Multispectral Satellite Images Research Articles

Roads and Woody Vegetation Structure Are Associated With Chimpanzee (Pan troglodytes) Occurrence at Its Northern Range Limit

ABSTRACTAimThe purported defining features of chimpanzee (Pan troglodytes) biogeography are sometimes simplistic and contradictory, yet we rely on these metrics to shape conservation and management planning for this endangered ape. We analysed the cover and configuration of woody vegetation at the northern margins of the species' range in Senegal to elucidate key predictors of chimpanzee biogeography.LocationSoutheastern Senegal.TaxaWestern chimpanzee (Pan troglodytes verus).MethodsWe combined reconnaissance surveys and interviews with published accounts of chimpanzee presence to verify previous estimates of the range limits of the species. High‐resolution, multispectral satellite images were used to quantify the configuration of trees and shrubs at each site. Woody vegetation cover and physiognomy, river density and road density were compared within and outside of the species range with generalised linear mixed models.ResultsOur surveys and interviews support the current estimates of the northern limits of the species range. Chimpanzee‐occupied sites had more patchily‐distributed vegetation, greater patch edge complexity, and slightly higher river density than unoccupied sites. Unoccupied sites had more woody vegetation cover and higher road density. Of all predictors, roads had the highest impact on chimpanzee occupancy.Main ConclusionsIn line with previous findings, anthropogenic modifications of the landscape had a strong impact on chimpanzee occupancy, but surprisingly, woody vegetation cover was negatively associated with chimpanzee occupancy in this region. Instead, more specific metrics of vegetation configuration were positively associated with chimpanzee site occupancy, indicating that precise measures are needed for assessing chimpanzee biogeography at the landscape scale.

Detection of Complex Formations in an Inland Lake from Sentinel-2 Images Using Atmospheric Corrections and a Fully Connected Deep Neural Network

The detection of complex formations, initially suspected to be oil spills, is investigated using atmospherically corrected multispectral satellite images and deep learning techniques. Several formations have been detected in an inland lake in Northern Greece. Four atmospheric corrections (ACOLITE, iCOR, Polymer, and C2RCC) that are specifically designed for water applications are examined and implemented on Sentinel-2 multispectral satellite images to eliminate the influence of the atmosphere. Out of the four algorithms, iCOR and ACOLITE are able to depict the formations sufficiently; however, the latter is chosen for further processing due to fewer uncertainties in the depiction of these formations as anomalies across the multispectral range. Furthermore, a number of formations are annotated at the pixel level for the 10 m bands (red, green, blue, and NIR), and a deep neural network (DNN) is trained and validated. Our results show that the four-band configuration provides the best model for the detection of these complex formations. Despite not being necessarily related to oil spills, studying these formations is crucial for environmental monitoring, pollution detection, and the advancement of remote sensing techniques.

Evaluating Flood Damage to Paddy Rice Fields Using PlanetScope and Sentinel-1 Data in North-Western Nigeria: Towards Potential Climate Adaptation Strategies

Floods are significant global disasters, but their impact in developing countries is greater due to the lower shock tolerance, many subsistence farmers, land fragmentation, poor adaptation strategies, and low technical capacity, which worsen food security and livelihoods. Therefore, accurate and timely monitoring of flooded crop areas is crucial for both disaster impact assessments and adaptation strategies. However, most existing methods for monitoring flooded crops using remote sensing focus solely on estimating the flood damage, neglecting the need for adaptation decisions. To address these issues, we have developed an approach to mapping flooded rice fields using Earth observation and machine learning. This approach integrates high-resolution multispectral satellite images with Sentinel-1 data. We have demonstrated the reliability and applicability of this approach by using a manually labelled dataset related to a devastating flood event in north-western Nigeria. Additionally, we have developed a land suitability model to evaluate potential areas for paddy rice cultivation. Our crop extent and land use/land cover classifications achieved an overall accuracy of between 93% and 95%, while our flood mapping achieved an overall accuracy of 99%. Our findings indicate that the flood event caused damage to almost 60% of the paddy rice fields. Based on the land suitability assessment, our results indicate that more land is suitable for cultivation during natural floods than is currently being used. We propose several recommendations as adaptation measures for stakeholders to improve livelihoods and mitigate flood disasters. This study highlights the importance of integrating multispectral and synthetic aperture radar (SAR) data for flood crop mapping using machine learning. Decision-makers will benefit from the flood crop mapping framework developed in this study in a number of spatial planning applications.

