Search Results (1,113)

Unmanned Aerial Vehicles (UAVs) have become essential instruments for precision agriculture and forest monitoring, offering rapid, high-resolution data collection over wide areas. This review synthesizes global advances (2015–2024) in UAV-derived vegetation indices (VIs), combining bibliometric and content analyses of 472 peer-reviewed publications. The study identifies key research trends, dominant indices, and technical progress achieved through RGB, multispectral, hyperspectral, and thermal sensors. Results show an exponential growth of scientific output, led by China, the USA, and Europe, with NDVI, NDRE, and GNDVI remaining the most widely applied indices. New indices such as GSI, RBI, and MVI demonstrate enhanced sensitivity for stress and disease detection in both crops and forests. UAV-based monitoring has proven effective for yield prediction, water-stress evaluation, pest identification, and biomass estimation. Despite significant advances, challenges persist regarding illumination correction, soil background influence, and limited forestry applications. The paper concludes that UAV-derived vegetation indices—when integrated with machine learning and multi-sensor data—represent a transformative approach for the sustainable management of agricultural and forest ecosystems. Full article

Mechanobiology explores how physical forces and cellular mechanics influence biological processes. This field has experienced rapid growth, driven by advances in high-resolution imaging, micromechanical testing, and computational modeling. At the same time, the increasing complexity and volume of mechanobiological imaging and measurement data have made traditional analysis methods difficult to scale. Artificial intelligence (AI) has emerged as a practical tool to address these challenges by providing new methods for interpreting and predicting biological behavior. Recent studies have demonstrated potential in several areas, including image-based analysis of cell and nuclear morphology, traction force microscopy (TFM), cell segmentation, motility analysis, and the detection of cancer biomarkers. Within this context, we review AI applications that either incorporate mechanical inputs/outputs directly or infer mechanobiologically relevant information from cellular and nuclear structure. This study summarizes progress in four key domains: AI/ML-based cell morphology studies, cancer biomarker identification, cell segmentation, and prediction of traction forces and motility. We also discuss the advantages and limitations of integrating AI/ML into mechanobiological research. Finally, we highlight future directions, including physics-informed and hybrid AI approaches, multimodal data integration, generative strategies, and opportunities for computational biophysics-aligned applications. Full article

Terraces are the main engineering of soil erosion control on the Loess Plateau, offering measures for sediment reduction and water conservation, as well as the potential for increasing agricultural productivity. Over the years, large-scale terrace construction has been undertaken; however, the management has been inadequate, especially in terms of long-term monitoring and mapping. Moreover, the sediment reduction effect of terrace construction is not yet fully understood. Therefore, this study utilizes Landsat series data, integrating remote sensing imaging principles with machine learning techniques to achieve long–term temporal sequence mapping of terraces at a 30 m spatial resolution on the Loess Plateau. The sediment reduction effect brought about by terrace construction on the Loess Plateau is quantified using a sediment reduction formula. The results show that Elevation (Ele.), red band (R), Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), and Near-infrared Reflectance of Vegetation (NIRv) are key parameters for remote sensing identification of terraces. These five remote sensing variables explain 88% of the terrace recognition variance. Coupling the Random Forest classification model with the LandTrendr algorithm allows for rapid time-series mapping of terrace spatial distribution characteristics on the Loess Plateau. The producer’s accuracy of terrace identification is 93.49%, the user’s accuracy is 93.81%, the overall accuracy is 88.61%, and the Kappa coefficient is 0.87. The LandTrendr algorithm effectively removes terraces affected by human activities. Terraces are mainly distributed in the southeastern Loess areas, including provinces such as Gansu, Shaanxi, and Ningxia. Over the past 30 years, the terrace area on the Loess Plateau has increased from 0.9790 million hectares in 1990 to 9.8981 million hectares in 2020. The sediment reduction effect is particularly notable, with an average reduction of 49.75% in soil erosion across the region. This indicates that terraces are a key measure for soil erosion control in the region and a critical strategy for improving farmland productivity. The data from this study provides scientific evidence for soil erosion control on the Loess Plateau and enhances the precision of terrace management. Full article

