Forest Values Research Articles

Forest plant indicator values for moisture reflect atmospheric vapour pressure deficit rather than soil water content.

Soil moisture shapes ecological patterns and processes, but it is difficult to continuously measure soil moisture variability across the landscape. To overcome these limitations, soil moisture is often bioindicated using community-weighted means of the Ellenberg indicator values of vascular plant species. However, the ecology and distribution of plant species reflect soil water supply as well as atmospheric water demand. Therefore, we hypothesized that Ellenberg moisture values can also reflect atmospheric water demand expressed as a vapour pressure deficit (VPD). To test this hypothesis, we disentangled the relationships among soil water content, atmospheric vapour pressure deficit, and Ellenberg moisture values in the understory plant communities of temperate broadleaved forests in central Europe. Ellenberg moisture values reflected atmospheric VPD rather than soil water content consistently across local, landscape, and regional spatial scales, regardless of vegetation plot size, depth as well as method of soil moisture measurement. Using in situ microclimate measurements, we discovered that forest plant indicator values for moisture reflect an atmospheric VPD rather than soil water content. Many ecological patterns and processes correlated with Ellenberg moisture values and previously attributed to soil water supply are thus more likely driven by atmospheric water demand.

Quantifying the unseen benefits: an innovative economic valuation of the social and cultural values of trees, woods, and forests at risk

ABSTRACT Trees, woods, and forests in England are associated with a wide range of social and cultural values (S&CV). However, these treescapes (i.e. trees in any location) face increasing risks from pests, diseases, climate change, and biosecurity threats. This study addresses the urgent need for comprehensive estimates of S&CV related to England’s treescapes. Current UK policies and resource allocations are based on limited “value at risk” estimates. The study proposes a novel anchor value method for holistic S&CV valuation, resulting in an annual benefits flow ranging from £7 to £10 billion. This estimate surpasses the current natural capital accounts for England’s woodlands and underscores the importance of including S&CV in total ecosystem benefits assessments. The study also applies traditional methods, namely Willingness to Pay (WTP) and Travel Cost Method (TCM), to economically value S&CV of trees at risk from pests and diseases. These methods, focusing on local use values, yield similar estimates of just under £1 billion per year. This preliminary valuation invites further debate and scrutiny.

Extracting above-ground biomass in areas corresponding to FAO’s definition of “Forest” using open geospatial data: Results for ASEAN

Abstract. In this study, we extracted above-ground biomass (AGB) information for forests in different ecological zones of ASEAN (Association of Southeast Asian Nations) by integrating freely-available global AGB, forest, and ecological zone map products. Our objective was to assess the suitability of the data and proposed approach for national reporting of forest carbon stocks. We compared the satellite-derived AGB values of forests in ASEAN countries with the corresponding AGB values provided by the Intergovernmental Panel for Climate Change (IPCC) in their Guidelines for National Greenhouse Gas Inventories (which are derived from ground-based measurements of forest AGB). For this, we used a map integration approach that ensures that AGB data is extracted from areas corresponding to the Food and Agricultural Association (FAO) of the UN’s definitions of “forest” and “ecological zones”, as recommended by the relevant IPCC Guidelines. We found that the average satellite-derived AGB values extracted for each ecological zone were generally lower than the values for natural forests (but higher than the values for plantation forests) provided in the IPCC Guidelines. Further investigation showed that this was partly due to the presence of many erroneously low AGB values for forests in the extracted results, caused by errors in the data masks applied to the original global AGB map, including masks of cropland, urban areas, bare soil, and water bodies. Our findings suggest that further processing is necessary before using satellite-derived data for national reporting of forest carbon stocks in ASEAN countries, and we give a few possible options for this.

