Supplemental figures for "Integrating Machine Learning and Remote Sensing to Determine Crop Nitrogen Content of Maize"

Abstract

This study developed machine learning models to predict maize crop nitrogen content (CNC) using vegetation indices derived from UAV and satellite imagery. Several models were evaluated, with Random Forest demonstrating the best performance. The study emphasizes that combining vegetation indices enhances prediction accuracy more than using individual spectral bands. Results show reliable CNC estimation across growth stages, although predictions at early stages are less precise due to low canopy cover and soil interference. The approach allows for real-time, field-to-regional-scale nitrogen monitoring, supporting improved fertilizer management and precision agriculture decision-making.

Plant phenotyping relevance

UAV・衛星画像と機械学習により、トウモロコシの作物窒素含量という植物形質を推定し、モデル性能を比較・評価しているため、リモートセンシング型フェノタイピング手法の適用が中心です。

Code and data availability

公開論文であることは確認できましたが、現在の公式API・許可済み取得経路では本文を自動取得できませんでした。

No evidence-backed public reproduction asset is currently recorded.