基于Deep Forest算法的对虾急性肝胰腺坏死病(AHPND)预警数学模型构建

为预报池塘养殖凡纳对虾(Penaeus vannamei)急性肝胰腺坏死病(AHPND)的发生,自2020年开始,笔者对凡纳对虾养殖区开展了连续监测工作,包括与疾病发生相关的环境理化因子、微生物因子、虾体自身健康状况等18个候选预警因子指标,通过数据标准化处理后分析病原、宿主与环境之间的相关性,对候选预警因子进行筛选,基于Python语言编程结合Deep Forest、Light GBM、XGBoost算法进行数据建模和预测性能评判,仿真环境为Python2.7,以预警因子指标作为输入样本(即警兆),以对虾是否发病指标作为输出结果(即警情),根据输入样本和输出结果各自建立输入数据矩阵和目标数据矩阵,利用原始数据矩阵对输入样本进行初始化,结合函数方程进行拟合,拟合的源代码能利用已知环境、病原及对虾免疫指标数据对目标警情进行预测。最终建立了基于Deep Forest算法的虾体(肝胰腺内)细菌总数、虾体弧菌(Vibrio)占比、水体细菌总数和盐度的4维向量预警预报模型,准确率达89.00%。本研究将人工智能算法应用到对虾AHPND发生的预测预报,相关研究结果为对虾AHPND疾病预警预报建立了预警数学模型,并为对虾健康养殖和疾病防控提供了技术支撑和有力保障。

收入分配差距与银行信用风险累积——基于企业部门杠杆的视角

改善收入分配状况、推进共同富裕是否有助于防范化解金融风险?立足于企业部门杠杆视角,构建包含家庭异质性、企业债务违约和银行破产特质的实际经济周期(RBC)模型,研究居民收入分配差距对银行信用风险的影响。理论模型预测显示,收入分配差距扩大会提高企业部门杠杆率,增加银行信用风险累积。其作用机制在于,收入分配差距扩大导致消费投资比下降,为企业部门加杠杆创造条件,但消费率和杠杆率的反向变动会造成企业实际收益率降低和违约风险上升,银行贷款信用风险敞口扩大。基于中国银行业数据的实证分析提供了上述理论推演成立的经验证据与微观基础。此外,本文还发现收入分配差距的影响存在地区性差异。上述结论隐含共同富裕目标的实现有利于守住不发生系统性风险底线,两个重大目标的内在逻辑自洽一致。

Predicting short-term major postoperative complications in intestinal resection for Crohn’s disease:A machine learning-based study

BACKGROUND Due to the complexity and numerous comorbidities associated with Crohn’s disease(CD),the incidence of postoperative complications is high,significantly impacting the recovery and prognosis of patients.Consequently,additional stu-dies are required to precisely predict short-term major complications following intestinal resection(IR),aiding surgical decision-making and optimizing patient care.AIM To construct novel models based on machine learning(ML)to predict short-term major postoperative complications in patients with CD following IR.METHODS A retrospective analysis was performed on clinical data derived from a patient cohort that underwent IR for CD from January 2017 to December 2022.The study participants were randomly allocated to either a training cohort or a validation cohort.The logistic regression and random forest(RF)were applied to construct models in the training cohort,with model discrimination evaluated using the area under the curves(AUC).The validation cohort assessed the performance of the constructed models.RESULTS Out of the 259 patients encompassed in the study,5.0%encountered major postoperative complications(Clavien-Dindo≥III)within 30 d following IR for CD.The AUC for the logistic model was 0.916,significantly lower than the AUC of 0.965 for the RF model.The logistic model incorporated a preoperative CD activity index(CDAI)of≥220,a diminished preoperative serum albumin level,conversion to laparotomy surgery,and an extended operation time.A nomogram for the logistic model was plotted.Except for the surgical approach,the other three variables ranked among the top four important variables in the novel ML model.CONCLUSION Both the nomogram and RF exhibited good performance in predicting short-term major postoperative complic-ations in patients with CD,with the RF model showing more superiority.A preoperative CDAI of≥220,a di-minished preoperative serum albumin level,and an extended operation time might be the most crucial variables.The findings of this study can assist clinicians in identifying patients at a higher risk for complications and offering personalized perioperative management to enhance patient outcomes.