A global comparative analysis of local recreation behaviors and values in peri-urban forests

Recreation is an essential ecosystem service (ES) provided by urban and peri-urban forests. In the context of adapting forest management to social demands, it is important to understand recreation behavior and the value that people place on their recreation. This study presents a comparison of recreation behavior and willingness to pay (WTP) across four peri-urban forests located in Freiburg (Germany), Oakville (Canada), Xi'an (China) and Zomba (Malawi). WTP was asked under two contingent valuation scenarios, one to improve the forest management according to the respondents' preferences for forest characteristics and the other to sustain the forest under climate change impacts. We conducted on-site surveys, focusing on the inhabitants of the associated cities. While the recreationists were generally satisfied with the forest infrastructure (e.g., paths), they were rather dissatisfied with the facilities (e.g., sanitation and drinking water). The mean annual WTP (adjusted by purchasing-power-parity, PPP) to improve the forest management was 21.07US$ PPP in Freiburg, 18.53US$ PPP in Oakville, 8.32US$ PPP in Xi'an, and 3.52US$ PPP in Zomba. Under climate change impacts, the mean annual WTP was 27.96US$ PPP in Freiburg, 19.29US$ PPP in Oakville, 7.52US$ PPP in Xi'an, and 3.53US$ PPP in Zomba. The statistical analysis revealed a positive effect of income on WTP in Freiburg, Oakville, and Xi'an. In addition, in Freiburg, education increased WTP, while in Xi'an, younger participants were more likely to pay. In Freiburg and Zomba, belief in climate change was found to increase the probability of WTP under the climate change scenario. Regarding the payment vehicle, a local tax and a voluntary donation were preferred in Freiburg and Oakville, an entry fee in Xi'an, and there was no preference in Zomba.

Лихенобиота заказника «Лисинский» (Ленинградская область)

The revealed lichen diversity of the Lisinsky Protected Area counts 296 species, including 262 lichens, 20 lichenicolous fungi, and 14 non-lichenized saprobic fungi. The species Normandina chlorococca is reported for the first time for Russia, Gyalidea minuta, Lecanora substerilis, Lecidea betulicola, Vezdaea stipitata are new to the North-Western European Russia, and Fellhanera bouteillei is new to the Leningrad Region. The territory is represented by a significant diversity of lichens and related fungi, including 28 protected species, indicator species and habitat specialists of biologically valuable forests. The communities formed by old-growth spruces and aspens are of greatest value for the conservation of lichen biota, as far as in such biotopes the species associated with biologically valuable forests are most often found in complexes.

Mycobiota of the Maksimjarvi Planned Protected Area (Republic of Karelia, Russia)

This paper is a first report on the results of macrofungi studies in the planned protected area (PPA) Maksimjarvi, situated in the middle part of the Republic of Karelia, near the Finnish border. The forests there are predominantly north-boreal pine stands with a smaller proportion of spruce stands. The data were gathered during the fieldwork carried out in 2022 by O. Predtechenskaya and A. Ruokolainen and combined with data from Finnish colleagues carried out in 2012 and 2016. The records are supported by specimens deposited in the herbarium of the Karelian Research Centre RAS (PTZ) and Botanical Museum of the University of Helsinki (H). The current checklist for the Maksimjarvi territory includes 196 species of 121 genera, 57 families, 14 orders of aphyllophoroid, agaricoid and gasteroid fungi. The records include the first finding of Phellodon secretus in the Republic of Karelia, and 3 fungal species (Botryobasidium laeve, Peniophora septentrionalis, Phellodon secretus) were found for the first time in the biogeographic province Karelia pomorica occidentalis. Surveys of the Maksimjarvi PPA revealed 17 fungal species listed in the Red Data Book of the Republic of Karelia (2020). The area is known to harbor indicator and specialized fungal species of biologically valuable forests. The need to designate it as a conservation area is substantiated with regard to the ongoing formation of the PA system of the Green Belt of Fennoscandia and the Republic of Karelia.

