Visual Interpretation Method Research Articles

Analysis of spatiotemporal evolution characteristics and recovery patterns of mangrove forests in China since 1978

Mangrove ecosystems have garnered significant attention for their pivotal role in the global carbon cycle and their contributions to multiple UN Sustainable Development Goals. In China, the strategic pivot towards comprehensive ecological restoration in mangrove management underscores an urgent need for a nuanced understanding of mangrove evolutionary patterns. However, existing remote sensing-based information on mangrove dynamics exhibits discrepancies, lacking a cohesive and precise understanding. Accordingly, this study utilized high-resolution GaoFen imagery and precise visual interpretation methods to meticulously update an existing mangrove dataset through 2022, ensuring high accuracy and improved timeliness. Building on this, the study conducted a rigorous spatiotemporal analysis of mangrove dynamics from 1978 to 2022, developed an index to assess recovery status, and ultimately proposed targeted recommendations for conservation and restoration. Findings reveal that between 2018 and 2022, China’s mangrove expanse witnessed an average annual net increase of 2.82%, marking an unprecedented high. Breaking down the net change, the rate of gain accelerated, averaging 878.63 ha per year, but it is noteworthy that the losses also increased rapidly, tripling that of the previous period, mainly in regions with intense human activities such as the Pearl River Estuary. This finding complements the general perception of a continuous net increase in mangrove areas, highlighting the paradox of significant contraction occurring alongside rapid expansion. Additionally, by 2022, mangrove extent had recovered to 28,641 ha, essentially returning to the 1978 level, yet characterized by poor stability and significant spatial heterogeneity, with Guangdong and Hainan exhibiting recovery indices below the average. The study emphasizes that the ecosystem’s intrinsic restorative capabilities have emerged as a critical factor in offsetting losses and signaling a positive trend. The latest data provided by this study can offer actionable insights and support for mangrove conservation and restoration initiatives, serving the goal of ecosystem recovery and affirming their indispensable role in environmental governance.

Characteristics and Correlation Study of Mountainous Lake Ice Phenology Changes in Xinjiang, China Based on Passive Microwave Remote Sensing Data

Lake ice phenology directly reflects local climate changes, serving as a key indicator of climate change. In today’s rapidly evolving climate, utilizing advanced remote sensing techniques to quickly extract long-term lake ice phenology features and studying their correlation with other climate factors is crucial. This study focuses on lakes in Xinjiang, China, with a mountainous area greater than 100 km2, including Sayram Lake, Ayahkum Lake, Achihkul Lake, Jingyu Lake, and Ahsaykan Lake. The Bayesian ensemble change detection algorithm was employed to extract lake ice phenology information, and the Mann–Kendall (MK) non-parametric test was used to analyze trends. The visual interpretation method was used to interpret the spatial evolution characteristics of lake ice, and the Pearson correlation coefficient was used to explore the driving factors of lake ice phenology. Results indicate the following: (1) Jingyu Lake exhibited the most significant delay in both freezing and complete freezing days, while Ayahkum Lake showed the most stable pattern. Ahsaykan Lake demonstrated the least delay in both starting and complete melting days. (2) Sayram Lake’s ice evolution was unstable, with wind causing variability in the locations where freezing begins and melting spreading from the west shore. Ayahkum Lake, Ahsaykan Lake, and Jingyu Lake exhibited similar seasonal variations, while Achihkul Lake’s ice spatial changes spread from the east to the center during freezing and from the center to the shore during melting. (3) The study found that the freeze–thaw process is influenced by a combination of factors including lake area, precipitation, wind speed, and temperature.

Mangroves Invaded by Spartina alterniflora Loisel: A Remote Sensing-Based Comparison for Two Protected Areas in China

