Fuyi Duan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Fuyi Duan has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Qian Cheng
Institute of Farmland Irrigation, Chinese Academy of Agricultural Sciences, Xinxiang 453002, China
5 shared publications - Zhen Chen
Institute of Farmland Irrigation, Chinese Academy of Agricultural Sciences, Xinxiang 453002, China
5 shared publications - Xiaohui Kuang
Heilongjiang Provincial Hydraulic Research Institute, Harbin 150080, China
4 shared publications - Yafeng Li
Institute of Farmland Irrigation, Chinese Academy of Agricultural Sciences, Xinxiang 453002, China
4 shared publications - Bohan Mao
Institute of Farmland Irrigation, Chinese Academy of Agricultural Sciences, Xinxiang 453002, China
3 shared publications - Deshan Chen
Institute of Farmland Irrigation, Chinese Academy of Agricultural Sciences, Xinxiang 453002, China
3 shared publications
Latest Publications
- Open Access
- 15 May 2026
- Published by Frontiers Media SA in Frontiers in Plant Science
- Vol. 17, 1827521
Monitoring plant moisture content and optimizing irrigation prescriptions based on UAV multimodal data
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.
- 15 May 2026
- Published by Frontiers Media SA in Frontiers in Plant Science
- Vol. 17, 1827521
Open AccessMonitoring plant moisture content and optimizing irrigation prescriptions based on UAV multimodal data
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.
- Open Access
- 9 April 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (8) , 1113
Correction: Kuang et al. A CNN-LSTM-XGBoost Hybrid Framework for Interpretable Nitrogen Stress Classification Using Multimodal UAV Imagery. Remote Sens. 2026, 18, 538
Following publication, the authors noticed that the author order and numbering, as well as the corresponding author details, displayed in the original publication
- 9 April 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (8) , 1113
Open AccessCorrection: Kuang et al. A CNN-LSTM-XGBoost Hybrid Framework for Interpretable Nitrogen Stress Classification Using Multimodal UAV Imagery. Remote Sens. 2026, 18, 538
Following publication, the authors noticed that the author order and numbering, as well as the corresponding author details, displayed in the original publication
- Top Cited PapersOpen Access
- 7 February 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (4) , 538
A CNN-LSTM-XGBoost Hybrid Framework for Interpretable Nitrogen Stress Classification Using Multimodal UAV Imagery
Accurate diagnosis of nitrogen status is essential for precision fertilization in winter wheat. Single-modal or single-temporal remote sensing often fails to capture the multidimensional crop responses to nitrogen stress. In this study, we propose a hybrid framework based on CNN-LSTM-XGBoost for interpretable classification of wheat nitrogen stress gradients using multimodal unmanned aerial vehicle (UAV) multispectral and thermal infrared (TIR) imagery. Field experiments were conducted at the Xinxiang base in Henan Province during the 2023–2024, following a randomized block design involving 10 cultivars, four nitrogen levels, and four water treatments. Multisource UAV images acquired at jointing, heading, and filling stages were used to construct a multimodal feature set consisting of manual features (spectral bands, vegetation indices (VIs), TIR, and their interaction terms) and seven temporal statistical features. A deep learning model (CNN-LSTM) was utilized to further extract deep spatiotemporal features, and its performance was systematically compared with traditional machine learning models. The results show that multimodal feature fusion significantly enhanced classification performance. The CNN-LSTM model achieved an accuracy of 89.38% with fused multimodal features, outperforming all traditional machine learning models. Incorporating multi-temporal features improved the F1macro of the XGBoost model to 0.9131, a 9.42 percentage-point increase over using the single heading stage alone. The hybrid model (CNN-LSTM-XGBoost) achieved the highest overall performance (Accuracy = 0.9208; F1macro = 0.9212; AUCmacro = 0.9879; Kappa = 0.8944). SHAP analysis identified TIR × NDRE as the most influential indicator, reflecting the coupled physiological response of reduced chlorophyll content and increased canopy temperature under nitrogen deficiency. The proposed multimodal, multi-temporal, and interpretable framework provides a robust technical foundation for UAV-assisted precision nitrogen management.
