) over South Korea. Topographic, meteorological, and spatial autocorrelation variables were combined as input variables, and the change in correction performance was quantified as the training gauge density was reduced from 100% to 10%. Performance was evaluated at independent validation stations for 2024 and 2025, comparing the raw satellite products, linear merging techniques, and gauge-only IDW under identical conditions. As a result, the DML achieved the highest KGE' of 0.755 among the compared methods, and with only 30 training stations (10%) it approached the accuracy of IDW based on the full gauge network. An input variable contribution analysis confirmed that this density dependence resulted from the reduced representativeness of neighboring gauge information rather than from the decrease in training samples. These results demonstrate that the proposed framework can serve as a practical alternative to gauge-only interpolation in sparsely gauged basins.

Keywords
Near-real-time satellite precipitation product
Bias correction
Double machine learning
LightGBM

본 연구는 남한 전역을 대상으로 3종의 준실시간 위성강수자료(IMERG-Early, GSMaP-Gauge-NRT, PERSIANN-V3)의 시공간 편의를 보정하기 위한 LightGBM 기반 이중기계학습(DML) 체계를 구축하였다. 이를 위해 지형, 기상 및 공간자기상관 변수를 입력자료로 결합하였으며 학습 관측망의 밀도를 100%에서 10%까지 축소하며 보정 성능의 변화를 정량화하였다. 성능 평가는 2024년과 2025년의 독립 검증 지점에서 수행하였으며, 원시 위성자료와 선형 결합 기법 및 지상관측 IDW를 동일 조건에서 비교하였다. 분석 결과, DML의 KGE'는 0.755로 비교 대상 중 가장 높았으며 학습 지점을 30개소(10%)로 축소하여도 전체 관측망을 사용한 IDW의 정확도에 근접하는 것으로 나타났다. 또한 이러한 밀도 의존성은 학습 표본의 감소가 아니라 인접 관측 정보의 대표성 저하에 기인하는 것으로 확인되었다. 제안된 보정 체계는 관측망 밀도가 낮은 유역에서 지상관측 내삽 기법의 실용적 대안으로 활용될 수 있을 것으로 기대된다.

키워드
준실시간 위성강수자료
편의 보정
이중기계학습
LightGBM
References
1

Baez-Villanueva, O.M., Zambrano-Bigiarini, M., Beck, H.E., McNamara, I., Ribbe, L., Nauditt, A., Birkel, C., Verbist, K., Giraldo-Osorio, J.D., and Thinh, N.X. (2020). “RF-MEP: A novel random forest method for merging gridded precipitation products and ground-based measurements.” Remote Sensing of Environment, Vol. 239, 111606.

10.1016/j.rse.2019.111606
2

Cheema, M.J.M., and Bastiaanssen, W.G.M. (2012). “Local calibration of remotely sensed rainfall from the TRMM satellite for different periods and spatial scales in the Indus Basin.” International Journal of Remote Sensing, Vol. 33, No. 8, pp. 2603-2627.

10.1080/01431161.2011.617397
3

Chen, H., Yong, B., Shen, Y., Liu, J., Hong, Y., and Zhang, J. (2020). “Comparison analysis of six purely satellite-derived global precipitation estimates.” Journal of Hydrology, Vol. 581, 124376.

10.1016/j.jhydrol.2019.124376
4

Duan, Z., and Bastiaanssen, W.G.M. (2013). “First results from Version 7 TRMM 3B43 precipitation product in combination with a new downscaling-calibration procedure.” Remote Sensing of Environment, Vol. 131, pp. 1-13.

10.1016/j.rse.2012.12.002
5

Gado, T.A., Hsu, K., and Sorooshian, S. (2017). “Rainfall frequency analysis for ungauged sites using satellite precipitation products.” Journal of Hydrology, Vol. 554, pp. 646-655.

10.1016/j.jhydrol.2017.09.043
6

Gupta, H.V., Kling, H., Yilmaz, K.K., and Martinez, G.F. (2009). “Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modelling.” Journal of Hydrology, Vol. 377, No. 1-2, pp. 80-91.

