Anterior|Siguiente

Downscaling of Landsat 8 land surface temperature products based on deep learning

  • role： First author第一作者
  • Affiliation：

    Anhui Key Laboratory of Wetland Ecological Protection and Restoration, Anhui University, Hefei 230601, China

  • Email：shsh4603zyz@163.com
  • Introduction：张义峥，1997年生，女，硕士研究生，研究方向为地表温度降尺度。E-mail： shsh4603zyz@163.com
ZHANG Yizheng1,  
  • role： Corresponding author通信作者
  • Affiliation：

    Anhui Key Laboratory of Wetland Ecological Protection and Restoration, Anhui University, Hefei 230601, China

    Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui University, Hefei 230601, China

  • Email：wuph@ahu.edu.cn
  • Introduction：吴鹏海，1987年生，男，副教授，研究方向为遥感地表温度智能重建与融合。E-mail：wuph@ahu.edu.cn
WU Penghai12*,  
  • Affiliation：

    Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, China

DUAN Sibo3,  
  • Affiliation：

    Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui University, Hefei 230601, China

YANG Hui2,  
  • Affiliation：

    Anhui Key Laboratory of Wetland Ecological Protection and Restoration, Anhui University, Hefei 230601, China

YIN Zhixiang1

resumen

The downscaling method using spectral index as trend surface factor is widely used in remote sensing land surface temperature scale conversion. However, it is difficult to highlight the distribution of land surface temperature and describe the complex relationship between trend surface factor and land surface temperature in statistical model. Therefore, this paper constructs a Land Surface Temperature Downscaling Residual Network (LSTDRN) taking Landsat 8 ARD LST as downscaling objects and Landsat 8 OLI raw data as potential trend surface factors. The LSTDRN aims to explore the trend surface bands or combinations suitable for spatial downscaling of Landsat 8 land surface temperature products, and verify the spatiotemporal applicability of the model.In view of the strong nonlinear relationship fitting and feature extraction ability of deep learning, this paper proposes a LST downscaling model based on deep learning. In the training stage, the relationship model between the Landsat 8 ARD LST and all bands of Landsat 8 OLI (except band 9) is fitted at the low resolution level. The Huber loss function is used to minimize the residual between the prediction results and the label to realize the transformation residual constraint. Then the optimal model is obtained through iterative learning and parameter adjustment. In the test stage, the optimal model is applied at the high resolution level to obtain the final downscaling results according to the “scale invariant” hypothesis of land surface temperature downscaling. In addition to visual evaluation, the downscaling results and original LST data were scaled up to 100 m resolution for quantitative evaluation. After evaluating the downscaling effect of each band, the multi-trend surface factor downscaling experiment was carried out. Meanwhile, the deep learning method is compared with the classic traditional method TsHARP to compare the stability of different land surface types and different seasons.In LSTDRN, using the original single band of Landsat 8 OLI as the trend surface factor has a good downscaling effect, and increasing the number of potential trend surface factors can not improve the downscaling effect. In the experiments of different land cover types, the effect of deep learning method is better than that of traditional methods, and the best effect is when NIR band is the trend surface factor. The order of deep learning downscaling effect in quantitative evaluation of different land cover types is vegetation > building > water, however, there is no obvious difference between the traditional methods. In different season experiments, the downscaling effect in quantitative evaluation of deep learning method in spring, summer and winter is better than that of traditional classical methods, and the downscaling results of the two methods in autumn are similar. Therefore, the proposed LSTDRN has better downscaling effect on Landsat 8 remote sensing land surface temperature products, which is superior to the traditional classical methods and has stronger stability.The LSTDRN proposed in this study can make good use of Landsat 8 OLI single band data as trend surface factors for downscaling. With the increase of trend surface factors, the downscaling effect is not significantly improved. Compared with the classic traditional method TsHARP, the downscaling effect of deep learning method is less affected by land cover types and seasonal factors, and the difference of downscaling effect is rather small in different spatial-temporal conditions. The method has stronger stability, which is conducive to enhancing the applicability of downscaling research and promoting the application of high-quality land surface temperature data.

palabra clave

remote sensing;land surface temperature;downscaling;Landsat 8;deep learning;trend surface

