Früher|Nächster

Sensitivity analysis of the training set to the performance of the machine learning-based land surface temperature reconstruction for cloud covered pixels

  • role： First author第一作者
  • Affiliation：

    School of Energy and Power Engineering, Xihua University, Chengdu 610039, China

    Institute of Mountain Hazards and Environment, Chinese Academy of Sciences, Chengdu 610041, China

  • Email：m18833028159@163.com
  • Introduction：何坤龙，1995年生，男，硕士研究生，研究方向为遥感水文水资源。E-mail： m18833028159@163.com
HE Kunlong12,  
  • role： Corresponding author通信作者
  • Affiliation：

    Institute of Mountain Hazards and Environment, Chinese Academy of Sciences, Chengdu 610041, China

  • Email：zhaow@imde.ac.cn
  • Introduction：赵伟，1984年生，男，青年研究员，研究方向为山地地表水热过程遥感。E-mail： zhaow@imde.ac.cn
ZHAO Wei2*,  
  • Affiliation：

    School of Energy and Power Engineering, Xihua University, Chengdu 610039, China

LIU Xiaohui1,  
  • Affiliation：

    School of Environment and Resources, Southwest University of Science and Technology, Mianyang 621010, China

LIU Jiao3

Resümee

Land Surface Temperature (LST) represents integrated features of land atmosphere physical and dynamic processe, It is a key element in the fields of climate change, the land–atmosphere energy budget, and the global hydrological cycle, vegetation monitoring urban climate and environmental studies. Thermal infrared remote sensing is an important technique for monitoring LST. However, the Moderate Resolution Imaging Spectroradiometer (MODIS) data are severely contaminated by cloud cover, which limits the applications of LST products. In recent years, the development of machine learning algorithms provides a promising technique for the reconstruction of LST under clouds. However, the accuracy of the cloud cover pixel reconstruction method based on machine learning is directly related to the number and regional distribution of training samples. In order to quantitatively evaluate the impact of the number and regional distribution of training samples on the LST reconstruction accuracy, based on MODIS land products and Meteosat Second Generation (MSG) incident short-wave radiation products, the LST reconstruction model depending on random forest method to construct an LST linking model for LSTs and a range of influencing factors were fitted based on clear-sky observations, which was then applied to cloud-covered pixels to obtain an LST reconstruction, the proposed reconstruction model was applied to carry out the influence of different training samples on the reconstruction accuracy of LST. The results show that: (1) A visual comparison with daily LST observations from (MSG) incident short-wave radiation products indicated that the LSTs reconstructed using this method were representative of LST patterns resulting from the influence of key variables including solar radiation intensity, vegetation cover, and geographical factor. (2) The accuracy of LST reconstruction improves significantly with the increase of the amount of training sample data, and the reconstruction accuracy is also different in different seasons. When the amount of training data increases from 5% to 95%, there are seasonal differences between summer and autumn due to the differences in vegetation and solar radiation. The variation range of correlation coefficient and root mean square error in summer is larger than that in autumn. (3) The random sampling method has higher and stabler accuracy than the regional sampling method because of its spatial representativeness, which can reduce the root mean square error to less than 2.1 k and increase the correlation coefficient to more than 0.93. Even if the amount of data is small, the reconstruction accuracy with the random sampling method is relatively stable, the negative effect of the insufficient number of training samples on the reduction of reconstruction accuracy is weakened. (4) The training sets were divided according to different elevations and vegetation coverage ranges to reconstruct the LST, and the results showed that the reconstruction accuracy was better when the range of the training sets included the range of the reconstruction area, that is, when the training set contains enough data features, it has a satisfactory spatial representation. The research results show that the proposed reconstruction model has a strong potential to reconstruct LSTs under cloud-covered conditions, and can also accurately describe the spatial distributions of LST. It also can provide a reference for future machine learning methods to select appropriate training samples and reconstruct the LST with high accuracy.