10.1016/j.jhydrol.2009.08.003
7

Hardwick Jones, R., Westra, S., and Sharma, A. (2010). “Observed relationships between extreme sub-daily precipitation, surface temperature, and relative humidity.” Geophysical Research Letters, Vol. 37, L22805.

10.1029/2010GL045081
8

Hong, Y., Gochis, D., Cheng, J.T., Hsu, K.L., and Sorooshian, S. (2007). “Evaluation of PERSIANN-CCS rainfall measurement using the NAME event rain gauge network.” Journal of Hydrometeorology, Vol. 8, No. 3, pp. 469-482.

10.1175/JHM574.1
9

Huang, D., Yan, P., Xiao, X., Zhu, J., Tang, X., Huang, A., and Cheng, J. (2019). “The tri-pole relation among daily mean temperature, atmospheric moisture and precipitation intensity over China.” Global and Planetary Change, Vol. 179, pp. 1-9.

10.1016/j.gloplacha.2019.04.016
10

Huffman, G.J., Bolvin, D.T., Braithwaite, D., Hsu, K.L., Joyce, R.J., Kidd, C., Nelkin, E.J., Sorooshian, S., Stocker, E.F., Tan, J., Wolff, D.B., and Xie, P. (2020). “Integrated multi-satellite retrievals for the Global Precipitation Measurement (GPM) mission (IMERG).” Satellite precipitation measurement, Edited by Levizzani, V., Kidd, C., Kirschbaum, D.B., Kummerow, C.D., Nakamura, K., Turk, F.J., Vol. 67, Springer, Cham, Switzerland, pp. 343-353.

10.1007/978-3-030-24568-9_19
11

Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017). “LightGBM: A highly efficient gradient boosting decision tree.” Proceedings of the 31st Conference on Neural Information Processing Systems, Long Beach, CA, U.S., Vol. 30, pp. 3146-3154.

12

Kling, H., Fuchs, M., and Paulin, M. (2012). “Runoff conditions in the upper Danube basin under an ensemble of climate change scenarios.” Journal of Hydrology, Vol. 424-425, pp. 264-277.

10.1016/j.jhydrol.2012.01.011
13

Kubota, T., Shige, S., Hashizume, H., Aonashi, K., Takahashi, N., Seto, S., Hirose, M., Takayabu, Y.N., Ushio, T., Iwanami, K., Kachi, M., and Okamoto, K. (2007). “Global precipitation map using satellite-borne microwave radiometers by the GSMaP project: Production and validation.” IEEE Transactions on Geoscience and Remote Sensing, Vol. 45, No. 7, pp. 2259-2275.

10.1109/TGRS.2007.895337
14

Lei, H., Zhao, H., and Ao, T. (2022). “A two-step merging strategy for incorporating multi-source precipitation products and gauge observations using machine learning classification and regression over China.” Hydrology and Earth System Sciences, Vol. 26, No. 11, pp. 2969-2995.

10.5194/hess-26-2969-2022
15

Liu, X., Yong, Z., Liu, L., Chen, T., Zhou, L., and Li, J. (2023). “Improving hydrological simulation accuracy through a three-step bias correction method for satellite precipitation products with limited gauge data.” Water, Vol. 15, No. 20, 3615.

10.3390/w15203615
16

Long, Y., Zhang, Y., and Ma, Q. (2016). “A merging framework for rainfall estimation at high spatiotemporal resolution for distributed hydrological modeling in a data-scarce area.” Remote Sensing, Vol. 8, No. 7, 599.

10.3390/rs8070599
17

Ma, Q., Xiong, L., Xia, J., Xiong, B., Yang, H., and Xu, C.Y. (2019). “A censored shifted mixture distribution mapping method to correct the bias of daily IMERG satellite precipitation estimates.” Remote Sensing, Vol. 11, No. 11, 1345.