Blind Deblurring Method for CASEarth Multispectral Images Based on Inter-Band Gradient Similarity Prior.

Multispectral remote sensing images contain abundant information about the distribution and reflectance of ground objects, playing a crucial role in target detection, environmental monitoring, and resource exploration. However, due to the complexity of the imaging process in multispectral remote sensing, image blur is inevitable, and the blur kernel is typically unknown. In recent years, many researchers have focused on blind image deblurring, but most of these methods are based on single-band images. When applied to CASEarth satellite multispectral images, the spectral correlation is unutilized. To address this limitation, this paper proposes a novel approach that leverages the characteristics of multispectral data more effectively. We introduce an inter-band gradient similarity prior and incorporate it into the patch-wise minimal pixel (PMP)-based deblurring model. This approach aims to utilize the spectral correlation across bands to improve deblurring performance. A solution algorithm is established by combining the half-quadratic splitting method with alternating minimization. Subjectively, the final experiments on CASEarth multispectral images demonstrate that the proposed method offers good visual effects while enhancing edge sharpness. Objectively, our method leads to an average improvement in point sharpness by a factor of 1.6, an increase in edge strength level by a factor of 1.17, and an enhancement in RMS contrast by a factor of 1.11.

SSGAN: Cloud removal in satellite images using spatiospectral generative adversarial network

Satellite data’s reliability, uniformity, and global scanning capabilities have revolutionized agricultural monitoring and crop management. However, the presence of clouds in satellite images can obscure useful information, rendering them difficult to infer. Aiming at the problem of cloud cover, this study presents a SpatioSpectral Generative Adversarial Network (SSGAN) approach for effectively eliminating cloud cover from multispectral satellite images. It utilizes the Synthetic Aperture Radar (SAR) images as complementary information with the optical images from the Sentinel-2 satellite. The proposed model exploits feature extraction by sub-grouping the 13 channels of Sentinel-2 images based on their electromagnetic wavelength. Experimentally, we demonstrated that the proposed SSGAN model surpasses conventional and state-of-the-art (SOTA) methods and can reconstruct regions obscured by clouds. The subgrouping optimized the utilization of sensor information and improved the performance metrics for reconstructed images. Compared to the state-of-the-art (SOTA) approach, the SSGAN model demonstrates higher performance, achieving a mPSNR of 32.771, mSSIM of 0.880, and correlation coefficient (CC) of 0.889. The SSGAN model was further evaluated under varying conditions, including scenarios without the inclusion of SAR data, where it achieved a mPSNR of 26.825, mSSIM of 0.726, and CC of 0.615. Adding SAR images into the model significantly enhanced its performance, resulting in a mPSNR of 29.932, mSSIM of 0.857, and CC of 0.735. These results indicate that higher mPSNR, mSSIM, and CC values correspond to better image reconstruction quality. Our method enhances the usability of satellite data for crop mapping, crop health monitoring, and crop yield prediction.

Improving rapid flood impact assessment: An enhanced multi-sensor approach including a new flood mapping method based on Sentinel-2 data

