Search Results (771)

Multi-centennial C budgets in forested watersheds require information on forest growth, detritus turnover, and disturbances, as well as the transfer to and fate of terrestrial C in aquatics systems. Here, a sediment gravity core was collected from a drinking water reservoir in Canada, and analyzed for temporal changes in charcoal, magnetic susceptibility, carbon, and nitrogen. These indicators were used to assess disturbance history and terrestrial C sequestration in sediments. During the reservoir development period from 1910 to 2012, charcoal flux and magnetic susceptibility increased ca. 10 years after nearby fire and forest-clearing events associated with reservoir expansion. Total C and δ¹³C gradually declined during the development period, likely due to increased inputs of mineral soil from human activity. Concurrently, total terrestrial C sequestered in sediments, estimated using three or eight marker compounds, ranged between 3557 and 5145 Mg C/100 yrs, accounting for 11%–17% of DOC exports to the reservoir (30,640 Mg C/100 yrs), as estimated from a previously developed terrestrial carbon budget model. In comparison, mixed-severity fires burned around the reservoir during the pre-development period (pre-1910), as evidenced by stand ages and/or increases in charcoal flux. In general, decreased terrestrial C flux was associated with higher-severity fires that burned between 1870 and 1890 and perhaps around 1790. Further, comparisons show that soil erosion was up to 3× greater in the development versus the pre-development period. Overall, this investigation revealed the impact of land use change and fire on watershed carbon budgets and advanced a previously developed pyGC-MS methodology that demonstrated the amount of terrestrial and aquatic C being buried in sediment. It also identified the fraction of terrestrial C that was exported from the forest to the reservoir and sequestered in the sediment, uncommon data that could inform current and future landscape C budget modelling studies in this region. Full article

Seasonal fires in northern Thailand are a persistent environmental and public health concern, yet existing fire probability mapping approaches in Thailand rely heavily on subjective multi-criteria analysis (MCA) methods and temporally static data aggregation methods. To address these limitations, we present a flexible, replicable, and operationally viable seasonal fire probability mapping methodology using a Random Forest (RF) machine learning model in the Google Earth Engine (GEE) platform. We trained the model on historical fire occurrence and fire predictor layers from 2016–2023 and applied it to 2024 conditions to generate a probabilistic fire prediction. Our novel approach improves upon existing operational methods and scientific literature in several ways. It uses a more representative sample design which is agnostic to the burn history of fire presences and absences, pairs fire and fire predictor data from each year to account for interannual variation in conditions, empirically refines the most influential fire predictors from a comprehensive set of predictors, and provides a reproducible and accessible framework using GEE. Predictor variables include both socioeconomic and environmental drivers of fire, such as topography, fuels, potential fire behavior, forest type, vegetation characteristics, climate, water availability, crop type, recent burn history, and human influence and accessibility. The model achieves an Area Under the Curve (AUC) of 0.841 when applied to 2016–2023 data and 0.848 when applied to 2024 data, indicating strong discriminatory power despite the additional spatial and temporal variability introduced by our sample design. The highest fire probabilities emerge in forested and agricultural areas at mid elevations and near human settlements and roads, which aligns well with the known anthropogenic drivers of fire in Thailand. Distinct areas of model uncertainty are also apparent in cropland and forests which are only burned intermittently, highlighting the importance of accounting for localized burning cycles. Variable importance analysis using the Gini Impurity Index identifies both natural and anthropogenic predictors as key and nearly equally important predictors of fire, including certain forest and crop types, vegetation characteristics, topography, climate, human influence and accessibility, water availability, and recent burn history. Our findings demonstrate the heavy influence of data preprocessing and model design choices on model results. The model outputs are provided as interpretable probability maps and the methods can be adapted to future years or augmented with local datasets. Our methodology presents a scalable advancement in wildfire probability mapping with machine learning and open-source tools, particularly for data-constrained landscapes. It will support Thailand’s fire managers in proactive fire response and planning and also inform broader regional fire risk assessment efforts. Full article

