Précédent|Prochain

Remote sensing retrieval based on machine learning algorithm： Uncertainty analysis

  • role： First author第一作者
  • Affiliation：

    College of Earth and Environmental Sciences, Lanzhou University, Lanzhou 730000, China

  • Email：jpwang2020@lzu.edu.cn
  • Introduction：汪静平，研究方向为定量遥感尺度转换。E-mail： jpwang2020@lzu.edu.cn
WANG Jingping1,  
  • role： Corresponding author通信作者
  • Affiliation：

    College of Earth and Environmental Sciences, Lanzhou University, Lanzhou 730000, China

  • Email：wuxd@lzu.edu.cn
  • Introduction：吴小丹，研究方向为遥感产品的真实性检验及尺度转换。E-mail： wuxd@lzu.edu.cn
WU Xiaodan1*,  
  • Affiliation：

    College of Earth and Environmental Sciences, Lanzhou University, Lanzhou 730000, China

MA Dujuan1,  
  • Affiliation：

    Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, China

    University of Chinese Academy of Sciences, Beijing 100049, China

WEN Jianguang23,  
  • Affiliation：

    Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, China

    University of Chinese Academy of Sciences, Beijing 100049, China

XIAO Qing23

résumé

Remote sensing retrieval is one of the core issues of quantitative remote sensing. High-precision retrieval can improve the utilization efficiency of satellite data and promote the development of quantitative remote sensing. Machine learning algorithms have been increasingly used in remote sensing domains due to the outstanding advantages in dealing with complex and nonlinear problems. They can avoid the complicated processing and calculation in physical models, and minimize the uncertainty resulting from data preprocessing such as geometric correction, radiometric correction, and atmospheric correction. However, the utility of machine learning algorithms in retrieval needs to be viewed objectively. For instance, which machine learning algorithm is the most appropriate or which parameter configuration is optimal in order to obtain more accurate retrieval results. What we are concerned about most is which factors might influence the accuracy of retrievals. Hence, this paper systematically combs the current situation and principles of the application of machine learning algorithms in remote sensing retrieval with the focus on the main uncertainty factors in machine learning-based retrieval.It was found that the number of relevant articles surged especially after 2018. Several mainstream algorithms including random forests, support vector machine, and artificial neural network have been widely used in remote sensing retrieval. And the retrievals of vegetation index, leaf area index, soil moisture, chlorophyll content, and biomass are the main research hotspots at present. MODIS and Sentinel datasets are the most widely used data. The process of machine learning-based retrieval can be summarized as the acquisition of training samples as well as the construction and application of the training model. The main factors causing the uncertainty of retrievals including the selection of machine learning models, the selection of auxiliary variables, the source and accuracy of the variable datasets, the selection of training samples, and the cross-regional and cross-area application of models were discussed in this paper. The findings are helpful in deepening the consciousness and understanding of the uncertainties of the retrieval results based on machine learning algorithms, which is necessary to select the most suitable algorithm and samples for improving the accuracy and reliability of the results.Moreover, it is important to note that there is a trade-off between the model accuracy and complexity for machine learning algorithms. Therefore, they may be not feasible in solving different remote sensing problems. Further retrieval based on machine learning models may be developed from the following four aspects: 1) Selecting more detailed information to fully capture the spatial heterogeneity of land surface and the spatiotemporal variation characteristics of parameters; 2) The training samples should be more representative to make the models more universal; 3) The scale mismatch between the in situ measurements and auxiliary variables extracted from satellite products should be fully taken into consideration to reduce the uncertainty caused by the scale effect; 4) The combination of physical models and machine learning algorithms can improve the representativeness of training samples, providing a new way for the construction of training samples.

mots-clés

machine learning;Retrieval;uncertainty;quantitative remote sensing;deep learning;literature analysis