Intergovernmental Panel on Climate Change (IPCC) Tier 1 forest biomass estimates from Earth Observation

Aboveground biomass density (AGBD) estimates from Earth Observation (EO) can be presented with the consistency standards mandated by United Nations Framework Convention on Climate Change (UNFCCC). This article delivers AGBD estimates, in the format of Intergovernmental Panel on Climate Change (IPCC) Tier 1 values for natural forests, sourced from National Aeronautics and Space Administration’s (NASA’s) Global Ecosystem Dynamics Investigation (GEDI) and Ice, Cloud and land Elevation Satellite (ICESat-2), and European Space Agency’s (ESA’s) Climate Change Initiative (CCI). It also provides the underlying classification used by the IPCC as geospatial layers, delineating global forests by ecozones, continents and status (primary, young (≤20 years) and old secondary (>20 years)). The approaches leverage complementary strengths of various EO-derived datasets that are compiled in an open-science framework through the Multi-mission Algorithm and Analysis Platform (MAAP). This transparency and flexibility enables the adoption of any new incoming datasets in the framework in the future. The EO-based AGBD estimates are expected to be an independent contribution to the IPCC Emission Factors Database in support of UNFCCC processes, and the forest classification expected to support the generation of other policy-relevant datasets while reflecting ongoing shifts in global forests with climate change.

Explainable artificial intelligence on safe balance and its major determinants in stroke patients

This study develops explainable artificial intelligence for predicting safe balance using hospital data, including clinical, neurophysiological, and diffusion tensor imaging properties. Retrospective data from 92 first-time stroke patients from January 2016 to June 2023 was analysed. The dependent variables were independent mobility scores, i.e., Berg Balance Scales with 0 (45 or below) vs. 1 (above 45) measured after three and six months, respectively. Twenty-nine predictors were included. Random forest variable importance was employed for identifying significant predictors of the Berg Balance Scale and testing its associations with the predictors, including Berg Balance Scale after one month and corticospinal tract diffusion tensor imaging properties. Shapley Additive Explanation values were calculated to analyse the directions of these associations. The random forest registered a higher or similar area under the curve compared to logistic regression, i.e., 91% vs. 87% (Berg Balance Scale after three months), 92% vs. 92% (Berg Balance Scale after six months). Based on random forest variable importance values and rankings: (1) Berg Balance Scale after three months has strong associations with Berg Balance Scale after one month, Fugl-Meyer assessment scale, ipsilesional corticospinal tract fractional anisotropy, fractional anisotropy laterality index and age; (2) Berg Balance Scale after six months has strong relationships with Fugl-Meyer assessment scale, Berg Balance Scale after one month, ankle plantar flexion muscle strength, knee extension muscle strength and hip flexion muscle strength. These associations were positive in the SHAP summary plots. Including Berg Balance Scale after one month, Fugl-Meyer assessment scale or ipsilesional corticospinal tract fractional anisotropy in the random forest will increase the probability of Berg Balance Scale after three months being above 45 by 0.11, 0.08, or 0.08. In conclusion, safe balance after stroke strongly correlates with its initial motor function, Fugl-Meyer assessment scale, and ipsilesional corticospinal tract fractional anisotropy. Diffusion tensor imaging information aids in developing explainable artificial intelligence for predicting safe balance after stroke.

Integrating basic human values with forest ecosystem services: pathways to sustainable forest management.

The article explores the intricate relationship between basic human values and forest ecosystem services (FES). The study highlights the critical role that forests play in providing essential services for biodiversity, forest products, climate stabilization and human well-being, and emphasizes the need to understand and integrate human values into forest management and planning. Through a novel approach, this study explores how the concept of "forest" can elicit considerations of fundamental human values that diverge from conventional classifications and measurements of forest values. The study uses a comprehensive methodology, including surveys and content analysis, to uncover the hierarchical structure of human values associated with forests. This approach enables the identification of fundamental values that remain constant despite situational variations. The main results reveal a hierarchical structure of values, with Apollonian values being more prevalent than Dionysian ones. The study shows significant differences in the importance attributed to different FES, reflecting underlying value differences between residents. The study makes a novel contribution by systematically examining the links between human values and FES and proposing a profound and sustainable approach to forest management that takes into account the psychological dimensions of human-forest interactions. The study suggests that recognizing and incorporating the intrinsic human values into forest ecosystem service frameworks can improve sustainable forest management practices and ultimately foster a deeper connection between people and the forest environment.

