Corn phenology and productivity with PlanetScope images

Corn (Zea mays) is a significant commodity in Brazil, used for human and animal consumption and biofuel use. This study evaluates the use of PlanetScope Dove and SuperDove images to monitor a central pivot with corn during a growth cycle with surface reflectance and vegetation indices. Its productivity per unit area was also evaluated. We then performed random sampling, extracted surface reflectance spectra, and performed statistical analysis. Results indicated significant surface reflectance variations throughout the crop growth cycle, and the highest accuracy in estimating productivity was in April using gamma distribution and logarithmic function (with an average of $7.88 \mathrm{Mg} \cdot \mathrm{ha}^{-1}$). We argue the PlanetScope Dove and SuperDove images can effectively monitor corn development and estimate its productivity, providing valuable support for agricultural management. In addition, the research demonstrates the potential of machine learning techniques to achieve a relatively accurate estimation of corn productivity at a regional scale.