Search

Accurately monitoring the assembly sequence of mechanical parts is significant for reducing assembly process errors and improving assembly accuracy. To monitor the newly assembled parts of mechanical assemblies from multiple views, this paper proposes a multi-view change detection network based on feature fusion and feature refinement with depthwise separable convolution (DWFR Net) for mechanical assembly images. Based on the BIT (Bitemporal Image Transformer) network, the DWFR Net adds a feature fusion structure to the convolutional neural network module to reduce the loss of shallow features due to the increase in network depth. Then, a feature refinement module is designed to refine the features extracted by the convolutional neural network and make the Q of the Transformer decoder more accurate. The depthwise separable convolution with a convolution kernel of 5 × 5 is used in the feature fusion structure and feature refinement module. It reduces the number of parameters added by the large convolution kernel while increasing the receptive field. Finally, the DWFR Net is evaluated on a mechanical assembly image change detection dataset and a public dataset LEVIR-CD. The experimental results show that the F1 of the DWFR Net can reach 95.60% on the mechanical assembly image change detection dataset and 90.12% on the LEVIR-CD dataset, and the latter is 0.81% higher than that of the BIT network. [ABSTRACT FROM AUTHOR]

Growing intracranial aneurysms pose a high risk of rupture, making the detection and quantification of the growth crucial for timely treatment strategy adoption. In this paper we propose a computer-assisted approach based on the extraction of IA shapes from associated baseline and follow-up angiographic scans and non-rigid morphing of the two shapes. From the obtained shape deformations we computed four novel features, including differential volume (dV), surface area (dSA), aneurysm-size normalized median deformation path length (dMPL), and integral of cumulative deformation distances (dICDD). An experienced neuroradiologist manually extracted the IA shape models from the baseline and follow-up MRAs and, by utilizing size change and visual assessments, classified each aneurysm into stable with morphology changes, stable or growing. We investigated the classification performance and found that three of the novel and one cross-sectional feature exhibited significantly different mean values (p-value < 0.05 ; Tukey's HSD test) between the stable and growing IA groups, while the mean dICDD was significantly different between all the three groups. The cross-sectional features has sensitivity to growing IAs in range 0.05–0.86, while novel features had generally higher sensitivity in range 0.81–0.90, making them promising candidates as surrogate follow-up imaging-based biomarkers for IA growth detection. These findings may offer valuable information for clinical management of patients with IAs based on follow-up imaging. [ABSTRACT FROM AUTHOR]

The large-scale removal of trees from forests to make way for human activities is known as deforestation, given that it may result in soil erosion, natural habitat deterioration, biodiversity loss, and water cycle disturbance, this is a major environmental problem. As a source of food, clean water, oxygen, and medicines as well as an essential component of the hydrological cycle—they supply water to the atmosphere through transpiration—forests are a contributing factor to climate change and global warming. In addition to decreasing soil fertility and rainfall, deforestation increases the likelihood of floods and droughts and has a major effect on global warming. Deforestation monitoring is an important input for forest management that helps to prepare an action plan, but monitoring is still a challenging task. Hence, there is a need for an accurate deforestation mechanism to monitor those areas that have been converted from forest to non-forest areas. Therefore, in this paper a deep learning-based forest monitoring approach has been proposed, which is implemented in two steps: (i) a machine learning-based classification technique has been applied to the Sentinel-2 images to classify the forest and non-forest areas, and (ii) a deep learning-based change detection technique is proposed to detect the changes occurred during 2017–2022 of the Kukrail forest range situated in India. The performance of the proposed algorithm is assessed by estimating the error measuring parameters like Precision, Recall, and F1 Score, and it is observed that the proposed approach is quite suitable for forest area change monitoring. [ABSTRACT FROM AUTHOR]

The aim of the paper is to introduce appropriate tools for quantifying the changes occurred at edge level when analyzing land cover changes. The research is conducted in two directions. Firstly, the binary change index at edge level is introduced and its relationship to the already existing binary change edge (computed at pixel level) is studied. It is proved that a certain inequality between the values of the two indices holds. The theoretical part is completed with real-world examples. The second direction investigated in the paper is the possibility of applying Markov type models, a basic tool in land cover change analysis, in quantifying the changes occurred at edge level. This combined approach is illustrated by a case study and it is shown that it provides complementary information related to the spatial extension of the land cover types and to their distribution. Thus, this type of analysis can improve the methodology of measuring the extent and the implications of land cover changes. [ABSTRACT FROM AUTHOR]

Deforestation is a major concern for preserving the biodiversity of the entire globe. During the last few years, machine learning and deep learning methods have been employed for mapping deforestation. There is still scope for ample improvement in these methods as they are prone to errors and can give inaccurate results because of over or under-segmentation. This paper uses deep convolutional neural network-based semantic segmentation to process multispectral satellite images to monitor forest cover changes in Tadoba-Andhari National Park during the period 2000–2022. The proposed approach uses the U-Net architecture with extended inputs which gives more accuracy as compared to U-Net with only image input. Landsat images along with vegetation indices have been used as training data. The proposed method requires less time to train the model and is also cost-efficient in terms of computing requirements. The performance of the proposed method was compared with state-of-the-art methods where the proposed method outperformed the other models with an F1-score of 0.90 and an accuracy of 84.83%. When compared with U-Net trained with Landsat images only, it was observed that the U-Net model trained with extended input was able to achieve better results. [ABSTRACT FROM AUTHOR]

The problem of change detection in remote sensing image processing is both difficult and important. It is extensively used in a variety of sectors, including land resource planning, monitoring and forecasting of agricultural plant health, and monitoring and assessment of natural disasters. Remote sensing images provide a large amount of long-term and fully covered data for earth environmental monitoring. A lot of progress has been made thanks to deep learning's quick development. But the majority of deep learning-based change detection techniques currently in use rely on the well-known Convolutional neural network (CNN). However, considering the locality of convolutional operation, CNN unable to master the interplay between global and distant semantic information. Some researches has employ Vision Transformer as a backbone in remote sensing field. Inspired by these researches, in this paper, we propose a network named Siam-Swin-Unet, which is a Siamesed pure Transformer with U-shape construction for remote sensing image change detection. Swin Transformer is a hierarchical vision transformer with shifted windows that can extract global feature. To learn local and global semantic feature information, the dual-time image are fed into Siam-Swin-Unet which is composed of Swin Transformer, Unet Siamesenet and two feature fusion module. Considered the Unet and Siamesenet are effective for change detection, We applied it to the model. The feature fusion module is designed for fusion of dual-time image features, and is efficient and low-compute confirmed by our experiments. Our network achieved 94.67 F1 on the CDD dataset (season varying). [ABSTRACT FROM AUTHOR]

Large scale datasets created from crowdsourced labels or openly available data have become crucial to provide training data for large scale learning algorithms. While these datasets are easier to acquire, the data are frequently noisy and unreliable, which is motivating research on weakly supervised learning techniques. In this paper we propose original ideas that help us to leverage such datasets in the context of change detection. First, we propose the guided anisotropic diffusion (GAD) algorithm, which improves semantic segmentation results using the input images as guides to perform edge preserving filtering. We then show its potential in two weakly-supervised learning strategies tailored for change detection. The first strategy is an iterative learning method that combines model optimisation and data cleansing using GAD to extract the useful information from a large scale change detection dataset generated from open vector data. The second one incorporates GAD within a novel spatial attention layer that increases the accuracy of weakly supervised networks trained to perform pixel-level predictions from image-level labels. Improvements with respect to state-of-the-art are demonstrated on 4 different public datasets. [ABSTRACT FROM AUTHOR]