Total deposition of sulphur to coniferous forests in Sweden - Taking canopy exchange into account

In the low deposition situation of today at many of the long-term Swedish forest monitoring sites, the deposition measured as precipitation to the open field, i.e. bulk deposition of oxidized sulphur (S) is often higher or equal to deposition of S sampled under the forest canopies, i.e. as throughfall. This suggests that the total S deposition estimated using throughfall is underestimated. The reason for this is direct exchange of S with the forest canopies, leading to an underestimation which becomes evident in low-deposition areas. We describe a new method to estimate the dry deposition of S to coniferous forest based on measurements with Teflon string samplers as surrogate surfaces, in combination with measurements of the net throughfall for sodium (throughfall subtracted with wet deposition). The wet deposition was estimated from bulk deposition measurements on the open field, corrected for dry deposition to the collectors. The method was applied for Norway spruce forests at monitoring sites across Sweden during nine years 2014–2022, and total deposition was calculated based on wet deposition and the estimated dry deposition. The estimated annual total deposition of S as a mean value for coniferous forests ranged between 0.8 and 5.2 kg S ha−1 yr−1 with lowest values in northern Sweden and highest in southwest Sweden. The share of dry deposition of the total S deposition was between 20 and 53%. The mean annual deposition of S measured as throughfall during 2014–2022 for three different regions in Sweden was between 16 and 41% lower compared to the corresponding total deposition estimated with the new method. The canopy exchange of S was analyzed on a monthly basis as the difference between the estimated total deposition and the measured throughfall deposition of S. At most sites, there was a canopy uptake of S during the summer months and a leakage of S during the winter months. This indicates that the canopy exchange of S is a phenomenon that involves some biological activity.

A study on the identification of factors related to depression in a population with an increasing number of chronic diseases in the short term in China based on a health ecology model

BackgroundThe rapid increase in the number of patients with chronic diseases and depression, as well as the rapid spread of their effects, have led to these two health problems gradually developing into major public health issues in China and around the world. Currently, many individuals with chronic diseases are experiencing depressive symptoms one after another. Therefore, it is imperative to conduct research on how to prevent depression in this growing population of individuals with chronic diseases in a timely manner. MethodsBased on the data of the 2015 and 2018 national follow-up surveys of the China Health and Retirement Longitudinal Study, a total of 7641 patients with short-term increase in the number of chronic diseases were selected as the study objects, and a binary logistic regression model was constructed according to the five dimensions of the health ecology model. The neural network model was used to explore the main (first two) factors affecting the increase in the number of chronic diseases in China in the short term, and the random forest and extreme value gradient lifting algorithm were used to verify them, and effective suggestions were put forward. ResultsThe detection rate of depression in the population with increasing number of chronic diseases from 2015 to 2018 was 42.13 %. The model was established based on five dimensions of the health ecology model: Model 1 (Personal trait layer), Model 2 (Personal trait layer plus Behavioral feature layer), Model 3 (Personal trait layer plus Behavioral feature layer plus Living and working conditions layer), Model 4 (Personal trait layer plus Behavioral feature layer plus Living and working conditions layer plus Networking layer) and Model 5 (Personal trait layer plus Behavioral feature layer plus Living and working conditions layer plus Networking layer plus Policy environment layer).The prediction accuracy of the five models was 66.4 %, 68.3 %, 70.7 %, 71.6 % and 71.6 %, respectively, and Model 5 showed that the P values of gender, self-rated health, night's sleep time (h), disability, life satisfaction, child satisfaction, place of residence and highest level of education were all <0.05, life satisfaction and self-rated health importance were 0.249 (100 %) and 0.226 (90.8 %). ConclusionGender, self-rated health, night sleep duration, disability, satisfaction with life, satisfaction with children, place of residence and highest level of education were the main influencing factors for the increase of depressive symptoms in the population with chronic diseases in the short term, among which life satisfaction and self-rated health have the greatest impact on depressive symptoms, and there is an interaction between the two.