Amazon River dolphins often form multi-species aggregations at water confluences. This study used a multi-year data set to examine dolphins, fish, and geomorphology at dolphin aggregations. Methods included dolphin transect surveys, dolphin point counts, net and line fish captures, side-scan sonar, and eDNA analyses at five dolphin aggregations and two control sites. Amazon River dolphins (Inia geoffrensis and Sotalia fluviatlis) are typically found at aggregation sites that occur at water confluences that have greater dolphin numbers than control sites. The confluences had riverbed depressions averaging six metres in depth where fish were concentrated. Pink river dolphins preferred to form aggregations in flooded forest tributaries and large rivers, while grey river dolphins preferred the larger rivers. There were eighty-nine fish species at the confluences within the size of fish consumed by dolphins, and a higher abundance of fish occurred in and around the aggregation sites compared to control sites. The number of dolphins present at the aggregation sites correlated with fish abundance. Dolphin life history, such as fishing, resting, raising calves, and social interactions, occur at the aggregation sites. The aggregation sites are important conservation areas of the endangered pink and grey river dolphins, and through their folklore, Indigenous people living at confluence sites assist in the conservation of the aggregations and have lived with dolphins at confluences for thousands of years, contributing to their survival. Full article

The species of the Bufonidae family exhibit a great diversity of habitats, diurnal or nocturnal habits, a complex evolutionary history, and a wide distribution, which makes this group suitable for morphological studies. In this work, we aimed to identify the existence of morphological patterns related to the habitat use and diurnal or nocturnal habits of Bufonidae in the Brazilian Amazon. To achieve this, we studied the morphological measurements of 210 specimens from three zoological collections and characterized the type of habitat and diurnality/nocturnality of the species. The morphological patterns and habitat use were investigated through principal component analysis (PCA) and multiple correspondence analysis (MCA), respectively. The evaluation of the relationships between morphological variation, habitat use, and diurnality/nocturnality was performed via redundancy analysis (RDA). Accordingly, Amazonian bufonids were divided into three morphological groups associated with different vegetation types and environments, demonstrating that body size is closely linked to diurnal or nocturnal life habits and habitat. Species with large body sizes are associated to anthropized areas, while intermediate and smaller species are associated with primary forests. Full article

Old-growth forests are crucial for biodiversity conservation and climate change mitigation due to their high carbon storage, structural complexity, and resilience to environmental stressors. Yet, such ecosystems are rare in Europe, and their ecological functioning remains poorly understood. This study assesses the capacity of Quercus pyrenaica forests in the Montesinho-Nogueira Natura 2000 site (Bragança, Portugal) to develop maturity attributes under different forest management histories. We compare an area with low human intervention for over 80 years (10.2 ha) to two areas harvested for traditional small-scale firewood and timber extraction around 30 years ago (11.4 ha and 2.73 ha). Dendrometric measurements, carbon storage, floristic inventories of understory vegetation, and regeneration surveys were conducted across 42 sub-plots during June–July 2024. Results show that older forests store significantly more carbon and support greater biodiversity, evenness and regeneration, while younger forests present higher values of species richness, including several rare taxa. Our findings suggest that under favorable conditions, secondary forests can recover substantial biomass and carbon stocks within a few decades, while mature stands continue to accumulate carbon and maintain complex structures. Differences in floristic composition between sites may also reflect distinct silvopastoral practices between patches, such as itinerant grazing through forest patches, which historically characterized the Montesinho landscape. These results highlight the value of preserving a mosaic of successional stages, as both mature and intermediate-phase forests, together with compatible human activities, provide complementary biodiversity benefits and contribute to the multifunctionality of Mediterranean agroforestry systems. Full article