Background: Chronic Obstructive Pulmonary Disease (COPD) represents a significant global health burden, characterized by complex diagnostic and management challenges. Artificial Intelligence (AI) presents a powerful opportunity to enhance clinical decision-making and improve patient outcomes by leveraging complex health data. Objectives: This scoping review aims to systematically map the existing literature on AI applications in COPD. The primary objective is to identify, categorize, and summarize research into three key domains: (1) Diagnosis, (2) Clinical Symptoms, and (3) Clinical Outcomes. Methods: A scoping review was conducted following the Arksey and O’Malley framework. A comprehensive search of major scientific databases, including PubMed, Scopus, IEEE Xplore, and Google Scholar, was performed. The Population–Concept–Context (PCC) criteria included patients with COPD (Population), the use of AI (Concept), and applications in healthcare settings (Context). A global search strategy was employed with no geographic restrictions. Studies were included if they were original research articles published in English. The extracted data were charted and classified into the three predefined categories. Results: A total of 120 studies representing global distribution were included. Most datasets originated from Asia (predominantly China and India) and Europe (notably Spain and the UK), followed by North America (USA and Canada). There was a notable scarcity of data from South America and Africa. The findings indicate a strong trend towards the use of deep learning (DL), particularly Convolutional Neural Networks (CNNs) for medical imaging, and tree-based machine learning (ML) models like CatBoost for clinical data. The most common data types were electronic health records, chest CT scans, and audio recordings. While diagnostic applications are well-established and report high accuracy, research into symptom analysis and phenotype identification is an emerging area. Key gaps were identified in the lack of prospective validation and clinical implementation studies. Conclusions: Current evidence shows that AI offers promising applications for COPD diagnosis, outcome prediction, and symptom analysis, but most reported models remain at an early stage of maturity due to methodological limitations and limited external validation. Future research should prioritize rigorous clinical evaluation, the development of explainable and trustworthy AI systems, and the creation of standardized, multi-modal datasets to support reliable and safe translation of these technologies into routine practice. Full article

Across the Baltic Sea region, areas situated in climate-sensitive water zones are increasingly exposed to environmental and socio-economic challenges. Gdańsk, Poland, is a prominent example where the rising threat of climate-related hazards, particularly connected with flooding, coincides with growing demand for resilient and adaptive housing solutions. Located in the Vistula Delta, the city’s vulnerability is heightened by its low-lying terrain, polder-based land systems, and extensive waterfronts. These geographic conditions underscore the urgent need for flexible, climate-responsive design strategies that support long-term adaptation while safeguarding the urban fabric and the well-being of local communities. This study provides evidence-based guidance for adaptive housing solutions tailored to Gdańsk’s waterfronts. It draws on successful architectural and urban interventions across the Baltic Sea region, selected for their environmental, social, and cultural relevance, to inform development approaches that strengthen resilience and social cohesion. To achieve this, an exploratory case study methodology was employed, supported by desk research and qualitative content analysis of strategic planning documents, academic literature, and project reports. A structured five-step framework, comprising project identification, document selection, qualitative assessment, data extraction, and analysis, was applied to examine three adaptive housing projects: Hammarby Sjöstad (Stockholm), Kalasataman Huvilat (Helsinki), and Urban Rigger (Copenhagen). Findings indicate measurable differences across nine sustainability indicators (1–5 scale): Hammarby Sjöstad excels in environmental integration (5/5 in carbon reduction and renewable energy), Kalasataman Huvilat demonstrates strong modular and human-scaled adaptability (3–5/5 across social and housing flexibility), and Urban Rigger leads in climate adaptability and material efficiency (4–5/5). Key adaptive measures include flexible spatial design, integrated environmental management, and community engagement. The study concludes with practical recommendations for local planning guidelines. The guidelines developed through the Gdańsk case study show strong potential for broader application in cities facing similar challenges. Although rooted in Gdańsk’s specific conditions, the model’s principles are transferable and adaptable, making the framework relevant to water sensitivity, flexible housing, and inclusive, resilient urban strategies. It offers transversal value to both urban scholars and practitioners in planning, policy, and community development. Full article