Second-hand car price prediction based on multiple linear regression and random forest

The second-hand car market is a hot topic. Buying a second-hand car has advantages in price and many other aspects. Therefore, it is important to establish a good price prediction model. This paper will explore the factors that affect the price of second-hand cars. After analyzing and learning many kinds of literature, this paper establishes a multiple linear regression model and a random forest model and makes a comparative analysis of the model effect. The sum of the square error and R-square value of the random forest are better than the multiple linear regression model. Among the factors affecting the price of second-hand cars, the year of production has the greatest impact on the price, which shows that the age of the year is an important factor in determining the price of second-hand cars. The next most important factor is the number of kilometers traveled, followed by fuel type and transmission type-finally, engine displacement, number of transfers and number of seats. The random forest model established in this paper has better application value to price prediction.

Treatment effect analysis of the Frailty Care Bundle (FCB) in a cohort of patients in acute care settings

PurposeThe aim of this study is to explore the feasibility of using machine learning approaches to objectively differentiate the mobilization patterns, measured via accelerometer sensors, of patients pre- and post-intervention.MethodsThe intervention tested the implementation of a Frailty Care Bundle to improve mobilization, nutrition and cognition in older orthopedic patients. The study recruited 120 participants, a sub-group analysis was undertaken on 113 patients with accelerometer data (57 pre-intervention and 56 post-intervention), the median age was 78 years and the majority were female. Physical activity data from an ankle-worn accelerometer (StepWatch 4) was collected for each patient during their hospital stay. These data contained daily aggregated gait variables. Data preprocessing included the standardization of step counts and feature computation. Subsequently, a binary classification model was trained. A systematic hyperparameter optimization approach was applied, and feature selection was performed. Two classifier models, logistic regression and Random Forest, were investigated and Shapley values were used to explain model predictions.ResultsThe Random Forest classifier demonstrated an average balanced accuracy of 82.3% (± 1.7%) during training and 74.7% (± 8.2%) for the test set. In comparison, the logistic regression classifier achieved a training accuracy of 79.7% (± 1.9%) and a test accuracy of 77.6% (± 5.5%). The logistic regression model demonstrated less overfitting compared to the Random Forest model and better performance on the hold-out test set. Stride length was consistently chosen as a key feature in all iterations for both models, along with features related to stride velocity, gait speed, and Lyapunov exponent, indicating their significance in the classification.ConclusionThe best performing classifier was able to distinguish between patients pre- and post-intervention with greater than 75% accuracy. The intervention showed a correlation with higher gait speed and reduced stride length. However, the question of whether these alterations are part of an adaptive process that leads to improved outcomes over time remains.

From resources to capital: Investigating the efficiency of forest ecosystem products value realization in China

Forest resources provide a good ecological environment for human beings and offer economic well-being and benefits. Value realization of ecosystem products reflects the process from resources to capital. This study investigates the two-stage value realization efficiency of China's forest ecosystem products from 2011 to 2021. A parallel nested network Data Envelopment Analysis model is applied to assess product supply and value transformation stages. In addition, the evolution of the spatial pattern is depicted by a multilayer Standard Deviational Ellipse. The results reveal that (1) the overall value realization trend of China's forest ecosystem products shows a fluctuating growth trend, with an average annual efficiency value of 0.86. (2) The efficiency level of the value transformation stage is lower than that of the product supply stage. (3) Regional disparities persist. The efficiency values in East China and South China are higher than that in other regions. (4) The value realization capacity of China's forest ecosystem products may be closely related to national development strategies and policy orientations.