References

  1. 1.
    Ahmad S, Kalra A and Stephen H. 2010. Estimating soil moisture using remote sensing data: a machine learning approach. Advances in Water Resources, 33(1): 69-80
  2. 2.
    Atzberger C, Guérif M, Baret F and Werner W. 2010. Comparative analysis of three chemometric techniques for the spectroradiometric assessment of canopy chlorophyll content in winter wheat. Computers and Electronics in Agriculture, 73(2): 165-173
  3. 3.
    Baret F and Guyot G. 1991. Potentials and limits of vegetation indices for LAI and APAR assessment. Remote Sensing of Environment, 35(2/3): 161-173
  4. 4.
    Breiman L. 2001. Random forests. Machine Learning, 45(1): 5-32
  5. 5.
    Chen J M, Pavlic G, Brown L, Cihlar J, Leblanc S G, White H P, Hall R J, Peddle D R, King D J, Trofymow J A, Swift E, Van Der Sanden J and Pellikka P K E. 2002. Derivation and validation of Canada-wide coarse-resolution leaf area index maps using high-resolution satellite imagery and ground measurements. Remote Sensing of Environment, 80(1): 165-184
  6. 6.
    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 and Geosciences, 124: 93-102
  7. 7.
    Ghulam A, Qin Q M, Teyip T and Li Z L. 2007. Modified perpendicular drought index(MPDI): a real-time drought monitoring method. ISPRS Journal of Photogrammetry and Remote Sensing, 62(2): 150-164
  8. 8.
    Goovaerts P. 1997. Geostatistics for Natural Resources Evaluation. New York: Oxford University Press: 28
  9. 9.
    Guan X D, Huang J P, Guo N, Bi J R and Wang G Y. 2009. Variability of soil moisture and its relationship with surface albedo and soil thermal parameters over the Loess Plateau. Advances in Atmospheric Sciences, 26(4): 692-700
  10. 10.
    Hansen P M and Schjoerring J K. 2003. Reflectance measurement of canopy biomass and nitrogen status in wheat crops using normalized difference vegetation indices and partial least squares regression. Remote Sensing of Environment, 86(4): 542-553
  11. 11.
    Hufkens K, Bogaert J, Dong Q H, Lu L, Huang C L, Ma M G, Che T, Li X, Veroustraete F and Ceulemans R. 2008. Impacts and uncertainties of upscaling of remote-sensing data validation for a semi-arid woodland. Journal of Arid Environments, 72(8): 1490-1505
  12. 12.
    Hutengs C and Vohland M. 2016. Downscaling land surface temperatures at regional scales with random forest regression. Remote Sensing of Environment, 178: 127-141
  13. 13.
    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
  14. 14.
    Ji T, Liu R, Yang H, He T R and Wu J F. 2015. Spatial downscaling of precipitation using multi-source remote sensing data: a case study of Sichuan-Chongqing region. Journal of Geo-Information Science, 17(1): 108-117
  15. 15.
    Jiang D, Yang X, Clinton N and Wang N. 2004. An artificial neural network model for estimating crop yields using remotely sensed information. International Journal of Remote Sensing, 25(9): 1723-1732
  16. 16.
    Ke Y H, Im J, Park S and Gong H L. 2016. Downscaling of MODIS One kilometer evapotranspiration using Landsat-8 data and machine learning approaches. Remote Sensing, 8(3): 215
  17. 17.
    Li W, Ni L, Li Z L, Duan S B and Wu H. 2019. Evaluation of machine learning algorithms in spatial downscaling of modis land surface temperature. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(7): 2299-2307
  18. 18.
    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, 22(8): 1666-1678
  19. 19.
    Li X C, Xu X G, Bao Y S, Huang W J, Luo J H, Dong Y Y, Song X Y and Wang J H. 2012. Retrieving LAI of winter wheat based on sensitive vegetation index by the segmentation method. Scientia Agricultura Sinica, 45(17): 3486-3496
  20. 20.
    Liang L, Di L P, Huang T, Wang J H, Lin L, Wang L J and Yang M H. 2018. Estimation of leaf nitrogen content in wheat using new hyperspectral indices and a random forest regression algorithm. Remote Sensing, 10(12): 1940
  21. 21.
    Liang S L, Cheng J, Jia K, Jiang B, Liu Q, Liu S H, Xiao Z Q, Xie X H, Yao Y J, Yuan W P, Zhang X T and Zhao X. 2016. Recent progress in land surface quantitative remote sensing. Journal of Remote Sensing, 20(5): 875-898
  22. 22.
    Liu H Z, Wang B M and Fu C B. 2008. Relationships between surface albedo, soil thermal parameters and soil moisture in the semi-arid area of Tongyu, northeastern China. Advances in Atmospheric Sciences, 25(5): 757-764
  23. 23.
    Liu Y, Liu R G, Chen J M, Cheng X and Zheng G. 2013. Current status and perspectives of leaf area index retrieval from optical remote sensing data. Journal of Geo-Information Science, 15(5): 734-743
