Analysis of Spatiotemporal Characteristics of Global TCWV and AI Hybrid Model Prediction
Abstract
1. Introduction
2. Materials and Methods
2.1. Study Area
2.2. Data Sources and Processing
2.3. Methods
2.3.1. Linear Fitting and Cumulative Averaging
2.3.2. Mann–Kendall Nonparametric Trend Test and Dynamic Sliding t Analysis
2.3.3. Pixel-Scale Least Squares Trend Estimation
2.3.4. Multi-Resolution Wavelet Decomposition and Reconstruction Analysis
2.3.5. LSTM Neural Network Model
2.3.6. TCN Neural Network Model
2.3.7. GRU Neural Network Model
2.3.8. Model Performance Evaluation
3. Results
3.1. Temporal Variation Characteristics
3.1.1. Seasonal and Long-Term Trends in Global TCWV
3.1.2. Annual Anomalies and Cumulative Trends
3.1.3. Mutation Analysis Using Sliding t-Test
3.2. Spatial Variation Characteristics
3.2.1. Annual Spatial Dynamics and Five-Year Interval Spatial Trends
3.2.2. Multi-Year Average Seasonal Distribution
3.2.3. Interannual Variation Rates
3.3. TCWV Prediction
3.3.1. Wavelet Transform Decomposition
3.3.2. Model Prediction and Validation
3.3.3. Comparison of Prediction Results
4. Discussion
4.1. The Spatiotemporal Variation Characteristics of TCWV
4.2. Stability of Hybrid Model Predictions
4.3. Impacts of TCWV Changes on Water Resource Management
5. Conclusions
Supplementary Materials
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Lesk, C.; Rowhani, P.; Ramankutty, N. Influence of extreme weather disasters on global crop production. Nature 2016, 529, 84–87. [Google Scholar] [CrossRef]
- Minoli, S.; Jägermeyr, J.; Asseng, S.; Urfels, C.; Müller, C. Global crop yields can be lifted by timely adaptation of growing periods to climate change. Nat. Commun. 2022, 13, 7079. [Google Scholar] [CrossRef] [PubMed]
- Trenberth, K.E. Changes in precipitation with climate change. Clim. Res. 2011, 47, 123–138. [Google Scholar] [CrossRef]
- Johnson, S.E.A.; Ye, H.; Fetzer, E.J.; Li, J. Satellite-observed precipitation and total column water vapor. Front. Environ. Sci. 2024, 12, 1338678. [Google Scholar] [CrossRef]
- Wu, H.; Su, X.; Huang, S.; Singh, V.P.; Zhou, S.; Tan, X.; Hu, X. Decreasing dynamic predictability of global agricultural drought with warming climate. Nat. Clim. Change 2025, 15, 411–419. [Google Scholar] [CrossRef]
- Li, S.; Wu, L.; Wang, Y.; Geng, T.; Cai, W.; Gan, B.; Jing, Z.; Yang, Y. Intensified Atlantic multidecadal variability in a warming climate. Nat. Clim. Change 2025, 15, 293–300. [Google Scholar] [CrossRef]
- Wang, Z.; Lei, Y.; Che, H.; Wu, B.; Zhang, X. Aerosol forcing regulating recent decadal change of summer water vapor budget over the Tibetan Plateau. Nat. Commun. 2024, 15, 2233. [Google Scholar] [CrossRef]
- Tan, J.; Chen, B.; Wang, W.; Yu, W.K.; Dai, W. Evaluating Precipitable Water Vapor Products From Fengyun-4A Meteorological Satellite Using Radiosonde, GNSS, and ERA5 Data. IEEE Trans. Geosci. Remote Sens. 2022, 60, 4106512. [Google Scholar] [CrossRef]
