Inspired by the tremendous success of deep learning (DL) and the increased availability of remote sensing data, DL-based image semantic segmentation has attracted growing interest in the remote sensing community. The ideal scenario of DL application requires a vast number of annotation data with the same feature distribution as the area of interest. However, obtaining such enormous training sets that suit the data distribution of the target area is highly time-consuming and costly. Consistency-regularization-based semi-supervised learning (SSL) methods have gained growing popularity thanks to their ease of implementation and remarkable performance. However, there have been limited applications of SSL in remote sensing. This study comprehensively analyzed several advanced SSL methods based on consistency regularization from the perspective of data- and model-level perturbation. Then, an end-to-end SSL approach based on a hybrid perturbation paradigm was introduced to improve the DL model’s performance with a limited number of labels. The proposed method integrates the semantic boundary information to generate more meaningful mixing images when performing data-level perturbation. Additionally, by using implicit pseudo-supervision based on model-level perturbation, it eliminates the need to set extra threshold parameters in training. Furthermore, it can be flexibly paired with the DL model in an end-to-end manner, as opposed to the separated training stages used in the traditional pseudo-labeling. Experimental results for five remote sensing benchmark datasets in the application of segmentation of roads, buildings, and land cover demonstrated the effectiveness and robustness of the proposed approach. It is particularly encouraging that the ratio of accuracy obtained using the proposed method with 5% labels to that using the purely supervised method with 100% labels was more than 89% on all benchmark datasets.

Crop classification is indispensable for agricultural monitoring and food security, but early-season mapping has remained challenging. Synthetic aperture radar (SAR), such as RADARSAT Constellation Mission (RCM) and Sentinel-1, can meet higher requirements on the reliability of satellite data acquisition with all-weather and all-day imaging capability to supply dense observations in the early crop season. This study applied the local window attention transformer (LWAT) to time-series SAR data, including RCM and Sentinel-1, for early-season crop classification. The performance of this integration was evaluated over crop-dominated regions (corn, soybean and wheat) in southwest Ontario, Canada. Comparative analyses against several machine learning and deep learning methods revealed the superiority of the LWAT, achieving an impressive F1-score of 97.96% and a Kappa coefficient of 97.08% for the northern crop region and F1-scores of 98.07% and 97.02% for the southern crop region when leveraging time-series data from RCM and Sentinel-1, respectively. Additionally, by the incremental procedure, the evolution of accuracy determined by RCM and Sentinel-1 was analyzed, which demonstrated that RCM performed better at the beginning of the season and could achieve comparable accuracy to that achieved by utilizing both datasets. Moreover, the beginning of stem elongation of corn was identified as a crucial phenological stage to acquire acceptable crop maps in the early season. This study explores the potential of RCM to provide reliable prior information early enough to assist with in-season production forecasting and decision making.

Compared with a monoculture planting mode, the practice of crop rotations improves fertilizer efficiency and increases crop yield. Large-scale crop rotation monitoring relies on the results of crop classification using remote sensing technology. However, the limited crop classification accuracy cannot satisfy the accurate identification of crop rotation patterns. In this paper, a crop classification and rotation mapping scheme combining the random forest (RF) algorithm and new statistical features extracted from time-series ground range direction (GRD) Sentinel-1 images. First, the synthetic aperture radar (SAR) time-series stacks are established, including VH, VV, and VH/VV channels. Then, new statistical features named the objected generalized gamma distribution (OGΓD) features are introduced to compare with other object-based features for each polarization. The results showed that the OGΓD σ^VH achieved 96.66% of the overall accuracy (OA) and 95.34% of the Kappa, improving around 4% and 6% compared with the object-based backscatter in VH polarization, respectively. Finally, annual crop-type maps for five consecutive years (2017–2021) are generated using the OGΓD σ^VH and the RF. By analyzing the five-year crop sequences, the soybean-corn (corn-soybean) is the most representative rotation in the study region, and the soybean-corn-soybean-corn-soybean (together with corn-soybean-corn-soybean-corn) has the highest count with 100 occurrences (25.20% of the total area). This study offers new insights into crop rotation monitoring, giving the basic data for government food planning decision-making.

