Search Results (2,649)

This study investigates the relationship between land use and soil organic carbon (SOC) storage in tropical Andean ecosystems, introducing a socio-ecological perspective to assess how community conservation perceptions influence SOC storage and contribute to climate change mitigation strategies. Background and Objectives: Land-use change reduces carbon stocks in tropical ecosystems. Focusing on the Las Piedras River basin (Popayan, Colombia), we evaluated SOC storage under four plant cover types—riparian forests (RFs), ecological restoration (ER), natural regeneration (NR), and livestock pastures (LSs)—and examined its association with local conservation perceptions. Materials and Methods: SOC storage at 30 cm depth, carbon inputs and outputs, and soil physicochemical properties were measured across land-use types. Conservation perceptions were assessed through 65 community surveys. Data analyses included ANOVA, principal component analysis, and multinomial logistic regression. Results: SOC storage was highest in RFs (148.68 Mg ha⁻¹), followed by ER and LSs, and lowest in NR (97.30 Mg ha⁻¹). A positive relationship was observed between high conservation perception and greater SOC content. Conclusions: SOC storage is strongly influenced by land use and community conservation values. Active restoration efforts, coupled with environmental education, are essential for enhancing the socio-ecological resilience of these ecosystems. Full article

Adverse childhood experiences (ACEs) are associated with profound long-term health and developmental consequences. However, current identification strategies are largely reactive, often missing opportunities for early intervention. Therefore, the potential of machine learning to proactively identify children at risk of ACE exposure needs to be explored. Using nationally representative data from 63,239 children in the 2018–2020 National Survey of Children’s Health (NSCH) after listwise deletion, we trained and validated multiple machine learning models to predict ACE exposure categorized as none, one, or two or more ACEs. Model performance was assessed using accuracy, precision, recall, F1 scores, and area under the curve (AUC) metrics with 5-fold cross-validation. The Random Forest model achieved the highest predictive accuracy (82%) and demonstrated strong performance across ACE categories. Key predictive features included child sex (female), food insufficiency, school absenteeism, quality of parent–child communication, and experiences of bullying. The model yielded high performance in identifying children with no ACEs (F1 = 0.89) and moderate performance for those with multiple ACEs (F1 = 0.64). However, performance for the single ACE category was notably lower (F1 = 0.55), indicating challenges in predicting this intermediate group. These findings suggest that family environment factors can be leveraged to predict ACE exposure with clinically meaningful accuracy, offering a foundation for proactive screening protocols. However, implementation must carefully address systematic selection bias, clinical utility limitations, and ethical considerations regarding predictive modeling of vulnerable children. Full article

The periphery of Lomami National Park in the Democratic Republic of the Congo (DR Congo) is experiencing intense and increasing hunting pressure, driven by both local subsistence needs and growing urban demand for bushmeat. This situation poses a serious challenge to sustainable natural resource management and underscores the need to realign protected-area policies with the realities faced by surrounding communities. In the absence of comprehensive ecological monitoring, this study used hunters’ perceptions to assess the current availability of mammalian wildlife around the park. From October to December 2023, surveys were conducted using a snowball sampling method with 60 hunters from nine villages bordering the park. Results show that hunting is a male-dominated activity, mainly practiced by individuals aged 30–40 years, with firearms as the primary tools. It occurs both in the park’s buffer zones and, alarmingly, within its core protected area. This practice has contributed to the local disappearance of key species such as African forest elephant (Loxodonta cyclotis), African buffalo (Syncerus caffer), and African leopard (Panthera pardus pardus), and to the marked decline of several Cephalophus species. These patterns of overexploitation reveal critical weaknesses in current conservation strategies and point to the urgent need for integrated, community-based resource management approaches. Strengthening law enforcement, improving ranger support, and enhancing participatory governance mechanisms are essential. Equally important is the promotion of sustainable alternative livelihoods—including livestock farming, aquaculture, and agroforestry—to reduce hunting dependence and build long-term resilience for both biodiversity and local communities. Full article

