Synthetic aperture radar (SAR) can be used to obtain remote sensing images of different growth stages of crops under all weather conditions. Such time-series SAR images can provide an abundance of temporal and spatial features for use in large-scale crop mapping and analysis. In this study, we propose a temporal feature-based segmentation (TFBS) model for accurate crop mapping using time-series SAR images. This model first extracts deep-seated temporal features and then learns the spatial context of the extracted temporal features for crop mapping. The results indicate that the TFBS model significantly outperforms traditional long short-term memory (LSTM), U-network, and convolutional LSTM models in crop mapping based on time-series SAR images. TFBS demonstrates better generalizability than other models in the study area, which makes it more transferable, and the results show that data augmentation can significantly improve this generalizability. The visualization of the temporal features extracted by the TFBS shows that there is a high degree of intraclass homogeneity among rice fields and interclass heterogeneity between rice fields and other features. TFBS also achieved the highest accuracy of the four deep learning models for multicrop classification in the study area. This study presents a feasible way of producing high-accuracy large-scale crop maps based on the proposed model.

Timely, accurate, and repeatable crop mapping is vital for food security. Rice is one of the important food crops. Efficient and timely rice mapping would provide critical support for rice yield and production prediction as well as food security. The development of remote sensing (RS) satellite monitoring technology provides an opportunity for agricultural modernization applications and has become an important method to extract rice. This paper evaluated how a semantic segmentation model U-net that used time series Landsat images and Cropland Data Layer (CDL) performed when applied to extractions of paddy rice in Arkansas. Classifiers were trained based on time series images from 2017–2019, then were transferred to corresponding images in 2020 to obtain resultant maps. The extraction outputs were compared to those produced by Random Forest (RF). The results showed that U-net outperformed RF in most scenarios. The best scenario was when the time resolution of the data composite was fourteen day. The band combination including red band, near-infrared band, and Swir-1 band showed notably better performance than the six widely used bands for extracting rice. This study found a relatively high overall accuracy of 0.92 for extracting rice with training samples including five years from 2015 to 2019. Finally, we generated dynamic maps of rice in 2020. Rice could be identified in the heading stage (two months before maturing) with an overall accuracy of 0.86 on July 23. Accuracy gradually increased with the date of the mapping date. On September 17, overall accuracy was 0.92. There was a significant linear relationship (slope = 0.9, r² = 0.75) between the mapped areas on July 23 and those from the statistical reports. Dynamic mapping is not only essential to assist farms and governments for growth monitoring and production assessment in the growing season, but also to support mitigation and disaster response strategies in the different growth stages of rice.

A deep semantic segmentation model-based method can achieve state-of-the-art accuracy and high computational efficiency in large-scale crop mapping. However, the model cannot be widely used in actual large-scale crop mapping applications, mainly because the annotation of ground truth data for deep semantic segmentation model training is time-consuming. At the operational level, it is extremely difficult to obtain a large amount of ground reference data by photointerpretation for the model training. Consequently, in order to solve this problem, this study introduces a workflow that aims to extract rice distribution information in training sample shortage regions, using a deep semantic segmentation model (i.e., U-Net) trained on pseudo-labels. Based on the time series Sentinel-1 images, Cropland Data Layer (CDL) and U-Net model, the optimal multi-temporal datasets for rice mapping were summarized, using the global search method. Then, based on the optimal multi-temporal datasets, the proposed workflow (a combination of K-Means and random forest) was directly used to extract the rice-distribution information of Jiangsu (i.e., the K–RF pseudo-labels). For comparison, the optimal well-trained U-Net model acquired from Arkansas (i.e., the transfer model) was also transferred to Jiangsu to extract local rice-distribution information (i.e., the TF pseudo-labels). Finally, the pseudo-labels with high confidences generated from the two methods were further used to retrain the U-Net models, which were suitable for rice mapping in Jiangsu. For different rice planting pattern regions of Jiangsu, the final results showed that, compared with the U-Net model trained on the TF pseudo-labels, the rice area extraction errors of pseudo-labels could be further reduced by using the U-Net model trained on the K–RF pseudo-labels. In addition, compared with the existing rule-based rice mapping methods, he U-Net model trained on the K–RF pseudo-labels could robustly extract the spatial distribution information of rice. Generally, this study could provide new options for applying a deep semantic segmentation model to training sample shortage regions.

