Study on Monitoring SPAD Values for Multispatial Spatial Vertical Scales of Summer Maize Based on UAV Multispectral Remote Sensing

Rapid acquisition of chlorophyll content in maize leaves is great significance for timely monitoring plant health and guiding field management. In order to accurately detect the relative summer study responsiveness vegetation indices SPAD (soil analyzer development) values at different spatial vertical scales, this paper established a prediction model scales based on UAV multispectral images. The experiment collected image data from jointing stage selected eight indices. By using sparrow search optimized kernel limit learning machine (SSA-KELM), models canopy leaf (CL) SPADCL ear (EL) SPADEL were established, linear fitting analysis was conducted combining measured ground. results showed that SPADCL, R2 between predicted 0.899, RMSE 1.068. For SPADEL, 0.837, 0.89. Compared with by partial least squares method (PLSR), it found (SSA-KELM) has more precise better stability adaptability small sample prediction. research can provide technical support remote sensing scales.