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.

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。

基于RF-SFLA-SVM的装配式建筑高空作业工人不安全行为预警

为有效预警装配式建筑高空作业工人不安全行为的发生趋势或状态,增强对装配式建筑工人不安全行为(PBWUBs)的管控,采用随机森林(RF)-混合蛙跳算法(SFLA)-支持向量机(SVM)模型,开展工人不安全行为预警研究。首先,采用SHEL模型分析处于高空作业危险中的PBWUBs的影响因素,并通过RF确定关键预警指标;然后,采用SFLA对SVM的参数进行寻优改进;最后,利用RF-SFLA-SVM预警高空作业PBWUBs,提出应对措施,并与其他预警模型对比。研究结果表明:基于RF-SFLA-SVM预警高空作业PBWUBs,准确率最高,为91.67%,与其他模型的预警性能相比,最高提升14%。研究结果可为高空作业PBWUBs的防控提供参考。

基于K-means SMOTE和IDBO-RF岩爆烈度等级预测模型

为解决岩爆数据集不均衡和模型参数寻优困难等问题,提出1种基于K-means SMOTE与改进蜣螂算法优化随机森林(random forest,RF)的预测模型。首先,分析岩爆发生机理构建指标体系;其次,使用K-means SMOTE算法对岩爆数据集进行均衡化处理,采用Robust标准化消除量纲;最后,引入Tent混沌映射和非线性递减策略组合改进蜣螂优化(improved dung beetle optimizer,IDBO)算法,寻优RF超参数,建立岩爆烈度等级预测模型(IDBO-RF)并与其他模型对比验证其有效性。研究结果表明:数据均衡处理后,各模型准确率提高10.85%~16.02%;设计的IDBO-RF预测模型平均准确率约为94.37%,较RF、GWO-RF、DBO-RF模型分别提高约7.76百分点、1.69百分点、1.11百分点;IDBO-RF预测模型准确率最高约为96.43%,优于RF、GWO-RF、DBO-RF模型。研究结果可为解决岩爆预测问题提供一定参考。

基于RF-RNN模型的DNS隐蔽信道检测方法

为提高检测隐蔽信道的灵敏度,提出一种基于随机森林(Random Forest,RF)和循环神经网络(Recurrent Neural Network,RNN)的域名系统(Domain Name System,DNS)隐蔽信道检测方法。该方法采用域名检测作为主要手段,使用RF模型对域名进行分类,通过深度学习方法挖掘更高阶的特征表示。实验结果表明,与单一模型相比,该方法在检测准确性和健壮性方面均取得了显著提升。

Predicting the Thickness of an Excavation Damaged Zone around the Roadway Using the DA-RF Hybrid Model

After the excavation of the roadway,the original stress balance is destroyed,resulting in the redistribution of stress and the formation of an excavation damaged zone(EDZ)around the roadway.The thickness of EDZ is the key basis for roadway stability discrimination and support structure design,and it is of great engineering significance to accurately predict the thickness of EDZ.Considering the advantages of machine learning(ML)in dealing with high-dimensional,nonlinear problems,a hybrid prediction model based on the random forest(RF)algorithm is developed in this paper.The model used the dragonfly algorithm(DA)to optimize two hyperparameters in RF,namely mtry and ntree,and used mean absolute error(MAE),rootmean square error(RMSE),determination coefficient(R^(2)),and variance accounted for(VAF)to evaluatemodel prediction performance.A database containing 217 sets of data was collected,with embedding depth(ED),drift span(DS),surrounding rock mass strength(RMS),joint index(JI)as input variables,and the excavation damaged zone thickness(EDZT)as output variable.In addition,four classic models,back propagation neural network(BPNN),extreme learning machine(ELM),radial basis function network(RBF),and RF were compared with the DA-RF model.The results showed that the DARF mold had the best prediction performance(training set:MAE=0.1036,RMSE=0.1514,R^(2)=0.9577,VAF=94.2645;test set:MAE=0.1115,RMSE=0.1417,R^(2)=0.9423,VAF=94.0836).The results of the sensitivity analysis showed that the relative importance of each input variable was DS,ED,RMS,and JI from low to high.

