Crop classification using spectral indices derived from Sentinel-2A imagery

ABSTRACT Optical remote sensing is one of the most attractive options for generating crop cover maps because it enables computation of vegetation indices, which are useful for assessing the condition of vegetation. The Sentinel-2A Multispectral Instrument (MSI), which is a multispectral sensor with 13 bands covering the visible, near infrared and short-wave infrared (SWIR) wavelength regions, offers a vast number of vegetation indices. Spectral indices, which are combinations of spectral measurements at different wavelengths, have been used in the previous studies and they sometimes contributed to improve classification accuracies. In this study, 91 published spectral indices were calculated from the MSI data. Additionally, classification algorithms are essential for generating accurate maps and the random forests classifier is one of which possesses the five hyperparameters were applied. The improvements in classification accuracies were confirmed achieving an overall accuracy of 93.1% based on the reflectance at 4 bands and 8 spectral indices.

[1]  Robert H. Kewley,et al.  Data strip mining for the virtual design of pharmaceuticals with neural networks , 2000, IEEE Trans. Neural Networks Learn. Syst..

[2]  A. Huete,et al.  Overview of the radiometric and biophysical performance of the MODIS vegetation indices , 2002 .

[3]  Scott V. Ollinger,et al.  Canopy-scale relationships between foliar nitrogen and albedo are not observed in leaf reflectance and transmittance within temperate deciduous tree species , 2011 .

[4]  Q. Mcnemar.  Note on the sampling error of the difference between correlated proportions or percentages , 1947, Psychometrika.

[5]  Jinling Zhao,et al.  Evaluating the potential of vegetation indices for winter wheat LAI estimation under different fertilization and water conditions , 2015 .

[6]  Didier Tanré,et al.  Atmospherically resistant vegetation index (ARVI) for EOS-MODIS , 1992, IEEE Trans. Geosci. Remote. Sens..

[7]  A. Kayad,et al.  Prediction of Potato Crop Yield Using Precision Agriculture Techniques , 2016, PloS one.

[8]  Alexander Brenning,et al.  Using spectrotemporal indices to improve the fruit-tree crop classification accuracy , 2017 .

[9]  A. Huete,et al.  A Modified Soil Adjusted Vegetation Index , 1994 .

[10]  H. Ishwaran.  Variable importance in binary regression trees and forests , 2007, 0711.2434.

[11]  Nadine Gobron,et al.  Advanced vegetation indices optimized for up-coming sensors: Design, performance, and applications , 2000, IEEE Trans. Geosci. Remote. Sens..

[12]  P. Ashburn,et al.  The vegetative index number and crop identification , 1979 .

[13]  I. Herrmann,et al.  LAI assessment of wheat and potato crops by VENμS and Sentinel-2 bands , 2011 .

[14]  Roberta E. Martin,et al.  Spectroscopy of canopy chemicals in humid tropical forests , 2011 .

[15]  Cheng-Ru Chen,et al.  Monitoring of rice cropping intensity in the upper Mekong Delta, Vietnam using time-series MODIS data , 2012 .

[16]  Dennis W. Hancock,et al.  Relationships between Blue‐ and Red‐based Vegetation Indices and Leaf Area and Yield of Alfalfa , 2007 .

[17]  F. Baret,et al.  Potentials and limits of vegetation indices for LAI and APAR assessment , 1991 .

[18]  Mourad Lounis,et al.  Remote Sensing Techniques for Salt Affected Soil Mapping: Application to the Oran Region of Algeria , 2012 .

[19]  C. Woodcock,et al.  Classification and Change Detection Using Landsat TM Data: When and How to Correct Atmospheric Effects? , 2001 .

[20]  A. Brenning,et al.  Balancing misclassification errors of land cover classification maps using support vector machines and Landsat imagery in the Maipo river basin (Central Chile, 1975–2010) , 2013 .

[21]  J. Eitel,et al.  Using in‐situ measurements to evaluate the new RapidEye™ satellite series for prediction of wheat nitrogen status , 2007 .

