Search Results (185)

This study explores land use classification in Trento using supervised learning techniques combined with call detail records (CDRs) as a proxy for human activity. Located in an alpine environment, Trento presents unique geographic challenges, including varied terrain and sparse network coverage, making it an ideal case for testing the robustness of supervised learning approaches. By analyzing spatiotemporal patterns in CDRs, we trained and evaluated several classification algorithms, including k-nearest neighbors (kNN), support vector machines (SVM), and random forests (RF), to map land use categories, such as home, work, and forest. A comparative analysis highlights the performance of each method, emphasizing the strengths of RF in capturing complex patterns, its good generalization ability, and the usage of kNN with different distance measures. Our supervised machine-learning approach outperforms unsupervised clustering techniques by capturing complex patterns and achieving higher accuracy. Results demonstrate the potential of CDRs for urban planning, offering a cost-effective approach for fine-grained land use monitoring with the particularities of Trento, as its landscape combines urban areas, agricultural fields, and forested regions, reflecting its alpine setting, in contrast with other metropolitan regions. Full article

Fast-developing countries, particularly in Southeast Asia, are critically susceptible to high concentrations of inhalable fine particulate pollution (PM2.5), which threatens public health and economic development. This study evaluates the incremental reduction in PM2.5 concentrations and its potential health and economic benefits, focusing on sustainable air quality management in vulnerable communities, particularly in the fisheries sector in the Philippines. Using satellite-derived PM2.5 data and the Environmental Benefits Mapping and Analysis Program–Community Edition (BenMAP-CE) model, the estimated premature mortality rates and the associated costs under various concentration reduction scenarios (25%, 50%, 75%, and 100%) for the regions of Navotas, Bohol, and Davao Del Sur revealed substantial health and economic benefits. Under 25–50% reduction scenarios, it could prevent annual premature mortalities of 55–104 in the three regions, generating approximately USD 1.15 million in monetary benefits. A more considerable 75–100% reduction scenario could prevent up to 206 mortalities annually, yielding USD 2.07 million in monetary benefits. These benefits were notable in areas with higher baseline PM2.5 concentrations, such as Navotas and Davao Del Sur, which experienced significant reductions in premature mortality within the range of 1–3% of the fisherfolk population. These findings highlight the incremental reduction strategies in a sector-specific approach to protect vulnerable communities crucial for economic development. The developed approach aims to improve the air quality in fishing-dependent regions to ensure sustainable livelihoods across the Philippines while meeting national and global health targets. Full article

Wildfires in the United States have increased in frequency and severity over recent decades, driven by climate change, altered weather patterns, and accumulated flammable materials. Accurately forecasting the Fire Weather Index (FWI) is crucial for mitigating wildfire risks and protecting ecosystems, human health, and infrastructure. This study analyzed FWI trends across the Continental United States (CONUS) from 2014 to 2023, using meteorological data from the gridMET dataset. Key variables, including temperature, relative humidity, wind speed, and precipitation, were utilized to calculate the FWI at a fine spatial resolution of 4 km, ensuring the precise identification of wildfire-prone areas. Based on this, our study developed a hybrid modeling framework to forecast FWI over a 14-day horizon, integrating Graph Neural Networks (GNNs) with Temporal Convolutional Neural Networks (TCNNs), Long Short-Term Memory (LSTM), and Deep Autoregressive Networks (DeepAR). The models were evaluated using the Index of Agreement (IOA) and root mean squared error (RMSE). The results revealed that the Southwest and West regions of CONUS consistently exhibited the highest mean FWI values, with the summer months demonstrating the greatest variability across all climatic zones. In terms of model performance on forecasting, Day 1 results highlighted the superior performance of the GNN-TCNN model, achieving an IOA of 0.95 and an RMSE of 1.21, compared to the GNN-LSTM (IOA: 0.93, RMSE: 1.25) and GNN-DeepAR (IOA: 0.92, RMSE: 1.30). On average, across all 14 days, the GNN-TCNN outperformed others with a mean IOA of 0.885 and an RMSE of 1.325, followed by the GNN-LSTM (IOA: 0.852, RMSE: 1.590) and GNN-DeepAR (IOA: 0.8225, RMSE: 1.755). The GNN-TCNN demonstrated robust accuracy across short-term (days 1–7) and long-term (days 8–14) forecasts. This study advances wildfire risk assessment by combining descriptive analysis with hybrid modeling, offering a scalable and robust framework for FWI forecasting and proactive wildfire management amidst a changing climate. Full article

