Change detection (CD) is the process of identifying changes in the category or attributes of ground objects by observing remote sensing images (RSI) taken at different times. In recent years, transformers have shown great potential in CD. However, current transformer-based CD networks have not fully exploited the capabilities of the transformer, especially when fusing features from bi-temporal and multi-stages. In this work, a pure transformer-based CD network (TFN) is built to fuse features better. Specifically, we build a Siamese CD network based on the transformer. Bi-temporal features are fused through a Shifted Window Fusion Model (SWFM) to address the misalignment between the features. In the decoding phase, a Multi-Scale Transformer Decoder (MSTD) is introduced to generate more complete change masks. The proposed method is validated on the WHU and SECOND datasets, demonstrating state-of-the-art performance (SOTA).

To overcome the effect of speckle noise on SAR image change detection, a superpixel segmentation algorithm based on speckle reducing anisotropic diffusion model is proposed and applied for object-oriented SAR image change detection. Based on the traditional modeling methods of the non-similarity between pixels and seed points by combining spectral distance and spatial distance in superpixel segmentation, the concept of diffusion flux is proposed to simulate the continuous and bounded evolution of the membership of pixels and seed points in the image plane lattice. Considering the effect of speckle noise and the demand of segmenting different shape surface features in complex scenes, the speckle reducing anisotropic diffusion is used to model the diffusion flux. After superpixel segmentation of dual-temporal remote sensing images, an overlay technology is adopted to obtain the finer results. Finally, the change detection result is generated based on the superpixelized difference image by the classical fuzzy clustering algorithm FCM. The experiments carried out on Sentinel-1 SAR images by comparing algorithms fully demonstrate the effectiveness of the proposed algorithm.

This study proposed a new application paradigm of time series SAR data for sugarcane mapping. First, the LOESS smoothing technique was exploited to reconstruct time series SAR data and reduce SAR noise in the time domain. Second, temporal importance was evaluated using RF MDA ranking, and basic parcel units were obtained only based on multitemporal SAR images with high importance values. At last, the parcel-based classification method, combining time series smoothing SAR data, RF classifier, and basic parcel units, was used to generate a sugarcane extent map without unreasonable sugarcane spots. The proposed paradigm was applied to map sugarcane cultivation in Suixi County, China. Results showed that the proposed paradigm was able to produce an accurate classification map with an overall accuracy of 96.09% and a Kappa coefficient of 0.91. Compared with the pixel-based classification result with original time series SAR data, the new paradigm performed much better in reducing the "salt and pepper" spots and improving the completeness of the sugarcane plots. Especially, the unreasonable non-vegetation spots in the sugarcane map were completely eliminated. The results demonstrated the efficacy of the new paradigm for mapping sugarcane cultivation.

Cloud detection is a crucial step in the analysis and processing of optical remote sensing satellite imagery. Existing methods often have large parameter sizes, high computational complexity, and experience a rapid drop in model accuracy when transferred to different sensors. We propose a cloud detection method based on Efficient Transformer and Neural Style Transfer, a lightweight cloud detection network that can be used across different sensors without requiring additional labeled data. Our contribution focus on two main aspects: 1.We design a lightweight cloud detection model that reduces redundant parameters without compromising model accuracy; 2.We introduce a Neural Style Transfer module for cross-sensor cloud detection, aiming to align cloud features from different sensors with training images. Experiments on the 38-Cloud dataset demonstrate that our proposed method achieves state-of-the-art performance while maintaining a small parameter size and floating-point computation. In cross-sensor cloud detection experiments, the inclusion of the Neural Style Transfer module significantly enhances the model’s capability for cross-sensor cloud detection.

This study investigates the potential of using satellite-retrieved biophysical variables to address the scarcity of agricultural management data when modeling crop productivity across heterogeneous fields with a terrestrial biosphere model (TBM). A two-season field trial was conducted in Spain, providing various combinations of nitrogen (N) fertilization and irrigation levels. The crop responses to these management levels were found to be well represented by the Leaf Area Index (LAI) retrieved from the Sentinel-2 data. The satellite-retrieved LAI was then incorporated into a terrestrial biosphere model to estimate crop biomass. This satellite-derived model produced accurate biomass estimates with an overall R2of 0.52 and RMSE of 269.7 g m-2(42.6%), with no prior knowledge of management practices nor local calibration. This study confirms the capability of satellite remote sensing to capture crop responses to management practices and highlights its potential to optimize resource use efficiency in agricultural systems.

A feature set that can fully reflect information regarding the cumulative dryness state (CDS) of forest fuels is crucial in forest fire risk modeling. Due to the uneven spatial and temporal distribution of rainfall, the CDS information often exhibits significant spatial heterogeneity. Current feature extraction methods for environmental factors based on fixed time windows struggle to capture this spatial heterogeneous information accurately. This paper proposes an adaptive time window-based method for extracting forest environmental factors features. By using precipitation as a constraint, this method adaptively constructs dynamic time windows for each pixel, thereby obtaining finer CDS information. The random forest (RF) and support vector machine (SVM) algorithms were used to construct the fire risk models, and both showed improvements in overall accuracy, indicating the effectiveness of the proposed method. The improvement performance of the RF model was better than that of the SVM model, and the overall accuracy can be improved by 5% to 8% under appropriate precipitation constraint settings.

In this paper, we propose a novel Synthetic Minority Oversampling Technique based Rotation forest (SMOTERoF) algorithm for the classification of imbalanced hyperspectral image data. The main idea of the proposed method is to iteratively balance the class distribution of training set by SMOTE for each rotation decision tree. Experiment results on the hyperspectral image Indian Pines AVRIS with different imbalance ratio (IR) show that our algorithm obtains better classification performance compared with Rotation Forest (RoF), random undersampling, random oversampling, SMOTE, as well as Under sampling based RoF (UnderRoF) which is an extended version of UnderBagging.