Machine Learning Regression Analysis for Estimation of Crop Emergence Using Multispectral UAV Imagery

Optimal crop emergence is an important trait in breeding for genotypic screening and achieving potential growth yield. Emergence conventionally quantified manually by counting the sub-sections of field plots or scoring; these are less reliable, laborious inefficient. Remote sensing technology being increasingly used high-throughput estimation agronomic traits crops. This study developed a method estimating wheat seedlings using multispectral images captured from unmanned aerial vehicle. A machine learning regression (MLR) analysis was combining spectral morphological information extracted images. The approach tested on diverse genotypes varying seedling emergence. In this study, three supervised MLR models including trees, support vector Gaussian process (GPR) were evaluated GPR model most effective compared to other methods, with R2 = 0.86, RMSE 4.07 MAE 3.21 when correlated manual count. addition, imagery data collected at multiple flight altitudes different stages suggested that 10 m altitude 20 days after sowing desirable optimal spatial resolution image analysis. deployable larger trials crops reliable estimates.