- Peng, Y.; Addisu, H.; Fadwa, A.; Joseph, A.; Anna, K.; Felix, N.T.; Hansjörg, K. Feasibility of ERA5 integrated water vapor trends for climate change analysis in continental Europe: An evaluation with GPS (1994–2019) by considering statistical significance. Remote Sens. Environ. 2021, 260, 112416. [Google Scholar] [CrossRef]
- Dee, D.P.; Uppala, S.M.; Simmons, A.J.; Berrisford, P. The ERA-Interim reanalysis: Configuration and performance of the data assimilation system. Q. J. R. Meteorol. Soc. 2011, 137, 553–597. [Google Scholar] [CrossRef]
- Sasayama, T.; Okamura, N.; Higashino, K.; Yoshida, T. Improvement in magnetic nanoparticle tomography estimation accuracy by combining sLORETA and non-negative least squares methods. J. Magn. Magn. Mater. 2022, 563, 169953–169960. [Google Scholar] [CrossRef]
- You, Y.; Ting, M.; Biasutti, M. Climate warming contributes to the record-shattering 2022 Pakistan rainfall. npj Clim. Atmos. Sci. 2024, 7, 89. [Google Scholar] [CrossRef]
- Borger, C.; Beirle, S.; Wagner, T. Analysis of global trends of total column water vapour from multiple years of OMI observations. Atmos. Chem. Phys. 2022, 22, 10603–10621. [Google Scholar] [CrossRef]
- Kim, S.; Sharma, A.; Wasko, C. Nathan, RLinking Total Precipitable Water to Precipitation Extremes Globally. Earth’s Future 2022, 10, e2021EF002473. [Google Scholar] [CrossRef]
- Ayantobo, O.O.; Wei, J.; Kang, B.; Zhang, H. Spatial and temporal characteristics of atmospheric water vapour content and its relationship with precipitation conversion in China during 1980–2016. Int. J. Climatol. 2020, 40, 702–722. [Google Scholar] [CrossRef]
- Ren, D.; Wang, Y.; Wang, G.; Liu, L. Rising trends of global precipitable water vapor and its correlation with flood frequency. Geod. Geodyn. 2023, 14, 355–367. [Google Scholar] [CrossRef]
- Chhetri, M.; Kumar, S.; Pratim Roy, P.; Kim, B. Deep BLSTM-GRU model for monthly rainfall prediction: A case study of Simtokha, Bhutan. Remote Sens. 2020, 12, 3174. [Google Scholar] [CrossRef]
- Richardson, D.; Neal, R.; Dankers, R.; Mylne, K.; Cowling, R.; Clements, H.; Millard, J. Linking weather patterns to regional extreme precipitation for highlighting potential flood events in medium-to long-range forecasts. Meteorol. Appl. 2020, 27, e1944. [Google Scholar] [CrossRef]
- Zhang, X.; Zhou, Y.; Zhang, W.; Kou, M.; Li, B.; Dai, Y.; Yang, C. Water vapor content prediction based on neural network model selection and optimal fusion. J. Comput. Sci. 2024, 79, 102310. [Google Scholar] [CrossRef]
- Acito, N.; Diani, M.; Corsini, G. CWV-Net: A deep neural network for atmospheric column water vapor retrieval from hyperspectral VNIR data. IEEE Trans. Geosci. Remote Sens. 2020, 58, 8163–8175. [Google Scholar] [CrossRef]
- Chen, K.; Chen, K.; Wang, Q.; He, Z.; Hu, J.; He, J. Short-term load forecasting with deep residual networks. IEEE Trans. Smart Grid 2019, 10, 3943–3952. [Google Scholar] [CrossRef]
