تهیة نقشة شاخص سطح برگ گیاه نیشکر با استفاده از معکوس‌سازی تصاویر ابرطیفی ماهوارة PRISMA

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری گروه سنجش از دور و GIS، دانشکدة جغرافیا، دانشگاه تهران

2 دانشیار گروه سنجش از دور و GIS، دانشکدة جغرافیا، دانشگاه تهران

3 استاد گروه سنجش از دور و GIS، دانشکدة جغرافیا، دانشگاه تهران

4 پژوهشگر ارشد آزمایشگاه مشاهدات زمینی، آزمایشگاه پردازش تصویر، دانشگاه والنسیا، اسپانیا

چکیده

شاخص سطح برگ نقش مهمی در تبادل ماده و انرژی بین زمین و اتمسفر دارد. مانند سایر گیاهان، شاخص سطح برگ نیشکر معیار خوبی برای وضعیت سلامت و رشد این محصول است که به‌دلیل نقش آن در صنایع غذایی و انرژی، اهمیت اقتصادی بسیاری دارد. ماهوارة PRISMA که در سال 2019 پرتاب شد، یکی از جدیدترین منابع داده‌های ابرطیفی را فراهم کرده است که به‌ویژه، در تهیة نقشة متغیرهای گیاهی کاربرد دارد. در پژوهش حاضر، نوع جدیدی از شبکه‌های عصبی مصنوعی، موسوم به شبکة عصبی تنظیم‌شده با روش بیزین (BRANN) که قانون بیز را برای غلبه بر مشکل بیش‌برازش شبکه‌های عصبی به‌کار می‌برد، استفاده می‌شود. مدل یادشده روی مجموعه‌ای داده، متشکل از طیف دریافت‌شده ازطریق ماهوارة PRISMA به‌منزلة متغیر مستقل و مقادیر اندازه‌گیری شاخص سطح برگ نیشکر به‌منزلة متغیر وابسته، اجرا شد. اندازه‌گیری‌های زمینی شاخص سطح برگ نیشکر در 118 واحد نمونه‌برداری زمینی، روی مزارع کشت‌و‌صنعت نیشکر امیرکبیر در استان خوزستان و در هفت تاریخ متفاوت طی یک دوره رشد نیشکر در سال 1399، انجام شد. مقایسة عملکرد BRANN‌ با یک روش متعارف شبکة عصبی، یعنی شبکة آموزش‌دیده با روش لونبرگ‌ـ مارکوارت (LMANN) در بازیابی شاخص سطح برگ نیشکر از طیف PRISMA، حاکی از این است کهRMSE  بازیابی از 26/2 (m2/m2) به‌روش LMANN به 67/0 (m2/m2)، با استفاده از روش BRANN کاهش یافته است. در این پژوهش، به‌منظور کاهش ابعاد داده نیز از تبدیل مؤلفه‌های اصلی استفاده شد. در بازیابی شاخص سطح برگ از بیست مؤلفة‌ اصلی اول نیز RMSE از 41/1 (m2/m2) با استفاده از روش LMANN به 71/0 (m2/m2) طبق روش BRANN کاهش یافت. استفاده از مؤلفه‌های اصلی باعث کاهش چشمگیر زمان محاسباتی شد. با اجرای مدل آموزش‌دیدة BRANN‌ روی تصاویر PRISMA به‌صورت پیکسل‌به‌پیکسل، نقشة شاخص سطح برگ نیشکر تولید شد. ارزیابی این نقشه نشان داد که این نقشه تغییرات مکانی شاخص سطح برگ نیشکر را به‌خوبی نشان می‌دهد. نتایج این تحقیق بیانگر قابلیت بالای روش BRANN‌ و تصاویر PRISMA برای بازیابی شاخص سطح برگ نیشکر است.