The high-intensity exploitation of mineral resources in mining cities in China has created new environmental challenges and serious environmental situations in recent years. The land use patterns in mining areas change rapidly for natural and anthropogenic reasons. Land-use/land-cover (LU/LC) change is extremely important in the sustainable development of mining cities. Large-scale opencast coal mining results in the destruction of built-up land, industrial land and mining land as well as arable land resources. Therefore, the analysis of changes in mineral resources and arable land use has attracted increasing attention. With the development of remote sensing (RS) and deep learning (DL) technology, many forms of data for detecting land-use changes are available. The goal of this paper is to promote coordinated land-use development. In this study, an ensemble feature pyramid convolutional neural network model (EFPCNNM) approach, which combines the theory of convolutional neural network (CNN), feature pyramid (FP) and ensemble learning (EL), was used to analyze land-use change in the Longmen Mountain opencast coal mine area in Anqing City, Huaining County, Anhui Province, China. Unlike the CNN, and ensemble convolutional neural network model (ECNNM), which only used the high-level features to predict the ground objects, and the feature information of other layers was not fully considered, EFPCNNM enhanced the small target information in high-level features and improved the detection performance of significant ground object. EFPCNNM was highly portable and could be embedded in many models to further boost performance. Comparative experiments on support vector machine (SVM), extreme learning machine (ELM), artificial neural network (ANN), CNN and ECNNM methods demonstrated that the EFPCNNM could exceed the other models in terms of detection accuracy and inference speed, e.g., the overall accuracy was 93.5036%, kappa coefficient was 0.9423, and time was 2.7569 s. Multitemporal RS images from eight periods starting in 2005 and ending in 2019 were used as the land-use data. With a typical classification system and RS quantitative analysis, this paper also evaluated the temporal and spatial changes in arable land use in the mining area. Of all the land-use types, the area of arable land decreased the most over the study period, and the area of mining land and construction land increased the most. In addition, changes in the seepage area associated with collapse sites in the study area were analyzed. The results of this change detection process could provide decision support for the coordinated development of land use and mineral resources in mining areas. [ABSTRACT FROM AUTHOR]

In fast-developing regions like Southeast Asia monitoring urban areas presents a challenge given the lack of publicly available data. This is an issue that precludes the nuances of a city's growth and undermines the way land use is considered with respect to planning. The issue of data availability is very much present in the small nation of Brunei. Little is still known about the spatiotemporal evolution of its urban realm in particular, with regard to its national development planning. The country presents an interesting case-study given the pursuit of two highly opposing master-plans within the last 40 years. Its first master plan advocated polycentric growth away from the capital city, Bandar Seri Begawan. Its latest plan, however, currently promotes compact growth within a predefined urban footprint as a development control mechanism. This paper looks at remotely-sensed satellite data to examine the way in which the two implemented master-plan strategies have translated into actual land-use thus far. It employs a supervised classification procedure and characterises urban land into three typologies: urban infill, edge growth, and leapfrog growth. The paper's findings suggest that residential developments play a stronger role in driving urban growth in Brunei. This is particularly true for public housing, which has typically persisted in isolated pockets of low density at the city fringe. This study has produced a novel dataset of urban land use and land cover in Brunei; and, its quantification may prove useful in understanding the impacts of master planning and the formulation of development policies both within Brunei, and the wider Southeast Asian region. [ABSTRACT FROM AUTHOR]

Recognizing dynamic variations on the ground, especially changes caused by various natural disasters, is critical for assessing the severity of the damage and directing the disaster response. However, current workflows for disaster assessment usually require human analysts to observe and identify damaged buildings, which is labor-intensive and unsuitable for large-scale disaster areas. In this paper, we propose a difference-aware attention network (D2ANet) for simultaneous building localization and multi-level change detection from the dual-temporal satellite imagery. Considering the differences in different channels in the features of pre- and post-disaster images, we develop a dual-temporal aggregation module using paired features to excite change-sensitive channels of the features and learn the global change pattern. Since the nature of building damage caused by disasters is diverse in complex environments, we design a difference-attention module to exploit local correlations among the multi-level changes, which improves the ability to identify damage on different scales. Extensive experiments on the large-scale building damage assessment dataset xBD demonstrate that our approach provides new state-of-the-art results. Source code is publicly available at https://github.com/mj129/D2ANet. [ABSTRACT FROM AUTHOR]

This study aims to detect changes that occurred in Ravi River channel over the period of last three decades (1990 to 2020). This paper spatially and temporally assesses the changes and geo-visualize variation of Ravi River using Landsat imageries. The maximum likelihood image classification technique has been used to process and analyze the spatial data in geographic information system (GIS) environment. It was found from the results that vegetation cover has gradually decreased from 976 km2 in 1990 to 905 km2 in 2019, whereas the built-up land had increased from 82 to 188 km2 in the same temporal extent. Generally, the channel is shifted from east to west and the growth of built-up land to towards river which has pushed the channel. Similarly, the extreme discharge also causes change in channel shifting. Minor floods have been occurred after 2010 but Ravi is not affected much as their discharge was not that much higher to put any abrupt or significant effect on Ravi River's channel pattern. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) image change detection technology is of great significance. In the existing convolutional wavelet neural networks (CWNN) based SAR image change detection methods, the precision of preclassification is not high. The precision of preclassification will affect the performance of the network, and thus affect the accuracy of image change detection. In order to further improve the accuracy of change detection, the method based on Gabor wavelets and convolutional wavelet neural networks (GWCWNN) is applied to SAR image change detection in this paper. This method combines Gabor wavelets and fuzzy C-means clustering algorithm to provide high precision training samples for the networks, so as to improve the accuracy of image change detection. The results on three real data sets respectively show that the proposed method is better than the existing four methods. [ABSTRACT FROM AUTHOR]

With the application of numerous services or software, process mining has attracted more and more attention. However, concept drift may occur during process mining due to the instability of the process. Sudden and gradual drifts are considered to be two basic modes of change, that may always appear in independent or nested forms. Although the existing methods have studied the detection of two basic modes, they do not consider the nesting of two change modes. We identify the change mode that sudden drifts and gradual drifts do not appear independently as nested drifts. The current drift detection methods can only detect the drift modes that occur independently, but not suitable for nested drift detection. To fill this gap, this paper proposes a business concept drift detection and localization framework called BRDDL (Behavior Replacement-based Drift Detection and Localization) which can not only detect independent drifts such as sudden drifts and gradual drifts, but also detect nested drifts. Firstly, we propose an integrated drift point detection and localization method which can report the location of change points and return the changed behaviors (activity relationship pairs). On this basis, we propose a behavior replacement method by updating the changed traces to restore an unchanged sub log. Then we compare the behaviors in the updated traces with those in the associated unchanged traces to judge the type of drifts. The effectiveness of the method is verified by simulation experiments on the synthetic log. [ABSTRACT FROM AUTHOR]