Urban agriculture’s potential for food production and other social benefits is widely documented. However, the diversity of organisational structures and contextual factors that shape and drive the practice leads to a range of productivity levels. Yet, most studies estimate productivity using average production data, which compromises the reliability of the estimates. The objective of the study presented here is to develop a GIS-based spatial analytical framework that takes into account varying levels of productivity for four urban food garden types: Home, Community, Educational, and Commercial. We apply this analytical framework in Bogotá, Colombia, a city at the forefront of policies promoting urban agriculture, where we collected data from a sample of urban food gardens (i.e., produce yield, resource use, and social benefits). To increase the precision and reliability of the estimates, we perform a spatial Multi-Criteria Decision Analysis through several ArcGIS pro 3.1 functions. This allows the identification of suitable areas for each urban agriculture type, based on key spatial and social characteristics (location, proximity to roads and to rivers, private or public land, urban density, and socio-economic demographic conditions). Results suggest that 25% of Bogotá’s surface area (including vacant urban land and roofs) presents potential physical and social conditions for food growing, within which Home Gardens occupy the largest share of suitable land. This shows that land availability is not a key limiting factor to a possible expansion of urban agriculture, particularly at a household level. Resource consumption and educational benefits are also estimated, hence providing a comprehensive picture of the impact of urban food production at a city scale. Full article

(1) Background: Backcross (BC) breeding is a key technology of crop improvement, yet its efficiency largely depends on the precise assessment of the genetic background recovery. Conventional molecular marker-assisted techniques suffer from inadequate genomic coverage or an inability to resolve true chromosomal structure. (2) Methods: To address major issues in maize BC breeding, we devised a G2H block-scanning strategy. This approach converts high-density point markers into haplotype blocks, enabling precise evaluation of the genetic background in backcross progenies. A key innovation is the CFDI, which quantifies the distribution of unrecovered fragments, allowing for visual tracking of chromosomal recombination and identification of ideal individuals with both a high genetic background recovery rate and few small fragments retention. (3) Results: We validated the accuracy and effectiveness of the G2H strategy across multiple backcross generations. Through enabling a precise “point-to-line-to-area” panoramic assessment of genetic background, G2H provides a powerful tool for developing ideal breeding materials with pure genetic background and minimized linkage drag. (4) Conclusions: Notably, this strategy significantly shortens the breeding cycle by 2–3 generations compared to conventional background assessment methods, thereby accelerating precision molecular design breeding in crops. Full article

The Linxing area on the eastern margin of the Ordos Basin is a key area for tight-gas exploration. Here, the He 8 Member is the principal target for reserve growth and gas production. However, accurate prediction of sweet spots remains challenging due to poorly constrained primary controlling factors affecting high-quality reservoirs and their diagenetic densification mechanisms. To address these issues, we integrated data from cores, petrographic thin sections, scanning electron microscopy (SEM), X-ray diffraction (XRD), and log-facies analysis to conduct refined sedimentary microfacies identification, diagenetic analysis, and quantitative porosity evolution analysis. Results indicate that high-quality reservoirs in the He 8 Member are predominantly controlled by distributary-channel microfacies of a braided-river delta plain. Reservoir densification resulted from destructive diagenesis, primarily intense compaction and multi-phase cementation. Compaction reduced porosity by 18.7% on average (accounting for 60% of the total loss), whereas cementation led to a 11.4% loss (36.5%). Dissolution locally enhanced reservoir quality but was insufficient to reverse the pre-existing tight background, providing a limited porosity increase of approximately 5.6%. This study reveals a depositional-diagenetic coupling control on reservoir quality and establishes a genetic model for tight sandstones, thereby providing a critical theoretical framework for sweet-spot prediction in the Linxing area and analogous geological settings. Full article

