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.

Weed competition causes serious economic losses to maize production. Timely and accurate assessment of pressure from competition is crucial for ecological weed management. In this work, we apply hyperspectral remote sensing (HRS) technology to conduct a competitive experiment in Harbin, China, in 2021, with 5-leaf maize as the study target. A weed competition assessment method that combines comprehensive competition indices (CCI) and deep learning is proposed. For the comprehensive competition assessment, the relationship between different weed competitive pressures (Levels 1-5) and changes in the structural and physiological information of maize was analyzed. The accumulative/transient competition indices CCI-A and CCI-T were designed for accurate quantification. The results showed that parameters such as plant height, stalk thickness and nutrient elements of maize decreased with increasing competition level. Parameters, such as stomatal conductance and transpiration rate, showed a fluctuating change of increasing and then decreasing with increasing competition level. Compared with the traditional relative competitive intensity (RCI), the standard deviation of CCI is 0.303 and 0.499. The dispersion effect of CCI is better and more suitable for quantifying the competition response. HRS images combined with 3D-CNN model were then applied to reveal the spectral response to different weed competition pressures (Levels 1-5) and to make early predictions of weed competition. The first-order derivative showed that the spectral reflectance exhibited significant differences at 520-525 nm peak, 570-655 nm trough, and near 700 nm red edge. For hyperspectral spatial-spectral features, the 3D-CNN model is proposed for prediction of competing indices CCI. In addition, the VIP method is used to select the characteristic wavelengths. The 3D-CNN model achieves a prediction accuracy of RMSE = 0.106 and 0.152 using 13 feature bands, which can accurately quantify the subtle changes in competition indices. Overall, this study shows that the combination of CCI and deep learning can provide a multivariate and comprehensive assessment of weed competition pressure.

Leaf age and plant centre are important phenotypic information of weeds, and accurate identification of them plays an important role in understanding the morphological structure of weeds, guiding precise targeted spraying and reducing the use of herbicides. In this work, a weed segmentation method based on BlendMask is proposed to obtain the phenotypic information of weeds under complex field conditions. This study collected images from different angles (front, side, and top views) of three kinds of weeds (Solanum nigrum, barnyard grass (Echinochloa crus-galli), and Abutilon theophrasti Medicus) in a maize field. Two datasets (with and without data enhancement) and two backbone networks (ResNet50 and ResNet101) were replaced to improve model performance. Finally, seven evaluation indicators are used to evaluate the segmentation results of the model under different angles. The results indicated that data enhancement and ResNet101 as the backbone network could enhance the model performance. The F₁ value of the plant centre is 0.9330, and the recognition accuracy of leaf age can reach 0.957. The mIOU value of the top view is 0.642. Therefore, deep learning methods can effectively identify weed leaf age and plant centre, which is of great significance for variable spraying.

Although weeds cause serious harm to crops through competition for resources, they also have ecological functions. We need to study the change law of competition between crops and weeds, and achieve scientific farmland weed management under the premise of protecting weed biodiversity. In the research, we perform a competitive experiment in Harbin, China, in 2021, with five periods of maize as the study subjects. Comprehensive competition indices (CCI-A) based on maize phenotypes were used to describe the dynamic processes and results of weeds competition. The relation between in structural and biochemical information of maize and weed competitive intensity (Levels 1-5) at different periods and the effects on yield parameters were analyzed. The results showed that the differences of maize plant height, stalk thickness, and N and P elements among different competition levels (Levels 1-5) changed significantly with increasing competition time. This directly resulted in 10%, 31%, 35% and 53% decrease in maize yield; and 3%, 7%, 9% and 15% decrease in hundred grain weight. Compared to the conventional competition indices, CCI-A had better dispersion in the last four periods and was more suitable for quantifying the time-series response of competition. Then, multi-source remote sensing technologies are applied to reveal the temporal response of spectral and lidar information to community competition. The first-order derivatives of the spectra indicate that the red edge (RE) of competition stressed plots biased in short-wave direction in each period. With increasing competition time, RE of Levels 1-5 shifted towards the long wave direction as a whole. The coefficients of variation of canopy height model (CHM) indicate that weed competition had a significant effect on CHM. Finally, the deep learning model with multimodal data (Mul-3DCNN) is created to achieve a large range of CCI-A predictions for different periods, and achieves a prediction accuracy of R² = 0.85 and RMSE = 0.095. Overall, this study use of CCI-A indices combined with multimodal temporal remote sensing imagery and DL to achieve large scale prediction of weed competitiveness in different periods of maize.