Search Results (1,949)

This study presents a comprehensive review and comparative analysis of traditional machine learning (ML) and deep learning (DL) models for land cover classification in agricultural remote sensing. We evaluate the reported successes, trade-offs, and performance metrics of ML and DL models across diverse agricultural contexts. Building on this foundation, we apply both model types to the specific case of almond crop field identification in California’s Central Valley using Landsat data. DL models, including U-Net, MANet, and DeepLabv3+, achieve high accuracy rates of 97.3% to 97.5%, yet our findings demonstrate that conventional ML models—such as Decision Tree, K-Nearest Neighbor, and Random Forest—can reach comparable accuracies of 96.6% to 96.8%. Importantly, the ML models were developed using data from a single year, while DL models required extensive training data spanning 2008 to 2022. Our results highlight that traditional ML models offer robust classification performance with substantially lower computational demands, making them especially valuable in resource-constrained settings. This paper underscores the need for a balanced approach in model selection—one that weighs accuracy alongside efficiency. The findings contribute actionable insights for agricultural land cover mapping and inform ongoing model development in the geospatial sciences. Full article

Deforestation driven by plantations, such as Pinus patula Schiede ex Schltdl. et Cham., is a major cause of biodiversity and functional loss in tropical ecosystems. We assessed the diversity and composition of lichens and bryophytes in four size categories of pine cones, small (3–5 cm), medium (5.1–8 cm), large (8.1–10 cm), and very large (10.1–13 cm), with a total of 150 pine cones examined, where the occurrence and cover of lichen and bryophyte species were recorded. Identification keys based on morpho-anatomical features were used to identify lichens and bryophytes. In addition, for lichens, secondary metabolites were tested using spot reactions with potassium hydroxide, commercial bleach, and Lugol’s solution, and by examining the specimens under ultraviolet light. To evaluate the effect of pine cone size on species richness, the Kruskal–Wallis test was conducted, and species composition among cones sizes was compared using multivariate analysis. A total of 48 taxa were recorded on cones, including 41 lichens and 7 bryophytes. A total of 39 species were found on very large cones, 37 species on large cones, 35 species on medium cones, and 24 species on small cones. This is comparable to the diversity found in epiphytic communities of pine plantations. Species composition was influenced by pine cone size, differing from small in comparison with very large ones. The PERMANOVA analyses revealed that lichen and bryophyte composition varied significantly among the pine cone categories, explaining 21% of the variance. Very large cones with specific characteristics harbored different communities than those on small pine cones. The presence of lichen and bryophyte species on the pine cones from managed Ecuadorian P. patula plantations may serve as refugia for the conservation of biodiversity. Pine cones and their scales (which range from 102 to 210 per cone) may facilitate colonization of new areas by dispersal agents such as birds and rodents. The scales often harbor lichen and bryophyte propagules as well as intact thalli, which can be effectively dispersed, when the cones are moved. The prolonged presence of pine cones in the environment further enhances their role as possible dispersal substrates over extended periods. To our knowledge, this is the first study worldwide to examine pine cones as substrates for lichens and bryophytes, providing novel insights into their potential role as microhabitats within P. patula plantations and forest landscapes across both temperate and tropical zones. Full article

Wildfires can significantly alter soil physicochemical conditions and microbial communities in forest ecosystems. This study aimed to characterize the culturable soil fungal community and evaluate biological activity in Banco Totumo Bijibana, a protected dry tropical forest in Atlántico, Colombia, affected by a wildfire in 2014. Twenty soil samples were collected for microbiological (10 cm depth) and physicochemical (30 cm) analysis. Basal respiration was measured using Stotzky’s method, nitrogen mineralization via Rawls’ method, and fungal diversity through culture-based identification and colony-forming unit (CFU) counts. Diversity was assessed using Simpson, Shannon–Weaver, and ACE indices. The soils presented low organic matter (0.70%) and nitrogen content (0.035%), with reduced biological activity as indicated by basal respiration (0.12 kg C ha⁻¹ d⁻¹) and mineralized nitrogen (5.61 kg ha⁻¹). Four fungal morphotypes, likely from the genus Aspergillus, were identified. Simpson index indicated moderate dominance, while Shannon–Weaver values reflected low diversity. Correlation analysis showed Aspergillus-3 was positively associated with moisture, whereas Aspergillus-4 correlated negatively with pH and sand content. The species accumulation curve reached an asymptote, suggesting an adequate sampling effort. Although no control site was included, the findings provide a baseline characterization of post-fire soil microbial structure and function in a dry tropical ecosystem. Full article