کلیدواژه‌ها


عنوان مقاله [English]

Mapping Sugarcane Leaf Area Index by Inverting PRISMA Hyperspectral Images

نویسندگان [English]

  • Mohammad Hajeb 1
  • Saeid Hamzeh 2
  • Seyed Kazem Alavipanah 3
  • Jochem Verrelst 4
1 P.hd. Student, Dep. of Remote Sensing and GIS, Faculty of Geography, University of Tehran, Tehran
2 Associate Prof., Dep. of Remote Sensing and GIS, Faculty of Geography, University of Tehran, Tehran
3 Prof. of Dep. of Remote Sensing and GIS, Faculty of Geography, University of Tehran, Tehran
4 Image Processing Laboratory (IPL), Parc Científic, Universitat de Val`encia, Val`encia, Spain
چکیده [English]

Leaf Area Index (LAI) plays a critical role in the mass and energy exchanges between the earth and the atmosphere. Like of other plants, LAI of sugarcane is a good indicator of the health status and growth of this crop which is of great economic importance due to its role in the food and energy industries. Launched in 2019, the PRISMA satellite provides one of the most recent hyperspectral data sources which are applicable especially for mapping plant variables. In this study, a new kind of Artificial Neural Networks (ANN) so-called Bayesian Regularized Artificial Neural Networkk (BRANN) which applies Bayes' theorem to overcome the overfitting problem of neural networks is used. The model was implemented on a data set consisting of spectrum obtained by PRISMA satellite as an independent variable and sugarcane LAI measurements as a dependent variable. The ground measurements of sugarcane LAI were carried out in 118 elementary sampling units on the fields of Amir Kabir sugarcane cultivation and industry in Khuzestan province and on seven different dates during a sugarcane growth period in 2020. Comparing the performance of BRANN in retrieving sugarcane LAI from PRISMA spectra with that of a conventional ANN trained with the Levenberg-Marquardt algorithm (LMANN) indicates that the retrieval RMSE is reduced from 2.26 m2/m2 applying LMANN to 0.67 m2/m2 applying the BRANN method. In this study, the principle component analysis was also used dimensionality reduction. Retrieving LAI from the first 20  principle components, RMSE was also reduced from 1.41 m2/m2 applying LMANN to 0.71 m2/m2 applying BRANN. Exploiting principal components significantly reduced computational time. By implementing the calibrated BRANN model over the PRISMA image pixel by pixel, the sugarcane LAI map was generated. Evaluating this map showed that this map represents the spatial variations of sugarcane LAI well. The results of this study indicate the high performance of the BRANN method and high potential of PRISMA images to retrieve sugarcane LAI.

کلیدواژه‌ها [English]

