Search Results (11)

As a key parameter of the Earth’s ecosystem, soil moisture significantly influences land-atmosphere interactions and has important applications in meteorology, hydrology, and agricultural studies. However, existing passive microwave remote sensing products of soil moisture are limited by their discontinuous temporal coverage and relatively coarse spatial resolution (typically 25–55 km), which cannot meet the requirements for fine-scale applications. This study developed and compared four machine learning-based downscaling approaches to improve the spatiotemporal resolution of MCCA SMAP soil moisture products. The methodology involved establishing complex nonlinear relationships between soil moisture and various high-resolution surface parameters including albedo, evapotranspiration, precipitation, and soil properties. High-resolution soil moisture maps were generated by leveraging the scale-invariant characteristics between soil moisture and surface parameters, followed by comprehensive evaluation using in situ ground observations and triple collocation analysis. The results demonstrated that all downscaling models showed excellent consistency with original MCCA SMAP observations (R > 0.93, RMSE < 0.033 m³ m⁻³), while successfully providing enhanced spatial details. The Random Forest (RF) model exhibited superior performance, showing higher correlation coefficients and lower biases when compared with in situ measurements. Uncertainty analysis revealed relatively low uncertainty levels for all models except Backpropagation Neural Network (BPNN) model. The RF-downscaled products accurately tracked temporal variations of soil moisture and showed good responsiveness to precipitation patterns, demonstrating their potential for fine-scale hydrological applications and regional environmental monitoring. Full article

Coastal wetland vegetation exhibits pronounced spectral mixing, complex mosaic spatial patterns, and small target sizes, posing considerable challenges for fine-grained classification in high-resolution UAV imagery. At present, remote sensing classification of ground objects based on deep learning mainly relies on spectral and structural features, while the frequency domain features of ground objects are not fully considered. To address these issues, this study proposes a vegetation classification model that integrates spatial-domain and frequency-domain features. The model enhances global contextual modeling through a large-kernel convolution branch, while a frequency-domain interaction branch separates and fuses low-frequency structural information with high-frequency details. In addition, a shallow auxiliary supervision module is introduced to improve local detail learning and stabilize training. With a compact parameter scale suitable for real-world deployment, the proposed framework effectively adapts to high-resolution remote sensing scenarios. Experiments on typical coastal wetland vegetation including Reeds, Spartina alterniflora, and Suaeda salsa demonstrate that the proposed method consistently outperforms representative segmentation models such as UNet, DeepLabV3, TransUNet, SegFormer, D-LinkNet, and MCCA across multiple metrics including Accuracy, Recall, F1 Score, and mIoU. Overall, the results show that the proposed model effectively addresses the challenges of subtle spectral differences, pervasive species mixture, and intricate structural details, offering a robust and efficient solution for UAV-based wetland vegetation mapping and ecological monitoring. Full article

In terms of facial expressions, micro-expressions are more realistic than macro-expressions and provide more valuable information, which can be widely used in psychological counseling and clinical diagnosis. In the past few years, deep learning methods based on optical flow and Transformer have achieved excellent results in this field, but most of the current algorithms are mainly concentrated on establishing a serialized token through the self-attention model, and they do not take into account the spatial relationship between facial landmarks. For the locality and changes in the micro-facial conditions themselves, we propose the deep learning model MCCA-VNET on the basis of Transformer. We effectively extract the changing features as the input of the model, fusing channel attention and spatial attention into Vision Transformer to capture correlations between features in different dimensions, which enhances the accuracy of the identification of micro-expressions. In order to verify the effectiveness of the algorithm mentioned, we conduct experimental testing in the SAMM, CAS (ME) II, and SMIC datasets and compared the results with other former best algorithms. Our algorithms can improve the UF1 score and UAR score to, respectively, 0.8676 and 0.8622 for the composite dataset, and they are better than other algorithms on multiple indicators, achieving the best comprehensive performance. Full article

Understanding and managing land use/cover changes (LUCC) is crucial for ensuring the sustainability of the region. With the support of remote sensing technology, intensity analysis, the geodetic detector model, and the Mixed-Cell Cellular Automata (MCCA) model, this paper constructs an integrated framework linking historical evolutionary pattern-driving mechanisms for future simulation for LUCC in the Lower Liaohe Plain. From 1980 to 2018, the increasing trends were in built-up land and water bodies, and the decreasing trends were in grassland, cropland, forest land, unused land, and swamps. Overall, the changes in cropland, forest land, and built-up land are more active, while the changes in water bodies are more stable; the sources and directions of land use conversion are more fixed. Land use changes in the Lower Liaohe Plain are mainly influenced by socio-economic factors, of which population density, primary industry output value, and Gross Domestic Product (GDP) have a higher explanatory power. The interactive influence of each factor is greater than any single factor. The results of the MCCA model showed high accuracy, with an overall accuracy of 0.8242, relative entropy (RE) of 0.1846, and mixed-cell figure of merit (mcFoM) of 0.1204. By 2035, the built-up land and water bodies will increase, while the rest of the land use categories will decrease. The decrease is more pronounced in the central part of the plains. The findings of the study provide a scientific basis for strategically allocating regional land resources, which has significant implications for land use research in similar regions. Full article