10.3390/rs11111345
18

Manz, B., Buytaert, W., Zulkafli, Z., Lavado, W., Willems, B., Robles, L.A., and Rodríguez-Sánchez, J.-P. (2016). “High-resolution satellite-gauge merged precipitation climatologies of the Tropical Andes.” Journal of Geophysical Research: Atmospheres, Vol. 121, No. 3, pp. 1190-1207.

10.1002/2015JD023788
19

Mastrantonas, N., Bhattacharya, B., Shibuo, Y., Rasmy, M., Espinoza-Dávalos, G., and Solomatine, D. (2019). “Evaluating the benefits of merging near-real-time satellite precipitation products: A case study in the Kinu basin region, Japan.” Journal of Hydrometeorology, Vol. 20, No. 6, pp. 1213-1233.

10.1175/JHM-D-18-0190.1
20

Meng, C., Mo, X., Liu, S., and Hu, S. (2023). “Improving near-real-time satellite precipitation products through multistage modified schemes.” Atmospheric Research, Vol. 292, 106875.

10.1016/j.atmosres.2023.106875
21

Nguyen, G.V., Le, X.H., Van, L.N., Jung, S., and Lee, G. (2023). “Machine learning approaches for reconstructing gridded precipitation based on multiple source products.” Journal of Hydrology: Regional Studies, Vol. 48, 101475.

10.1016/j.ejrh.2023.101475
22

Nguyen, P., Dao, V., Ung, T., Arellano, C.J., Hsu, K., Sorooshian, S., Aghakouchak, A., Huffman, G.J., and Ralph, F.M. (2026). “PERSIANN-U-Net: A global deep learning framework for near-real-time precipitation estimation using infrared data.” Journal of Hydrometeorology, Vol. 27, No. 4, pp. 597-615.

10.1175/JHM-D-25-0162.1
23

Shen, Y., Zhao, P., Pan, Y., and Yu, J. (2014). “A high spatiotemporal gauge-satellite merged precipitation analysis over China.” Journal of Geophysical Research: Atmospheres, Vol. 119, No. 6, pp. 3063-3075.

10.1002/2013JD020686
24

Shen, Z., Yong, B., Gourley, J.J., and Qi, W. (2021). “Real-time bias adjustment for satellite-based precipitation estimates over Mainland China.” Journal of Hydrology, Vol. 596, 126133.

10.1016/j.jhydrol.2021.126133
25

Shi, J., Yuan, F., Shi, C., Zhao, C., Zhang, L., Ren, L., Zhu, Y., Jiang, S., and Liu, Y. (2020). “Statistical evaluation of the latest GPM-era IMERG and GSMaP satellite precipitation products in the Yellow River source region.” Water, Vol. 12, No. 4, 1006.

10.3390/w12041006
26

Tan, J., Huffman, G.J., Bolvin, D.T., and Nelkin, E.J. (2019). “Diurnal cycle of IMERG V06 precipitation.” Geophysical Research Letters, Vol. 46, No. 22, pp. 13584-13592.

10.1029/2019GL085395
27

Tang, G., Clark, M.P., Papalexiou, S.M., Ma, Z., and Hong, Y. (2020). “Have satellite precipitation products improved over last two decades? A comprehensive comparison of GPM IMERG with nine satellite and reanalysis datasets.” Remote Sensing of Environment, Vol. 240, 111697.

10.1016/j.rse.2020.111697
28

Ushio, T., Sasashige, K., Kubota, T., Shige, S., Okamoto, K., Aonashi, K., Inoue, T., Takahashi, N., Iguchi, T., Kachi, M., Oki, R., Morimoto, T., and Kawasaki, Z.-I. (2009). “A Kalman filter approach to the Global Satellite Mapping of Precipitation (GSMaP) from combined passive microwave and infrared radiometric data.” Journal of the Meteorological Society of Japan. Vol. 87A, pp. 137-151.