  • Vegetation parameter retrieval
  • Leaf Area Index
  • Artificial Neural Networks
  • Inverting
  • Hyperspectral Remote Sensing
  • Sugarcane
ASI, 2020, PRISMA Product Specifications, 1-262.
Atzberger, C., 2010, Inverting the PROSAIL Canopy Reflectance Model Using Neural Nets Trained on Streamlined Databases, J. Spectr. Imaging, 1, P. a2, https://doi.org/ 10.1255/jsi.2010.a2.
Atzberger, C., Jarmer, T., Schlerf, M., Kötz, B. & Werner, W., 2003, Spectroradiometric Determination of Wheat Bio-Physical Variables: Comparison of Different Empirical-Statistical Approaches, Remote Sens. Transitions, Proc. 23rd EARSeL Symp, Belgium 2-5.
Bacour, C., Baret, F., Béal, D., Weiss, M. & Pavageau, K., 2006, Neural Network Estimation of LAI, fAPAR, fCover and LAI×Cab, from Top of Canopy MERIS REFLECTANCE DATA: PRINCIPLES and Validation, Remote Sens. Environ, 105, PP. 313-325, https://doi.org/https:// doi.org/10.1016/j.rse.2006.07.014.
Baret, F. & Buis, S., 2008, Estimating Canopy Characteristics from Remote Sensing Observations: Review of Methods and Associated Problems, Adv. L. Remote Sens. Syst. Model. Invers. Appl., PP. 173-201, https://doi.org/10.1007/978-1-4020-6450-0_7.
Bishop, C.M., 1995, Neural Networks for Pattern Recognition, Oxford University Press.
Buntine, W.L., 1991, Bayesian Back-Propagation 5.
Burden, F. & Winkler, D., 2008, Bayesian Regularization of Neural Networks, Methods Mol. Biol., 458, PP. 25-44, https://doi.org/10.1007/978-1-60327-101-1_3.
Casa, R., Upreti, D., Palombo, A., Pascucci, S., Yang, H., Yang, G., Huang, W. & Pignatti, S., 2020, Evaluation and Exploitation of Retrieval Algorithms for Estimating Biophysical Crop Variables Using Sentinel-2, Venµs and PRISMA Satellite Data, J. Geod. Geoinf. Sci., 3, PP. 79-88, https://doi.org/10.11947/j. JGGS.2020.0408
Choudhury, T.A., Hosseinzadeh, N. & Berndt, C.C., 2012, Improving the Generalization Ability of an Artificial Neural Network in Predicting In-Flight Particle Characteristics of an Atmospheric Plasma Spray Process, J. Therm. Spray Technol., 21, PP. 935-949, https://doi.org/ 10.1007/s11666-012-9775-9.
Combal, B., Baret, F. & Weiss, M., 2002, Improving Canopy Variables Estimation from Remote Sensing Data by Exploiting Ancillary Information, Case Study on Sugar Beet Canopies, Agronomie, 22, PP. 205-215, https://doi.org/10.1051/agro:2002008.
Dabrowska-Zielinska, K., Kogan, F., Ciolkosz, A., Gruszczynska, M. & Kowalik, W., 2002, Modelling of crop Growth Conditions and Crop Yield in Poland Using AVHRR-Based Indices, Int. J. Remote Sens., 23, PP. 1109-1123, https://doi.org/10.1080/01431160110070744.
Dan Foresee, F. & Hagan, M.T., 1997, Gauss-Newton Approximation to Bayesian Learning, in: IEEE International Conference on Neural Networks - Conference Proceedings. PP. 1930-1935, https://doi.org/10.1109/ICNN.1997.614194.
 