Mangroves are one of the world’s most productive and ecologically important ecosystems, and they are threatened by the widespread invasion of Spartina alterniflora Loisel in China. As few studies have examined the spatial pattern differences of S. alterniflora invasion and the nearby mangroves in different latitudes, we chose the Zhangjiang Estuary and the Dandou Sea, two representative mangrove–salt marsh ecotones in the north and south of the Tropic of Cancer, as the study areas for comparison. The object-based image analysis and visual interpretation methods were combined to construct fine-scale mangrove and S. alterniflora maps using high-resolution satellite imagery from 2005 to 2019. We applied spatial analysis, centroid migration, and landscape indexes to analyze the spatio–temporal distribution changes of mangroves and S. alterniflora in these two ecotones over time. We used the landscape expansion index to investigate the S. alterniflora invasion process and expansion patterns. The annual change rates of mangrove and S. alterniflora areas in the Zhangjiang Estuary showed a continuous growth trend. However, the mangrove areas in the Dandou Sea showed a fluctuating trend of increasing, decreasing, and then increasing again, while S. alterniflora areas kept rising from 2005 to 2019. Spartina alterniflora showed larger annual change rates compared with mangroves, indicating rapid S. alterniflora invasion in the intertidal zones. The opposite centroid migration directions of mangroves and S. alterniflora and the decreasing distances between the mangrove and S. alterniflora centroids indirectly revealed the fierce competition between mangroves and S. alterniflora for habitat resources. Both regions saw a decrease in mangrove patch integrality and connectivity. The integrality of mangrove patches in the Zhangjiang Estuary was always higher than those in the Dandou Sea. We observed the growth stage (2011–2014) and outbreak stage (2014–2019) of S. alterniflora expansion in the Zhangjiang Estuary and the outbreak stage (2005–2009) and plateau stage (2009–2019) of S. alterniflora expansion in the Dandou Sea. The expansion pattern of S. alterniflora varies in time and place. Since the expansion of S. alterniflora in the outbreak stage is rapid, with a large annual change rate, early warning of S. alterniflora invasion is quite important for the efficient and economical removal of the invasive plant. Continuous and accurate monitoring of S. alterniflora is highly necessary and beneficial for the scientific management and sustainable development of coastal wetlands.

Study of the patterns of ice lake variation and the factors influencing these changes in the western Nyingchi area

Abstract The current ice lake dataset in the western region of Nyingchi requires further improvement. Due to the intricate distribution of ice lakes and imprecise boundary delineation, research tends to overlook small-scale ice lakes in this area. Moreover, most related studies have focused solely on variations in ice lake areas within key regions, such as the Himalayas, with little attention given to changes occurring in southeastern Tibet. The frequency of ice and snow disasters in the study area has been steadily increasing over the years. Therefore, this study utilizes Landsat satellite images and employs visual interpretation methods to generate more precise and comprehensive maps depicting the distribution of ice lakes in the western region of Nyingchi Province for the years 1994, 2010, 2018, and 2022. Additionally, changes in scale and spatial patterns of different types of ice lakes were investigated. Between 1994 and 2022, the ice lake area in the study area significantly increased by 22.5%, reaching a total of 35.8 ± 3.0 km2. This expansion was primarily driven by glacier-fed lakes, which experienced a remarkable growth rate of 30.8%. In contrast, the non-glacier-fed lakes experienced an increase by only 15.6%. Notably, ice lakes at higher elevations exhibited a peak in expansion, with those above 5143.0 m experiencing the most substantial growth rate of 44.8%. The long-term expansion rate of ice lakes is investigated through the measurement of changes in their boundaries, with the aim to understand the factors contributing to their growth. These findings indicate the rapid expansion of the ice lake near the glacier, with an annual growth rate of 1.3% per annum. Specifically, the glacial-fed section exhibited an expansion rate of 1.1% per annum, while the nonglacial-fed section experienced a growth rate of 0.6% per annum. The seasonal variability in marine glaciers is the primary factor influencing the expansion of ice lakes in this region, with temperature and precipitation serving as the principal driving forces impacting the transformation of these lakes. The data provided by the research results will facilitate a comprehensive understanding of the dynamics and mechanisms governing the ice lake in western Nyingchi, thereby contributing to an enhanced scientific comprehension of potential disaster risks associated with this ice lake.