In recent decades, technological developments in archaeological geophysics have led to growing data volumes, so that an important bottleneck is now at the stage of data interpretation. The manual delineation and classification of anomalies are time-consuming, and different methods for (semi-)automatic image segmentation have been proposed, based on explicitly formulated rulesets or deep convolutional neural networks (DCNNs). So far, these have not been used widely in archaeological geophysics because of the complexity of the segmentation task (due to the low contrast between archaeological structures and background and the low predictability of the targets). Techniques based on shallow machine learning (e.g., random forests, RFs) have been explored very little in archaeological geophysics, although they are less case-specific than most rule-based methods, do not require large training sets as is the case for DCNNs, and can easily handle 3D data. In this paper, we show their potential for geophysical data analysis. For the classification on the pixel level, we use ilastik, an open-source segmentation tool developed in medical imaging. Algorithms for object classification, manual reclassification, post-processing, vectorisation, and georeferencing were brought together in a Jupyter Notebook, available on GitHub (version 7.3.2). To assess the accuracy of the RF classification applied to geophysical datasets, we compare it with manual interpretation. A quantitative evaluation using the mean intersection over union metric results in scores of ~60%, which only slightly increases after the manual correction of the RF classification results. Remarkably, a similar score results from the comparison between independent manual interpretations. This observation illustrates that quantitative metrics are not a panacea for evaluating machine-generated geophysical data interpretation in archaeology, which is characterised by a significant degree of uncertainty. It also raises the question of how the semantic segmentation of geophysical data (whether carried out manually or with the aid of machine learning) can best be evaluated. Full article

The use of drones for monitoring mammal populations has increased in recent years due to their relatively low cost, accessibility, and ability to survey large areas quickly and efficiently. The type of drone sensor used during surveys can significantly influence species detection probability. For arboreal mammals, thermal infrared (TIR) sensors are commonly used because they can detect heat signatures of canopy-dwelling species. However, drones equipped with TIR cameras are more expensive and thus less accessible to conservation practitioners who often work with limited funding compared to drones equipped exclusively with standard visual spectrum cameras (Red, Green, Blue; RGB drones). Although RGB drones may represent a viable low-cost alternative for wildlife monitoring, their effectiveness for monitoring arboreal mammals remains poorly understood. Our objective was to evaluate the use of RGB drones for monitoring arboreal mammals, focusing on Geoffroy’s spider monkeys (Ateles geoffroyi) and southern muriquis (Brachyteles arachnoides). We used pre-programmed flights for spider monkeys and manual flights for muriquis, selecting the most suitable method according to the landscape characteristics of each study site; flat terrain with relatively homogeneous forest canopy height and mountainous forests with highly variable canopy height, respectively. We detected spider monkeys in only 0.4% of the 232 flights, whereas we detected muriquis in 6.2% of the 113 flights. Considering that both species are highly arboreal, use the upper canopy, and share similar locomotion patterns and group size, differences in detectability are more likely related to the type of drone flights used in each case study than to species differences. Preprogrammed flights allow for systematic and efficient area coverage but limit real-time adjustments to environmental conditions such as wind, canopy structure, and visibility. In contrast, manual flights offer greater flexibility, with pilots being able to adjust speed, height, and flight path as needed and spend more time over specific areas to conduct a more exhaustive search. This flexibility likely contributed to the higher detection rate observed in the muriqui study, but detectability was still low. The findings of the two studies suggest that RGB drones are better suited as a complementary tool rather than a primary method for monitoring arboreal mammals in dense forest habitats. Nonetheless, RGB drones offer valuable opportunities for other applications, and we highlight several examples of their potential utility in arboreal mammal research and conservation. Full article

