Using Boruta-Selected Spectroscopic Wavebands for the Asymptomatic Detection of Fusarium Circinatum Stress

High spectral resolution multitemporal data were used to model asymptomatic stress caused by Fusarium circinatum in 3-month old Pinus radiata seedlings. The objectives of the study were: 1) to identify an optimal subset of wavebands that could model asymptomatic stress in P. radiata seedlings and 2) to develop a robust classification model for discriminating healthy and stressed seedlings. To achieve these objectives, spectral data were collected for healthy, infected, and damaged seedlings using a hand-held field spectroradiometer. The data were analyzed, first for combined classes and then for class pairs using the Boruta algorithm. Results indicated that the best discrimination was possible at week three for all classes, with a KHAT value of 0.79 and an out of bag error of 14.00% (CV error = 16.00%), using a subset of 107 wavebands. A closer examination of the class pairs, namely healthy-infected (H-I) and infected-damaged (I-D), showed improved discrimination with KHAT values of 0.82 and 0.84, respectively. The H-I class pair was classified using a subset of just 38 wavebands, whereas the I-D class pair was classified using a subset of just 40 wavebands. Overall, this study demonstrated that it is more difficult to discriminate asymptomatic stress when additional stress related classes are present. Nonetheless, the methodology developed in this study has the potential to be operationalized within a nursery environment for the early detection of F. circinatum-induced stress in P. radiata seedlings.

[1]  Russell G. Congalton,et al.  Assessing the accuracy of remotely sensed data : principles and practices , 1998 .

[2]  Laurie A. Chisholm,et al.  Spectral reflectance characteristics of Pinus radiata needles affected by dothistroma needle blight , 2003 .

[3]  Armando Apan,et al.  Detection of pests and diseases in vegetable crops using hyperspectral sensing: a comparison of reflectance data for different sets of symptoms , 2005 .

[4]  Witold R. Rudnicki,et al.  Feature Selection with the Boruta Package , 2010 .

[5]  P. Zimba,et al.  Detecting Sugarcane yellow leaf virus infection in asymptomatic leaves with hyperspectral remote sensing and associated leaf pigment changes. , 2010, Journal of virological methods.

[6]  G. Carter,et al.  Leaf optical properties in higher plants: linking spectral characteristics to stress and chlorophyll concentration. , 2001, American journal of botany.

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

[8]  O. Mutanga,et al.  Imaging spectroscopy (hyperspectral remote sensing) in southern Africa: an overview , 2010 .

[9]  Robin Genuer,et al.  Random Forests: some methodological insights , 2008, 0811.3619.

[10]  Pol Coppin,et al.  Detection of biotic stress (Venturia inaequalis) in apple trees using hyperspectral data: Non-parametric statistical approaches and physiological implications , 2007 .

[11]  Clark,et al.  Association of the pitch canker fungus, Fusarium subglutinans f.sp. pini, with Monterey pine seeds and seedlings in California , 1998 .

[12]  D. Moshou,et al.  The potential of optical canopy measurement for targeted control of field crop diseases. , 2003, Annual review of phytopathology.

[13]  Won Suk Lee,et al.  Original paper: Diagnosis of bacterial spot of tomato using spectral signatures , 2010 .

[14]  Pat Langley,et al.  Selection of Relevant Features and Examples in Machine Learning , 1997, Artif. Intell..

[15]  O. Mutanga,et al.  Discriminating the papyrus vegetation (Cyperus papyrus L.) and its co-existent species using random forest and hyperspectral data resampled to HYMAP , 2012 .

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

[17]  Thomas R. Gordon,et al.  Susceptibility of Douglas fir (Pseudotsuga menziesii) to pitch canker, caused by Gibberella circinata (anamorph = Fusarium circinatum) , 2006 .

[18]  H. Hiendl,et al.  Reflectance, Colour, and Histological Features as Parameters for the Early Assessment of Forest Damages , 1992 .

[19]  Jun Ma,et al.  The Genboree Microbiome Toolset and the analysis of 16S rRNA microbial sequences , 2012, BMC Bioinformatics.

[20]  Andrea Vannini,et al.  Interactive effects of drought and pathogens in forest trees , 2006 .

[21]  Onisimo Mutanga,et al.  Discriminating the early stages of Sirex noctilio infestation using classification tree ensembles and shortwave infrared bands , 2011 .

[22]  Onisimo Mutanga,et al.  A comparison of regression tree ensembles: Predicting Sirex noctilio induced water stress in Pinus patula forests of KwaZulu-Natal, South Africa , 2010, Int. J. Appl. Earth Obs. Geoinformation.

[23]  A. Bachelor.  GLOSSARY OF TERMS GLOSSARY OF TERMS , 2010 .

[24]  Onisimo Mutanga,et al.  Discriminating Sirex noctilio Attack in Pine Forest Plantations in South Africa Using High Spectral Resolution Data , 2008 .

[25]  Ye Zhang,et al.  Robust Hyperspectral Classification Using Relevance Vector Machine , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[26]  Joydeep Ghosh,et al.  Investigation of the random forest framework for classification of hyperspectral data , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[27]  Alexander Hapfelmeier,et al.  A new variable selection approach using Random Forests , 2013, Comput. Stat. Data Anal..