Landslide event inventories are one of the most critical datasets to increase knowledge on landslide occurrences. However, they are rarely available in various regions, especially in countries of the Global South. This study aims to generate rainfall-induced landslide event inventories and define the rainfall thresholds responsible for landslide occurrence at the national scale of Malawi, Africa. We mainly followed a three-step methodology to generate landslide inventories. First, we went through media reports to identify documented landslide events. Second, we used Sentinel-2 images to identify possible areas affected by landslides using automated change detection algorithms based on vegetation indices. Third, we manually went through optical images provided by Planet Lab and Google Earth and mapped landslides via visual image interpretation. Overall, we mapped 27 rainfall-induced landslide inventories between 2003 and 2022, with a total of 4709 individual landslides. We then analysed the Malawian terrain and identified two different landscape clusters (i.e. Cluster 1 and Cluster 2) showing similar morphometric and climatic conditions. Ultimately, we calculated the rainfall threshold for each landscape cluster. The minimum rainfall amounts responsible for landsliding correspond to 66 mm/two-day and 51 mm/day in Clusters 1 and 2, respectively. In this context, our paper not only presents and shares the first national-scale, digital rainfall-induced landslide event inventory database of Malawi but also suitable rainfall thresholds to be potentially exploited for a national scale landslide early warning system. A similar framework could be applied to generate landslide inventories for other data scarce regions. [ABSTRACT FROM AUTHOR]

Change detection (CD) is rapidly becoming a fundamental approach due to its vast applications in image or video analysis. Siamese convolutional networks (SCN) have recently been used to detect changes. However, these approaches are unable to eliminate drawbacks such as coarse borders and empty holes because of the lack of spatial and other necessary information. So, the main goal of this paper is to develop a network that captures necessary features and has a better feature fusion technique for detecting changes. This is achieved by the proposed Siamese Capsule Multi-level Attention-based CD Network (SCMACDnet). Initially, the Siamese Capsule Encoder–Decoder Network (SCEDnet) is introduced to extract spatial features effectively using capsule attention block (CAB). Afterward, Change Atrous Feature Fusion (CAFF) is introduced to hierarchically combine them by exploring the fusion of channel pairs at several feature levels. Also, multi-scale data from the feature map (FM) is captured with a quicker inference speed using Stride Atrous Convolutional Pooling (SACP) in CAFF. Finally, an effective Reverse Dual Attention (RDA) module is introduced to highlight the changed areas by considering both the channel and pixel-wise correlation (PC) to preserve the shape and edges of the changed areas. Experiments conducted on the CDnet 2014 dataset demonstrate that the SCMACDnet method outperforms other existing methods in terms of precision (.963), sensitivity (.960), the F1 measure (.95), and the Percentage of Wrong Classification (.212). Further, the ablation study validates the efficiency of the proposed SCEDnet, CAFF, and RDA. The results show that the proposed SCMACDnet successfully identifies changes with accurate boundaries and shapes. [ABSTRACT FROM AUTHOR]

In order to improve the accuracy of change detection, a novel synthetic aperture radar (SAR) image change detection method based on Gamma correction and fuzzy local information c-means clustering (FLICM) model is proposed in this paper. Firstly, the original SAR images are filtered by speckle reducing anisotropic diffusion filter; secondly, the difference image (DI) is obtained by log-ratio operator; thirdly, the DI is processed by the Gamma correction operation; finally, the FLICM model is used to get the change detection result. Experimental results on four groups of SAR images demonstrate that the proposed algorithm has a good performance than many competitive approaches in terms of SAR image change detection. [ABSTRACT FROM AUTHOR]

A novel and effective change detection method based on manifold regularized joint non-negative matrix factorization (MJNMF) framework is proposed in this paper, which detects the changes that occurred in multi-temporal remote sensing images. Most change detection methods, including dictionary learning, principal component analysis (PCA), etc., do not consider the non-negativity among image pixels. However, image itself is a non-negative signal, and the non-negative constraint has better interpretability in practical applications. Nonnegative Matrix Factorization, which incorporates the non-negativity constraint and thus learns object parts, obtains the parts-based representation as well as enhancing the interpretability of the issue correspondingly. In this paper, our proposed approach based on MJNMF framework aims to establish a pair of joint basis matrices by unchanged training samples from unchanged area. Then, unchanged pixels can be well reconstructed by the corresponding basis matrix, while changed pixels cannot be reconstructed from the basis matrix corresponding to the knowledge of unchanged samples, or a larger reconstruction error can be generated even if changed pixels are reconfigurable. In order to suppress similar information and highlight different information, the cross-reconstruction error is used to generate the difference image. Finally, the binary image is obtained by the robust fuzzy local information c-means (FLICM) clustering algorithm. In addition, inspired by manifold learning, we incorporate manifold regularization into the proposed method to keep the geometric structure of data and improve the accuracy of change detection. Experimental results obtained on simulated and real remote sensing images confirm the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Urban areas are subject to multiple and very different changes, in a two- and three-dimensional sense, mostly as a consequence of human activities, such as urbanization, but also because of catastrophic and sudden events, such as earthquakes, landslides, or floods. This paper aims at designing a procedure able to cope with both types of changes by combining interferometric coherence and backscatter amplitude, and provide a semantically meaningful analysis of the changes detected in both city inner cores and suburban areas. Specifically, this paper focuses on detecting multi-dimensional changes in urban areas using a stack of repeat-pass SAR data sets from Sentinel-1A/B satellites. The proposed procedure jointly exploits amplitude and coherence time series to perform this task. SAR amplitude is used to extract changes about the urban extents, i.e. in 2D, while interferometric coherence is sensitive to the presence of buildings and to their size, i. e. to 3D changes. The proposed algorithm is tested using a time-series of two years of Sentinel-1 data, from May 2016 to October 2018, and in two different Chinese cities, Changsha and Hangzhou, with the aim to understand both the temporal evolution of the urban extents, and the changes within what is constantly classified as "urban" throughout the considered time period. [ABSTRACT FROM AUTHOR]

Since their advent, deep learning (DL) techniques have made great achievement in synthetic aperture radar (SAR) image change detection problem. Yet, their efficiency and accuracy with a presence of speckle noise and limited labeled training data are always full of challenges. To overcome these issues, this paper advocates an innovative approach by exploiting the advantage of the capsule network that can achieve a similar performance with less training samples thanks to its ability to make full use of the relative spatial relationships between features. The proposed multidimensional parallel capsule network (Mdp-CapsNet) includes an attention module to mitigate interference of speckle noise. By focusing more on prominent parts of the feature maps, the attention module guides the network to improve feature extraction. Moreover, a margin-focal loss function is suggested to overcome the influence of imbalanced samples during network optimization. The effectiveness and reliability of the proposed method are demonstrated by comparing its results with other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Remote sensing images change detection (RSICD) is a task to identify desired significant differences between multi-temporal images acquired at different times. From the existing methods, most of them solved this issue with a Siamese network, focusing on how to utilize the comparison between two image features to generate an initial difference map. However, Siamese network-based methods have three drawbacks: (1) complex architecture; (2) rough change map; (3) cumbersome detecting procedure: including feature extraction and feature comparison. To overcome the above drawbacks, we devoted our work to design a general framework which has a simple architecture, integrated detecting procedure, and good capacity of detecting subtle changes. In this paper, we proposed a channel self-attention network based on the generative adversarial network for change detection of remote sensing images. The network used an encoder–decoder network to directly produce a change map from two input images. It was better to detect small punctate and slim linear changes than Siamese-based networks. By regarding RSICD as an image translation problem, we used a Generative Adversarial Network to detect changes. In addition, a channel self-attention module was proposed to further improve the performance of this network. Experimental results on three public remote sensing RGB-image datasets, including change detection dataset, Wuhan University building change detection dataset and LEVIR building Change Detection dataset demonstrated that our method outperformed other state-of-the-art methods. In terms of the F1 score, the proposed method achieved maximum improvements of 5.1%, 3.1%, and 1.7% on the above datasets, respectively. Models and codes will be available at https://github.com/wangle53/CSA-CDGAN. [ABSTRACT FROM AUTHOR]