Major depressive disorder (MDD) is a prevalent mental illness globally, yet its etiology remains largely elusive. Recent interest in the scientific community has focused on the correlation between the disruption of iron homeostasis and MDD. Prior studies have revealed anomalous levels of iron in both peripheral blood and the brain of MDD patients; however, these findings are not consistent. This study involved 95 MDD patients aged 18–35 and 66 sex- and age-matched healthy controls (HCs) who underwent 3D-T1 and quantitative susceptibility mapping (QSM) sequence scans to assess grey matter volume (GMV) and brain iron concentration, respectively. Plasma ferritin (pF) levels were measured in a subset of 49 MDD individuals and 41 HCs using the Enzyme-linked immunosorbent assay (ELISA), whose blood data were simultaneously collected. We hypothesize that morphological brain changes in MDD patients are related to abnormal regulation of iron levels in the brain and periphery. Multimodal canonical correlation analysis plus joint independent component analysis (MCCA+jICA) algorithm was mainly used to investigate the covariation patterns between the brain iron concentration and GMV. The results of “MCCA+jICA” showed that the QSM values in bilateral globus pallidus and caudate nucleus of MDD patients were lower than HCs. While in the bilateral thalamus and putamen, the QSM values in MDD patients were higher than in HCs. The GMV values of these brain regions showed a significant positive correlation with QSM. The GMV values of bilateral putamen were found to be increased in MDD patients compared with HCs. A small portion of the thalamus showed reduced GMV values in MDD patients compared to HCs. Furthermore, the region of interest (ROI)-based comparison results in the basal ganglia structures align with the outcomes obtained from the “MCCA+jICA” analysis. The ELISA results indicated that the levels of pF in MDD patients were higher than those in HCs. Correlation analysis revealed that the increase in pF was positively correlated with the iron content in the left thalamus. Finally, the covariation patterns obtained from “MCCA+jICA” analysis as classification features effectively differentiated MDD patients from HCs in the support vector machine (SVM) model. Our findings indicate that elevated peripheral ferritin in MDD patients may disrupt the normal metabolism of iron in the brain, leading to abnormal changes in brain iron levels and GMV. Full article

Analyzing the relationship between rural settlements and rural population change under different policy scenarios is key in the sustainable development of China’s urban and rural areas. We proposed a framework that comprised the mixed land use structure simulation (MCCA) model and the human–land coupling development model to assess the spatiotemporal dynamic changes in rural settlements and its’ coupling relationship with the rural population in the economically developed region of Deqing, Zhejiang Province. The results showed that rural settlements and urban land increased by 14.36 and 29.07 km², respectively, over the last 20 years. The expansion of some rural settlements and urban land occurred at the cost of cropland occupation. Rural settlements showed an expansion trend from 2000 to 2020, increasing from 42.69 km² in 2000 to 57.05 km² in 2020. In 2035, under the natural development scenario, the cropland protection scenario, and the rural development scenario, rural settlements are projected to show an expansion trend and Wukang and Leidian are the key regions with rural settlement expansion. The distance to Hangzhou, nighttime light data, distance to rivers, and precipitation are important factors influencing the expansion of rural settlements. The coupling relationship between rural settlements and the rural population developed in a coordinated manner from 2000 to 2020. For 2035, under different scenarios, the coupling relationship between rural settlements and the rural population showed different trends. In the rural development scenario, the highest number of towns with coordinated development between rural settlements and the rural population is in Deqing, predominantly with Type I coupling. Overall, an important recommendation from this study is that the sustainable development of regional land use can be promoted by controlling the occupation of cropland for urban and rural construction, balancing rural settlement expansion and rural population growth, and formulating land use policies that are more suitable for rural development. Full article

Modern water distribution systems (WDSs) offer automated controls and operations to improve their efficiency and reliability. Nonetheless, such automation can be vulnerable to cyber-attacks. Therefore, various approaches have been suggested to detect cyber-attacks in WDSs. However, most of these approaches rely on labeled attack records which are rarely available in real-world applications. Thus, for a detection model to be practical, it should be able to detect and localize events without referring to a predetermined list of labeled attacks. This study proposes a semi-supervised approach that relies solely on attack-free datasets to address this challenge. The approach utilizes a reduction in dimensionality by using maximum canonical correlation analysis (MCCA) followed by support vector data description (SVDD). The developed algorithm was tested on two case studies and various datasets, demonstrating consistently high performance in detecting and localizing cyber-attacks. Full article