  24. 24.
    Liu Y, Liu R G, Liu S L, Liu J Y, Chen Z X, Wang L M and Zou J Q. 2010. Estimation of Crop LAI based on the neural network trained from physical model. Journal of Geo-Information Science, 12(3): 426-435
  25. 25.
    Liu Z J, Shao Q Q, Tao J and Chi W F. 2015. Intra-annual variability of satellite observed surface albedo associated with typical land cover types in China. Journal of Geographical Sciences, 25(1): 35-44
  26. 26.
    Mao K B, Yang J, Han X Z, Tang S H, Yuan Z J and Gao C Y. 2018. Retrieving land surface temperature based on deep dynamic learning NN algorithm and radiation transmission model. China Agricultural Informatics, 30(5): 47-57
  27. 27.
    Masson V, Champeaux J L, Chauvin F, Meriguet C and Lacaze R. 2003. A global database of land surface parameters at 1-km resolution in meteorological and climate models. Journal of Climate, 16(9): 1261-1282
  28. 28.
    Meyer H, Kühnlein M, Appelhans T and Nauss T. 2016. Comparison of four machine learning algorithms for their applicability in satellite-based optical rainfall retrievals. Atmospheric Research, 169: 424-433
  29. 29.
    Pan S F, Pan N Q, Tian H Q, Friedlingstein P, Sitch S, Shi H, Arora V K, Haverd V, Jain A K, Kato E, Lienert S, Lombardozzi D, Nabel J E M S, Ottlé C, Poulter B, Zaehle S and Running S W. 2020. Evaluation of global terrestrial evapotranspiration using state-of-the-art approaches in remote sensing, machine learning and land surface modeling. Hydrology and Earth System Sciences, 24(3): 1485-1509
  30. 30.
    Peng J J, Liu Q, Wen J G, Liu Q H, Tang Y, Wang L Z, Dou B C, You D Q, Sun C K, Zhao X J, Feng Y B and Shi J. 2015. Multi-scale validation strategy for satellite albedo products and its uncertainty analysis. Science China Earth Sciences, 58(4): 573-588
  31. 31.
    Qin W M, Wang L C, Lin A W, Zhang M and Bilal M. 2018. Improving the estimation of daily aerosol optical depth and aerosol radiative effect using an optimized artificial neural network. Remote Sensing, 10(7): 1022
  32. 32.
    Salomonson V V and Appel I. 2004. Estimating fractional snow cover from MODIS using the normalized difference snow index. Remote Sensing of Environment, 89(3): 351-360.
  33. 33.
    Srinet R, Nandy S and Patel N R. 2019. Estimating leaf area index and light extinction coefficient using Random Forest regression algorithm in a tropical moist deciduous forest, India. Ecological Informatics, 52: 94-102
  34. 34.
    Wang J P, Wu X D, Wen J G, Xiao Q, Gong B C, Ma D J, Cui Y R, Lin X W and Bao Y F. 2022. Upscaling in situ site-based albedo using machine learning models: main controlling factors on results. IEEE Transactions on Geoscience and Remote Sensing, 60: 4403516
  35. 35.
    Wang J W, Yuan Q Q, Shen H F, Liu T T, Li T W, Yue L W, Shi X G and Zhang L P. 2020. Estimating snow depth by combining satellite data and ground-based observations over Alaska: a deep learning approach. Journal of Hydrology, 585: 124828.
  36. 36.
    Wang K C, Wang P C, Liu J M, Sparrow M, Haginoya S and Zhou X J. 2005. Variation of surface albedo and soil thermal parameters with soil moisture content at a semi-desert site on the western Tibetan Plateau. Boundary-Layer Meteorology, 116(1): 117-129
  37. 37.
    Wang L A, Zhou X D, Zhu X K, Dong Z D and Guo W S. 2016. Estimation of biomass in wheat using random forest regression algorithm and remote sensing data. The Crop Journal, 4(3): 212-219
  38. 38.
    Wang L H and Xing Y Q. 2008. Remote sensing estimation of natural forest biomass based on an artificial neural network. The Journal of Applied Ecology, 19(2): 261-266
  39. 39.
    Wang Q. 2021. Progress of environmental remote sensing monitoring technology in China and some related frontier issues. National Remote Sensing Bulletin, 25(1): 25-36
  40. 40.
    Weng Q H and Hu X F. 2008. Medium spatial resolution satellite imagery for estimating and mapping urban impervious surfaces using LSMA and ANN. IEEE Transactions on Geoscience and Remote Sensing, 46(8): 2397-2406
  41. 41.
    Wu X D, Wen J G, Xiao Q and You D Q. 2020. Upscaling of single-site-based measurements for validation of long-term coarse-pixel albedo products. IEEE Transactions on Geoscience and Remote Sensing, 58(5): 3411-3425
  42. 42.
    Wu X D, Wen J G, Xiao Q, Liu Q, Peng J J, Dou B C, Li X H, You D Q, Tang Y and Liu Q H. 2016. Coarse scale in situ albedo observations over heterogeneous snow-free land surfaces and validation strategy: a case of MODIS albedo products preliminary validation over northern China. Remote Sensing of Environment, 184: 25-39
