Crop growth monitoring at various growth stages is essential for optimizing agricultural inputs and enhancing crop yield. Nitrogen plays a critical role in plant development; however, its improper application can reduce productivity and, in the long term, degrade soil health. The aim of this study was to develop a non-invasive approach for nitrogen estimation through proxies (Nitrogen Flavanol Index) in Mentha arvensis using UAV-derived multispectral vegetation indices and machine learning models. Support Vector Regression, Random Forest, and Gradient Boosting were used to predict the Nitrogen Flavanol Index (NFI) across different growth stages. Among the tested models, Random Forest achieved the highest predictive accuracy (R2 = 0.86, RMSE = 0.32) at 75 days after planting (DAP), followed by Gradient Boosting (R2 = 0.75, RMSE = 0.43). Model performance was lowest during early growth stages (15–30 DAP) but improved markedly from mid to late growth stages (45–90 DAP). The findings highlight the significance of UAV-acquired data coupled with machine learning approaches for non-destructive nitrogen flavanol estimation, which can immensely contribute to improving real-time crop growth monitoring.
Crop growth monitoring during its growth stages is essential for optimizing agricultural resource inputs and enhancing crop productivity. Nitrogen plays a critical role during plant growth but its improper application not only reduces the crop productivity but also in the long turn cause soil degradation. This study addresses an advanced and integrated approach to develop a non-invasive mechanism for nitrogen estimation through proxies (Nitrogen Flavanol Index) in Mentha arvensis. This study integrates UAV-based multispectral imagery vegetation indices, field observed non-invasive data, and machine learning (ML) models to predict NFI during growth stages of Mentha arvensis. Machine learning models (Support Vector Regression, Random Forest, and Gradient Boosting) were evaluated, with Random Forest achieving highest accuracy (R² = 0.86, RMSE = 0.32), followed by Gradient Boosting (R² = 0.75, RMSE = 0.43) at 75 Days After Planting (DAP). Model performances were observed to be lowest at early growth stages (15–30 DAP), however, it improved significantly from mid to late growth stages (45–90 DAP). The findings highlight the significance of UAV-acquired data coupled with machine learning approaches for non-destructive nitrogen flavanol estimation, which can immensely contribute to improved real-time crop growth monitoring.