نوع مقاله : علمی - پژوهشی

نویسندگان

1 کارشناسی ارشد سنجش از دور و GIS، دانشگاه تربیت مدرس

2 استادیار گروه سنجش از دور و GIS، دانشگاه تربیت مدرس

چکیده

متغیرهای بیوفیزیکی و بیوشیمیایی پوشش گیاهی، به‌منزلة متغیرهای ورودی، برای مدل‌های متفاوت چرخة کربن، آب، انرژی و مدل‌های اقلیمی و کشاورزی دقیق نقش مهمی ایفا‌ می‌کنند. یکی از مهم‌ترین متغیرهای مربوط به تاج‌پوشش گیاه، که کاربردهای فراوانی در مدل‌سازی‏های گوناگون خاک و گیاه و اتمسفر دارد، شاخص سطح برگ (LAI) است. روش‏های گوناگونی برای بازیابی LAI از تصاویر ابرطیفی به‌کار رفته‌اند که، از میان آنها، روش‏های ناپارامتریک غیرخطی یادگیری ماشین بسیار مورد توجه قرار گرفته‌اند زیرا، در مواجهه با داده‌های دارای ابعاد زیاد، انعطاف‌پذیرند. بااین‌حال، در مطالعات پیشین، به بررسی عملکرد روش‏های یادگیری ماشین در بازیابی مقادیر LAI در مقادیر حاشیه‏ای (مقادیر خارج از دامنة نمونه‏گیری زمینی) و قابلیت این روش‌ها در تهیة نقشة متغیر توجه چندانی نشده است. در این تحقیق، عملکرد چهار روش پرکاربرد یادگیری ماشین شامل رگرسیون بردار پشتیبان، فرایند گاوسی، شبکة عصبی مصنوعی و جنگل تصادفی در بازیابی LAI از تصویر ابرطیفی ماهوارة کریس‌ـ پروبا بررسی شده است. نتایج نشان داد که، به‌رغم کارآیی هر چهار روش در بازیابی مقادیر LAI برای دامنة مقادیر اندازه‏گیری‌‌شدة زمینی با RMSE بهتر از 0.5 و خطای نسبی کمتر از 10%، روش‏های فرایند گاوسی و رگرسیون بردار پشتیبان صحت بالاتری در مقایسه با سایر روش‏ها دارند. باوجوداین، عملکرد روش شبکة عصبی مصنوعی، در تخمین LAIهای دارای مقادیر حاشیه‏ای، بهتر از دیگر روش‏هاست و نقشة تهیه‌شده با این روش و تابع یادگیری GDA  تطابق بیشتری با نقشة NDVI و تصویر ابرطیفی منطقه دارد.

کلیدواژه‌ها

عنوان مقاله [English]

Comparative analysis of LAI retrieval from hyperspectral imagery using machine learning approaches

نویسندگان [English]

  • Behzad Mohammadi Sheikh Razi 1
  • Mohammad Sharif Molla 1
  • Ali Jafar Mousivand 2
  • Ali Shamsoddini 2

1 M.sc. in Remote Sensing and GIS, Tarbiat Modarres University

2 . Assistant prof. of Remote Sensing, Remote Sensing and GIS Dep., Tarbiat Modarres University

چکیده [English]

< p >Vegetation biophysical and biochemical variables are key inputs to a wide range of modelling approaches for carbon, water, energy cycle, climate and agricultural applications. Leaf Area Index (LAI) is among the most important canopy variables, used by many different physiological and functional plant models. Several approaches have been developed for vegetation properties retrieval from remotely sensed hyperspectral data. Among them, nonparametric machine learning methods have increasingly gained attention in vegetation variable retrieval due to their flexibility and efficiency while working with data of high dimensionality over the last decades. Although these methods provide reasonable accuracy at relatively high speed, they are mainly restricted to estimate values within their training domain and often perform poorly on the marginal values (i.e. outside of the training domain). The performance of these methods has not been adequately studied in retrieving LAI on the marginal values. This study employs four well-known machine learning methods including SVR, GPR, ANN, and RF to retrieve LAI from a hyperspectral CHRIS-Proba image over Barrax, Spain, in order to inspect their capability in retrieving marginal values. The results showed that although all the methods perform similarly well on retrieving LAI over the training domain values with RMSE values of less than 0.5 and relative error of less than 10%, GPR and SVR performed slightly better. However, ANN outperformed the other methods in estimating LAI on the marginal values, resulted in the generated LAI map more consistent with the NDVI map, as well as, the hyperspectral image of the region.