As a transitional zone between urban and rural areas, the peri-urban areas are the areas with the most intense urban expansion and the most frequent spatial reconfiguration, and in this context, it is particularly important to reveal the evolution pattern of rural settlements in the peri-urban areas to provide reference for the rearrangement of rural settlements. The study takes five townships in the urban suburbs, and explores the scale, shape, spatial layout, and spatial characteristics of the urban suburbs of Hefei from 1980 to 2030 under the influence of urban-lake symbiosis based on spatial mathematical analysis and geographical simulation software. The study shows that: (1) the overall layout of rural settlements in the study area is randomly distributed due to the hilly terrain, but in small areas there is a high and low clustering phenomenon, and the spatial density shows the distribution characteristics of “high in the east and low in the west”; (2) since the reform and opening up, there are large spatial differences in the scale of rural settlements in the study area. (3) Different development scenarios have a strong impact on the future spatial pattern of rural settlement land use within the study area, which is a strong reflection of policy. Full article

Casein kinase 2 (CK2) is considered an important target for anti-cancer drugs. Given the structural diversity and broad spectrum of pharmaceutical activities of natural products, numerous studies have been performed to prove them as valuable sources of drugs. However, there has been little study relevant to identifying structural factors responsible for their inhibitory activity against CK2 with machine learning methods. In this study, classification studies were conducted on 115 natural products as CK2 inhibitors. Seven machine learning methods along with six molecular fingerprints were employed to develop qualitative classification models. The performances of all models were evaluated by cross-validation and test set. By taking predictive accuracy(CA), the area under receiver operating characteristic (AUC), and (MCC)as three performance indicators, the optimal models with high reliability and predictive ability were obtained, including the Extended Fingerprint-Logistic Regression model (CA = 0.859, AUC = 0.826, MCC = 0.520) for training test andPubChem fingerprint along with the artificial neural model (CA = 0.826, AUC = 0.933, MCC = 0.628) for test set. Meanwhile, the privileged substructures responsible for their inhibitory activity against CK2 were also identified through a combination of frequency analysis and information gain. The results are expected to provide useful information for the further utilization of natural products and the discovery of novel CK2 inhibitors. Full article

This study explored the past and present land-use/land-cover (LULC) changes and urban expansion pattern for the cities of the Kathmandu valley and their surroundings using Landsat satellite images from 1988 to 2016. For a better analysis, LULC change information was grouped into seven time-periods (1988–1992, 1992–1996, 1996–2000, 2000–2004, 2004–2008, 2008–2013, and 2013–2016). The classification was conducted using the support vector machines (SVM) technique. A hybrid simulation model that combined the Markov-Chain and Cellular Automata (MC-CA) was used to predict the future urban sprawl existing by 2024 and 2032. Research analysis explored the significant expansion in urban cover which was manifested at the cost of cultivated land. The urban area totaled 40.53 km² in 1988, which increased to 144.35 km² in 2016 with an average annual growth rate of 9.15%, an overall increase of 346.85%. Cultivated land was the most affected land-use from this expansion. A total of 91% to 98% of the expanded urban area was sourced from cultivated land alone. Future urban sprawl is likely to continue, which will be outweighed by the loss of cultivated land as in the previous decades. The urban area will be expanded to 200 km² and 238 km² and cultivated land will decline to 587 km² and 555 km² by 2024 and 2032. Currently, urban expansion is occurring towards the west and south directions; however, future urban growth is expected to rise in the southern and eastern part of the study area, dismantling the equilibrium of environmental and anthropogenic avenues. Since the study area is a cultural landscape and UNESCO heritage site, balance must be found not only in developing a city, but also in preserving the natural environment and maintaining cultural artifacts. Full article

This study analyses the expansion of urban growth and land cover changes in five Saudi Arabian cities (Riyadh, Jeddah, Makkah, Al-Taif and the Eastern Area) using Landsat images for the 1985, 1990, 2000, 2007 and 2014 time periods. The classification was carried out using object-based image analysis (OBIA) to create land cover maps. The classified images were used to predict the land cover changes and urban growth for 2024 and 2034. The simulation model integrated the Markov chain (MC) and Cellular Automata (CA) modelling methods and the simulated maps were compared and validated to the reference maps. The simulation results indicated high accuracy of the MC–CA integrated models. The total agreement between the simulated and the reference maps was >92% for all the simulation years. The results indicated that all five cities showed a massive urban growth between 1985 and 2014 and the predicted results showed that urban expansion is likely to continue going for 2024 and 2034 periods. The transition probabilities of land cover, such as vegetation and water, are most likely to be urban areas, first through conversion to bare soil and then to urban land use. Integrating of time-series satellite images and the MC–CA models provides a better understanding of the past, current and future patterns of land cover changes and urban growth in this region. Simulation of urban growth will help planners to develop sustainable expansion policies that may reduce the future environmental impacts. Full article