Crop-type identification is one of the most significant applications of agricultural remote sensing, and it is important for yield estimation prediction and field management. At present, crop identification using datasets from unmanned aerial vehicle (UAV) and satellite platforms have achieved state-of-the-art performances. However, accurate monitoring of small plants, such as the coffee flower, cannot be achieved using datasets from these platforms. With the development of time-lapse image acquisition technology based on ground-based remote sensing, a large number of small-scale plantation datasets with high spatial-temporal resolution are being generated, which can provide great opportunities for small target monitoring of a specific region. The main contribution of this paper is to combine the binarization algorithm based on OTSU and the convolutional neural network (CNN) model to improve coffee flower identification accuracy using the time-lapse images (i.e., digital images). A certain number of positive and negative samples are selected from the original digital images for the network model training. Then, the pretrained network model is initialized using the VGGNet and trained using the constructed training datasets. Based on the well-trained CNN model, the coffee flower is initially extracted, and its boundary information can be further optimized by using the extracted coffee flower result of the binarization algorithm. Based on the digital images with different depression angles and illumination conditions, the performance of the proposed method is investigated by comparison of the performances of support vector machine (SVM) and CNN model. Hence, the experimental results show that the proposed method has the ability to improve coffee flower classification accuracy. The results of the image with a 52.5 angle of depression under soft lighting conditions are the highest, and the corresponding Dice (F1) and intersection over union (IoU) have reached 0.80 and 0.67, respectively.

Severe meteorological drought is generally considered to lead to crop damage and loss. In this study, we created a new standard value by averaging the values distributed in the middle 30–70% instead of the traditional mean value, and we proposed a new index calculation method named Normalized Indices (NI) for meteorological drought monitoring after normalized processing. The TRMM-derived precipitation data, GLDAS-derived soil moisture data, and MODIS-derived vegetation condition data from 2003 to 2019 were used, and we compared the NI with commonly used Condition Indices (CI) and Anomalies Percentage (AP). Taking the mid-to-lower reaches of the Yangtze River (MLRYR) as an example, the drought monitoring results for paddy rice and winter wheat showed that (1) NI can monitor well the relative changes in real precipitation/soil moisture/vegetation conditions in both arid and humid regions, while meteorological drought was overestimated with CI and AP, and (2) due to the monitoring results of NI, the well-known drought event that occurred in the MLRYR from August to October 2019 had a much less severe impact on vegetation than expected. In contrast, precipitation deficiency induced an increase in sunshine and adequate heat resources, which improved crop growth in 78.8% of the area. This study discusses some restrictions of CI and AP and suggests that the new NI index calculation provides better meteorological drought monitoring in the MLRYR, thus offering a new approach for future drought monitoring studies.

Agricultural remote sensing community is increasingly focusing on enhancing crop mapping accuracy by improving data-driven machine learning model structures, yet ignoring impact of sampling–model structure combination on it, which may prevent full utilization of input data, especially for Synthetic Aperture Radar images with fewer crop prior features. Consequently, this study took rice as target crop, and systematically performed rice mapping experiments based on Sentinel-1 images to assess mapping accuracies, model learning results and model uncertainty under different sampling–model structures combinations. The sampling methods included pixel sampling in buffer or non-buffer mode with equal proportion and equal quantity (pixel sample), as well as panoramic information sampling (image sample). The included model structures mainly focused on the models commonly used in rice mapping (i.e., Random Forest and Unet as traditional pixel and image data driven machine learning models), and related advanced model structures (i.e., popular Transformer and Unet's variant, TransUnet, served as advanced model structures compared to the corresponding model structures commonly used in rice mapping). The experimental results showed that, when image sample was annotated well, both Unet and TransUnet were more suitable for rice mapping based on Sentinel-1 images, their overall accuracies could reach 95% as sample size increased. Otherwise, when pixel sample size exceeded 100,000-level, non-buffer equal proportion sampling–advanced Transformer combination could be the currently optimal selection over the combination of this sampling method and Random Forest, its overall accuracy could reach 91% as sample size increased. Besides, it was worth noting that for data-driven machine learning models commonly used in rice mapping, key factors for pixel data-driven ones to improve mapping accuracy was model structure upgrade, while for image data-driven ones, richness of image samples was more important.