کلیدواژه‌ها [English]

  • Parameter retrieval
  • Leaf Area Index
  • nonparameteric machine leraning
  • CHRIS-Proba
Asner, G.P., 1998, Biophysical and Biochemical Sources of Variability in Canopy Reflectance, Remote Sensing of Environment, 64(3), PP. 234-253.
Atkinson, P.M. & Tatnall, A.R., 1997, Introduction Neural Networks in Remote Sensing, International Journalof Remote Sensing, 18(4), PP. 699-709.
Baptista, F.D., Rodrigues, S. & Morgado-Dias, F., 2013, Performance Comparison of ANN Training Algorithms for Classification, Paper presented at the 2013 IEEE 8th International Symposium on Intelligent Signal Processing.
Baret, F. & Buis, S., 2008, Estimating Canopy Characteristics from Remote Sensing Observations: Review of Methods and Associated Problems, In Advances in Land Remote Sensing (PP. 173-201), Springer.
 
ـــــــــــــــــــــــــــــــــــــــــــــــــــــــــــ
1. Extrapolation
2. Adaptability
3. Vegetation Properties Mapping
 
 
Baret, F., Hagolle, O., Geiger, B., Bicheron, P., Miras, B., Huc, M., . . . & Samain, O., 2007, LAI, fAPAR and fCover CYCLOPES global Products Derived from VEGETATION: Part 1: Principles of the Algorithm, Remote Sensing of Environment, 110(3), PP. 275-286.
Belgiu, M. & Drăguţ, L., 2016, Random Forest in Remote Sensing: A Review of Applications and Future Directions, ISPRS Journal of Photogrammetry and Remote Sensing, 114, PP. 24-31.
Breiman, L., 2001, Random Forests, Machine learning, 45(1), PP. 5-32.
Camps-Valls, G., 2009, Machine Learning in Remote Sensing Data Processing, Paper presented at the 2009 IEEE International Workshop on Machine Learning for Signal Processing.
Camps-Vails, G., Gómez-Chova, L., Muñoz-Mari, J., Vila-Francés, J., Amoros, J., del Valle-Tascon, S. & Calpe-Maravilla, J., 2009, Biophysical Parameter Estimation with Adaptive Gaussian Processes, Paper presented at the 2009 IEEE International Geoscience and Remote Sensing Symposium.
Camps-Valls, G., Verrelst, J., Munoz-Mari, J., Laparra, V., Mateo-Jimenez, F. & Gomez-Dans, J., 2016, A Survey on Gaussian Processes for Earth-Observation Data Analysis: A Comprehensive Investigation, IEEE Geoscience and Remote Sensing Magazine, 4(2), PP. 58-78.
Cherkassky, V. & Ma, Y., 2004, Practical Selection of SVM Parameters and Noise Estimation for SVM Regression, Neural Networks, 17(1), PP. 113-126.
Clevers, J., 2014, Beyond NDVI: Extraction of Biophysical Variables from Remote Sensing Imagery, In Land Use and Land Cover Mapping in Europe (PP. 363-381), Springer.
Darvishzadeh, R., 2008, Hyperspectral Remote Sensing of Vegetation Parameters Using Statistical and Physical Models.
Demuth, H. & Beale, M., 1998, User’s Guide for Neural Network Toolbox for Use with MATLAB, The Mathworks Inc., Natick, 3.
Durbha, S.S., King, R.L. & Younan, N.H., 2007, Support Vector Machines Regression for Retrieval of Leaf Area Index from Multiangle Imaging Spectroradiometer, Remote Sensing of Environment, 107(1-2), PP. 348-361.
Duveiller, G., Weiss, M., Baret, F. & Defourny, P., 2011, Retrieving Wheat Green Area Index During the Growing Season from Optical Time Series Measurements Based on Neural Network Radiative Transfer Inversion, Remote Sensing of Environment, 115(3), PP. 887-896.
Erästö, P., 2001, Support Vector Machines-Backgrounds and Practice.
Fawagreh, K., Gaber, M.M. & Elyan, E., 2014, Random Forests: From Early Developments to Recent Advancements, Systems Science & Control Engineering: An Open Access Journal, 2(1), PP. 602-609.