Identification of Mixtures of Two Types of Body Fluids Using the Multiplex Methylation System and Random Forest Models

Objective Body fluid mixtures are complex biological samples that frequently occur in crime scenes,and can provide important clues for criminal case analysis.DNA methylation assay has been applied in the identification of human body fluids,and has exhibited excellent performance in predicting single-source body fluids.The present study aims to develop a methylation SNaPshot multiplex system for body fluid identification,and accurately predict the mixture samples.In addition,the value of DNA methylation in the prediction of body fluid mixtures was further explored.Methods In the present study,420 samples of body fluid mixtures and 250 samples of single body fluids were tested using an optimized multiplex methylation system.Each kind of body fluid sample presented the specific methylation profiles of the 10 markers.Results Significant differences in methylation levels were observed between the mixtures and single body fluids.For all kinds of mixtures,the Spearman’s correlation analysis revealed a significantly strong correlation between the methylation levels and component proportions(1:20,1:10,1:5,1:1,5:1,10:1 and 20:1).Two random forest classification models were trained for the prediction of mixture types and the prediction of the mixture proportion of 2 components,based on the methylation levels of 10 markers.For the mixture prediction,Model-1 presented outstanding prediction accuracy,which reached up to 99.3%in 427 training samples,and had a remarkable accuracy of 100%in 243 independent test samples.For the mixture proportion prediction,Model-2 demonstrated an excellent accuracy of 98.8%in 252 training samples,and 98.2%in 168 independent test samples.The total prediction accuracy reached 99.3%for body fluid mixtures and 98.6%for the mixture proportions.Conclusion These results indicate the excellent capability and powerful value of the multiplex methylation system in the identification of forensic body fluid mixtures.

Fusion-Based Deep Learning Model for Automated Forest Fire Detection

Earth resource and environmental monitoring are essential areas that can be used to investigate the environmental conditions and natural resources supporting sustainable policy development,regulatory measures,and their implementation elevating the environment.Large-scale forest fire is considered a major harmful hazard that affects climate change and life over the globe.Therefore,the early identification of forest fires using automated tools is essential to avoid the spread of fire to a large extent.Therefore,this paper focuses on the design of automated forest fire detection using a fusion-based deep learning(AFFD-FDL)model for environmental monitoring.The AFFDFDL technique involves the design of an entropy-based fusion model for feature extraction.The combination of the handcrafted features using histogram of gradients(HOG)with deep features using SqueezeNet and Inception v3 models.Besides,an optimal extreme learning machine(ELM)based classifier is used to identify the existence of fire or not.In order to properly tune the parameters of the ELM model,the oppositional glowworm swarm optimization(OGSO)algorithm is employed and thereby improves the forest fire detection performance.A wide range of simulation analyses takes place on a benchmark dataset and the results are inspected under several aspects.The experimental results highlighted the betterment of the AFFD-FDL technique over the recent state of art techniques.

基于RSIV-RF模型的凉山州泥石流易发性评价

针对随机森林(RF)模型进行泥石流易发性评价过程中存在连续型因子依靠主观意识分级、随机选取的非泥石流样本准确度较低等问题,以位于四川西南部的凉山彝族自治州为研究区,提出基于统计学先验模型抽样的随机森林对研究区进行泥石流易发性评价分区。利用累计灾害频率等曲线的相对变化对连续型因子进行分级处理;采用粗糙集理论(RS)和信息量法(IV)计算加权信息量值,划定极低和低易发性区并从中选择负样本数据。通过袋外误差(OOB)变化曲线确定RF模型的最佳树棵数n_estimators和分裂特征数max_features,随后构建加权信息量-随机森林(RSIV-RF)模型预测凉山州泥石流易发性。进一步地,与从全区随机选择非泥石流样本的RF模型开展对比研究。结果表明,训练集和测试集下RSIV-RF模型的准确度分别为0.89,0.83,且对应的ROC曲线的AUC值分别为0.920,0.895,均高于单独的RF模型;RSIV-RF绘制的泥石流易发性评价图与历史灾害分布较为一致,较高和高易发性等级区域占研究区面积比为18.625%,包含了78.57%的泥石流点。性能评估和易发性统计结果均表明基于RSIV-RF能够解决单独模型存在的非泥石样本采样不准确的问题,其泥石流易发性预测精度更高,在凉山州地区泥石流易发性评价研究中具有较好的适应性。