While traditional self-supervised learning methods improve performance and robustness across various medical tasks, they rely on single-vector embeddings that may not capture fine-grained concepts such as anatomical structures or organs. The ability to identify such concepts and their characteristics without supervision has the potential to improve pre-training methods, and enable novel applications such as fine-grained image retrieval and concept-based outlier detection. In this paper, we introduce ConceptVAE, a novel pre-training framework that detects and disentangles fine-grained concepts from their style characteristics in a self-supervised manner. We present a suite of loss terms and model architecture primitives designed to discretise input data into a preset number of concepts along with their local style. We validate ConceptVAE both qualitatively and quantitatively, demonstrating its ability to detect fine-grained anatomical structures such as blood pools and septum walls from 2D cardiac echocardiographies. Quantitatively, ConceptVAE outperforms traditional self-supervised methods in tasks such as region-based instance retrieval, semantic segmentation, out-of-distribution detection, and object detection. Additionally, we explore the generation of in-distribution synthetic data that maintains the same concepts as the training data but with distinct styles, highlighting its potential for more calibrated data generation. Overall, our study introduces and validates a promising new pre-training technique based on concept-style disentanglement, opening multiple avenues for developing models for medical image analysis that are more interpretable and explainable than black-box approaches. Full article

Wildfires significantly impact human health, air quality, visibility, weather, and climate change and cause substantial economic losses. While state and county-operated air quality monitors provide critical insights during wildfires, they are not available in all regions. This highlights the need for affordable, accessible tools that allow the general public to assess air quality impacts. In this study, we apply machine learning with deep neural networks to diagnose air quality rapidly from sky images taken at the Pacific Northwest National Laboratory in Richland, WA, USA. Using a convolutional neural network (CNN) framework, we trained a deep learning model to classify air quality indices based on sky images. By leveraging transfer learning, our approach fine-tunes a pre-trained model on a small dataset of sky images, significantly reducing training time while maintaining high accuracy. Our results demonstrate the potential of deep learning to provide rapid air quality diagnostics during wildfire episodes, offering early warnings to the public and enabling timely mitigation strategies, particularly for vulnerable populations. Additionally, we show that lower respiratory infections pose the highest health risk during acute smoke exposures. Reactive oxygen species (ROS) from wildfire particles further exacerbate health risks by triggering inflammation and other adverse effects. Full article