Severe Global Environmental Issues Caused by Canada’s Record-Breaking Wildfires in 2023

Due to the record-breaking wildfires that occurred in Canada in 2023,unprecedented quantities of air pollutants and greenhouse gases were released into the atmosphere.The wildfires had emitted more than 1.3 Pg CO_(2)and 0.14 Pg CO_(2)equivalent of other greenhouse gases(GHG)including CH4 and N_(2)O as of 31 August.The wildfire-related GHG emissions constituted more than doubled Canada’s planned cumulative anthropogenic emissions reductions in 10 years,which represents a significant challenge to climate mitigation efforts.The model simulations showed that the Canadian wildfires impacted not only the local air quality but also that of most areas in the northern hemisphere due to long-range transport,causing severe PM_(2.5)pollution in the northeastern United States and increasing daily mean PM_(2.5)concentration in northwestern China by up to 2μg m-3.The observed maximum daily mean PM_(2.5)concentration in New York City reached 148.3μg m-3,which was their worst air quality in more than 50 years,nearly 10 times that of the air quality guideline(i.e.,15μg m-3)issued by the World Health Organization(WHO).Aside from the direct emissions from forest fires,the peat fires beneath the surface might smolder for several months or even longer and release substantial amounts of CO_(2).The substantial amounts of greenhouse gases from forest and peat fires might contribute to the positive feedback to the climate,potentially accelerating global warming.To better understand the comprehensive environmental effects of wildfires and their interactions with the climate system,more detailed research based on advanced observations and Earth System Models is essential.

How do the landslide and non-landslide sampling strategies impact landslide susceptibility assessment? d A catchment-scale case study from China

The aim of this study is to investigate the impacts of the sampling strategy of landslide and non-landslide on the performance of landslide susceptibility assessment(LSA).The study area is the Feiyun catchment in Wenzhou City,Southeast China.Two types of landslides samples,combined with seven non-landslide sampling strategies,resulted in a total of 14 scenarios.The corresponding landslide susceptibility map(LSM)for each scenario was generated using the random forest model.The receiver operating characteristic(ROC)curve and statistical indicators were calculated and used to assess the impact of the dataset sampling strategy.The results showed that higher accuracies were achieved when using the landslide core as positive samples,combined with non-landslide sampling from the very low zone or buffer zone.The results reveal the influence of landslide and non-landslide sampling strategies on the accuracy of LSA,which provides a reference for subsequent researchers aiming to obtain a more reasonable LSM.

Implication of community-level ecophysiological parameterization to modelling ecosystem productivity:a case study across nine contrasting forest sites in eastern China

Parameterization is a critical step in modelling ecosystem dynamics.However,assigning parameter values can be a technical challenge for structurally complex natural plant communities;uncertainties in model simulations often arise from inappropriate model parameterization.Here we compared five methods for defining community-level specific leaf area(SLA)and leaf C:N across nine contrasting forest sites along the North-South Transect of Eastern China,including biomass-weighted average for the entire plant community(AP_BW)and four simplified selective sampling(biomass-weighted average over five dominant tree species[5DT_BW],basal area weighted average over five dominant tree species[5DT_AW],biomass-weighted average over all tree species[AT_BW]and basal area weighted average over all tree species[AT_AW]).We found that the default values for SLA and leaf C:N embedded in the Biome-BGC v4.2 were higher than the five computational methods produced across the nine sites,with deviations ranging from 28.0 to 73.3%.In addition,there were only slight deviations(<10%)between the whole plant community sampling(AP_BW)predicted NPP and the four simplified selective sampling methods,and no significant difference between the predictions of AT_BW and AP_BW except the Shennongjia site.The findings in this study highlights the critical importance of computational strategies for community-level parameterization in ecosystem process modelling,and will support the choice of parameterization methods.

