본문 바로가기
KERD
논문KCI 등재

Enhancing leaf area index estimation in tropical vegetation: a comparative study of multivariate linear regression and Sentinel Application Platform-derived leaf area index

0

조회

0

다운로드

0

인용

0

참고문헌

키워드

주제분류생물학

초록

Background: The leaf area index (LAI) quantifies the total one-sided green leaf area per unit of soil area, making it a crucial parameter in models that simulate carbon, nutrient, water, and energy fluxes within forest ecosystems. This study enhances LAI estimation techniques by employing a multivariate linear regression (MVLR) approach specifically tailored to tropical vegetation. We integrated field-collected LAI data with spectral indices and multispectral bands to develop a robust predictive empirical model. The LAI estimates derived from the MVLR approach are rigorously compared with those obtained from the Sentinel Application Platform (SNAP), a widely utilized tool for remote sensing analysis. Results: In developing the MVLR model, nine multispectral bands, seven vegetation indices (VIs), and two biophysical variables derived from Sentinel-2 multispectral image were tested to identify efficient predictors for LAI estimation. To determine significant multispectral bands and VIs (ensuring no multicollinearity, high coefficient of determination (R2), low root mean square error (RMSE), and a p-value < 0.05) for the best representative model, stepwise multiple linear regression (SMLR) was employed. Multispectral bands 7 and 8, along with the VIs soil adjusted vegetation index and normalized difference vegetation index, and the fraction of vegetation cover biophysical variable, produced superior outcomes and serve as strong predictor variables for LAI. The accuracy of the MVLR model was validated using 17 directly measured LAI sample plots with the leave-one-out cross-validation method. The estimated LAI using the MVLR model achieved higher accuracy, with an R2 of 0.94, compared to the SNAP toolbox (R2 = 0.71). The RMSE and bias of the MVLR model were 0.18 and 0.006, respectively, while for SNAP-derived LAI, the RMSE and bias were 0.53 and 0.31, respectively. Conclusions: The improved accuracy and reduced error of the MVLR model are attributed to its adjustment for tropical vegetation types. Future research should focus on comparing the MVLR model with other global LAI products to further validate and enhance its applicability.

Abstract

Background: The leaf area index (LAI) quantifies the total one-sided green leaf area per unit of soil area, making it a crucial parameter in models that simulate carbon, nutrient, water, and energy fluxes within forest ecosystems. This study enhances LAI estimation techniques by employing a multivariate linear regression (MVLR) approach specifically tailored to tropical vegetation. We integrated field-collected LAI data with spectral indices and multispectral bands to develop a robust predictive empirical model. The LAI estimates derived from the MVLR approach are rigorously compared with those obtained from the Sentinel Application Platform (SNAP), a widely utilized tool for remote sensing analysis. Results: In developing the MVLR model, nine multispectral bands, seven vegetation indices (VIs), and two biophysical variables derived from Sentinel-2 multispectral image were tested to identify efficient predictors for LAI estimation. To determine significant multispectral bands and VIs (ensuring no multicollinearity, high coefficient of determination (R2), low root mean square error (RMSE), and a p-value < 0.05) for the best representative model, stepwise multiple linear regression (SMLR) was employed. Multispectral bands 7 and 8, along with the VIs soil adjusted vegetation index and normalized difference vegetation index, and the fraction of vegetation cover biophysical variable, produced superior outcomes and serve as strong predictor variables for LAI. The accuracy of the MVLR model was validated using 17 directly measured LAI sample plots with the leave-one-out cross-validation method. The estimated LAI using the MVLR model achieved higher accuracy, with an R2 of 0.94, compared to the SNAP toolbox (R2 = 0.71). The RMSE and bias of the MVLR model were 0.18 and 0.006, respectively, while for SNAP-derived LAI, the RMSE and bias were 0.53 and 0.31, respectively. Conclusions: The improved accuracy and reduced error of the MVLR model are attributed to its adjustment for tropical vegetation types. Future research should focus on comparing the MVLR model with other global LAI products to further validate and enhance its applicability.

