Currently, the main remote sensing-based crop mapping methods are based on spectral-temporal features. However, there has been a lack research on the selection of the multi-temporal images, and most of the methods are based on the use of all the available images during the cycle of crop growth. In this study, in order to explore the optimal temporal window for crop mapping with limited remote sensing data, we tested all possible combinations of temporal windows in an exhaustive manner, and made a comprehensive consideration of the spatial accuracy and statistical accuracy as evaluation indices. We collected all the available cloud-free Sentinel-2 multi-spectral images for the winter wheat and rapeseed growth periods in the study area in southern China, and used the random forest (RF) method as the classifier to identify the optimal temporal window. The spatial and statistical accuracies of all the results were assessed by using ground survey data and local agricultural census data. The optimal temporal window for the mapping of winter wheat and rapeseed in the study area was obtained by identifying the best-performing set of results. In addition, the variable importance (VI) index was used to evaluate the importance of the different bands for crop mapping. The results of the spatial accuracy, statistical accuracy, and the VI showed that the combinations of images from the later stages of crop growth were more suitable for crop mapping.

In deep learning (DL)-based hyperspectral imagery classification, “spatial patching” is primarily used as a preprocessing for incorporating local spatial information. This operation can help to promote classification accuracy but it is facing new challenges in the unmanned aerial vehicle (UAV)-borne hyperspectral imagery with high spatial and spectral resolutions (H ² imagery). The ground objects’ various spatial scales result in it being challenging to determine the optimal size for the spatial patches. In addition, due to the severe spectral variability and spatial heterogeneity of the H ² imagery, “spatial patching” only exploits the local spatial information and results in serious salt-and-pepper (SP) noise and isolated areas in the classification maps. In this article, to address these issues, a novel spectral patching network (SPNet) with an end-to-end DL architecture is proposed for UAV-borne H ² imagery classification. The “spectral patching” approach is proposed to preserve the global spatial information and almost all the spectral information of the original hyperspectral imagery. An end-to-end deep encoder–decoder network is then constructed based on the spectral patching mechanism, which introduces the deep residual network (ResNet) and atrous spatial pyramid pooling (ASPP) modules to extract multiscale high-level semantic information for the H ² imagery classification. The experimental results obtained with the Wuhan UAV-borne H ² imagery (WHU-Hi) UAV-borne hyperspectral data set demonstrate that SPNet can achieve state-of-the-art accuracy and visualization performance in the classification of H ² imagery.

There is inconsistency between the existing remote sensing cropland products, whose accuracy of estimated cropland area and spatial positioning needs to be improved. The existing generalized methods of generating synergy cropland products for improving the accuracy of existing products do not consider the overall consistency difference between the different products in each grid cell in the fusion process. To reduce the impact of the abnormal estimated cropland areas of the individual cropland products on the results, this paper proposes a method of generating a synergy cropland product by fusing the multiple existing cropland products, based on the overall consistency difference. In the proposed method, the process of fusing the multiple existing cropland products is based on the overall consistency difference of the estimated cropland area of all the cropland products in each grid cell. The synergy cropland product is then generated after determining the best combination level with the cropland statistics. In this study, we set 2010 as the base year, and used the proposed method to conduct experiments with four remote sensing cropland products: GlobCover 2009, MODIS Cropland, MCD12Q1, and FROM-GLC within China, and national cropland statistics. The results show that the synergy cropland product generated by the proposed method has a higher accuracy of cropland area estimation and spatial positioning than the results obtained by the generalized model, as well as the original products.

Large scale crop mapping is an important task in agricultural resource monitoring. To obtain a distribution map of crops, traditional methods usually require the well-designed manufacture features and the ground-truth labels of all land-cover types for training a multi-class classifier. However, the redundant labeling for each land-cover type is time-consuming and labor-intensive, and the feature design for different remote sensing data is complex and limited to human prior knowledge. In this paper, a deep one-class crop extraction framework is proposed to solve the problems mentioned above. Specifically, it uses the deep one-class crop extraction module to extract the feature automatically for any remote sensing imagery and the one-class crop extraction loss to address the lack of negative class in the deep one-class classification model. In addition, the proposed framework can be applied to multi-modal remote sensing data, i.e. hyperspectral, multispectral, and SAR images, which is verified in the experiments and the proposed framework can achieve the highest accuracy on each multi-modal data.