10.2151/jmsj.87A.137
29

Wang, S., Zhang, K., Chao, L., Li, D., Tian, X., Bao, H., Chen, G., and Xia, Y. (2021). “Exploring the utility of radar and satellite-sensed precipitation and their dynamic bias correction for integrated prediction of flood and landslide hazards.” Journal of Hydrology, Vol. 603, 126964.

10.1016/j.jhydrol.2021.126964
30

Wei, L., Jiang, S., Ren, L., Zhang, L., Wang, M., Liu, Y., and Duan, Z. (2022). “Bias correction of GPM IMERG Early Run daily precipitation product using near real-time CPC global measurements.” Atmospheric Research, Vol. 279, 106403.

10.1016/j.atmosres.2022.106403
31

Xie, P., and Xiong, A.Y. (2011). “A conceptual model for constructing high-resolution gauge-satellite merged precipitation analyses.” Journal of Geophysical Research: Atmospheres, Vol. 116, D21106.

10.1029/2011JD016118
32

Yin, Y., Chen, H., Wang, G., Xu, W., Wang, S., and Yu, W. (2021). “Characteristics of the precipitation concentration and their relationship with the precipitation structure: A case study in the Huai River basin, China.” Atmospheric Research, Vol. 253, 105484.

10.1016/j.atmosres.2021.105484
33

Zeng, Q., Chen, H., Xu, C.Y., Jie, M.X., Chen, J., Guo, S.L., and Liu, J. (2018). “The effect of rain gauge density and distribution on runoff simulation using a lumped hydrological modelling approach.” Journal of Hydrology, Vol. 563, pp. 106-122.

10.1016/j.jhydrol.2018.05.058
34

Zhang, L., Li, X., Zheng, D., Zhang, K., Ma, Q., Zhao, Y., and Ge, Y. (2021). “Merging multiple satellite-based precipitation products and gauge observations using a novel double machine learning approach.” Journal of Hydrology, Vol. 594, 125969.

10.1016/j.jhydrol.2021.125969
35

Zhang, Y., Ye, A., Nguyen, P., Analui, B., Sorooshian, S., and Hsu, K. (2022). “QRF4P-NRT: Probabilistic post-processing of near-real-time satellite precipitation estimates using quantile regression forests.” Water Resources Research, Vol. 58, e2022WR032117.

10.1029/2022WR032117
36

Zhou, L., Koike, T., Takeuchi, K., Rasmy, M., Onuma, K., Ito, H., Selvarajah, H., Liu, L., Li, X., and Ao, T. (2022). “A study on availability of ground observations and its impacts on bias correction of satellite precipitation products and hydrologic simulation efficiency.” Journal of Hydrology, Vol. 610, 127595.

10.1016/j.jhydrol.2022.127595
37

Zhou, T., Nijssen, B., Huffman, G.J., and Lettenmaier, D.P. (2014). “Evaluation of real-time satellite precipitation data for global drought monitoring.” Journal of Hydrometeorology, Vol. 15, No. 4, pp. 1651-1660.

10.1175/JHM-D-13-0128.1
38

Zounemat-Kermani, M., Batelaan, O., Fadaee, M., and Hinkelmann, R. (2021). “Ensemble machine learning paradigms in hydrology: A review.” Journal of Hydrology, Vol. 598, 126266.

10.1016/j.jhydrol.2021.126266
Information
  • Publisher :KOREA WATER RESOURECES ASSOCIATION
  • Publisher(Ko) :한국수자원학회
  • Journal Title :Journal of Korea Water Resources Association
  • Journal Title(Ko) :한국수자원학회 논문집
  • Volume : 59
  • No :8
  • Pages :921-935
  • Received Date : 2026-07-23
  • Revised Date : 2026-08-10
  • Accepted Date : 2026-08-10
  • DOI :https://doi.org/10.3741/JKWRA.2026.59.8.921
Journal Informaiton Journal of Korea Water Resources Association Journal of Korea Water Resources Association
Online Submission
Archives
  • scopus
  • KCI-수자원
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close