Earth Science Frontiers ›› 2024, Vol. 31 ›› Issue (6): 450-461.DOI: 10.13745/j.esf.sf.2024.5.30
Previous Articles Next Articles
LIANG Wenxiang1,2(), LUO Zhen3, CHEN Fulong1,2,*(
), WANG Tongxia1,2, AN Jie1,2, LONG Aihua1,4, HE Chaofei1,2
Received:
2023-12-22
Revised:
2024-04-02
Online:
2024-11-25
Published:
2024-11-25
Contact:
CHEN Fulong
CLC Number:
LIANG Wenxiang, LUO Zhen, CHEN Fulong, WANG Tongxia, AN Jie, LONG Aihua, HE Chaofei. Simulation and prediction of inland river runoff based on CMIP6 multi-model ensemble[J]. Earth Science Frontiers, 2024, 31(6): 450-461.
数据类型 | 数据名称 | 数据描述 | 来源 |
---|---|---|---|
历史实测数据 | 径流、降水、气温和 蒸发数据 | 肯斯瓦特水文站2000—2014年 实测数据 | 石河子市水文勘测局 |
CMIP6模式数据 (2024—2030年) | 历史数据 | 时间长度为2000—2014年 | https://esgf-node.llnl.gov/projects/cmip6/ |
SSP1-2.6 | 未来情景数据:低强迫情景,辐射 强迫在2100年达到2.6 W/m2 | ||
SSP2-4.5 | 未来情景数据:中等辐射强迫情景, 辐射强迫在2100年达到4.5 W/m2 | ||
SSP5-8.5 | 未来情景数据:高强迫情景,辐射 强迫在2100年达到4.5 W/m2 | ||
预报因子 (2000—2014年) | 大气环流因子 | 北半球极涡面积指数、西藏高原 (30°~40°N,75°~105°E)、冷空气、太阳黑子 | 国家气候中心 ( |
海温因子 | 东大西洋/俄罗斯西部(NOAA)、全球 平均陆地/海洋温度指数、北极涛动 | NOAA气候预测中心 ( |
Table 1 Details of the observation data
数据类型 | 数据名称 | 数据描述 | 来源 |
---|---|---|---|
历史实测数据 | 径流、降水、气温和 蒸发数据 | 肯斯瓦特水文站2000—2014年 实测数据 | 石河子市水文勘测局 |
CMIP6模式数据 (2024—2030年) | 历史数据 | 时间长度为2000—2014年 | https://esgf-node.llnl.gov/projects/cmip6/ |
SSP1-2.6 | 未来情景数据:低强迫情景,辐射 强迫在2100年达到2.6 W/m2 | ||
SSP2-4.5 | 未来情景数据:中等辐射强迫情景, 辐射强迫在2100年达到4.5 W/m2 | ||
SSP5-8.5 | 未来情景数据:高强迫情景,辐射 强迫在2100年达到4.5 W/m2 | ||
预报因子 (2000—2014年) | 大气环流因子 | 北半球极涡面积指数、西藏高原 (30°~40°N,75°~105°E)、冷空气、太阳黑子 | 国家气候中心 ( |
海温因子 | 东大西洋/俄罗斯西部(NOAA)、全球 平均陆地/海洋温度指数、北极涛动 | NOAA气候预测中心 ( |
模式名称 | 国家 | 所属机构 | 水平分辨率 |
---|---|---|---|
BCC-CSM2-MR | 中国 | 国家(北京)气候中心(BCC) | 1.125°×1.1° |
CanESM5 | 加拿大 | 加拿大气候建模和分析中心(CCCma) | 2.8°×2.8° |
EC-Earth3 | 欧盟 | 欧共体地球联合会(EC) | 0.7°×0.7° |
FGOALS-gs | 中国 | 中国科学院大气物理研究所(CAS) | 2.0°×2.0° |
GFDL-ESM4 | 美国 | 美国国家海洋和大气管理局地球物理流体动力学实验室(GFDL) | 1.25°×1° |
IPSL-CM6A-LR | 法国 | 皮埃尔—西蒙拉普拉斯学院(IPSL) | 2.5°×1.26° |
MPI-ESM1-2-HR | 德国 | 马克斯普朗克气象研究所(MPI-M) | 1.875°×1.875° |
MRI-ESM2-0 | 日本 | 日本气象厅气象研究所(JMA) | 1.125°×1.125° |
Table 2 Overview of 8 GCMs in CMIP6 mode