Hagan, M.T., Demuth, H.B., Beale, M.H. & De Jesús, O., 1996, Neural Network Design (Vol. 20), Pws Pub. Boston.
Kimes, D.S., Knyazikhin, Y., Privette, J., Abuelgasim, A. & Gao, F., 2000, Inversion Methods for Physically‐Based Models, Remote Sensing Reviews, 18(2-4), PP. 381-439.
Kumar, P., Gupta, D.K., Mishra, V.N. & Prasad, R., 2015, Comparison of Support Vector Machine, Artificial Neural Network, and Spectral Angle Mapper Algorithms for Crop Classification Using LISS IV Data, International Journal of Remote Sensing, 36(6), PP. 1604-1617.
Kuss, M. & Rasmussen, C.E., 2005, Assessing Approximate Inference for Binary Gaussian Process Classification, Journal of Machine Learning Research, 6(Oct), PP. 1679-1704.
Lawrence, N., 2005, Probabilistic Non-Linear Principal Component Analysis with Gaussian Process Latent Variable Models, Journal of Machine Learning Research, 6(Nov), PP. 1783-1816.
LeCun, Y., Touresky, D., Hinton, G. & Sejnowski, T., 1988, A Theoretical Framework for Back-Propagation, Paper presented at the Proceedings of the 1988 Connectionist Models Summer School.
Menenti, M., Rast, M., Baret, F., van den Hurk, B., Knorr, W., Mauser, W., . . . & Verstraete, M., 2003, Understanding Vegetation Response to Climate Variability from Space: Recent Advances towards the SPECTRA Mission, Paper presented at the EGS-AGU-EUG Joint Assembly.
Meroni, M., Colombo, R. & Panigada, C., 2004, Inversion of a Radiative Transfer Model with Hyperspectral Observations for LAI Mapping in Poplar Plantations, Remote Sensing of Environment, 92(2), PP. 195-206.
Moreno, J.F., Baret, F., Leroy, M., Menenti, M., Rast, M. & Shaepman, M., 2003, Retrieval of Vegetation Properties from Combined Hyperspectral/Multiangular Optical Measurements: Results from the DAISEX Campaigns, Paper presented at the IGARSS 2003, 2003 IEEE International Geoscience and Remote Sensing Symposium, Proceedings (IEEE Cat. No. 03CH37477).
Mousivand, A., 2015, Retrieval of Vegetation Properties Using Top of Atmosphere Radiometric Data: A Multi-Sensor Approach.
Mousivand, A., Menenti, M., Gorte, B. & Verhoef, W., 2014, Global Sensitivity Analysis of the Spectral Radiance of a Soil–Vegetation System, Remote Sensing of Environment, 145, PP. 131-144.
Mutanga, O., Adam, E. & Cho, M.A., 2012, High Density Biomass Estimation for Wetland Vegetation Using WorldView-2 Imagery and Random Forest Regression Algorithm, International Journal of Applied Earth Observation and Geoinformation, 18, PP. 399-406.
O'Hagan, A., 1978, Curve Fitting and Optimal Design for Prediction, Journal of the Royal Statistical Society: Series B (Methodological), 40(1), PP. 1-24.
Pham, T.D., Yoshino, K. & Bui, D.T., 2017, Biomass Estimation of Sonneratia Caseolaris (l.) Engler at a Coastal Area of Hai Phong City (Vietnam) Using ALOS-2 PALSAR Imagery and GIS-Based Multi-Layer Perceptron Neural Networks, GIScience & RemoteSensing, 54(3), PP. 329-353.
Rivera-Caicedo, J.P., Verrelst, J., Muñoz-Marí, J., Camps-Valls, G. & Moreno, J., 2017, Hyperspectral Dimensionality Reduction for Biophysical Variable Statistical Retrieval, ISPRS Journal of Photogrammetry and Remote Sensing, 132, PP. 88-101.
Rumelhart, D.E., Hinton, G.E. & McClelland, J.L., 1986, A General Framework for Parallel Distributed Processing, Parallel Distributed Processing: Explorations in the Microstructure of Cognition, 1(45-76), P. 26.
Sellers, P., Dickinson, R., Randall, D., Betts, A., Hall, F., Berry, J., . . . & Nobre, C., 1997, Modeling the Exchanges of Energy, Water, and Carbon between Continents and the Atmosphere, Science, 275(5299), PP. 502-509.
