浏览全部资源
扫码关注微信
纸质出版日期： 2020-10-07 ，
扫 描 看 全 文
张天一，苏华，杨欣，严晓海.2020.基于LightGBM的全球海洋次表层温盐遥感预测.遥感学报，24（10）： 1255-1269
Zhang T Y，Su H，Yang X and Yan X H 2020. Remote sensing prediction of global subsurface thermohaline and the impact of longitude and latitude based on LightGBM. Journal of Remote Sensing（Chinese）， 24（10）：1255-1269［DOI：10.11834/jrs.20200007］
随着卫星遥感技术的发展，越来越多的卫星观测数据被应用于预测海洋内部温盐结构信息，而如何有效提高海洋内部温盐信息的预测精度仍是一个挑战。本文应用LightGBM算法结合随机森林算法构建全球海洋次表层（0—1000 m）温度异常（STA）与盐度异常（SSA）的预测模型，模型使用海表卫星观测数据（海表高度异常（SSHA）、海表温度异常（SSTA）、海表盐度异常（SSSA）和海表风场异常水平和垂直分量（USSWA、VSSWA），结合经纬度信息（LON、LAT）作为预测变量，使用Argo次表层温盐数据作为模型训练与测试标记。本文使用五参数模型（SSTA、SSHA、SSSA、USSWA、VSSWA）、带纬度六参数模型（LAT、SSTA、SSHA、SSSA、USSWA、VSSWA）、带经度六参数模型（LON、SSTA、SSHA、SSSA、USSWA、VSSWA）与带经纬度七参数模型（LON、LAT、SSTA、SSHA、SSSA、USSWA、VSSWA）来着重分析LON与LAT在STA、SSA遥感预测中发挥的作用。结果表明LON与LAT在STA、SSA各自预测中发挥不同的作用。在单时相和时序预测STA中LON与LAT对模型的贡献随着深度的增加逐渐增大，而在单时相和时序预测SSA中LON与LAT对不同深度预测模型始终保持较大的贡献。在单时相预测STA与SSA中LON较LAT对模型贡献更大，而在时序预测STA与SSA中LAT较LON对模型贡献更大。经纬度信息是全球海洋次表层温盐机器学习预测的重要参数，可以提高模型的预测精度。同时，LightGBM较随机森林在预测海洋次表层温盐异常时精度更高鲁棒性更强。
Satellite observation data are increasingly used to derive and predict thermohaline information within the ocean due to the development of satellite technology. However
the effective improvement of prediction accuracy in satellite remote sensing is still challenging. A model with strong spatiotemporal applicability and high robustness for subsurface thermohaline estimation is necessary due to the complex and highly dynamic processes in the ocean.
In this study
a new LightGBM method combined with random forest algorithm is used to predict global subsurface temperature and salinity anomalies in the upper 1000 m depth based on remote sensing and Argo float data. The proposed method uses multisource sea surface parameters
including Sea Surface Height Anomaly (SSHA)
Sea Ssurface Temperature Anomaly (SSTA)
Sea Surface Salinity Anomaly (SSSA)
and northward and eastward components of sea surface wind anomaly (USSWA and VSSWA)
combined with longitude and latitude data (LON and LAT) as predictor variables and Argo gridded data as training and testing labels for model construction and prediction. This study creates five-parameter model (SSTA
SSHA
SSSA
USSWA
and VSSWA)
six-parameter model with latitude (LAT
SSTA
SSHA
SSSA
USSWA
and VSSWA)
six-parameter model with longitude (LON
SSTA
SSHA
SSSA
USSWA
and VSSWA)
and seven-parameter model with longitude and latitude (LON
LAT
SSTA
SSHA
SSSA
USSWA
and VSSWA) to analyze and evaluate the role of LON + LAT in STA and SSA prediction using LightGBM and RF models.
