Evaluating Sugarcane Yield Variability with UAV-Derived Cane Height under Different Water and Nitrogen Conditions

TL;DR

This study uses UAV-derived digital surface models to analyze how water and nitrogen levels affect sugarcane height and yield, revealing a strong correlation between cane height and productivity.

Contribution

It introduces a novel method of deriving cane height from UAV data and links it to yield under different water and nitrogen conditions.

Findings

High correlation (R^2=0.95) between cane height and yield.

Water and nitrogen levels significantly influence cane height and yield.

UAV-based DSM provides effective pre-harvest yield estimation.

Abstract

This study investigates the relationship between sugarcane yield and cane height derived under different water and nitrogen conditions from pre-harvest Digital Surface Model (DSM) obtained via Unmanned Aerial Vehicle (UAV) flights over a sugarcane test farm. The farm was divided into 62 blocks based on three water levels (low, medium, and high) and three nitrogen levels (low, medium, and high), with repeated treatments. In pixel distribution of DSM for each block, it provided bimodal distribution representing two peaks, ground level (gaps within canopies) and top of the canopies respectively. Using bimodal distribution, mean cane height was extracted for each block by applying a trimmed mean to the pixel distribution, focusing on the top canopy points. Similarly, the extracted mean elevation of the base was derived from the bottom points, representing ground level. The Derived Cane Height Model (DCHM) was generated by taking the difference between the mean canopy height and mean base elevation for each block. Yield measurements (tons/acre) were recorded post-harvest for each block. By aggregating the data into nine treatment zones (e.g., high water-low nitrogen, low water-high nitrogen), the DCHM and median yield were calculated for each zone. The regression analysis between the DCHM and corresponding yields for the different treatment zones yielded an R 2 of 0.95. This study demonstrates the significant impact of water and nitrogen treatments on sugarcane height and yield, utilizing one-time UAV-derived DSM data.