Establishing a Landslide Traces Inventory for the Baota District, Yan’an City, China, Using High-Resolution Satellite Images

The Baota District of Yan’an City, located in the Loess Plateau, is an important patriotic education base in China. The region’s fragile geological environment and frequent geological disasters pose significant threats to the production and livelihood of residents. Establishing a landslide traces inventory can provide crucial assistance for studying regional land disaster distribution patterns and implementing disaster prevention and mitigation measures. However, the Baota District has not yet established a comprehensive and detailed landslide traces inventory, resulting in a lack of clear understanding and comprehensive knowledge regarding the threats and impacts of landslide disasters in the area. Therefore, this study employed high-resolution satellite images, applying a human–computer interactive visual interpretation method in conjunction with field survey verifications, to develop the most detailed and comprehensive landslide traces inventory for the Baota District to date. The results indicate that within the 3556 km2 area of the Baota District, there are 73,324 landslide traces, with an average landslide density of 20.62 km-2 and a total landslide area of 769.12 km2, accounting for 21.63% of the total land area. These landslides are relatively evenly distributed throughout the district, with a higher concentration in the east compared to the west. Most of the landslides are small in size. This study can support disaster prevention and mitigation efforts in the Baota District and serve as a reference for establishing landslide inventories in other regions of the Loess Plateau.

Detailed Landslide Traces Database of Hancheng County, China, Based on High-Resolution Satellite Images Available on the Google Earth Platform

Hancheng is located in the eastern part of China’s Shaanxi Province, near the west bank of the Yellow River. It is located at the junction of the active geological structure area. The rock layer is relatively fragmented, and landslide disasters are frequent. The occurrence of landslide disasters often causes a large number of casualties along with economic losses in the local area, seriously restricting local economic development. Although risk assessment and deformation mechanism analysis for single landslides have been performed for landslide disasters in the Hancheng area, this area lacks a landslide traces database. A complete landslide database comprises the basic data required for the study of landslide disasters and is an important requirement for subsequent landslide-related research. Therefore, this study used multi-temporal high-resolution optical images and human-computer interaction visual interpretation methods of the Google Earth platform to construct a landslide traces database in Hancheng County. The results showed that at least 6785 landslides had occurred in the study area. The total area of the landslides was about 95.38 km2, accounting for 5.88% of the study area. The average landslide area was 1406.04 m2, the largest landslide area was 377,841 m2, and the smallest landslide area was 202.96 m2. The results of this study provides an important basis for understanding the spatial distribution of landslides in Hancheng County, the evaluation of landslide susceptibility, and local disaster prevention and mitigation work.

Fault diagnosis for cross-building energy systems based on transfer learning and model interpretation

Timely and accurate fault diagnosis in building energy systems is crucial for improving the energy efficiency of equipment and realizing energy savings. With the widespread use of building automation systems, data-driven deep-learning fault diagnosis methods have gained popularity due to their flexibility and accuracy. However, they have certain associated challenges, such as limited extrapolation capabilities and their black-box nature. To address these issues, this study focuses on transfer learning to improve the energy efficiency of building energy system equipment, exploring the influencing factors and behaviours of transfer learning fault diagnosis performance and model interpretation results. A transfer-learning strategy is employed, utilizing feature-level SHAP and visual interpretation methods to understand the inner workings and diagnostic mechanisms of transfer-learning models. The study constructs five transfer-learning strategies for two typical building energy systems. The results demonstrate that the proposed fine-tuning approach achieves the highest accuracy, of 94.32 %, surpassing non-transferred and shallow approaches. The interpreted methods reflect the joint diagnosis of refrigerant leakage faults by compressor discharge temperature and condenser inlet and outlet water temperature in the target chiller. The findings from both the transfer mechanism and interpretation of the deep-learning model provide valuable guidance for the development of practical deep transfer-learning models and corresponding interpretation methods. This research contributes to improving fault diagnosis accuracy and understanding the diagnostic mechanisms in building energy systems, ultimately leading to enhanced energy efficiency and energy savings.

2020–2022年环渤海地区8 m分辨率露天采矿区空间分布数据集

With the increase of mining activities in China, the ecological environment around mines is facing unprecedented pressure, leading to a series of resource, ecological and environmental problems, such as air pollution, soil erosion, solid waste pollution, landslides and debris flows. To precisely obtain the spatial distribution data of open-pit mining, scholars and regulatory bodies are actively seeking timely and efficient methods to monitor open-pit mining areas by using the remote sensing, an innovative technology, for this purpose. In this research, we adopted high-resolution optical remote sensing image GF-6 with a resolution of 8m to obtain the open-pit mining dataset in the Bohai Rim through rule-based feature extraction, time-series image discrimination and visual interpretation methods, covering over 8000 open-pit mining areas. The dataset exhibits a high level of accuracy, with an overall accuracy of 95.0%, a producer accuracy of 98.0% and a user accuracy of 92.4%. It effectively reflects the spatial dynamics in the distribution of open-pit mining areas within the Bohai Rim region and reveals the influence of economic growth and policy-making on these changes. Thus, the dataset can offer valuable data support for managing open-pit mining operations and the development of related policies.