Effects of crown condition, tree damage, and site Quality on forest health in Gapoktan Wana Karya I

Forests are land in which there are flora and fauna life that are symbiotic with each other so as to form various ecosystems. Forests have a very important role for the components that make up them and for the surrounding environment. Damage that occurs to trees and their constituent soil can disrupt the ecosystem in them which can have an impact on the function of the forest. The importance of the role of forests for the surrounding environment, it is necessary to monitor the health condition of forests to have benefits so that forests are monitored for sustainability so that forests can carry out their functions optimally. This study aims to find the value of forest health conditions in land cultivated by Gapoktan Wana Karya I (Gapoktan WK) and to determine the influence of tree damage indicators, header conditions, and site quality on forest health. The forest health condition in this study was monitored through three indicators, namely tree damage, header condition, and site quality with Forest Health Monitoring (FHM) as the method. Then for the influence use simple linear regression. The results of the research on forest health conditions in Gapoktan WK showed an average value of 4.5, which was included in the medium category. The results of the simple linear regression analysis showed that the indicators of canopy condition and site quality had a unidirectional influence on forest health while the tree damage indicators had an influence but in the opposite direction on the forest health value.

Mycobiota of the planned protected area Nyuk Lake (Republic of Karelia, Russia)

The article reports the results of macrofungi surveys in the planned protected area Lake Nyuk (pPA), situated in the north-west of the Republic of Karelia. The forests there are primarily north-boreal pine stands with pine trees aged 170—250 years at maximum. As of now, records from the pPA include 183 species of 114 genera of aphyllophoroid and agaricoid fungi. The annotation for each species specifies their habitats and occurrence. Seven species are reported for the biogeographical province Karelia pomorica occidentalis for the first time; of which two species, Hydnellum gracilipes and Tubulicrinis medius, are first records for the Republic of Karelia. The territory was found to harbor nine fungal species (Anthoporia albobrunnea, Diplomitoporus crustulinus, Flavidoporia mellita, Gloeophyllum protractum, Resinoporia crassa, Rhodonia placenta, Sidera lenis, Skeletocutis sajanensis, S. stellae) red-listed in the Republic of Karelia (2020). Locations of 13 indicator species and 16 specialist species of biologically valuable forests are known within the pPA. The findings are validated by the herbarium specimens stored at the Karelian Research Centre RAS Herbarium (PTZ) and Botanical Museum of the University of Helsinki (H). The rationale for establishing a nature conservation area in the territory is provided.

Evaluating financing risk for forest recreation value development project—A case study focused on S National Forest Park in Fujian Province

In the process of forest recreation value development, there are some characteristics, such as large amount of investment capital, long financing recovery cycle and high potential risks, which lead to limited capital source and prominent financing risks. To achieve sustainable development, forest recreational value development enterprises must solve the financing dilemma, therefore, it is very urgent to identify the financing risk factors. The research constructed financing risk evaluation index system through WSR (Wuli-Shili-Renli) methodology (from affair law, matter principle and human art dimensions), taking S National Forest Park at Fujian Province as a case study, the analytic hierarchy process (AHP) and fuzzy comprehensive evaluation method were used for empirical analysis. The results showed that for the first level indicators, operational risk should be paid close attention to, followed by political risk and environmental risk. Among the secondary level indicators, policy changes, financing availability and market demand need attention, which are consistent with the result of field survey. Based on that, countermeasures were put forward such as the multiple collaborative linkage and effective internal control; reduction on operating costs and broaden financing channels; encouragement diversification of investment entities and improvement of financial and credit support; strengthening government credit supervision, optimizing financing risk evaluation, and building a smart tourism financing information platform, to reduce and control financing risks, then promote the development of forest recreation value projects.

