In change detection, the pseudovariations in the visual features of remote sensing (RS) images are attributed to imaging conditions, lighting, seasonal changes, atmospheric interference, and other factors. These pseudovariations yield a great challenge to change detection. The traditional change detection network usually suffers from upsampling information loss and blurred edges. Aiming at resolving the above problems, a semantic flow and edge-aware refinement network (SFEARNet) for highly efficient RS image change detection has been proposed. The pyramid feature enhancement module (PFEM) has been designed for the enhancement of differential information. The introduction of the semantic flow information transmission module (SFITM) enables the effective transmission and retaining of key information through semantic flow. An edge-aware refinement module (EARM) has been developed, designed to extract change edge and enhance the refinement effect of the edge. The experiments have been conducted on the LEVIR building change detection dataset (LEVIR-CD), WHU building dataset (WHU-CD), Google dataset (GZ-CD), and cropland change detection dataset (CLCD). In comparison with the existing methodologies, the experimental results demonstrate that SFEARNet attains the highest change detection accuracy and the smallest floating-point operations per second (FLOPs) while maintaining a similar number of parameters (Params). This enables more efficient change detection. In particular, the proposed method can effectively refine the edges of the change region, reduce the loss of upsampling information, and enhance differential feature extraction. This brings a new solution to the field of RS image change detection. The code is available athttps://github.com/miao-0417/SFEARNet.

Currently in Landslide Susceptibility Mapping (LSM), data-driven models mostly utilize association to present the connection between landslide and Conditioning Factor (CF). However, association cannot reflect the structural interaction or the underlying causal mechanism. This leads to black-box results and reduces interpretability. To address this problem, this study introduces an unsupervised causal model to LSM. The methodology consists of two parts: causal discovery with Non-combinatoric Optimization via Trace Exponential Augmented Lagrangian Structure learning (NOTEARS) algorithm, and causal inference with Bayesian Networks (BN). By applying structural causality to LSM, we “white-boxed” the procession of data-driven model, thereby ensuring the interpretability and data utility. To comprehensively evaluate the results, comparison experiments with other machine learning models were performed. The results showed that BN achieved the highest accuracy (approximately 0.877) and the second highest AUC (0.907). Moreover, BN outperformed other models in ground-truth validation. The high and extremely high susceptibility zones in BN-LSM result covered the most actual landslides (more than 71.07% of the total, and more than 80% after excluding areas not used in model training). This showed the generalizability and stability of structural causality-guided-BN. The proposed methodology provides a link between data-driven causal science and natural hazard analysis, which can help intelligent hazard managements. Data and codes that support the findings of this study are openly available at doi.org/10.6084/m9.figshare.26395420.

Image segmentation represents a fundamental step in analyzing very high-spatial-resolution (VHR) remote sensing imagery. Its objective is to partition an image into segments that best match with geo-objects. However, the diverse appearances of geospatial objects often lead to interobject homogeneity and intraobject heterogeneity. Existing segmentation methods often struggle to accurately segment geo-objects with varying shapes and scales. To address these challenges, we propose DeepMerge, a novel method that integrates deep learning and region adjacency graphs (RAGs) to accurately segment complete geo-objects in large VHR images. DeepMerge begins with an initial over-segmentation of the image and then iteratively merges similar regions to achieve complete geo-object segmentation. A deep learning model is employed to learn the similarity between adjacent superpixel pairs. This approach only requires labels indicating whether adjacent superpixels belong to the same geo-object eliminating the need for object-level annotations, enabling weakly supervised segmentation. A cross-scale module is incorporated to capture multiscale information, enhancing the representation of superpixels. In addition, the feature distances between neighboring super-pixels are deemed as scale parameters (thresholds) to control the merging procedure, thus yielding an interpretable, predictable, stable, and optimal scale parameter 0.5. DeepMerge can achieve high segmentation accuracy in a weakly supervised manner, which is validated on large-scale remote sensing images of 0.55-m resolution covering an area of 5660 km2. The experimental results demonstrate that DeepMerge achieves the highest F value (0.9552) and the lowest total error (TE) (0.0827), accurately segmenting geo-objects of varying sizes and outperforming all competing methods.