Dendroclimatological study of Sabina saltuaria and Abies faxoniana in the mixed forests of the Qionglai Mountains,eastern Tibetan Plateau

Tree-ring chronologies were developed for Sabina saltuaria and Abies faxoniana in mixed forests in the Qionglai Mountains of the eastern Tibetan Plateau.Climate-growth relationship analysis indicated that the two co-exist-ing species reponded similarly to climate factors,although S.saltuaria was more sensitive than A.faxoniana.The strong-est correlation was between S.saltuaria chronology and regional mean temperatures from June to November.Based on this relationship,a regional mean temperature from June to November for the period 1605-2016 was constructed.Reconstruction explained 37.3%of the temperature variance during th period 1961-2016.Six major warm periods and five major cold periods were identified.Spectral analysis detected significant interannual and multi-decadal cycles.Reconstruction also revealed the influence of the Atlantic Multi-decadal Oscillation,confirming its importance on climate change on the eastern Tibetan Plateau.

Enhancing rock fragmentation prediction in mining operations:A hybrid GWO-RF model with SHAP interpretability

In the mining industry,precise forecasting of rock fragmentation is critical for optimising blasting processes.In this study,we address the challenge of enhancing rock fragmentation assessment by developing a novel hybrid predictive model named GWO-RF.This model combines the grey wolf optimization(GWO)algorithm with the random forest(RF)technique to predict the D_(80)value,a critical parameter in evaluating rock fragmentation quality.The study is conducted using a dataset from Sarcheshmeh Copper Mine,employing six different swarm sizes for the GWO-RF hybrid model construction.The GWO-RF model’s hyperparameters are systematically optimized within established bounds,and its performance is rigorously evaluated using multiple evaluation metrics.The results show that the GWO-RF hybrid model has higher predictive skills,exceeding traditional models in terms of accuracy.Furthermore,the interpretability of the GWO-RF model is enhanced through the utilization of SHapley Additive exPlanations(SHAP)values.The insights gained from this research contribute to optimizing blasting operations and rock fragmentation outcomes in the mining industry.

Aboveground carbon sequestration of Cunninghamia lanceolata forests:Magnitude and drivers

Understanding the spatial variation,temporal changes,and their underlying driving forces of carbon sequestration in various forests is of great importance for understanding the carbon cycle and carbon management options.How carbon density and sequestration in various Cunninghamia lanceolata forests,extensively cultivated for timber production in subtropical China,vary with biodiversity,forest structure,environment,and cultural factors remain poorly explored,presenting a critical knowledge gap for realizing carbon sequestration supply potential through management.Based on a large-scale database of 449 permanent forest inventory plots,we quantified the spatial-temporal heterogeneity of aboveground carbon densities and carbon accumulation rates in Cunninghamia lanceolate forests in Hunan Province,China,and attributed the contributions of stand structure,environmental,and management factors to the heterogeneity using quantile age-sequence analysis,partial least squares path modeling(PLS-PM),and hot-spot analysis.The results showed lower values of carbon density and sequestration on average,in comparison with other forests in the same climate zone(i.e.,subtropics),with pronounced spatial and temporal variability.Specifically,quantile regression analysis using carbon accumulation rates along an age sequence showed large differences in carbon sequestration rates among underperformed and outperformed forests(0.50 and 1.80 Mg·ha^(-1)·yr^(-1)).PLS-PM demonstrated that maximum DBH and stand density were the main crucial drivers of aboveground carbon density from young to mature forests.Furthermore,species diversity and geotopographic factors were the significant factors causing the large discrepancy in aboveground carbon density change between low-and high-carbon-bearing forests.Hotspot analysis revealed the importance of culture attributes in shaping the geospatial patterns of carbon sequestration.Our work highlighted that retaining largesized DBH trees and increasing shade-tolerant tree species were important to enhance carbon sequestration in C.lanceolate forests.

