Correlation between Ground Measurements and UAV Sensed Vegetation Indices for Yield Prediction of Common Bean Grown under Different Irrigation Treatments and Sowing Periods

The objective of this study is to assess the possibility using unmanned aerial vehicle (UAV) multispectral imagery for rapid monitoring, water stress detection and yield prediction under different sowing periods irrigation treatments common bean (Phaseolus vulgaris, L). used a two-factorial split-plot design, divided into subplots. There were three (plots; I—mid April, II—end May/beginning June, III—third decade June/beginning July) levels (subplots; full (F)—providing 100% crop evapotranspiration (ETc), deficit (R)—providing 80% ETc, (S) providing—60% ETc). Canopy cover (CC), leaf area index (LAI), transpiration (T) soil moisture (Sm) monitored in all during growth period. A camera was mounted on drone seven occasions two years research which provided raw images. NDVI (Normalized Difference Vegetation Index), MCARI1 (Modified Chlorophyll Absorption Reflectance NDRE Red Edge), GNDVI (Green Normalized Index) Optimized Soil Adjusted Index (OSAVI) computed from results indicated that NDVI, derived UAV are sensitive S treatments, while mild among R could not be detected. II-S treatment predicted yields better (r2 = 0.65, y 4.01 tha−1; r2 0.70, 4.28 tha−1) than III-S 0.012, 3.54 0.020, 3.7 tha−1). use MCARI will able predict conditions. However, remote sensing methods did reveal pest invasion, so good predictions require observations field. Generally, low-flying proved useful monitoring status predicting regimes