참고문헌 (62)

  1. Alexandridis TK, "Relationship between MODIS EVI and LAI across time and space", Geocarto Int, 35(13), pp.1385~1399 (2019)[DOI]
  2. Ali AM, "Validating the Predictive power of statistical models in retrieving leaf dry matter content of a coastal wetland from a sentinel-2 image", Remote Sens, 11(16), pp.1936~ (2019)[DOI]
  3. Alin A, "Multicollinearity", Wiley Interdisciplinary Reviews : Computational Statistics, 2(3), pp.370~374 (2010)[DOI]
  4. Baret F, "Potentials and limits of vegetation indices for LAI and APAR assessment", Remote Sens Environ, 35, pp.161~173 (1991)[DOI]
  5. Binh NA, "Quantifying mangrove leaf area index from Sentinel-2 imagery using hybrid models and active learning", Int J Remote Sens, 43, pp.5636~5657 (2022)[DOI]
  6. Bochenek Z, "Validation of the LAI biophysical product derived from Sentinel-2 and Proba-V images for winter wheat in western Poland", Geoinf Issues, 9(1), pp.15~26 (2017)
  7. Brown LA, "Estimating forest leaf area index and canopy chlorophyll content with sentinel-2 : an evaluation of two hybrid retrieval algorithms", Remote Sens, 11(15), pp.1752~ (2019)[DOI]
  8. Campos-Taberner M, "A critical comparison of remote sensing leaf area index estimates over rice-cultivated areas : from sentinel-2 and landsat-7", 8 to MODIS, GEOV1 and EUMETSAT polar system, 2018, pp.10(5), 763~
  9. Cawley GC, "Leave-one-out cross-validation based model selection criteria for weighted LS-SVMs", Paper presented at: The 2006 IEEE International Joint Conference on Neural Network Proceedings (2006), IEEE
  10. Chauhan KK, "Validation of biophysical parameters of wheat retrieved from sentinel-2 data using in-situ measurements at Anand Region of India", Int J Environ Climate Ch, 14(1), pp.626~638 (2024)[DOI]
  11. Cho MA, "Towards red-edge positions less sensitive to canopy biophysical parameters for leaf chlorophyll estimation using properties optique spectrales des feuilles(PROSPECT)and scattering by arbitrarily inclined leaves(SAILH)simulated data", Int J Remote Sens, 29(8), pp.2241~2255 (2008)[DOI]
  12. Chrysafis I, "Retrieval of leaf area index using sentinel-2 imagery in a mixed Mediterranean forest area", ISPRS Int J Geo-Inf, 9(11), pp.622~ (2020)[DOI]
  13. Confalonieri R, "Development of an app for estimating leaf area index using a smartphone, Trueness and precision determination and comparison with other indirect methods", Comput Electron Agric, 96, pp.67~74 (2013)[DOI]
  14. Daoud JI, "Multicollinearity and regression analysis", Paper presented at: 4th International Conference on Mathematical Applications in Engineering (2017), International Islamic University Malaysia
  15. Darvishzadeh R, "Analysis of sentinel-2 and rapideye for retrieval of leaf area index in a saltmarsh using a radiative transfer model", Remote Sens, 11(6), pp.671~ (2019)[DOI]
  16. Djamai N, "Validation and Comparison of Cropland Leaf Area Index Retrievals from Sentinel-2", MSI Data Using Sl2P Processor and Vegetation Indices Models, 2019, 4595~4598[DOI]
  17. Djamai N, "Evaluation of vegetation biophysical variables time series derived from synthetic sentinel-2 images", Remote Sens, 11(13), pp.1547~ (2019)[DOI]
  18. Durbha SS, "Support vector machines regression for retrieval of leaf area index from multiangle imaging spectroradiometer", Remote Sens Environ, 107, pp.348~361 (2007)[DOI]
  19. Modelling net primary productivity and above-ground biomass for mapping of spatial biomass distribution in Kazakhstan, "Eisfelder C", German Remote Sensing Data Center of the German Aerospace Center, ~ (2013)
