Assessing Legume Crop Growth and Yield Prediction using Drone-based Remote Sensing

Abstract

Background: The purpose of this project is to evaluate the prospective use of drone-based remote sensing for assessing legume crop development and predicting their yields. Traditional agricultural procedures often fall short in delivering timely and accurate monitoring, necessitating the adoption of innovative techniques. Methods: The study considers vegetative indicators such as NDVI, GNDVI and canopy cover to track the growth of three legume crops-peanut, soybean and common bean. Machine learning models, including random forest, support vector machines and multiple linear regression, were developed to predict agricultural production using remote sensing data. Statistical analysis was performed to verify the trustworthiness of vegetation indicators against ground-truth measurements. Result: The models achieved high accuracy, with R² values reaching up to 0.92. Statistical analysis confirmed strong relationships between vegetation indicators and ground-truth data. Among the studied crops, soybeans exhibited the highest growth vigor and yield. The study demonstrates that integrating machine learning with drone photography can enhance precision agriculture, making it more scalable and sustainable. Future research is recommended to explore different crop varieties and environmental conditions to further optimize the application of these technologies.

Code and data availability

No public paper-specific assets. The paper's drone imagery, vegetation index measurements, and ML models are not deposited anywhere; data are available only from the corresponding author upon request. All URLs in the article are cited references, not author asset deposits.

No evidence-backed public reproduction asset is currently recorded.