Change detection is a fundamental problem in remote sensing image processing. Due to the great advantages in learning the knowledge representations and the complex relationship from large-scale datasets, deep learning has made great progress in change detection tasks in remote sensing community. However, most of the existing methods based on deep learning for change detection are implemented by learning differences of image pairs directly without paying considerations in influences of unstructured and temporal changes, or called nature changes, such as light and seasonal changes. In this paper, an end-to-end deep learning network for remote sensing image change detection is proposed, aiming to accurately detect the change of regions from a high-resolution image pair by learning prototype similarity, in which the metric learning is used and it is one of the meta-learning methods to learn change prototypes from support image pairs. The similarity between the query image pairs and the change prototypes can be measured by a learnable CNN metric. The experimental results based on the two public change detection datasets of high-resolution satellite images, CDD and BCDD, show that our proposed method performs better than other state-of-the-art change detection methods with an improvement of 3.5% and 0.4%, respectively. [ABSTRACT FROM AUTHOR]

Remote sensing image change detection is an important technology in remote sensing data analysis. Existing mainstream solutions are divided into supervised and unsupervised solutions. Among supervised methods, most remote sensing image change methods based on deep learning are related to semantic segmentation. However, these methods only use deep learning model to extract and process single-level information of the image, and do not separately train the changed and unchanged areas according to the task characteristics of change detection. Also this model do not aggregate the deep and shallow-level feature information, so many local change details cannot be detected. This paper proposes a multilateral feature-guided aggregation network. The network firstly extracts the whole information, the changed area information and the unchanged area information of remote sensing image through the main network and two auxiliary networks: difference network and assimilation network. Then, the whole information of the image is aggregated with the changed and unchanged region information by feature aggregation network (all subnetworks are composed of convolutional neural networks (CNNs)). The proposed method is end-to-end trainable, and each component in the network does not need to be trained separately. [ABSTRACT FROM AUTHOR]

Various applications in remote sensing demand automatic detection of changes in optical satellite images of the same scene acquired over time. This paper investigates how to leverage autoencoders in change vector analysis, in order to better delineate possible changes in a couple of co-registered, optical satellite images. Let us consider both a primary image and a secondary image acquired over time in the same scene. First an autoencoder artificial neural network is trained on the primary image. Then the reconstruction of both images is restored via the trained autoencoder so that the spectral angle distance can be computed pixelwise on the reconstructed data vectors. Finally, a threshold algorithm is used to automatically separate the foreground changed pixels from the unchanged background. The assessment of the proposed method is performed in three couples of benchmark hyperspectral images using different criteria, such as overall accuracy, missed alarms and false alarms. In addition, the method supplies promising results in the analysis of a couple of multispectral images of the burned area in the Majella National Park (Italy). [ABSTRACT FROM AUTHOR]

Clustering of Remote Sensing (RS) images is one of the most accurate methods for land cover Change Detection (CD). Despite its popularity for unsupervised CD, the necessity to determine the number of clusters is the main shortcoming of Fuzzy C-Means(FCM) for CD. Clustering the absolute difference image to pre-defined two clusters (includes change versus no-change), which is called binary FCM, is a conventional strategy to mitigate the cluster number problem. This strategy suffers from low CD accuracy because of its inability to detect multiple changes in RS images. In this paper, a novel framework for unsupervised CD is proposed, which is called Multiple FCM (MFCM). In this method, the optimal cluster number of MFCM is determined by analyzing the cluster-validity indices when clustering the difference image. After clustering the difference image, binarizing of the clustered image produces the Binary Change Map (BCM). The performance of the proposed approach along with two state-of-the-art binary CD methods (BFCM and PCA-Kmeans) were evaluated on two different datasets with 5 and 2 real cluster numbers. The implementation results show that the proposed approach not only detects multiple land cover changes but also improves the binary change detection accuracy. Utilizing the proposed MFCM, the total errors of BCM reduced by 20% and 24% as compared to BFCM and PCA- Kmeans methods in the first dataset with multiple land cover changes. In the second dataset, which has only two real clusters no significant difference was observed between the results of the proposed method and reference approaches. [ABSTRACT FROM AUTHOR]

Terrestrial lidar scanning (TLS) has become a widely accepted expert tool for monitoring geohazards on bare or sparsely vegetated slopes through change detection. While trees can be an important indicator of landslide activity at a slope, vegetation is often removed or ignored when monitoring landslides with TLS. This paper explores the use of multi-temporal terrestrial lidar scanning at a slope in the Peace River valley of British Columbia to test the author's hypothesis that tree stems in TLS data can be used to track landslide displacement and provide insight into the landslide mechanism. Six TLS datasets, each collected approximately 6 months apart, are used, and roto-translation methods are employed to determine the azimuth, plunge, and toppling angle of trees between each TLS scan. The tree displacement patterns are compared to TLS change detection results on bare-ground, and to single-point tracking techniques for extracting displacement vectors. Considerations for future applications are discussed. [ABSTRACT FROM AUTHOR]

Background: Protected areas (PA) are central to biodiversity, but their efficiency is challenged by human-induced habitat loss and fragmentation. In the Fennoscandian boreal region, forestry with clearcutting is a threat to biodiversity causing the loss of mature forest elements and deterioration of ecological processes in forest landscapes, ultimately affecting PAs via declined structural connectivity. This paper aims to (1) determine PAs with high, red-listed species concentrations; (2) estimate the change in forest habitat around these PAs on different spatial scales; and (3) determine if forest management intensity is higher around biologically most valuable PAs. Occurrences of red-listed forest-dwelling species in Finland were used to identify PAs harbouring these species and to produce site-specific importance indices. CORINE landcover data was used as a baseline for the distribution of forests to assess the cover of clear-cuttings from 2001 to 2019 with the Global Forest Change (GFC) data set in three buffer areas around the PAs with occurrences of red-listed species. Results: The largest proportion of clear-cuts occurred in 1 km and 10 km buffers around the PAs in the southern and middle boreal zones, being ca. 20%. This indicates that the forest habitat is degrading fast at regional and landscape levels. On the positive side, the change in forest cover was lower around the biologically most important PAs compared to other PAs with red-listed species. Conclusions: Open and free satellite-data based assessments of the cover and change of forests provide reliable estimates about the rates at which mature and old-growth forests are being converted into young managed ones in Finland mainly via clear-cuts on different scales around PAs. The rate of clear-cuts was lowest in adjacent buffer areas next to the most species-rich PAs, which provides opportunities for biodiversity conservation efforts to be targeted to the remaining mature and old-growth forests found in the vicinity of these areas. [ABSTRACT FROM AUTHOR]

In evaluating the change detection algorithms, the algorithm evaluated must show a superior performance than the state-of-the-art algorithms. The evaluation process steps comprise executing a new algorithm to segment a set of videos from a dataset and compare the results regarding a ground truth. In this paper, we propose using additional information in evaluating change detection algorithms: the level of difficulty in classifying a pixel. First, for each video frame used in the evaluation, we created a difficulty map structure, which stores values representing the level of difficulty required by an algorithm to classify each pixel of that frame. Second, we developed a metric to estimate each dataset video's difficulty based on our difficulty maps. Third, we applied the metric to selecting the more representative videos from the dataset based on their difficulty level. Finally, to demonstrate the method's contribution, we evaluated it using all videos from the CDNet 2014 dataset. The results showed that a subset of videos selected by our method has the same potential as the original CDNet 2014 dataset. Hence, a new change detection algorithm can be evaluated more quickly using our subset of videos selected. [ABSTRACT FROM AUTHOR]

