Deep Learning-Based Change Detection in Remote Sensing Images: A Review

Enhanced hybrid CNN and transformer network for remote sensing image change detection

Remote sensing (RS) change detection incurs a high cost because of false negatives, which are more costly than false positives. Existing frameworks, struggling to improve the Precision metric to reduce the cost of false positive, still have limitations in focusing on the change of interest, which leads to missed detections and discontinuity issues. This work tackles these issues by enhancing feature learning capabilities and integrating the frequency components of feature information, with a strategy to incrementally boost the Recall value. We propose an enhanced hybrid of CNN and Transformer network (EHCTNet) for effectively mining the change information of interest. Firstly, a dual branch feature extraction module is used to extract the multi-scale features of RS images. Secondly, the frequency component of these features is exploited by a refined module I. Thirdly, an enhanced token mining module based on the Kolmogorov-Arnold Network is utilized to derive semantic information. Finally, the semantic change information's frequency component, beneficial for final detection, is mined from the refined module II. Extensive experiments validate the effectiveness of EHCTNet in comprehending complex changes of interest. The visualization outcomes show that EHCTNet detects more intact and continuous changed areas and perceives more accurate neighboring distinction than state-of-the-art models.

Efficient detection and characterization of targets of natural selection using transfer learning

Natural selection leaves detectable patterns of altered spatial diversity within genomes, and identifying affected regions is crucial for understanding species evolution. Recently, machine learning approaches applied to raw population genomic data have been developed to uncover these adaptive signatures. Convolutional neural networks (CNNs) are particularly effective for this task, as they handle large data arrays while maintaining element correlations. However, shallow CNNs may miss complex patterns due to their limited capacity, while deep CNNs can capture these patterns but require extensive data and computational power. Transfer learning addresses these challenges by utilizing a deep CNN pre-trained on a large dataset as a feature extraction tool for downstream classification and evolutionary parameter prediction. This approach reduces extensive training data generation requirements and computational needs while maintaining high performance. In this study, we developed TrIdent, a tool that uses transfer learning to enhance detection of adaptive genomic regions from image representations of multilocus variation. We evaluated TrIdent across various genetic, demographic, and adaptive settings, in addition to unphased data and other confounding factors. TrIdent demonstrated improved detection of adaptive regions compared to recent methods using similar data representations. We further explored model interpretability through class activation maps and adapted TrIdent to infer selection parameters for identified adaptive candidates. Using whole-genome haplotype data from European and African populations, TrIdent effectively recapitulated known sweep candidates and identified novel cancer, and other disease-associated genes as potential sweeps.

A Comprehensive Survey of Deep Learning Approaches in Image Processing

The integration of deep learning (DL) into image processing has driven transformative advancements, enabling capabilities far beyond the reach of traditional methodologies. This survey offers an in-depth exploration of the DL approaches that have redefined image processing, tracing their evolution from early innovations to the latest state-of-the-art developments. It also analyzes the progression of architectural designs and learning paradigms that have significantly enhanced the ability to process and interpret complex visual data. Key advancements, such as techniques improving model efficiency, generalization, and robustness, are examined, showcasing DL's ability to address increasingly sophisticated image-processing tasks across diverse domains. Metrics used for rigorous model evaluation are also discussed, underscoring the importance of performance assessment in varied application contexts. The impact of DL in image processing is highlighted through its ability to tackle complex challenges and generate actionable insights. Finally, this survey identifies potential future directions, including the integration of emerging technologies like quantum computing and neuromorphic architectures for enhanced efficiency and federated learning for privacy-preserving training. Additionally, it highlights the potential of combining DL with emerging technologies such as edge computing and explainable artificial intelligence (AI) to address scalability and interpretability challenges. These advancements are positioned to further extend the capabilities and applications of DL, driving innovation in image processing.

