Search

Weed competitiveness monitoring is crucial for field management at specific locations. Recent research in the fusion of multimodal data from unmanned aerial vehicles (UAVs) has propelled this advancement. However, these studies merely stack extracted features equivalently, neglecting the full utilization of fused information. This study utilizes hyperspectral and LiDAR data collected by UAVs to proposes a multimodal deep fusion model (MulDFNet) using Transformer and multi-layer residuals. It utilizes a comprehensive competitive index (CCI-A) based on multidimensional phenotypes of maize to assess the competitiveness of weeds in farmland ecosystems. To validate the effectiveness of this model, a series of ablation studies were conducted involving different modalities data, with/without the Transformer Encoder (TE) modules, and different fusion modules (shallow residual fusion module, deep feature fusion module). Additionally, a comparison was made with early/late stacking fusion models, traditional machine learning models, and deep learning models from relevant studies. The results indicate that the multimodal deep fusion model utilizing HSI, VI, and CHM data achieved a predictive effect of R2 = 0.903 (RMSE = 0.078). Notably, the best performance was observed during the five-leaf stage. The combination of shallow and deep fusion modules demonstrated better predictive performance compared to a single fusion module. The positive impact of the TE module on model performance is evident, as its multi-head attention mechanism aids in better capturing the relationships and importance between feature maps and competition indices, thereby enhancing the model's predictive capability. In weed competition prediction, the multimodal deep fusion model proposed in this study has demonstrated significantly better predictive performance compared to early/late stacking fusion models and other machine learning models (RF, SVR, PLS, DNN-F2 and Multi-channel CNN). Overall, the multimodal deep fusion model developed in this study demonstrates outstanding performance in assessing weed competitiveness and can predict the competitive intensity of weeds in maize across various growth stages on a broad scale.

Herbicide-resistant weeds represent a significant challenge to modern agriculture. The need for innovative and sustainable weed management strategies has become increasingly pressing as the threat of herbicide-resistant weeds continues to escalate. Unmanned aerial vehicles (UAVs) and various sensors have become indispensable tools in plant phenotyping studies. In this study, a comprehensive resistance score (CRS) was proposed to effectively quantify weed resistance in the field. Multimodal data fusion and deep learning were utilized to perform regression of CRS, three different fusion methods for 3D-CNN and 2D-CNN to extract and fuse multimodal information collected by UAVs including spectral, structural, and texture information for weed resistance. Our findings demonstrate that (1) discernible differences in spectral response exist between susceptible and resistant weeds, with the optimal band for the Successive Projections Algorithm (SPA) selection coinciding with the optimal band for resistance expression band; (2) resistance assessment accuracy is enhanced through multimodal data fusion, with the late deep fusion network exhibiting the best accuracy, R2 of 0.777 and RMSE of 0.547; (3) the multimodal fusion network model displays robust adaptability in resistance assessment across varying densities and effectively generates weed resistance map. Overall, this research demonstrates the effectiveness of using multimodal data fusion and CRS, combined with deep learning for achieving accurate and reliable weed resistance assessment in agricultural fields.

Currently, mechanical and chemical damage is the main way to carry out weed control. The use of chlorophyll fluorescence (CF) technology to nondestructively monitor the stress physiological state of weeds is significant to reveal the damage mechanism of mechanical and chemical stresses as well as complex stresses. Under simulated real field environmental conditions, different species and leaf age weeds (Digitaria sanguinalis 2-5 leaf age, and Erigeron canadensis 5-10 leaf age) were subjected to experimental treatments for 1-7 days, and fluorescence parameters were measured every 24 h using a chlorophyll fluorometer. The aim of this study was to investigate the changes in CF parameters of different species of weeds (Digitaria sanguinalis, Erigeron canadensis) at their different stress sites under chemical, mechanical and their combined stresses. The results showed that when weeds (Digitaria sanguinalis and Erigeron canadensis) were chemically stressed in different parts, their leaf back parts were the most severely stressed after 7 days, with photosynthetic inhibition reaching R=75%. In contrast, mechanical stress differs from its changes, and after a period of its stress, each parameter recovers somewhat after 1 to 2 days of stress, with heavy mechanical stress R=11%. Complex stress had the most significant effect on CF parameters, mainly in the timing and efficiency of changes in Fv/Fm, Fq’/Fm’, ETR, Rfd, NPQ and Y(NO), with R reaching 71%-73% after only 3-4 days of complex stress, and its changes in complex stress were basically consistent with the pattern of changes in its chemical stress. The results of the study will help to understand the effects of mechanical and chemical stresses and combined stresses on CF parameters of weeds and serve as a guide for efficient weed control operations and conducting weed control in the future.

Atrazine is one of the most widely used herbicides in weed management. However, the widespread use of atrazine has concurrently accelerated the evolution of weed resistance mechanisms. Resistant weeds were identified early to contribute to crop protection in precision agriculture before visible symptoms of atrazine application to weeds in actual field environments. New developments in unmanned aerial vehicle (UAV) platforms and sensor technologies promote cost-effective data collection by collecting multi-modal data at very high spatial and spectral resolution. In this study, we obtained multispectral and RGB images using UAVs, increased available information with the help of image fusion technology, and developed a weed spectral resistance index, WSRI = (RE-R)/(RE-B), based on the difference between susceptible and resistant weed biotypes. A deep convolutional neural network (DCNN) was applied to evaluate the potential for identifying resistant weeds in the field. Comparing the WSRI introduced in this study with previously published vegetation indices (VIs) shows that the WSRI is better at classifying susceptible and resistant weed biotypes. Fusing multispectral and RGB images improved the resistance identification accuracy, and the DCNN achieved high field accuracies of 81.1% for barnyardgrass and 92.4% for velvetleaf. Time series and weed density influenced the study of weed resistance, with 4 days after application (4DAA) identified as a watershed timeframe in the study of weed resistance, while different weed densities resulted in changes in classification accuracy. Multispectral and deep learning proved to be effective phenotypic techniques that can thoroughly analyze weed resistance dynamic response and provide valuable methods for high-throughput phenotyping and accurate field management of resistant weeds.

The aberrant expression of Wnt3 has linked to several types of human malignancies. However, it is not known for its role in tumorigenesis of colorectal cancer (CRC). Herein, we show that Wnt3 is upregulated in human CRC tissues and is essential for the CRC progression. Knockdown of Wnt3 in human CRC cells delayed tumor formation in nude mouse xenografts through silencing of canonical Wnt pathway and glycolysis. We further found that silencing of Wnt3 enhanced the sensitivity of CRC cells to cisplatin through inducing apoptotic cell death. Taken together, it demonstrates that Wnt3 is a novel clinical biomarker for the detection of CRC and plays an important role in colorectal tumorigenesis. Therefore, downregulation of Wnt3 will be a valuable strategy in CRC treatment.

Multi-wavelength fiber lasers have emerged as a promising light source for the application in wavelength division multiplexing communication, terahertz wave generation and optical sensing due to high efficiency and robustness. Lyot-filter emerges as a potential device for multi-wavelength generation application. However, because of the high birefringence of polarization maintaining fiber in Lyot-filter, it is difficult to generate broadband dual-wavelength or multi-wavelength mode-locked fiber laser by using common Lyot-filter. In this paper, for the first time, we propose an idea of using the low birefringence induced by bending the single-mode fiber to form a Lyot-filter for dual-wavelength mode-locked fiber laser generation. The dual-wavelength output centers at 1532 and 1556 nm and it may simplify the set-up for dual-wavelength mode-locked laser.