Spatial distribution similarity analysis has extensive application value in multiple domains including geographic information science, urban planning, and engineering site selection. However, traditional regional similarity analysis methods face three key challenges: high sensitivity to directional changes, limitations in feature interpretability, and insufficient adaptability to multi-type data. Addressing these issues, this paper proposes a rotation-invariant spatial distribution similarity analysis method based on ring vectors. This method comprises three stages. First, the traversal starting point of the ring vector is dynamically selected based on the maximum value point of the regional feature matrix. Next, concentric ring features are extracted according to this starting point to achieve multi-scale characterization. Finally, the bidirectional weighted comprehensive distance of ring vectors between regions is calculated to measure the similarity between regions. Three experimental sets verified the method’s effectiveness in terrain matching, engineering site selection, and urban functional area identification. These results confirm its rotational invariance, feature interpretability, and adaptability to multi-type data. This research provides a new technical approach for spatial distribution similarity analysis, with significant theoretical and practical implications for geographic information science, urban planning, and engineering site selection. Full article

Urban areas globally face the critical challenge of meeting growing energy demands while maintaining environmental sustainability. However, existing research provides limited and often inconsistent evidence on how green finance affects urban energy efficiency, largely due to heterogeneous measurement systems, methodological constraints, and insufficient identification of underlying mechanisms. To address these research gaps, this study investigates two core questions: Does green finance significantly improve urban energy efficiency? If so, what are the specific transmission mechanisms driving this impact? Methodologically, this exploration employs a Double Machine Learning (DML) approach to analyze panel data from 210 Chinese cities between 2006 and 2022. The analysis demonstrates a significant and positive impact of green finance on urban energy efficiency, with an estimated coefficient of 0.1910. Further analysis identifies three constructive mechanisms, including environmental regulations, industrial structures, and green technological innovation, which enhance resource allocation and energy utilization efficiency. Moreover, green finance shows a stronger positive impact in non-resource-dependent cities, regions outside traditional industrial bases, and financially developed areas. These findings recommend establishing standardized green finance frameworks, increasing targeted financial support for key regions, and integrating green innovation with industrial restructuring. These measures help consolidate China’s green finance system and improve regional energy efficiency through market expansion, energy transition, and technological advancement. Full article

In coastal regions, the interaction between freshwater and seawater creates a dynamic system in which the spatial distribution of salinity critically constrains the use of freshwater for human consumption. Although saline intrusion is a globally widespread phenomenon, its inland extent varies significantly with hydrological conditions, posing a persistent threat to groundwater quality and sustainability. This study aimed to characterize salinity distribution using an integrated karst-watershed approach, thereby enabling the identification of both lateral and vertical salinity gradients. The study area is in the northwestern Yucatan Peninsula. Available hydrogeological data were analyzed to determine aquifer type, soil texture, evidence of saline intrusion, seawater fraction, vadose zone thickness, and field measurements. These included sampling from 42 groundwater sites (open sinkholes and dug wells), which indicated a fringe zone approximately 5 km in size influenced by seawater interaction, in mangrove areas and in three key zones of salinity patterns: west of Mérida (Celestun and Chunchumil), and northern Yucatan (Sierra Papacal, Motul, San Felipe). Vertical Electrical Sounding (VES) and conductivity profiling in two piezometers indicated an apparent seawater influence. The interface was detected at a depth of 28 m in Celestun and 18 m in Chunchumil. These depths may serve as hydrogeological thresholds for freshwater abstraction. Results indicate that saltwater can extend several kilometers inland, a factor to consider when evaluating freshwater availability. This issue is particularly critical within the first 20 km from the coastline, where increasing tourism exerts substantial pressure on groundwater reserves. A coastal-to-inland salinity was identified, and an empirical equation was proposed to estimate the seawater fraction (fsea%) as a function of distance from the shoreline in the Cenote Ring trajectory. Vertically, a four-layer model was identified in this study through VES in the western watershed: an unsaturated zone approximately 2.6 m thick, a confined layer in the coastal Celestun profile about 9 m thick, a freshwater lens floating above a brackish layer between 8 and 25 m, and a saline interface at 37 m depth. The novelty of this study, in analyzing all karstic water surfaces together as a system, including the vadose zone and the aquifer, and considering the interactions with the surface, is highlighted by the strength of this approach. This analysis provides a better understanding and more precise insight into the integrated system than analyzing each component separately. These findings have significant implications for water resource management in karst regions such as Yucatan, underscoring the urgent need for sustainable groundwater management practices to address seawater intrusion. Full article