Deep-Learning-Based Automatic Extraction of Aquatic Vegetation from Sentinel-2 Images—A Case Study of Lake Honghu

Aquatic vegetation is an important component of aquatic ecosystems; therefore, the classification and mapping of aquatic vegetation is an important aspect of lake management. Currently, the decision tree (DT) classification method based on spectral indices has been widely used in the extraction of aquatic vegetation data, but the disadvantage of this method is that it is difficult to fix the threshold value, which, in turn, affects the automatic classification effect. In this study, Sentinel-2 MSI data were used to produce a sample set (about 930 samples) of aquatic vegetation in four inland lakes (Lake Taihu, Lake Caohai, Lake Honghu, and Lake Dongtinghu) using the visual interpretation method, including emergent, floating-leaved, and submerged vegetation. Based on this sample set, a DL model (Res-U-Net) was used to train an automatic aquatic vegetation extraction model. The DL model achieved a higher overall accuracy, relevant error, and kappa coefficient (90%, 8.18%, and 0.86, respectively) compared to the DT method (79%, 23.07%, and 0.77) and random forest (78%,10.62% and 0.77) when utilizing visual interpretation results as the ground truth. When utilizing measured point data as the ground truth, the DL model exhibited accuracies of 59%, 78%, and 91% for submerged, floating-leaved, and emergent vegetation, respectively. In addition, the model still maintains good recognition in the presence of clouds with the influence of water bloom. When applying the model to Lake Honghu from January 2017 to October 2023, the obtained temporal variation patterns in the aquatic vegetation were consistent with other studies. The study in this paper shows that the proposed DL model has good application potential for extracting aquatic vegetation data.

Formation of the Environmental and Economic Orientation of the Individual for the Purpose of Sustainable Development of Territories

Public awareness of the global problems of our time that impede the harmonious development of society is reflected in the social, economic and environmental spheres. Identification of factors and assessment of their influence on the sustainable development of the region is the key to solving the problem of developing theoretical and methodological foundations for the formation of an individual’s environmental and economic orientation, which presupposes the presence of relevant needs and interests, along with motives, goals and beliefs that guide a person’s behavior and activities in within the framework of ecological-economic balance. The purpose of the study is to assess the influence of objective factors on the formation of environmental and economic needs and interests of a person as the basis for the environmental and economic orientation of an individual. When studying the problem of identifying and assessing the socio-ecological-economic factors of sustainable development of the region, the authors used strategic analysis, integrated methods of special theories — development modeling, and used methods of visual interpretation of research results. An assessment was made of the influence of socio-ecological-economic factors in the regions of the Ural macrozone on the formation of the environmental-economic orientation of behavior. The regions united in the macrozone demonstrate an asymmetry in the conditions of their development, in which points of regional competitiveness are formed, which have the greatest potential for the formation of an environmental-economic orientation, ensuring the adoption of management decisions within the framework of socio-ecological-economic balance. Options for the manifestation of contradictions that influence the degree of formation of an individual’s environmental-economic orientation are presented; connections between levels (strategic, operational, discretionary), objects and management tools are developed to minimize socio-ecological-economic contradictions.

Remote Sensing Identification and Spatiotemporal Change Analysis of Cladophora with Different Morphologies