Mamba (Dendroaspis species) snakebites are critical medical emergencies across sub-Saharan Africa. Envenomings can result in the rapid onset of complex neurotoxic symptoms, often leading to high rates of mortality without timely intervention with antivenom. The ancestral state of mambas is the green coloured, forest dwelling type, with the tan/grey coloured, savannah dwelling D. polylepis (Black Mamba) representing a derived state both ecologically and morphologically. However, it has not been tested whether these changes are paralleled by changes in venom biochemistry or if there are differential molecular evolutionary patterns. To fill these knowledge gaps, this study evaluated the neurotoxic effects of all Dendroaspis species venoms using the chick biventer cervicis nerve-muscle preparation, assessed the neutralizing efficacy of three antivenoms commercially available in Africa, and reconstructed the molecular evolutionary history of the toxin types to ascertain whether some were unique to particular species. All Dendroaspis venoms demonstrated potent flaccid-paralysis due to postsynaptic neurotoxicity. The only exception was D. angusticeps venom, which conversely exhibited spastic-paralysis due to presynaptic/synaptic neurotoxicity characterised by potentiation of acetylcholine presynaptic release and sustained synaptic activity of this neurotransmitter. Antivenom efficacy varied significantly. All three antivenoms neutralized to some degree the flaccid-paralysis postsynaptic effects for all species, with D. viridis venom being the best neutralized, and this pattern extended to all the antivenoms. However, neutralisation of flaccid-paralysis postsynaptic effects unmasked spastic-paralysis presynaptic/synaptic neurotoxicity within non-angusticeps venoms. Spastic-paralysis presynaptic effects were poorly neutralized for all species by all antivenoms, consistent with prior clinical reports of poor neutralisation of spastic-paralytic effects. Geographic variation in D. polylepis venom was evident for the relative neutralisation of both spastic-paralysis presynaptic/synaptic and flaccid-paralysis postsynaptic/synaptic neurotoxic pathophysiological effects, with differential neutralization capabilities noted between the Kenyan and South African populations studied. Molecular phylogenetic analyses confirmed spastic-paralysis and flaccid- paralysis toxins to be a trait that emerged in the Dendroaspis last common ancestor, with all species sharing all toxin types. Therefore, differences in venoms’ pathophysiological actions between species are due to differential expression of toxin isoforms rather than the evolution of species-specific novel toxins. Our findings highlight the synergistic nature of flaccid-paralysis postsynaptic and spastic-paralysis presynaptic/synaptic toxins, while contributing significant clinical and evolutionary knowledge of Dendroaspis venoms. These data are crucial for the continued development of more effective therapeutic interventions to improve clinical outcomes and for evidence-based design of clinical management strategies for the envenomed patient. Full article

Background/Objectives: Multiple sclerosis (MS) is an autoimmune disorder affecting the central nervous system, characterised by the degradation of myelin, which results in various neurological symptoms. This study aims to utilise radiomics features to evaluate the predictive value of IVIM diffusion parameters, namely, the true diffusion coefficient (D), pseudo-diffusion coefficient (D*), and perfusion fraction (f), in relation to disability severity, assessed using the Expanded Disability Status Scale (EDSS), and mobility in patients with relapsing–remitting MS. Methods: This retrospective cross-sectional study analysed MRI data from 197 patients diagnosed with multiple sclerosis (MS). Quantitative intravoxel incoherent motion (IVIM) parameters were obtained using a 1.5 Tesla MRI scanner. Clinical information collected included age, disease duration, number of relapses, status of disease-modifying therapy (DMT), and the need for mobility assistance. Machine learning (ML) techniques, such as XGB, Random Forest, and ANN, were employed to explore the relationships between radiomic IVIM parameters and these clinical variables. Results: IVIM radiomics achieved high accuracy in lesion phenotyping. Random Forest distinguished enhancements from non-enhancing lesions with 96% accuracy and AUC = 0.99 with IVIM-f and D* maps. CNN also reached ~92% accuracy (AUC 0.97) with IVIM-f. For disability prediction, IVIM-D and D* radiomics strongly correlated with EDSS: Random Forest achieved 89% accuracy (AUC = 0.90), while CNN achieved 90% accuracy (AUC = 0.95). Mobility impairment was predicted with the highest performance—RNN achieved 96% accuracy (AUC = 0.99) across IVIM-f features. In contrast, relapse history, disease duration, and treatment status were poorly predicted (<75% accuracy). Conclusions: ML analyses of IVIM metrics provided independent predictors of functional impairment and disability in MS. Our novel approach may be used to improve diagnostic accuracy and develop personalised treatment strategies for MS patients. Full article