GATIS score for predicting the prognosis of rectal neuroendocrine neoplasms:A Chinese multicenter study of 12-year experience

BACKGROUND There is currently a shortage of accurate,efficient,and precise predictive instruments for rectal neuroendocrine neoplasms(NENs).AIM To develop a predictive model for individuals with rectal NENs(R-NENs)using data from a large cohort.METHODS Data from patients with primary R-NENs were retrospectively collected from 17 large-scale referral medical centers in China.Random forest and Cox proportional hazard models were used to identify the risk factors for overall survival and progression-free survival,and two nomograms were constructed.RESULTS A total of 1408 patients with R-NENs were included.Tumor grade,T stage,tumor size,age,and a prognostic nutritional index were important risk factors for prognosis.The GATIS score was calculated based on these five indicators.For overall survival prediction,the respective C-indexes in the training set were 0.915(95%confidence interval:0.866-0.964)for overall survival prediction and 0.908(95%confidence interval:0.872-0.944)for progression-free survival prediction.According to decision curve analysis,net benefit of the GATIS score was higher than that of a single factor.The time-dependent area under the receiver operating characteristic curve showed that the predictive power of the GATIS score was higher than that of the TNM stage and pathological grade at all time periods.CONCLUSION The GATIS score had a good predictive effect on the prognosis of patients with R-NENs,with efficacy superior to that of the World Health Organization grade and TNM stage.

Dynamic Hand Gesture-Based Person Identification Using Leap Motion and Machine Learning Approaches

Person identification is one of the most vital tasks for network security. People are more concerned about theirsecurity due to traditional passwords becoming weaker or leaking in various attacks. In recent decades, fingerprintsand faces have been widely used for person identification, which has the risk of information leakage as a resultof reproducing fingers or faces by taking a snapshot. Recently, people have focused on creating an identifiablepattern, which will not be reproducible falsely by capturing psychological and behavioral information of a personusing vision and sensor-based techniques. In existing studies, most of the researchers used very complex patternsin this direction, which need special training and attention to remember the patterns and failed to capturethe psychological and behavioral information of a person properly. To overcome these problems, this researchdevised a novel dynamic hand gesture-based person identification system using a Leap Motion sensor. Thisstudy developed two hand gesture-based pattern datasets for performing the experiments, which contained morethan 500 samples, collected from 25 subjects. Various static and dynamic features were extracted from the handgeometry. Randomforest was used to measure feature importance using the Gini Index. Finally, the support vectormachinewas implemented for person identification and evaluate its performance using identification accuracy. Theexperimental results showed that the proposed system produced an identification accuracy of 99.8% for arbitraryhand gesture-based patterns and 99.6% for the same dynamic hand gesture-based patterns. This result indicatedthat the proposed system can be used for person identification in the field of security.

Community structure and species diversity dynamics of a subtropical evergreen broad-leaved forest in China:2005 to 2020

Here,we characterize the temporal and spatial dynamics of forest community structure and species diversity in a subtropical evergreen broad-leaved forest in China.We found that community structure in this forest changed over a 15-year period.Specifically,renewal and death of common species was large,with the renewal of individuals mainly concentrated within a few populations,especially those of Aidia canthioides and Cryptocarya concinna.The numbers of individual deaths for common species were concentrated in the small and mid-diameter level.The spatial distribution of community species diversity fluctuated in each monitoring period,showing a more dispersed diversity after the 15-year study period,and the coefficient of variation on quadrats increased.In 2010,the death and renewal of the community and the spatial variation of species diversity were different compared to other survey years.Extreme weather may have affected species regeneration and community stability in our subtropical monsoon evergreen broad-leaved forests.Our findings suggest that strengthening the monitoring and management of the forest community will help better understand the long-and short-term causes of dynamic fluctuations of community structure and species diversity,and reveal the factors that drive changes in community structure.