模式名称 | 国家 | 所属机构 | 水平分辨率 |
---|---|---|---|
BCC-CSM2-MR | 中国 | 国家(北京)气候中心(BCC) | 1.125°×1.1° |
CanESM5 | 加拿大 | 加拿大气候建模和分析中心(CCCma) | 2.8°×2.8° |
EC-Earth3 | 欧盟 | 欧共体地球联合会(EC) | 0.7°×0.7° |
FGOALS-gs | 中国 | 中国科学院大气物理研究所(CAS) | 2.0°×2.0° |
GFDL-ESM4 | 美国 | 美国国家海洋和大气管理局地球物理流体动力学实验室(GFDL) | 1.25°×1° |
IPSL-CM6A-LR | 法国 | 皮埃尔—西蒙拉普拉斯学院(IPSL) | 2.5°×1.26° |
MPI-ESM1-2-HR | 德国 | 马克斯普朗克气象研究所(MPI-M) | 1.875°×1.875° |
MRI-ESM2-0 | 日本 | 日本气象厅气象研究所(JMA) | 1.125°×1.125° |
模型分类 | 模型名称 | 模型简写 |
---|---|---|
单一模型 | LSTM | Model.L |
SVM | Model.S | |
RFR | Model.R | |
分解—模拟—重构模型 | VMD-LSTM | Model.VL |
VMD-SVM | Model.VS | |
VMD-RFR | Model.VR | |
EMSD-LSTM | Model.EL | |
EMSD-SVM | Model.ES | |
EMSD-RFR | Model.ER | |
分解—模拟—优化— 重构模型 | VMD-LSTM-EnKF | Model.VLE |
VMD-SVM-EnKF | Model.VSE | |
VMD-RFR-EnKF | Model.VRE | |
EMSD-LSTM-EnKF | Model.ELE | |
EMSD-SVM-EnKF | Model.ESE | |
EMSD-RFR-EnKF | Model.ERE |
Table 3 Model classification and abbreviation
模型分类 | 模型名称 | 模型简写 |
---|---|---|
单一模型 | LSTM | Model.L |
SVM | Model.S | |
RFR | Model.R | |
分解—模拟—重构模型 | VMD-LSTM | Model.VL |
VMD-SVM | Model.VS | |
VMD-RFR | Model.VR | |
EMSD-LSTM | Model.EL | |
EMSD-SVM | Model.ES | |
EMSD-RFR | Model.ER | |
分解—模拟—优化— 重构模型 | VMD-LSTM-EnKF | Model.VLE |
VMD-SVM-EnKF | Model.VSE | |
VMD-RFR-EnKF | Model.VRE | |
EMSD-LSTM-EnKF | Model.ELE | |
EMSD-SVM-EnKF | Model.ESE | |
EMSD-RFR-EnKF | Model.ERE |
训练期 | 验证期 | |||||||
---|---|---|---|---|---|---|---|---|
模型类型 | R2 | NSE | RMSE | TPE | R2 | NSE | RMSE | TPE |
Model.L | 0.986 4 | 0.983 3 | 7.299 2 | 0.107 8 | 0.781 4 | 0.777 5 | 25.497 7 | 0.289 1 |
Model.S | 0.818 3 | 0.808 1 | 24.714 8 | 0.287 4 | 0.748 5 | 0.732 7 | 27.937 4 | 0.375 6 |
Model.R | 0.995 1 | 0.994 7 | 4.094 5 | 0.040 1 | 0.773 2 | 0.762 2 | 26.355 9 | 0.307 8 |
Table 4 Comparison table of runoff simulation results based on a single model
训练期 | 验证期 | |||||||
---|---|---|---|---|---|---|---|---|
模型类型 | R2 | NSE | RMSE | TPE | R2 | NSE | RMSE | TPE |
Model.L | 0.986 4 | 0.983 3 | 7.299 2 | 0.107 8 | 0.781 4 | 0.777 5 | 25.497 7 | 0.289 1 |
Model.S | 0.818 3 | 0.808 1 | 24.714 8 | 0.287 4 | 0.748 5 | 0.732 7 | 27.937 4 | 0.375 6 |