Cancer metabolic reprogramming plays a critical role in tumor progression and therapeutic resistance, underscoring the need for advanced analytical strategies. Metabolomics, leveraging mass spectrometry and nuclear magnetic resonance (NMR) spectroscopy, offers a comprehensive and functional readout of tumor biochemistry. By enabling both targeted metabolite quantification and untargeted profiling, metabolomics captures the dynamic metabolic alterations associated with cancer. The integration of metabolomics with machine learning (ML) approaches further enhances the interpretation of these complex, high-dimensional datasets, providing powerful insights into cancer biology from biomarker discovery to therapeutic targeting. This review systematically examines the transformative role of ML in cancer metabolomics. We discuss how various ML methodologies—including supervised algorithms (e.g., Support Vector Machine, Random Forest), unsupervised techniques (e.g., Principal Component Analysis, t-SNE), and deep learning frameworks—are advancing cancer research. Specifically, we highlight three major applications of ML–metabolomics integration: (1) cancer subtyping, exemplified by the use of Similarity Network Fusion (SNF) and LASSO regression to classify triple-negative breast cancer into subtypes with distinct survival outcomes; (2) biomarker discovery, where Random Forest and Partial Least Squares Discriminant Analysis (PLS-DA) models have achieved >90% accuracy in detecting breast and colorectal cancers through biofluid metabolomics; and (3) prognostic modeling, demonstrated by the identification of race-specific metabolic signatures in breast cancer and the prediction of clinical outcomes in lung and ovarian cancers. Beyond these areas, we explore applications across prostate, thyroid, and pancreatic cancers, where ML-driven metabolomics is contributing to earlier detection, improved risk stratification, and personalized treatment planning. We also address critical challenges, including issues of data quality (e.g., batch effects, missing values), model interpretability, and barriers to clinical translation. Emerging solutions, such as explainable artificial intelligence (XAI) approaches and standardized multi-omics integration pipelines, are discussed as pathways to overcome these hurdles. By synthesizing recent advances, this review illustrates how ML-enhanced metabolomics bridges the gap between fundamental cancer metabolism research and clinical application, offering new avenues for precision oncology through improved diagnosis, prognosis, and tailored therapeutic strategies. Full article

Accurate side road detection is essential for traffic management, urban planning, and vehicle navigation. However, existing research mainly focuses on road network construction, lane extraction, and intersection identification, while fine-grained side road detection remains underexplored. Therefore, this study proposes a road segment-level side road detection method based on crowdsourced trajectory data: First, considering the geometric and dynamic characteristics of trajectories, SRDet introduces a trajectory lane-change pattern recognition method based on mutation intervals to distinguish the heterogeneity of lane-change behaviors between main and side roads. Secondly, combining geometric features with spatial statistical theory, SRDet constructs multimodal features for trajectories and road segments, and proposes a potential side road segment classification model based on random forests to achieve precise detection of side road segments. Finally, based on mutation intervals and potential side road segments, SRDet utilizes density peak clustering to identify main and side road access points, completing the fitting of side roads. Experiments were conducted using 2021 Beijing trajectory data. The results show that SRDet achieves precision and recall rates of 84.6% and 86.8%, respectively. This demonstrates the superior performance of SRDet in side road detection across different areas, providing support for the precise updating of urban road navigation information. Full article

The somatic cell count (SCC) and differential somatic cell count (DSCC) are proxies for the udder health of dairy cattle, regarded as the criterion of mastitis identification with healthy, suspicious mastitis, mastitis, and chronic/persistent mastitis. However, SCC and DSCC are tested using flow cytometry, which is expensive and time-consuming, particularly for DSCC analysis. Mid-infrared spectroscopy (MIR) enables qualitative and quantitative analysis of milk constituents with great advantages, being cheap, non-destructive, fast, and high-throughput. The objective of this study is to develop a dairy cattle udder health status diagnostic model of MIR. Data on milk composition, SCC, DSCC, and MIR from 2288 milk samples collected in dairy farms were analyzed using the CombiFoss 7 DC instrument (FOSS, Hilleroed, Denmark). Three MIR spectral preprocessing methods, six modeling algorithms, and three different sets of MIR spectral data were employed in various combinations to develop several diagnostic models for mastitis of dairy cattle. The MIR diagnostic model of effectively identifying the healthy and mastitis cattle was developed using a spectral preprocessing method of difference (DIFF), a modeling algorithm of Random Forest (RF), and 1060 wavenumbers, abbreviated as “DIFF-RF-1060 wavenumbers”, and the AUC reached 1.00 in the training set and 0.80 in the test set. The other MIR diagnostic model of effectively distinguishing mastitis and chronic/persistent mastitis cows was “DIFF-SVM-274 wavenumbers”, with an AUC of 0.87 in the training set and 0.85 in the test set. For more effective use of the model on dairy farms, it is necessary and worthwhile to gather more representative and diverse samples to improve the diagnostic precision and versatility of these models. Full article