Research on the Multiple Small Target Detection Methodology in Remote Sensing

This study focuses on advancing the field of remote sensing image target detection, addressing challenges such as small target detection, complex background handling, and dense target distribution. We propose solutions based on enhancing the YOLOv7 algorithm. Firstly, we improve the multi-scale feature enhancement (MFE) method of YOLOv7, enhancing its adaptability and precision in detecting small targets and complex backgrounds. Secondly, we design a modified YOLOv7 global information DP-MLP module to effectively capture and integrate global information, thereby improving target detection accuracy and robustness, especially in handling large-scale variations and complex scenes. Lastly, we explore a semi-supervised learning model (SSLM) target detection algorithm incorporating unlabeled data, leveraging information from unlabeled data to enhance the model's generalization ability and performance. Experimental results demonstrate that despite the outstanding performance of YOLOv7, the mean average precision (MAP) can still be improved by 1.9%. Specifically, under testing on the TGRS-HRRSD-Dataset, the MFE and DP-MLP models achieve MAP values of 93.4% and 93.1%, respectively. Across the NWPU VHR-10 dataset, the three models achieve MAP values of 93.1%, 92.1%, and 92.2%, respectively. Significant improvements are observed across various metrics compared to the original model. This study enhances the adaptability, accuracy, and generalization of remote sensing image object detection.

Quantifying the scale of erosion along major coastal aquifers of Pakistan using geospatial and machine learning approaches

Insufficient freshwater recharge and climate change resulted in seawater intrusion in most of the coastal aquifers in Pakistan. Coastal aquifers represent diverse landcover types with varying spectral properties, making it challenging to extract information about their state hence, such investigation requires a combination of geospatial tools. This study aims to monitor erosion along the major coastal aquifers of Pakistan and propose an approach that combines data fusion into the machine and deep learning image segmentation architectures for the erosion and accretion assessment in seascapes. The analysis demonstrated the image segmentation U-Net with EfficientNet backbone achieved the highest F1 score of 0.93, while ResNet101 achieved the lowest F1 score of 0.77. Resultant erosion maps indicated that Sandspit experiencing erosion at 3.14 km2 area. Indus delta is showing erosion, approximately 143 km2 of land over the past 30 years. Sonmiani has undergone substantial erosion with 52.2 km2 land. Miani Hor has experienced erosion up to 298 km2, Bhuri creek has eroded over 4.11 km2, east Phitii creek over 3.30 km2, and Waddi creek over 3.082 km2 land. Tummi creek demonstrates erosion, at 7.12 km2 of land, and East Khalri creek near Keti Bandar has undergone a measured loss of 5.2 km2 land linked with quantified reduction in the vertical sediment flow from 50 (billion cubic meters) to 10 BCM. Our analysis suggests that intense erosions are primarily a result of reduced sediment flow and climate change. Addressing this issue needs to be prioritized coastal management and climate change mitigation framework in Pakistan to safeguard communities. Leveraging emerging solutions, such as loss and damage financing and the integration of nature-based solutions (NbS), should be prioritized for the revival of the coastal aquifers.

Multi-decadal coastal change detection using remote sensing: the Mediterranean coast of Egypt between El-Dabaa and Ras El-Hekma

A key source of information for many decision support systems is identifying land use and land cover (LULC) based on remote sensing data. Land conservation, sustainable development, and water resource management all benefit from the knowledge obtained from detecting changes in land use and land cover. The present study aims to investigate the multi-decadal coastal change detection for Ras El-Hekma and El-Dabaa area along the Mediterranean coast of Egypt, a multi-sectoral development area. Besides, the superiority of the area is highly dependent on its proximity to three development projects: the tourism and urban growth pole at Ras El-Hekma, the beachfront Alamain New Mega City, and the Nuclear Power Plant at El Dabaa. This study utilized multi-spectral Landsat satellite images covering 1990, 2010, and 2020 to perceive the post-classification change detection analysis of the land use and land cover changes (LULCC) over 30 years. The results of the supervised classification from 1990 to 2020 showed a 47.33 km2 (4.13%) expansion of the agricultural land area, whereas the bare soil land area shrunk to 73.13 km2 (6.24%). On the other hand, the built-up activities in the area launched in 2010 and escalated to 20.51 km2(1.77%) in 2020. The change in land use reveals the shift in the economic growth pattern in the last decade toward tourism and urban development. Meanwhile, it indicates that no conflict has yet arisen regarding the land use between the expanded socioeconomic main sectors (i.e., agriculture, and tourism). Therefore, the best practices of land use management and active participation of the stakeholders and the local community should be enhanced to achieve sustainability and avoid future conflicts. An area-specific plan including resource conservation measures and the provision of livelihood alternatives should be formulated within the National Integrated Coastal Zone Management (ICZM) plan with the participation of the main stakeholders and beneficiaries. The findings of the present work may be considered useful for sustainable management and supportive to the decision-making process for the sustainable development of this area.

