Study on Maize Yield Estimation Based on Unmanned Aerial Vehicle Remote Sensing

Abstract

Accurately estimating crop yields is crucial for effective agricultural management, particularly with the continuous development of agricultural technology. However, traditional farmland survey methods are time-consuming and expensive. In recent years, there has been a growing interest in using UAV remote sensing technology for maize yield estimation. This study utilized UAV remote sensing technology and data assimilation methods to estimate maize yields. The study utilized UAV remote sensing to acquire ground remote sensing images and estimate maize yield by inverting the leaf area index (LAI). The WOFOST crop growth model was then employed to simulate the growth process of maize using meteorological data and soil property parameters. Finally, the ensemble Kalman filter (EnKF) method was applied to estimate and predict the growth status of maize based on the observed data and model simulation results. The experimental results indicate that the EnKF method can effectively integrate multi-source data, including UAV remote sensing data, meteorological data, and soil data, with the maize growth model for model state assimilation. As a result, it can accurately estimate the maize growth state and yield. This study provides a scientific basis for maize production management and has significant application value.