Soil organic carbon (SOC) constitutes the largest terrestrial carbon pool and plays a crucial role in climate regulation, soil fertility, and ecosystem functioning. Understanding its spatiotemporal dynamics is particularly important in semi-arid regions, where fragile environments and extensive ecological restoration may alter carbon cycling. The Loess Plateau, the world’s largest loess accumulation area with a history of severe erosion and large-scale vegetation restoration, provides a natural laboratory for examining how environmental gradients influence SOC storage over time. This study used a random forest model with multi-source environmental data to quantify soil organic carbon density (SOCD) dynamics in the 0–100 cm soil layer of the Loess Plateau from 2005 to 2020. SOCD showed strong spatial heterogeneity, decreasing from the humid southeast to the arid northwest. Over the 15-year period, total SOC storage increased from 4.84 to 5.23 Pg C (a 7.9% rise), while the annual sequestration rate declined from 0.046 to 0.020 kg·m⁻²·yr⁻¹, indicating that the regional carbon sink may be approaching saturation after two decades of restoration. Among soil types, Cambisols were the largest carbon pool, accounting for over 44% of total SOC storage. Vegetation productivity emerged as the dominant driver of SOC variability, with clay content as a secondary factor. These results indicate that although ecological restoration has substantially enhanced SOC storage, its marginal benefits are diminishing. Understanding the spatial and temporal patterns of SOC and their environmental drivers provides essential insights for evaluating long-term carbon sequestration potential and informing future land management strategies. Broader generalization requires multi-regional comparisons, long-term monitoring, and deeper soil investigations to capture ecosystem-scale carbon dynamics fully. Full article

Camphora officinarum Nees constitutes a pivotal tree species within the evergreen broad-leaved forests of East Asia, endowed with significant economic, ornamental, and ecological importance. Nevertheless, previous research has markedly underestimated the genetic diversity of this species, thereby hindering our efforts in conserving resources and enhancing genetic breeding. The current study generated 155 chloroplast genomes from specimens of C. officinarum obtained from six provinces/regions in China. The results reveal the identification of seven distinct clades (I–VII), with Clades II, III, V, and VII exhibiting genome expansions, primarily influenced by lineage-specific elongation of inverted repeats (IRs), whereas Clades I, IV, and VI maintained conserved IR lengths. Despite the structural plasticity, the GC content remained highly conserved. Geographic patterns indicated gene flow between adjacent regions (e.g., Hunan and Hubei with identical IR lengths), but genetic isolation in Fujian. High-polymorphism regions (psba-matK, ycf1, ycf2, and ndhF) were identified as superior phylogenetic markers, enhancing intraspecies-level resolution. Simple sequence repeats (SSRs) varied significantly among clades, dominated by A/T-rich mononucleotide repeats. These repeats, along with divergent repeat types (e.g., absence of reverse repeats in Clades V/VI), serve as robust tools for resource identification and evolutionary trajectory inference. Phylogenetically, samples from Fujian formed a distinct lineage, while samples from other regions, especially Guangdong, were mixed, with this finding probably being a reflection of historical cultivation and anthropogenic translocation. This study offers a framework for the genetic breeding and investigation of the evolutionary history of C. officinarum. Full article

Background/Objectives: The use of artificial intelligence (AI) in oncology has the potential to improve decision making, particularly in managing the risk associated with targeted therapies. This study aimed to develop and validate a machine learning-based clinical decision support system (CDSS) capable of predicting complications associated with Bevacizumab or its biosimilars and to translate the resulting predictive model into a clinically applicable tool. Methods: A prospective observational study was conducted on 395 records from patients treated with Bevacizumab or biosimilars for solid tumors. Pretherapeutic variables, such as demographic data, medical history, tumor characteristics and laboratory findings, were retrieved from medical records. Several machine learning models (logistic regression, Random Forest, XGBoost) were trained using 70/30 and 80/20 data splits. Their predictive performances were compared using accuracy, AUC-ROC, sensitivity, specificity, F1-scores and error rate. The best-performing model was used to derive a logistic-based risk score, which was further implemented as an interactive HTML form. Results: The optimized Random Forest model trained on the 80/20 split demonstrated the best balance between accuracy (70.63%), sensitivity (66.67%), specificity (73.85%), and AUC-ROC (0.75). The derived logistic risk score showed good performance (AUC-ROC = 0.720) and calibration. It identified variables, such as age ≥ 65, anemia, elevated urea, leukocytosis, tumor differentiation, and stage, as significant predictors of complications. The final tool provides clinicians with an easy-to-use, offline form that estimates individual risk levels and stratifies patients into low-, intermediate-, or high-risk categories. Conclusions: This study offers a proof of concept for developing AI-supported predictive tools in oncology using real-world data. The resulting logistic risk score and interactive form can assist clinicians in tailoring therapeutic decisions for patients receiving targeted therapies, enhancing the personalization of care without replacing clinical judgment. Full article