A novel model to evaluate spatial structure in thinned conifer-broadleaved mixed natural forests

In order to ensure the effective analysis and reconstruction of forests,it is key to ensure the quantitative description of their spatial structure.In this paper,a distance model for the optimal stand spatial structure based on weighted Voronoi diagrams is proposed.In particular,we provide a novel methodological model for the comprehensive evaluation of the spatial structure of forest stands in natural mixed conifer-broadleaved forests and the formulation of management decision plans.The applicability of the rank evaluation and the optimal solution distance model are compared and assessed for different standard sample plots of natural mixed conifer-broadleaved forests.The effect of crown width on the spatial structure unit of the trees is observed to be higher than that of the diameter at breast height.Moreover,the influence of crown length is greater than that of tree height.There are nine possible spatial structure units determined by the weighted Voronoi diagram for the number of neighboring trees in the central tree,with an average intersection of neighboring crowns reaching 80%.The rank rating of natural forest sample plots is correlated with the optimal solution distance model,and their results are generally consistent for natural forests.However,the rank rating is not able to provide a quantitative assessment.The optimal solution distance model is observed to be more comprehensive than traditional methods for the evaluation of the spatial structure of forest stands.It can effectively reflect the trends in realistic stand spatial structure factors close to or far from the ideal structure point,and accurately assesses the forest spatial structure.The proposed optimal solution distance model improves the integrated evaluation of the spatial structure of forest stands and provides solid theoretical and technical support for sustainable forest management.

基于GJO特征量优选的AO-RF的变压器故障诊断模型

在变压器故障诊断过程中,进行合理的特征优选,将有助于提高诊断模型的诊断精度,为此,文中提出了一种基于金豺优化算法(golden Jackal optimization,GJO)特征量优选与AO-RF的变压器故障诊断模型。首先,采用GJO对构建的21维变压器油中溶解气体特征量进行优选;然后,根据GJO得到的特征优选结果,采用天鹰算法(aquila optimizer,AO)优化随机森林(random forest,RF)的变压器故障诊断模型对变压器故障进行诊断,并与不同特征量、不同故障诊断模型的诊断结果进行了对比。实验结果表明:GJO优选特征量相比21维原始特征、三比值法、无编码比值法以及AO优选特征量的故障诊断准确率可提高1.12%~25.78%,kappa系数可提高0.02~0.24;AO-RF故障诊断模型较RF、SVM、ELM、SSA-RF、WOA-RF、GJO-RF模型的诊断准确率可提高1.84%~15.86%,kappa系数可提高0.02~0.16,验证了所提方法的有效性和准确性。

Prediction and driving factors of forest fire occurrence in Jilin Province,China

Forest fires are natural disasters that can occur suddenly and can be very damaging,burning thousands of square kilometers.Prevention is better than suppression and prediction models of forest fire occurrence have developed from the logistic regression model,the geographical weighted logistic regression model,the Lasso regression model,the random forest model,and the support vector machine model based on historical forest fire data from 2000 to 2019 in Jilin Province.The models,along with a distribution map are presented in this paper to provide a theoretical basis for forest fire management in this area.Existing studies show that the prediction accuracies of the two machine learning models are higher than those of the three generalized linear regression models.The accuracies of the random forest model,the support vector machine model,geographical weighted logistic regression model,the Lasso regression model,and logistic model were 88.7%,87.7%,86.0%,85.0%and 84.6%,respectively.Weather is the main factor affecting forest fires,while the impacts of topography factors,human and social-economic factors on fire occurrence were similar.