Rapid flood impact assessment methods need complete and accurate flood maps to provide reliable information for disaster risk management, in particular for emergency response and recovery and reconstruction plans. With the aim of improving the rapid assessment of flood impacts, this work presents a new impact assessment method characterized by an enhanced satellite multi-sensor approach for flood mapping, which improves the characterization of the hazard. This includes a novel flood mapping method based on the new multi-temporal Modified Normalized Difference Water Index (MNDWI) that uses multi-temporal statistics computed on time-series of Sentinel-2 multi-spectral satellite images. The multi-temporal aspect of the MNDWI improves characterization of land cover over time and enhances the temporary flooded areas, which can be extracted through a thresholding technique, allowing the delineation of more precise and complete flood maps. The methodology, if implemented in cloud-based environments such as Google Earth Engine (GEE), is computationally light and robust, allowing the derivation of flood maps in matters of minutes, also for large areas.The flood mapping and impact assessment method has been applied to the seasonal flood occurred in South Sudan in 2020, using Sentinel-1, Sentinel-2 and PlanetScope satellite imagery. Flood impacts were assessed considering damages to buildings, roads, and cropland. The multi-sensor approach estimated an impact of 57.4 million USD (considering a middle-bound scenario), higher than what estimated by using Sentinel-1 data only, and Sentinel-2 data only (respectively 24% and 78% of the estimation resulting from the multi-sensor approach). This work highlights the effectiveness and importance of considering multi-source satellite data for flood mapping in a context of disaster risk management, to better inform disaster response, recovery and reconstruction plans.

Estimation of soil organic matter content by combining Zhuhai-1 hyperspectral and Sentinel-2A multispectral images

Hyperspectral satellite imagery has significant advantages in rapidly monitoring soil organic matter (SOM) content over a large area. However, limitations in the timely acquisition of site-specific data may affect its effectiveness due to weather influences and revisit cycles. This paper proposes a novel method for estimating SOM content that combines the high temporal resolution of the Zhuhai-1 hyperspectral satellite image and Sentinel-2A multispectral satellite image to broaden the spectral range of Zhuhai-1 images. Multisource features, including spectral bands, topographic features, textural features, and spectral indexes, are extracted from the combined image and digital elevation model. An improved genetic algorithm (IGA) is proposed to optimize feature selection and extreme gradient boosting (XGBoost) is then applied to estimate SOM content. The proposed method was validated using 197 topsoil samples and satellite images collected from a demonstration area in Lishu County, Jilin Province, China. The results indicate that the estimation accuracy using the combined image was greater than using one single image. Compared with only using the Sentinel-2A and Zhuhai-1 images, the coefficient of determination (R2) values improved from 0.61 and 0.73 to 0.82, the ratio of the prediction to the deviation (RPD) values improved from 1.62 and 1.93 to 2.35, and the ratio of performance to the interquartile distance (RPIQ) values improved from 2.16 and 2.58 to 3.15, respectively. Furthermore, the XGBoost algorithm outperformed the random forest algorithm in terms of model accuracy and mapping reliability. The use of multisource features improved the R2 value from 0.45 to 0.82 compared to only using 31 spectral bands of Zhuhai-1 and Sentinel-2A image, with contribution rates in descending order of spectral indexes (48.2%), topographic features (24.7%), spectral bands (19.9%), and textural features (7.2%). This paper thus presents a promising method for efficient periodic mapping of the SOM content by combining data from a hyperspectral satellite constellation and a multispectral satellite image.

Multi-Stage Feature Fusion of Multispectral and SAR Satellite Images for Seasonal Crop-Type Mapping at Regional Scale Using an Adapted 3D U-Net Model

Multi-Stage Feature Fusion of Multispectral and SAR Satellite Images for Seasonal Crop-Type Mapping at Regional Scale Using an Adapted 3D U-Net Model

Design and on-orbit performance evaluation of Ethiopian earth observation satellite multispectral optical imaging payload

The Ethiopian Earth observation micro-satellite was successfully launched into a sun-synchronous orbit equipped with an optical multispectral imaging payload system. This optical multispectral imaging payload camera weighs 1.4 kg with four spectral bands: RGB and NIR, each having a unique spectral range. Furthermore, it has a field of view of 7.4°×0.3°, a relative F-number of 9.8°, and a spectral range of 0.45∼0.9μm. The present article covers the design and on-orbit performance analysis of the ETRSS-1 electro-optical imaging payload system, which is based on the COTS compact and unobscured off-axis three-mirror anastigmatic system for high-resolution imaging. Additionally, selecting an appropriate imaging sensor, optomechanical architecture, and performance characteristics for optical instruments is investigated to evaluate spatial, spectral, and radiometric requirements and the payload’s on-orbit performance and capability.