Model.R | 0.995 1 | 0.994 7 | 4.094 5 | 0.040 1 | 0.773 2 | 0.762 2 | 26.355 9 | 0.307 8 |
训练期 | 验证期 | |||||||
---|---|---|---|---|---|---|---|---|
模型类型 | R2 | NSE | RMSE | TPE | R2 | NSE | RMSE | TPE |
Model.VR | 0.803 3 | 0.788 4 | 25.952 5 | 0.314 2 | 0.787 0 | 0.782 0 | 25.242 6 | 0.321 7 |
Model.VS | 0.835 2 | 0.828 3 | 23.369 7 | 0.305 5 | 0.825 1 | 0.821 8 | 22.815 5 | 0.307 8 |
Model.VL | 0.963 8 | 0.961 7 | 11.290 6 | 0.143 3 | 0.845 5 | 0.799 0 | 21.975 9 | 0.300 4 |
Model.ER | 0.993 3 | 0.992 9 | 4.759 7 | 0.053 8 | 0.789 3 | 0.756 2 | 26.136 2 | 0.348 0 |
Model.ES | 0.992 0 | 0.991 7 | 5.247 3 | 0.070 9 | 0.787 1 | 0.782 3 | 25.213 4 | 0.303 8 |
Model.EL | 0.978 5 | 0.973 7 | 9.149 9 | 0.151 2 | 0.794 9 | 0.794 2 | 24.517 1 | 0.274 8 |
Table 5 Comparison of runoff simulation results based on decomposition-simulation-reconstruction model
训练期 | 验证期 | |||||||
---|---|---|---|---|---|---|---|---|
模型类型 | R2 | NSE | RMSE | TPE | R2 | NSE | RMSE | TPE |
Model.VR | 0.803 3 | 0.788 4 | 25.952 5 | 0.314 2 | 0.787 0 | 0.782 0 | 25.242 6 | 0.321 7 |
Model.VS | 0.835 2 | 0.828 3 | 23.369 7 | 0.305 5 | 0.825 1 | 0.821 8 | 22.815 5 | 0.307 8 |
Model.VL | 0.963 8 | 0.961 7 | 11.290 6 | 0.143 3 | 0.845 5 | 0.799 0 | 21.975 9 | 0.300 4 |
Model.ER | 0.993 3 | 0.992 9 | 4.759 7 | 0.053 8 | 0.789 3 | 0.756 2 | 26.136 2 | 0.348 0 |
Model.ES | 0.992 0 | 0.991 7 | 5.247 3 | 0.070 9 | 0.787 1 | 0.782 3 | 25.213 4 | 0.303 8 |
Model.EL | 0.978 5 | 0.973 7 | 9.149 9 | 0.151 2 | 0.794 9 | 0.794 2 | 24.517 1 | 0.274 8 |
训练期 | 验证期 | |||||||
---|---|---|---|---|---|---|---|---|
模型类型 | R2 | NSE | RMSE | TPE | R2 | NSE | RMSE | TPE |
Model.VRE | 0.830 6 | 0.788 5 | 25.946 4 | 0.313 9 | 0.797 6 | 0.791 4 | 24.684 5 | 0.314 2 |
Model.VSE | 0.834 3 | 0.827 7 | 23.424 9 | 0.307 3 | 0.831 4 | 0.828 7 | 22.366 9 | 0.297 3 |
Model.VLE | 0.971 8 | 0.969 2 | 9.900 6 | 0.137 7 | 0.861 9 | 0.821 4 | 22.818 5 | 0.276 5 |
Model.ERE | 0.993 3 | 0.992 9 | 4.770 3 | 0.054 5 | 0.818 1 | 0.765 4 | 21.653 7 | 0.313 2 |
Model.ESE | 0.991 6 | 0.991 3 | 5.251 1 | 0.073 0 | 0.788 9 | 0.784 1 | 25.112 0 | 0.315 0 |
