Fine-grained weed recognition using Swin Transformer and two-stage transfer learning.

Weeding is very critical for agriculture due to its importance for reducing crop yield loss. Accurate recognition of weed species is one of the major challenges for achieving automatic and precise weeding. To improve the recognition performance of weeds and crops with similar visual characteristics, a fine-grained weed recognition method based on Swin Transformer and two-stage transfer learning is proposed in this study. First, the Swin Transformer network is introduced to learn the discriminative features that can distinguish subtle differences between visually similar weeds and crops. Second, a contrastive loss is applied to further enlarge the feature differences between different categories of weeds and crops. Finally, a two-stage transfer learning strategy is proposed to address the problem of insufficient training data and improve the accuracy of weed recognition. To evaluate the effectiveness of the proposed method, we constructed a private weed dataset (MWFI) with maize seedling and seven species of associated weeds that are collected in the farmland environment. The experimental results on this dataset show that the proposed method achieved the recognition accuracy, precision, recall, and F1 score of 99.18%, 99.33%, 99.11%, and 99.22%, respectively, which are superior to the performance of the state-of-the-art convolutional neural network (CNN)-based architectures including VGG-16, ResNet-50, DenseNet-121, SE-ResNet-50, and EfficientNetV2. Additionally, evaluation results on the public DeepWeeds dataset further demonstrate the effectiveness of the proposed method. This study can provide a reference for the design of automatic weed recognition systems.

A new algorithm for evaluating reservoir density based on X-ray logging technology.

Rock density is an important parameter to provide critical information for evaluating both conventional and unconventional reservoirs. During the drilling process, it's a huge challenge to eliminating the negative effects of irregular mud cake formed in drilling fluid deposition to evaluating reservoir information accurately. However, the calibration of density measurement by correction charts would usually generate large errors, and the parameters that need to be corrected are often unpredictable. Therefore, based on the X-ray density logging technology, while eliminating the radioactive hazards of the isotope gamma source (137Cs), a new method is proposed to address the problem through the energy spectrum information from four detectors. Theoretically, this method would analyze the role of X-rays in the dual media of formation and mud cake and then integrate the energy spectrum information from four detectors, while using Newton iterative inversion to invert the parameters about formation and mud cake. As a result, the evaluation of reservoir parameters can be achieved without correcting the mud cake. In verifying the effectiveness of this method, a simulation example shows the high accuracy of X-ray density inversion for multiple parameters. This research provides an X-ray density inversion algorithm to realize the simultaneous calculation of formation and mud cake parameters, which is of great significance for guiding hydrocarbon exploration and production.