Spectral Identification of Disease in Weeds Using Multilayer Perceptron with Automatic Relevance Determination

Microbotryum silybum, a smut fungus, is studied as an agent for the biological control of Silybum marianum (milk thistle) weed. Confirmation of the systemic infection is essential in order to assess the effectiveness of the biological control application and assist decision-making. Nonetheless, in situ diagnosis is challenging. The presently demonstrated research illustrates the identification process of systemically infected S. marianum plants by means of field spectroscopy and the multilayer perceptron/automatic relevance determination (MLP-ARD) network. Leaf spectral signatures were obtained from both healthy and infected S. marianum plants using a portable visible and near-infrared spectrometer (310–1100 nm). The MLP-ARD algorithm was applied for the recognition of the infected S. marianum plants. Pre-processed spectral signatures served as input features. The spectra pre-processing consisted of normalization, and second derivative and principal component extraction. MLP-ARD reached a high overall accuracy (90.32%) in the identification process. The research results establish the capacity of MLP-ARD to precisely identify systemically infected S. marianum weeds during their vegetative growth stage.

[1]  Roberto Oberti,et al.  Detection of biotic and abiotic stresses in crops by using hierarchical self organizing classifiers , 2017, Precision Agriculture.

[2]  T R Brown,et al.  NMR spectral quantitation by principal component analysis , 2001, NMR in biomedicine.

[3]  L. Plümer,et al.  Development of spectral indices for detecting and identifying plant diseases , 2013 .

[4]  C. Lacomme.  Plant Pathology , 2015, Methods in Molecular Biology.

[5]  B. Lorenzen,et al.  Changes in leaf spectral properties induced in barley by cereal powdery mildew , 1989 .

[6]  T. Malthus,et al.  High resolution spectroradiometry: Spectral reflectance of field bean leaves infected by Botrytis fabae , 1993 .

[7]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[8]  H. Ghosheh.  Constraints in implementing biological weed control: A review , 2005 .

[9]  R. Barnes,et al.  Standard Normal Variate Transformation and De-Trending of Near-Infrared Diffuse Reflectance Spectra , 1989 .

[10]  Xanthoula Eirini Pantazi,et al.  Detection of Silybum marianum infection with Microbotryum silybum using VNIR field spectroscopy , 2017, Comput. Electron. Agric..

[11]  V. A. Gulhane Dr. A. A. Gurjar,et al.  Detection of Diseases on Cotton Leaves and its Possible Diagnosis , 2011 .

[12]  Martin J. Kropff,et al.  A simple model of crop loss by weed competition from early observations on relative leaf area of the weeds , 1991 .

[13]  Khan,et al.  Impact of crop and weed densities on competition between wheat and Silybum marianum Gaertn. , 2006 .

[14]  J. F. Ortega,et al.  Estimation of leaf area index in onion (Allium cepa L.) using an unmanned aerial vehicle , 2013 .

[15]  R. Westerman,et al.  Palmer Amaranth (Amaranthus palmeri) Effects on the Harvest and Yield of Grain Sorghum (Sorghum bicolor)1 , 2004, Weed Technology.

[16]  W. Parsons,et al.  Noxious Weeds of Australia , 2001 .

[17]  G. K. Vianna,et al.  A Neural Network Classifier for Estimation of the Degree of Infestation by Late Blight on Tomato Leaves , 2016 .

[18]  Taskin Kavzoglu,et al.  Increasing the accuracy of neural network classification using refined training data , 2009, Environ. Model. Softw..

[19]  Wang Xiangdong,et al.  Recognition of Greenhouse Cucumber Disease Based on Image Processing Technology , 2013 .

[20]  Aditya Singh,et al.  Leaf and Canopy Level Detection of Fusarium Virguliforme (Sudden Death Syndrome) in Soybean , 2018, Remote. Sens..

[21]  Thomas Elmqvist,et al.  Use of near-infrared reflectance spectrometry and multivariate data analysis to detect anther smut disease (Microbotryum violaceum) in Silene dioica , 1994 .

[22]  R. D. Goeden.  The Phytophagous Insect Fauna of Milk Thistle In Southern California , 1971 .

[23]  T. W. Anderson.  An Introduction to Multivariate Statistical Analysis, 2nd Edition. , 1985 .

[24]  Alice N. Cheeran,et al.  Color Transform Based Approach for Disease Spot Detection on Plant Leaf , 2012 .

[25]  Anja Vogler,et al.  An Introduction to Multivariate Statistical Analysis , 2004 .

[26]  A. Kulkarni,et al.  Applying image processing technique to detect plant diseases , 2012 .

[27]  B. S. Ausmus,et al.  Reflectance studies of healthy, maize dwarf mosaic virus-infected, and Helminthosporium maydis-infected corn leaves , 1971 .

[28]  Jayamala K. Patil,et al.  Color Feature Extraction of Tomato Leaf Diseases , 2011 .

[29]  Dimitrios Moshou,et al.  Evaluation of UAV imagery for mapping Silybum marianum weed patches , 2017 .

[30]  W. Donald,et al.  Canada Thistle (Cirsium arvense) Effects on Yield Components of Spring Wheat (Triticum aestivum) , 1996, Weed Science.

[31]  F. Howes.  Poisonous Plants , 1958, Nature.

[32]  A. Caesar,et al.  Insect - Pathogen synergisms are the foundation of weed biocontrol , 1999 .

[33]  Christina Gloeckner,et al.  Modern Applied Statistics With S , 2003 .

[34]  K. A. Hibberd,et al.  Herbicide Resistance in Plants , 2020 .

[35]  D. Berner,et al.  Microbotryum silybum sp. nov. (Microbotryales) , 2003 .

[36]  Max Kuhn,et al.  Building Predictive Models in R Using the caret Package , 2008 .