The remote sensed images carry large amount of crucial information. Image processing, a field of signal processing, helps in analysis of remote sensed data. One of the major processing areas is image segmentation with edge detection, which helps in segmenting an image into various sub regions. These regions identified from images, captured over long span of time can help in identification of change detection. This paper presents an application of nature-inspired algorithms viz.: Ant Colony Algorithm, Particle Swarm Optimization and Genetic Algorithm to optimize edge detection procedure. These methods have been implemented on a set of 15 satellite images and further enhancement is done by application of adaptive thresholding using Python. For qualitative analysis, entropy of each output image is computed. The comparison of computer results revealed that particle swarm optimization outperforms conventional methods, i.e., Sobel, Canny and Prewitt as well as ACO and GA. The PSO-based method is able to find more edges and presents far superior quality output images for further analysis with respect to change detection. [ABSTRACT FROM AUTHOR]

The present paper highlights the classification, change detection and future prediction of Sundarban reserve forest using multi-spectral satellite data over last 43 years (1975–2018). The remote sensing data are classified using back-propagation neural network algorithm which are healthy vegetation, unhealthy vegetation, wet land, and water bodies. The classification result demonstrates that the net forest areas were gradually declined by around 6.83% during 1975–2018, while it was not uniform over the whole period. Besides the other features also correspondingly changes. The change detection results revealed that some of the forest areas were converted into wet land and part of the wet land also flooded by water bodies due to rising sea level. To validate the forest cover classification on the images, the overall accuracy and Kappa coefficient were used. The resulting overall accuracy were 91.8%, 94.1%, 87.5%, 88.1% and 90.1% and Kappa coefficients were 0.8903, 0.9201, 0.8292, 0.8413 and 0.8680 for 1975, 1990, 2000, 2010, and 2018 respectively. Future predictions were obtained through CA-Markov Chain model which is based on the probabilistic modeling methods. The CA–Markov model shows that constant changes in forest cover. Changes in the extent of forest cover of the study area were further projected until 2034, representing that the area of net forest will be continuously reduced to 12.89%. The outcomes of this study may be offer quantitative information, which signify the base for measurement of forest ecosystem and for taking actions to reduce their degradation. [ABSTRACT FROM AUTHOR]

Image change detection is an active research topic in the field of remote sensing, as it allows monitoring environmental changes that occur on temporal and spatial scales. However, most of the existing change detection methods suffer from a lack of adaptability to different image types and lack of large-scale validation. In this study, we propose an automatic change detection method, called "CD-ResUNet," based on multi-spectral NDVI imagery. It is an end-to-end deep learning method based on the fusion of two complementary deep learning networks: UNet and residual networks (ResNet). Extensive experiments have been conducted on low-resolution as well as high-resolution datasets using four represented geographical areas, which are Colombia, California, Brazil, and Duluth, each containing 145,161 patches, and the Change Detection Dataset containing 16,000 patches. For all the investigated regions, the proposed method outperforms many relevant state-of-the-art methods with an accuracy up to 99.5% and an F1-score of 99.40%. [ABSTRACT FROM AUTHOR]

Science, Technology, Engineering, and Mathematics (STEM) domains require people to recognize and transform complex visuospatial displays that appear to vastly exceed the limits of visuospatial working memory. Here, we consider possible domain-general mechanisms that may explain this advantage: capitalizing on symmetry, a structural regularity that can produce more efficient representations. Participants briefly viewed a structure made up of three-dimensional connected cubes of different colors, which was either asymmetrical or symmetrical. After a short delay, they were asked to detect a change (colors swapping positions) within a rotated second view. In change trials, the second display always had an asymmetrical structure. The presence of symmetry in the initial view improved change detection, and performance also declined with angular disparity of the encoding and test displays. People with higher spatial ability performed better on the change-detection task, but there was no evidence that they were better at leveraging symmetry than low-spatial individuals. The results suggest that leveraging symmetrical structures can help people of all ability levels exceed typical working memory limits by constructing more efficient representations and substituting resource-demanding mental rotation operations with alternative orientation-independent strategies. [ABSTRACT FROM AUTHOR]

Wildfires are uncontrolled fires fuelled by dry conditions, high winds, and flammable materials that profoundly impact vegetation, leading to significant consequences including noteworthy changes to ecosystems. In this study, we provide a novel methodology to understand and evaluate post-fire effects on vegetation. In regions affected by wildfires, earth-observation data from various satellite sources can be vital in monitoring vegetation and assessing its impact. These effects can be understood by detecting vegetation change over the years using a novel unsupervised method termed Deep Embedded Clustering (DEC), which enables us to classify regions based on whether there has been a change in vegetation after the fire. Our model achieves an impressive accuracy of 96.17%. Appropriate vegetation indices can be used to evaluate the evolution of vegetation patterns over the years; for this study, we utilized Enhanced Vegetation Index (EVI) based trend analysis showing the greening fraction, which ranges from 0.1 to 22.4 km2 while the browning fraction ranges from 0.1 to 18.1 km2 over the years. Vegetation recovery maps can be created to assess re-vegetation in regions affected by the fire, which is performed via a deep learning-based unsupervised method, Adaptive Generative Adversarial Neural Network Model (AdaptiGAN) on post-fire data collected from various regions affected by wildfire with a training error of 0.075 proving its capability. Based on the results obtained from the study, our approach tends to have notable merits when compared to pre-existing works. [ABSTRACT FROM AUTHOR]

The change detection (CD) technology has greatly improved the ability to interpret land surface changes. Deep learning (DL) methods have been widely used in the field of CD due to its high detection accuracy and application range. DL-based CD methods usually cannot fuse the extracted feature information at full scale, leaving out effective information, and commonly use transfer learning methods, which rely on the original dataset and training weights. To address the above issues, we propose a deeply supervised (DS) change detection network (DASUNet) that fuses full-scale features, which adopts a Siamese architecture, fuses full-scale feature information, and realizes end-to-end training. In order to obtain higher feature information, the network uses atrous spatial pyramid pooling (ASPP) module in the coding stage. In addition, the DS module is used in the decoding stage to exploit feature information at each scale in the final prediction. The experimental comparison shows that the proposed network has the current state-of-the-art performance on the CDD and the WHU-CD, reaching 94.32% and 90.37% on F1, respectively. [ABSTRACT FROM AUTHOR]

Land use and land cover (LULC) analysis is crucial for understanding societal development and assessing changes during the Anthropocene era. Conventional LULC mapping faces challenges in capturing changes under cloud cover and limited ground truth data. To enhance the accuracy and comprehensiveness of the descriptions of LULC changes, this investigation employed a combination of advanced techniques. Specifically, multitemporal 30 m resolution Landsat-8 satellite imagery was utilized, in addition to the cloud computing capabilities of the Google Earth Engine (GEE) platform. Additionally, the study incorporated the random forest (RF) algorithm. This study aimed to generate continuous LULC maps for 2014 and 2020 for the Shrirampur area of Maharashtra, India. A novel multiple composite RF approach based on LULC classification was utilized to generate the final LULC classification maps utilizing the RF-50 and RF-100 tree models. Both RF models utilized seven input bands (B1 to B7) as the dataset for LULC classification. By incorporating these bands, the models were able to influence the spectral information captured by each band to classify the LULC categories accurately. The inclusion of multiple bands enhanced the discrimination capabilities of the classifiers, increasing the comprehensiveness of the assessment of the LULC classes. The analysis indicated that RF-100 exhibited higher training and validation/testing accuracy for 2014 and 2020 (0.99 and 0.79/0.80, respectively). The study further revealed that agricultural land, built-up land, and water bodies have changed adequately and have undergone substantial variation among the LULC classes in the study area. Overall, this research provides novel insights into the application of machine learning (ML) models for LULC mapping and emphasizes the importance of selecting the optimal tree combination for enhancing the accuracy and reliability of LULC maps based on the GEE and different RF tree models. The present investigation further enabled the interpretation of pixel-level LULC interactions while improving image classification accuracy and suggested the best models for the classification of LULC maps through the identification of changes in LULC classes. [ABSTRACT FROM AUTHOR]

