Applying Spectral Fractal Dimension to Predict the SPAD Value of Rice Leaves Under Disease Stress

BackgroundThe chlorophyll content is a vital indicator for reflecting the photosynthesis ability of plants and it plays a significant role in monitoring the general health of plants. Since the chlorophyll content and the soil-plant analysis development (SPAD) value are positively correlated, it is feasible to estimate the SPAD value by calculating the vegetation indices (VIs) through hyperspectral images, thereby estimating the chlorophyll content. However, current indices simply adopted few wavelengths of the hyperspectral information, which may decrease the estimation accuracy. Besides, few researches explored the applicability of VIs over plant leaves under disease stress.MethodsIn this study, the SPAD value was estimated by calculating the fractal dimension of hyperspectral curves, ranging from 420 to 950 nm. The correlation between the SPAD value and wavelengths under disease stress was analyzed. In addition, a SPAD prediction model was built upon the combination of selected indices and 4 machine learning methods, including decision tree (DT), partial least square regression (PLSR), support vector regression (SVR), and back propagation neural network (BPNN). The performance of these models was compared through the correlation of determination, root mean square error, and relative error.ResultsThe results suggested that the SPAD value of rice leaves under different disease levels were sensitive to different wavelengths, meaning that the fixed wavelength selection in current indices may achieve poor estimation results. Compared with current VIs, a stronger positive correlation was detected between the SPAD value and our proposal, reaching an average correlation coefficient of 0.8263. For the prediction model, the one built with our proposal and SVR achieved the best performance, reaching R2, RMSE, and RE at 0.8752, 3.7715, and 7.8614%, respectively.ConclusionsThis work provides an in-depth insight for accurately and robustly estimating the SPAD value of rice leaves under disease stress, and our proposal is of great significance for monitoring the chlorophyll content in large-scale fields non-destructively.