CD44, a pivotal cell surface molecule, plays a crucial role in many cellular functions, including cell-cell interactions, adhesion, and migration. It serves as a receptor for hyaluronic acid and is involved in lymphocyte activation, recirculation, homing, and hematopoiesis. Moreover, CD44 is a commonly used cancer stem cell marker associated with tumor progression and metastasis. The development of CD44 aptamers that specifically target CD44 can be utilized to target CD44-positive cells, including cancer stem cells, and for drug delivery. Building on the primary sequences of our previously selected thioaptamers (TAs) and observed variations, we developed a bead-based X-aptamer (XA) library by conjugating drug-like ligands (X) to the 5-positions of certain uridines on a complete monothioate backbone. From this, we selected an XA with high affinity to the CD44 hyaluronic acid binding domain (HABD) from a large combinatorial X-aptamer library modified with N-acetyl-2,3-dehydro-2-deoxyneuraminic acid (ADDA). This XA demonstrated an enhanced binding affinity for the CD44 protein up to 23-fold. The selected CD44 X-aptamers (both amine form and ADDA form) also showed enhanced binding affinity to CD44-overexpressing human ovarian cancer IGROV cells. Secondary structure predictions of CD44 using MFold identified several binding motifs and smaller constructs of various stem-loop regions. Among our identified binding motifs, X-aptamer motif 3 and motif 5 showed enhanced binding affinity to CD44-overexpressing human ovarian cancer IGROV cells with ADDA form, compared to the binding affinities with amine form and scrambled sequence. The effect of ADDA as a binding affinity enhancer was not uniform within the aptamer, highlighting the importance of optimal ligand positioning. The incorporation of ADDA not only broadened the XA’s chemical diversity but also increased the binding surface area, offering enhanced specificity. Therefore, the strategic use of site-directed modifications allows for fine-tuning aptamer properties and offers a flexible, generalizable framework for developing high-performance aptamers that target a wide range of molecules. Full article

Accurate seabed topography is crucial for marine research, resource exploration, and engineering applications. While deep learning techniques have been widely applied in seabed inversion, existing methods often overlook the multi-scale influence of gravity anomalies, particularly the critical role of short-wavelength gravity anomalies in resolving fine-scale bathymetric features. In this study, we propose a novel Fully Connected Deep Neural Network (FCDNN) approach that systematically integrates long-wavelength, short-wavelength, and residual gravity anomaly components for seabed topography inversion. Using multi-satellite altimetry-derived gravity anomaly data (SIO V32.1) and shipborne bathymetric data (NCEI), we constructed a high-resolution (1′ × 1′) seabed topography model for the South China Sea (108°E–121°E, 6°N–23°N), termed FCD_Depth_SCS. The workflow included multi-scale decomposition of gravity anomalies, linear regression-based residual calculation, and FCDNN-based nonlinear training to capture the complex relationships between gravity anomalies and water depth. The FCD_Depth_SCS model achieved a difference standard deviation (STD) of 44.755 m and a mean absolute percentage error (MAPE) of 2.903% when validated against 160,476 shipborne control points. This performance significantly outperformed existing models, including GEBCO_2024, SIOv25.1, DTU18, and GGM_Depth (derived from the Gravity–Geologic Method), whose STDs were 82.234 m, 108.241 m, 186.967 m, and 58.874 m, respectively. Notably, the inclusion of short-wavelength gravity anomalies enabled the model to capture fine-scale bathymetric variations, particularly in open-sea regions. However, challenges remain near coastlines and complex terrains, highlighting the need for further model partitioning to address localized nonlinearity. This study highlights the benefits of integrating multi-scale gravity anomaly data with a fully connected deep neural network. Employing this innovative and robust approach enables high-resolution inversion of seabed topography with enhanced precision. The proposed method provides significant advancements in accuracy and resolution, contributing valuable insights for marine environmental research, resource management, and oceanographic studies. Full article

Accuratesnake species identification is essential for effective snakebite management, particularly in regions like Morocco, where approximately 400 snakebite incidents are reported annually, with a case fatality rate of 7.2%. Identifying venomous snakes promptly can significantly improve treatment outcomes by enabling the timely administration of specific antivenoms. However, the absence of comprehensive databases and rapid identification tools for Moroccan snake species poses challenges to effective clinical responses. This study presents a deep learning-based approach for the automated identification of Moroccan snake species. Several architectures, including VGG-19, VGG-16, and EfficientNet B0, were evaluated for their classification performance. EfficientNet B0 emerged as the most effective model, achieving an accuracy of 92.23% and an F1-score of 93.67%. After training on the SnakeCLEF 2021 dataset and fine-tuning with a specialized local dataset, the model attained a validation accuracy of 94% and an F1-score of 95.86%. To ensure practical applicability, the final model was deployed on a web platform, enabling the rapid and accurate identification of snake species via image uploads. This platform serves as a valuable tool for healthcare professionals and the general public, facilitating improved clinical response and educational awareness. This study highlights the potential of AI-driven solutions to address challenges in snakebite identification and management, offering a scalable approach for regions with limited resources and high snakebite prevalence. Full article