Change detection using multispectral satellite images: a systematic review of literature

Change detection (CD) provides information about the changes on earth’s surface over a period of time. Many algorithms have been proposed over the years for effective CD of satellite imagery. This paper presents the steps to preprocess the captured satellite images, which can be used to perform predictive analysis of earth’s surface by CD techniques. To design a highly effective system for CD, it is recommended that algorithm designers select efficient algorithms from any given application. Thus, this paper presents and investigates the review of most appropriate literature on CD, where CD techniques have been presented into three groups; i) thresholding, ii) clustering, and iii) deep learning. The first two categories mainly rely on the traditional machine learning, whereas the last one exploits the state-of-the-art deep learning models. At the end, the standard methods are summarized based on advantages, limitation, and research gap.

Wide-Scale Identification of Small Woody Features of Landscape from Remote Sensing

Small landscape features (i.e., trees outside forest, small woody features) and linear vegetation such as hedgerows, riparian vegetation, and green lanes are vital ecological structures in agroecosystems, enhancing the biodiversity, landscape diversity, and protecting water bodies. Therefore, their monitoring is fundamental to assessing a specific territory’s arrangement and verifying the effectiveness of strategies and financial measures activated at the local or European scale. The size of these elements and territorial distribution make their identification extremely complex without specific survey campaigns; in particular, remote monitoring requires data of considerable resolution and, therefore, is very costly. This paper proposes a methodology to map these features using a combination of open-source or low-cost high-resolution orthophotos (RGB), which are typically available to local administrators and are object-oriented classification methods. Additionally, multispectral satellite images from the Sentinel-2 platform were utilized to further characterize the identified elements. The produced map, compared with the other existing layers, provided better results than other maps at the European scale. Therefore, the developed method is highly effective for the remote and wide-scale assessment of SWFs, making it a crucial tool for defining and monitoring development policies in rural environments.

Understanding impact of urban sprawl over sanitation risks using GIS‐based multicriteria decision‐making approach

AbstractUrban sprawl and the shortage of proper sanitary infrastructures significantly jeopardize public health and urban sustainability. The problem is further aggravated as a result of the rapid urbanization and urban sprawl. This study investigated the relationship between urban sprawl and sanitation risk conditions in a rapidly growing city in India. This was accomplished by investigating changes in urban sprawl areas between the periods 2000–2020 using multispectral satellite images and Shanon's entropy model and studying the pattern of spatial variations in basic sanitation services derived from the 100 household‐based surveyed WASH (water availability, sanitation, and hygiene) data collected in 2018 before COVID‐19 from 45 sprawl regions. Spatial statistical techniques, namely, the inverse distance weighted (IDW) interpolation and the multicriteria decision technique, were employed for neighborhood analysis and assessing sanitation risks inside the sprawl region. Results showed that Raipur exhibited urban sprawl and around 93.68% of the sprawl area was classified between high (6.47%)‐ and medium (80.52%)‐risk zones.

Developing a novel index for detection of optically shallow waters using multispectral satellite imagery and radiative transfer modelling

ABSTRACT Optical remote sensing of water quality has been problematic due to contamination of remote sensing observations by the sea-bottom effect over complex shallow or very clear waters. This has resulted in providing misleading information on the estimation of Water Constituent Concentrations (WCCs) retrieved from satellite images. In this research, we used Radiative Transfer (RT) Modelling to develop a simple and innovative index named the Sea-Bottom Effect Index (SEBEI) to readily determine water pixels contaminated by the sea-bottom effect, (hereafter named Optically Shallow Waters, (OSWs)) from remote sensing observations. To define the SEBEI, we initially assessed the influence of the sea-bottom on simulated water-leaving reflectance (R rs ) using RT Water-Sea-Bottom (WSB) modelling. This evaluation encompassed a range of water depths, seabed albedos, and WCCs (i.e. Chlorophyll-a (Chla) and Suspended Particulate Matter (SPM)). Next, we detected the most sensitive wavelengths (i.e. 750 nm, 810 nm, and 900 nm) to the seabed contribution on the simulated R rs spectra at the water surface level and developed the SEBEI. We validated the accuracy of the proposed SEBEI over a time series of MEdium Resolution Imaging Spectrometer (MERIS) and Ocean and Land Colour Instrument (OLCI) images captured during low and high tidal phases over shallow waters of the Dutch Wadden Sea, the Netherlands. The results indicate that the SEBEI effectively distinguishes between OSWs and Optically Deep Waters (ODWs) using satellite images (with an R2 value of ≥ 0.97 and a Root Mean Square Error (RMSE) of ≤ 0.65). The SEBEI can serve as an intermediate solution for detecting OSWs in multispectral and hyperspectral satellite images worldwide. It eliminates the need for ancillary datasets like bathymetry maps and significantly enhances the reliability of WCC maps produced over complex shallow coastal waters.