- 7 February 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (4) , 538
Top Cited PapersOpen AccessA CNN-LSTM-XGBoost Hybrid Framework for Interpretable Nitrogen Stress Classification Using Multimodal UAV Imagery
Accurate diagnosis of nitrogen status is essential for precision fertilization in winter wheat. Single-modal or single-temporal remote sensing often fails to capture the multidimensional crop responses to nitrogen stress. In this study, we propose a hybrid framework based on CNN-LSTM-XGBoost for interpretable classification of wheat nitrogen stress gradients using multimodal unmanned aerial vehicle (UAV) multispectral and thermal infrared (TIR) imagery. Field experiments were conducted at the Xinxiang base in Henan Province during the 2023–2024, following a randomized block design involving 10 cultivars, four nitrogen levels, and four water treatments. Multisource UAV images acquired at jointing, heading, and filling stages were used to construct a multimodal feature set consisting of manual features (spectral bands, vegetation indices (VIs), TIR, and their interaction terms) and seven temporal statistical features. A deep learning model (CNN-LSTM) was utilized to further extract deep spatiotemporal features, and its performance was systematically compared with traditional machine learning models. The results show that multimodal feature fusion significantly enhanced classification performance. The CNN-LSTM model achieved an accuracy of 89.38% with fused multimodal features, outperforming all traditional machine learning models. Incorporating multi-temporal features improved the F1macro of the XGBoost model to 0.9131, a 9.42 percentage-point increase over using the single heading stage alone. The hybrid model (CNN-LSTM-XGBoost) achieved the highest overall performance (Accuracy = 0.9208; F1macro = 0.9212; AUCmacro = 0.9879; Kappa = 0.8944). SHAP analysis identified TIR × NDRE as the most influential indicator, reflecting the coupled physiological response of reduced chlorophyll content and increased canopy temperature under nitrogen deficiency. The proposed multimodal, multi-temporal, and interpretable framework provides a robust technical foundation for UAV-assisted precision nitrogen management.
- Open Access
- 12 June 2025
- Published by MDPI AG in Agriculture
- Vol. 15 (12) , 1272
Maize Leaf Area Index Estimation Based on Machine Learning Algorithm and Computer Vision
Precise estimation of the leaf area index (LAI) is vital in efficient maize growth monitoring and precision farming. Traditional LAI measurement methods are often destructive and labor-intensive, while techniques relying solely on spectral data suffer from limitations such as spectral saturation. To overcome these difficulties, the study integrated computer vision techniques with UAV-based remote sensing data to establish a rapid and non-invasive method for estimating the LAI in maize. Multispectral imagery of maize was acquired via UAV platforms across various phenological stages, and vegetation features were derived based on the Excess Green (ExG) Index and the Hue–Saturation–Value (HSV) color space. LAI standardization was performed through edge detection and the cumulative distribution function. The proposed LAI estimation model, named VisLAI, based solely on visible light imagery, demonstrated high accuracy, with R2 values of 0.84, 0.75, and 0.50, and RMSE values of 0.24, 0.35, and 0.44 across the big trumpet, tasseling–silking, and grain filling stages, respectively. When HSV-based optimization was applied, VisLAI achieved even better performance, with R2 values of 0.92, 0.90, and 0.85, and RMSE values of 0.19, 0.23, and 0.22 at the respective stages. The estimation results were validated against ground-truth data collected using the LAI-2200C plant canopy analyzer and compared with six machine learning algorithms, including Gradient Boosting (GB), Random Forest (RF), Ridge Regression (RR), Support Vector Regression (SVR), and Linear Regression (LR). Among these, GB achieved the best performance, with R2 values of 0.88, 0.88, and 0.65, and RMSE values of 0.22, 0.25, and 0.34. However, VisLAI consistently outperformed all machine learning models, especially during the grain filling stage, demonstrating superior robustness and accuracy. The VisLAI model proposed in this study effectively utilizes UAV-captured visible light imagery and computer vision techniques to achieve accurate, efficient, and non-destructive estimation of maize LAI. It outperforms traditional and machine learning-based approaches and provides a reliable solution for real-world maize growth monitoring and agricultural decision-making.