The aim was to explore using machine learning (including cluster mapping and k-means methods) to classify types of mead based on sensory analysis and aromatic compounds. Machine learning is a modern tool that helps with detailed analysis, especially because verifying aromatic compounds is challenging. In the first stage, a cluster map analysis was conducted, allowing for the exploratory identification of the most characteristic features of mead. Based on this, k-means clustering was performed to evaluate how well the identified sensory features align with logically consistent groups of observations. In the next stage, experiments were carried out to classify the type of mead using algorithms such as Random Forest (RF), adaptive boosting (AdaBoost), Bootstrap aggregation (Bagging), K-Nearest Neighbors (KNN), and Decision Tree (DT). The analysis revealed that the RF and KNN algorithms were the most effective in classifying mead based on sensory characteristics, achieving the highest accuracy. In contrast, the AdaBoost algorithm consistently produced the lowest accuracy results. However, the Decision Tree algorithm achieved the highest accuracy value (0.909), demonstrating its potential for precise classification based on aroma characteristics. The error matrix analysis also indicated that acacia mead was easier for the algorithms to identify than tilia or buckwheat mead. The results show the potential of combining an exploratory approach (cluster map with the k-means method) with machine learning. It is also important to focus on selecting and optimizing classification models used in practice because, as the results so far indicate, choosing the right algorithm greatly affects the success of mead identification. Full article

Reducing gear noise in electric vehicle (EV) drivetrains is crucial due to the absence of internal combustion engine noise, making even minor acoustic disturbances noticeable. Manufacturing parameters significantly influence gear-generated noise, yet traditional analytical methods often fail to predict these complex relationships accurately. This research addresses this gap by introducing a data-driven approach using machine learning (ML) to predict gear noise levels from manufacturing and sensor-derived data. The presented methodology encompasses systematic data collection from various production stages—including soft and hard machining, heat treatment, honing, rolling tests, and end-of-line (EOL) acoustic measurements. Predictive models employing Random Forest, Gradient Boosting (XGBoost), and Neural Network algorithms were developed and compared to traditional statistical approaches. The analysis identified critical manufacturing parameters, such as surface waviness, profile errors, and tooth geometry deviations, significantly influencing noise generation. Advanced ML models, specifically Random Forest, XGBoost, and deep neural networks, demonstrated superior prediction accuracy, providing early-stage identification of gear units likely to exceed acceptable noise thresholds. Integrating these data-driven models into manufacturing processes enables early detection of potential noise issues, reduces quality assurance costs, and supports sustainable manufacturing by minimizing prototype production and resource consumption. This research enhances the understanding of gear noise formation and offers practical solutions for real-time quality assurance. Full article

On 20 April 2024, an extreme rainfall event occurred in Jiangwan Town Shaoguan City, Guangdong Province, China, where a historic 24 h precipitation of 206 mm was recorded. This triggered extensive landslides that destroyed residential buildings, severed roads, and drew significant societal attention. Rapid acquisition of landslide inventories, distribution patterns, and key controlling factors is critical for post-disaster emergency response and reconstruction. Based on high-resolution Planet satellite imagery, landslide areas in Jiangwan Town were automatically extracted using the Normalized Difference Vegetation Index (NDVI) differential method, and a detailed landslide inventory was compiled. Combined with terrain, rainfall, and geological environmental factors, the spatial distribution and causes of landslides were analyzed. Results indicate that the extreme rainfall induced 1426 landslides with a total area of 4.56 km², predominantly small-to-medium scale. Landslides exhibited pronounced clustering and linear distribution along river valleys in a NE–SW orientation. Spatial analysis revealed concentrations on slopes between 200–300 m elevation with gradients of 20–30°. Four machine learning models—Logistic Regression, Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting (XGBoost)—were employed to assess landslide susceptibility mapping (LSM) accuracy. RF and XGBoost demonstrated superior performance, identifying high-susceptibility zones primarily on valley-side slopes in Jiangwan Town. Shapley Additive Explanations (SHAP) value analysis quantified key drivers, highlighting elevation, rainfall intensity, profile curvature, and topographic wetness index as dominant controlling factors. This study provides an effective methodology and data support for rapid rainfall-induced landslide identification and deep learning-based susceptibility assessment. Full article