Using the monotemporal LightGBM model to predict STA
the average
R
2
of the seven-parameter model
six-parameter model with latitude
six-parameter model with longitude
five-parameter model is 0.980
0.922
0.937
0.776 and the average RMSE is 0.072 ℃
0.141 ℃
0.127 ℃
0.240 ℃. The average
R
2
in the SSA prediction is 0.963
0.846
0.872
0.545
and the average RMSE is 0.012 psu
0.025 psu
0.022 psu
0.042 psu. The average
R
2
of the seven-parameter model
six-parameter model with latitude
six-parameter model with longitude
five-parameter model when using time-series LightGBM model to predict STA is 0.703
0.655
0.585
0.523
and the average RMSE is 0.298 ℃
0.317 ℃
0.356 ℃
0.378 ℃. The average
R
2
in the SSA prediction is 0.426
0.277
0.197
0.103
and the average RMSE is 0.050 psu
0.057 psu
0.059 psu
0.064 psu. Hence
the seven-parameter model demonstrated the best performance. The maximum
R
2
and minimum RMSE in the seven-parameter LightGBM model are 0.992
0.981 and 0.022 ℃
0.004 psu in the monotemporal STA
SSA prediction. Meanwhile
the maximum
R
2
and minimum RMSE are 0.817
0.574 and 0.092 ℃
0.013 psu in the time-series STA
SSA prediction. The prediction accuracy of the model decreases gradually with increasing depth.
This study suggested that LON + LAT significantly contribute to both STA and SSA prediction
but differently impact on respective STA and SSA prediction. The contribution of LON + LAT to the model increases with depth in the monotemporal and time-series STA prediction while maintaining a large contribution to the model at different depths in the monotemporal and time-series SSA prediction. LON makes a larger contribution than LAT in the monotemporal STA and SSA prediction
while LAT plays a more significant role than LON in the time-series STA and SSA prediction. Furthermore
LightGBM outperforms RF and is more robust in the subsurface thermohaline prediction.
海洋次表层温盐异常LightGBM遥感预测经纬度
subsurface oceanthermohaline anomalyLightGBMremote sensing predictionlongitude and latitude
Ali M M, Swain D and Weller R A. 2004. Estimation of ocean subsurface thermal structure from surface parameters: a neural network approach. Geophysical Research Letters, 31(20): L20308 [DOI: 10.1029/2004gl021192http://dx.doi.org/10.1029/2004gl021192]
Balmaseda M A, Trenberth K E and Källén E. 2013. Distinctive climate signals in reanalysis of global ocean heat content. Geophysical Research Letters, 40(9): 1754-1759 [DOI: 10.1002/grl.50382http://dx.doi.org/10.1002/grl.50382]
Bao S L, Zhang R, Wang H Z, Yan H Q, Yu Y and Chen J. 2019. Salinity profile estimation in the Pacific Ocean from satellite Surface salinity observations. Journal of Atmospheric and Oceanic Technology, 36(1): 53-68 [DOI: 10.1175/JTECH-D-17-0226.1http://dx.doi.org/10.1175/JTECH-D-17-0226.1]
Breiman L. 2001. Random forests. Machine Learning, 45(1): 5-32 [DOI: 10.1023/A:1010933404324http://dx.doi.org/10.1023/A:1010933404324]
Chapman C and Charantonis A A. 2017. Reconstruction of subsurface velocities from satellite observations using iterative self-organizing maps. IEEE Geoscience and Remote Sensing Letters, 14(5): 617-620 [DOI: 10.1109/LGRS.2017.2665603http://dx.doi.org/10.1109/LGRS.2017.2665603]
