Monitoring plant moisture content and optimizing irrigation prescriptions based on UAV multimodal data

Abstract

Introduction With the continuous advancement of smart agriculture, multi-modal remote sensing based on unmanned aerial vehicles (UAVs) offers new technical approaches for monitoring and managing crop moisture in fields. However, significant challenges remain in developing high-precision field-scale crop Plant Moisture Content (PMC) prediction models and translating them into actionable irrigation strategies. Methods This study focuses on winter wheat, employing field experiments with PMC and water use efficiency (WUE) as indicators of crop water status. Vegetation indices (VIs) derived from UAV data were used to construct a leaf area index (LAI) inversion model. Crop Height was extracted from oblique photogrammetry point cloud data. By combining the Penman-Monteith equation with dual crop coefficients, an improved evapotranspiration (ET) model was developed, utilizing multispectral data from UAVs, thermal infrared data, point cloud-derived plant height, and LAI inversion results. Further utilizing VIs, temperature indices (TIs), and machine learning algorithms (Random Forest Regression (RFR), Back Propagation Neural Network (BPNN), Partial Least Squares Regression (PLSR), and Support Vector Regression (SVR), we established PMC prediction models for winter wheat at different growth stages. These models, integrated with WUE, form the basis for an irrigation scheduling optimization framework at the field scale. Results Results indicate that VIs, the difference between canopy temperature and air temperature (ΔT), Crop Water Stress Index (CWSI), and ET exhibit varying correlations with PMC during three critical growth stages of winter wheat, with ET showing the highest correlation during the jointing and heading stages (absolute correlation coefficient |r| ≥ 0.639). Compared to PMC prediction models constructed with different combinations of VIs, ET, VIs+ET, and VIs+TIs, the model employing the RFR algorithm with multimodal inputs (VIS+TIs+ET) demonstrated the best performance. The model’s predictive accuracy gradually improved across all growth stages, peaking during the grain-filling stage, with the coefficient of determination(R 2 ) of 0.900 and a normalized root mean square error (nRMSE) of 2.688%. Optimal WUE varied across growth stages under different irrigation treatments. The highest values were achieved at the jointing stage under treatment W3 (PMC = 81.8%), and at the heading and grain-filling stages under treatment W1 (PMC = 76.8% and 64.0%, respectively). Discussion The study suggests that stage-specific irrigation scheduling based on PMC thresholds can improve overall water use efficiency. This study shows that integrating multi-modal UAV data with machine learning and an improved ET model enables high-precision PMC monitoring, supporting data-driven irrigation scheduling in precision agriculture.

Plant phenotyping relevance

UAVマルチモーダルデータと機械学習により、作物水分状態（PMC）、LAI、草高、蒸発散量を推定する手法を開発・評価しており、フェノタイピング手法が研究の中心である。

Code and data availability

The supplied blocks contain no data availability statement, public dataset, image repository, or author code/model deposit. Phenotyping data (UAV imagery, point clouds, PMC measurements) are described but no public availability or URL is provided.

No evidence-backed public reproduction asset is currently recorded.