The mapping and monitoring of coastal regions are critical to ensure their sustainable use and viability in the long term. Delineation of coastlines is becoming increasingly important in the light of climate change and rising sea levels. However, many coastlines are highly dynamic; therefore, mono-temporal assessments of coastal ecosystems and coastlines are mere snapshots of limited practical value for space-based planning. Understanding of the spatio-temporal dynamics of coastal ecosystem boundaries is important to inform ecosystem management but also for a meaningful delineation of the high-water mark, which is used as a benchmark for coastal spatial planning in South Africa. This research aimed to use hyper-temporal Sentinel-2 imagery to extract ecological zones on the coast of KwaZulu-Natal, South Africa. A total of 613 images, collected between 2019 and 2023, were classified into four distinct coastal ecological zones—vegetation, bare, surf, and water—using a Random Forest model. Across all classifications, the percentage of each of the four classes’ occurrence per pixel over time was determined. This enabled the identification of ecosystem locations, spatially static ecosystem boundaries, and the occurrence of ecosystem boundaries with a more dynamic location over time, such as the non-permanent vegetation zone of the foredune area as well as the intertidal zone. The overall accuracy of the model was 98.13%, while the Kappa coefficient was 0.975, with user’s and producer’s accuracies ranging between 93.02% and 100%. These results indicate that cloud-based analysis of Sentinel-2 time series holds potential not just for delineating coastal ecosystem boundaries, but also for enhancing the understanding of spatio-temporal dynamics between them, to inform meaningful environmental management, spatial planning, and climate adaptation strategies. Full article

Background: Extremely premature neonates are at increased risk for respiratory complications, often resulting in recurrent hospitalizations during early childhood. Early identification of preterm infants at highest risk of respiratory hospitalizations could enable targeted preventive interventions. While clinical and demographic factors offer some prognostic value, integrating transcriptomic data may improve predictive accuracy. Objective: To determine whether early-life gene expression profiles can predict respiratory-related hospitalizations within the first four years of life in extremely preterm neonates. Methods: We conducted a retrospective cohort study of 58 neonates born at <32 weeks’ gestational age, using publicly available transcriptomic data from peripheral blood samples collected on days 5, 14, and 28 of life. Random forest models were trained to predict unplanned respiratory readmissions. Model performance was evaluated using sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (AUC). Results: All three models, built using transcriptomic data from days 5, 14, and 28, demonstrated strong predictive performance (AUC = 0.90), though confidence intervals were wide due to small sample size. We identified 31 genes and eight biological pathways that were differentially expressed between preterm neonates with and without subsequent respiratory readmissions. Conclusions: Transcriptomic data from the neonatal period, combined with machine learning, accurately predicted respiratory-related rehospitalizations in extremely preterm neonates. The identified gene signatures offer insight into early biological disruptions that may predispose preterm neonates to chronic respiratory morbidity. Validation in larger, diverse cohorts is needed to support clinical translation. Full article

Cellulose, the most abundant organic polymer in soil, is degraded by the action of microbial communities. Cellulolytic taxa are widespread in soils, enhancing the biodegradation of cellulose by the synergistic action of different cellulase enzymes. β-glucosidases are the last enzymes responsible for the degradation of cellulose by producing glucose from the conversion of the disaccharide cellobiose. Different soils from the states of Delaware, Maryland, New Jersey, and New York were analyzed by direct DNA extraction, PCR analysis, and next generation sequencing of amplicon sequences coding for β-glucosidase genes. To determine the community structure and diversity of microorganisms carrying β-glucosidase genes, amplicon sequence variant analysis was performed. Results showed that the majority of β-glucosidase genes did not match any known phylum or genera with an average of 84% of sequences identified as unclassified. The forest soil sample from New York showed the highest value with 95.62%. When identification was possible, the bacterial phyla Pseudomonadota, Actinomycetota, and Chloroflexota were found to be dominant microorganisms with β-glucosidase genes in soils. The Delaware soil showed the highest diversity with phyla and genera showing the presence of β-glucosidase gene sequences in bacteria, fungi, and plants. However, the Chloroflexota genus Kallotanue was detected in 3 out of the 4 soil locations. When phylogenetic analysis of unclassified β-glucosidase genes was completed, most sequences aligned with the Chloroflexota genus Kallotenue and the Pseudomonadota species Sphingomonas paucimobilis. Since most sequences did not match known phyla, there is tremendous potential to discover new enzymes for possible biotechnological and pharmaceutical applications. Full article