Chen C, Yang K D, Ma Y L and Wang Y. 2018. Reconstructing the subsurface temperature field by using sea surface data through self-organizing map method. IEEE Geoscience and Remote Sensing Letters, 15(12): 1812-1816 [DOI: 10.1109/LGRS.2018.2866237http://dx.doi.org/10.1109/LGRS.2018.2866237]
Chen X Y and Tung K K. 2014. Varying planetary heat sink led to global-warming slowdown and acceleration. Science, 345(6199): 897-903 [DOI: 10.1126/science.1254937http://dx.doi.org/10.1126/science.1254937]
Cheng L J and Zhu J. 2014. Uncertainties of the ocean heat content estimation induced by insufficient vertical resolution of historical ocean subsurface observations. Journal of Atmospheric and Oceanic Technology, 31(6): 1383-1396 [DOI: 10.1175/JTECH-D-13-00220.1http://dx.doi.org/10.1175/JTECH-D-13-00220.1]
Cheng L J, Zhu J, Abraham J, Trenberth K E, Fasullo J T, Zhang B, Yu F J, Wan L Y, Chen X R and Song X Z. 2019. 2018 Continues record global ocean warming. Advances in Atmospheric Sciences, 36(3): 249-252 [DOI: 10.1007/s00376-019-8276-xhttp://dx.doi.org/10.1007/s00376-019-8276-x]
Ding Y H. 2016. Analysis of the process and mechanisms of genesis and development for 2014-2016 mega El Niño event. Transactions of Atmospheric Sciences, 39(6): 722-734
丁一汇. 2016. 2014—2016年超强El Niño事件的发生发展过程与机理分析. 大气科学学报, 39(6): 722-734 [DOI: 10.13878/j.cnki.dqkxxb.20161028003http://dx.doi.org/10.13878/j.cnki.dqkxxb.20161028003]
Fox D N, Teague W J, Barron C N, Carnes M R and Lee C M. 2002. The modular ocean data assimilation system (MODAS). Journal of Atmospheric and Oceanic Technology, 19(2): 240-252 [DOI: 10.1175/1520-0426(2002)019<0240:TMODAS>2.0.CO;2http://dx.doi.org/10.1175/1520-0426(2002)019<0240:TMODAS>2.0.CO;2]
Guo L K, Qi M, Finley T, Wang T F, Chen W, Ma W D, Ye Q W and Liu T Y. 2017. LightGBM: a highly efficient gradient boosting decision tree//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach, CA, USA: ACM: 3149-3157
Klemas V and Yan X H. 2014. Subsurface and deeper ocean remote sensing from satellites: an overview and new results. Progress in Oceanography, 122: 1-9 [DOI: 10.1016/j.pocean.2013.11.010http://dx.doi.org/10.1016/j.pocean.2013.11.010]
Li W E, Su H, Wang X Q and Yan X H. 2017. Estimation of global subsurface temperature anomaly based on multisource satellite observations. Journal of Remote Sensing, 21(6): 881-891
黎文娥, 苏华, 汪小钦, 严晓海. 2017. 多源卫星观测的全球海洋次表层温度异常信息提取. 遥感学报, 21(6): 881-891 [DOI: 10.11834/jrs.20177026http://dx.doi.org/10.11834/jrs.20177026]
Liu L. 2016. Ocean’s Interior Reconstruction from Satellite-derived Surface Information. Beijing: University of Chinese Academy of Sciences
刘磊. 2016. 利用卫星遥感海表信息对海洋内部状态的反演研究. 北京: 中国科学院大学
Lu W F, Su H, Yang X and Yan X H. 2019. Subsurface temperature estimation from remote sensing data using a clustering-neural network method. Remote Sensing of Environment, 229: 213-222 [DOI: 10.1016/j.rse.2019.04.009http://dx.doi.org/10.1016/j.rse.2019.04.009]
Maes C, Behringer D, Reynolds R W and Ji M. 2000. Retrospective analysis of the salinity variability in the western tropical pacific ocean using an indirect minimization approach. Journal of Atmospheric and Oceanic Technology, 17(4): 512-524 [DOI: 10.1175/1520-0426(2000)017<0512:RAOTSV>2.0.CO;2http://dx.doi.org/10.1175/1520-0426(2000)017<0512:RAOTSV>2.0.CO;2]