The potential for an old-growth forest to store carbon in the topsoil:A case study at Sasso Fratino,Italy

There is considerable interest devoted to oldgrowth forests and their capacity to store carbon(C)in biomass and soil.Inventories of C stocks in old-growth forests are carried out worldwide,although there is a lack of information on their actual potential for C sequestration.To further understand this,soil organic carbon(SOC)was measured in one of Italy's best-preserved old-growth forests,the Sasso Fratino Integral Nature Reserve.This reserve is on the World Heritage List along with other ancient beech forests of Europe,and it is virtually untouched due to the steepness of the terrain,even before legal constraints were imposed.Although the sandstone-derived soils are often shallow,they are rich in organic matter.However,no quantification had been carried out.By systematically sampling the topsoil across the forest,we accurately determined the average amount of SOC(62.0±16.9 Mg ha^(–1))and nitrogen(4.0±1.2 Mg ha^(–1))in the top 20 cm.Using the CENTURY model,future dynamics of SOC stocks were predicted to 2050 according to two climate scenarios,A1F1 and B2,the first of high concern and the second more optimistic.The model projected an increase of 0.2 and 0.3 Mg ha^(–1)a^(–1)by 2030 under the A1F1 and B2 scenarios,respectively,suggesting that the topsoil in old-growth forests does not reach equilibrium but continues accumulating SOC.However,from 2030 to 2050,a decline in SOC accumulation is predicted,indicating SOC net loss at high altitudes under the worst-case scenario.This study confirms that soils in oldgrowth forests play a significant role in carbon sequestration.It also suggests that climate change may affect the potential of these forests to store SOC not only in the long term but also in the coming years.

基于混合式SMOTE和RF模型的小额贷款公司客户信用风险研究

小额借贷中的个人信用风险问题持续制约着小额贷款行业的健康可持续发展。针对小贷公司在进行信用风险评估时对高违约风险客户识别准确率较低的难题,运用混合式SMOTE、RF算法来同时处理业务数据中高维、非均衡两个问题。本文借助江苏J小贷公司的实例数据,依次构建随机森林(Random Forest, RF)模型、SMOTE-RF模型以及Borderline-SMOTE-RF模型并进行模型测试;再选用SVM算法进行对比实验以此衡量模型的信用风险评价精度。随后基于模型对于指标重要性的评分筛选出6项指标作为影响个人信用风险的关键指标。实验证明基于Borderline-SMOTE-RF算法对于小额贷款个人信用风险评价模型的分类性能最佳;在筛选关键指标时,为避免人工合成虚拟样本对指标重要性影响,需要结合三类模型评分进行综合选择。

An Optimization Approach of IoD Deployment for Optimal Coverage Based on Radio Frequency Model