Uncertainties in landslide susceptibility prediction:Influence rule of different levels of errors in landslide spatial position

The accuracy of landslide susceptibility prediction(LSP)mainly depends on the precision of the landslide spatial position.However,the spatial position error of landslide survey is inevitable,resulting in considerable uncertainties in LSP modeling.To overcome this drawback,this study explores the influence of positional errors of landslide spatial position on LSP uncertainties,and then innovatively proposes a semi-supervised machine learning model to reduce the landslide spatial position error.This paper collected 16 environmental factors and 337 landslides with accurate spatial positions taking Shangyou County of China as an example.The 30e110 m error-based multilayer perceptron(MLP)and random forest(RF)models for LSP are established by randomly offsetting the original landslide by 30,50,70,90 and 110 m.The LSP uncertainties are analyzed by the LSP accuracy and distribution characteristics.Finally,a semi-supervised model is proposed to relieve the LSP uncertainties.Results show that:(1)The LSP accuracies of error-based RF/MLP models decrease with the increase of landslide position errors,and are lower than those of original data-based models;(2)70 m error-based models can still reflect the overall distribution characteristics of landslide susceptibility indices,thus original landslides with certain position errors are acceptable for LSP;(3)Semi-supervised machine learning model can efficiently reduce the landslide position errors and thus improve the LSP accuracies.

Coupling Analysis of Multiple Machine Learning Models for Human Activity Recognition

Artificial intelligence(AI)technology has become integral in the realm of medicine and healthcare,particularly in human activity recognition(HAR)applications such as fitness and rehabilitation tracking.This study introduces a robust coupling analysis framework that integrates four AI-enabled models,combining both machine learning(ML)and deep learning(DL)approaches to evaluate their effectiveness in HAR.The analytical dataset comprises 561 features sourced from the UCI-HAR database,forming the foundation for training the models.Additionally,the MHEALTH database is employed to replicate the modeling process for comparative purposes,while inclusion of the WISDM database,renowned for its challenging features,supports the framework’s resilience and adaptability.The ML-based models employ the methodologies including adaptive neuro-fuzzy inference system(ANFIS),support vector machine(SVM),and random forest(RF),for data training.In contrast,a DL-based model utilizes one-dimensional convolution neural network(1dCNN)to automate feature extraction.Furthermore,the recursive feature elimination(RFE)algorithm,which drives an ML-based estimator to eliminate low-participation features,helps identify the optimal features for enhancing model performance.The best accuracies of the ANFIS,SVM,RF,and 1dCNN models with meticulous featuring process achieve around 90%,96%,91%,and 93%,respectively.Comparative analysis using the MHEALTH dataset showcases the 1dCNN model’s remarkable perfect accuracy(100%),while the RF,SVM,and ANFIS models equipped with selected features achieve accuracies of 99.8%,99.7%,and 96.5%,respectively.Finally,when applied to the WISDM dataset,the DL-based and ML-based models attain accuracies of 91.4%and 87.3%,respectively,aligning with prior research findings.In conclusion,the proposed framework yields HAR models with commendable performance metrics,exhibiting its suitability for integration into the healthcare services system through AI-driven applications.

Clinical study of different prediction models in predicting diabetic nephropathy in patients with type 2 diabetes mellitus

