Investigation on Data Fusion of Multisource Spectral Data for Rice Leaf Diseases Identification Using Machine Learning Methods

Rice diseases are major threats to rice yield and quality. Rapid and accurate detection of rice diseases is of great importance for precise disease prevention and treatment. Various spectroscopic techniques have been used to detect plant diseases. To rapidly and accurately detect three different rice diseases [leaf blight (Xanthomonas oryzae pv. Oryzae), rice blast (Pyricularia oryzae), and rice sheath blight (Rhizoctonia solani)], three spectroscopic techniques were applied, including visible/near-infrared hyperspectral imaging (HSI) spectra, mid-infrared spectroscopy (MIR), and laser-induced breakdown spectroscopy (LIBS). Three different levels of data fusion (raw data fusion, feature fusion, and decision fusion) fusing three different types of spectral features were adopted to categorize the diseases of rice. Principal component analysis (PCA) and autoencoder (AE) were used to extract features. Identification models based on each technique and different fusion levels were built using support vector machine (SVM), logistic regression (LR), and convolution neural network (CNN) models. Models based on HSI performed better than those based on MIR and LIBS, with the accuracy over 93% for the test set based on PCA features of HSI spectra. The performance of rice disease identification varied with different levels of fusion. The results showed that feature fusion and decision fusion could enhance identification performance. The overall results illustrated that the three techniques could be used to identify rice diseases, and data fusion strategies have great potential to be used for rice disease detection.

[1]  Chu Zhang,et al.  Detection of Sclerotinia Stem Rot on Oilseed Rape (Brassica napus L.) Based on Laser- Induced Breakdown Spectroscopy , 2019, Transactions of the ASABE.

[2]  A. A. Gomes,et al.  Simultaneous Classification of Teas According to Their Varieties and Geographical Origins by Using NIR Spectroscopy and SPA-LDA , 2014, Food Analytical Methods.

[3]  Chu Zhang,et al.  Detection of Subtle Bruises on Winter Jujube Using Hyperspectral Imaging With Pixel-Wise Deep Learning Method , 2019, IEEE Access.

[4]  Budiman Minasny,et al.  Convolutional neural network for soil microplastic contamination screening using infrared spectroscopy. , 2019, The Science of the total environment.

[5]  Kutubuddin A Molla,et al.  Understanding sheath blight resistance in rice: the road behind and the road ahead , 2019, Plant biotechnology journal.

[6]  Debashree Sengupta,et al.  Deployment of Genetic and Genomic Tools Toward Gaining a Better Understanding of Rice-Xanthomonas oryzae pv. oryzae Interactions for Development of Durable Bacterial Blight Resistant Rice , 2020, Frontiers in Plant Science.

[7]  Teresa Flores,et al.  Rapid identification of Huanlongbing-infected citrus plants using laser-induced breakdown spectroscopy of phloem samples. , 2018, Applied optics.

[8]  Narangerel Altangerel,et al.  In vivo diagnostics of early abiotic plant stress response via Raman spectroscopy , 2017, Proceedings of the National Academy of Sciences.

[9]  Ricard Boqué,et al.  Data fusion methodologies for food and beverage authentication and quality assessment - a review. , 2015, Analytica chimica acta.

[10]  Yidan Bao,et al.  Near-Infrared Hyperspectral Imaging Combined with Deep Learning to Identify Cotton Seed Varieties , 2019, Molecules.

[11]  Zhou Jianmin,et al.  Responses of Leaf Cuticles to Rice Blast: Detection and Identification Using Depth-Profiling Fourier Transform Mid-Infrared Photoacoustic Spectroscopy. , 2020, Plant disease.

[12]  C Baumgartner,et al.  Prediction model optimization using full model selection with regression trees demonstrated with FTIR data from bovine milk. , 2019, Preventive veterinary medicine.

[13]  Ricardo N M J Páscoa,et al.  Varietal discrimination of hop pellets by near and mid infrared spectroscopy. , 2018, Talanta.

[14]  Yong He,et al.  Identifying Freshness of Spinach Leaves Stored at Different Temperatures Using Hyperspectral Imaging , 2019, Foods.

[15]  Chu Zhang,et al.  Variety Identification of Raisins Using Near-Infrared Hyperspectral Imaging , 2018, Molecules.

[16]  Chen Yuan,et al.  Identification of Stable Quantitative Trait Loci for Sheath Blight Resistance Using Recombinant Inbred Line , 2019, Rice Science.

[17]  Chu Zhang,et al.  Developing deep learning based regression approaches for determination of chemical compositions in dry black goji berries (Lycium ruthenicum Murr.) using near-infrared hyperspectral imaging. , 2020, Food chemistry.

[18]  A. Smilde,et al.  On the increase of predictive performance with high-level data fusion. , 2011, Analytica Chimica Acta.