- 12 June 2025
- Published by MDPI AG in Agriculture
- Vol. 15 (12) , 1272
Open AccessMaize Leaf Area Index Estimation Based on Machine Learning Algorithm and Computer Vision
Precise estimation of the leaf area index (LAI) is vital in efficient maize growth monitoring and precision farming. Traditional LAI measurement methods are often destructive and labor-intensive, while techniques relying solely on spectral data suffer from limitations such as spectral saturation. To overcome these difficulties, the study integrated computer vision techniques with UAV-based remote sensing data to establish a rapid and non-invasive method for estimating the LAI in maize. Multispectral imagery of maize was acquired via UAV platforms across various phenological stages, and vegetation features were derived based on the Excess Green (ExG) Index and the Hue–Saturation–Value (HSV) color space. LAI standardization was performed through edge detection and the cumulative distribution function. The proposed LAI estimation model, named VisLAI, based solely on visible light imagery, demonstrated high accuracy, with R2 values of 0.84, 0.75, and 0.50, and RMSE values of 0.24, 0.35, and 0.44 across the big trumpet, tasseling–silking, and grain filling stages, respectively. When HSV-based optimization was applied, VisLAI achieved even better performance, with R2 values of 0.92, 0.90, and 0.85, and RMSE values of 0.19, 0.23, and 0.22 at the respective stages. The estimation results were validated against ground-truth data collected using the LAI-2200C plant canopy analyzer and compared with six machine learning algorithms, including Gradient Boosting (GB), Random Forest (RF), Ridge Regression (RR), Support Vector Regression (SVR), and Linear Regression (LR). Among these, GB achieved the best performance, with R2 values of 0.88, 0.88, and 0.65, and RMSE values of 0.22, 0.25, and 0.34. However, VisLAI consistently outperformed all machine learning models, especially during the grain filling stage, demonstrating superior robustness and accuracy. The VisLAI model proposed in this study effectively utilizes UAV-captured visible light imagery and computer vision techniques to achieve accurate, efficient, and non-destructive estimation of maize LAI. It outperforms traditional and machine learning-based approaches and provides a reliable solution for real-world maize growth monitoring and agricultural decision-making.
- Open Access
- 28 August 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (17) , 3176
Estimating Maize Crop Height and Aboveground Biomass Using Multi-Source Unmanned Aerial Vehicle Remote Sensing and Optuna-Optimized Ensemble Learning Algorithms
Accurately assessing maize crop height (CH) and aboveground biomass (AGB) is crucial for understanding crop growth and light-use efficiency. Unmanned aerial vehicle (UAV) remote sensing, with its flexibility and high spatiotemporal resolution, has been widely applied in crop phenotyping studies. Traditional canopy height models (CHMs) are significantly influenced by image resolution and meteorological factors. In contrast, the accumulated incremental height (AIH) extracted from point cloud data offers a more accurate estimation of CH. In this study, vegetation indices and structural features were extracted from optical imagery, nadir and oblique photography, and LiDAR point cloud data. Optuna-optimized models, including random forest regression (RFR), light gradient boosting machine (LightGBM), gradient boosting decision tree (GBDT), and support vector regression (SVR), were employed to estimate maize AGB. Results show that AIH99 has higher accuracy in estimating CH. LiDAR demonstrated the highest accuracy, while oblique photography and nadir photography point clouds were slightly less accurate. Fusion of multi-source data achieved higher estimation accuracy than single-sensor data. Embedding structural features can mitigate spectral saturation, with R2 ranging from 0.704 to 0.939 and RMSE ranging from 0.338 to 1.899 t/hm2. During the entire growth cycle, the R2 for LightGBM and RFR were 0.887 and 0.878, with an RMSE of 1.75 and 1.76 t/hm2. LightGBM and RFR also performed well across different growth stages, while SVR showed the poorest performance. As the amount of nitrogen application gradually decreases, the accumulation and accumulation rate of AGB also gradually decrease. This high-throughput crop-phenotyping analysis method offers advantages, such as speed and high accuracy, providing valuable references for precision agriculture management in maize fields.