Recently,Internet of Drones(IoD)has garnered significant attention due to its widespread applications.However,deploying IoD for area coverage poses numerous limitations and challenges.These include interference between neighboring drones,the need for directional antennas,and altitude restrictions for drones.These challenges necessitate the development of efficient solutions.This research paper presents a cooperative decision-making approach for an efficient IoDdeployment to address these challenges effectively.The primary objective of this study is to achieve an efficient IoDdeployment strategy thatmaximizes the coverage regionwhile minimizing interference between neighboring drones.In deployment problem,the interference increases as the number of deployed drones increases,resulting in bad quality of communication.On the other hand,deploying a few drones cannot satisfy the coverage demand.To accomplish this,an enhanced version of a concise population-based meta-heuristic algorithm,namely Improved Particle SwarmOptimization(IPSO),is applied.The objective function of IPSO is defined based on the coverage probability,which is primarily influenced by the characteristics of the antennas and drone altitude.A radio frequency(RF)model is derived to evaluate the coverage quality,considering both Line of Sight(LOS)and Non-Line of Sight(NLOS)down-link coverage probabilities for ground communication.It is assumed that each drone is equipped with a directional antenna to optimize coverage in a given region.Extensive simulations are conducted to assess the effectiveness of the proposed approach.Results demonstrate that the proposed method achieves maximum coverage with minimum transmission power.Furthermore,a comparison is made against Collaborative Visual Area Coverage Approach(CVACA),and a game-based approach in terms of coverage quality and convergence speed.The simulation results reveal that our approach outperforms both CVACA and the gamebased schemes in terms of coverage and convergence speed.Comparisons validate the superiority of our approach over existing methods.To assess the robustness of the proposed RFmodel,we have considered two distinct ranges of noise:range1 spanning from−120 to−90 dBm,and range2 spanning from−90 to−70 dBmfor different numbers of UAVs.In summary,this research presents a cooperative decision-making approach for efficient IoD deployment to address the challenges associatedwith area coverage and achieves an optimal coveragewithminimal interference.

Reconstructing historical forest fire risk in the non-satellite era using the improved forest fire danger index and long short-term memory deep learning-a case study in Sichuan Province,southwestern China

Historical forest fire risk databases are vital for evaluating the effectiveness of past forest management approaches,enhancing forest fire warnings and emergency response capabilities,and accurately budgeting potential carbon emissions resulting from fires.However,due to the unavailability of spatial information technology,such databases are extremely difficult to build reliably and completely in the non-satellite era.This study presented an improved forest fire risk reconstruction framework that integrates a deep learning-based time series prediction model and spatial interpolation to address the challenge in Sichuan Province,southwestern China.First,the forest fire danger index(FFDI)was improved by supplementing slope and aspect information.We compared the performances of three time series models,namely,the autoregressive integrated moving average(ARIMA),Prophet and long short-term memory(LSTM)in predicting the modified forest fire danger index(MFFDI).The bestperforming model was used to retrace the MFFDI of individual stations from 1941 to 1970.Following this,the Anusplin spatial interpolation method was used to map the distributions of the MFFDI at five-year intervals,which were then subjected to weighted overlay with the distance-to-river layer to generate forest fire risk maps for reconstructing the forest fire danger database.The results revealed LSTM as the most accurate in fitting and predicting the historical MFFDI,with a fitting determination coefficient(R^2)of 0.709,mean square error(MSE)of0.047,and validation R^2 and MSE of 0.508 and 0.11,respectively.Independent validation of the predicted forest fire risk maps indicated that 5 out of 7 historical forest fire events were located in forest fire-prone areas,which is higher than the results determined from the original FFDI(2 out of 7).This proves the effectiveness of the improved MFFDI and indicates a high level of reliability of the historical forest fire risk reconstruction method proposed in this study.

Drivers of spatial structure in thinned forests

Background:As is widely known,an increasing number of forest areas were managed to preserve and enhance the health of forest ecosystems.However,previous research on forest management has often overlooked the importance of structure-based.Aims:Our objectives were to define the direction of structure-based forest management.Subsequently,we investigated the relationships between forest structure and the regeneration,growth,and mortality of trees under different thinning treatments.Ultimately,the drivers of forest structural change were explored.Methods:On the basis of 92 sites selected from northeastern China,with different recovery time (from 1 to 15years) and different thinning intensities (0–59.9%) since the last thinning.Principal component analysis (PCA)identified relationships among factors determining forest spatial structure.The structural equation model (SEM)was used to analyze the driving factors behind the changes in forest spatial structure after thinning.Results:Light thinning (0–20%trees removed) promoted forest regeneration,and heavy thinning (over 35% of trees removed) facilitated forest growth.However,only moderate thinning (20%–35%trees removed) created a reasonable spatial structure.While dead trees were clustered,and they were hardly affected by thinning intensity.Additionally,thinning intensity,recovery time,and altitude indirectly improve the spatial structure of the forest by influencing diameter at breast height (DBH) and canopy area.Conclusion:Creating larger DBH and canopy area through thinning will promote the formation of complex forest structures,which cultivates healthy and stable forests.