Meehl G A, Arblaster J M, Fasullo J T, Hu A X and Trenberth K E. 2011. Model-based evidence of deep-ocean heat uptake during surface-temperature hiatus periods. Nature Climate Change, 1(7): 360-364 [DOI: 10.1038/nclimate1229http://dx.doi.org/10.1038/nclimate1229]
Roemmich D and Gilson J. 2009. The 2004-2008 mean and annual cycle of temperature, salinity, and steric height in the global ocean from the Argo Program. Progress in Oceanography, 82(2): 81-100 [DOI: 10.1016/j.pocean.2009.03.004http://dx.doi.org/10.1016/j.pocean.2009.03.004]
Shen R P, Guo J, Zhang J X and Li L X. 2017. Construction of a drought monitoring model using the random forest based remote sensing. Journal of Geo-Information Science, 19(1): 125-133
沈润平, 郭佳, 张婧娴, 李洛晞. 2017. 基于随机森林的遥感干旱监测模型的构建. 地球信息科学学报, 19(1): 125-133 [DOI: 10.3724/SP.J.1047.2017.00125http://dx.doi.org/10.3724/SP.J.1047.2017.00125]
Su H, Li W and Yan X H. 2018. Retrieving temperature anomaly in the global subsurface and deeper ocean from satellite observations. Journal of Geophysical Research: Oceans, 123(1): 399-410 [DOI: 10.1002/2017JC013631http://dx.doi.org/10.1002/2017JC013631]
Su H, Wu X B, Lu W F, Zhang W W and Yan X H. 2017. Inconsistent subsurface and deeper ocean warming signals during recent global warming and hiatus. Journal of Geophysical Research: Oceans, 122(10): 8182-8195 [DOI: 10.1002/2016jc012481http://dx.doi.org/10.1002/2016jc012481]
Su H, Wu X B, Yan X H and Kidwell A. 2015. Estimation of subsurface temperature anomaly in the Indian Ocean during recent global surface warming hiatus from satellite measurements: a support vector machine approach. Remote Sensing of Environment, 160: 63-71 [DOI: 10.1016/j.rse.2015.01.001http://dx.doi.org/10.1016/j.rse.2015.01.001]
Su H, Yang X, Lu W F and Yan X H. 2019. Estimating subsurface thermohaline structure of the global ocean using surface remote sensing observations. Remote Sensing, 11(13): 1598 [DOI: 10.3390/rs11131598http://dx.doi.org/10.3390/rs11131598]
Wang G J, Cheng L J, Abraham J and Li C Y. 2017. Consensuses and discrepancies of basin-scale ocean heat content changes in different ocean analyses. Climate Dynamics, 50(7): 2471-2487 [DOI: 10.1007/s00382-017-3751-5http://dx.doi.org/10.1007/s00382-017-3751-5]
Wang J B, Flierl G R, LaCasce J H, McClean J L and Mahadevan A. 2013. Reconstructing the ocean’s interior from surface data. Journal of Physical Oceanography, 43(8): 1611-1626 [DOI: 10.1175/JPO-D-12-0204.1http://dx.doi.org/10.1175/JPO-D-12-0204.1]
Wu X B, Yan X H, Jo Y H and Liu W T. 2012. Estimation of subsurface temperature anomaly in the north Atlantic using a self-organizing map neural network. Journal of Atmospheric and Oceanic Technology, 29(11): 1675-1688 [DOI: 10.1175/jtech-d-12-00013.1http://dx.doi.org/10.1175/jtech-d-12-00013.1]
Yang X, Su H, Li W E, Huang L J, Wang X Q and Yan X H. 2019. Seasonal-spatial variations in satellite-derived global subsurface temperature anomalies. Journal of Remote Sensing, 23(5): 997-1010
杨欣, 苏华, 黎文娥, 黄琳瑾, 汪小钦, 严晓海. 2019. 全球海洋次表层温度异常遥感反演的季节时空变化特征. 遥感学报, 23(5): 997-1010 [DOI: 10.11834/jrs.20198391http://dx.doi.org/10.11834/jrs.20198391]
Zhao S Y, An R and Zhu M R. 2019. Urban change detection by aerial remote sensing using combining features of pixel-depth-object. Acta Geodaetica et Cartographica Sinica, 48(11): 1452-1463
赵生银, 安如, 朱美如. 2019. 联合像元—深度—对象特征的遥感图像城市变化检测. 测绘学报, 48(11): 1452-1463
相关文章
相关作者
相关机构
京公网安备11010802024621