Temperate broadleaf forests in the Western Himalaya support a large number of local agro-pastoral communities and provide numerous ecosystem services. Several authors have raised serious concerns about the sustainability of current extractive pressures in these forests. We conducted a detailed ecological study on different forests in Askot Wildlife Sanctuary area to assess their current status in terms of species composition and regeneration of dominant tree species. We quantified structure and composition, population structure and regeneration pattern in six major forest types and compared the findings of a previous study conducted by other authors in the same area about 20 years ago. A total of 180 plots in 18 sites were sampled following the standard phytosociological methods. Canonical component analysis was used to predict the impact of environmental factors on forest communities, and land use land cover changes detected influence of ongoing anthropogenic pressures in the area. The study revealed that extractive pressures in the study area have increased since then, which resulted in the decline of the forested area. However, there has been an expansion of Macaranga pustulata, Quercus leucotrichophora and Quercus lanuginosa since the year 2000 and there is a decline in the regeneration of Quercus semecarpifolia. Considering the significance of high-altitude forests and the ecological sensitivity of Q. semecarpifolia, it is recommended to initiate urgent conservation measures in the region. [ABSTRACT FROM AUTHOR]

This paper focuses on establishing an effective predictive model to quickly and accurately alert hypoglycemia and hyperglycemia for helping control blood glucose levels of people with diabetes. In general, a good predictive model is established on the features of data. Inspired by this, we first analyze the characteristics of continuous glucose monitoring (CGM) data by the equality of variances test and outlier detection, which show time-varying fluctuations and jump points in CGM data. Therefore, we incorporate the change detection method and the Winsorization method into the predictive model based on the autoregressive moving average (ARMA) model and the recursive least squares (RLS) method to fit the above characteristics. To the best of our knowledge, the proposed method is the first attempt to give a solution for matching the time-varying fluctuations and jump points of CGM data simultaneously. A case study using CGM data is given to validate the effectiveness of the proposed method under 30-min-ahead prediction. The results show that the proposed method can improve the true alarm ratio of hypoglycemia and hyperglycemia from 0.7983 to 0.8783, and lengthen the average advance detection time of hypoglycemia and hyperglycemia from 19.77 to 22.64 min. [ABSTRACT FROM AUTHOR]

One of the most important aspects of climate change is alterations in the amount and characteristics of precipitation. The present study intended to project precipitation changes over Iran based on the regional models of the CORDEX project under two scenarios (namely, RCP4.5 and RCP8.5). For this purpose, six indices, including maximum 1-day precipitation, simple precipitation intensity index, maximum length of dry spell, annual count of days when PRCP ≥ 10 mm, annual count of days when PRCP ≥ 1 mm, and annual total precipitation in wet days, were extracted. MERRA2 reanalysis precipitation data, highly correlated with observation data from 48 weather stations all over the country, were used for the 1980–2006 time period to assess the CORDEX project outputs. The results were presented in three different time periods, including the base period (1980–2006), the near future (2021–2050), and the far future (2071–2100). The results of the analyses indicated that four indices, namely the maximum 1-day precipitation, the annual count of days when PRCP ≥ 1 mm, the annual count of days when PRCP ≥ 10 mm, and the annual total precipitation in wet days, demonstrated a decrease in precipitation and an increase in dry spells all over the country except for the east and the southeast regions where these indices will increase compared to the base period (except for the maximum length of the dry spell). Research Highlights: 1. The study focuses on monitoring and projecting spatiotemporal changes in extreme precipitation indices over Iran for historic (1980 to 2006), near future (2021-2050), and far future (2071-2100) time periods. 2. From 1980 to 2006, MERRA2 reanalysis precipitation data show a strong spatial correlation with monthly observational data, and total precipitation shows negative significant trends in the northwest and positive significant trends in the north. 2. From 1980 to 2006, MERRA2 reanalysis precipitation data show a strong spatial correlation with monthly observational data, and total precipitation shows negative significant trends in the northwest and positive significant trends in the north. 3. For projecting extreme precipitation, four CORDEX-WAS models based on two RCPs (RCP4.5 and RCP8.5) are used. 4. A precise plane is required to deal with precipitation reduction and increased dry spells in the near and far future. [ABSTRACT FROM AUTHOR]

This study comprehensively assessed long-term vegetation changes and forest fragmentation dynamics in the Himalayan temperate region of Pakistan from 1989 to 2019. Four satellite images, including Landsat-5 TM and Landsat-8 Operational Land Imager (OLI), were chosen for subsequent assessments in October 1989, 2001, 2011 and 2019. The classified maps of 1989, 2001, 2011 and 2019 were created using the maximum likelihood classifier. Post-classification comparison showed an overall accuracy of 82.5% and a Kappa coefficient of 0.79 for the 2019 map. Results revealed a drastic decrease in closed-canopy and open-canopy forests by 117.4 and 271.6 km2, respectively, and an increase in agriculture/farm cultivation by 1512.8 km2. The two-way ANOVA test showed statistically significant differences in the area of various cover classes. Forest fragmentation was evaluated using the Landscape Fragmentation Tool (LFT v2.0) between 1989 and 2019. The large forest core (> 2.00 km2) decreased from 149.4 to 296.7 km2, and a similar pattern was observed in medium forest core (1.00–2.00 km2) forests. On the contrary, the small core (< 1.00 km2) forest increased from 124.8 to 145.3 km2 in 2019. The perforation area increased by 296.9 km2, and the edge effect decreased from 458.9 to 431.7 km2. The frequency of patches also increased by 119.1 km2. The closed and open canopy classes showed a decreasing trend with an annual rate of 0.58% and 1.35%, respectively. The broad implications of these findings can be seen in the studied region as well as other global ecological areas. They serve as an imperative baseline for afforestation and reforestation operations, highlighting the urgent need for efficient management, conservation, and restoration efforts. Based on these findings, sustainable land-use policies may be put into place that support local livelihoods, protect ecosystem services, and conserve biodiversity. [ABSTRACT FROM AUTHOR]

The world we live in is dynamic by nature. Frequently, the environment changes in ways we cannot predict. In machine learning, the phenomenon that occurs when a model has its prediction effectiveness degraded due to unforeseen changes is known as concept drift. Applications of smart video surveillance tend to suffer from concept drift due to changes in illumination, weather, and scene structure. This work differs from previous ones as it brings focus to the problem of concept drift from a surveillance video perspective which presents additional challenges compared to other sources of data, such as high dimensionality, spatial and temporal relations between data, and real-time constraints. The approaches and algorithms used to cope with concept drift are compared and discussed. We also present datasets and metrics used to evaluate the effectiveness of the algorithms. As contributions, we present a new classification of concept drift adaptation methods, delineate the characteristics and limitations of techniques that deal with concept drift, and analyze practical aspects, such as real-time processing and memory constraints. Moreover, we conclude that informed concept drift adaptation methods have been employed 90% less than continuous adaptation ones. Research directions include using established concept drift detection techniques applied to surveillance video data, exploring datasets for concept drift in surveillance, strategies to deal with the high dimensionality and volume of surveillance video data when adapting existing models, and the creation of frameworks to manage drift adaptation while applying computer vision tasks. [ABSTRACT FROM AUTHOR]