BACKGROUND Among older adults,type 2 diabetes mellitus(T2DM)is widely recognized as one of the most prevalent diseases.Diabetic nephropathy(DN)is a frequent com-plication of DM,mainly characterized by renal microvascular damage.Early detection,aggressive prevention,and cure of DN are key to improving prognosis.Establishing a diagnostic and predictive model for DN is crucial in auxiliary diagnosis.AIM To investigate the factors that impact T2DM complicated with DN and utilize this information to develop a predictive model.METHODS The clinical data of 210 patients diagnosed with T2DM and admitted to the First People’s Hospital of Wenling between August 2019 and August 2022 were retrospectively analyzed.According to whether the patients had DN,they were divided into the DN group(complicated with DN)and the non-DN group(without DN).Multivariate logistic regression analysis was used to explore factors affecting DN in patients with T2DM.The data were randomly split into a training set(n=147)and a test set(n=63)in a 7:3 ratio using a random function.The training set was used to construct the nomogram,decision tree,and random forest models,and the test set was used to evaluate the prediction performance of the model by comparing the sensitivity,specificity,accuracy,recall,precision,and area under the receiver operating characteristic curve.RESULTS Among the 210 patients with T2DM,74(35.34%)had DN.The validation dataset showed that the accuracies of the nomogram,decision tree,and random forest models in predicting DN in patients with T2DM were 0.746,0.714,and 0.730,respectively.The sensitivities were 0.710,0.710,and 0.806,respectively;the specificities were 0.844,0.875,and 0.844,respectively;the area under the receiver operating characteristic curve(AUC)of the patients were 0.811,0.735,and 0.850,respectively.The Delong test results revealed that the AUC values of the decision tree model were lower than those of the random forest and nomogram models(P<0.05),whereas the difference in AUC values of the random forest and column-line graph models was not statistically significant(P>0.05).CONCLUSION Among the three prediction models,random forest performs best and can help identify patients with T2DM at high risk of DN.

基于节点评估与最大类间方差的孤立森林异常值检测

针对孤立森林(isolation forest, iForest)无法有效检测局部异常值且异常值分数阈值难以精确设定的问题,提出一种基于节点评估(node evaluation, NE)与最大类间方差(Otsu)的iForest异常值检测方法。首先,在样本评估过程中将节点深度与相对质量同时引入评分机制,使算法对全局和局部异常值敏感;然后,为了准确设定分数阈值,采用Otsu自适应设定异常值分数阈值;最后,在不同数据集上验证所提方法的有效性。实验结果表明,该方法可以有效兼顾全局和局部异常值的检测,提高iForest检测异常值的准确性。

Biodiversity responses to insular fragmentation in Amazonia: Two decades of research in the Balbina Hydroelectric Reservoir

As hydropower development expands across lowland tropical forests,flooding and concomitant insular fragmentation have become important threats to biodiversity.Newly created insular landscapes serve as natural laboratories to investigate biodiversity responses to fragmentation.One of these most iconic landscapes is the Balbina Hydroelectric Reservoir in Brazilian Amazonia,occupying>400000 ha and comprising>3500 forest islands.Here,we synthesise the current knowledge on responses of a wide range of biological groups to insular fragmentation at Balbina.Sampling has largely concentrated on a set of 22 islands and three mainland sites.In total,39 studies were conducted over nearly two decades,covering 17 vertebrate,invertebrate,and plant taxa.Although species responses varied according to taxonomic group,island area was consistently included and played a pivotal role in 66.7%of all studies examining patterns of species diversity.Species persistence was further affected by species traits,mostly related to species capacity to use/traverse the aquatic matrix or tolerate habitat degradation,as noted for species of vertebrates and orchid bees.Further research is needed to improve our understanding of such effects on wider ecosystem functioning.Environmental Impact Assessments must account for changes in both the remaining habitat amount and configuration,and subsequent long-term species losses.

Twenty years of population dynamics in European beech-oak forest at their rear range margin anticipate changes in its structure and composition

There is an increasing interest in restoring degraded forests,which occupy half of the forest areas.Among the forms of restoration,passive restoration,which involves the elimination of degrading factors and the free evolution of natural dynamics by applying minimal or no management,is gaining attention.Natural dynamics is difficult to predict due to the influence of multiple interacting factors such as climatic and edaphic conditions,composition and abundance of species,and the successional character of these species.Here,we study the natural dynamics of a mixed forest located in central Spain,which maintained an open forest structure,due to intensive use,until grazing and cutting were banned in the 1960s.The most frequent woody species in this forest are Fagus sylvatica,Quercus petraea,Quercus pyrenaica,Ilex aquifolium,Sorbus aucuparia,Sorbus aria and Prunus avium,with contrasting shade and drought tolerance.These species are common in temperate European deciduous forest and are found here near their southern distribution limit,except for Q.pyrenaica.In order to analyze forest dynamics and composition,three inventories were carried out in 1994,2005 and 2015.Our results show that,despite the Mediterranean influence,the natural dynamics of this forest has been mainly determined by different levels of shade tolerance.After the abandonment of grazing and cutting,Q.pyrenaica expanded rapidly due to its lower shade tolerance,whereas after canopy closure and forest densification,shade-tolerant species gained ground,particularly F.sylvatica,despite its lower drought and late-frost tolerance.If the current dynamics continue,F.sylvatica will overtake the rest of the species,which will be relegated to sites with shallow soils and steep slopes.Simultaneously,all the multi-centennial beech trees,which are undergoing a rapid mortality and decline process,will disappear.