  43. 43.
    Wu X D, Wen J G, Xiao Q, You D Q, Liu Q and Lin X W. 2018. Forward a spatio-temporal trend surface for long-term ground-measured albedo upscaling over heterogeneous land surface. International Journal of Digital Earth, 11(5): 470-484
  44. 44.
    Xiao Z Q, Liang S L, Wang T T and Jiang B. 2016. Retrieval of Leaf Area Index (LAI) and Fraction of Absorbed Photosynthetically Active Radiation (FAPAR) from VIIRS time-series data. Remote Sensing, 8(4): 351
  45. 45.
    Xu B D, Li J, Park T, Liu Q H, Zeng Y L, Yin G F, Zhao J, Fan W L, Yang L, Knyazikhin Y and Myneni R B. 2018a. An integrated method for validating long-term leaf area index products using global networks of site-based measurements. Remote Sensing of Environment, 209: 134-151
  46. 46.
    Xu G H, Liu Q H, Chen L F and Liu L Y. 2016. Remote sensing for China’s sustainable development: Opportunities and challenges. Journal of Remote Sensing, 20(5): 679-688
  47. 47.
    Xu T R, Guo Z X, Liu S M, He X L, Meng Y F Y, Xu Z W, Xia Y L, Xiao J F, Zhang Y, Ma Y F and Song L S. 2018b. Evaluating different machine learning methods for upscaling evapotranspiration from flux towers to the regional scale. Journal of Geophysical Research: Atmospheres, 123(16): 8674-8690
  48. 48.
    Yang G J, Pu R L, Huang W J, Wang J H and Zhao C J. 2010. A novel method to estimate subpixel temperature by fusing solar-reflective and thermal-infrared remote-sensing data with an artificial neural network. IEEE Transactions on Geoscience and Remote Sensing, 48(4): 2170-2178
  49. 49.
    Yang G J, Zhao C J, Xing Z R, Huang W J and Wang J H. 2011. LAI inversion of spring wheat based on PROBA/CHRIS hyperspectral multi-angular data and PROSAIL model. Transactions of the CSAE, 27(10): 88-94
  50. 50.
    Yang R M, Zhang G L, Liu F, Lu Y Y, Yang F, Yang F, Yang M, Zhao Y G and Li D C. 2016. Comparison of boosted regression tree and random forest models for mapping topsoil organic carbon concentration in an alpine ecosystem. Ecological Indicators, 60: 870-878
  51. 51.
    Yang Y B, Cao C, Pan X, Li X L and Zhu X. 2017. Downscaling land surface temperature in an arid area by using multiple remote sensing indices with random forest regression. Remote Sensing, 9(8): 789
  52. 52.
    Yao Y J, Liang S L, Li X L, Chen J Q, Liu S M, Jia K, Zhang X T, Xiao Z Q, Fisher J B, Mu Q Z, Pan M, Liu M, Cheng J, Jiang B, Xie X H, Grünwald T, Bernhofer C and Roupsard O. 2017. Improving global terrestrial evapotranspiration estimation using support vector machine by integrating three process-based algorithms. Agricultural and Forest Meteorology, 242: 55-74
  53. 53.
    Yuan H H, Yang G J, Li C C, Wang Y J, Liu J G, Yu H Y, Feng H K, Xu B, Zhao X Q and Yang X D. 2017. Retrieving soybean leaf area index from unmanned aerial vehicle hyperspectral remote sensing: analysis of RF, ANN, and SVM regression models. Remote Sensing, 9(4): 309
  54. 54.
    Yuan Q Q, Xu H Z, Li T W, Shen H F and Zhang L P. 2020. Estimating surface soil moisture from satellite observations using a generalized regression neural network trained on sparse ground-based measurements in the continental U.S. Journal of Hydrology, 580: 124351
  55. 55.
    Yue J B, Yang G J, Li C C, Li Z H, Wang Y J, Feng H K and Xu B. 2017. Estimation of winter wheat above-ground biomass using unmanned aerial vehicle-based snapshot hyperspectral sensor and crop height improved models. Remote Sensing, 9(7): 708
  56. 56.
    Zhang L P and Wu C. 2017. Advance and future development of change detection for multi-temporal remote sensing imagery. Acta Geodaetica et Cartographica Sinica, 46(10): 1447-1459
  57. 57.
    Zhao W, Sánchez N, Lu H and Li A N. 2018. A spatial downscaling approach for the SMAP passive surface soil moisture product using random forest regression. Journal of Hydrology, 563: 1009-1024
  58. 58.
    Zhao X Z, Yu B L, Liu Y, Chen Z Q, Li Q X, Wang C X and Wu J P. 2019. Estimation of poverty using random forest regression with multi-source data: a case study in Bangladesh. Remote Sensing, 11(4): 375
  59. 59.
    Zheng H P, Yan J Z, Liu L S, Li L H and Zhang Y L. 2017. Research advances in grassland remote sensing based on bibliometrology. Chinese Journal of Grassland, 39(4): 101-110, 115
  60. 60.
    Zhu J S, Ji X Y and Song Z Z. 2019. Water Depth Inversion Based on Support Vector Machine and BP Neural Network. Geomatics and Spatial Information Technology, 42(6): 11-14

Lire l'article complet

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