Danner, M., Berger, K., Wocher, M., Mauser, W. & Hank, T., 2021, Efficient RTM-Based Training of Machine Learning Regression Algorithms to Quantify Biophysical & Biochemical Traits of Agricultural Crops, ISPRS J. Photogramm. Remote Sens., 173, PP. 278-296, https://doi.org/https://doi.org/10.1016/ j.isprsjprs.2021.01.017.
Darvishzadeh, R., Skidmore, A., Schlerf, M. & Atzberger, C., 2008, Inversion of a Radiative Transfer Model for Estimating Vegetation LAI and Chlorophyll in a Heterogeneous Grassland, Remote Sensing of Environment, 112(5), PP. 2592-2604, https://doi.org/10. 1016/j.rse.2007.12.003.
De Grave, C., Verrelst, J., Morcillo-Pallarés, P., Pipia, L., Rivera-Caicedo, J.P., Amin, E., Belda, S. & Moreno, J., 2020, Quantifying Vegetation Biophysical Variables from the Sentinel-3/FLEX Tandem Mission: Evaluation of the Synergy of OLCI and FLORIS Data Sources, Remote Sens. Environ., 251, P. 112101, https://doi.org/ 10.1016/j.rse.2020.112101.
Demuth, H. & Beale, M., 2004, Neural Network Toolbox - For Use with MATLAB, Matlab.
Efron, B. & Tibshirani, R.J., 1994, An Introduction to the Bootstrap, CRC press.
Fang, H., Baret, F., Plummer, S. & Schaepman-Strub, G., 2019, An Overview of Global Leaf Area Index (LAI): Methods, Products, Validation, and Applications, Rev. Geophys., 57, PP. 739-799, https://doi.org/10.1029/2018RG000608.
Feng, N., Wang, F. & Qiu, Y., 2006, Novel Approach for Promoting the Generalization Ability of Neural Networks, Int. J. Signal Process, 2.
Gianola, D., Okut, H., Weigel, K.A. & Rosa, G.J., 2011, Predicting Complex Quantitative Traits with Bayesian Neural Networks: A Case Study with Jersey Cows and Wheat, BMC Genet., 12, P. 87, https://doi.org/10.1186/1471-2156-12-87.
Guarini, R., Loizzo, R., Longo, F., Mari, S., Scopa, T. & Varacalli, G., 2017, Overview of the Prisma Space and Ground Segment and Its Hyperspectral Products, in: International Geoscience and Remote Sensing Symposium (IGARSS), PP. 431-434, https://doi.org/10.1109/IGARSS.2017. 8126986.
Kayri, M., 2016, Predictive Abilities of Bayesian Regularization and Levenberg-Marquardt Algorithms in Artificial Neural Networks: A Comparative Empirical Study on Social Data, Math. Comput. Appl., 21, P. 20, https://doi.org/ 10.3390/mca21020020.
Kimes, D.S., Nelson, R.F., Manry, M.T. & Fung, A.K., 1998, Attributes of Neural Networks for Extracting Continuous Vegetation Variables from Optical and Radar Measurements, Int. J. Remote Sens., 19, PP. 2639-2663, https://doi.org/ 10.1080/014311698214433.
Kimes, D.S., Knyazikhin, Y., Privette, J.L., Abuelgasim, A.A. & Gao, F., 2000, Inversion Methods for physically‐Based Models, Remote Sens. Rev., 18, PP. 381-439, https://doi.org/10.1080/02757250009532396.
Kumar Sethy, P., Kanta Barpanda, N., Rath, A., Sethy, P.K., Patel, K. & Rath, A.K., 2019, BRANN Model for Identification of Rice Leaf Diseases Using Texture Feature, JETIR, 6(5), PP. 569-573.
Loizzo, R., Daraio, M., Guarini, R., Longo, F., Lorusso, R., DIni, L. & Lopinto, E., 2019, Prisma Mission Status and Perspective, in: International Geoscience and Remote Sensing Symposium (IGARSS), PP. 4503-4506, https://doi.org/10.1109/IGARSS.2019.8899272.
Lu, B., Dao, P.D., Liu, J., He, Y. & Shang, J., 2020, Recent Advances of Hyperspectral Imaging Technology and Applications in Agriculture, Remote Sens., 12, P. 2659, https://doi.org/10.3390/RS12162659.
Lwin, A., Yang, D. & Hong, X., 2020, Leveraging Bayesian Deep Learning for Spaceborne GNSS-R Retrieval on Global Soil Moisture, 2020 Int. Conf. Artif. Intell. Inf. Commun. ICAIIC 2020, PP. 352-355, https://doi.org/10.1109/ICAIIC48513.2020.9065053.
MacKay, D.J.C., 1992, Bayesian Interpolation, Neural Comput., 4, PP. 415-447, https:// doi.org/10.1162/neco.1992.4.3.415.