Background/Objectives: Cowpea is an important legume crop in sub-Saharan Africa (SSA) and beyond. However, access to phosphorus (P), a critical element for plant growth and development, is a significant constraint in SSA. Thus, it is essential to have high P-use efficiency varieties to achieve increased yields in environments where little-to- no phosphate fertilizers are applied. Methods: In this study, crop phenology, yield, and grain P efficiency traits were assessed in two recombinant inbred line (RIL) populations across ten environments under high- and low-P soil conditions to identify traits’ response to different soil P levels and associated quantitative trait loci (QTLs). Single-environment (SEA) and multi-environment (MEA) QTL analyses were conducted for days to flowering (DTF), days to maturity (DTM), biomass yield (BYLD), grain yield (GYLD), grain P-use efficiency (gPUE) and grain P-uptake efficiency (gPUpE). Results: Phenotypic data indicated significant variation among the RILs, and inadequate soil P had a negative impact on flowering, maturity, and yield traits. A total of 40 QTLs were identified by SEA, with most explaining greater than 10% of the phenotypic variance, indicating that many major-effect QTLs contributed to the genetic component of these traits. Similarly, MEA identified 23 QTLs associated with DTF, DTM, GYLD, and gPUpE under high- and low-P environments. Thirty percent (12/40) of the QTLs identified by SEA were also found by MEA, and some of those were identified in more than one P environment, highlighting their potential in breeding programs targeting PUE. QTLs on chromosomes Vu03 and Vu08 exhibited consistent effects under both high- and low-P conditions. In addition, candidate genes underlying the QTL regions were identified. Conclusions: This study lays the foundation for molecular breeding for PUE and contributes to understanding the genetic basis of cowpea response in different soil P conditions. Some of the identified genomic loci, many being novel QTLs, could be deployed in marker-aided selection and fine mapping of candidate genes. Full article

Background: The balance of omega-6/omega-3 (n-6/n-3) is crucial for proper brain function as they have opposite physiological roles. Objectives: To analyze the association between maternal serum ratios of n-6/n-3 in the first and third trimesters of pregnancy and the neurodevelopment of their children in the early days after birth in the population of Northern Spain’s Mediterranean region. Methods: Longitudinal study in which 336 mother–child pairs participated. Mother serum concentrations of long-chain polyunsaturated fatty acids (LCPUFAs), docosahexaenoic acid (DHA), eicosapentaenoic acid (EPA), and arachidonic acid (ARA) were determined. Sociodemographic, clinical, lifestyle habits, and obstetrical variables were collected. The Bayley Scales of Infant and Toddler Development (BSID-III) was used to assess infant neurodevelopment. Multiple linear regression models adjusting for confounding factors were performed. Results: In the third trimester, a higher maternal n-6/n-3 ratio was negatively associated with infant motor development (β = −0.124, p = 0.023). Similarly, higher ARA/DHA ratios were negatively associated with total motor (β = −2.005, p = 0.002) and fine motor development (β = −0.389, p = 0.001). No significant associations were observed in the first trimester nor for the ARA/EPA ratio in the third trimester. Conclusions: Our findings indicate that an elevated n-6/n-3 ratio and ARA/DHA ratio in the third trimester of pregnancy are associated with poorer motor development outcomes in infants. These results highlight the importance of optimizing maternal fatty acid balance during pregnancy to support fetal neurodevelopment, suggesting a need for further research to verify these associations and elucidate underlying mechanisms. Full article

