Grain yield is increasingly affected by climate factors such as drought and heat. To develop resilient and high-yielding cultivars, high-throughput phenotyping (HTP) techniques are essential for precise decisions in wheat breeding. The ability of unmanned aerial vehicle (UAV)-based multispectral imaging and ensemble learning methods to increase the accuracy of grain yield prediction in practical breeding work is evaluated in this study. For this, 211 winter wheat genotypes were planted under full and limited irrigation treatments, and multispectral data were collected at heading, flowering, early grain filling (EGF), and mid-grain filling (MGF) stages. Twenty multispectral vegetation indices (VIs) were estimated, and VIs with heritability greater than 0.5 were selected to evaluate the models across the growth stages under both irrigation treatments. A framework for ensemble learning was developed by combining multiple base models such as random forest (RF), support vector machine (SVM), Gaussian process (GP), and ridge regression (RR). The R² values between VIs and grain yield for individual base models were ranged from 0.468 to 0.580 and 0.537 to 0.598 for grain yield prediction in full and limited irrigation treatments across growth stages, respectively. The prediction results of ensemble models were ranged from 0.491 to 0.616 and 0.560 to 0.616 under full and limited irrigation treatments respectively, and were higher than that of the corresponding base learners. Moreover, the grain yield prediction results were observed high at mid grain filling stage under both full (R² = 0.625) and limited (R² = 0.628) irrigation treatments through ensemble learning based stacking of four base learners. Further improvements in ensemble learning models can accelerate the use of UAV-based multispectral data for accurate predictions of complex traits like grain yield in wheat.

Above-ground biomass (AGB) serves as an indicator of crop growth status, and acquiring timely AGB information is crucial for estimating crop yield and determining appropriate water and fertilizer inputs. Unmanned Aerial Vehicles (UAVs) equipped with RGB cameras offer an affordable and practical solution for efficiently obtaining crop AGB. However, traditional vegetation indices (VIs) alone are insufficient in capturing crop canopy structure, leading to poor estimation accuracy. Moreover, different flight heights and machine learning algorithms can impact estimation accuracy. Therefore, this study aims to enhance wheat AGB estimation accuracy by combining VIs, crop height, and texture features while investigating the influence of flight height and machine learning algorithms on estimation. During the heading and grain-filling stages of wheat, wheat AGB data and UAV RGB images were collected at flight heights of 30 m, 60 m, and 90 m. Machine learning algorithms, including Random Forest Regression (RFR), Gradient Boosting Regression Trees (GBRT), Ridge Regression (RR), Least Absolute Shrinkage and Selection Operator (Lasso) and Support Vector Regression (SVR), were utilized to construct wheat AGB estimation models. The research findings are as follows: (1) Estimation accuracy using VIs alone is relatively low, with R² values ranging from 0.519 to 0.695. However, combining VIs with crop height and texture features improves estimation accuracy, with R² values reaching 0.845 to 0.852. (2) Estimation accuracy gradually decreases with increasing flight height, resulting in R² values of 0.519–0.852, 0.438–0.837, and 0.445–0.827 for flight heights of 30 m, 60 m, and 90 m, respectively. (3) The choice of machine learning algorithm significantly influences estimation accuracy, with RFR outperforming other machine learnings. In conclusion, UAV RGB images contain valuable crop canopy information, and effectively utilizing this information in conjunction with machine learning algorithms enables accurate wheat AGB estimation, providing a new approach for precision agriculture management using UAV remote sensing technology.

Crop chlorophyll content measuring plays a vital role in monitoring crop growth and optimizing agricultural inputs such as water and fertilizer. However, traditional methods for measuring chlorophyll content primarily rely on labor-intensive chemical analysis. These methods not only involve destructive sampling but also are time-consuming, often resulting in obtaining monitoring results after the optimal growth period of crops. Unmanned aerial vehicle (UAV) remote sensing technology offers the potential for rapidly acquiring chlorophyll content estimations over large areas. Currently, most studies only utilize single features from UAV data and employ traditional machine learning algorithms to estimate chlorophyll content, while the potential of multisource feature fusion and stacking ensemble learning in chlorophyll content estimation research remains largely unexplored. Therefore, this study collected UAV spectral features, thermal features, structural features, as well as chlorophyll content data during maize jointing, trumpet, and big trumpet stages, creating a multisource feature dataset. Subsequently, chlorophyll content estimation models were built based on four machine learning algorithms, namely, ridge regression (RR), light gradient boosting machine (LightGBM), random forest regression (RFR), and stacking ensemble learning. The research results demonstrate that (1) the multisource feature fusion approach achieves higher estimation accuracy compared to the single-feature method, with R² ranging from 0.699 to 0.754 and rRMSE ranging from 8.36% to 9.47%; and (2) the stacking ensemble learning outperforms traditional machine learning algorithms in chlorophyll content estimation accuracy, particularly when combined with multisource feature fusion, resulting in the best estimation results. In summary, this study proves the effective improvement in chlorophyll content estimation accuracy through multisource feature fusion and stacking ensemble learning. The combination of these methods provides reliable estimation of chlorophyll content using UAV remote sensing technology and brings new insights to precision agriculture management in this field.

