Diagnosis of bacterial spot of tomato using spectral signatures

• Published in: Computers and electronics in agriculture Vol. 74; no. 2; pp. 329 - 335
• Main Authors: Jones, C.D., Jones, J.B., Lee, W.S.
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.11.2010; [Amsterdam]: Elsevier Science; Elsevier
• Subjects: Agronomy. Soil science and plant productions; Bacteria; Bacterial leaf spot of tomato; Biological and medical sciences; disease diagnosis; Fundamental and applied biological sciences. Psychology; image analysis; leaf spotting; Lycopersicon esculentum; NIRS; Phytopathology. Animal pests. Plant and forest protection; Plant disease; plant pathogenic bacteria; PLS; Reflectance; Significant wavelength; Solanum lycopersicum; spectral analysis; tomatoes; Xanthomonas; Xanthomonas perforans; NIRS; Bacterial leaf spot of tomato; Significant wavelength; Plant disease; PLS; Reflectance; Plant pathology; Plant leaf; Tomato; Wavelength; Spectral signature; Vegetable crop; Dicotyledones; Angiospermae; Lycopersicon esculentum; Bacteria; Spermatophyta; Solanaceae; Partial least squares
• ISSN: 0168-1699; 1872-7107
• DOI: 10.1016/j.compag.2010.09.008

▶ Tomato leaves were infected with bacterial leaf spot of tomato. ▶ Leaves were rated for disease severity and leaf reflectance was measured. ▶ Significant wavelengths were identified using chemometric methods. ▶ The best model predicted the disease severity with a RMSD of 4.9% and R 2 of 0.82. Ultraviolet, visible, and near-infrared reflectance spectroscopy was used to determine the disease severity of tomato ( Lycopersicon esculentum) leaves infected with Xanthomonas perforans, the causal agent of bacterial leaf spot of tomato. Chemometric methods were used to identify significant wavelengths and create spectral-based prediction models. Significant wavelengths were identified through analysis of the B-matrix from partial least squares (PLS) regression, analysis of a correlation coefficient spectrum, and through the use of a stepwise multiple linear regression (SMLR) procedure. These analysis methods revealed several significant regions wavelengths and produced predictive models of disease severity based on absorbance spectra. The best model predicted the disease severity of the validation data set with a root mean square difference (RMSD) of 4.9% and a coefficient of determination ( R 2) of 0.82. The results of this initial study indicate the potential for the use of spectral technology to detect bacterial leaf spot of tomato in the field.