- 28 August 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (17) , 3176
Open AccessEstimating Maize Crop Height and Aboveground Biomass Using Multi-Source Unmanned Aerial Vehicle Remote Sensing and Optuna-Optimized Ensemble Learning Algorithms
Accurately assessing maize crop height (CH) and aboveground biomass (AGB) is crucial for understanding crop growth and light-use efficiency. Unmanned aerial vehicle (UAV) remote sensing, with its flexibility and high spatiotemporal resolution, has been widely applied in crop phenotyping studies. Traditional canopy height models (CHMs) are significantly influenced by image resolution and meteorological factors. In contrast, the accumulated incremental height (AIH) extracted from point cloud data offers a more accurate estimation of CH. In this study, vegetation indices and structural features were extracted from optical imagery, nadir and oblique photography, and LiDAR point cloud data. Optuna-optimized models, including random forest regression (RFR), light gradient boosting machine (LightGBM), gradient boosting decision tree (GBDT), and support vector regression (SVR), were employed to estimate maize AGB. Results show that AIH99 has higher accuracy in estimating CH. LiDAR demonstrated the highest accuracy, while oblique photography and nadir photography point clouds were slightly less accurate. Fusion of multi-source data achieved higher estimation accuracy than single-sensor data. Embedding structural features can mitigate spectral saturation, with R2 ranging from 0.704 to 0.939 and RMSE ranging from 0.338 to 1.899 t/hm2. During the entire growth cycle, the R2 for LightGBM and RFR were 0.887 and 0.878, with an RMSE of 1.75 and 1.76 t/hm2. LightGBM and RFR also performed well across different growth stages, while SVR showed the poorest performance. As the amount of nitrogen application gradually decreases, the accumulation and accumulation rate of AGB also gradually decrease. This high-throughput crop-phenotyping analysis method offers advantages, such as speed and high accuracy, providing valuable references for precision agriculture management in maize fields.
- Open Access
UAV-Based Hyperspectral and Ensemble Machine Learning for Predicting Yield in Winter Wheat
Winter wheat is a widely-grown cereal crop worldwide. Using growth-stage information to estimate winter wheat yields in a timely manner is essential for accurate crop management and rapid decision-making in sustainable agriculture, and to increase productivity while reducing environmental impact. UAV remote sensing is widely used in precision agriculture due to its flexibility and increased spatial and spectral resolution. Hyperspectral data are used to model crop traits because of their ability to provide continuous rich spectral information and higher spectral fidelity. In this study, hyperspectral image data of the winter wheat crop canopy at the flowering and grain-filling stages was acquired by a low-altitude unmanned aerial vehicle (UAV), and machine learning was used to predict winter wheat yields. Specifically, a large number of spectral indices were extracted from the spectral data, and three feature selection methods, recursive feature elimination (RFE), Boruta feature selection, and the Pearson correlation coefficient (PCC), were used to filter high spectral indices in order to reduce the dimensionality of the data. Four major basic learner models, (1) support vector machine (SVM), (2) Gaussian process (GP), (3) linear ridge regression (LRR), and (4) random forest (RF), were also constructed, and an ensemble machine learning model was developed by combining the four base learner models. The results showed that the SVM yield prediction model, constructed on the basis of the preferred features, performed the best among the base learner models, with an R2 between 0.62 and 0.73. The accuracy of the proposed ensemble learner model was higher than that of each base learner model; moreover, the R2 (0.78) for the yield prediction model based on Boruta’s preferred characteristics was the highest at the grain-filling stage.
Open AccessUAV-Based Hyperspectral and Ensemble Machine Learning for Predicting Yield in Winter Wheat
Winter wheat is a widely-grown cereal crop worldwide. Using growth-stage information to estimate winter wheat yields in a timely manner is essential for accurate crop management and rapid decision-making in sustainable agriculture, and to increase productivity while reducing environmental impact. UAV remote sensing is widely used in precision agriculture due to its flexibility and increased spatial and spectral resolution. Hyperspectral data are used to model crop traits because of their ability to provide continuous rich spectral information and higher spectral fidelity. In this study, hyperspectral image data of the winter wheat crop canopy at the flowering and grain-filling stages was acquired by a low-altitude unmanned aerial vehicle (UAV), and machine learning was used to predict winter wheat yields. Specifically, a large number of spectral indices were extracted from the spectral data, and three feature selection methods, recursive feature elimination (RFE), Boruta feature selection, and the Pearson correlation coefficient (PCC), were used to filter high spectral indices in order to reduce the dimensionality of the data. Four major basic learner models, (1) support vector machine (SVM), (2) Gaussian process (GP), (3) linear ridge regression (LRR), and (4) random forest (RF), were also constructed, and an ensemble machine learning model was developed by combining the four base learner models. The results showed that the SVM yield prediction model, constructed on the basis of the preferred features, performed the best among the base learner models, with an R2 between 0.62 and 0.73. The accuracy of the proposed ensemble learner model was higher than that of each base learner model; moreover, the R2 (0.78) for the yield prediction model based on Boruta’s preferred characteristics was the highest at the grain-filling stage.