Cladophora qinghaiensis, an endemic species of Cladophora in saltwater lakes, was scientifically named in 2021 (hereafter referred to as Cladophora). Cladophora exists in different morphologies, including attached submerged Cladophora (AC), grown floating Cladophora (GFC), and death floating Cladophora (DFC). Previous satellite remote sensing has mainly focused on identifying floating algae. In this study, Qinghai Lake served as a case study, and a classification decision tree model (CDTM) was proposed. The model employed the chlorophyll spectral index (CSI) and the normalized difference vegetation index (NDVI) to differentiate AC, Floating Cladophora (FC), and water. Additionally, the floating Cladophora index (FCI) was introduced to further distinguish GFC and DFC within FC. The method was applicable to Sentinel-2 images from 2016–2023. Visual interpretation methods were used for Landsat series images from the summer months (July to September) to obtain the AC and FC. The results demonstrate that over the past 30 years, the areas inhabited by AC and FC have increased gradually. The three morphologies of Cladophora also exhibited seasonal variations, with growth observed annually in May–June, reaching peaks in August–September, and gradually declining in October. In addition, by combining factors such as water surface area and climatic factors, we analyzed the driving forces influencing the changes in Cladophora. In this research, AC and FC showed significant correlations with the water surface area, with correlation coefficients (r) of approximately 0.9 and 0.7, respectively. These new findings provide valuable insights regarding the spatiotemporal changes and underlying causes for different morphologies of Cladophora in global saline lakes.

Spatial Mapping of Coconut Plantation in Airmadidi District, North Sulawesi Using Geographical Information System

Coconut (Cocos nucifera L.) known by many as the "tree of life is a leading agricultural commodity in North Sulawesi. Coconut is one of the most significant palm crops for both commercial and subsistence use worldwide. Airmadidi District has the potential for plantation land, especially coconut, which is indicated by the area of ??coconut plantation land in Airmadidi in 2021 of 3,373.13 Ha. This research aims to produce spatial mapping of coconut plantation in Airmadidi District using visual interpretation techniques; and to determine the area of ??coconut plantations in Airmadidi District. Visual interpretation method using on screen classification of satelite imagery SPOT 2022 obtained from SAS Planet. Images were digitized with a geographic information system using ArcGIS 10.8.2 software. The results of the visual interpretation show a map of the distribution of coconut plantations spread across all villages in Airmadidi District, North Minahasa Regency. The total area of coconut plantations in Airmadidi District is 3 023 Ha. Tanggari village has the largest spread of coconut plantations, namely 870,460 Ha, while Sarongsong Satu village has the smallest area, only 2.24 Ha. There was a decrease in the area of coconut plantation during the period of three year which was 305,51 Ha. The decline in the area of coconut plantations in North Sulawesi, especially in Airmadidi District, is thought to be caused by the conversion of coconut plantation land into residential or industrial areas.

Attribution Analysis on Areal Change of Main Wetland and Its Influence on Runoff in the Naolihe River Basin

Wetlands have powerful runoff regulation functions, which can effectively store and retain surface runoff. The runoff regulation function of wetlands is affected by wetland areas, which affect the capacity of flood control. To explore the law of the area change of the main wetlands of the Naolihe River Basin (MWNRB), the visual interpretation method was used to extract wetlands. To identify the reasons for area changes in the MWNRB, the maximum likelihood method, minimum distance method, and neural network method were used to classify land use types from remote sensing images; the M-K variation point test and Theil-Sen trend analysis were used to test the variation point and calculate the trend of precipitation and temperature series. To clarify the influence of wetland areas on runoff, the Gini coefficient and SRI of runoff were used to calculate runoff temporal inhomogeneity. The results showed that the area of the MWNRB obviously decreased, with 74.5 × 106 m2/year from 1993 to 2008, and increased slowly from 2008 to 2015, with 27.7 × 106 m2/year. From 1993 to 2008, 50.74% and 38.87% of wetlands were transformed into paddy fields and dry fields, respectively. From 2008 to 2015, 61.69% and 7.76% of wetlands were transformed from paddy fields and dry fields, respectively. The temperature of the MWNRB increased slowly by 0.04 °C/year from 1993 to 2008 and increased obviously by 0.16 °C/year from 2008 to 2015. The precipitation decreased by 5.6–8.1 mm/year and increased by 16.6–41.2 mm/year in 1993–2008 and 2008–2015, respectively. Compared with precipitation and temperature, land use change caused by human activities is the main cause of wetland area change. The area change of the MWNRB has a certain influence on the runoff regulation and storage capacity. The Gini coefficient and SRI index increased from 0.002/year (0.008) to 0.023/year from 1993 to 2008 and decreased from 0.046/year (0.045) to 0.161/year from 2008 to 2015, respectively.