Smola, A.J. & Schölkopf, B., 1998, On a Kernel-Based Method for Pattern Recognition, Regression, Approximation, and Operator Inversion, Algorithmica, 22(1-2), PP. 211-231.
Smola, A.J. & Schölkopf, B., 2004, A Tutorial on Support Vector Regression, Statistics and Computing, 14(3), PP. 199-222.
Vapnik, V., 2013, TheNature of Statistical Learning Theory, Springer Science & Business Media.
Verger, A., Baret, F. & Camacho, F., 2011, Optimal Modalities for Radiative Transfer-Neural Network Estimation of Canopy Biophysical Characteristics: Evaluation over an Agricultural Area with CHRIS/PROBA Observations, Remote Sensing of Environment, 115(2), PP. 415-426.
Verrelst, J., Alonso, L., Camps-Valls, G., Delegido, J. & Moreno, J., 2012, Retrieval of Vegetation Biophysical Parameters Using Gaussian Process Techniques, IEEE Transactions on Geoscience and Remote Sensing, 50(5), PP. 1832-1843.
Verrelst, J., Malenovský, Z., Van der Tol, C., Camps-Valls, G., Gastellu-Etchegorry, J.-P., Lewis, P., . . . & Moreno, J., 2018, Quantifying Vegetation Biophysical Variables from Imaging Spectroscopy Data: A Review on Retrieval Methods, Surveys in Geophysics, PP. 1-41.
Verrelst, J., Rivera, J.P., Gitelson, A., Delegido, J., Moreno, J. & Camps-Valls, G., 2016, Spectral Band Selection for Vegetation Properties Retrieval Using Gaussian Processes Regression, International Journal of Applied Earth Observation and Geoinformation, 52, PP. 554-567.
Verrelst, J., Rivera, J.P., Veroustraete, F., Muñoz-Marí, J., Clevers, J.G., Camps-Valls, G. & Moreno, J., 2015, Experimental Sentinel-2 LAI Estimation Using Parametric, Non-Parametric and Physical Retrieval Methods–A Comparison, ISPRS Journal of Photogrammetry and Remote Sensing, 108, PP. 260-272.
Verstraete, M.M., Pinty, B. & Myneni, R.B., 1996, Potential and Limitations of Information Extraction on the Terrestrial Biosphere from Satellite Remote Sensing, Remote Sensing of Environment, 58(2), PP. 201-214.
Wang, F., Huang, J., Wang, Y., Liu, Z., Peng, D. & Cao, F., 2013, Monitoring Nitrogen Concentration of Oilseed Rape from Hyperspectral Data Using Radial Basis Function, International Journal of Digital Earth, 6(6), PP. 550-562.
Watson, D.J., 1947, Comparative Physiological Studies on the Growth of Field Crops: I. Variation in Net Assimilation Rate and Leaf Area between Species and Varieties, and within and between Years, Annals of Botany, 11(41), PP. 41-76.
Weiss, M., Baret, F., Smith, G., Jonckheere, I. & Coppin, P., 2004, Review of Methods for in Situ Leaf Area Index (LAI) Determination: Part II. Estimation of LAI, Errors and Sampling, Agricultural andForest Meteorology, 121(1-2), PP. 37-53.
Williams, C.K. & Rasmussen, C.E., 1996, Gaussian Processes for Regression, Paper presented at the Advances in Neural Information Processing Systems.
Williams, C.K. & Rasmussen, C.E., 2006, Gaussian Processesfor Machine Learning (Vol. 2), MIT Press Cambridge, MA.
Yi, G., Shi, J. & Choi, T., 2011, Penalized Gaussian Process Regression and Classification for High‐Dimensional Nonlinear Data, Biometrics, 67(4), PP. 1285-1294.
Yu, X., Hyyppä, J., Vastaranta, M., Holopainen, M. & Viitala, R., 2011, Predicting Individual Tree Attributes from Airborne Laser Point Clouds Based on the Random Forests Technique, ISPRS Journal of Photogrammetry and Remote Sensing, 66(1), PP. 28-37.
Yuan, H., Yang, G., Li, C., Wang, Y., Liu, J., Yu, H., ... & Yang, X., 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), P. 309.