предыдущий|следующий

Remote sensing feature selection for alpine wetland classification

  • role： First author第一作者
  • Affiliation：

    School of Earth Science and Resources, Chang'an University, Xi'an 710054, China

    State Key Laboratory of Remote Sensing Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

  • Email：h1160964174@gmail.com
  • Introduction：霍轩琳， 研究方向为湿地生态与环境遥感。E-mail： h1160964174@gmail.com
HUO Xuanlin12,  
  • role： Corresponding author通信作者
  • Affiliation：

    State Key Laboratory of Remote Sensing Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

  • Email：Niuzg@aircas.ac.cn
  • Introduction：牛振国，研究方向为湿地生态与环境遥感。E-mail：Niuzg@aircas.ac.cn
NIU Zhenguo2*,  
  • Affiliation：

    State Key Laboratory of Remote Sensing Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

ZHANG Bo2,  
  • Affiliation：

    State Key Laboratory of Remote Sensing Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

LIU Linsong2,  
  • Affiliation：

    School of Land Engineering, Chang'an University, Xi'an 710054, China

LI Xia3

реферат

Alpine wetlands are an important surface cover type on the Qinghai―Tibet Plateau because they play a key role in water conservation, climate regulation, and biodiversity maintenance. Accurate and timely knowledge of the temporal and spatial distribution of alpine wetlands is necessary for wetland protection and management. The selection of remote sensing classification features is crucial in wetland mapping. Although spectral, texture, and topographic features have been investigated, studies focusing on spectral index features and their mathematical statistical features and feature selection methods are limited. This study aims to classify alpine wetlands from the aspects of mathematical statistical features, alpine wetland types, feature selection methods, and selected feature sets combined with random forest classification algorithm using Sentinel-2 image data and taking the Shouqu Alpine Wetland Reserve as the research site. An in-depth and comprehensive analysis on the spectral index characteristics of alpine wetlands is performed to optimize the classification characteristics of alpine wetlands.The Gansu Shouqu Alpine Wetland Reserve was used as the research area, and classification characteristics (spectrum, vegetation index, red edge index, and water body index) were obtained on the basis of Sentinel-2 data. Filter and wrapper feature selection methods, including Jeffries–Matusita distance, Spectral Angular Distance (SAD), Euclidean Distance (ED), RF-RFE algorithm, and Relief-F algorithm are utilized to optimize these features. Meanwhile, Z test is applied for quantitative evaluation.The following conclusions can be drawn from this study. (1) Among the categories of alpine wetlands involved in the classification, rivers and bare land are the easiest to distinguish, followed by grasslands and swamps and then swampy meadows and meadows. MCARI2, NDWI, DVI, EVI, EWI, IRECI, MCARI, TCARI, and UGWI indices can be used to differentiate among adjacent swamps, swampy meadows, meadows, and grasslands. (2) The order of contribution of different index characteristics to wetland information extraction in terms of degree is water body index characteristics > vegetation index characteristics > red edge index characteristics. (3) ED and Relief-F algorithms in the filter method demonstrate excellent performance from the perspective of feature optimization methods. (4) A suitable alpine wetland information extraction method is selected using the indices RDVI, NDVI, MSR, RVI, VIgreen, RNDWI, NDWI, NDWI_B, MNDWI, EWI, and CIre. (5) The mathematical statistics of different classification features indicated that the median feature obtains the best classification result, followed by the average value feature.We provide detailed results from feature optimization methods, wetland classification optimization index, statistical feature evaluation, and categories involved in alpine wetland classification using multi-dimensional analysis. To the best of our knowledge, this study provides a novel transferable and universal method for the selection of characteristic variables for wetland information extraction.

ключеви́че слова́

remote sensing;wetland classification;alpine wetland;feature selection;Qinghai-Tibet Plateau;Sentinel-2

