Location: Water Management and Systems Research
Title: Enhancing corn yield prediction with UAV remote sensing: Optimizing data quality or model complexity?Author
 |
Zhang, Huihui |
|
ZHOU, YUTING - Oklahoma State University |
|
MA, SHENGFANG - Oklahoma State University |
|
Submitted to: Meeting Abstract
Publication Type: Abstract Only Publication Acceptance Date: 10/1/2024 Publication Date: N/A Citation: N/A Interpretive Summary: Technical Abstract: Accurate and timely prediction of corn yield is crucial for efficient resource allocation in agriculture. Traditional methods, reliant on ground surveys, are labor-intensive and time-consuming. This study explores the potential of remote sensing and machine learning to address these challenges. We compare the performance of various machine learning models, including Random Forest, Gradient Boosting, ResNet, and a novel shallow CNN architecture (SimRes), in predicting corn yield across different growth stages using both RGB and multispectral UAV imagery. Our analysis considers the impact of irrigation regimes (deficit vs. full) on model performance. Results indicate that multispectral data and deep learning models generally outperform RGB data and traditional machine learning methods, especially in early and late growth stages. While SimRes offers comparable accuracy to deep learning models with reduced computational costs, further research is needed to fully optimize yield prediction and inform agricultural management decisions. |