Leaf Area Index (LAI) serves as a key ecophysiological parameter for assessing plant growth and is particularly vital for crop monitoring. Using Unmanned Aerial Vehicle (UAV)-based point cloud data generated through photogrammetry techniques offers valuable structural insights into crops, facilitating LAI retrieval. This study introduces a method for estimating LAI from three-dimensional (3-D) point clouds. By employing spherical voxel partitioning, vegetation gap fraction is computed based on the spatial distribution of point clouds. Furthermore, leaf inclination angle is determined through triangular patch collections reconstructed from 3-D point clouds. Projection functions, accounting for varying zenith perspectives, are developed considering the leaf inclination angle. Subsequently, the combination of vegetation gap fraction and projection functions is used within the Beer Lambert law framework to calculate LAI. Validation against ground measurements demonstrates a strong correlation between measured and retrieved LAI (R ² = 0.64, RMSE = 0.43), affirming the effectiveness of the proposed method in estimating LAI using UAV-based structure from motion (SfM) point cloud data.

In the aftermath of a natural hazard, rapid and accurate building damage assessment from remote sensing imagery is crucial for disaster response and rescue operations. Although recent deep learning-based studies have made considerable improvements in assessing building damage, most state-of-the-art works focus on pixel-based, multi-stage approaches, which are more complicated and suffer from partial damage recognition issues at the building-instance level. In the meantime, it is usually time-consuming to acquire sufficient labeled samples for deep learning applications, making a conventional supervised learning pipeline with vast annotation data unsuitable in time-critical disaster cases. In this study, we present an end-to-end building damage assessment framework integrating multitask semantic segmentation with semi-supervised learning to tackle these issues. Specifically, a multitask-based Siamese network followed by object-based post-processing is first constructed to solve the semantic inconsistency problem by refining damage classification results with building extraction results. Moreover, to alleviate labeled data scarcity, a consistency regularization-based semi-supervised semantic segmentation scheme with iteratively perturbed dual mean teachers is specially designed, which can significantly reinforce the network perturbations to improve model performance while maintaining high training efficiency. Furthermore, a confidence weighting strategy is embedded into the semi-supervised pipeline to focus on convincing samples and reduce the influence of noisy pseudo-labels. The comprehensive experiments on three benchmark datasets suggest that the proposed method is competitive and effective in building damage assessment under the circumstance of insufficient labels, which offers a potential artificial intelligence-based solution to respond to the urgent need for timeliness and accuracy in disaster events.

The soil freeze/thaw (F/T) cycles play an important role in the climate system and human activities. However, the harsh environment in the Qinghai-Tibet Plateau (QTP) poses great challenges for both in-situ observation and remote-sensing monitoring of the soil F/T process. In this article, the time series of scattering and coherence of the high-resolution Sentinel-1 C- band synthetic aperture radar (SAR) is analyzed to identify the soil F/T state. The time series of scattering, including intensity and decomposition parameters, and coherence, are analyzed based on three typical landcover types (i.e., desert, grassland, and meadow) in the QTP. They are given the mathematical description by second-order and fourth-order Fourier functions, respectively. Based on Fourier functions, the initial F/T time points of the soil are detected in each pixel to draw the F/T map of the entire study area. The experiment results are cross-validated with the initial F/T time points of the soil calculated from the MODIS land surface temperatures, showing that the differences in days are less than one revisit cycle of Sentinel-1 (i.e., 12 days). Furthermore, the possible impacts of environmental factors acquired from the Wudaoliang meteorological station, including air temperature, ground surface temperature, snow depth, and precipitation, on scattering and coherence are discussed. This study explores that Sentinel-1 has great potential for soil F/T monitoring in the QTP, which can indicate F/T states of the surface soil as well as F/T information of the deeper soil with a high spatial–temporal resolution.