MacKay, D.J.C., 1995, Probable Networks and Plausible Predictions — A Review of Practical Bayesian Methods for Supervised Neural Networks, Netw. Comput. Neural Syst., 6, PP. 469-505, https://doi.org/10.1088/0954-898X_6_3_011.
Mzid, N., Castaldi, F., Tolomio, M., Pascucci, S., Casa, R. & Pignatti, S., 2022, Evaluation of Agricultural Bare Soil Properties Retrieval from Landsat 8, Sentinel‐2 and PRISMA Satellite Data, Remote Sens., 14, P. 714, https://doi.org/10.3390/rs14030714.
Neal, R.M., 2012, Bayesian Learning for Neural Networks, Springer Science & Business Media.
Okut, H., 2016, Bayesian Regularized Neural Networks for Small n Big p Data, Artificial Neural Networks - Models and Applications, IntechOpen, https://doi.org/ 10.5772/63256.
Pôças, I., Gonçalves, J., Costa, P.M., Gonçalves, I., Pereira, L.S. & Cunha, M., 2017, Hyperspectral-Based Predictive Modelling of Grapevine Water Status in the Portuguese Douro Wine Region, Int. J. Appl. Earth Obs. Geoinf., 58, PP. 177-190, https://doi.org/https://doi.org/10.1016/j.jag.2017.02.013.
Qu, Y., Wang, J., Wan, H., Li, X. & Zhou, G., 2008, A Bayesian Network Algorithm for Retrieving the Characterization of Land Surface Vegetation, Remote Sens. Environ., 112, PP. 613-622, https://doi.org/ https://doi.org/10.1016/j.rse.2007.03.031.
Richter, K., Atzberger, C., Hank, T.B. & Mauser, W., 2012, Derivation of Biophysical Variables from Earth Observation Data: Validation and Statistical Measures, J. Appl. Remote Sens., 6, PP. 063557-1, https://doi.org/10.1117/1.jrs.6.063557.
Rivera-Caicedo, J.P., Verrelst, J., Leonenko, G. & Moreno, J., 2013, Multiple Cost Functions and Regularization Options for Improved Retrieval of Leaf Chlorophyll Content and LAI through Inversion of the PROSAIL Model, Remote Sens., 5, PP. 3280-3304.
Rivera-Caicedo, J.P., Verrelst, J., Muñoz-Marí, J., Camps-Valls, G. & Moreno, J., 2017, Hyperspectral Dimensionality Reduction for Biophysical Variable Statistical Retrieval, ISPRS J. Photogramm. Remote Sens., 132, PP. 88-101, https://doi.org/ 10.1016/j.isprsjprs.2017.08.012.
Rumelhart, D.E., Hinton, G.E. & Williams, R.J., 1986, Learning Representations by Back-Propagating Errors, Nature, 323, PP. 533-536, https://doi.org/10.1038/323533a0.
Sanches, G.M., Graziano Magalhães, P.S. & Junqueira Franco, H.C., 2019, Site-Specific Assessment of Spatial and Temporal Variability of Sugarcane Yield Related to Soil Attributes, Geoderma, 334, PP. 90-98, https://doi.org/https://doi.org/10.1016/j.geoderma.2018.07.051.
Sariev, E. & Germano, G., 2020, Bayesian Regularized Artificial Neural Networks for the Estimation of the Probability of Default, Quant. Financ., 20, PP. 311-328, https://doi.org/10.1080/14697688.2019.1633014.
Sellers, P.J., Dickinson, R.E., Randall, D.A., Betts, A.K., Hall, F.G., Berry, J.A., Collatz, G.J., Denning, A.S., Mooney, H.A., Nobre, C.A., Sato, N., Field, C.B. & Henderson-Sellers, A., 1997, Modeling the Exchanges of Energy, Water, and Carbon between Continents and the Atmosphere, Science (80-. ), 275, PP. 502-509, https://doi.org/ 10.1126/science.275.5299.502.
Som-Ard, J., Atzberger, C., Izquierdo-Verdiguier, E., Vuolo, F., Immitzer, M., 2021, Remote Sensing Applications in Sugarcane Cultivation: A Review, Remote Sens., https://doi.org/10.3390/rs13204040.
Steyerberg, E.W., Harrell, F.E.J., Borsboom, G.J., Eijkemans, M.J., Vergouwe, Y. & Habbema, J.D., 2001, Internal Validation of Predictive Models: Efficiency of Some Procedures for Logistic Regression Analysis, J. Clin. Epidemiol., 54, PP. 774-781, https://doi.org/10.1016/s0895-4356(01) 00341-9.
