Sugarcane Yield Estimation Using UAV-Based RGB Images and Allometric Equations

Abstract

Accurately estimating pre-harvest sugarcane yield has long been a challenge. There are many methods for predicting sugarcane yield, ranging from simple empirical equations to complex physiological models. This paper reports a study on a method for predicting sugarcane yield using allometric equations combined with UAV-based RGB images (UAVI). UAVI were used for the estimation of the sugarcane height, which is in the form of the sugarcane height model (HM). Sugarcane height is one of the key factors in calculating sugarcane yield in the allometric equation. The results showed that the HM could be used in the allometric equation. There was only a slight discrepancy compared to measurement with a tape measure in the field. In developing the allometric equation, the authors created regression models to estimate aboveground biomass weight in leaf bush (Wl) and millable stalk (Wms) based on sugarcane height (H) and diameter measured from the first segment of sugarcane aboveground (Dfs). The model estimated aboveground biomass weight sufficiently for all stages of cultivation. Based on this model, the authors developed two general equations: Y = 0.0842 H * Dfs0.9827; R2 = 0.93 (used for leaf bush), and Y = 0.1254 H * Dfs1.3926; R2 = 0.93 (used for millable stalk). The decision correlation coefficient (R2) was 80% reliable. The HM models were slightly different from field measurements with a tape measure. Also, there was a little inaccuracy in the root-mean-square error (RMSE) between the sugarcane heights analyzed from UAVI and field measurements using tape measure. The RMSE values, arranged from highest to lowest according to the sugarcane growth stage were: 0.35 m (tillering phase, TP), 0.25 m (grand growth phase, GP), and 0.24 m (ripening phase, RP). Using the HM value in the allometric equation effectively estimated the sugarcane yield at different growth stages. Sugarcane growth at TP and GP phases gave the highest sugarcane yield at 200 cm of the HM value, with total yields of 11.49 and 16.75 ton/hectare, respectively. Whereas, RP gave the highest sugarcane yield at 350 cm of the HM value (total yield at 42.97 ton/hectare). Overall, an accurate estimation of the aboveground biomass of leaf bush and millable stalk can be obtained using these equations. The authors believe that the research methods presented here can help sugarcane farmers to better estimate yield prior to harvest.