This study investigates the factors that influence household trip generation across the United States using the National Household Travel Survey (NHTS) dataset. Recognizing the limits of a one-size-fits-all modeling approach, we conduct a two-stage analysis to investigate spatial heterogeneity within travel behavior. Stage one creates a benchmark analysis, comparing advanced machine learning models (CatBoost and random forest) to a traditional linear regression model. Contrary to prevailing trends in predictive modeling, the results reveal that linear regression not only delivers competitive overall performance but also emerges as the best performing model in the majority of states. Providing optimal balance between predictive accuracy and interpretability. Building on these findings, the second stage applies state specific linear models to uncover geographic differences in trip generation drivers. The findings highlight extensive spatial heterogeneity: while core demographic variables like household size and the presence of young children show consistent effects across the US, the influence of socio-economic factors such as income and vehicle ownership are highly context-dependent and spatially volatile. These findings highlight the importance of moving beyond black box modeling and instead implementing place based, context sensitive techniques in the promotion of more effective and equitable transportation plans. Full article

In the face of mounting challenges related to limited availability of urban land and ecological degradation, emerging novel ecosystems offer unique opportunities for ecological regeneration, social redefinition of space, and alternative urban visions. This study presents the multi-layer analysis of the Goccia Forest in Milan (Italy), a wild urban woodland that has developed over sealed and polluted post-industrial land, aiming to investigate the potential of this novel ecosystem to sustain Nature-based Solutions (NbSs). Using an integrated approach (surveys on fauna, vascular flora, lichens, analysis of forest evolution, mapping of sealed surfaces, and soil characterization) the research looks at the novel ecosystem as a whole, highlighting its ecological dynamics and Ecosystem Services (ES). La Goccia Forest serves as a prime example of how the implementation of NbSs is intricately intertwined with the spontaneous regeneration of urban brownfields. The present study offers the opportunity to rethink urban policies, ensuring their alignment with the demands of the population and the latest scientific knowledge. Full article

Prepartum vaccination of dairy cows against newborn calf diarrhea protects calves during the first weeks of life via the colostrum. Vaccination may also induce non-specific effects (NSEs) beyond antibody production, altering the disease susceptibility and productivity of the vaccinated mother. This retrospective study analyzed herd records and on-site survey data from 73,378 dairy cows on 20 German farms using linear mixed-effects models and random forest algorithms. Management practices and milk yield showed stronger associations with outcomes than vaccination. However, the cows vaccinated with non-live vaccines had increased odds of retained placenta and metritis (OR: 1.5–1.7), as well as endometritis (OR: 3–6), and were 20–24% less likely to conceive than non-vaccinated cows. Among non-live vaccinated cows, those vaccinated 2.5–4 weeks before calving had an 8% higher non-return rate compared to those vaccinated 6–8 weeks prior. Multiparous cows receiving live vaccine components were 1.9 times more likely to conceive, compared to non-live vaccinated multiparous cows. These findings suggest potential NSE of prepartum vaccination on uterine health and fertility. However, this study’s retrospective design limits causal interpretation, and the benefits in calves may outweigh possible adverse effects. Further research should clarify the mechanisms and optimize vaccine timing and composition. Full article

Rice is a staple crop for over half the world’s population, and accurate, timely information on its planted area and production is crucial for food security and agricultural policy, particularly in developing nations like Sri Lanka. However, reliable rice monitoring in regions like Sri Lanka faces significant challenges due to frequent cloud cover and the fragmented nature of smallholder farms. This research introduces a novel, cost-effective method for mapping rice-planted area and yield at field scales in Sri Lanka using optical satellite data. The rice-planted fields were identified and mapped using a phenologically tuned image classification algorithm that highlights rice presence by observing water occurrence during transplanting and vegetation activity during subsequent crop growth. To estimate yields, a random forest regression model was trained at the district level by incorporating a satellite-derived chlorophyll index and environmental variables and subsequently applied at the field level. The approach has enabled the creation of two decades (2000–2022) of reliable, field-scale rice area and yield estimates, achieving map accuracies between 70% and over 90% and yield estimates with less than 20% error. These highly granular results, which are not available through traditional surveys, show a strong correlation with government statistics. They also demonstrate the advantages of a rule-based, phenology-driven classification over purely statistical machine learning models for long-term consistency in dynamic agricultural environments. This work highlights the significant potential of remote sensing to provide accurate and detailed insights into rice cultivation, supporting policy decisions and enhancing food security in Sri Lanka and other cloud-prone regions. Full article