- Shi, X.; Li, T.; Wang, H.; Yeung, D.-Y.; Wong, W.K.; Woo, W.-C. Convolutional LSTM network: A machine learning approach for precipitation nowcasting. Adv. Neural Inf. Process. Syst. 2015, 28, 802–810. [Google Scholar] [CrossRef]
- Bai, S.; Kolter, J.Z.; Koltun, V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv 2018, arXiv:1803.01271. [Google Scholar] [CrossRef]
- Zhang, H.; Xu, T.; Li, H.; Zhang, S.; Wang, X.; Huang, X. StackGAN: Text to photo-realistic image synthesis with stacked generative adversarial networks. In Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 29 October 2017; pp. 5907–5915. [Google Scholar] [CrossRef]
- Xiao, C.; Chen, N.; Hu, C.; Wang, K.; Gong, J.; Chen, Z. Short and mid-term sea surface temperature prediction using time-series satellite data and LSTM-Adaboost combination approach. Remote Sens. Environ. 2019, 233, 111358. [Google Scholar] [CrossRef]
- Chen, R.; Wang, X.; Zhang, W.; Zhu, X.; Li, A.; Yang, C. A hybrid CNN-LSTM model for typhoon formation forecasting. Geoinformatica 2019, 23, 375–396. [Google Scholar] [CrossRef]
- Diouf, D.; Niang, A.; Thiria, S. Deep learning based multiple regression to predict total column water vapor (TCWV) from physical parameters in West Africa by using Keras library. Int. J. Data Min. Knowl. Manag. Process 2019, 9, 13–21. [Google Scholar] [CrossRef]
- Graham, R.M.; Hudson, S.R.; Maturilli, M. Improved performance of ERA5 in Arctic gateway relative to four global atmospheric reanalyses. Geophys. Res. Lett. 2019, 46, 6138–6147. [Google Scholar] [CrossRef]
- Hersbach, H.; Bell, B.; Berrisford, P.; Hirahara, S. The ERA5 global reanalysis. Q. J. R. Meteorol. Soc. 2020, 146, 1999–2049. [Google Scholar] [CrossRef]
- Durre, I.; Yin, X.; Vose, R.S.; Applequist, S.; Arnfield, J. Enhancing the Data Coverage in the Integrated Global Radiosonde Archive. J. Atmos. Ocean. Technol. 2018, 35, 1753–1770. [Google Scholar] [CrossRef]
- Liu, S.; Gong, P. Change of surface cover greenness in China between 2000 and 2010. Chin. Sci. Bull. 2012, 57, 1423–1434. [Google Scholar] [CrossRef]
- Mann, H.B. Nonparametric tests against trend. Econometrica 1945, 13, 245–259. [Google Scholar] [CrossRef]
- Topaloğlu, F.; Irvem, A.; Özfidaner, M. Re-evaluation of trends in annual streamflows of Turkish rivers for the period 1968–2007. Fresenius Environ. Bull. 2012, 21, 2043–2050. [Google Scholar]
- Yue, S.; Pilon, P. A comparison of the power of the t test, Mann-Kendall and bootstrap tests for trend detection. Hydrol. Sci. J. 2004, 49, 21–37. [Google Scholar] [CrossRef]
- Peng, J.; Chen, S.; Lü, H.; Liu, Y.; Wu, J. Spatiotemporal patterns of remotely sensed PM2.5 concentration in China from 1999 to 2011. Remote Sens. Environ. 2016, 174, 109–121. [Google Scholar] [CrossRef]
- Theil, H. A rank-invariant method of linear and polynomial regression analysis. Indag. Math. 1950, 12, 85–91. [Google Scholar] [CrossRef]
- Sen, P.K. Estimates of the regression coefficient based on Kendall’s tau. J. Am. Stat. Assoc. 1968, 63, 1379–1389. [Google Scholar] [CrossRef]