Model.ELE | 0.978 5 | 0.972 6 | 9.340 4 | 0.155 4 | 0.801 9 | 0.800 9 | 24.111 0 | 0.260 5 |
Table 6 Comparison of runoff simulation results based on decomposition-simulation-optimization-reconstruction model
训练期 | 验证期 | |||||||
---|---|---|---|---|---|---|---|---|
模型类型 | R2 | NSE | RMSE | TPE | R2 | NSE | RMSE | TPE |
Model.VRE | 0.830 6 | 0.788 5 | 25.946 4 | 0.313 9 | 0.797 6 | 0.791 4 | 24.684 5 | 0.314 2 |
Model.VSE | 0.834 3 | 0.827 7 | 23.424 9 | 0.307 3 | 0.831 4 | 0.828 7 | 22.366 9 | 0.297 3 |
Model.VLE | 0.971 8 | 0.969 2 | 9.900 6 | 0.137 7 | 0.861 9 | 0.821 4 | 22.818 5 | 0.276 5 |
Model.ERE | 0.993 3 | 0.992 9 | 4.770 3 | 0.054 5 | 0.818 1 | 0.765 4 | 21.653 7 | 0.313 2 |
Model.ESE | 0.991 6 | 0.991 3 | 5.251 1 | 0.073 0 | 0.788 9 | 0.784 1 | 25.112 0 | 0.315 0 |
Model.ELE | 0.978 5 | 0.972 6 | 9.340 4 | 0.155 4 | 0.801 9 | 0.800 9 | 24.111 0 | 0.260 5 |
[1] |
陈亚宁, 李稚, 范煜婷, 等. 西北干旱区气候变化对水文水资源影响研究进展[J]. 地理学报, 2014, 69(9): 1295-1304.
DOI |
[2] |
骆成彦, 陈伏龙, 何朝飞, 等. CMADS在玉龙喀什河径流模拟中的适用性研究[J]. 干旱区研究, 2022, 39(4): 1090-1101.
DOI |
[3] | MALIK M A, DAR A Q, JAIN M K. Modelling streamflow using the SWAT model and multi-site calibration utilizing SUFI-2 of SWAT-CUP model for high altitude catchments, NW Himalaya’s[J]. Modeling Earth Systems and Environment, 2022, 8(1): 1203-1213. |
[4] | 黄平, 赵吉国. 流域分布型水文数学模型的研究及应用前景展望[J]. 水文, 1997(5): 6-11. |
[5] | HU C H, WU Q, LI H, et al. Deep learning with a long short-term memory networks approach for rainfall-runoff simulation[J]. Water, 2018, 10(11): 1543. |
[6] | 祁继霞, 粟晓玲, 张更喜, 等. VMD-LSTM模型对不同预见期月径流的预测研究[J]. 干旱地区农业研究, 2022, 40(6): 258-267. |
[7] | CHEN Y C, GAO J J, BIN Z H, et al. Application study of IFAS and LSTM models on runoff simulation and flood prediction in the Tokachi River basin[J]. Journal of Hydroinformatics, 2021, 23(5): 1098-1111. |
[8] | ZHANG L Y Z, PANG B, XU Z X, et al. Assessment on the applicability of support vector machine-based models for runoff simulation in Shiyang River basin[J]. Journal of Arid Land Resources and Environment, 2013, 27(7): 113-118. |
[9] |
蔡文静, 陈伏龙, 何朝飞, 等. 基于时频分析的LSTM组合模型径流预测[J]. 干旱区地理, 2021, 44(6): 1696-1706.