Using Multi-Source National Forest Inventory Data for the Prediction of Tree Lists of Individual Stands for Long-Term Simulation

Forest resource maps and small area estimates have been produced by combining national forest inventory (NFI) field plot data, multispectral satellite images and numerical map data. We evaluated k-nearest neighbors (k-NN) method-based predictions of forest variables for pixels in predicting tree lists of individual stands, including tree diameters at breast height and tree heights and then calculated stem volumes and tree species proportions. We compared alternative parameters (k-NN) using k of either 1 or 5 according to preliminary plot-level study and applying either measured trees (1-NN_trees) or mean stand characteristics (k-NN_stand). In the 1-NN_trees method, a tree list was generated based on the measured trees of the NFI plots, whereas in the 1-NN_stand and 5-NN_stand methods, a Weibull-based diameter distribution was recovered from the stand characteristics of the same inventory plots. In both methods, tree lists were predicted for each 16 m × 16 m pixel included in the stand compartment. Both methods performed well and resulted in 8–14% differences in the total volume compared with the field inventory of the 27 stands used for the evaluation. Moreover, the main tree species was correctly predicted for 74% of cases. The RMSE in total volume ranged from 25% (5-NN_stand) to 31% (1-NN_stand), while the smallest RMSEs in volume by tree species were 61% for broadleaves and 65% for pine and spruce using the 5-NN_stand. When comparing input data for a long-term growth simulation, the choice of the method was less influential as the effect of the error in the initial stand characteristics decreased over time during the simulation period. After 30-year simulation of the inventoried stands, the respective RMSEs were 9.4% for total volume and 39%, 50% and 59% for tree species, respectively. The satellite-based data with NFI plots were useful for predicting tree lists for pixels of a stand. However, the accuracy for operational forest management was still questionable. For a larger area’s strategic information, the accuracy is considered adequate.

RDC-UNet++: An end-to-end network for multispectral satellite image enhancement

Multi-spectral satellite imagery is an ideal data source for comprehensive, real-time Earth observation (EO) due to its extensive coverage of Earth and regular updates. It has a wide range of applications in environment monitoring, disaster management, urban planning, weather forecasting etc. Yet, the visual aspect of these images and thus the possibility to extract useful information using image processing techniques is often degraded due to fog, rain, dust, cloud, etc. Satellite image enhancement denotes a set of techniques designed to improve the quality of a satellite image such that the result is more useful for image analysis. The image enhancement aims to improve the quality of an image such that the enhanced image is more useful for image analysis than the original image for a particular remote sensing application. This study introduces a multi-spectral satellite image enhancement architecture called Residual Dense Connection-based UNet++ (RDC-UNet++). The unique design can improve multi-spectral images by enhancing their color and texture details. Extensive experimental studies on multi-spectral image datasets containing more than 150 images prove that the proposed architecture performs better than recent state-of-the-art satellite image enhancement algorithms.

