Phenological Windows for UAV and PlanetScope Monitoring of Greenhouse Gas Fluxes in AWD Rice on the Peruvian North Coast

Alternate wetting and drying (AWD) irrigation reduces CH4 emissions from flooded rice but amplifies N2O pulses; identifying candidate phenological windows for the remote screening of greenhouse gas (GHG) fluxes remains challenging with small datasets. In a single-site, single-season exploratory study at INIA Vista Florida (Lambayeque, Peru), eight UAV flights were paired with eight PlanetScope SuperDove scenes (|Δ|≤1 d) and closed-chamber CH4, N2O and CO2 fluxes under four water regimes (CF, AWD5, AWD10, AWD20; 96 sub-plot × date observations). Multivariate explanatory power was assessed by bootstrap Ridge regression on each sensor’s native predictors (VI + GLCM + Tmean for the UAV, VI for PlanetScope). Maximum tillering (79 DAS) emerged as a candidate UAV window, ranking in the top three for all gases through GLCM textures, whereas PlanetScope peaked at Mid-boot and Late-boot (103–107 DAS), with median R2˜UAV at 0.34–0.71 and R2˜Planet at 0.20–0.60. Nested Leave-One-Plot-Out (LOPO) validation gave RCV2 between +0.57 and +0.69 for four of six platform × gas combinations (UAV-CH4 and Planet-N2O stayed weak), and Tmean was decisive for N2O on the UAV (ΔR2=+0.48). Repeating the stage selection inside every LOPO fold preserved the leading combinations and their ranking. These exploratory windows and sensor-native descriptors need multi-site, multi-season validation before operational use.