  20. Eisfelder C, "Above-ground biomass estimation based on NPP time-series-A novel approach for biomass estimation in semi-arid Kazakhstan", Ecol Indic, 72, pp.13~22 (2017)[DOI]
  21. Fang H, "Seasonal variation of leaf area index (LAI) over paddy rice fields in NE China: Intercomparison of destructive sampling, LAI-2200, digital hemispherical photography (DHP), and AccuPAR methods", Agric For Meteorology, 198-199, pp.126~141 (2014)[DOI]
  22. Ghebremicael ST, "Estimating the leaf area index(LAI)of black wattle from Landsat ETM+ satellite imagery", South Afr For J, 201(1), pp.3~12 (2004)[DOI]
  23. Jacquemoud S, "Comparison of four radiative transfer models to simulate plant canopies reflectance : direct and inverse mode", Remote Sens Environ, 74(3), pp.471~481 (2000)[DOI]
  24. Jin M, "Observed variations of leaf area index and its relationship with surface temperatures during warm seasons", Meteorol Atmos Phys, 80, pp.117~129 (2002)[DOI]
  25. Jonckheere I, "Review of methods for in situ leaf area index determination: Part I Theories, sensors and hemispherical photography", Agric For Meteorology, 121(1-2), pp.19~35 (2004)[DOI]
  26. Joseph M, "Using landsat imagery and census data for urban population density modeling in Port-au-Prince, Haiti", GISci & Remote Sens, 49(2), pp.228~250 (2012)[DOI]
  27. Kamenova I, "Evaluation of Sentinel-2 vegetation indices for prediction of LAI, fAPAR and fCover of winter wheat in Bulgaria", Eur J Remote Sens, 54, pp.89~108 (2020)[DOI]
  28. Kganyago M, "Validation of sentinel-2 leaf area index(LAI)product derived from SNAP toolbox and its comparison with global LAI products in an African semi-arid agricultural landscape", Remote Sens Lett, 11(10), pp.883~892 (2020)[DOI]
  29. Kim JH, "Multicollinearity and misleading statistical results", Korean J Anesthesiol, 72(6), pp.558~569 (2019)[DOI]
  30. Li W, "Mapping crop leaf area index and canopy chlorophyll content using UAV multispectral imagery : impacts of illuminations and distribution of input variables", Remote Sens, 15(6), pp.1539~ (2023)[DOI]
  31. Lillesand TM, "Remote sensing and image interpretation" (2015), Wiley
  32. Ma Y, "Estimation of cotton leaf area index(LAI)based on spectral transformation and vegetation index", Remote Sens, 14(1), pp.136~ (2022)[DOI]
  33. Magney TS, "Mapping wheat nitrogen uptake from RapidEye vegetation indices", Precision Agric, 18, pp.429~451 (2017)[DOI]
  34. Main-Knorn M, "Calibration and validation plan for the l2A processor and products of the Sentinel-2 mission", Int Arch Photogramm Remote Sens Spatial Inf Sci, 40, pp.1249~1255 (2015)[DOI]
  35. Middinti S, "Estimating the leaf area index in Indian tropical forests using Landsat-8 OLI data", Int J Remote Sens, 38(23), pp.6769~6789 (2017)[DOI]
  36. Mourad R, "Assessment of leaf area index models using harmonized landsat and Sentinel-2 surface reflectance data over a semi-arid irrigated landscape", Remote Sens, 12(19), pp.3121~ (2020)[DOI]
  37. Muhe S, "Estimation of above-ground biomass in tropical afro-montane forest using Sentinel-2 derived indices", Environ Syst Res, 11, pp.5~ (2022)[DOI]
  38. Mwangi P, "Analysis of the relationship between land surface temperature and vegetation and built-up indices in Upper-Hill, Nairobi", J Geosci Environ Prot, 6, pp.1~16 (2018)[DOI]
  39. Myneni RB, "Estimation of global leaf area index and absorbed par using radiative transfer models", IEEE Transactions Geosci Remote Sens, 35(6), pp.1380~1393 (1997)[DOI]
  40. O’Hagan A, "Bayesian analysis of computer code outputs : a tutorial", Reliab Eng Syst Saf, 91, pp.1290~1300 (2006)[DOI]
  41. Pasqualotto N, "Multi-crop green LAI estimation with a new simple Sentinel-2 LAI index(SeLI)", Sens, 19(4), pp.904~ (2019)[DOI]