Clinical and biomarker characteristics of amnestic MCI patients exhibiting a temporo‐limbic FDG‐PET pattern suggestive of LATE

AbstractBackgroundWe have recently described a specific temporo‐limbic FDG‐PET signature that characterizes autopsy‐confirmed cases with limbic age‐related TDP‐43 encephalopathy (LATE), and have demonstrated its clinical utility for differential diagnosis of amnestic dementia patients. Here we assessed the utility of this pattern for patient stratification at a predementia disease stage, and further used tau‐PET data to study the degree to which this “LATE‐specific” FDG‐PET signature may correspond to a limbic‐predominant AD subtype.MethodIndividual FDG‐PET scans of 909 amnestic MCI (aMCI) patients from the ADNI cohort were screened for hypometabolic patterns being suggestive of LATE (sLATE) or typical AD (sAD) using automated pattern‐matching to autopsy‐confirmed pathology‐specific FDG‐PET signatures. sLATE and sAD patients were compared on clinical features, APOE4 genotype, and CSF biomarkers. Tau‐PET scans ([18F]Flortaucipir) were available in a smaller subsample (30%) and were analyzed for tau‐positivity using an FDA‐approved visual interpretation method as well as entorhinal SUVR (positivity‐threshold: SUVR = 2.1).Result734 aMCI patients showed evidence of significant regional hypometabolism, and of these 92 had a pronounced temporo‐limbic hypometabolic pattern classified as sLATE, whereas 68 had a classical temporo‐parietal pattern classified as sAD(Fig‐1). Compared to sAD, sLATE patients had similar MMSE and memory scores but more preserved executive function scores, and they showed generally slower cognitive decline over follow‐up (p<0.001)(Fig‐2). They were also significantly older (d = 0.83, p = 0.01), less often APOE4 carriers (39% vs 64%, p<0.001), and had less abnormal CSF Aß42 (d = 0.60, p = 0.001) and p‐tau181 levels (d = ‐0.40, p = 0.01). With regards to tau‐PET, 9/30 sLATE (30%) and 9/10 sAD (90%) patients were visually positive and similar proportions were seen for entorhinal SUVR (40% vs 90%).ConclusionThe majority of amnestic MCI patients exhibiting a LATE‐typical temporo‐limbic FDG‐PET pattern show clinical and biomarker features that deviate from prodromal AD. A smaller subset of these patients shows elevated tau‐PET signal and could thus represent a limbic‐predominant AD subtype.

Clinical and biomarker characteristics of amnestic MCI patients exhibiting a temporo‐limbic FDG‐PET pattern suggestive of LATE

AbstractBackgroundWe have recently described a specific temporo‐limbic FDG‐PET signature that characterizes autopsy‐confirmed cases with limbic age‐related TDP‐43 encephalopathy (LATE), and have demonstrated its clinical utility for differential diagnosis of amnestic dementia patients. Here we assessed the utility of this pattern for patient stratification at a predementia disease stage, and further used tau‐PET data to study the degree to which this “LATE‐specific” FDG‐PET signature may correspond to a limbic‐predominant AD subtype.MethodIndividual FDG‐PET scans of 909 amnestic MCI (aMCI) patients from the ADNI cohort were screened for hypometabolic patterns being suggestive of LATE (sLATE) or typical AD (sAD) using automated pattern‐matching to autopsy‐confirmed pathology‐specific FDG‐PET signatures. sLATE and sAD patients were compared on clinical features, APOE4 genotype, and CSF biomarkers. Tau‐PET scans ([18F]Flortaucipir) were available in a smaller subsample (30%) and were analyzed for tau‐positivity using an FDA‐approved visual interpretation method as well as entorhinal SUVR (positivity‐threshold: SUVR≥2.1).Result734 aMCI patients showed evidence of significant regional hypometabolism, and of these 92 had a pronounced temporo‐limbic hypometabolic pattern classified as sLATE, whereas 68 had a classical temporo‐parietal pattern classified as sAD(Fig‐1). Compared to sAD, sLATE patients had similar MMSE and memory scores but more preserved executive function scores, and they showed generally slower cognitive decline over follow‐up (p<0.001)(Fig‐2). They were also significantly older (d = 0.83, p = 0.01), less often APOE4 carriers (39% vs 64%, p<0.001), and had less abnormal CSF Aβ42 (d = 0.60, p = 0.001) and p‐tau181 levels (d = ‐0.40, p = 0.01). With regards to tau‐PET, 9/30 sLATE (30%) and 9/10 sAD (90%) patients were visually positive and similar proportions were seen for entorhinal SUVR (40% vs 90%).ConclusionThe majority of amnestic MCI patients exhibiting a LATE‐typical temporo‐limbic FDG‐PET pattern show clinical and biomarker features that deviate from prodromal AD. A smaller subset of these patients shows elevated tau‐PET signal and could thus represent a limbic‐predominant AD subtype.

