The timely and accurate detection of wheat lodging at a large scale is necessary for loss assessments in agricultural insurance claims. Most existing deep-learning-based methods of wheat lodging detection use data from unmanned aerial vehicles, rendering monitoring wheat lodging at a large scale difficult. Meanwhile, the edge feature is not accurately extracted. In this study, a semantic segmentation network model called the pyramid transposed convolution network (PTCNet) was proposed for large-scale wheat lodging extraction and detection using GaoFen-2 satellite images with high spatial resolutions. Multi-scale high-level features were combined with low-level features to improve the segmentation’s accuracy and to enhance the extraction sensitivity of wheat lodging areas in the proposed model. In addition, four types of vegetation indices and three types of edge features were added into the network and compared to the increment in the segmentation’s accuracy. The F1 score and the intersection over union of wheat lodging extraction reached 85.31% and 74.38% by PTCNet, respectively, outperforming other compared benchmarks, i.e., SegNet, PSPNet, FPN, and DeepLabv3+ networks. PTCNet can achieve accurate and large-scale extraction of wheat lodging, which is significant in the fields of loss assessment and agricultural insurance claims.

The segmentation of crop disease zones is an important task of image processing since the knowledge of the growth status of crops is critical for agricultural management. Nowadays, images taken by unmanned aerial vehicles (UAVs) have been widely used in the segmentation of crop diseases, and almost all current studies use the study paradigm of full supervision, which needs a large amount of manually labelled data. In this study, a weakly supervised method for disease segmentation of UAV images is proposed. In this method, auxiliary branch block (ABB) and feature reuse module (FRM) were developed. The method was tested using UAV images of maize northern leaf blight (NLB) based on image-level labels only, i.e., only the information as to whether NBL occurs is given. The quality (intersection over union (IoU) values) of the pseudo-labels in the validation dataset achieved 43% and the F1 score reached 58%. In addition, the new method took 0.08 s to generate one pseudo-label, which is highly efficient in generating pseudo-labels. When pseudo-labels from the train dataset were used in the training of segmentation models, the IoU values of disease in the test dataset reached 50%. These accuracies outperformed the benchmarks of the ACoL (45.5%), RCA (36.5%), and MDC (34.0%) models. The segmented NLB zones from the proposed method were more complete and the boundaries were more clear. The effectiveness of ABB and FRM was also explored. This study is the first time supervised segmentation of UAV images of maize NLB using only image-level data was applied, and the above test results confirm the effectiveness of the proposed method.

Soybean, a globally important food and oil crop, requires accurate estimation of above-ground biomass (AGB) to optimize management and prevent yield loss. Despite the availability of various remote sensing methods, systematic research on effectively integrating canopy height (CH) and spectral information for improved AGB estimation remains insufficient. This study addresses this gap using drone data. Three CH utilization approaches were tested: (1) simple combination of CH and spectral vegetation indices (VIs), (2) fusion of CH and VI, and (3) integration of CH, VI, and growing-degree days (GDDs). The results indicate that adding CH always enhances AGB estimation which is based only on VIs, with the fusion approach outperforming simple combination. Incorporating GDD further improved AGB estimation for highly accurate CH data, with the best model achieving a root mean square error (RMSE) of 87.52 ± 5.88 g/m² and a mean relative error (MRE) of 28.59 ± 1.99%. However, for the multispectral data with low CH accuracy, the VIs + GDD fusion (RMSE = 92.94 ± 6.84 g/m², MRE = 30.08 ± 2.29%) surpassed CH + VIs + GDD (RMSE = 97.99 ± 6.71 g/m², MRE = 31.41 ± 2.56%). The findings highlight the role of CH accuracy in AGB estimation and validate the value of growth-stage information in robust modeling. Future research should prioritize the refining of CH prediction and the optimization of composite variable construction to promote the application of this approach in agricultural monitoring.