Grouping tree species to estimate basal area increment in temperate multispecies forests in Durango,Mexico

Multispecies forests have received increased scientific attention,driven by the hypothesis that biodiversity improves ecological resilience.However,a greater species diversity presents challenges for forest management and research.Our study aims to develop basal area growth models for tree species cohorts.The analysis is based on a dataset of 423 permanent plots(2,500 m^(2))located in temperate forests in Durango,Mexico.First,we define tree species cohorts based on individual and neighborhood-based variables using a combination of principal component and cluster analyses.Then,we estimate the basal area increment of each cohort through the generalized additive model to describe the effect of tree size,competition,stand density and site quality.The principal component and cluster analyses assign a total of 37 tree species to eight cohorts that differed primarily with regard to the distribution of tree size and vertical position within the community.The generalized additive models provide satisfactory estimates of tree growth for the species cohorts,explaining between 19 and 53 percent of the total variation of basal area increment,and highlight the following results:i)most cohorts show a"rise-and-fall"effect of tree size on tree growth;ii)surprisingly,the competition index"basal area of larger trees"had showed a positive effect in four of the eight cohorts;iii)stand density had a negative effect on basal area increment,though the effect was minor in medium-and high-density stands,and iv)basal area growth was positively correlated with site quality except for an oak cohort.The developed species cohorts and growth models provide insight into their particular ecological features and growth patterns that may support the development of sustainable management strategies for temperate multispecies forests.

User Purchase Intention Prediction Based on Improved Deep Forest

Widely used deep neural networks currently face limitations in achieving optimal performance for purchase intention prediction due to constraints on data volume and hyperparameter selection.To address this issue,based on the deep forest algorithm and further integrating evolutionary ensemble learning methods,this paper proposes a novel Deep Adaptive Evolutionary Ensemble(DAEE)model.This model introduces model diversity into the cascade layer,allowing it to adaptively adjust its structure to accommodate complex and evolving purchasing behavior patterns.Moreover,this paper optimizes the methods of obtaining feature vectors,enhancement vectors,and prediction results within the deep forest algorithm to enhance the model’s predictive accuracy.Results demonstrate that the improved deep forest model not only possesses higher robustness but also shows an increase of 5.02%in AUC value compared to the baseline model.Furthermore,its training runtime speed is 6 times faster than that of deep models,and compared to other improved models,its accuracy has been enhanced by 0.9%.

基于CF融入SSA优化SVM和RF模型的滑坡易发性评价

针对传统的区域滑坡易发性评价建模过程可能存在的样本数据量纲不统一以及模型参数选取误差等问题,本文以陕西省留坝县为研究区,选取高程、坡度、水系、降雨量、地层岩性等10个评价因子,采用确定性系数模型(CF)计算各评价因子的敏感值作为支持向量机模型(SVM)和随机森林模型(RF)的输入样本属性值,引入麻雀搜索算法(SSA)分别对SVM模型和RF模型的参数进行优化,获取最优参数对两种模型进行训练,最终构建了CF-SSA-SVM和CF-SSA-RF模型,从而对整个研究区进行预测,完成滑坡易发性评价,并通过受试者工作特征曲线(ROC)对两种模型进行精度验证。结果表明,两种模型的评价结果均有较多滑坡点落在极高易发区,无滑坡点落在极低易发区,评价结果均有较高的准确率。其中,CF-SSA-RF模型的成功率和预测率曲线AUC值分别为0.994和0.940,高于CF-SSA-SVM模型;并以三处典型滑坡为例进行验证,结果显示易发性分区与历史滑坡点分布较为吻合。进一步表明CF-SSA-RF模型更适用于留坝县的滑坡易发性评价,为当地滑坡灾害风险评估提供了指导依据。