Augmented Grad-CAM++: Super-Resolution Saliency Maps for Visual Interpretation of Deep Neural Network

In recent years, deep neural networks have shown superior performance in various fields, but interpretability has always been the Achilles’ heel of deep neural networks. The existing visual interpretation methods for deep neural networks still suffer from inaccurate and insufficient target localization and low-resolution saliency maps. To address the above issues, this paper presents a saliency map generation method based on image geometry augmentation and super-resolution called augmented high-order gradient weighting class activation mapping (augmented grad-CAM++). Unlike previous approaches that rely on a single input image to generate saliency maps, this method first introduces the image geometry augmentation technique to create a set of augmented images for the input image and generate activation mappings separately. Secondly, the augmented activation mappings are combined to form the final saliency map. Finally, a super-resolution technique is introduced to add pixel points to reconstruct the saliency map pixels to improve the resolution of the saliency map. The proposed method is applied to analyze standard image data and industrial surface defect images. The results indicate that, in experiments conducted on standard image data, the proposed method achieved a 3.1% improvement in the accuracy of capturing target objects compared to traditional methods. Furthermore, the resolution of saliency maps was three times higher than that of traditional methods. In the application of industrial surface defect detection, the proposed method demonstrated an 11.6% enhancement in the accuracy of capturing target objects, concurrently reducing the false positive rate. The presented approach enables more accurate and comprehensive capture of target objects with higher resolution, thereby enhancing the visual interpretability of deep neural networks. This improvement contributes to the greater interpretability of deep learning models in industrial applications, offering substantial performance gains for the practical deployment of deep learning networks in the industrial domain.

Study on diel migration of zooplankton in the Arctic surrounding seas during summer season based on mathematical statistics

Marine zooplankton have diel vertical migration behavior and play a key role in the transport of surface organic compounds to the deep ocean, which is of great significance in studying marine climate change. In this research, the manual visual interpretation method was used to preprocess the biological backscattering intensity data of acoustic Doppler current profiler (ADCP) during the eighth Arctic expedition. Results showed that the extracted vertical migration trajectory was in good agreement with the variation of backscattering intensity data. The amount of zooplankton in the Arctic Ocean is significantly lower than that in the North Pacific and the North Atlantic, and sea ice cover has a significant effect on the diel vertical migration of zooplankton. Characteristics of zooplankton distribution in the North Atlantic Ocean were analyzed based on mathematical statistical methods. The results also prove that the backscattering intensity of -90dB can distinguish scattering layer and water, and that of -78dB can distinguish general scatters and zooplankton. There are two significant concentrations of zooplankton in the Atlantic Ocean which were located at the surface and at depths of 350-450 m, respectively.

Improvement of approaches in forming the classification of types of modern digital financial technologies