The advent of remote sensing and deep learning has rendered the automated detection of postearthquake building damage a necessity for effective disaster response. However, the inherent unpredictability of earthquakes and the limited revisit frequency of satellites frequently result in inadequate postdisaster data for effective model training. Furthermore, conventional data augmentation techniques have the potential to lead to model overfitting, thereby further complicating the development of robust detection systems. To address the challenge, this article introduces an innovative end-to-end data augmentation approach that combines a multichannel fusion Wasserstein generative adversarial network (MCFWGAN) with a Mask-CutMix sample augmentation technique. This approach first introduces a multichannel fusion (MCF) mechanism into the WGAN framework, constructing the MCFWGAN model, which enhances global feature extraction capabilities while strengthening the interdependencies among image channels. After generating images, the Mask-CutMix method integrates these generated images into large-scale remote sensing imagery, thereby augmenting the dataset. The integrated image dataset contains a small amount of pre-earthquake and postearthquake data. Finally, a target detection network is employed to extract damaged buildings from the images. Two study areas were selected to implement data augmentation and target detection. Experimental results demonstrate that the proposed data augmentation method outperforms traditional techniques in terms of accuracy metrics for target detection. Furthermore, to address the issues of missed and false detections of intact buildings within severely damaged areas, the use of style transfer-based sample augmentation was shown to effectively improve accuracy metrics. The experimental results demonstrate that the proposed data enhancement method outperforms the traditional technique with respect to the target detection evaluation metric. In Study Area 1, the detection accuracy is enhanced by 5.08% in comparison to the conventional data enhancement method. In Study Area 2, the mean accuracy is elevated by 3.32%. The data augmentation method proposed in this study not only increases the number of samples but also enhances the diversity of samples representing damaged buildings. The MCFWGAN model is particularly well-suited for generating images of damaged buildings in complex postearthquake scenarios, offering significant potential for the accurate acquisition of postdisaster information and emergency rescue operations.

Rainfall is the primary landslide triggering factor in China, and the spatial-temporal hazard prediction of rainfall-induced landslides is of great practical significance. Currently, most countries and regions establish landslide hazard prediction systems based on rainfall data only, resulting in low spatial precision of hazard prediction results and a high false alarm rate. This paper proposes a hazard prediction model that considers landslide triggering factors, landslide predisposing environment, and the spatial regularity of historical landslides based on multi-modal earth observation data. The proposed model has significantly improved the spatial-temporal hazard prediction performance of rainfall-induced natural terrain landslides in Hong Kong.

Object-based convolutional neural networks (OCNNs) have achieved great performance in the field of land-cover and land-use classification. Studies have suggested that the generation of object convolutional positions (OCPs) largely determines the performance of OCNNs. Optimized distribution of OCPs facilitates the identification of segmented objects with irregular shapes. In this study, we propose a morphology-based binary tree sampling (BTS) method that provides a reasonable, effective, and robust strategy to generate evenly distributed OCPs. The proposed BTS algorithm consists of three major steps: 1) calculating the required number of OCPs for each object, 2) dividing a vector object into smaller sub-objects, and 3) generating OCPs based on the sub-objects. Taking the object identification in land-cover and land-use classification as a case study, we compare the proposed BTS algorithm with other competing methods. The results suggest that the BTS algorithm outperforms all other competing methods, as it yields more evenly distributed OCPs that contribute to better representation of objects, thus leading to higher object identification accuracy. Further experiments suggest that the efficiency of BTS can be improved when multi-thread technology is implemented.