References

  1. 1.
    Barnes E M, Clarke T R, Richards S R, Colaizzi P D, Haberland J, Kostrzewski M, Waller P, Choi C, Riley E, Thompson T, Lascano R J, Li H and Moran M S. 2000. Coincident detection of crop water stress, nitrogen status and canopy density using ground-based multispectral data//Proceedings of the 5th International Conference on Precision Agriculture. Bloomington, Minnesota, USA: [s.n.]: 1-15
  2. 2.
    Birth G S and Mcvey G R. 1968. Measuring the color of growing turf with a reflectance Spectrophotometer. Agronomy Journal, 60(6): 640-643
  3. 3.
    Breiman L. 2001. Random forest. Machine Learning, 45(1): 5-32
  4. 4.
    Broge N H and Leblanc E. 2001. Comparing prediction power and stability of broadband and hyperspectral vegetation indices for estimation of green leaf area index and canopy chlorophyll density. Remote Sensing of Environment, 76(2): 156-172
  5. 5.
    Carvalho Júnior O A, Guimarães R F, Gillespie A R, Silva N C and Gomes R A T. 2011. A new approach to change vector analysis using distance and similarity measures. Remote Sensing, 3(11): 2473-2493
  6. 6.
    Chang W T, Wang H, Ning X G and Zhang H C. 2020. Extraction of Zhalong wetlands information based on images of Sentinel-2 red-edge bands and Sentinel-1 radar bands. Wetland Science, 18(1): 10-19
  7. 7.
    Chen J M. 1996. Evaluation of vegetation indices and a modified simple ratio for boreal applications. Canadian Journal of Remote Sensing, 22(3): 229-242
  8. 8.
    Chen W Q, Ding J L, Li Y H and Niu Z Y. 2015. Extraction of water information based on China made-GF-1 remote sense image. Resources Science, 37(6): 1166-1172
  9. 9.
    Dabboor M, Howell S, Shokr M and Yackel J. 2014. The Jeffries-Matusita distance for the case of complex Wishart distribution as a separability criterion for fully polarimetric SAR data. International Journal of Remote Sensing, 35(19/20): 6859-6873
  10. 10.
    Dash M, Choi K, Scheuermann P and Liu H. 2002. Feature selection for clustering-a filter solution//2002 IEEE International Conference on Data Mining. Maebashi City, Japan: IEEE: 115-122
  11. 11.
    Dash J and Curran P J. 2004. The MERIS terrestrial chlorophyll index. International Journal of Remote Sensing, 25(23): 5403-5413
  12. 12.
    Dash M and Liu H. 1997. Feature selection for classification. Intelligent Data Analysis, 1(1/4): 131-156
  13. 13.
    Daughtry C S T, Walthall C L, Kim M S, de Colstoun E B and McMurtrey J E III. 2000. Estimating corn leaf chlorophyll concentration from leaf and canopy reflectance. Remote sensing of Environment, 74(2): 229-239
  14. 14.
    Defries R S and Townshend J R G. 1994. NDVI-derived land cover classifications at a global scale. International Journal of Remote Sensing, 15(17): 3567-3586
  15. 15.
    Duan J W, Zhong J S, Jiang L and Zhong M M. 2021. Extraction method of ultra-green water index for flood area after rain based on GF-2 image. Geography and Geo-Information Science, 37(3): 35-41
  16. 16.
    Elavarasan D, Vincent P M D R, Srinivasan K and Chang C Y. 2020. A hybrid CFS filter and RF-RFE wrapper-based feature extraction for enhanced agricultural crop yield prediction modeling. Agriculture, 10(9): 400
  17. 17.
    Frampton W J, Dash J, Watmough G and Milton E J. 2013. Evaluating the capabilities of Sentinel-2 for quantitative estimation of biophysical variables in vegetation. ISPRS Journal of Photogrammetry and Remote Sensing, 82: 83-92
  18. 18.
    Gao B B. 2008. Research on the Status Quo of Wetland in Shouqu Nature Reserve of the Yellow River in Gansu Province and its protection Countermeasures. Gansu Science and Technology, 24(12): 3-5
  19. 19.
    Gitelson A A, Kaufman Y J, Stark R and Rundquist D. 2002. Novel algorithms for remote estimation of vegetation fraction. Remote Sensing of Environment, 80(1): 76-87
  20. 20.
    Gitelson A A, Keydan G P and Merzlyak M N. 2006. Three-band model for noninvasive estimation of chlorophyll, carotenoids, and anthocyanin contents in higher plant leaves. Geophysical Research Letters, 33(11): L11402
  21. 21.