Rock glaciers have been recognized as key indicators of geomorphic and climatic processes in high mountain environments. In this study, Sentinel-2 MSI imagery and topographic data were integrated to construct enhanced feature sets for rock glacier identification. Three state-of-the-art deep learning models (U-Net, DeepLabV3+, and HRnet) were employed to perform semantic segmentation for extracting rock glacier boundaries in the Hunza River Basin, located in the eastern Karakoram Mountains. The combination of spectral and terrain features significantly improved the differentiation of rock glaciers from surrounding landforms, establishing a robust basis for model training. A series of comparative experiments were conducted to evaluate the performance of each model. The HRnet model achieved the highest overall accuracy, exhibiting superior capabilities in high-resolution feature representations and generalization. Using the HRnet framework, a total of 597 rock glaciers were identified, covering an area of 183.59 km². Spatial analysis revealed that these rock glaciers are concentrated between elevations of 4000 m and 6000 m, with maximum density near 5000 m, and a predominant south and southwest orientation. These spatial patterns reflect the combined influences of topography, thermal conditions, and snow accumulation on the formation and preservation of rock glaciers. The results confirm the effectiveness of deep learning-based semantic segmentation for large-scale rock glacier mapping. The proposed framework establishes a technical foundation for automated monitoring of alpine landforms and supports future assessments of rock glacier dynamics under climate variability. Full article

Background/Objectives: Metabolic syndrome (MetS) increases the risk of type 2 diabetes and cardiovascular disease. We aimed to identify the key metabolic predictors of MetS in a Central European cohort and to compare classical statistics with modern machine learning (ML) models. Methods: We analysed 956 adults from the Lower Silesia Healthy Donors cohort. Clinical, anthropometric, biochemical, and lifestyle variables were collected using standardised procedures. Group differences were tested with Mann–Whitney U tests and effect sizes. A multivariable logistic regression (outcome: binary MetS defined as ≥3 harmonised components, MetS_bin) estimated adjusted odds ratios. In parallel, ML models (logistic regression, Random Forest, XGBoost, LightGBM, CatBoost) were trained with stratified 5-fold cross-validation. Performance was evaluated by accuracy, F1-macro, and area under the receiver-operating characteristic curve (ROC AUC). Model interpretability used SHAP values. Results: Overweight/obese participants had higher fasting glucose (median 92.0 vs. 84.6 mg/dL), fasting insulin (9.9 vs. 6.6 µU/mL), and systolic blood pressure (134 vs. 121 mmHg) and lower HDL cholesterol (53 vs. 66 mg/dL) compared to normal-BMI individuals (all p < 0.001, r ≈ 0.39–0.41). Participants with a higher waist circumference also showed markedly increased HOMA-IR (2.16 vs. 1.34; p < 0.001). In multivariable logistic regression, waist circumference, BMI, triglycerides, HDL cholesterol, fasting glucose, and systolic blood pressure were independently associated with MetS, yielding a test ROC-AUC of 0.98 and PR-AUC of 0.88. Machine learning models further improved discrimination: Random Forest, XGBoost, LightGBM, and CatBoost all achieved very high performance (test ROC-AUC ≥ 0.99, PR-AUC ≥ 0.98), with CatBoost showing the best cross-validated PR-AUC (~0.99) and favourable calibration. SHAP analyses consistently highlighted fasting glucose, triglycerides, HDL cholesterol, waist circumference, and systolic blood pressure as the most influential predictors. Conclusions: Combining classical regression with modern gradient-boosting models substantially improves the identification of individuals at risk of MetS. CatBoost, XGBoost, and LightGBM delivered near-perfect discrimination in this Central European cohort while remaining explainable with SHAP. This framework supports clinically meaningful risk stratification—including a “subclinical” probability zone—and may inform targeted prevention strategies rather than purely reactive treatment. Full article