The spatial arrangement of land-cover features constitutes different urban functional zone. With the same attributes of the urban functional zone, the land-cover features that make up the functional zone will have similar spatial distribution characteristics. Considering the importance of understanding spatial relationships between land-cover features, the up-bottom hierarchical decomposition and semantic understanding of functional zone are achieved. First, for object convolution neural network (OCNN)-based land cover classification, an equal-area dividing algorithm is proposed to automatically generate convolution kernel position. Second, to extract spatial relationship features of urban land covers, a novel distance weight-graph attention model (DW-GAM) is originally proposed for classifying urban functional zones by comparing the feature similarity of the land cover relationship graph. Third, considering the extreme difficulties in expressing the urban structure characteristic on a single scale, a recursive model that uses an urban road network of different levels to divide multiscale functional zones is built. Finally, taking the analysis of urban function allocation as the application objective, this article establishes a primary framework of the spatial pattern evaluation index. Experimental results conducted on a Google Earth image of Xi’an city show that the multiscale recursive model can accurately recognize urban functional zones by using the originally proposed DW-GAM. Then, based on the outcome of urban functional zone identification, the case study of urban function allocation analysis is innovatively conducted on the fine scale to give some suggestions on future urban planning, which is, hence, of great significance for urban function pattern analysis and urban planning.

Object-based image analysis (OBIA) provides a better solution for information extraction from high spatial resolution remote sensing image. Currently, selection of scale parameters is often dependent on subjective trial-and-error methods or post-evaluation of multi-segmentation, which directly reduces efficiency of land cover classification. This paper proposes a OBIA classification method combining spatial statistics based adaptive scale parameter pre-estimation and Mean-shift segmentation. Series of object based classification were employed to verify the validity of this method. Experimental results show that the pre-estimated scale parameter can guarantee a classification result with both high classification accuracy and good completeness for land cover classification. This presented method avoids the time-consuming trial-and-error practice so that it speeds up the object-oriented classification procedure.

Image segmentation is a key procedure that partitions an image into homogeneous parcels in object-based image analysis (OBIA). Scale selection in image segmentation is always difficult for high-performance OBIA. This letter is aimed at scale selection before segmentation in OBIA and proposes a spatial statistics-based spatial bandwidth selection method based on mean-shift segmentation. This study uses Ikonos and Quickbird panchromatic images as the experimental data and then computes their semivariances to select the optimal spatial bandwidth for mean-shift segmentation. To validate this method and interpret the relationship between the semivariances and segmentation scale, this letter implements an image segmentation evaluation based on the homogeneity within and the heterogeneity between the segmentation parcels. The evaluation results basically support the proposed scale selection method based on the semivariogram. Consequently, the semivariogram-based spatial bandwidth selection method is practically meaningful for pre-estimating the appropriate scale and thus contributes to improving the performance and efficiency of OBIA.

This paper analyses the advantages of remote sensing image processing per-parcel compared to per-pixel; Based on huaman's visual mechanism and theory of scale spatial, this paper designs the technique flow of multi-scale information extraction from high resolution remote sensing images based on features: rough classification - parcel unit extraction expression of feature - ntelligent illation - information extraction or target recognition. Especially, this paper expatiates the work flow of block and linear parcel unit extraction in detail and gives tests with IKONOS and QUICKBIRD images. The test shows that the methods of this paper is convenient to integrating visual and environmental knowledge and can improve the level of automatization and intelligentization of remote sensing data process and application.

With the development of Remote Sensing and digital image processing technology, it become's very important and imminent for remotely sensed images to be processed in the distributed environment. This paper aims at the implementation of remotely sensed image distributed processing, firstly analyzes the current implementation method and technique of remotely sensed image distributed processing, then points out the problems it faces. After analyzing the characteristics of web service technology, this paper draws the conclusion that web service technology can be applied to remotely sensed image distributed processing field because it can solve these problems, such as large amount of data processing and network computing and so on. This paper firstly gives the framework design of remotely sensed image distributed processing based on web service, then takes remotely sensed image distributed edge detection and segmentation as the example, according to the need of our image distributed processing task, this paper gives the interfaces and classes definition. then talks about their implementation method. At last we give in example and its image processing effect of our distributed system, and the result shows the feasibility of the remotely sensed image distributed processing implementation with die technology of web service.