Detection and counting of wheat heads are crucial for wheat yield estimation. To address the issues of overlapping and small volumes of wheat heads on complex backgrounds, this paper proposes the YOLOv7-MA model. By introducing micro-scale detection layers and the convolutional block attention module, the model enhances the target information of wheat heads and weakens the background information, thereby strengthening its ability to detect small wheat heads and improving the detection performance. Experimental results indicate that after being trained and tested on the Global Wheat Head Dataset 2021, the YOLOv7-MA model achieves a mean average precision (MAP) of 93.86% with a detection speed of 35.93 frames per second (FPS), outperforming Faster-RCNN, YOLOv5, YOLOX, and YOLOv7 models. Meanwhile, when tested under the three conditions of low illumination, blur, and occlusion, the coefficient of determination (R²) of YOLOv7-MA is respectively 0.9895, 0.9872, and 0.9882, and the correlation between the predicted wheat head number and the manual counting result is stronger than others. In addition, when the YOLOv7-MA model is transferred to field-collected wheat head datasets, it maintains high performance with MAP in maturity and filling stages of 93.33% and 93.03%, respectively, and R² values of 0.9632 and 0.9155, respectively, demonstrating better performance in the maturity stage. Overall, YOLOv7-MA has achieved accurate identification and counting of wheat heads in complex field backgrounds. In the future, its application with unmanned aerial vehicles (UAVs) can provide technical support for large-scale wheat yield estimation in the field.

Introduction: In the context of climate variability, rapid and accurate estimation of winter wheat yield is essential for agricultural policymaking and food security. With advancements in remote sensing technology and deep learning, methods utilizing remotely sensed data are increasingly being employed for large-scale crop growth monitoring and yield estimation.Methods: Solar-induced chlorophyll fluorescence (SIF) is a new remote sensing metric that is closely linked to crop photosynthesis and has been applied to crop growth and drought monitoring. However, its effectiveness for yield estimation under various data fusion conditions has not been thoroughly explored. This study developed a deep learning model named BO-CNN-BiLSTM (BCBL), combining the feature extraction capabilities of a convolutional neural network (1DCNN) with the time-series memory advantages of a bidirectional long short-term memory network (BiLSTM). The Bayesian Optimization (BOM) method was employed to determine the optimal hyperparameters for model parameter optimization. Traditional remote sensing variables (TS), such as the Enhanced Vegetation Index (EVI) and Leaf Area Index (LAI), were fused with the SIF and climate data to estimate the winter wheat yields in Henan Province, exploring the SIF’s estimation capabilities using various datasets.Results and Discussion: The results demonstrated that the BCBL model, integrating TS, climate, and SIF data, outperformed other models (e.g., LSTM, Transformer, RF, and XGBoost) in the estimation accuracy, with R^²=0.81, RMSE=616.99 kg/ha, and MRE=7.14%. Stepwise sensitivity analysis revealed that the BCBL model reliably identified the critical stage of winter wheat yield formation (early March to early May) and achieved high yield estimation accuracy approximately 25 d before harvest. Furthermore, the BCBL model exhibited strong stability and generalization across different climatic conditions.Conclusion: Thus, the BCBL model combined with SIF data can offer reliable winter wheat yield estimates, hold significant potential for application, and provide valuable insights for agricultural policymaking and field management.

The segmentation of plant disease images enables researchers to quantify the proportion of disease spots on leaves, known as disease severity. Current deep learning methods predominantly focus on single diseases, simple lesions, or laboratory-controlled environments. In this study, we established and publicly released image datasets of field scenarios for three diseases: soybean bacterial blight (SBB), wheat stripe rust (WSR), and cedar apple rust (CAR). We developed Plant Disease Segmentation Networks (PDSNets) based on LinkNet with ResNet-18 as the encoder, including three versions: ×1.0, ×0.75, and ×0.5. The ×1.0 version incorporates a 4 × 4 embedding layer to enhance prediction speed, while versions ×0.75 and ×0.5 are lightweight variants with reduced channel numbers within the same architecture. Their parameter counts are 11.53 M, 6.50 M, and 2.90 M, respectively. PDSNetx0.5 achieved an overall F1 score of 91.96%, an Intersection over Union (IoU) of 85.85% for segmentation, and a coefficient of determination (R²) of 0.908 for severity estimation. On a local central processing unit (CPU), PDSNetx0.5 demonstrated a prediction speed of 34.18 images (640 × 640 pixels) per second, which is 2.66 times faster than LinkNet. Our work provides an efficient and automated approach for assessing plant disease severity in field scenarios.