BACKGROUND: The timely, rapid, and accurate near real-time observations are urgent to monitor the damage of corn armyworm, because the rapid expansion of armyworm would lead to severe yield losses. Therefore, the potential of machine learning algorithms for identifying the armyworm infected areas automatically and accurately by multispectral unmanned aerial vehicle (UAV) dataset is explored in this study. The study area is in Beicuizhuang Village, Langfang City, Hebei Province, which is the main corn-producing area in the North China Plain.RESULTS: Firstly, we identified the optimal combination of image features by Gini-importance and the comparation of four kinds of machine learning methods including Random Forest (RF), Multilayer Perceptron (MLP), Naive Bayesian (NB) and Support Vector Machine (SVM) was done. And RF was proved to be the most potential with the highest Kappa and OA of 0.9709 and 0.9850, respectively. Secondly, the armyworm infected areas and healthy corn areas were predicted by an optimized RF model in the UAV dataset, and the armyworm incidence levels were classified subsequently. Thirdly, the relationship between the spectral characteristics of different bands and pest incidence levels within the Sentinel-2 and UAV images were analyzed, and the B3 in UAV images and the B6 in Sentinel-2 image were less sensitive for armyworm incidence levels. Therefore, the Sentinel-2 image was used to monitor armyworm in two towns. CONCLUSIONS:The optimized dataset and RF model are effective and reliable, which can be used for identifying the corn damage by armyworm using UAV images accurately and automatically in field-scale.

Black soil is one of the most productive soils with high organic matter content. Crop residue covering is important for protecting black soil from alleviating soil erosion and increasing soil organic carbon. Mapping crop residue covered areas accurately using remote sensing images can monitor the protection of black soil in regional areas. Considering the inhomogeneity and randomness, resulting from human management difference, the high spatial resolution Chinese GF-1 B/D image and developed MSCU-net+C deep learning method are used to mapping corn residue covered area (CRCA) in this study. The developed MSCU-net+C is joined by a multiscale convolution group (MSCG), the global loss function, and Convolutional Block Attention Module (CBAM) based on U-net and the full connected conditional random field (FCCRF). The effectiveness of the proposed MSCU-net+C is validated by the ablation experiment and comparison experiment for mapping CRCA in Lishu County, Jilin Province, China. The accuracy assessment results show that the developed MSCU-net+C improve the CRCA classification accuracy from IOUAVG = 0.8604 and KappaAVG = 0.8864 to IOUAVG = 0.9081 and KappaAVG = 0.9258 compared with U-net. Our developed and other deep semantic segmentation networks (MU-net, GU-net, MSCU-net, SegNet, and Dlv3+) improve the classification accuracy of IOUAVG/KappaAVG with 0.0091/0.0058, 0.0133/0.0091, 0.044/0.0345, 0.0104/0.0069, and 0.0107/0.0072 compared with U-net, respectively. The classification accuracies of IOUAVG/KappaAVG of traditional machine learning methods, including support vector machine (SVM) and neural network (NN), are 0.576/0.5526 and 0.6417/0.6482, respectively. These results reveal that the developed MSCU-net+C can be used to map CRCA for monitoring black soil protection.

Urban forms are closely related to the urban environment, providing great potential to analyze human socioeconomic activities. However, limited studies have investigated the impacts of three-dimensional (3-D) urban forms on socioeconomic activities across cities. In this paper, we explored the relationship between urban form and socioeconomic activities using 3-D building height data from 38 cities in China. First, we aggregated the building footprint data and calculated three building indicators at the grid scale, based on which the spatial patterns of building height and road density were analyzed. Then, we examined the capacities of two-dimensional (2D)/3D urban forms in characterizing socioeconomic activities using satellite-derived nighttime light (NTL) data. Finally, we analyzed the relationship between road density distributions and building heights across 38 cities in China. Our results suggest that the building height information can improve the correlation between urban form and NTL. Different patterns of road distribution were revealed according to the distribution of road density change from the building hotspots, showing the capacity of 3-D building height data in helping characterize socioeconomic activities. Our study indicates that the 3-D building height information is of great potential to support a variety of studies in urban domains, such as population distribution and carbon emissions, with significantly improved capacities.

Background: Monitoring armyworm (Mythimna separata Walker) damage in crops requires timely, rapid and accurate observations to avoid severe yield losses. Results: The Random Forest (RF) classifier was more effective at automatically and accurately monitoring armyworm damage compared with Support Vector Machine (SVM), Multilayer Perceptron Classifier (MLPC) and Naive Bayes Classifier (NB) classifiers. Furthermore, the incorporation of an Unmanned Aerial Vehicle (UAV) image-generated digital surface model improved the performance of the RF classifier, increasing the F-score from 0.985 and 0.970 to 0.997 and 0.994, and increasing the Kappa coefficient from 0.955 to 0.990. In addition, we found that Band 3 (735 nm) of the UAV image and Band 6 (740 nm) of a coincident Sentinel-2 image were not sensitive to an armyworm infestation in this study. Conclusions: We developed an accurate algorithm for the automated identification of armyworm-damaged corn plants using UAV images at the field scale. The study also indicated the feasibility of the developed method for monitoring corn armyworm damage at regional scale when combined with Sentinel-2 images.