Soil salinization seriously affects the sustainable development of agricultural production; thus, the timely, efficient, and accurate estimation of soil salt content (SSC) has important research significance. In this study, the feasibility of soil salt content retrieval using machine learning models was explored based on a UAV (unmanned aerial vehicle) multi-spectral remote sensing platform. First, two variable screening methods (Pearson correlation analysis and Grey relational analysis) are used to screen the characteristic importance of 20 commonly used spectral indices. Then, the sensitive spectral variables were divided into a vegetation index group, a salt index group, and a combination variable group, which represent the model. To estimate SSC information for soil depths of 0–20 cm and 20–40 cm, three machine learning regression models were constructed: Support Vector Machine (SVM), Random Forest (RF), and Backpropagation Neural Network (BPNN). Finally, the salt distribution map for a 0–20 cm soil depth was drawn based on the best estimation model. The results of experiments show that GRA is better than PCA in improving the accuracy of the estimation model, and the combination variable group containing soil moisture information performs best. The three machine learning models have achieved good prediction effects to some extent. The accuracy and stability of the model are considered comprehensively, the prediction effect of 0–20 cm is higher than that of 20–40 cm, and the validation set coefficient of determination (R²), Root-Mean-Square-Error (RMSE), and Mean Absolute Error (MAE) of the best inversion model are 0.775, 0.055, and 0.038, and the soil salt spatial map based on the optimal estimation model can reflect the salinization distribution in the study area. Therefore, this study shows that a UAV multi-spectral remote sensing platform combined with machine learning models can better monitor farmland soil salt content.

The rapid and accurate identification of sunflower lodging is important for the assessment of damage to sunflower crops. To develop a fast and accurate method of extraction of information on sunflower lodging, this study improves the inputs to SegNet and U-Net to render them suitable for multi-band image processing. Random forest and two improved deep learning methods are combined with RGB, RGB + NIR, RGB + red-edge, and RGB + NIR + red-edge bands of multi-spectral images captured by a UAV (unmanned aerial vehicle) to construct 12 models to extract information on sunflower lodging. These models are then combined with the method used to ignore edge-related information to predict sunflower lodging. The results of experiments show that the deep learning methods were superior to the random forest method in terms of the obtained lodging information and accuracy. The predictive accuracy of the model constructed by using a combination of SegNet and RGB + NIR had the highest overall accuracy of 88.23%. Adding NIR to RGB improved the accuracy of extraction of the lodging information whereas adding red-edge reduced it. An overlay analysis of the results for the lodging area shows that the extraction error was mainly caused by the failure of the model to recognize lodging in mixed areas and low-coverage areas. The predictive accuracy of information on sunflower lodging when edge-related information was ignored was about 2% higher than that obtained by using the direct splicing method.

An improved semantic segmentation method based on object contextual representations network (OCRNet) is proposed to accurately identify zucchinis intercropped with sunflowers from unmanned aerial vehicle (UAV) visible images taken over Hetao Irrigation District, Inner Mongolia, China. The proposed method improves on the performance of OCRNet in two respects. First, based on the object region context extraction structure of the OCRNet, a branch that uses the channel attention module was added in parallel to rationally use channel feature maps with different weights and reduce the noise of invalid channel features. Secondly, Lovász-Softmax loss was introduced to improve the accuracy of the object region representation in the OCRNet and optimize the final segmentation result at the object level. We compared the proposed method with extant advanced semantic segmentation methods (PSPNet, DeepLabV3+, DNLNet, and OCRNet) in two test areas to test its effectiveness. The results showed that the proposed method achieved the best semantic segmentation effect in the two test areas. More specifically, our method performed better in processing image details, segmenting field edges, and identifying intercropping fields. The proposed method has significant advantages for crop classification and intercropping recognition based on UAV visible images, and these advantages are more substantive in object-level evaluation metrics (mIoU and intercropping IoU).