[22]  Severino G. Salmo,et al.  Estimation and mapping of above-ground biomass of mangrove forests and their replacement land uses in the Philippines using Sentinel imagery , 2017 .

[23]  Felix Kogan,et al.  Seasonal and interannual responses of the vegetation and production of crops in Cordoba – Argentina assessed by AVHRR derived vegetation indices , 2007 .

[24]  W. E. Larson,et al.  Coincident detection of crop water stress, nitrogen status and canopy density using ground-based multispectral data. , 2000 .

[25]  J. A. Schell,et al.  Monitoring vegetation systems in the great plains with ERTS , 1973 .

[26]  Rei Sonobe,et al.  Assessing the suitability of data from Sentinel-1A and 2A for crop classification , 2017 .

[27]  M. Hardisky.  The Influence of Soil Salinity, Growth Form, and Leaf Moisture on-the Spectral Radiance of Spartina alterniflora Canopies , 2008 .

[28]  Chao Chen,et al.  Using Random Forest to Learn Imbalanced Data , 2004 .

[29]  Fumin Wang,et al.  New Vegetation Index and Its Application in Estimating Leaf Area Index of Rice , 2007 .

[30]  L. Rowan,et al.  Lithologic mapping in the Mountain Pass, California area using Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) data , 2003 .

[31]  Gregory Asner,et al.  Spectroscopic Remote Sensing of Non-Structural Carbohydrates in Forest Canopies , 2015, Remote. Sens..

[32]  John R. Miller,et al.  Scaling-up and model inversion methods with narrowband optical indices for chlorophyll content estimation in closed forest canopies with hyperspectral data , 2001, IEEE Trans. Geosci. Remote. Sens..

[33]  A. K. Skidmore,et al.  Derivation of the red edge index using the MERIS standard band setting , 2002 .

[34]  A. Karnieli,et al.  AFRI — aerosol free vegetation index , 2001 .

[35]  Martha C. Anderson,et al.  Toward mapping crop progress at field scales through fusion of Landsat and MODIS imagery , 2017 .

[36]  A. Gitelson,et al.  Use of a green channel in remote sensing of global vegetation from EOS- MODIS , 1996 .

[37]  Kiyoshi Honda,et al.  Estimation of methane emission from a deep-water rice field using Landsat TM and NOAA AVHRR: a case study of Bangkok Plain , 2000 .

[38]  Neal W. Aven,et al.  Mapping urban tree species using integrated airborne hyperspectral and LiDAR remote sensing data , 2017 .

[39]  J. K. Garg,et al.  A novel strategy for wetland area extraction using multispectral MODIS data , 2017 .

[40]  Compton J. Tucker,et al.  Monitoring corn and soybean crop development with hand-held radiometer spectral data , 1979 .

[41]  N. Benson,et al.  Landscape Assessment: Ground measure of severity, the Composite Burn Index; and Remote sensing of severity, the Normalized Burn Ratio , 2006 .

[42]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[43]  Maria Gruszczynska,et al.  Validation of satellite-derived soil-vegetation indices for prognosis of spring cereals yield reduction under drought conditions – Case study from central-western Poland , 2007 .

[44]  Cao Weixing,et al.  Monitoring soluble sugar, total nitrogen & its ratio in wheat leaves with canopy spectral reflectance , 2005 .

[45]  P. Atkinson,et al.  Random Forest classification of Mediterranean land cover using multi-seasonal imagery and multi-seasonal texture , 2012 .

[46]  Giorgos Mallinis,et al.  Analysis of Time-Series Spectral Index Data to Enhance Crop Identification Over a Mediterranean Rural Landscape , 2017, IEEE Geoscience and Remote Sensing Letters.

[47]  Moon S. Kim,et al.  The use of high spectral resolution bands for estimating absorbed photosynthetically active radiation (A par) , 1994 .

[48]  B. Pinty,et al.  GEMI: a non-linear index to monitor global vegetation from satellites , 1992, Vegetatio.

[49]  A. Huete.  A soil-adjusted vegetation index (SAVI) , 1988 .