  42. Pasqualotto N, "Retrieval of evapotranspiration from Sentinel-2 : comparison of vegetation indices, semi-empirical models and SNAP biophysical processor approach", Agronomy, 9(10), pp.663~ (2019)[DOI]
  43. Pizaña JMG, "Environmental applications of remote sensing", pp.3~40 (2016), InTechOpen
  44. Reygadas Y, "Assessing the relationship between vegetation greenness and surface temperature through granger causality and impulse-response coefficients : a case study in Mexico", Int J Remote Sens, 41(10), pp.3761~3783 (2020)[DOI]
  45. Richter K, "Evaluation of Sentinel-2 spectral sampling for radiative transfer model based LAI estimation of wheat, sugar beet, and maize", IEEE J Sel Top Appl Earth Observat Remote Sens, 4(2), pp.458~464 (2011)[DOI]
  46. Sikand MV, "Radiative transfer models : available tools, patents and commercial potential to remote sensing", Recent Pat Sp Technol, 2(1), pp.49~56 (2012)[DOI]
  47. Singh J, "Estimation of leaf area by mobile application: fast and accurate method", Pharma Innovation J, 10(4S), pp.272~275 (2021)[DOI]
  48. Sishodia RP, "Applications of remote sensing in precision agriculture : a review", Remote Sens, 12(19), pp.3136~ (2020)[DOI]
  49. Sola I, "Assessment of atmospheric correction methods for Sentinel-2 images in Mediterranean landscapes", Int J Appl Earth Obs Geoinf, 73, pp.63~76 (2018)[DOI]
  50. Stenberg P, "Performance of the LAI-2000 plant canopy analyzer in estimating leaf area index of some Scots pine stands", Tree Physiol, 14, pp.981~995 (1994)[DOI]
  51. Upreti D, "A comparison of hybrid machine learning algorithms for the retrieval of wheat biophysical variables from Sentinel-2", Remote Sens, 11(5), pp.481~ (2019)[DOI]
  52. Vafaei S, "Estimation of forest leaf area index using satellite multispectral and synthetic aperture radar data in Iran", iForest, 14, pp.278~284 (2021)[DOI]
  53. Verrelst J, "Experimental Sentinel-2 LAI estimation using parametric, non-parametric and physical retrieval methods – a comparison", ISPRS J Photogrammetry Remote Sens, 108, pp.260~272 (2015)[DOI]
  54. Verrelst J, "Emulation of leaf, canopy and atmosphere radiative transfer models for fast global sensitivity analysis", Remote Sens, 8(8), pp.673~ (2016)[DOI]
  55. Weiss M, "S2ToolBox Level 2 products: LAI, FAPAR, FCOVER - version 1.1. S2 Toolbox Level 2 Prod algorithm", ~ (2016)
  56. Xie Q, "Vegetation indices combining the red and red-edge spectral information for leaf area index retrieval", IEEE J Sel Top Appl Earth Observat Remote Sens, 11(5), pp.1482~1493 (2018)[DOI]
  57. Xie Q, "Retrieval of crop biophysical parameters from Sentinel-2 remote sensing imagery", Int J Appl Earth Observat Geoinf, 80, pp.187~195 (2019)[DOI]
  58. Xu J, "Forest and crop leaf area index estimation using remote sensing : research trends and future directions", Remote Sens, 12(18), pp.2934~ (2020)[DOI]
  59. Yao X, "Estimation of wheat LAI at middle to high levels using unmanned aerial vehicle narrowband multispectral imagery", Remote Sens, 9(12), pp.1304~ (2017)[DOI]
  60. Zhang J, "Combining texture, color, and vegetation indices from fixed-wing UAS imagery to estimate wheat growth parameters using multivariate regression methods", Comput Electron Agric, 185, pp.106138~ (2021)[DOI]
  61. Zhang Y, "Estimation of multi-species leaf area index based on Chinese GF-1 satellite data using look-up table and gaussian process regression methods", Sens, 20(9), pp.2460~ (2020)[DOI]
  62. Zheng G, "Retrieving leaf area index(LAI)using remote sensing : theories, methods and sensors", Sens, 9(4), pp.2719~2745 (2009)[DOI]

관련 논문AI추천

이 간행물의 다른 논문 (12건)