- Arts, L.P.A.; van den Broek, E.L. The fast continuous wavelet transformation (fCWT) for real-time, high-quality, noise-resistant time–frequency analysis. Nat. Comput. Sci. 2022, 2, 47–58. [Google Scholar] [CrossRef]
- Prokoph, A.; El Bilali, H. Cross-wavelet analysis: A tool for detection of relationships between paleoclimate proxy records. Math. Geosci. 2008, 40, 575–586. [Google Scholar] [CrossRef]
- Kisi, O. Wavelet regression model as an alternative to neural networks for river stage forecasting. Water Resour. Manag. 2011, 25, 579–600. [Google Scholar] [CrossRef]
- Mallat, S.G. A theory for multiresolution signal decomposition: The wavelet representation. IEEE Trans. Pattern Anal. Mach. Intell. 1989, 11, 674–693. [Google Scholar] [CrossRef]
- Hochreiter, S.; Schmidhuber, J. Long short-term memory. Neural Comput. 1997, 9, 1735–1780. [Google Scholar] [CrossRef]
- Cho, K.; Van Merriënboer, B.; Gulcehre, C.; Bahdanau, D.; Bougares, F.; Schwenk, H.; Bengio, Y. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv 2014, arXiv:1406.1078. [Google Scholar] [CrossRef]
- Shen, G.; Tan, Q.; Zhang, H.; Zeng, P.; Xu, J. Deep learning with gated recurrent unit networks for financial sequence predictions. Procedia Comput. Sci. 2018, 131, 895–903. [Google Scholar] [CrossRef]
- Rahul, G.D.; Harigovindan, V.P.; Rasheed, A.H.K.P.; Amrtha, B. Attention-driven LSTM and GRU deep learning techniques for precise water quality prediction in smart aquaculture. Aquac. Int. 2024, 32, 8455–8478. [Google Scholar] [CrossRef]
- Hewage, P.; Behera, A.; Trovati, M.; Pereira, E.; Ghahremani, M.; Palmier, F.; Liu, Y. Temporal convolutional neural (TCN) network for an effective weather forecasting using time-series data from the local weather station. Soft Comput. 2020, 24, 16453–16482. [Google Scholar] [CrossRef]
- Liu, S.; Xu, T.; Du, X.; Zhang, Y.; Wu, J. A hybrid deep learning model based on parallel architecture TCN-LSTM with Savitzky-Golay filter for wind power prediction. Energy Convers. Manag. 2024, 302, 118122. [Google Scholar] [CrossRef]
- Zheng, Y.; Lu, C.; Wu, Z.; Liao, J.; Zhang, Y.; Wang, Q. Machine learning-based model for real-time GNSS precipitable water vapor sensing. Geophys. Res. Lett. 2022, 49, e2021GL096408. [Google Scholar] [CrossRef]
- Huang, L.; Peng, H.; Liu, L.; Xiong, S.; Xie, S.; Chen, J.; Li, H.; He, H. GNSS precipitable water vapor retrieval with the aid of NWM data for China. Earth Space Sci. 2021, 8, e2020EA001550. [Google Scholar] [CrossRef]
- Kim, S.; Shin, J.-Y.; Lee, G.; Park, J.; Sung, K. Future changes in precipitation extremes over South Korea based on observations and CMIP6 SSP scenarios. Water 2025, 17, 1702. [Google Scholar] [CrossRef]
- IPCC. Climate Change 2023: Synthesis Report; Intergovernmental Panel on Climate Change: Geneva, Switzerland, 2023; pp. 1–85. Available online: https://www.ipcc.ch/report/ar6/syr/ (accessed on 5 May 2025).