    Gitelson A and Merzlyak M N. 1994. Spectral reflectance changes associated with autumn senescence of Aesculus hippocastanum L. and Acer platanoides L. leaves. Spectral features and relation to chlorophyll estimation. Journal of Plant Physiology, 143(3): 286-292
  22. 22.
    Gitelson A A and Merzlyak M N. 1996. Signature analysis of leaf reflectance spectra: algorithm development for remote sensing of chlorophyll. Journal of Plant Physiology, 148(3/4): 494-500
  23. 23.
    Gitelson A A, Viña A, Arkebauer T J, Rundquist D C, Keydan G and Leavitt B. 2003. Remote estimation of leaf area index and green leaf biomass in maize canopies. Geophysical Research Letters, 30(5): 1248
  24. 24.
    Guyon I and Elisseeff A. 2003. An introduction to variable and feature selection. Journal of Machine Learning Research, 3: 1157-1182
  25. 25.
    Guyot G and Baret F. 1988. Utilisation de la haute resolution spectrale pour suivre l'etat des couverts vegetaux//Proceedings of the 4th International Conference on Spectral Signatures of Objects in Remote Sensing. Aussois, France: [s.n.]: 279-286
  26. 26.
    Haboudane D, Miller J R, Tremblay N, Zarco-Tejada P J and Dextraze L. 2002. Integrated narrow-band vegetation indices for prediction of crop chlorophyll content for application to precision agriculture. Remote Sensing of Environment, 81(2/3): 416-426
  27. 27.
    Han N, Wang K, Yu L and Zhang X Y. 2012. Integration of texture and landscape features into object-based classification for delineatingTorreyausing IKONOS imagery. International Journal of Remote Sensing, 33(7): 2003-2033
  28. 28.
    Hao Y F, Man W D, Wang J H, Liu M Y and Zhang K. 2021. Wetland information extraction based on Relief-F algorithm and decision tree method. Journal of Liaoning Technical University (Natural Science), 40(3): 225-233
  29. 29.
    He J H, Zhang T B, Yi G H, Bie X J, Luo N, Wang Q and Fan W W. 2015. Wetland information extraction and change detection in Zoige Plateau area based on the EOS/MODIS. Geomatics and Spatial Information Technology, 38(9): 38-41
  30. 30.
    Huete A, Didan K, Miura T, Rodriguez E P, Gao X and Ferreira L G. 2002. Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote Sensing of Environment, 83(1/2): 195-213
  31. 31.
    Huete A R.1988. A soil-adjusted vegetation index (SAVI). Remote Sensing of Environment, 25(3): 295-309
  32. 32.
    John G H, Kohavi R and Pfleger K. 1994. Irrelevant features and the subset selection problem//Proceedings of the Eleventh International Conference on Machine Learning. New Brunswick, NJ: Rutgers University, 121-129
  33. 33.
    Kira K and Rendell L A. 1992. The feature selection problem: traditional methods and a new algorithm//Proceedings of the Tenth National Conference on Artificial Intelligence. San Jose, California: AAAI Press: 129-134
  34. 34.
    Korhonen L, Hadi, Packalen P and Rautiainen M. 2017. Comparison of Sentinel-2 and Landsat 8 in the estimation of boreal forest canopy cover and leaf area index. Remote Sensing of Environment, 195: 259-274
  35. 35.
    Kruse F A, Lefkoff A B and Dietz J B. 1993. Expert system-based mineral mapping in northern Death Valley, California/Nevada, using the airborne visible/infrared imaging spectrometer (AVIRIS). Remote Sensing of Environment, 44(2/3): 309-336
  36. 36.
    Liu J H and Wang F. 2021. A semi-supervised feature selection algorithm based on Relief-F. Journal of Zhengzhou University (Natural Science Edition), 53(1): 42-46, 53
  37. 37.
    Mahdianpari M, Salehi B, Mohammadimanesh F, Homayouni S and Gill E. 2019. The first wetland inventory map of newfoundland at a spatial resolution of 10 m using Sentinel-1 and Sentinel-2 data on the Google earth engine cloud computing platform. Remote Sensing, 11(1): 43
  38. 38.
    McFeeters S K. 1996. The use of the normalized difference water index (NDWI) in the delineation of open water features. International Journal of Remote Sensing, 17(7): 1425-1432
  39. 39.
    Moor H, Hylander K and Norberg J. 2015. Predicting climate change effects on wetland ecosystem services using species distribution modeling and plant functional traits. Ambio, 44(S1): 113-126
