Performance of stacking machine learning and volume model for improving corn above ground biomass prediction.

Abstract

The aboveground biomass (AGB) of crops is an essential metric for monitoring crop growth, making timely and accurate AGB forecasting critical for effective agricultural management. The introduction of Unmanned Aerial Vehicles (UAVs) and advanced sensor technologies has revolutionized traditional AGB prediction techniques. Currently, machine learning (ML) combined with UAV data are commonly utilized, along with the Vegetation Index Weighted Canopy Volume Model (CVM VI ) for AGB prediction. Nevertheless, there is limited investigation into how these methods perform across different agricultural conditions. This study aims to fill this gap by creating specific methodologies for estimating corn AGB under diverse fertilization and irrigation treatments. We utilized LiDAR, multispectral (MS), thermal infrared (TIR), along with measured AGB and Leaf Area Index (LAI) data from various growth stages to develop a stacking ensemble learning model. This model effectively integrates data from multiple sources, resulting in a strong prediction performance with R 2 of 0.86, Mean Absolute Error (MAE) of 1.54 ​t/ha, and Root Mean Square Error (RMSE) of 2.06 ​t/ha. Meanwhile, the analysis of the accuracy of CVM VI revealed its efficacy during the early-stage when corn is short, with its predictive capability diminishing as AGB increases. Consequently, we recommend the CVM VI for early-stage AGB prediction, which can streamline data collection and computational efforts. In contrast, the ML approach, which benefits from data fusion, is more appropriate for predicting AGB during the mid to late growth stages. This study enhances AGB prediction accuracy and speed, providing critical understanding of regional AGB dynamics and supporting better agricultural decision-making.

Plant phenotyping relevance

UAVのLiDAR・マルチスペクトル・熱赤外データを統合し、トウモロコシの地上部バイオマスを推定するモデルを開発・比較・評価しており、植物形質取得手法が中心である。

Code and data availability

The paper's Data Availability statement explicitly deposits authors' model training code and test data at a public GitHub repository, which qualifies as a paper-specific public code asset for the AGB prediction analysis.