[19]  Federico Castanedo,et al.  A Review of Data Fusion Techniques , 2013, TheScientificWorldJournal.

[20]  Xing Chen,et al.  Stacked Denoise Autoencoder Based Feature Extraction and Classification for Hyperspectral Images , 2016, J. Sensors.

[21]  Peijun Du,et al.  Novel segmented stacked autoencoder for effective dimensionality reduction and feature extraction in hyperspectral imaging , 2016, Neurocomputing.

[22]  Roberto Oberti,et al.  Plant disease detection based on data fusion of hyper-spectral and multi-spectral fluorescence imaging using Kohonen maps , 2005, Real Time Imaging.

[23]  이창기,et al.  Convolutional Neural Network를 이용한 한국어 영화평 감성 분석 , 2016 .

[24]  Charles Farber,et al.  Advanced spectroscopic techniques for plant disease diagnostics. A review , 2019, TrAC Trends in Analytical Chemistry.

[25]  Da-Wen Sun,et al.  Application of Hyperspectral Imaging to Discriminate the Variety of Maize Seeds , 2015, Food Analytical Methods.

[26]  Jifeng Shen,et al.  Nondestructive identification of green tea varieties based on hyperspectral imaging technology , 2018 .

[27]  Ping Jiang,et al.  Research on optimal predicting model for the grading detection of rice blast , 2019 .

[28]  Christian Nansen,et al.  Hyperspectral imaging to characterize plant–plant communication in response to insect herbivory , 2018, Plant Methods.

[29]  K. Moffett,et al.  Remote Sens , 2015 .

[30]  Andrea D. Magrì,et al.  Data-fusion for multiplatform characterization of an Italian craft beer aimed at its authentication. , 2014, Analytica chimica acta.

[31]  Marco Mazzotti,et al.  ATR‐FTIR Spectroscopy , 2012 .

[32]  Anne-Katrin Mahlein,et al.  Fusion of sensor data for the detection and differentiation of plant diseases in cucumber , 2014 .

[33]  Hanping Mao,et al.  Portable Rice Disease Spores Capture and Detection Method Using Diffraction Fingerprints on Microfluidic Chip , 2019, Micromachines.

[34]  Fei Liu,et al.  Mid-infrared spectroscopy combined with chemometrics to detect Sclerotinia stem rot on oilseed rape (Brassica napus L.) leaves , 2017, Plant Methods.

[35]  Martin R. McAinsh,et al.  ATR-FTIR spectroscopy non-destructively detects damage-induced sour rot infection in whole tomato fruit , 2018, Planta.

[36]  Bosoon Park,et al.  Detection of Citrus Huanglongbing by Fourier Transform Infrared—Attenuated Total Reflection Spectroscopy , 2010, Applied spectroscopy.

[37]  Alan K. Knapp,et al.  LEAF OPTICAL PROPERTIES IN HIGHER PLANTS , 2001 .

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

[39]  Tariq Umer,et al.  Diagnosis and recognition of grape leaf diseases: An automated system based on a novel saliency approach and canonical correlation analysis based multiple features fusion , 2019, Sustain. Comput. Informatics Syst..

[40]  Chu Zhang,et al.  Discrimination of Chrysanthemum Varieties Using Hyperspectral Imaging Combined with a Deep Convolutional Neural Network , 2018, Molecules.

[41]  Chu Zhang,et al.  Identification of coffee bean varieties using hyperspectral imaging: influence of preprocessing methods and pixel-wise spectra analysis , 2018, Scientific Reports.

[42]  U. Knauer,et al.  Improved classification accuracy of powdery mildew infection levels of wine grapes by spatial-spectral analysis of hyperspectral images , 2017, Plant Methods.

[43]  Marco Orlandi,et al.  Chemical profiling and multivariate data fusion methods for the identification of the botanical origin of honey. , 2018, Food chemistry.

[44]  Paul Scheunders,et al.  Close-range hyperspectral image analysis for the early detection of stress responses in individual plants in a high-throughput phenotyping platform , 2018 .

[45]  Yong He,et al.  Information fusion of emerging non-destructive analytical techniques for food quality authentication: A survey , 2020 .

[46]  Syed Aziz Shah,et al.  Machine learning driven non-invasive approach of water content estimation in living plant leaves using terahertz waves , 2019, Plant Methods.

[47]  Gang Wang,et al.  Spectral-spatial classification of hyperspectral image using autoencoders , 2013, 2013 9th International Conference on Information, Communications & Signal Processing.

[48]  Yong He,et al.  Challenging applications for multi-element analysis by laser-induced breakdown spectroscopy in agriculture: A review , 2016 .

[49]  Stefan Thomas,et al.  Quantitative assessment of disease severity and rating of barley cultivars based on hyperspectral imaging in a non-invasive, automated phenotyping platform , 2018, Plant Methods.