DOI |
[10] | 包苑村, 解建仓, 罗军刚. 基于VMD-CNN-LSTM模型的渭河流域月径流预测[J]. 西安理工大学学报, 2021, 37(1): 1-8. |
[11] | 吕晗芳, 赵雪花, 桑宇婷, 等. 基于VMD-LSSVM的月径流预测方法研究[J]. 中国农村水利水电, 2020(8): 166-170, 176. |
[12] | 岳延兵, 李致家, 范敏. 集合卡尔曼滤波与神经网络融合的洪水预报研究[J]. 水力发电学报, 2014, 33(1): 23-28. |
[13] |
钱玉霞, 陈伏龙, 何朝飞, 等. “分解—校正—集成” 模式下基于深度信念网络模型的径流预测[J]. 长江科学院院报, 2024, 41(5): 35-44.
DOI |
[14] |
何朝飞, 骆成彦, 陈伏龙, 等. 基于CMIP6多模式的和田河流域未来气候变化预估[J]. 地学前缘, 2023, 30(3): 515-528.
DOI |
[15] | 任锦豪, 乔长录, 赵进勇, 等. 基于主成分分析法的玛纳斯河水文情势分析[J]. 水电能源科学, 2022, 40(1): 25-29. |
[16] | HAMED M M, NASHWAN M S, SHAHID S. Inter-comparison of historical simulation and future projections of rainfall and temperature by CMIP5 and CMIP6 GCMs over Egypt[J]. International Journal of Climatology, 2022, 42(8): 4316-4332. |
[17] | EVENSEN G. Sequential data assimilation with a nonlinear quasi-geostrophic model using Monte Carlo methods to forecast error statistics[J]. Journal of Geophysical Research: Oceans, 1994, 99(C5): 10143-10162. |
[18] |
柳梅英, 包安明, 陈曦, 等. 近30年玛纳斯河流域土地利用/覆被变化对植被碳储量的影响[J]. 自然资源学报, 2010, 25(6): 926-938.
DOI |
[19] | 杨莲梅, 关学锋, 张迎新. 亚洲中部干旱区降水异常的大气环流特征[J]. 干旱区研究, 2018, 35(2): 249-259. |
[20] | ZOSSO D, DRAGOMIRETSKIY K. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544. |
[21] | 李文武, 石强, 王凯, 等. 基于变分模态分解和深度门控网络的径流预测[J]. 水力发电学报, 2020, 39(3): 34-44. |
[22] | 李继清, 王爽, 黄婧, 等. 应用极点对称模态分解分析径流时空演化规律[J]. 水力发电学报, 2020, 39(7): 73-87. |
[23] | 殷兆凯, 廖卫红, 王若佳, 等. 基于长短时记忆神经网络(LSTM)的降雨径流模拟及预报[J]. 南水北调与水利科技, 2019, 17(6): 1-9, 27. |
[24] | LIU P, WANG J, SANGAIAH A K, et al. Analysis and prediction of water quality using LSTM deep neural networks in IoT environment[J]. Sustainability, 2019, 11(7): 2058. |
[25] | 汪嘉杨, 王文圣, 李祚泳, 等. 基于TS-SVM模型的水安全评价[J]. 水资源保护, 2010, 26(2): 1-4, 9. |
[26] | 钟登华, 田耕, 关涛, 等. 基于混沌时序—随机森林回归的堆石坝料加水量预测研究[J]. 水力发电学报, 2018, 37(8): 1-12. |
[27] | EVENSEN G. Sampling strategies and square root analysis schemes for the EnKF[J]. Ocean Dynamics, 2004, 54(6): 539-560. |
[28] | TONG Y, GAO X J, HAN Z Y, et al. Bias correction of temperature and precipitation over China for RCM simulations using the QM and QDM methods[J]. Climate Dynamics, 2021, 57(5): 1425-1443. |
[29] |
赵梦霞, 苏布达, 姜彤, 等. CMIP6模式对黄河上游降水的模拟及预估[J]. 高原气象, 2021, 40(3): 547-558.