Livestock farms are recognized sources of ammonia emissions, impacting nearby regions’ fine dust particle concentrations, though the full extent of this impact remains uncertain. Air dispersion models, commonly employed to estimate particulate matter (PM) levels, are heavily reliant on data quality, resulting in varying levels of accuracy. This study compares the performance of both air dispersion models and spatiotemporal deep learning models in estimating PM concentrations in Republic of Korea’s livestock-farming areas. Hourly PM concentration data, alongside temperature, humidity, and air pressure, were collected from seven monitoring stations across the study area. Using a 200 m × 200 m prediction grid, forecasts were generated for both 1 h and 24 h intervals using the Graz Lagrangian model (GRAL) and a one-dimensional convolutional neural network combined with the long short-term memory algorithm (1DCNN-LSTM). Results highlight the potential of the deep learning model to enhance PM prediction, indicating its promise as an effective alternative or supplement to conventional air dispersion models, particularly in data-scarce areas such as those surrounding livestock farms. Gaining a comprehensive understanding and evaluating the advantages and disadvantages of each approach would offer valuable scientific insights for monitoring atmospheric pollution levels within a specific area. Full article

Diesel engines employed in non-road machinery are significant contributors to nanoparticulate matters. This paper presents a novel device based on the principle of split-stream rushing to mitigate particulate matter emissions from these engines. By organizing and intensifying the airflow movement of the jet in the rushing region, the probability of collisions between nanoparticles is enhanced. This accelerates the growth and coagulation of nanoparticles, reducing the number density of fine particulate matter. This, in turn, facilitates the capture or sedimentation of particulate matter in the diesel engine exhaust aftertreatment system. The coagulation kernel function tailored for diesel engine exhaust nanoparticles is developed. Then, the particle balance equation is solved to investigate the evolution and coagulation characteristics. Afterwards, three-dimensional numerical simulations are performed to study the flow field characteristics of the split-stream rushing device and the particle evolution within it. The results show that the device achieves a maximum coagulation efficiency of 59.73%, increasing the average particle diameter from 96 nm to 121 nm. The particle number density uniformity index exceeded 0.93 in most flow regions, highlighting the effectiveness of the device in ensuring consistent particle distribution. Full article

Spatial and temporal information about cropping patterns of single and multiple crops is important for monitoring crop production and land-use intensity. We used time-series MODIS NDVI 8-day composite data to develop annual cropping pattern products at a 250 m spatial resolution for China, covering the period from 2001 to 2023. To address the potential impacts of varying parameters in both data pre-processing and the peak detection algorithm on the accuracy of cropping pattern mapping, we employed a grid-search method to fine-tune these parameters. This process focused on optimizing the Savitzky–Golay smoothing window size and the peak width parameters using a calibration dataset. The results highlighted that an optimal combination of a five to seven MODIS composite window size in Savitzky–Golay smoothing and a peak width of four MODIS composites achieved good overall mapping accuracy. Pixel-wise accuracy assessments were conducted for the selected mapping years of 2001, 2011, and 2021. Overall accuracies were between 89.7% and 92.0%, with F1 scores ranging from 0.921 to 0.943. Nationally, this study observed a fluctuating trend in multiple cropping percentages, with a notable increase after 2013, suggesting shifts toward more intensive agricultural practices in recent years. At a finer spatial scale, the combination of Mann–Kendall and Sen’s slope analyses revealed that approximately 12.9% of 3 km analytical windows exhibited significant changes in cropping intensity. We observed spatial clusters of increasing and decreasing crop intensity trends across provinces such as Hebei, Shandong, Shaanxi, and Gansu. This study underscores the importance of data smoothing and peak detection methods in analyzing high temporal resolution remote sensing data. The generation of annual single/multiple cropping pattern maps at a 250 m spatial resolution enhances our comprehension of agricultural dynamics through time and across different regions. Full article