Background: Transcatheter aortic valve replacement (TAVR) has emerged as a pivotal minimally invasive interventional therapy for aortic valve disease and has seen increasingly widespread clinical adoption in recent years. Despite its overall safety, the adverse events and even deaths in the postoperative period still account for a certain percentage. Accurate identification of high-risk patients is therefore critical for optimizing preoperative decision making, guiding individualized treatment strategies and improving long-term outcomes. However, existing scoring systems and predictive models fail to fully leverage multimodal clinical data from patients, resulting in suboptimal predictive accuracy that falls short of the demands of precision medicine, indicating substantial room for improvement. Methods: In this study, a multimodal deep learning model named MULTINet (multimodal learning for TAVR risk network) was constructed using data from the MIMIC-IV (Medical Information Mart for Intensive Care) cohort. This model achieved unimodal and multimodal modeling through a dual-branch structure, and, by using an attention pooling fusion module, flexibly handled the input that contained missing modalities, to predict the 30-day all-cause mortality in TAVR patients. The area under the receiver operating characteristic curve (AUC), the area under the precision–recall curve (AUPR) and the recall rate were used for prediction evaluation. The calibration degree was evaluated by calibration diagrams and Brier scores, and its clinical practicability was assessed through decision curve analysis (DCA). And the integrated gradient method was used to identify key predictive features to enhance interpretability of the model. Results: In the postoperative 30-day all-cause mortality prediction task, the MULTINet method achieved an AUC value of 0.9153, AUPR value of 0.5708 and Recall value of 0.8051, which was significantly superior to the XGBoost method (AUC 0.8958, AUPR 0.4053 and Recall 0.7793) and the MedFuse method (AUC 0.5571, AUPR 0.2487 and Recall 0.3089). The MULTINet method demonstrated more robust and reliable probability estimation performance, with a Brier score of 0.0269, outperforming XGBoost (0.0343) and MedFuse (0.2496). It achieved a higher net benefit in decision analysis, reflecting its effectiveness in strategy optimization and actual decision-making benefits. The renal function, cardiac function and inflammation-related indicators contributed greatly in the prediction process. Conclusions: The multimodal deep learning model proposed in this study named MULTINet enables adaptive integration of multimodal clinical information for predicting all-cause mortality within 30 days post-TAVR, substantially improving both predictive accuracy and clinical applicability, providing robust support for clinical decision making and boosting TAVR management toward greater precision and intelligence. Full article

The paper presents the model, methodology and results of experimental research focused on identification of the wave form generated during the crossing of 30-ton and 60-ton vehicles on a ribbon-type pontoon bridge and the analysis of its influence on the characteristics of the maximum draught. A review of the literature revealed that ribbon-type pontoon bridges are subject to significant vertical deflection. This results from the need to generate sufficient buoyant force to balance the weight of crossing vehicles. The area of maximum draught occurs directly beneath the vehicle and moves along with it, generating a front wave—referred to as a bow wave—which propagates along the crossing and alters the local draught of individual pontoons. Due to the fact that pontoon bridges transfer loads through buoyancy force, a key issue in the process of their design is the precise knowledge of the formation of the volume of the droughted part. No information was found in any publication about the influence of the front wave on the draught form of a ribbon-type pontoon bridge. Their authors do not indicate that the analytical or simulation models they use reflect this phenomenon. Equally, the analysis of the methodologies and results of experimental studies in this area did not show that any attempts were made to identify the form of the front wave. The paper presents the results of measurements of vertical displacements of individual pontoon blocks of the crossing and the characteristics of the front wave occurring during the passing of 30- and 60-ton vehicles with speeds ranging from 7.4 to 30 km/h. Based on the obtained data, an attempt was made to identify the phenomenon of undulation of the surface of the water obstacle and its impact on the loads on the bridge structure. The results allow for identifying a significant front wave with a wavelength of 30–50 m, appearing clearly at speeds above 21 km/h. This wave substantially affects the draught measurement—at a speed of 25 km/h, the maximum draught increased by approximately 30%. Statistical analysis confirmed the significance of this effect (p < 0.05), indicating that wave formation must be considered for accurate determination of pontoon block draught. Furthermore, the mass of the vehicle had a strong influence on the wave and draught parameters—the 60-ton vehicle produced wave troughs and draught depths 55–65% greater than those of the 30-ton vehicle. Full article