Background: Inborn errors of immunity (IEIs) are a heterogeneous group of rare disorders caused by genetic defects in one or more components of the immune system. The Jeffrey Modell Foundation’s (JMF) Ten Warning Signs are widely used for early detection; however, their diagnostic sensitivity is limited. Machine learning (ML) approaches may improve prediction accuracy by integrating additional clinical variables into decision-making frameworks. Methods: This retrospective study included 298 participants (98 IEI, 200 non-IEI) evaluated at a university-affiliated clinical immunology clinic between January and December 2020. IEI diagnoses were confirmed using European Society for Immunodeficiencies (ESID) criteria. Two datasets were constructed: one containing only JMF criteria and another combining JMF criteria with additional clinical variables. Four ML algorithms—random forest (RF), k-nearest neighbors (k-NN), support vector machine (SVM), and naive Bayes (NB)—were trained and optimized using nested 5-fold stratified cross-validation repeated three times. Performance metrics included accuracy, sensitivity, specificity, F1 score, Youden Index, and the area under the receiver operating characteristic curve (AUROC). SHapley Additive exPlanations (SHAP) were applied to evaluate feature importance. Results: Using only JMF criteria, the best-performing model was SVM (accuracy: 0.90 ± 0.04, sensitivity: 0.93 ± 0.05, AUROC: 0.91 ± 0.02). With the addition of clinical variables, the SVM achieved superior performance (accuracy: 0.94 ± 0.03, sensitivity: 0.97 ± 0.03, AUROC: 0.99 ± 0.00), outperforming both the classical JMF criteria (accuracy: 0.91, sensitivity: 0.87, AUROC: 0.90) and the JMF-only SVM model. SHAP analysis identified family history of early death, pneumonia history, and ICU admission as the most influential predictors. Conclusions: ML models, particularly SVM integrating JMF criteria with additional clinical variables, substantially improve IEI prediction compared with classical JMF criteria. Implementation of such models in clinical settings may facilitate earlier diagnosis and timely intervention, potentially reducing morbidity and healthcare burden in IEI patients. Full article

Background: Psoriasis is a chronic inflammatory skin disease with a variable course. Early identification of patients likely to require biologic therapy may help reduce complications and optimize care. In this study, we developed machine learning (ML) models to predict future biologic therapy use in psoriasis patients. Methods: We conducted a retrospective study using electronic health records (EHR) from Clalit Health Services in Israel, including psoriasis patients who started biologic therapy and matched psoriasis controls. Predictors included demographics, comorbidities, treatment history, and laboratory test results. KNN, SVM, Random Forest, and Logistic Regression ML models were trained on data from either the first five years post-onset or the five years preceding biologic therapy. Performance was evaluated on a held-out test set using AUC-ROC, precision, recall, and F1-score, with an emphasis on recall to maximize identification of true positive cases. Results: The best-performing models incorporated clinical, demographic, and laboratory data. Using data from the first five years after onset, the SVM model achieved the highest performance (AUC = 0.83, recall = 0.7). For data from the five years preceding biologic therapy, the Random Forest model performed best (AUC = 0.93, recall = 0.95). Key predictors included comorbid immune-mediated conditions, topical treatment frequency, and markers of inflammation and metabolism. Conclusions: EHR-based ML models, particularly those incorporating routine laboratory, demographic, and clinical data, can effectively predict future biologic therapy use in psoriasis patients. Model performance may be improved with larger cohorts and more complete clinical and laboratory data. Full article