[28]  Elizabeth Pattey,et al.  Narrowband vegetation indexes and detection of disease damage in soybeans , 2004, IEEE Geoscience and Remote Sensing Letters.

[29]  Jean-Philippe Domenger,et al.  Document Images Indexing with Relevance Feedback: An Application to Industrial Context , 2011, 2011 International Conference on Document Analysis and Recognition.

[30]  E. Abdel-Rahman,et al.  Potential of spectroscopic data sets for sugarcane thrips (Fulmekiola serrata Kobus) damage detection , 2010 .

[31]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[32]  Elfatih M. Abdel-Rahman,et al.  Hand-held spectrometry for estimating thrips (Fulmekiola serrata) incidence in sugarcane , 2009, 2009 IEEE International Geoscience and Remote Sensing Symposium.

[33]  F. J. Pierce,et al.  The potential of spectral reflectance technique for the detection of Grapevine leafroll-associated virus-3 in two red-berried wine grape cultivars , 2009 .

[34]  Onisimo Mutanga,et al.  Determining the susceptibility of Eucalyptus nitens forests to Coryphodema tristis (cossid moth) occurrence in Mpumalanga, South Africa , 2013, Int. J. Geogr. Inf. Sci..

[35]  H. Lichtenthaler,et al.  The Stress Concept in Plants: An Introduction , 1998, Annals of the New York Academy of Sciences.

[36]  Gérard Biau,et al.  Analysis of a Random Forests Model , 2010, J. Mach. Learn. Res..

[37]  R. Knight,et al.  Supervised classification of human microbiota. , 2011, FEMS microbiology reviews.

[38]  Michelle M. Cram,et al.  Seed diseases and seedborne pathogens of North America , 2010 .

[39]  Witold R. Rudnicki,et al.  The All Relevant Feature Selection using Random Forest , 2011, ArXiv.

[40]  Witold R. Rudnicki,et al.  Boruta - A System for Feature Selection , 2010, Fundam. Informaticae.

[41]  Jean-Michel Poggi,et al.  Variable selection using random forests , 2010, Pattern Recognit. Lett..

[42]  Witold R. Rudnicki,et al.  A Deceiving Charm of Feature Selection: The Microarray Case Study , 2011, ICMMI.

[43]  M. Wingfield,et al.  Pitch canker caused by Fusarium circinatum — a growing threat to pine plantations and forests worldwide , 2008, Australasian Plant Pathology.

[44]  G. F. Hughes,et al.  On the mean accuracy of statistical pattern recognizers , 1968, IEEE Trans. Inf. Theory.

[45]  Ramón Díaz-Uriarte,et al.  Gene selection and classification of microarray data using random forest , 2006, BMC Bioinformatics.

[46]  Richard Hallett,et al.  Assessing Hemlock Decline Using Visible and Near-Infrared Spectroscopy: Indices Comparison and Algorithm Development , 2005, Applied spectroscopy.

[47]  L. Plümer,et al.  Original paper: Early detection and classification of plant diseases with Support Vector Machines based on hyperspectral reflectance , 2010 .

[48]  Michael J. Wingfield,et al.  Susceptibility of South African native conifers to the pitch canker pathogen, Fusarium circinatum. , 2009 .

[49]  H. Jones,et al.  Monitoring and screening plant populations with combined thermal and chlorophyll fluorescence imaging. , 2007, Journal of experimental botany.

[50]  S. Vincenzi,et al.  Application of a Random Forest algorithm to predict spatial distribution of the potential yield of Ruditapes philippinarum in the Venice lagoon, Italy , 2011 .

[51]  H. Ramon,et al.  Automatic detection of ‘yellow rust’ in wheat using reflectance measurements and neural networks , 2004 .

[52]  Reza Ehsani,et al.  Review: A review of advanced techniques for detecting plant diseases , 2010 .

[53]  Wilfried N. Gansterer,et al.  On the Relationship Between Feature Selection and Classification Accuracy , 2008, FSDM.

[54]  Anne-Katrin Mahlein,et al.  Recent advances in sensing plant diseases for precision crop protection , 2012, European Journal of Plant Pathology.

[55]  Rob Knight,et al.  Supervised classification of microbiota mitigates mislabeling errors , 2011, The ISME Journal.

[56]  A. Nel,et al.  Testing of selected South African Pinus hybrids and families for tolerance to the pitch canker pathogen, Fusarium circinatum , 2007, New Forests.

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

[58]  G. Carter,et al.  Early detection of plant stress by digital imaging within narrow stress-sensitive wavebands , 1994 .

[59]  Giles M. Foody,et al.  Feature Selection for Classification of Hyperspectral Data by SVM , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[60]  Jörg Müller,et al.  Modelling Forest α-Diversity and Floristic Composition - On the Added Value of LiDAR plus Hyperspectral Remote Sensing , 2012, Remote. Sens..

[61]  Aleksandar Milosavljevic,et al.  Gastrointestinal microbiome signatures of pediatric patients with irritable bowel syndrome. , 2011, Gastroenterology.

[62]  Ravinder Singh,et al.  Fast-Find: A novel computational approach to analyzing combinatorial motifs , 2006, BMC Bioinformatics.

[63]  Michael J. Wingfield,et al.  The pitch canker fungus, Fusarium circinatum: implications for South African forestry , 2011 .