Accurately obtaining the multi-year spatial distribution information of crops combined with the corresponding agricultural production data is of great significance to the optimal management of agricultural production in the future. However, there are still some problems, such as low generality of crop type mapping models and susceptibility to cloud pollution in large-area crop mapping. Here, the models were constructed by using multi-phase images at the key periods to improve model generality. Multi-phase images in key periods masked each other to obtain large-area cloud-free images, which were combined with the general models to map large areas. The key periods were determined by calculating the global separation index (GSI) of the main crops (wheat, maize, sunflower, and squash) in different growth stages in the Hetao Irrigation District (HID) in China. The multi-phase images in the key period were used to make the data set and were then combined with a variety of deep learning algorithms (U-Net, U-Net++, Deeplabv3+, and SegFormer) to construct general models. The selection of the key periods, the acquisition of regional cloud-free images, and the construction of the general crop mapping models were all based on 2021 data. Relevant models and methods were respectively applied to crop mapping of the HID from 2017 to 2020 to study the generality of mapping methods. The results show that the images obtained by combining multi-phase images in the key period effectively avoided the influence of clouds and aerosols in large areas. Compared with the other three algorithms, U-Net had better mapping results. The F1-score, mean intersection-over-union, and overall accuracy were 78.13%, 75.39% and 96.28%, respectively. The crop mapping model was applied to images in 2020, and its average overall accuracy was more than 88.28%. When we applied the model to map crops (county food crops, cash crops, and cultivated land area) from 2017 to 2019, the regression analysis between the mapping areas obtained by the model and the ground measurements was made. The R2 was 0.856, and the RMSE was 17,221 ha, which reached the application accuracy, indicating that the mapping method has certain universality for mapping in different years.

This study explores the classification potential of a multispectral classification model for farmland with planting structures of different complexity. Unmanned aerial vehicle (UAV) remote sensing technology is used to obtain multispectral images of three study areas with low-, medium-, and high-complexity planting structures, containing three, five, and eight types of crops, respectively. The feature subsets of three study areas are selected by recursive feature elimination (RFE). Object-oriented random forest (OB-RF) and object-oriented support vector machine (OB-SVM) classification models are established for the three study areas. After training the models with the feature subsets, the classification results are evaluated using a confusion matrix. The OB-RF and OB-SVM models’ classification accuracies are 97.09% and 99.13%, respectively, for the low-complexity planting structure. The equivalent values are 92.61% and 99.08% for the medium-complexity planting structure and 88.99% and 97.21% for the high-complexity planting structure. For farmland with fragmentary plots and a high-complexity planting structure, as the planting structure complexity changed from low to high, both models’ overall accuracy levels decreased. The overall accuracy of the OB-RF model decreased by 8.1%, and that of the OB-SVM model only decreased by 1.92%. OB-SVM achieves an overall classification accuracy of 97.21%, and a single-crop extraction accuracy of at least 85.65%. Therefore, UAV multispectral remote sensing can be used for classification applications in highly complex planting structures.

This study designed a vertical take-off and landing tailsitter unmanned aerial vehicle (UAV) with a long endurance time. Nine parameters of the tailsitter UAV were investigated. Using a 2^k full factorial test, 512 experiments on the nine parameters were conducted at their maximum and minimum values. The time coefficient and air resistance were calculated using the computational fluid dynamics (CFD) method under different parameter combinations. The analysis of variance determined that the specific factors influencing the time coefficient and air resistance were the root chord, wingtip chord, wingspan, and sweep angle. By carrying out a central composite design (CCD) test, 25 sample points of the four particular factors were constructed. The time coefficient and air resistance were simulated under different structural parameter combinations using the CFD method. CFD simulation was verified by carrying out a wind tunnel test, and the results revealed that the aerodynamic coefficient error was less than 5%, while the air resistance error was less than 6%. The response surface methodology (RSM) for the time coefficient and air resistance was established using a genetic aggregation method. A multi-objective genetic algorithm (MOGA) was used to optimize the parameters with regard to the maximum time coefficient and minimum air resistance. The optimal structural parameters were wing root chord length at 315 mm, wingtip chord length at 182 mm, wingspan length at 1198 mm, and sweep angle at 16°. Compared with the original layout and size, the time coefficient of the new design of the tailsitter UAV improved by 19.5%, while the air resistance reduced by 34.78%. The results obtained by this study are significant for the design of tailsitter UAVs.