Schlüsselwort

land surface temperature;Random Forest;reconstruction;training dataset;elevation;vegetation

References

  1. 1.
    Belgiu M and Drăguţ L. 2016. Random forest in remote sensing: a review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114: 24-31
  2. 2.
    Corbari C and Mancini M. 2014. Calibration and validation of a distributed energy–water balance model using satellite data of land surface temperature and ground discharge measurements. Journal of Hydrometeorology, 15(1): 376-392
  3. 3.
    Dai A G, Fyfe J C, Xie S P and Dai X G. 2015. Decadal modulation of global surface temperature by internal climate variability. Nature Climate Change, 5(6): 555-559
  4. 4.
    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
  5. 5.
    Fu P, Xie Y H, Weng Q H, Myint S, Meacham-Hensold K and Bernacchi C. 2019. A physical model-based method for retrieving urban land surface temperatures under cloudy conditions. Remote Sensing of Environment, 230: 111191
  6. 6.
    Geiger B, Meurey C, Lajas D, Franchistéguy L, Carrer D and Roujean J L. 2008. Near real‐time provision of downwelling shortwave radiation estimates derived from satellite observations. Meteorological Applications, 15(3): 411-420
  7. 7.
    Hong F L, Zhan W F, Göttsche F M, Liu Z H, Zhou J, Huang F, Lai J M and Li M C. 2018. Comprehensive assessment of four-parameter diurnal land surface temperature cycle models under clear-sky. ISPRS Journal of Photogrammetry and Remote Sensing, 142: 190-204
  8. 8.
    Im J, Park S, Rhee J, Baik J and Choi M. 2016. Downscaling of AMSR-E soil moisture with MODIS products using machine learning approaches. Environmental Earth Sciences, 75(15): 1120
  9. 9.
    Liu M, Tang R L, Li Z L, Gao M F and Yao Y J. 2021. Progress of data-driven remotely sensed retrieval methods and products on land surface evapotranspiration. National Remote Sensing Bulletin, 25(8): 1517-1537
  10. 10.
    Jin M L and Dickinson R E. 1999. Interpolation of surface radiative temperature measured from polar orbiting satellites to a diurnal cycle: 1. Without clouds. Journal of Geophysical Research, 104(D2): 2105-2116
  11. 11.
    Jin M L and Dickinson R E. 2000. A generalized algorithm for retrieving cloudy sky skin temperature from satellite thermal infrared radiances. Journal of Geophysical Research, 105(D22): 27037-27047
  12. 12.
    Kang J, Tan J L, Jin R, Li X and Zhang Y. 2018. Reconstruction of MODIS land surface temperature products based on multi-temporal information. Remote Sensing, 10(7): 1112
  13. 13.
    Kargar K, Samadianfard S, Parsa J, Nabipour N, Shamshirband S, Mosavi A and Chau K W. 2020. Estimating longitudinal dispersion coefficient in natural streams using empirical models and machine learning algorithms. Engineering Applications of Computational Fluid Mechanics, 14(1): 311-322
  14. 14.
    La Sorte F A, Butchart S H M, Jetz W and Böhning-Gaese K. 2014. Range-wide latitudinal and elevational temperature gradients for the world’s terrestrial birds: implications under global climate change. PLoS One, 9(5): e98361
  15. 15.
    Li Y C, Li M Y, Li C and Liu Z Z. 2020. Forest aboveground biomass estimation using Landsat 8 and Sentinel-1A data with machine learning algorithms. Scientific Reports, 10(1): 9952
  16. 16.
    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
  17. 17.
    Long D, Bai L L, Yan L, Zhang C J, Yang W T, Lei H M, Quan J L, Meng X Y and Shi C X. 2019. Generation of spatially complete and daily continuous surface soil moisture of high spatial resolution. Remote Sensing of Environment, 233: 111364
  18. 18.
    Neteler M. 2010. Estimating daily land surface temperatures in mountainous environments by reconstructed MODIS LST data. Remote Sensing, 2(1): 333-351
  19. 19.
    Noi P T, Degener J and Kappas M. 2017. Comparison of multiple linear regression, cubist regression, and random forest algorithms to estimate daily air surface temperature from dynamic combinations of MODIS LST data. Remote Sensing, 9(5): 398
  20. 20.
    Shamshirband S, Hashemi S, Salimi H, Samadianfard S, Asadi E, Shadkani S, Kargar K, Mosavi A, Nabipour N and Chau K W. 2020. Predicting Standardized Streamflow index for hydrological drought using machine learning models. Engineering Applications of Computational Fluid Mechanics, 14(1): 339-350
  21. 21.
    Shwetha H R and Kumar D N. 2016. Prediction of high spatio-temporal resolution land surface temperature under cloudy conditions using microwave vegetation index and ANN. ISPRS Journal of Photogrammetry and Remote Sensing, 117: 40-55