References

  1. 1.
    Agam N, Kustas W P, Anderson M C, Li F and Neale CMU. 2007. A vegetation index based technique for spatial sharpening of thermal imagery. Remote Sensing of Environment, 107(4):545-558.
  2. 2.
    Duan S B and Li Z L. 2016. Spatial downscaling of MODIS land surface temperatures using geographically weighted regression: Case study in Northern China, IEEE Trans. Geosci. Remote Sens, 54(11): 6458-6469
  3. 3.
    Duan S B, Ru C, Li Z L, Wang M M, Xu H Q, Li H, Wu P H, Zhan W F, Zhou J, Zhao W, Ren H Z, Wu H, Tang B H, Zhang X, Shang Guo F and Qin Z H. 2021. Reviews of methods for land surface temperature retrieval from Landsat thermal infrared data. National Remote Sensing Bulletin, 25(8): 1591-1617
  4. 4.
    Ebrahimy H and Azadbakht M . 2019. Downscaling MODIS land surface temperature over a heterogeneous area: An investigation of machine learning techniques, feature selection, and impacts of mixed pixels. Computers & Geosciences, 124:93-102
  5. 5.
    Guo H M, Gong A D, He R Y and Jiang J B. 2015. Spatial Downscaling Research of the Remotely Land Surface Temperature. Remote Sensing Information, 000(004):29-36
  6. 6.
    Hua J W, Zhu S Y and Zhang G Ｘ. 2018. Downscaling land surface temperature based on random forest algorithm. Remote Sensing for Land and Resources, 30(1):78-86
  7. 7.
    Hutengs C and Vohland M. 2016. Downscaling land surface temperatures at regional scales with random forest regression. Remote Sensing of Environment, 178:127-141
  8. 8.
    Li W, Niu L, Chen H and Wu H. 2020. Robust downscaling method of land surface temperature by using random forest algorithm. Journal of Geo-information Science, 2020,22(8):1666-1678
  9. 9.
    Li X J, Xin X Z, Jiang T and Zhang H L. 2017. Spatial Downscaling Research of Satellite Land Surface Temperature Based on Spectral Normalization Index. Acta Geodaetica et Cartographica Sinica ,46(3):353-361
  10. 10.
    Li Z L, Duan S B, Tang B H, Wu H, Ren H Z, Yan G J, Tang R L and Leng P. 2016. Review of methods for land surface temperature derived from thermal infrared remotely sensed data.Journal of Remote Sensing, 20(5): 899-920
  11. 11.
    Liu Q H, Xu X R and Chen J Y. 1998. The Retrieval of Land Surface Temperature and Emissivity by Remote Sensing Data: Theory and Digital Simulation, 2(1):1-9
  12. 12.
    Liu Y, Zhu R, Qian J X, Dang C Y and Yue H. 2020. Land Surface Temperature Downscaling Based on Multiple Factors. Remote Sensing Information. 35(06):6-18
  13. 13.
    Luo X B, Wang S M, Gao Y H and Chen Y. 2020. Research on downscaling algorithm of land surface temperature based on the non-linear geographically weighted model. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 32(06):1003-1011
  14. 14.
    Mukherjee S, Joshi P K and Garg R D. 2015. Regression-Kriging Technique to Downscale Satellite-Derived Land Surface Temperature in Heterogeneous Agricultural Landscape. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(3):1-1 [ DOI:10.1109/JSTARS.2015.2396032]
  15. 15.
    Peng Y D, Li W S, Luo X B and Li H. 2019. A Geographically and Temporally Weighted Regression Model for Spatial Downscaling of MODIS Land Surface Temperatures Over Urban Heterogeneous Regions, IEEE transactions on geoscience and remote sensing: a publication of the IEEE Geoscience and Remote Sensing Society, 57(7):5012-5027
  16. 16.
    Quan J L, Zhan W F, Chen Y H and Liu W Y. 2013. Downscaling remotely sensed land surface temperatures: A comparison of typical methods. Journal of Remote Sensing, 17(2) : 361-387
  17. 17.
    Wang Y T, Xie D H and Li Y H. 2014. Downscaling remotely sensed land surface temperature over urban areas using trend surface of spectral index. Journal of Remote Sensing, 18(6):1169-1181
  18. 18.
    Wang Z H, Qin Q M, Sun Y H, Zhang T Y and Ren H Z. 2018. Downscaling of Remotely Sensed Land Surface Temperature with the BP Neural Network. Remote Sensing Technology and Application, 2018, 33(5): 793-802
  19. 19.
    Wu J H, Zhong B, Tian S F, Yang A X and Wu J J. 2019. Downscaling of Urban Land Surface Temperature Based on Multi-Factor Geographically Weighted Regression, Selected Topics in Applied Earth Observations and Remote Sensing, IEEE Journal of, 2019, 12(8):2897-2911
  20. 20.
    Wu H and Li W. 2019. Downscaling land surface temperatures using a random forest regression model with multitype predictor variables. IEEE Access, 2019:1-1
  21. 21.
    Wu H, Li X J, Li Z L, Duan S B and Qian Y G. 2021. Hyperspectral thermal infrared remote sensing:current status and perspectives. National Remote Sensing Bulletin, 25(8): 1567-1590
  22. 22.
    Yang C, Zhan Q, Lv Y and Liu H. 2019. Downscaling Land Surface Temperature Using Multiscale Geographically Weighted Regression Over Heterogeneous Landscapes in Wuhan, China. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, PP(99):1-10
  23. 23.
    Yang Y B, Li X L and Cao C. 2017. Downscaling urban land surface temperature based on multi-scale factor. Science of Surveying and Mapping, 42(010):73-79
  24. 24.
    Zakšek K and Ostir K. 2012. Downscaling land surface temperature for urban heat island diurnal cycle analysis. Remote Sensing of Environment, 117:114-124
  25. 25.
    Zhan W F, Chen Y H, Wang J F, Zhou J, Quan J L, Liu W Y and Li J. 2012. Downscaling land surface temperatures with multi-spectral and multi-resolution images. International Journal of Applied Earth Observation and Geoinformation, 18: 23-36
  26. 26.
    Zhan W F, Chen Y H, Zhou J, Wang J F, Liu W Y, Voogt J, Zhu X L, Quan J L and Li J. 2013. Disaggregation of remotely sensed land surface temperature: Literature survey, taxonomy, issues, and caveats. Remote Sensing of Environment, 131: 119-139

Leer el texto completo

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website