  40. 40.
    Phan T N, Kuch V and Lehnert L W. 2020. Land cover classification using Google earth engine and random forest classifier—The role of image composition. Remote Sensing, 12(15): 2411
  41. 41.
    Roujean J L and Breon F M. 1995. Estimating PAR absorbed by vegetation from bidirectional reflectance measurements. Remote Sensing of Environment, 51(3): 375-384
  42. 42.
    Saeys Y, Inza I and Larrañaga P. 2007. A review of feature selection techniques in bioinformatics. Bioinformatics, 23(19): 2507-2517
  43. 43.
    Shoko C and Mutanga O. 2017. Examining the strength of the newly-launched Sentinel 2 MSI sensor in detecting and discriminating subtle differences between C3 and C4 grass species. ISPRS Journal of Photogrammetry and Remote Sensing, 129: 32-40
  44. 44.
    Sun Y L, Zhang X, Shuai T, Shang K and Feng S N. 2015. Radiometric normalization of hyperspectral satellite images with spectral angle distance and Euclidean distance. Journal of Remote Sensing, 19(4): 618-626
  45. 45.
    Tucker C J. 1979. Red and photographic infrared linear combinations for monitoring vegetation. Remote Sensing of Environment, 8(2): 127-150
  46. 46.
    Wang G X, Li Y S, Wang Y B and Chen L. 2007. Typical alpine wetland system changes on the Qinghai-Tibet Plateau in recent 40 years. Acta Geographica Sinica, 62(5): 481-491
  47. 47.
    White L, Ryerson R A, Pasher J and Duffe J. 2020. State of science assessment of remote sensing of great lakes coastal wetlands: responding to an operational requirement. Remote Sensing, 12(18): 3024
  48. 48.
    Wu C Y, Niu Z, Tang Q and Huang W J. 2008. Estimating chlorophyll content from hyperspectral vegetation indices: modeling and validation. Agricultural and Forest Meteorology, 148(8/9): 1230-1241
  49. 49.
    Xiao X M, Boles S, Liu J Y, Zhuang D F, Frolking S, Li C S, Salas W and Moore B. 2005. Mapping paddy rice agriculture in southern China using multi-temporal MODIS images. Remote Sensing of Environment, 95(4): 480-492
  50. 50.
    Xie S Y, Fu B L, Li Y, Liu Z L, Zuo P P, Lan F W, He H C and Fan D L. 2021. Classification method on marsh wetlands in Honghe National Nature Reserve based on multi-dimensional remote sensing images. Wetland Science, 19(1): 1-16
  51. 51.
    Xu H Q. 2005. A study on information extraction of water body with the modified normalized difference water index (MNDWI). Journal of Remote Sensing, 9(5): 589-595
  52. 52.
    Xu X L, Liu J Y, Shao Q Q and Fan J W. 2008. The dynamic changes of ecosystem spatial pattern and structure in the Three-River Headwaters region in Qinghai Province during recent 30 years. Geographical Research, 27(4): 829-838
  53. 53.
    Xue P F, Li W L, Zhu G F, Zhou H K, Liu C L and Yan H P. 2021. Changes in the pattern of an alpine wetland landscape in Maqu County in the first meander of the Yellow River. Chinese Journal of Plant Ecology, 45(5): 467-475
  54. 54.
    Yan P, Zhang Y J and Zhang Y. 2007. A study on information extraction of water system in semi- arid regions with the enhanced water index (EWI) and GIS based noise remove techniques. Remote Sensing Information, (6): 62-67
  55. 55.
    Yu L and Liu H. 2003. Feature selection for high-dimensional data: a fast correlation-based filter solution//Proceedings of the Twentieth International Conference on Machine Learning. Washington, DC, USA: AAAI Press: 856-863
  56. 56.
    Zhang L, Gong Z N, Wang Q W, Jin D D and Wang X. 2019. Wetland mapping of Yellow River Delta wetlands based on multi-feature optimization of Sentinel-2 images. Journal of Remote Sensing, 23(2): 313-326
  57. 57.
    Zhang S Q, Zhou B R, Shi F F, Chen Q and Su S L. 2020. Study on information extraction method of alpine wetland in Qinghai-Xizang Plateau based on remote sensing data of GF-1 Satellite. Plateau Meteorology, 39(6): 1309-1317
  58. 58.
    Zheng Y, Wu B F and Zhang M. 2017. Estimating the above ground biomass of winter wheat using the Sentinel-2 data. Journal of Remote Sensing, 21(2): 318-328

Читать полностью

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