This study explores the effects of varying exposure times of microelement fertilization on hydrochemical parameters, plant growth, and nutrient content in an aquaponic system cultivating Capsicum annuum L. (pepper) with Cyprinus carpio (Common carp L.). It also investigates the potential of visible–near-infrared (VIS-NIR) spectroscopy to differentiate between treated plants based on their spectral characteristics. The findings aim to enhance the understanding of microelement dynamics in aquaponics and optimize the use of VIS-NIR spectroscopy for nutrient and stress detection in crops. The effects of microelement exposure on the growth and health of Cyprinus carpio (Common carp L.) in an aquaponic system are investigated, demonstrating a 100% survival rate and optimal growth performance. The findings suggest that microelement treatments, when applied within safe limits, can enhance system productivity without compromising fish health. Concerning hydrochemical parameters, conductivity remained stable, with values ranging from 271.66 to 297.66 μS/cm, while pH and dissolved oxygen levels were within optimal ranges for aquaponic systems. Ammonia nitrogen levels decreased significantly in treated variants, suggesting improved water quality, while nitrate and orthophosphate reductions indicated an enhanced plant nutrient uptake. The findings underscore the importance of managing water chemistry to maintain a balanced and productive aquaponic system. The increase in root length observed in treatments 2 and 6 suggests that certain microelement exposure times may enhance root development, with treatment 6 showing the longest roots (58.33 cm). Despite this, treatment 2 had a lower biomass (61.2 g), indicating that root growth did not necessarily translate into increased plant weight, possibly due to energy being directed towards root development over fruit production. In contrast, treatment 6 showed both the greatest root length and the highest weight (133.4 g), suggesting a positive correlation between root development and fruit biomass. Yield data revealed that treatment 4 produced the highest yield (0.144 g), suggesting an optimal exposure time before nutrient imbalances negatively impact growth. These results highlight the complexity of microelement exposure in aquaponic systems, emphasizing the importance of fine-tuning exposure times to balance root growth, biomass, and yield for optimal plant development. The spectral characteristics of the visible–near-infrared region of pepper plants treated with microelements revealed subtle differences, particularly in the green (534–555 nm) and red edge (680–750 nm) regions. SIMCA models successfully classified control and treated plants with a misclassification rate of only 1.6%, highlighting the effectiveness of the spectral data for plant differentiation. Key wavelengths for distinguishing plant classes were 468 nm, 537 nm, 687 nm, 728 nm, and 969 nm, which were closely related to plant pigment content and nutrient status. These findings suggest that spectral analysis can be a valuable tool for the non-destructive assessment of plant health and nutrient status. Full article

Airwave interference presents a major source of noise in seismic exploration, posing significant challenges to the quality control of raw seismic data. With the increasing data volume in 3D seismic exploration, manual identification methods fall short of meeting the demands of high-density 3D seismic surveys. This study employs the YOLOv5 model, a widely used tool in object detection, to achieve rapid identification of airwave noise in seismic profiles. Initially, the model was pre-trained on the COCO dataset—a large-scale dataset designed for object detection—and subsequently fine-tuned using a training set specifically labeled for airwave noise data. The fine-tuned model achieved an accuracy and recall rate of approximately 85% on the test dataset, successfully identifying not only the presence of noise but also its location, confidence levels, and range. To evaluate the model’s effectiveness, we applied the YOLOv5 model trained on 2D data to seismic records from two regions: 2D seismic data from Ningqiang, Shanxi, and 3D seismic data from Xiushui, Sichuan. The overall prediction accuracy in both regions exceeded 90%, with the accuracy and recall rates for airwave noise surpassing 83% and 90%, respectively. The evaluation time for single-shot 3D seismic data (over 8000 traces) was less than 2 s, highlighting the model’s exceptional transferability, generalization ability, and efficiency. These results demonstrate that the YOLOv5 model is highly effective for detecting airwave noise in raw seismic data across different regions, marking the first successful attempt at computer recognition of airwaves in seismic exploration. Full article