[50]  N. H. Brogea,et al.  Comparing prediction power and stability of broadband and hyperspectral vegetation indices for estimation of green leaf area index and canopy chlorophyll density , 2022 .

[51]  Giles M. Foody,et al.  Status of land cover classification accuracy assessment , 2002 .

[52]  A. J. Richardsons,et al.  DISTINGUISHING VEGETATION FROM SOIL BACKGROUND INFORMATION , 1977 .

[53]  Moon S. Kim,et al.  Estimating Corn Leaf Chlorophyll Concentration from Leaf and Canopy Reflectance , 2000 .

[54]  J. Chen,et al.  Retrieving Leaf Area Index of Boreal Conifer Forests Using Landsat TM Images , 1996 .

[55]  Liu Chuang,et al.  Study on extraction of crop information using time-series MODIS data in the Chao Phraya Basin of Thailand , 2010 .

[56]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[57]  Edward M. Barnes,et al.  Remote Sensing of Cotton Nitrogen Status Using the Canopy Chlorophyll Content Index (CCCI) , 2008 .

[58]  Matthias Drusch,et al.  Sentinel-2: ESA's Optical High-Resolution Mission for GMES Operational Services , 2012 .

[59]  Achim Zeileis,et al.  Conditional variable importance for random forests , 2008, BMC Bioinformatics.

[60]  Hirokazu Yamamoto,et al.  Inter-Comparison of ASTER and MODIS Surface Reflectance and Vegetation Index Products for Synergistic Applications to Natural Resource Monitoring , 2008, Sensors.

[61]  H. Shimamura,et al.  Random forest classification of crop type using multi-temporal TerraSAR-X dual-polarimetric data , 2014 .

[62]  G. Asner.  Biophysical and Biochemical Sources of Variability in Canopy Reflectance , 1998 .

[63]  A. Gitelson,et al.  Nondestructive estimation of anthocyanins and chlorophylls in anthocyanic leaves. , 2009, American journal of botany.

[64]  Fumin Wang,et al.  DEVELOPMENT OF A VEGETATION INDEX FOR ESTIMATION OF LEAF AREA INDEX BASED ON SIMULATION MODELING , 2010 .

[65]  Rei Sonobe,et al.  Combining ASNARO-2 XSAR HH and Sentinel-1 C-SAR VH/VV Polarization Data for Improved Crop Mapping , 2019, Remote. Sens..

[66]  Rei Sonobe,et al.  Estimating leaf carotenoid contents of shade-grown tea using hyperspectral indices and PROSPECT–D inversion , 2018 .

[67]  M. Hill.  Vegetation index suites as indicators of vegetation state in grassland and savanna: An analysis with simulated SENTINEL 2 data for a North American transect , 2013 .

[68]  D. Sims,et al.  Relationships between leaf pigment content and spectral reflectance across a wide range of species, leaf structures and developmental stages , 2002 .

[69]  G. Agati,et al.  New vegetation indices for remote measurement of chlorophylls based on leaf directional reflectance spectra. , 2001, Journal of photochemistry and photobiology. B, Biology.

[70]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[71]  Erwan Scornet,et al.  A random forest guided tour , 2015, TEST.

[72]  Hemant Ishwaran,et al.  Random Survival Forests , 2008, Wiley StatsRef: Statistics Reference Online.

[73]  J. Chen.  Evaluation of Vegetation Indices and a Modified Simple Ratio for Boreal Applications , 1996 .

[74]  Bisun Datt,et al.  Remote Sensing of Water Content in Eucalyptus Leaves , 1999 .

[75]  John R. Miller,et al.  Remote Estimation of Crop Chlorophyll Content Using Spectral Indices Derived From Hyperspectral Data , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[76]  Ashutosh Kumar Singh,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2010 .

[77]  John R. Miller,et al.  Integrated narrow-band vegetation indices for prediction of crop chlorophyll content for application to precision agriculture , 2002 .

[78]  Jan G. P. W. Clevers,et al.  Remote estimation of crop and grass chlorophyll and nitrogen content using red-edge bands on Sentinel-2 and -3 , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[79]  G. Rondeaux,et al.  Optimization of soil-adjusted vegetation indices , 1996 .