  22. 22.
    Taormina R and Chau K W. 2015. ANN-based interval forecasting of streamflow discharges using the LUBE method and MOFIPS. Engineering Applications of Artificial Intelligence, 45: 429-440
  23. 23.
    Tian N M, Lan H X, Wu Y M and Li L P. 2020. Performance comparison of BP artificial neural network and CART decision tree model in landslide susceptibility prediction. Journal of Geo-information Science, 22(12): 2304-2316
  24. 24.
    Trigo I F, Dacamara C C, Viterbo P, Roujean J L, Olesen F, Barroso C, Camacho-de-Coca F, Carrer D, Freitas S C, García-Haro J, Geiger B, Gellens-Meulenberghs F, Ghilain N, Meliá J, Pessanha L, Siljamo N and Arboleda A. 2011. The satellite application facility for land surface analysis. International Journal of Remote Sensing, 32(9/10): 2725-2744
  25. 25.
    Wang F, Qin Z H, Fan W and Zhang S M. 2019. Quantitative analysis between land surface temperature and radiation covered by clouds. Journal of Remote Sensing, 23(6): 1113-1122
  26. 26.
    Wang X P, Zhang F and Ding J L. 2017. Evaluation of water quality based on a machine learning algorithm and water quality index for the Ebinur Lake Watershed, China. Scientific Reports, 7(1): 12858
  27. 27.
    Weng Q H, Fu P and Gao F. 2014. Generating daily land surface temperature at Landsat resolution by fusing Landsat and MODIS data. Remote Sensing of Environment, 145: 55-67
  28. 28.
    Wu P H, Shen H F, Zhang L P and Göttsche F M. 2015. Integrated fusion of multi-scale polar-orbiting and geostationary satellite observations for the mapping of high spatial and temporal resolution land surface temperature. Remote Sensing of Environment, 156: 169-181
  29. 29.
    Wu P H, Yin Z X, Yang H, Wu Y L and Ma X S. 2019. Reconstructing geostationary satellite land surface temperature imagery based on a multiscale feature connected convolutional neural network. Remote Sensing, 11(3): 300
  30. 30.
    Wu P H, Yin Z X, Zeng C, Duan S B, Gottsche F M, Li X H, Ma X S, Yang H and Shen H F. 2021. Spatially continuous and high-resolution land surface temperature product generation: a review of reconstruction and spatiotemporal fusion techniques. IEEE Geoscience and Remote Sensing Magazine
  31. 31.
    Yang G, Sun W W, Shen H F, Meng X C and Li J L. 2019. An integrated method for reconstructing daily MODIS land surface temperature data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(3): 1026-1040
  32. 32.
    Ying W M, Liu X J, Fang S F, Li X J, Lai M, Zhang X Z and Wu H. 2020. Retrieval of daily net surface shortwave radiation climatic resources based on machine learning. Resources Science, 42(10): 1998-2009
  33. 33.
    Yu W P, Tan J L, Ma M G, Li X L, She X J and Song Z J. 2019. An effective similar-pixel reconstruction of the high-frequency cloud-covered areas of Southwest China. Remote Sensing, 11(3): 336
  34. 34.
    Zeng C, Long D, Shen H F, Wu P H, Cui Y K and Hong Y. 2018. A two-step framework for reconstructing remotely sensed land surface temperatures contaminated by cloud. ISPRS Journal of Photogrammetry and Remote Sensing, 141: 30-45
  35. 35.
    Zhan C, Tang B H and Li Z L. 2018. Retrieval and validation of land surface temperature for atmospheres with air temperature inversion. Journal of Remote Sensing, 22(1): 28-37
  36. 36.
    Zhang G L, Xiao X M, Dong J W, Kou W L, Jin C, Qin Y W, Zhou Y T, Wang J, Menarguez M A and Biradar C. 2015. Mapping paddy rice planting areas through time series analysis of MODIS land surface temperature and vegetation index data. ISPRS Journal of Photogrammetry and Remote Sensing, 106: 157-171
  37. 37.
    Zhang X D, Zhou J, Liang S L and Wang D D. 2021. A practical reanalysis data and thermal infrared remote sensing data merging (RTM) method for reconstruction of a 1-km all-weather land surface temperature. Remote Sensing of Environment, 260: 112437 []
  38. 38.
    Zhao W, Duan S B, Li A and Yin G. 2019. A practical method for reducing terrain effect on land surface temperature using random forest regression. Remote Sensing of Environment, 221, 635-649 []
  39. 39.
    Zhao W and Duan S B. 2020. Reconstruction of daytime land surface temperatures under cloud-covered conditions using integrated MODIS/Terra land products and MSG geostationary satellite data. Remote Sensing of Environment, 247: 111931

Lesen Sie die ganze Passage

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