Understanding and modeling the flow of information in human societies is essential for capturing phenomena such as polarization, opinion formation, and misinformation diffusion. Traditional agent-based models often rely on simplified behavioral rules that fail to capture the nuanced and context-sensitive nature of human decision-making. In this study, we explore the potential of Large Language Models (LLMs) as data-driven, high-fidelity agents capable of simulating individual opinions under varying informational conditions. Conditioning LLMs on real survey data from the 2020 American National Election Studies (ANES), we investigate their ability to predict individual-level responses across a spectrum of political and social issues in a zero-shot setting, without any training on the survey outcomes. Using Jensen–Shannon distance to quantify divergence in opinion distributions and F1-score to measure predictive accuracy, we compare LLM-generated simulations to those produced by a supervised Random Forest model. While performance at the individual level is comparable, LLMs consistently produce aggregate opinion distributions closer to the empirical ground truth. These findings suggest that LLMs offer a promising new method for simulating complex opinion dynamics and modeling the probabilistic structure of belief systems in computational social science. Full article

To evaluate the stability dynamics of typical forest plant communities in Northeast China, 57 forest plots were surveyed in 2009 and surveyed again in 2014. By adapting temporary stability (TS) as the community stability indicator, all plots were divided into three groups of low, moderate, and high stability, and the community initial state and state changes in different groups were analyzed. Results showed that the first dominant species in 15.8% (3/19) of plots was replaced by the second dominant species from 2009 to 2014 in the low stability group, but no such changes occurred in the moderate and high stability groups. The TS change amplitude was obvious in the low stability group, while that was slight in the high stability group. The relative basal area of the top two species was close in the low stability group in both 2009 and 2014, while the first dominant species was prominent in the high stability group. Communities in the high stability group had lower tree diversity, and those in the low stability group had more trees in 2009. Furthermore, tree size increased significantly in the low and moderate stability groups, and tree number decreased significantly in the moderate stability group from 2009 to 2014. The TS indicator is feasible in describing the stability state and change processes of forest plant communities on a time scale. Full article

Online Courses are one of the most popular ways to learn, but the technology used has a vital effect on the learner. In this study, we will research the prediction of students’ course engagement. International surveys show that students have a 70% interest in joining online learning, and just 30% of students are interested in traditional learning. However, keeping students engaged is one of the most difficult tasks, since low engagement contributes to lower learning outcomes and higher dropout rates. We studied more than 15 papers of existing research, and were able to achieve a 96% accuracy rate, which is a very welcome improvement on previous results. This paper examines machine learning algorithms, including Decision Trees, Random Forest, Gradient Booster, Naive Bayes, and K-Nearest Neighbors (KNN), to efficiently predict engagement during online courses. By systematically examining existing published research studies, we identify gaps and limitations of existing methods, such as problems with variant datasets, chances of overtraining, and a lack of accessibility to real-time engagement data. Full article