Background: Mild Cognitive Impairment (MCI) represents an intermediate stage between normal cognitive aging and Alzheimer’s Disease (AD). Early and accurate identification of MCI is crucial for implementing interventions that may delay or prevent further cognitive decline. This study aims to develop a machine learning-based model for differentiating between Cognitively Normal (CN) individuals and MCI patients using data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). Methods: An ensemble classification approach was designed by integrating Extra Trees, Random Forest, and Light Gradient Boosting Machine (LightGBM) algorithms. Feature selection emphasized clinically relevant biomarkers, including Amyloid-β 42, phosphorylated tau, diastolic blood pressure, age, and gender. The dataset was split into training and held-out test sets. A probability thresholding strategy was employed to flag uncertain predictions for potential deferral, enhancing model reliability in borderline cases. Results: The final ensemble model achieved an accuracy of 83.2%, a recall of 80.2%, and a precision of 86.3% on the independent test set. The probability thresholding mechanism flagged 23.3% of cases as uncertain, allowing the system to abstain from low-confidence predictions. This strategy improved clinical interpretability and minimized the risk of misclassification in ambiguous cases. Conclusions: The proposed AI-driven ensemble model demonstrates strong performance in classifying MCI versus CN individuals using multimodal ADNI data. Incorporating a deferral mechanism through uncertainty estimation further enhances the model’s clinical utility. These findings support the integration of machine learning tools into early screening workflows for cognitive impairment. Full article

Machine learning (ML) has established itself as an innovative tool in sustainable forest management, essential for tackling critical challenges such as deforestation, biodiversity loss, and climate change. Through the analysis of large volumes of data from satellites, drones, and sensors, machine learning facilitates everything from precise forest health assessments and real-time deforestation detection to wildfire prevention and habitat mapping. Other significant advancements include species identification via computer vision and predictive modeling to optimize reforestation and carbon sequestration. Projects like SILVANUS serve as practical examples of this approach’s success in combating wildfires and restoring ecosystems. However, for these technologies to reach their full potential, obstacles like data quality, ethical issues, and a lack of collaboration between different fields must be overcome. The solution lies in integrating the power of machine learning with ecological expertise and local community engagement. This partnership is the path forward to preserve biodiversity, combat climate change, and ensure a sustainable future for our forests. Full article

This study employed multiple machine learning and hyperparameter optimization techniques to analyze and predict the mechanical properties of self-drilling screw connections in thin-walled steel–ply–bamboo shear walls, leveraging the renewable and eco-friendly nature of bamboo to enhance structural sustainability and reduce environmental impact. The dataset, which included 249 sets of measurement data, was derived from 51 disparate connection specimens fabricated with engineered bamboo—a renewable and low-carbon construction material. Utilizing factor analysis, a ranking table recording the comprehensive score of each connection specimen was established to select the optimal connection type. Eight machine learning models were employed to analyze and predict the mechanical performance of these connection specimens. Through comparison, the most efficient model was selected, and five hyperparameter optimization algorithms were implemented to further enhance its prediction accuracy. The analysis results revealed that the Random Forest (RF) model demonstrated superior classification performance, prediction accuracy, and generalization ability, achieving approximately 61% accuracy on the test set (the highest among all models). In hyperparameter optimization, the RF model processed through Bayesian Optimization (BO) further improved its predictive accuracy to about 67%, outperforming both its non-optimized version and models optimized using the other algorithms. Considering the mechanical performance of connections within TWS composite structures, applying the BO algorithm to the RF model significantly improved the predictive accuracy. This approach enables the identification of the most suitable specimen type based on newly provided mechanical performance parameter sets, providing a data-driven pathway for sustainable bamboo–steel composite structure design. Full article