Applying Neural Networks to Hyperspectral and Multispectral Field Data for Discrimination of Cruciferous Weeds in Winter Crops

In the context of detection of weeds in crops for site-specific weed control, on-ground spectral reflectance measurements are the first step to determine the potential of remote spectral data to classify weeds and crops. Field studies were conducted for four years at different locations in Spain. We aimed to distinguish cruciferous weeds in wheat and broad bean crops, using hyperspectral and multispectral readings in the visible and near-infrared spectrum. To identify differences in reflectance between cruciferous weeds, we applied three classification methods: stepwise discriminant (STEPDISC) analysis and two neural networks, specifically, multilayer perceptron (MLP) and radial basis function (RBF). Hyperspectral and multispectral signatures of cruciferous weeds, and wheat and broad bean crops can be classified using STEPDISC analysis, and MLP and RBF neural networks with different success, being the MLP model the most accurate with 100%, or higher than 98.1%, of classification performance for all the years. Classification accuracy from hyperspectral signatures was similar to that from multispectral and spectral indices, suggesting that little advantage would be obtained by using more expensive airborne hyperspectral imagery. Therefore, for next investigations, we recommend using multispectral remote imagery to explore whether they can potentially discriminate these weeds and crops.

[1]  Francisca López-Granados,et al.  Weed detection for site-specific weed management: mapping and real-time approaches , 2011 .

[2]  M. Jurado-Expósito,et al.  Spectral discrimination of wild oat and canary grass in wheat fields for less herbicide application , 2010, Agronomy for Sustainable Development.

[3]  F. López-Granados,et al.  A digital elevation model to aid geostatistical mapping of weeds in sunflower crops , 2009, Agronomy for Sustainable Development.

[4]  Francisca López-Granados,et al.  Classifying Irrigated Crops as Affected by Phenological Stage Using Discriminant Analysis and Neural Networks , 2010 .

[5]  J. C. van de Zande,et al.  Classification of sugar beet and volunteer potato reflection spectra with a neural network and statistical discriminant analysis to select discriminative wavelengths , 2010 .

[6]  R. Blackshaw,et al.  A Sustainable Management Package to Improve Winter Wheat Production and Competition with Weeds , 2010 .

[7]  Luis García Torres,et al.  Clasificación de "diplotaxis virgata" y "Sinapis arvensis" en trigo, habas y guisantes mediante imágenes aéreas , 2009 .

[8]  M. Jurado-Expósito,et al.  Multispectral classification of grass weeds and wheat (Triticum durum) using linear and nonparametric functional discriminant analysis and neural networks , 2008 .

[9]  Alfred Stein,et al.  Are weed patches stable in location? Application of an explicitly two-dimensional methodology , 2007 .

[10]  G. McDonald,et al.  Increasing plant density improves weed competition in lentil (Lens culinaris) , 2007 .

[11]  P. Miller,et al.  Cropping sequence effect of pea and pea management on spring wheat in the northern Great Plains , 2006 .

[12]  M. Jurado-Expósito,et al.  Using remote sensing for identification of late-season grass weed patches in wheat , 2006, Weed Science.

[13]  R. King,et al.  Differentiation of turfgrass and common weed species using hyperspectral radiometry , 2006, Weed Science.

[14]  Francisca López-Granados,et al.  Spectral discrimination of Ridolfia segetum and sunflower as affected by phenological stage , 2006 .

[15]  Jan Jacobi,et al.  CLASSIFICATION OF WEED PATCHES IN QUICKBIRD IMAGES: VERIFICATION BY GROUND TRUTH DATA , 2006 .

[16]  I. Eleftherohorinos,et al.  Wild Mustard (Sinapis arvensis L.) Competition with Three Winter Cereals as Affected by Nitrogen Supply , 2005 .

[17]  T. F. Burks,et al.  Evaluation of Neural-network Classifiers for Weed Species Discrimination , 2005 .

[18]  Shiv O. Prasher,et al.  DISCRIMINANT ANALYSIS OF HYPERSPECTRAL DATA FOR ASSESSING WATER AND NITROGEN STRESSES IN CORN , 2005 .

[19]  P. Dutilleul,et al.  CLASSIFICATION ACCURACY OF DISCRIMINANT ANALYSIS, ARTIFICIAL NEURAL NETWORKS, AND DECISION TREES FOR WEED AND NITROGEN STRESS DETECTION IN CORN , 2005 .

[20]  L. Tian,et al.  A Review on Remote Sensing of Weeds in Agriculture , 2004, Precision Agriculture.

[21]  Ismail Kavdir,et al.  Discrimination of sunflower, weed and soil by artificial neural networks , 2004 .

[22]  M. Ashton,et al.  Accuracy assessments of hyperspectral waveband performance for vegetation analysis applications , 2004 .

[23]  L. Bruce,et al.  Detection of pitted morningglory (Ipomoea lacunosa) with hyperspectral remote sensing. II. Effects of vegetation ground cover and reflectance properties , 2004, Weed Science.

[24]  Mika Keränen,et al.  Automatic Plant Identification with Chlorophyll Fluorescence Fingerprinting , 2003, Precision Agriculture.

[25]  Canakkale Onsekiz,et al.  Discrimination of sunflower, weed and soil by artificial neural networks , 2004 .

[26]  M. Mas,et al.  Tillage system effects on weed communities in a 4-year crop rotation under Mediterranean dryland conditions , 2003 .

[27]  C. H. Koger,et al.  Detecting Late-Season Weed Infestations in Soybean (Glycine max)1 , 2003, Weed Technology.

[28]  A. Smith,et al.  Weed–Crop Discrimination Using Remote Sensing: A Detached Leaf Experiment1 , 2003, Weed Technology.

[29]  L. Bruce,et al.  Wavelet analysis of hyperspectral reflectance data for detecting pitted morningglory (Ipomoea lacunosa) in soybean (Glycine max) , 2003 .

[30]  Francisca López-Granados,et al.  Multi-species weed spatial variability and site-specific management maps in cultivated sunflower , 2003, Weed Science.

[31]  A. Skidmore,et al.  Spectral discrimination of vegetation types in a coastal wetland , 2003 .

[32]  Shiv O. Prasher,et al.  Potential of airborne hyperspectral remote sensing to detect nitrogen deficiency and weed infestation in corn , 2003 .

[33]  P. Lutman.  Estimation of seed production by Stellaria media, Sinapis arvensis and Tripleurospermum inodorum in arable crops , 2002 .

[34]  Bienvenido Visauta Vinacua.  Análisis estadístico con SPSS para Windows: estadística básica , 2002 .

[35]  Chun-Chieh Yang,et al.  Development of neural networks for weed recognition in corn fields , 2002 .

[36]  S. Brandt.  Management practices for black lentil green manure for the semi-arid Canadian prairies , 1999 .

[37]  P. Lancashire,et al.  A uniform decimal code for growth stages of crops and weeds , 1991 .

[38]  J. Everitt,et al.  Detecting Huisache (Acacia farnesiana) and Mexican Palo-verde (Parkinsonia aculeata) by Aerial Photography , 1987, Weed Science.

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

[40]  C. Jordan.  Derivation of leaf-area index from quality of light on the forest floor , 1969 .