Understanding how endangered carnivores partition spatiotemporal distribution in human-dominated landscapes is pivotal for mitigating biodiversity loss in climate-sensitive boreal ecosystems. Here, we used kernel density data derived from a 16-month camera-trap survey (140 UVL7 cameras), cold single-season (November–April) occupancy models, and MaxEnt 3.4.4 to identify the effects of biotic interactions, anthropogenic disturbance, and environmental factors on the spatiotemporal distribution of the wolverine (Gulo gulo) in Beijicun National Nature Reserve, Heilongjiang Province, China. We found that wolverines exhibited crepuscular activity patterns using night-time relative abundance index (NRAI) = 50.29% with bimodal peaks (05:00–07:00, 13:00–15:00), with dawn activity predominant during the warm season (05:00–06:00) and a bimodal activity pattern in the cold season (08:00–09:00, 14:00–15:00). Temporal overlap with prey (overlap coefficient Δ = 0.84) and competitors (Δ = 0.70) was high, but overlap with human-dominated temporal patterns was low (Δ = 0.58). Wolverines avoided human settlements and major roads, preferred moving along forest trails and gentle slopes, and avoided high-altitude deciduous forests. Populations were mainly concentrated in southern Hedong and Qianshao Forest Farms, which are characterized by high habitat integrity, high prey densities, and minimal anthropogenic disturbance. These findings suggest that wolverines may influence boreal trophic networks, especially in areas with intact prey communities, competitors, and spatial refugia from human disturbances. We recommend that habitat protection and management within the natural reserve be prioritized and that sustainable management practices for prey species be implemented to ensure the long-term survival of wolverines. Full article

Linpan ecosystems, distinct to western Sichuan, China, are integral to regional biodiversity and carbon cycling. However, comprehensive biomass estimation for these systems has not been thoroughly investigated. This study seeks to fill this gap by enhancing the accuracy and precision of biomass estimation in these ecologically vital landscapes through the application of multi-source remote sensing techniques, specifically by integrating the strengths of optical and radar remote sensing data. The focus of this research is on the forest biomass of Linpan, encompassing the tree layer, which includes the trunk, branches, leaves, and underground roots. Specifically, the research focused on the Linpan ecosystems in the Wenjiang District of western Sichuan, utilizing an integration of Sentinel-1 SAR, Sentinel-2 multispectral, and GF-2 high-resolution data for multi-source remote sensing-based biomass estimation. Through the preprocessing of these data, Pearson correlation analysis was conducted to identify variables significantly correlated with the forest biomass as determined by field surveys. Ultimately, 19 key modeling factors were selected, including band information, vegetation indices, texture features, and phenological characteristics. Subsequently, three algorithms—multiple stepwise regression (MSR), support vector machine (SVM), and random forest (RF)—were employed to model biomass across mixed-type, deciduous broadleaved, evergreen broadleaved, and bamboo Linpan. The key findings include the following: (1) Sentinel-2 spectral data and Sentinel-1 VH backscatter coefficients during the summer, combined with vegetation indices and texture features, were critical predictors, while phenological indices exhibited unique correlations with biomass. (2) Biomass displayed a marked north–south gradient, characterized by higher values in the south and lower values in the north, with a mean value of 161.97 t ha⁻¹, driven by dominant tree species distribution and management intensity. (3) The RF model demonstrated optimal performance in mixed-type Linpan (R² = 0.768), whereas the SVM was more suitable for bamboo Linpan (R² = 0.892). The research suggests that integrating multi-source remote sensing data significantly enhances Linpan biomass estimation accuracy, offering a robust framework to improve estimation precision. Full article

The population size of black poplar (Populus nigra L.), once an important part of floodplain forests in the Czech Republic, has greatly declined due to human activity. In this study, we applied microsatellite (SSR) markers to identify species and assess genetic diversity, with the aim of supporting conservation of this endangered species. A total of 378 poplar trees were analyzed following field surveys. Five diagnostic SSR markers with species-specific alleles for P. deltoides Bartr. ex Marsh. enabled the identification of 39 interspecific hybrids, which were distinguished from native P. nigra. Thirteen SSR loci were used to evaluate genetic diversity among confirmed P. nigra individuals. The results revealed high genetic variation, with 66% of pairwise genotype comparisons differing at all loci. After excluding 45 genetically similar individuals, 292 genetically verified and polymorphic P. nigra trees were selected as potential sources of reproductive material. Genetic differentiation (Fst) was highest between P. nigra and P. deltoides (0.27), and lowest between reference Populus ×euroamericana clones and detected hybrid poplars (0.05) from natural localities. Distinct genetic structures were identified among P. nigra, P. deltoides, and hybrid individuals. These findings provide essential data for the protection, reproduction, and planting of black poplar. Full article