The expected color of an object influences how it is perceived. For example, a banana in a greyscale photo may appear slightly yellow because bananas are expected to be yellow. This phenomenon is known as the memory color effect (MCE), and the objects with a memory color are called "color-diagnostic." The MCE is theorized to be a top-down influence of color knowledge on visual perception. However, its validity has been questioned because most evidence for the MCE is based on subjective reports. Here a change detection task is used as an objective measure of the effect and the results show that change detection differs for color-diagnostic objects. Specifically, it was predicted and found that unnaturally colored color-diagnostic objects (e.g., a blue banana) would attract attention and thus be discovered more quickly and accurately. In the experiment, two arrays alternated with the target present in one array and absent in the other while all other objects remained unchanged. Participants had to find the target as quickly and accurately as possible. In the experimental condition, the targets were color-diagnostic objects (e.g., a banana) presented in either their natural (yellow) or an unnatural (blue) color. In the control condition, non-color-diagnostic objects (e.g., a mug) were presented with the same colors as the color-diagnostic objects. Unnaturally colored color-diagnostic objects were found more quickly, which suggests that the MCE is a top-down, preattentive process that can influence a nonsubjective visual perceptual task such as change detection. [ABSTRACT FROM AUTHOR]

Change detection is becoming more and more popular technology for the analysis of remote sensing data and is very important for an accurate understanding of changes that are happening in the Earth's surface. Different Deep Learning methods proposed till now are mainly focused on simple networks which results in poor detection for small changed areas because they can not differentiate between the bi-temporal image's characteristics. To solve this problem, this article proposes a novel Building Change Detection Network (BCDetNet) for building object change detection and its analysis from bi-temporal high resolution satellite image. The proposed BCDetNet model can detect small change areas with the help of multiple feature extraction block. The proposed BCDetNet model executes building change detection using bi-temporal high resolution satellite images. The proposed BCDetNet model is trained on two publicly available datasets namely LEVIR and WHU change detection(CD) datasets. These datasets contain RGB images with dimensions of (1024 × 1024) and (512 × 512), respectively. The BCDetNet model can learn from scratch during training and performs better than the benchmark change detection models with fewer trainable parameters. The BCDetNet model gives Recall—94.06%, Precision—93.00%, Jaccard score—88.40%, Accuracy—98.73%, F1 score—93.52% and Kappa coefficient—87.05% on LEVIR CD dataset and Recall—89.51%, Precision —92.78%, Jaccard score - 84.38%, Accuracy—96.78%, F1 score—91.06% and Kappa coefficient - 82.12% on WHU CD dataset. This work is a step in the direction of achieving best results in building change detection from high resolution satellite images. [ABSTRACT FROM AUTHOR]

Kenya experiences massive urban growth, also into natural hazard-prone areas, exposing settlements and the natural environment to riverine and pluvial floods and other natural hazards. While Nairobi as the capital and principal city has been extensively analysed regarding urban growth and flood hazard in some central parts, awareness of growing peri-urban areas has not been studied as much. The results are of interest to other locations in Kenya and worldwide, too, since the current research and disaster risk practice focus is still too much on megacities and city centres. Therefore, the study compares urban growth into hazard areas in urban rims of Nairobi and Nyeri, Kenya. A change assessment from 1948 to 2020 is conducted by aerial images, declassified satellite images, and recent data. Urban growth rates are 10- to 26-fold, while growth into flood exposed areas ranges from 2- to 100-fold. This study reveals unused opportunities for expanding existing land-use change analysis back to the 1940s in data-scarce environments. [ABSTRACT FROM AUTHOR]

High-resolution satellite data are an excellent way to monitor the growth of an urban area in terms of vertical and horizontal growth. Time-series data over two different zones from the same satellite sensor or contemporary sensors act as a good test bed for change detection. In most of the cases, 2D images of different time frames are spatially registered, and pixel difference is calculated which enables the detection of change in horizontal growths. Three-dimensional change detection to mark a change in the vertical direction can also be computed by comparing high-resolution digital surface models (DSM) of two different times and detect changes in topography. Using accurate DSM and derived digital terrain models (DTM) information from DSM, exact and accurate heights of the building footprints can be extracted. Using 3D city models, information about horizontal growth and vertical growth of the city can be assessed using change detection over the temporal data. Three-dimensional change detection can also enable district and state administration to discern the planned growth of the city, illegal constructions and future planning of the city, especially in the projects like smart cities. In this study, we are comparing 2D raster images of different time frames to assess change in horizontal direction, very high-resolution DSMs and DTMs datasets of two different time zones to assess change in vertical directions and visualizing 3D change detection of Ahmedabad city, in terms of its horizontal and vertical changes in urban growth area. We are also making the assessment of the growth of the city (5% change in building structures) and population in the studied area. It is inferred that the city population in the year 2018 is more than 35% as compared to the population in the year 2011. Further, we are calculating geophysical parameters of land surface temperature (LST) and normalized difference vegetation index (NDVI) over a time using satellite datasets, which provides a proxy observation for the changes in the urban growth. Using satellite data, it is concluded that NDVI is reduced over the study area whereas there is an increase in LST temperature at night time during the winter season. We concluded that increased urbanization and population (> 35%) are also contributing for rise in the LST temperature at nights in the city apart from the other big environmental parameters such as global warming, etc. [ABSTRACT FROM AUTHOR]

Land use / land cover (LULC) has changed dramatically in recent years, especially in areas that have experienced severe climate change and population growth. Evaluation of LULC changes is the most accurate method to understand past land uses and predict their future changes. Analysis of multi-temporal optic and radar remotely sensed images is an effective tool for monitoring LULC changes, and fusion of these datasets has provided significant developments in the detection and modeling of land surface changes due to their unique features individually. Time-series image (TSI) analysis provides a history of changes in an area and allows for predicting future changes. This study aims to develop a method for modeling LULC changes and predicting future trends. To this end, a spatiotemporal regression model is proposed based on TSI. In this method, land surface changes are first modeled by considering the spatiotemporal behavioral patterns of cover changes in a given period. Then, future land covers are predicted by a spatiotemporal regression. To evaluate the proposed method, LULC changes of the Maharloo Lake (Fars province, Iran) were modeled using fused optical and radar TSI (12 consecutive image sets) and then predicted for time t = 13. Compared to ground truth data, the different land covers including; water bodies, vegetation cover, bare land, and saline area were predicted by accuracies of 84.9, 98.4, 90.7, and 97.3%, respectively, indicating the remarkable efficiency of the model proposed for predicting LULC. [ABSTRACT FROM AUTHOR]