- He, C.; Wang, Z.; Zhou, T.; Li, T. Enhanced Latent Heating over the Tibetan Plateau as a Key to the Enhanced East Asian Summer Monsoon Circulation under a Warming Climate. J. Clim. 2019, 32, 3373–3388. [Google Scholar] [CrossRef]
- Liu, Y.; Fang, J.; Mu, S. Evaluation and future projection of compound extreme events in China using CMIP6 models. Clim. Change 2025, 178, 11. [Google Scholar] [CrossRef]
- Trenberth, K.E. The changing flow of energy through the climate system. J. Clim. 2020, 33, 5187–5202. [Google Scholar] [CrossRef]
- IPCC. Climate Change 2021: The Physical Science Basis; Cambridge University Press: Cambridge, UK, 2021. [Google Scholar] [CrossRef]
- Zelinka, M.D.; Myers, T.A.; McCoy, D.T.; Po-Chedley, S.; Caldwell, P.M.; Ceppi, P.; Klein, S.A.; Taylor, K.E. Causes of higher climate sensitivity in CMIP6 models. Geophys. Res. Lett. 2020, 47, e2019GL085782. [Google Scholar] [CrossRef]
- Huang, B.; Menne, M.J.; Boyer, T.; Freeman, E.; Gleason, B.E.; Lawrimore, J.H.; Liu, C.; Rennie, J.J.; Schreck, C.J.; Yang, F.; et al. Uncertainty estimates for sea surface temperature and land surface air temperature in NOAAGlobalTemp version 5. J. Clim. 2020, 33, 1351–1379. [Google Scholar] [CrossRef]
- World Meteorological Organization (WMO). State of the Global Climate 2023; WMO Report: Geneva, Switzerland, 2023; pp. 1–84. Available online: https://library.wmo.int/idurl/4/68236 (accessed on 1 May 2025).
- Lobell, D.B.; Schlenker, W.; Costa-Roberts, J. Climate trends and global crop production since 1980. Science 2011, 333, 616–620. [Google Scholar] [CrossRef] [PubMed]
- Sukanya, S.; Joseph, S. Climate change impacts on water resources: An overview. Vis. Tech. Clim. Change Mach. Learn. Artif. Intell. 2023, 4, 55–76. [Google Scholar] [CrossRef]
- Shangguan, M.; Dang, M.; Yue, Y.; Zou, R. A combined model to predict GNSS precipitable water vapor based on deep learning. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2023, 16, 4713–4723. [Google Scholar] [CrossRef]
- Lu, H.X.; Li, K.; Li, L.; He, Q.; Yu, H.; Dong, Z. Research on precipitable water vapor prediction method based on LightGBM algorithm. GNSS World China 2024, 49, 110–119. [Google Scholar] [CrossRef]
- Piao, S.; Ciais, P.; Huang, Y.; Shen, Z.; Peng, S.; Li, S.; Zhou, L.; Liu, H.; Ma, Y.; Ding, Y.; et al. The impacts of climate change on water resources and agriculture in China. Nature 2010, 467, 43–51. [Google Scholar] [CrossRef]
- Handoko, E.Y.; Syariz, M.A.; Hanansyah, M.P.; Kuryawati, P.; Wijayanti, R.F.; Karondia, L.A. Assessing drought related to global climate phenomena using Sentinel-3 SLSTR data around East Java, Indonesia. Res. Sq. 2025, 1–20. [Google Scholar] [CrossRef]
- Musyimi, P.K.; Sahbeni, G.; Timár, G.; Weidinger, T.; Székely, B. Analysis of short-term drought episodes using Sentinel-3 SLSTR data under a semi-arid climate in Lower Eastern Kenya. Remote Sens. 2023, 15, 3041. [Google Scholar] [CrossRef]