Integrating Depth Measurements From Gaging Stations With Image Archives for Spectrally Based Remote Sensing of River Bathymetry

AbstractRemote sensing can be an effective tool for mapping river bathymetry, but the need for direct measurements to calibrate image‐derived depth estimates impedes broader application of this approach. One way to circumvent the need for field campaigns dedicated to calibration is to capitalize upon existing data. In this study, we introduce a framework for Bathymetric Mapping using Gage Records and Image Databases (BaMGRID). This workflow involves retrieving depth measurements made during gaging station site visits, downloading archived multispectral images, and then combining these two data sets to establish a relationship between depth and reflectance. We developed a processing chain that involves using application programming interfaces to obtain both depth measurements made during site visits and images centered on the gage and then linking depth to reflectance via an optimal band ratio analysis (OBRA) algorithm modified for small sample sizes. Applying this workflow to selected gages within two river basins indicated that depth retrieval from multispectral satellite images could be highly accurate, but with variable results from one image to the next at a given site. High resolution aerial photography was less conducive to bathymetric mapping in one of the basin considered. Of the four predictors of depth retrieval performance we evaluated (mean and standard deviation of depth, width, and an index of water clarity), only width was consistently significantly correlated with OBRA R2 (p < 0.026). Currently, BaMGRID is best‐suited for site‐by‐site analysis to support practical applications at the reach scale; continuous, basin‐wide mapping of river bathymetry will require additional research.

Application of Remote Sensing for Identifying Soil Erosion Processes on a Regional Scale: An Innovative Approach to Enhance the Erosion Potential Model

Soil erosion represents a complex ecological issue that is present on a global level, with negative consequences for environmental quality, the conservation and availability of natural resources, population safety, and material security, both in rural and urban areas. To mitigate the harmful effects of soil erosion, a soil erosion map can be created. Broadly applied in the Balkan Peninsula region (Serbia, Bosnia and Herzegovina, Croatia, Slovenia, Montenegro, North Macedonia, Romania, Bulgaria, and Greece), the Erosion Potential Method (EPM) is an empirical erosion model that is widely applied in the process of creating soil erosion maps. In this study, an innovation in the process of the identification and mapping of erosion processes was made, creating a coefficient of the types and extent of erosion and slumps (φ), representing one of the most sensitive parameters in the EPM. The process of creating the coefficient (φ) consisted of applying remote sensing methods and satellite images from a Landsat mission. The research area for which the satellite images were obtained and thematic maps of erosion processes (coefficient φ) were created is the area of the Federation of Bosnia and Herzegovina and the Brčko District (situated in Bosnia and Herzegovina). The Google Earth Engine (GEE) platform was employed to process and retrieve Landsat 7 Enhanced Thematic Mapper plus (ETM+) and Landsat 8 Operational Land Imager and Thermal Infrared Sensor (OLI/TIRS) satellite imagery over a period of ten years (from 1 January 2010 to 31 December 2020). The mapping and identification of erosion processes were performed based on the Bare Soil Index (BSI) and by applying the equation for fractional bare soil cover. The spatial–temporal distribution of fractional bare soil cover enabled the definition of coefficient (φ) values in the field. An accuracy assessment was conducted based on 190 reference samples from the field using a confusion matrix, overall accuracy (OA), user accuracy (UA), producer accuracy (PA), and the Kappa statistic. Using the confusion matrix, an OA of 85.79% was obtained, while UA ranged from 33% to 100%, and PA ranged from 50% to 100%. Applying the Kappa statistic, an accuracy of 0.82 was obtained, indicating a high level of accuracy. The availability of a time series of multispectral satellite images for each month is a crucial element in monitoring the occurrence of erosion processes of various types (surface, mixed, and deep) in the field. Additionally, it contributes significantly to decision-making, strategies, and plans in the domain of erosion control work, the development of plans for identifying erosion-prone areas, plans for defense against torrential floods, and the creation of soil erosion maps at local, regional, and national levels.