Characterization of Forest Soil Acidification in Wenzhou Daluoshan and Zhejiang Wuyanling National Nature Reserve

Forest soil acidification is a global environmental problem, and forest ecosystems play an important role in terrestrial ecosystems. To provide a theoretical basis for the sustainable development of areas, this study selected Daluoshan and Wuyanling National Nature Reserve, Wenzhou, Zhejiang Province, China and determined the characteristics of soil acidification in the two forested areas and the relationship between forest soil acidification and soil physicochemical properties. The forest soil pH value of Daluoshan was 4.25–5.40, and that of Wuyanling was 4.14–5.71. There was a significant difference between the mean soil pH values of the two woodlands (p &lt; 0.01). The two forest soils were dominated by strongly acidic soils, and the top layer of the soils was susceptible to disturbances by environmental factors. With the increase in altitude, different layers of soil in the forests in the two woodland areas showed deepening acidification. Regarding the different plant types and slope directions, the soils under trees in the forests showed the most serious acidification, followed by the soils under shrubs and herbs. Compared with the soils on the leeward slopes, the soils of the forest sites on the windward slopes showed a more severe situation of soil acidification. Redundancy analysis between forest soil acidity indicators and soil physicochemical properties in the two forest sites showed that the main environmental factor affecting soil acidity indicators was salt base saturation, and soil pH and active state Cr, Ni, and Pb showed negative correlations in both forest sites.

Predicting 30-day mortality in severely injured elderly patients with trauma in Korea using machine learning algorithms: a retrospective study.

The number of elderly patients with trauma is increasing; therefore, precise models are necessary to estimate the mortality risk of elderly patients with trauma for informed clinical decision-making. This study aimed to develop machine learning based predictive models that predict 30-day mortality in severely injured elderly patients with trauma and to compare the predictive performance of various machine learning models. This study targeted patients aged ≥65 years with an Injury Severity Score of ≥15 who visited the regional trauma center at Chungbuk National University Hospital between 2016 and 2022. Four machine learning models-logistic regression, decision tree, random forest, and eXtreme Gradient Boosting (XGBoost)-were developed to predict 30-day mortality. The models' performance was compared using metrics such as area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, specificity, F1 score, as well as Shapley Additive Explanations (SHAP) values and learning curves. The performance evaluation of the machine learning models for predicting mortality in severely injured elderly patients with trauma showed AUC values for logistic regression, decision tree, random forest, and XGBoost of 0.938, 0.863, 0.919, and 0.934, respectively. Among the four models, XGBoost demonstrated superior accuracy, precision, recall, specificity, and F1 score of 0.91, 0.72, 0.86, 0.92, and 0.78, respectively. Analysis of important features of XGBoost using SHAP revealed associations such as a high Glasgow Coma Scale negatively impacting mortality probability, while higher counts of transfused red blood cells were positively correlated with mortality probability. The learning curves indicated increased generalization and robustness as training examples increased. We showed that machine learning models, especially XGBoost, can be used to predict 30-day mortality in severely injured elderly patients with trauma. Prognostic tools utilizing these models are helpful for physicians to evaluate the risk of mortality in elderly patients with severe trauma.

Recovering connectivity through restoration corridors in a fragmented landscape in the magdalena river’s valley in Colombia

Forest fragmentation is one of the main drivers of global biodiversity loss leading to the isolation of wildlife populations. This study focuses on understanding the role of restoration corridors as a strategy promoting resilience and viability of mammal and bird populations in a fragmented landscape in Colombia. We installed 98 camera-trap stations − 8497 camera-trap days - in four different land cover categories: (1) forest fragments, (2) natural corridors, (3) stablished corridors and (4) pastures. We evaluated if restoration corridors do promote connectivity for large vertebrates and recover species richness and functional diversity lost in anthropogenically transformed pastures. We used indices of taxonomic and functional diversity and a non-metric multidimensional scaling to evaluate the influence of land cover over mammal and bird communities. Both, species richness and functional diversity have higher values in forests, followed by natural corridors and corridors and lower values in open pastures. Differences in species composition were greater between forests and pastures, and species composition of restoration corridors begins to resemble that of riparian forests and forest fragments. Our results provide initial evidence on the role of restoration corridors as an efficient strategy aimed to recover biodiversity and functional diversity in pervasively fragmented landscapes.