with the collaboration of Iranian Society of Mechanical Engineers (ISME)

Document Type : Research Article

Authors

1 University of California

2 Mashhad University of Medical Sciences, Department of Medical Physics, Mashad, Iran

3 Ferdowsi University of Mashhad

Abstract

Introduction
Pistachio production has been adversely affected by Psylla, which is a devastating insect. The primary goal of this research study was to select sensitive spectral bands to distinguish pistachio leaves infected by Psylla from healthy leaves.
Materials and Methods
A total number of 160 healthy and diseased leaves were scanned in 64 spectral bands between 400-1100 nm with 10 nm spectral resolution. A random forest algorithm was used to identify the importance of features in classifying the dataset into diseased and healthy leaves. After computing the features importance, a clustering algorithm was developed to cluster the most important features into six clusters such that the center of clusters were 50 nm apart. To transfer the hyperspectral dataset into a multispectral dataset, the reflectance was averaged in spectral bands within ±15 nm of each cluster center and achieved six broad multispectral bands. Afterwards, a support vector machine algorithm was utilized to classify the diseased and healthy leaves using both hyperspectral and multispectral datasets.
Results and Discussion
The center of clusters were 468 nm, 598 nm, 710 nm, 791 nm, 858 nm, and 1023 nm, which were calculated by taking the average of all the members assigned to the individual clusters. These are the most informative spectral bands to distinguish the pistachio leaves infected by Psylla from the healthy leaves. The F1-score was 90.91 when the hyperspectral dataset (all bands) was used, while the F1-score was 88.69 for the multispectral dataset. The subtle difference between the F1-scores indicates that the proposed pipeline in this study was able to select appropriately the sensitive bands while retaining all relevant information.
Conclusion
The results of this study revealed that the proposed framework could be used for selecting the most informative spectral bands and accordingly develop custom-designed multispectral sensors for disease detection in pistachio. In addition, we could reduce the dimensionality of the hyperspectral datasets and avoid the issues related to the curse of dimensionality.  

Keywords

  1. Al-Saddik H., Simon J.C. & Cointault F. ( 2018) Assessment of the optimal spectral bands for designing a sensor for vineyard disease detection. Precision Agriculture . DOI: 10.1007/s11119-018-9594-1
    Alisaac E., Behmann J., Kuska M. T., Dehne H.W., & Mahlein A. K.( 2018) Hyperspectral quantification of wheat resistance to fusarium head blight: Comparison of two fusarium species. European Journal of Plant Pathology 1–16.
    Breiman L.( 2001) Random forests. Machine Learning 45(1):5–32.
    Hastie T., Tibshirani R. & Friedman J.( 2009) The Elements of statistical learning: Data Mining, Inference & Prediction. New York: Springer-Verlag New York.
    Mahlein A.K., Oerke E.C., Ulrike S. & Wilhelm Dehne H.( 2011). Recent advances in sensing plant diseases for precision crop protection.” European Journal of Plant Pathology 133(1):197–209.
    Min M. & Lee W.S.( 2005) Determination of significant wavelengths & prediction of nitrogen content for citrus. Transactions of the ASAE 48(2):455–61.
    Moghimi A., Aghkhani M. H., Sazgarnia A. & Abbaspour-Fard M. (2011) Improvement of NIR transmission mode for internal quality assessment of fruit using different orientations. Journal of Food Process Engineering 34(5):1759–74.
    Moghimi A., Aghkhani M.H., Sazgarnia A. & Sarmad M.( 2010) Vis/NIR spectroscopy & chemometrics for the prediction of soluble solids content & acidity (PH) of kiwifruit.” Biosystems Engineering 106(3):295–302.
    Moghimi A., Yang C. & Marchetto P.M.(2018) Ensemble feature selection for plant phenotyping: A journey from hyperspectral to multispectral imaging. IEEE Access.
    Moghimi A., Yang c., Miller M.E., Shahryar F., Kianian S. & Marchetto P.M.(2018) A novel approach to assess salt stress tolerance in wheat using hyperspectral imaging. Frontiers in Plant Science.
    Moghimi A., Yang c., Miller M.E., Shahryar F., Kianian S. & Marchetto P.M.(2017) Hyperspectral imaging to identify salt-tolerant wheat lines, in autonomous air & ground sensing systems for agricultural optimization & phenotyping II 2017. Anaheim, California, United States.
    Mutanga O.& Skidmore A.K.(2007) Red edge shift & biochemical content in grass canopies. ISPRS Journal of Photogrammetry & Remote Sensing 62(1):34–42.
    Sankaran S. & Ehsani R.(2011) Visible-near infrared spectroscopy based citrus greening detection: Evaluation of spectral feature extraction techniques. Crop Protection 30(11):1508–13.
    Sankaran S., Mishra A., Maja J.M. & Ehsani R.( 2011) Visible-near infrared spectroscopy for detection of huanglongbing in citrus orchards. Computers & Electronics in Agriculture 77(2):127–34.
    Susic N., Zibrat U., Sirca S., Strajnar P., Razinger J.aka, Knapic M., Voncina A., Urek G. & Geric Stare B. (2018) Discrimination between abiotic & biotic drought stress in tomatoes using hyperspectral imaging. Sensors & Actuators, B: Chemical 273(June):842–52.
    Wahabzada M., Mahlein A.K., Bauckhage C., Steiner U., Oerke E.C. & Kersting K.(2016) Plant phenotyping using probabilistic topic models: Uncovering the hyperspectral language of plants. Scientific Reports 6(February):22482.