[80]  Hiroshi Tani,et al.  Mapping crop cover using multi-temporal Landsat 8 OLI imagery , 2017 .

[81]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[82]  Tian Yong.  Monitoring Soluble Sugar, Total Nitrogen & Its Ratio in Wheat Leaves with Canopy Spectral Reflectance , 2005 .

[83]  Anatoly A. Gitelson,et al.  Reflectance Spectral Features and Detection of Superficial Scald–induced Browning in Storing Apple Fruit , 2001 .

[84]  G. Foody.  Classification accuracy comparison: hypothesis tests and the use of confidence intervals in evaluations of difference, equivalence and non-inferiority , 2009 .

[85]  A. Huete,et al.  Development of a two-band enhanced vegetation index without a blue band , 2008 .

[86]  Gérard Dedieu,et al.  Assessing the robustness of Random Forests to map land cover with high resolution satellite image time series over large areas , 2016 .

[87]  A. Gitelson.  Wide Dynamic Range Vegetation Index for remote quantification of biophysical characteristics of vegetation. , 2004, Journal of plant physiology.

[88]  B. Wardlow,et al.  Large-area crop mapping using time-series MODIS 250 m NDVI data: An assessment for the U.S. Central Great Plains , 2008 .

[89]  A. Huete,et al.  Vegetation Index Methods for Estimating Evapotranspiration by Remote Sensing , 2010 .

[90]  L. Lymburner,et al.  Estimation of Canopy-Average Surface-Specific Leaf Area Using Landsat TM Data , 2000 .

[91]  Timothy A. Warner,et al.  Does spatial resolution matter? A multi-scale comparison of object-based and pixel-based methods for detecting change associated with gas well drilling operations , 2013 .

[92]  Menas Kafatos,et al.  Inter-annual variability of vegetation cover and rainfall over india , 2007 .

[93]  R. Pontius,et al.  Death to Kappa: birth of quantity disagreement and allocation disagreement for accuracy assessment , 2011 .

[94]  A. Gitelson,et al.  Novel algorithms for remote estimation of vegetation fraction , 2002 .

[95]  Udaya B. Kogalur,et al.  Random Survival Forests for R , 2007 .

[96]  C. Tucker.  Red and photographic infrared linear combinations for monitoring vegetation , 1979 .

[97]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[98]  John R. Miller,et al.  Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies: Modeling and validation in the context of precision agriculture , 2004 .

[99]  Paulo Cortez,et al.  Using sensitivity analysis and visualization techniques to open black box data mining models , 2013, Inf. Sci..

[100]  M. Cho,et al.  An investigation into robust spectral indices for leaf chlorophyll estimation , 2011 .

[101]  R. Fensholt,et al.  Derivation of a shortwave infrared water stress index from MODIS near- and shortwave infrared data in a semiarid environment , 2003 .

[102]  C. Daughtry,et al.  Remote Sensing Leaf Chlorophyll Content Using a Visible Band Index , 2011 .

[103]  R. Crippen.  Calculating the vegetation index faster , 1990 .

[104]  B. Datt.  Remote Sensing of Chlorophyll a, Chlorophyll b, Chlorophyll a+b, and Total Carotenoid Content in Eucalyptus Leaves , 1998 .

[105]  A. Gitelson,et al.  Optical Properties and Nondestructive Estimation of Anthocyanin Content in Plant Leaves¶ , 2001, Photochemistry and photobiology.

[106]  G. Metternicht.  Vegetation indices derived from high-resolution airborne videography for precision crop management , 2003 .

[107]  Filiz Sunar,et al.  Process-based image analysis for agricultural mapping: A case study in Turkgeldi region, Turkey , 2015 .

[108]  Chenghai Yang,et al.  Airborne hyperspectral imagery and linear spectral unmixing for mapping variation in crop yield , 2007, Precision Agriculture.

[109]  KyleA. Hartfield,et al.  Contemporary and historical classification of crop types in Arizona , 2013 .