Fine classification of vegetation types has always been the focus and difficulty in the application field of remote sensing. Unmanned Aerial Vehicle (UAV) sensors and platforms have become important data sources in various application fields due to their high spatial resolution and flexibility. Especially, UAV hyperspectral images can play a significant role in the fine classification of vegetation types. However, it is not clear how the ultrahigh resolution UAV hyperspectral images react in the fine classification of vegetation types in highly fragmented planting areas, and how the spatial resolution variation of UAV images will affect the classification accuracy. Based on UAV hyperspectral images obtained from a commercial hyperspectral imaging sensor (S185) onboard a UAV platform, this paper examines the impact of spatial resolution on the classification of vegetation types in highly fragmented planting areas in southern China by aggregating 0.025 m hyperspectral image to relatively coarse spatial resolutions (0.05, 0.1, 0.25, 0.5, 1, 2.5 m). The object-based image analysis (OBIA) method was used and the effects of several segmentation scale parameters and different number of features were discussed. Finally, the classification accuracies from 84.3% to 91.3% were obtained successfully for multi-scale images. The results show that with the decrease of spatial resolution, the classification accuracies show a stable and slight fluctuation and then gradually decrease since the 0.5 m spatial resolution. The best classification accuracy does not occur in the original image, but at an intermediate level of resolution. The study also proves that the appropriate feature parameters vary at different scales. With the decrease of spatial resolution, the importance of vegetation index features has increased, and that of textural features shows an opposite trend; the appropriate segmentation scale has gradually decreased, and the appropriate number of features is 30 to 40. Therefore, it is of vital importance to select appropriate feature parameters for images in different scales so as to ensure the accuracy of classification.

Change detection in remote sensing (RS) images typically involves processing and analyzing RS images of the same geographic location captured at different times to identify changes. In recent years, deep learning has seen increased application in the field of RS, particularly in the context of change detection in RS images. Compared to conventional approaches, deep learning-based methods can automatically identify subtle changes in high-resolution RS images with greater accuracy and efficiency. This article provides an overview of deep learning-based change detection research from a variety of perspectives, including data samples, algorithms, computational power, and commercially driven developments. First, this paper compiles datasets for RS change detection, including SAR, multispectral, hyperspectral, and multimodal images. Second, it introduces the process and framework of deep learning-based change detection, along with mainstream deep learning networks employed for image feature extraction. In addition, change detection is described in terms of different detection granularity sizes and different detection methods. Furthermore, this article provides the first analysis of deep learning-based RS change detection from the perspective of computational power and commercially driven developments. This article also discusses the current major challenges and future directions in the field of deep learning change detection. Deep learning-based methods need to overcome the problem of undesirable samples, integrate multimodal RS images, focus on the extraction of multiple change information, and advance the development of foundation models for change detection.

The use of remote sensing images for land cover classification is an important and challenging pixel-level classification task. However, the different distribution of the same land cover categories across different datasets, the accuracy of the classification is significantly reduced when a classification model trained on one dataset is used directly on another dataset. To address the issue, numerous unsupervised domain adaptation (UDA) methods have been proposed. However, the existing UDA methods focus mainly on natural images and are not suited to remote sensing images with large variations in spectral information and texture features. Therefore, we develop a new full-level domain adaptation network (FLDA-NET) applicable for cross-domain land cover classification of remote sensing images. It aligns the source domain and target domain through a two-stage process encompassing image-level, feature-level and output-level. In stage I, we align at image-level by converting the source domain image to the target domain image style. In stage II, at the feature-level we align the entropy of the two domain features. At the output-level we do not use simple global alignment, but category-level alignment. Furthermore, a self-training strategy (SPST) based on superpixel segmentation and softmax probability is proposed to further enhance the model's performance on the target domain. Extensive experiments on our proposed FLDA-NET are performed on the Potsdam and Vaihingen datasets and compared to other advanced UDA methods. The outcome demonstrates that this approach greatly improves improve the ability of cross-domain land cover classification in remote sensing images.

High-quality ground observation networks are an important basis for scientific research. Here, an automatic soil observation network for high-resolution satellite applications in China (SONTE-China) was established to measure both pixel- and multilayer-based soil moisture and temperature. SONTE-China is distributed across 17 field observation stations with a variety of ecosystems, covering both dry and wet zones. In this paper, the average root mean squared error (RMSE) of station-based soil moisture for well-characterized SONTE-China sites is 0.027 m³/m³ (0.014~0.057 m³/m³) following calibration for specific soil properties. The temporal and spatial characteristics of the observed soil moisture and temperature in SONTE-China conform to the geographical location, seasonality and rainfall of each station. The time series Sentinel-1 C-band radar signal and soil moisture show strong correlations, and the RMSE of the estimated soil moisture from radar data was lower than 0.05 m³/m³ for the Guyuan and Minqin stations. SONTE-China is a soil moisture retrieval algorithm that can validate soil moisture products and provide basic data for weather forecasting, flood forecasting, agricultural drought monitoring and water resource management.

Remote sensing technology has the potential to enhance the lake’s large-scale and long-term dynamic monitoring capabilities significantly. High-quality in-situ datasets are essential for improving the accuracy and reliability of remote sensing retrieval of lake ecosystems. This dataset provides satellite-ground synchronized in-situ data on water multi-parameters for typical lakes in China spanning the period between 2020 and 2023. It includes quality-checked water optical parameters (remote sensing reflectance (Rrs), chlorophyll-a (Chl-a), total suspended matter (TSM) and Secchi disk depth (SDD)), and water surface temperature (WST) data. It encompasses 586 sampling points across 18 lakes. The dataset exhibits two significant highlights: Firstly, synchronous observations from multiple satellites are coordinated during the data collection effectively supporting the retrieval and validation of water remote sensing products. Secondly, it encompasses diverse data types, collecting synchronous measurements of Rrs and various parameters. This dataset will continuously update, substantially enhancing regional and global lake monitoring capabilities through satellite remote sensing data.

The scope of this research lies in the combination of pre-trained Convolutional Neural Networks (CNNs) and Quantum Convolutional Neural Networks (QCNN) in application to Remote Sensing Image Scene Classification(RSISC). Deep learning (RL) is improving by leaps and bounds pretrained CNNs in Remote Sensing Image (RSI) analysis, and pre-trained CNNs have shown remarkable performance in remote sensing image scene classification (RSISC). Nonetheless, CNNs training require massive, annotated data as samples. When labeled samples are not sufficient, the most common solution is using pre-trained CNNs with a great deal of natural image datasets (e.g., ImageNet). However, these pre-trained CNNs require a large quantity of labelled data for training, which is often not feasible in RSISC, especially when the target RSIs have different imaging mechanisms from RGB natural images. In this paper, we proposed an improved hybrid classical–quantum transfer learning CNNs composed of classical and quantum elements to classify open-source RSI dataset. The classical part of the model is made up of a ResNet network which extracts useful features from RSI datasets. To further refine the network performance, a tensor quantum circuit is subsequently employed by tuning parameters on near-term quantum processors. We tested our models on the open-source RSI dataset. In our comparative study, we have concluded that the hybrid classical–quantum transferring CNN has achieved better performance than other pre-trained CNNs based RSISC methods with small training samples. Moreover, it has been proven that the proposed algorithm improves the classification accuracy while greatly decreasing the amount of model parameters and the sum of training data.