DOI |
[1] | WANG Pengshou, XU Min, HAN Haidong, LI Zhenzhong, SONG Xuanyu, ZHOU Weiyong. Response of glacier mass balance and meltwater runoff to climate change in the Akesu River Basin, southern Tianshan [J]. Earth Science Frontiers, 2024, 31(2): 435-446. |
[2] | SONG Xuanyu, XU Min, KANG Shichang, SUN Liping. Modeling of hydrological processes in cryospheric watersheds based on machine learning [J]. Earth Science Frontiers, 2023, 30(4): 451-469. |
[3] | XIA Dunsheng, YANG Junhuai, WANG Shuyuan, LIU Xin, CHEN Zixuan, ZHAO Lai, NIU Xiaoyi, JIN Ming, GAO Fuyuan, LING Zhiyong, WANG Fei, LI Zaijun, WANG Xin, JIA Jia, YANG Shengli. Aeolian deposits in the Yarlung Zangbo River basin, southern Tibetan Plateau: Spatial distribution, depositional model and environmental impact [J]. Earth Science Frontiers, 2023, 30(4): 229-244. |
[4] | HE Chaofei, LUO Chengyan, CHEN Fulong, LONG Aihua, TANG Hao. CMIP6 multi-model prediction of future climate change in the Hotan River Basin [J]. Earth Science Frontiers, 2023, 30(3): 515-528. |
[5] | SUN Hui, LIU Xiaodong. Numerical simulation of the climate effects of the Tibetan Plateau uplift: A review of research advances [J]. Earth Science Frontiers, 2022, 29(5): 300-309. |
[6] | HU Zhaobin, WEI Jiangong, XIE Zhiyuan, ZHANG Huodai, ZHONG Guangfa. Research progress in global sea level change: A critical review on international ocean drilling [J]. Earth Science Frontiers, 2022, 29(4): 10-24. |
[7] | LIU Zhifei, CHEN Jianfang, SHI Xuefa. Deep-sea sediments and global change: Research frontiers and challenges [J]. Earth Science Frontiers, 2022, 29(4): 1-9. |
[8] | NI Yanhua, LI Minghui, FANG Xiaomin, MENG Fanwei, YAN Maodu, LIU Yingxin. Paleotemperature during the Mid-Pleistocene Transition in western Qaidam Basin: Evidence from fluid inclusions in halite from drill hole SG-1 [J]. Earth Science Frontiers, 2021, 28(6): 115-124. |
[9] | S.K.KRIVONOGOV, T.I.KENSHINBAY, R.Kh.KURMANBAEV, B.S.KARIMOVA. The key question of the Aral Sea evolution important for understanding its economic, social and ecological values [J]. Earth Science Frontiers, 2021, 28(6): 196-204. |
[10] | WANG Jun, ZHANG Xiao, GAO Yan. The relationships between vegetation dynamics and environmental factors on the Qinghai-Tibet Plateau: A review of research progress and prospect [J]. Earth Science Frontiers, 2021, 28(4): 70-82. |
[11] | GUAN Kaiping,TIAN Li,AN Zhihui,YE Qin,,HU Jun,TONG Jinnan. Stratigraphic succession of the Nanhuan Period in the Shennongjia area in western Hubei and its regional correlation. [J]. Earth Science Frontiers, 2016, 23(6): 236-245. |
[12] | YAN Li-Juan, ZHENG Mian-Beng, WEI Le-Jun. Change of the lakes in Tibetan Plateau and its response to climate in the past forty years. [J]. Earth Science Frontiers, 2016, 23(4): 310-323. |
[13] | TU Chao, YANG Zhong-Fang, HOU Jing-Xie, JIA Hua-Ji, ZONG Sai-Feng, LI Biao. Distribution and influencing factors of paddy soil organic carbon content in Chinas major farming areas. [J]. Earth Science Frontiers, 2011, 18(6): 11-19. |
[14] | DAI Shuang, HUANG Yong-Bei, DIAO Jie, SHU Jiang, LIU Dun-Wei, KONG Li, ZHANG Meng-Shen, HU Hong-Fei. The climate change during 1281111905 Ma recorded by the susceptibility of the sediments of Liupanshan Group. [J]. Earth Science Frontiers, 2010, 17(3): 242-249. |
[15] | CHENG Zun-Lan, TIAN Jin-Chang, ZHANG Zheng-Bei, JIANG Ba. Debris flow induced by glaciallake break in Southeast Tibet. [J]. Earth Science Frontiers, 2009, 16(6): 207-214. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||