Convolutional neural network for high-resolution wetland mapping with open data: Variable selection and the challenges of a generalizable model

Landscape scale wetland conservation requires accurate, up-to-date wetland maps. The most useful approaches to creating such maps are automated, spatially generalizable, temporally repeatable, and can be applied at large spatial scales. However, mapping wetlands with predictive models is challenging due to the highly variable characteristics of wetlands in both space and time. Currently, most approaches are limited by coarse resolution, commercial data, and geographic specificity. Here, we trained a deep learning model and evaluated its ability to automatically map wetlands at landscape scale in a variety of geographies. We trained a U-Net architecture to map wetlands at 1-meter spatial resolution with the following remotely sensed covariates: multispectral data from the National Agriculture Imagery Program and the Sentinel-2 satellite system, and two LiDAR-derived datasets, intensity and geomorphons. The full model mapped wetlands accurately (94 % accuracy, 96.5 % precision, 95.2 % AUC) at 1-meter resolution. Post hoc model evaluation showed that the model correctly predicted wetlands even in areas that had incorrect label/training data, which penalized the recall rate (90.2 %). Applying the model in a new geography resulted in poor performance (precision = ~80 %, recall = 48 %). However, limited retraining in this geography improved model performance substantially, demonstrating an effective means to create a spatially generalizable model. We demonstrate wetlands can be mapped at high-resolution (1 m) using free data and efficient deep-learning models that do not require manual feature engineering. Including LiDAR and geomorphons as input data improved model accuracy by 2 %, and where these data are unavailable a simpler model can efficiently map wetlands. Given the dynamic nature of wetlands and the important ecosystem services they provide, high-resolution mapping can be a game changer in terms of informing restoration and development decisions.

Method of Building Detection in Optical Remote Sensing Images Based on SegFormer

An appropriate detection network is required to extract building information in remote sensing images and to relieve the issue of poor detection effects resulting from the deficiency of detailed features. Firstly, we embed a transposed convolution sampling module fusing multiple normalization activation layers in the decoder based on the SegFormer network. This step alleviates the issue of missing feature semantics by adding holes and fillings, cascading multiple normalizations and activation layers to hold back over-fitting regularization expression and guarantee steady feature parameter classification. Secondly, the atrous spatial pyramid pooling decoding module is fused to explore multi-scale contextual information and to overcome issues such as the loss of detailed information on local buildings and the lack of long-distance information. Ablation experiments and comparison experiments are performed on the remote sensing image AISD, MBD, and WHU dataset. The robustness and validity of the improved mechanism are demonstrated by control groups of ablation experiments. In comparative experiments with the HRnet, PSPNet, U-Net, DeepLabv3+ networks, and the original detection algorithm, the mIoU of the AISD, the MBD, and the WHU dataset is enhanced by 17.68%, 30.44%, and 15.26%, respectively. The results of the experiments show that the method of this paper is superior to comparative methods such as U-Net. Furthermore, it is better for integrity detection of building edges and reduces the number of missing and false detections.

Modelling hydrological strength and alteration in moribund deltaic India

The Ganga-Brahmaputra moribund deltaic floodplain region hosted many socio-ecologically precious freshwater wetland ecosystems experiencing hydrological alteration. The present study aimed to model hydrological strength (HS) to show the spatial difference and account for the degree and direction of hydrological alteration of Indian moribund deltaic wetland in three phases e.g. (1) phase I (1988-1997), (2) phase II (1998-2007) and phase III (2008-2017). Three key hydrological parameters, such as Water Presence Frequency (WPF), water depth, and hydro-period were considered for hydrological strength modelling using two ensemble Machine Learning (ML) techniques (Random Forest (RF) and XGBoost). Image algebra was employed for phasal change detection. Hydrological strength models show that around 75% of the wetland area was lost in-between phases I to III and the loss was found more intensive in moderate and weak HS zones. Existing wetland shows a clear spatial difference of HS between wetland core and periphery and river linked and delinked or not linked wetlands. Regarding the suitability of the ML models, both are acceptable, however, the XGBoost outperformed in reference to applied 15 statistical validation techniques and field evidence. HS models based on change detection clarified that more than 22% and 55% of the weak HS zone in phases II and III respectively were turned into non-wetland. The degree of alteration revealed that about 40% of wetland areas experienced a negative alteration during phases I to II, and this proportion increased to 63% in between phases II to III. Since the study figured out the spatial nature of HS, degree and direction of alteration at a spatial scale, these findings would be instrumental for adopting rational planning towards wetland conservation and restoration.