The Accra Metropolis of Ghana has experienced rapid urban expansion over the past decades. Agricultural and forestlands have been transformed into urban/built-up areas. This study analysed urban expansion and its relationship with the temperature of Accra from 1986 to 2022. Multi-source datasets such as remote sensing (RS) and other ancillary data were utilised. Land use land cover (LULC) maps were produced employing the random forests classifier. Land surface temperature (LST) and selected d(RS) Indices were extracted. Regression techniques assessed the interplay between LST and remote sensing indices. The LULC maps revealed increasing trends in the urban/built-up areas at the expense of the other LULC types. The analysis from the LST and the RS indices revealed a direct relationship between temperature and urban/built-up areas and an inverse relationship between temperature and vegetation. Thus, spatial urban expansion has modified the urban temperature of Accra. The integrated utilisation of RS and GIS demonstrated to be an efficient approach for analysing and monitoring urban expansion and its relationship with temperature.Article Highlights: Urban expansion has led to the conversion of agricultural and forestlands into urban areas in Accra, Ghana. There is a direct relationship between temperature and urban/built-up areas. The adopted techniques proved effective in analysing and monitoring urban expansion and its impact on temperature. [ABSTRACT FROM AUTHOR]

The pace and magnitude of land use and land cover (LULC) change are of global concern due to its role in pressing issues such as climate change, food security, soil degradation and biodiversity loss. The present study analyzed the spatiotemporal changes in LULC in the Hafir-Zariffet forest of Tlemcen, Northwest Algeria. We also simulated possible future LULC scenarios for the area. LULC maps of 1989, 1999, 2009 and 2019 were classified using the Random Forest Algorithm in R software and change assessed via intensity analysis. The results revealed that the first decade (1989–1999) showed a faster intensity of change compared to the second (1999–2009) and the third decades (2009–2019). Sparse wooded maquis experienced a major decline (1989–2019) of 15.19% whereas open matorral (+ 14.30), forest (+ 0.15%), and agriculture (+ 1.33%) increased. The simulation at a skill measure of > 0.50 showed that the open matorral could witness the highest loss of 29.13% while forest cover, sparse wooded maquis, settlement and barelands, and agriculture could increase by 9.51%, 13.26%, 0.56% and 5.79%, respectively between 2019 and 2039 based on the change pattern between 2009 and 2019 in the study area. The substantial decline of open matorral and the expansion of agriculture, settlement and barelands could pose a threat to the ecology of the environment as the changes will impact the ecosystem functions of the landscape. The findings of this study provide useful information on understanding spatiotemporal LULC change in the semi-arid Mediterranean region and can assist sustainable land development policies. [ABSTRACT FROM AUTHOR]

Urban growth and the changing scenario of Land Use and Land Cover (LULC) have been an increasing trend in both towns and cities. The higher rate of transformation from non-built up land to the impervious area becomes a warning symbol of Land surface temperature variations. In this study, an attempt has been made to determine the transition of natural land area and its impact on Land surface temperature (LST) in Vellore district, Tamil Nadu, India. According to the current statistics, the study area records the hottest climate crossing 40° mark in recent years. This is mainly due to the minimum rainfall, the ground level is 200 m just above the sea level, and the pollution caused by tanneries. Landsat imageries are collected for three different years 1994, 2002, and 2018 that map the LULC into agricultural, water bodies, built-up land, and barren land classes. The major purpose of this research is to (i) analyze changes of LULC in and around Vellore city, (ii) categorize the images into various classes like vegetative and non-vegetative land, (iii) Assessment of Spatio-temporal variations in LST and link with classes and urbanization growth using satellite images. The LULC impact on LST is analyzed with the widely used Getis–Ord statistics. The simulation result shows that the built-up area raises to 81%, vegetation land decline by about −65% for the years 1994–2018 respectively. It is observed that LST has attained the highest degree in the built-up class due to the unplanned LULC changes and the conversion of built-up areas. The overall accuracy is achieved at about 92, 89, and 91% for three different years respectively. Based on the obtained result, this can be adopted for the development of rural, and urban areas in the coming future. [ABSTRACT FROM AUTHOR]

Monitoring a specific area to analyze a continuous change has become more accessible by using optical images in remote sensing technology. However, several natural and artificial aspects such as fog and air pollution make it difficult to extract correct geometric information. To overcome the limitation of optical images, Synthetic Aperture Radar (SAR) images can be used to access more accurate information with respect to the targeted area. In this manner, optical and SAR images can be utilized together to detect the scale of change even in bad weather conditions. To process optical and SAR images, an image translation process-oriented Deep Adaptation-based Change Detection Technique (DACDT) is proposed. An optimized U-Net++ model is proposed that helps to improve the global and regional impacts of the images. Moreover, a multi-scale loss function is utilized to access the features of different dimensions. In this manner, the final change maps are generated by transferring the features of optical images to the SAR images for better change analysis. The prediction performance of the proposed approach is evaluated on four different datasets such as Gloucester I, Shuguang Village, Gloucester-II, and California. The calculated outcomes define the prediction performance of the proposed solution by registering the accuracy of 98.67%, 99.77%, 97.68%, and 98.87%, respectively. [ABSTRACT FROM AUTHOR]

Land use/land cover (LULC) changes can occur naturally or due to human activities. In this study, the maximum likelihood algorithm (MLH) and machine learning (random forest algorithm (RF) and support vector machine (SVM)) were investigated for image classification to oversight spatio-temporal land use changes in El-Fayoum governorate, Egypt. The Google Earth Engine has been utilized to pre-process the Landsat imagery, and then upload it for classification. Each classification method was evaluated using field observations and high-resolution Google Earth imagery. LULC changes were assessed, utilizing Geographic Information System (GIS) techniques, over the last 20 years in three different periods: 2000–2012, 2012–2016, and 2016–2020. The results showed that socioeconomic changes occurred during these transitions. The SVM procedure provided the most accurate maps in terms of the kappa coefficient (0.916) compared to MLH (0.878) and RF (0.909) procedures. Therefore, the SVM technique was adopted to classify all available satellite imagery. The results of change detection showed that urban sprawl has occurred and most of the encroachments were on agricultural land. The results showed that agricultural land area decreased from 26.84% in 2000 to 26.61% in 2020 and urban area increased from 3.43% in 2000 to 5.99% in 2020. In addition, urban land expanded rapidly on account of agricultural lands by a total of 4.78% from 2012 to 2016, while it expanded slowly by a total of 3.23% from 2016 to 2020. Overall, this study offers useful insight into LULC changes that might aid shareholders and decision makers in making informed decisions. [ABSTRACT FROM AUTHOR]

Land use and land cover (LULC) is a major concern of global environmental change, particularly the case, in developing countries. In the Central Ethiopian Rift Valley (CRV), unprecedented changes in LULC have been observed over the last decades. This study aims to scrutinize the dynamics of the CRV over a timespan of three decades (1984–2013). Satellite imageries were acquired from Multispectral Scanner System, Thematic Mapper, and Enhanced Thematic mapper for the years 1984, 1995, and 2013 respectively. The data were obtained from the United States Geological Survey and Ethiopian Geospatial Information Institute. In addition, Focus Group Discussions and Key Informants Interviews were undertaken to support analysis and interpretation of LULC anomalies, identify drivers, and associated impacts. Geospatial technologies were used to analyze the extent of LULC change across the study period. An object-oriented supervised classification and a change detection technique were applied to compartmentalize the change into six LULC classes. Results revealed that farmlands and built-up areas have shown continuous progressive expansion at the expense of bareland and forestland. Farmland and built-up area in 1984 were expanded from 33.3% and 2.6% to 40.6% and 8.2% in 2013, respectively. In contrast, forestland and bareland coverages in 1984 were dwindled from 11.7% and 17.7% to 4.2% and 10.1% in 2013, respectively. Comparatively, shrubland and waterbody were also slightly augmented by 1.9% and 0.2% from 1984 to 2013. Therefore, the result suggested that policymakers and development actors must take appropriate actions to minimize the progressive decline of forest cover in the milieu. [ABSTRACT FROM AUTHOR]