- Vörösmarty, C.J.; Green, P.; Salisbury, J.; Lammers, R.B. Global water resources: Vulnerability from climate change and population growth. Science 2000, 289, 284–288. [Google Scholar] [CrossRef] [PubMed]
Data | RMSE | MAE | MSE | R2 |
---|---|---|---|---|
(a) LSTM Model | ||||
A1 | 0.166 | 0.076 | 0.027 | 0.882 |
D1 | 0.105 | 0.081 | 0.011 | 0.879 |
D2 | 0.102 | 0.077 | 0.010 | 0.967 |
D3 | 0.185 | 0.097 | 0.034 | 0.941 |
D4 | 0.125 | 0.070 | 0.015 | 0.866 |
(b) GRU Model | ||||
A1 | 0.166 | 0.079 | 0.028 | 0.879 |
D1 | 0.089 | 0.066 | 0.007 | 0.914 |
D2 | 0.071 | 0.054 | 0.005 | 0.983 |
D3 | 0.103 | 0.045 | 0.010 | 0.981 |
D4 | 0.135 | 0.097 | 0.018 | 0.843 |
(c) TCN Model | ||||
A1 | 0.188 | 0.124 | 0.035 | 0.848 |
D1 | 0.079 | 0.056 | 0.006 | 0.932 |
D2 | 0.077 | 0.052 | 0.005 | 0.981 |
D3 | 0.113 | 0.075 | 0.012 | 0.978 |
D4 | 0.123 | 0.070 | 0.015 | 0.870 |
Model | RMSE | MAE | MAPE | MSE | R2 |
---|---|---|---|---|---|
WT-LSTM | 0.258 | 0.195 | 0.786 | 0.066 | 0.946 |
WT-GRU | 0.244 | 0.181 | 0.730 | 0.059 | 0.949 |
WT-TCN | 0.242 | 0.170 | 0.687 | 0.058 | 0.953 |
LSTM | 0.653 | 0.452 | 1.808 | 0.427 | 0.669 |
GRU | 0.704 | 0.499 | 2.003 | 0.495 | 0.615 |
TCN | 0.649 | 0.480 | 1.911 | 0.421 | 0.673 |
Model | RMSE | MAE | MAPE | MSE | R2 |
---|---|---|---|---|---|
(a) WT-LSTM Model | |||||
LSTM | −60.45 | −56.65 | −56.47 | −84.47 | 41.48 |
GRU | −63.33 | −60.92 | −60.77 | −86.67 | 53.73 |
TCN | −60.26 | −59.38 | −58.83 | −84.30 | 40.68 |
WT-GRU | 5.74 | 7.73 | 7.67 | 11.86 | −0.32 |
WT-TCN | 6.61 | 14.71 | 14.41 | 13.79 | −0.74 |
(b) WT-GRU Model | |||||
LSTM | −62.66 | −59.73 | −59.63 | −86.17 | 41.85 |
GRU | −65.31 | −63.53 | −63.47 | −88.12 | 54.34 |
TCN | −62.34 | −62.50 | −61.86 | −85.99 | 40.98 |
WT-LSTM | −5.43 | −7.18 | −7.12 | −10.61 | 0.32 |
WT-TCN | 0.82 | 6.47 | 6.26 | 1.72 | −0.42 |
(c) WT-TCN Model | |||||
LSTM | −63.04 | −62.72 | −61.94 | −86.42 | 42.45 |
GRU | −65.66 | −65.73 | −65.71 | −88.32 | 54.79 |
TCN | −62.71 | −64.58 | −64.02 | −86.21 | 41.65 |
WT-LSTM | −6.20 | −12.82 | −12.57 | −12.12 | 0.74 |
WT-GRU | −0.82 | −6.06 | −5.88 | −1.69 | 0.42 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Xu, L.; Mao, K.; Guo, Z.; Shi, J.; Bateni, S.M.; Yuan, Z. Analysis of Spatiotemporal Characteristics of Global TCWV and AI Hybrid Model Prediction. Hydrology 2025, 12, 206. https://doi.org/10.3390/hydrology12080206
Xu L, Mao K, Guo Z, Shi J, Bateni SM, Yuan Z. Analysis of Spatiotemporal Characteristics of Global TCWV and AI Hybrid Model Prediction. Hydrology. 2025; 12(8):206. https://doi.org/10.3390/hydrology12080206
Chicago/Turabian StyleXu, Longhao, Kebiao Mao, Zhonghua Guo, Jiancheng Shi, Sayed M. Bateni, and Zijin Yuan. 2025. "Analysis of Spatiotemporal Characteristics of Global TCWV and AI Hybrid Model Prediction" Hydrology 12, no. 8: 206. https://doi.org/10.3390/hydrology12080206
APA StyleXu, L., Mao, K., Guo, Z., Shi, J., Bateni, S. M., & Yuan, Z. (2025). Analysis of Spatiotemporal Characteristics of Global TCWV and AI Hybrid Model Prediction. Hydrology, 12(8), 206. https://doi.org/10.3390/hydrology12080206