Synthesis and evaluation of seamless, large-scale, multispectral satellite images using Generative Adversarial Networks on land use and land cover and Sentinel-2 data

ABSTRACT Artificial intelligence (AI) began to make its way into geoinformation science several decades ago and since then has constantly brought forth new cutting-edge approaches for diverse geographic use cases. AI and deep learning methods have become essential approaches for land use and land cover (LULC) classifications, which are important in urban planning and regional management. While the extraction of LULC information from multispectral satellite images has been a well-studied part of past and present research, only a few studies emerged about the recovery of spectral properties from LULC information. Estimates of the spectral characteristics of LULC categories could enrich LULC forecasting models by providing necessary information to delineate vegetation indices or microclimatic parameters. We train two identical Conditional Generative Adversarial Networks (CGAN) to synthesize a multispectral Sentinel-2 image based on different combinations of open-source LULC data sets. Large-scale synthetic multispectral satellite images of the administrative region of Bonn and Rhein-Sieg in Germany are generated with a Euclidean distance-based patch-fusion method. The approach generated a realistic-looking satellite image without noticeable seams between patch borders. Based on several metrics, such as difference calculations, the spectral information divergence (SID), and the Fréchet inception distance (FID), we evaluate the resulting images. The models reach mean SIDs as low as 0.026 for urban fabrics and forests and FIDs below 90 for bands B2 and B5 showing that the CGAN is capable of synthesizing distinct synthetic features matching with features typical for respective LULC categories and manages to mimic multispectral signatures. The method used in this paper to generate large-scale synthetic multispectral satellite images can be used as an approach to support scenario-oriented sustainable urban planning.

MFPANet: Multi-Scale Feature Perception and Aggregation Network for High-Resolution Snow Depth Estimation

Accurate snow depth estimation is of significant importance, particularly for preventing avalanche disasters and predicting flood seasons. The predominant approaches for such snow depth estimation, based on deep learning methods, typically rely on passive microwave remote sensing data. However, due to the low resolution of passive microwave remote sensing data, it often results in low-accuracy outcomes, posing considerable limitations in application. To further improve the accuracy of snow depth estimation, in this paper, we used active microwave remote sensing data. We fused multi-spectral optical satellite images, synthetic aperture radar (SAR) images and land cover distribution images to generate a snow remote sensing dataset (SRSD). It is a first-of-its-kind dataset that includes active microwave remote sensing images in high-latitude regions of Asia. Using these novel data, we proposed a multi-scale feature perception and aggregation neural network (MFPANet) that focuses on improving feature extraction from multi-source images. Our systematic analysis reveals that the proposed approach is not only robust but also achieves high accuracy in snow depth estimation compared to existing state-of-the-art methods, with RMSE of 0.360 and with MAE of 0.128. Finally, we selected several representative areas in our study region and applied our method to map snow depth distribution, demonstrating its broad application prospects.

АНАЛІЗ МЕТОДІВ ЗНАХОДЖЕННЯ АНОМАЛІЙ У ЗОБРАЖЕННЯХ

Abstract. Automatic anomaly detection is of great importance in industry, remote sensing, and medicine. It is important to be able to automatically process large amounts of data to detect, for example, chemical objects in multispectral and hyperspectral satellite images, sea mines in side-scan sonar images, or defects in industrial monitoring applications. Automatic detection of anomalous structures on arbitrary images refers to the task of finding inappropriate patterns relative to the normal state of the image. This is a difficult task in computer vision, since there is no clear and straightforward definition of what is normal or not normal for a given arbitrary image. The practical importance is manifested in the development of algorithms and models that can automatically detect unusual or anomalous patterns in images. An analysis of methods for finding anomalies in images from the point of view of the possibility of application to arbitrary images has been carried out. The classification of anomaly detection methods according to the criteria of the involved approaches and models used for modeling the background is presented. Methods that use machine learning, such as one-class support vector method and variational autoencoder, nearest neighbor-based anomaly detection, clustering-based anomaly detection, statistical anomaly detection, spectral anomaly detection, anomaly detection using information theory are discussed. The main attention is paid to the methods classified according to the background modeling approach. Five categories of background modeling methods based on probability density function, global and local homogeneity, sparsity, and self-similarity are considered. For anomaly detection applications, it is recommended to use methods in which the background model best describes the expected anomaly-free background, as this generally results in the best performance. On the basis of research, it was established that an effective universal model for detecting anomalies in arbitrary images should: use only a self-similar or sparse background model; process the residual image as a stochastic process to detect anomalies, such as anomalies in color noise; preprocess the residual image before detecting the anomaly.