000			03493 a2200421 4500
008			230525b |||||||| |||| 00| 0 eng d
022			_a2160889X
022			_a21608881
041			_aEn
044			_aCIV
090			_bDG/A/1461
100			_aDIOMANDE, Kedro Sidiki
100			_aKAMATE, Amara
100			_aSORO, Penetjiligue Adama
100			_aZORO-DIAMA, Emma Georgina
100			_aADOHI-KROU, Adjo Viviane
110			_aCentre National de Recherche Agronomique
110			_bCote d'Ivoire
242			_aDetection de la marbrure jaune du riz au stade asymptomatique par spectroscopies de fluorescence et de reflectance hyperspectrales
245			_aDetection of rice yellow mottle at the asymptomatic stage by hyperspectral fluorescence and reflectance spectroscopies
260			_aAbidjan
260			_bOptics and Photonics Journal
260			_cAvr 2023
302			_ap. 63-78
362			_a2023
388			_a25-05-2023
520			_aRice yellow mottle is considered the most destructive disease threatening rice production in Africa. Early detection of this infection in rice is essential to limit its expansion and proliferation. However, there is no research devoted to the spectral detection of rice yellow mottle virus (RYMV) infection, especially in the asymptomatic or early stages. This work proposes the use of hyperspectral fluorescence and reflectance data at leaf level for the detection of this disease in asymptomatic stages. A greenhouse experiment was therefore conducted to collect hyperspectral fluorescence and reflectance data at different stages of infection. These data allowed to calculate nine vegetation indices: one from fluorescence spectra and eight from reflectance spectra. A t-test made it possible to identify, from the second day after infection, four relevant reflectance vegetation indices to discriminate healthy leaves from those infected: these are Photochemical Reflectance Index (PRI), Transformed Chlorophyll Absorption in Reflectance Index (TCARI), Structure Intensive Pigment Index (SIPI) and Simple Ratio Pigment Index (SRPI). The fluorescence index was less sensitive in detecting infection. The four significant vegetation indices for the detection of RYMV were then used to build and evaluate models for discriminating plants according to their health status by the supervised classification of support vector machine (SVM) at different stages of infection. The maximum overall accuracy is 92.5% six days after inoculation (6 DAI). The sixth day after inoculation would be the adequate day to detect RYMV. This plants discrimination was validated by the mean reflectance spectra and by the histograms showing the differences between the average reflectance vegetation indices values of the two types of plants. Our results demonstrate the feasibility of differentiating RYMV-infected samples. They suggest that support vector machine learning models could be developed to diagnose RYMV-infected plants based on vegetation indices derived from spectral profiles at early stages of disease development.
650			_2AGROVOC _gVirus de la marbrure jaune du riz
650			_gSpectres de fluorescence
650			_gSpectres de reflectance
650			_gIndices de vegetation
650			_gClassification SVM
650			_gFiltrage Savitzky Golay
760			_b13
760			_w4
856			_uhttps://www.scirp.org/pdf/opj_2023052320511543.pdf
856			_uhttps://doi.org/10.4236/opj.2023.134005
999			_c5053 _d5053