Aim. To consider a set of the main modern approaches to determining the varieties of digital financial instruments, as well as to unite these varieties into a single classification and to supplement the modifications with the necessary features in terms of scientific argumentation and practical approaches.Objectives. To investigate the concept and meaning of digital financial technologies/instruments; to consider the most relevant and modern classification features applied in practice and in the scientific environment to the classification of types of digital financial technologies/instruments; if necessary, to supplement the selected classification features with new types; to bring together the characteristics of types of digital financial instruments into a single classification.Methods. The study was conducted using the method of theoretical description, in the study of scientific literature and legal framework on the subject of digitalization of the Russian economy in the financial sphere; using the method of formal-logical approach, concretization of conclusions, method of thinking and visual interpretation of the results obtained.Results. Digital financial technologies/tools represent a special type and means of managing financial flows of an organization (business entity), which uses computing computer technology with the recording of code pulses in a certain sequence and with a certain frequency. The conducted research has shown that the complex of digital financial technologies can be divided according to the following classification features: depending on the methods of financing, on the methods and forms of financial management, on the management of settlement and payment operations, on the basis of financial risk management, on the basis of control and supervisory functions, on the management of financial security/cybersecurity, on the management of financial relations with partners, on the use of forecasting technologies, on the scale and duration of application of digital technologies, on the scale and duration of financial management, on the basis of the management of financial and economic relations with partners, on the basis of the management of financial security and cybersecurity, on the basis of the management of financial relations with partners. The addition of five new classification attributes to the narrow classification is traced. These include financial cybersecurity management, monetary relations with partners, material digital base equipment, advertising and marketing impact, and predictive technologies.Conclusions. Understanding the essence and content of digital financial technologies/tools and the varieties of their types is primarily essential for financial management from a digital transformation perspective. Indeed, before making the choice of a digital tool to manage the financial flows of an organization, the management of any company first needs to establish what tools are relevant, how they are classified based on financing, depending on the management of finances, payments and transfers, among others. This aspect plays an essential role in the beginning of the journey of choosing digital aspects of budget management and, as a result, determines the efficiency of financial and economic activities of conducting almost any business.

Extraction of Roads Using the Archimedes Tuning Process with the Quantum Dilated Convolutional Neural Network.

Road network extraction is a significant challenge in remote sensing (RS). Automated techniques for interpreting RS imagery offer a cost-effective solution for obtaining road network data quickly, surpassing traditional visual interpretation methods. However, the diverse characteristics of road networks, such as varying lengths, widths, materials, and geometries across different regions, pose a formidable obstacle for road extraction from RS imagery. The issue of road extraction can be defined as a task that involves capturing contextual and complex elements while also preserving boundary information and producing high-resolution road segmentation maps for RS data. The objective of the proposed Archimedes tuning process quantum dilated convolutional neural network for road Extraction (ATP-QDCNNRE) technology is to tackle the aforementioned issues by enhancing the efficacy of image segmentation outcomes that exploit remote sensing imagery, coupled with Archimedes optimization algorithm methods (AOA). The findings of this study demonstrate the enhanced road-extraction capabilities achieved by the ATP-QDCNNRE method when used with remote sensing imagery. The ATP-QDCNNRE method employs DL and a hyperparameter tuning process to generate high-resolution road segmentation maps. The basis of this approach lies in the QDCNN model, which incorporates quantum computing (QC) concepts and dilated convolutions to enhance the network's ability to capture both local and global contextual information. Dilated convolutions also enhance the receptive field while maintaining spatial resolution, allowing fine road features to be extracted. ATP-based hyperparameter modifications improve QDCNNRE road extraction. To evaluate the effectiveness of the ATP-QDCNNRE system, benchmark databases are used to assess its simulation results. The experimental results show that ATP-QDCNNRE performed with an intersection over union (IoU) of 75.28%, mean intersection over union (MIoU) of 95.19%, F1 of 90.85%, precision of 87.54%, and recall of 94.41% in the Massachusetts road dataset. These findings demonstrate the superior efficiency of this technique compared to more recent methods.

Gully Erosion Zoning in the Middle Volga Region

The article presents a new scheme of zoning of modern gully erosion in a large region of the Russian Federation. Automated landscape zoning by means of artificial neural networks was carried out in order to determine the natural and anthropogenic conditions for the development of the gully network. Erosion zoning was implemented on the basis of large-scale geoinformation mapping of gullies by the method of visual interpretation of high- and ultra-high-resolution satellite images for 2017–2021. The basins of small rivers (1314 in total) with an average area of 91 km2 are taken as operational-territorial units. 22688 gullies (including their holes) were identified in the study area, the average length of which is 65 m, and the total length of the gully network is about 1500 km. The density of the gully network averages 12 m/km2, reaching a maximum of 301 m/km2. The density of gully dissection is used as an indicator for the zoning of gully erosion, this indicator indirectly reflects the intensity of gully formation in geo-space. The dominant (84% of basins) are areas either with no gully dissection or having weak or very weak gully erosion. The main reasons for the widespread damping of gully erosion are related to changes in land use and in the climate system, as well as an evolutionary factor – the transition of many gully forms to the balka stage of development.