Tagliabue, G., Boschetti, M., Bramati, G., Candiani, G., Colombo, R., Nutini, F., Pompilio, L., Rivera-Caicedo, J.P., Rossi, M., Rossini, M., Verrelst, J. & Panigada, C., 2022, Hybrid Retrieval of Crop Traits from Multi-Temporal PRISMA Hyperspectral Imagery, ISPRS J. Photogramm. Remote Sens., 187, PP. 362-377, https://doi.org/ 10.1016/j.isprsjprs.2022.03.014.
Teruel, D.A., Barbieri, V., & Ferraro Jr., L.A., 1997, Sugarcane Leaf Area Index Modeling under Different Soil Water Conditions, Sci. Agric., 54, PP. 39-44, https://doi.org/10.1590/s0103-90161997000300008.
Tikhonov, A.N., 1963, On the Solution of Ill-Posed Problems and the Method of Regularization, in: Doklady Akademii Nauk, Russian Academy of Sciences, PP. 501-504.
Urgesa, G.D. & Keyata, E.O., 2021, Effect of Harvesting Ages on Yield and Yield Components of Sugar Cane Varieties Cultivated at Finchaa Sugar Factory, Oromia, Ethiopia, Int. J. Food Sci., 2021, PP. 1-6, https://doi.org/10.1155/2021/ 2702095.
Vangi, E., D’amico, G., Francini, S., Giannetti, F., Lasserre, B., Marchetti, M. & Chirici, G., 2021, The New Hyperspectral Satellite Prisma: Imagery for Forest Types Discrimination, Sensors (Switzerland), 21(4), P. 1182, https://doi.org/10.3390/ s21041182.
Verrelst, J., Rivera, J.P., Leonenko, G., Alonso, L. & Moreno, J., 2014, Optimizing LUT-Based RTM Inversion for Semiautomatic Mapping of Crop Biophysical Parameters from Sentinel-2 and -3 Data: Role of Cost Functions, IEEE Trans. Geosci. Remote Sens., 52, PP. 257-269, https://doi.org/ 10.1109/TGRS.2013.2238242.
Verrelst, J., Camps-valls, G., Muñoz-marí, J., Pablo, J., Veroustraete, F., Clevers, J.G.P.W. & Moreno, J., 2015a, ISPRS Journal of Photogrammetry and Remote Sensing Optical Remote Sensing and the Retrieval of Terrestrial Vegetation Bio-Geophysical Properties – A Review, ISPRS J. Photogramm. Remote Sens., 108, PP. 273-290, https://doi.org/10.1016/ j.isprsjprs.2015.05.005.
Verrelst, J., Rivera, J.P., Veroustraete, F., Muñoz-Marí, J., Clevers, J.G.P.W., Camps-Valls, G. & Moreno, J., 2015b, Experimental Sentinel-2 LAI Estimation Using Parametric, Non-Parametric and Physical Retrieval Methods – A Comparison, ISPRS J. Photogramm. Remote Sens., 108, PP. 260-272, https://doi.org/https://doi.org/10.1016/j.isprsjprs.2015.04.013.
Verrelst, J., Malenovský, Z., Van der Tol, C., Camps-Valls, G., Gastellu-Etchegorry, J.-P., Lewis, P., North, P. & Moreno, J., 2019, Quantifying Vegetation Biophysical Variables from Imaging Spectroscopy Data: A Review on Retrieval Methods, Surv. Geophys., 40, PP. 589-629, https://doi.org/10.1007/s10712-018-9478-y.
Verrelst, J., Rivera-Caicedo, J.P., Reyes-Muñoz, P., Morata, M., Amin, E., Tagliabue, G., Panigada, C., Hank, T. & Berger, K., 2021, Mapping Landscape Canopy Nitrogen Content from Space Using PRISMA Data, ISPRS J. Photogramm. Remote Sens., 178, PP. 382-395, https://doi.org/10.1016/ j.isprsjprs.2021.06.017.
Verstraete, M.M., Pinty, B. & Myneni, R.B., 1996, Potential and Limitations of Information Extraction on the Terrestrial Biosphere from Satellite Remote Sensing, Remote Sens. Environ., 58, PP. 201-214, https://doi.org/https://doi.org/10.1016/S0034-4257(96)00069-7.
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.
Yan, D., Zhou, Q., Wang, J. & Zhang, N., 2017, Bayesian Regularisation Neural Network Based on Artificial Intelligence Optimisation, Int. J. Prod. Res., 55, PP. 2266-2287, https://doi.org/10.1080/00207543. 2016.1237785.
Yao, Y., Rosasco, L. & Caponnetto, A., 2007, On Early Stopping in Gradient Descent Learning, Constr. Approx., 26, PP. 289-315, https://doi.org/10.1007/s00365-006-0663-2.
Ye, L., Jabbar, S.F., Abdul Zahra, M.M. & Tan, M.L., 2021, Bayesian Regularized Neural Network Model Development for Predicting Daily Rainfall from Sea Level Pressure Data: Investigation on Solving Complex Hydrology Problem, Complexity, 2021, PP. 1-14, https://doi.org/ 10.1155/ 2021/6631564.