Evolutionary fingerprint, phylogenetic and forest structure of tropical montane Atlantic cloud forests along an elevation gradient

Environmental conditions can change markedly over geographical distances along elevation gradients,making them natural laboratories to study the processes that structure communities.This work aimed to assess the influences of elevation on Tropical Montane Cloud Forest plant communities in the Brazilian Atlantic Forest,a historically neglected ecoregion.We evaluated the phylogenetic structure,forest structure(tree basal area and tree density)and species richness along an elevation gradient,as well as the evolutionary fingerprints of elevation-success on phylogenetic lineages from the tree communities.To do so,we assessed nine communities along an elevation gradient from 1210 to 2310 m a.s.l.without large elevation gaps.The relationships between elevation and phylogenetic structure,forest structure and species richness were investigated through Linear Models.The occurrence of evolutionary fingerprint on phylogenetic lineages was investigated by quantifying the extent of phylogenetic signal of elevation-success using a genus-level molecular phylogeny.Our results showed decreased species richness at higher elevations and independence between forest structure,phylogenetic structure and elevation.We also verified that there is a phylogenetic signal associated with elevation-success by lineages.We concluded that the elevation is associated with species richness and the occurrence of phylogenetic lineages in the tree communities evaluated in Mantiqueira Range.On the other hand,elevation is not associated with forest structure or phylogenetic structure.Furthermore,closely related taxa tend to have their higher ecological success in similar elevations.Finally,we highlight the fragility of the tropical montane cloud forests in the Mantiqueira Range in face of environmental changes(i.e.global warming)due to the occurrence of exclusive phylogenetic lineages evolutionarily adapted to environmental conditions(i.e.minimum temperature)associated with each elevation range.

Assessment of large-scale multiple forest disturbance susceptibilities with AutoML framework: an Izmir Regional Forest Directorate case

Disturbances such as forest fires,intense winds,and insect damage exert strong impacts on forest ecosystems by shaping their structure and growth dynamics,with contributions from climate change.Consequently,there is a need for reliable and operational methods to monitor and map these disturbances for the development of suitable management strategies.While susceptibility assessment using machine learning methods has increased,most studies have focused on a single disturbance.Moreover,there has been limited exploration of the use of“Automated Machine Learning(AutoML)”in the literature.In this study,susceptibility assessment for multiple forest disturbances(fires,insect damage,and wind damage)was conducted using the PyCaret AutoML framework in the Izmir Regional Forest Directorate(RFD)in Turkey.The AutoML framework compared 14 machine learning algorithms and ranked the best models based on AUC(area under the curve)values.The extra tree classifier(ET)algorithm was selected for modeling the susceptibility of each disturbance due to its good performance(AUC values>0.98).The study evaluated susceptibilities for both individual and multiple disturbances,creating a total of four susceptibility maps using fifteen driving factors in the assessment.According to the results,82.5%of forested areas in the Izmir RFD are susceptible to multiple disturbances at high and very high levels.Additionally,a potential forest disturbances map was created,revealing that 15.6%of forested areas in the Izmir RFD may experience no damage from the disturbances considered,while 54.2%could face damage from all three disturbances.The SHAP(Shapley Additive exPlanations)methodology was applied to evaluate the importance of features on prediction and the nonlinear relationship between explanatory features and susceptibility to disturbance.