Documenting and preserving cultural heritage assets is increasingly important, with threats from natural disasters, conflicts, climate change, and neglect, and some sites are both contested and physically difficult to access or document, posing the issue of “challenging heritage”. A range of innovative digital methods have emerged, offering practical, low-cost, efficient techniques for the 3D documentation of threatened heritage, including smart phone-based mobile light detection and ranging (LiDAR) and photogrammetry. Such techniques offer quick, accessible, and cost-effective alternatives to terrestrial laser scanners, albeit with reduced accuracy and detail, offering practical solutions in cases with restricted funding, limited time for access, complex architectural geometries, or the unavailability of high-end equipment on site. This paper presents a real-world case study integrating iPhone LiDAR with aerial photogrammetry for the rapid documentation of Sourp Magar Monastery, a Medieval site located in a forested slopes of the Kyrenia Range, Cyprus. Due to its poor state of preservation and years of abandonment, as well as its remote nature and location, the monastery is considered a “challenging heritage” monument. In the context of a recent international restoration initiative, a preliminary digital survey was undertaken to both document the current condition of Sourp Magar and contribute to a better understanding of its construction history. This paper outlines the workflow integrating the use of smartphone LiDAR and aerial photogrammetry, evaluates its efficacy in challenging heritage sites, and discusses its potential implications for rapid, low-cost documentation. Finally, the present paper aims to show the multifaceted benefit of easy-to-use, low-cost technologies in the preliminary study of sites and monuments. Full article

Acid mine drainage (AMD) poses significant environmental and health risks due to its high acidity and elevated metal and sulfate contents. Previous studies have primarily focused on short-term AMD monitoring, with limited attention paid to long-term, spatially resolved datasets and predictive modeling. In this 3.5-year study, six wells down-stream of a mine waste rock pile were monitored, and 132 sets of associated water quality (AWQ), geological (GEO), and climate history (CH) parameters were compiled to develop predictive models for Fe, Cu, and Zn concentrations. Random forest (RF), extreme gradient boosting (XGBoost), and support vector machine (SVM) algorithms were applied using different combinations of input variables. The combined AWQ-GEO-CH dataset achieved the best overall performance, with XGBoost yielding the highest R² values for Fe (0.81) and Cu (0.77), and SVM performing best for Zn (0.94). CH variables, particularly precipitation and evaporation over 60-day periods, strongly influenced metal concentrations by driving hydrological and solute redistribution processes. AWQ parameters, especially F⁻ and S²⁻, were key predictors for Fe and Zn and ranked second for Cu, likely due to shared upstream sources and coupled geochemical processes such as FeF₃ dissolution. The most impactful GEO factor was the installation of a vertical barrier, which reduced metal concentrations by 73–80%. These findings highlight the value of integrating multi-source datasets with ML for long-term AMD prediction and management. Full article

The rapid growth of the automobile industry has intensified the demand for accurate price prediction models in the used car market. Buyers often struggle to determine fair market value due to the complexity of factors such as mileage, brand, model, transmission type, accident history, and overall condition. This study presents a comparative analysis of machine learning models for used car price prediction, with a strong emphasis on the impact of feature engineering. We begin by evaluating multiple models, including Linear Regression, Decision Trees, Random Forest, Support Vector Regression (SVR), XGBoost, Stacking Regressor, and Keras-based neural networks, on raw, unprocessed data. We then apply a comprehensive feature engineering pipeline that includes categorical encoding, outlier removal, data standardization, and extraction of hidden features (e.g., vehicle age, horsepower). The results demonstrate that advanced preprocessing significantly improves predictive performance across all models. For instance, the Stacking Regressor’s R² score increased from 0.14 to 0.8899 after feature engineering. Ensemble methods, such as CatBoost and XGBoost, also showed strong gains. This research not only benchmarks models for this task but also serves as a practical tutorial illustrating how engineered features enhance performance in structured ML pipelines for the fellow researchers. The proposed workflow offers a reproducible template for building high-accuracy pricing tools in the automotive domain, fostering transparency and informed decision making. Full article