Mapping species assemblages of tropical forests at different hierarchical levels based on multivariate regression trees

Background: Vegetation distribution maps are of great significance for nature protection and management. In diverse tropical forests, accurate spatial mapping of vegetation types is challenging;the high species diversity and abundance of rare species challenge classification concepts, while remote sensing signals may not vary systematically with species composition, complicating the technical capability for delineating vegetation types in the landscape.Methods: We used a combination of field-based compositional data and their relations to environmental variables to predict the distribution of forest types in the Wuzhishan National Natural Reserve(WNNR), Hainan Island,China, using multivariate regression trees(MRT). The MRT was based on arboreal vegetation composition in 132plots of 20 m×20 m with a regular spacing of 1 km. Apart from the MRT, non-metric multidimensional scaling(NMDS) was used to evaluate vegetation-environment relationships.Results: The MRT model worked best when using 14 key environmental variables including topography, climate,latitude and soil, although the difference with the simpler model including only topographical variables was small. The full model classified the 132 plots into 3 vegetation types, 6 formation groups, 20 formations and 65associations at different hierarchical syntaxonomic levels. This model was the basis for forest vegetation maps for the WNNR. MRT and NMDS showed that elevation was the main driving force for the distribution of vegetation types and formation groups. Climate, latitude, and soil(especially available P), together with topographic variables, all influenced the distribution of formations and associations.Conclusions: While elevation determines forest-type distributions, lower-level syntaxonomic forest classes respond to the topographic diversity typical for mountains. Apart from providing the first detailed forest vegetation map for any part of WNNR, we show how, in spite of limitations, MRT with existing environmental data can be a useful method for mapping diverse and remote tropical forests.

Groundwater level prediction of landslide based on classification and regression tree

According to groundwater level monitoring data of Shuping landslide in the Three Gorges Reservoir area, based on the response relationship between influential factors such as rainfall and reservoir level and the change of groundwater level, the influential factors of groundwater level were selected. Then the classification and regression tree（CART） model was constructed by the subset and used to predict the groundwater level. Through the verification, the predictive results of the test sample were consistent with the actually measured values, and the mean absolute error and relative error is 0.28 m and 1.15%respectively. To compare the support vector machine（SVM） model constructed using the same set of factors, the mean absolute error and relative error of predicted results is 1.53 m and 6.11% respectively. It is indicated that CART model has not only better fitting and generalization ability, but also strong advantages in the analysis of landslide groundwater dynamic characteristics and the screening of important variables. It is an effective method for prediction of ground water level in landslides.

Prediction method of restoring force based on online AdaBoost regression tree algorithm in hybrid test

In order to solve the poor generalization ability of the back-propagation(BP)neural network in the model updating hybrid test,a novel method called the AdaBoost regression tree algorithm is introduced into the model updating procedure in hybrid tests.During the learning phase,the regression tree is selected as a weak regression model to be trained,and then multiple trained weak regression models are integrated into a strong regression model.Finally,the training results are generated through voting by all the selected regression models.A 2-DOF nonlinear structure was numerically simulated by utilizing the online AdaBoost regression tree algorithm and the BP neural network algorithm as a contrast.The results show that the prediction accuracy of the online AdaBoost regression algorithm is 48.3%higher than that of the BP neural network algorithm,which verifies that the online AdaBoost regression tree algorithm has better generalization ability compared to the BP neural network algorithm.Furthermore,it can effectively eliminate the influence of weight initialization and improve the prediction accuracy of the restoring force in hybrid tests.

A New Approach to Predict Financial Failure： Classification and Regression Trees （CART）

The increase of competition, economic recession and financial crises has increased business failure and depending on this the researchers have attempted to develop new approaches which can yield more correct and more reliable results. The classification and regression tree （CART） is one of the new modeling techniques which is developed for this purpose. In this study, the classification and regression trees method is explained and tested the power of the financial failure prediction. CART is applied for the data of industry companies which is trade in Istanbul Stock Exchange （ISE） between 1997-2007. As a result of this study, it has been observed that, CART has a high predicting power of financial failure one, two and three years prior to failure, and profitability ratios being the most important ratios in the prediction of failure.

Monthly Electricity Consumption Forecast Based on Multi-Target Regression

Urban grid power forecasting is one of the important tasks of power system operators, which helps to analyze the development trend of the city. As the demand for electricity in various industries is affected by many factors, the data of relevant influencing factors are scarce, resulting in great deviations in the accuracy of prediction results. In order to improve the prediction results, this paper proposes a model based on Multi-Target Tree Regression to predict the monthly electricity consumption of different industrial structures. Due to few data characteristics of actual electricity consumption in Shanghai from 2013 to the first half of 2017. Thus, we collect data on GDP growth, weather conditions, and tourism season distribution in various industries in Shanghai, model and train the electricity consumption data of different industries in different months. The multi-target tree regression model was tested with actual values to verify the reliability of the model and predict the monthly electricity consumption of each industry in the second half of 2017. The experimental results show that the model can accurately predict the monthly electricity consumption of various industries.

An Empirical Comparison on Multi-Target Regression Learning

Multi-target regression is concerned with the simultaneous prediction of multiple continuous target variables based on the same set of input variables.It has received relatively small attention from the Machine Learning community.However,multi-target regression exists in many real-world applications.In this paper we conduct extensive experiments to investigate the performance of three representative multi-target regression learning algorithms(i.e.Multi-Target Stacking(MTS),Random Linear Target Combination(RLTC),and Multi-Objective Random Forest(MORF)),comparing the baseline single-target learning.Our experimental results show that all three multi-target regression learning algorithms do improve the performance of the single-target learning.Among them,MTS performs the best,followed by RLTC,followed by MORF.However,the single-target learning sometimes still performs very well,even the best.This analysis sheds the light on multi-target regression learning and indicates that the single-target learning is a competitive baseline for multi-target regression learning on multi-target domains.

Predicting the Underlying Structure for Phylogenetic Trees Using Neural Networks and Logistic Regression

Understanding an underlying structure for phylogenetic trees is very important as it informs on the methods that should be employed during phylogenetic inference. The methods used under a structured population differ from those needed when a population is not structured. In this paper, we compared two supervised machine learning techniques, that is artificial neural network (ANN) and logistic regression models for prediction of an underlying structure for phylogenetic trees. We carried out parameter tuning for the models to identify optimal models. We then performed 10-fold cross-validation on the optimal models for both logistic regression?and ANN. We also performed a non-supervised technique called clustering to identify the number of clusters that could be identified from simulated phylogenetic trees. The trees were from?both structured?and non-structured populations. Clustering and prediction using classification techniques were?done using tree statistics such as Colless, Sackin and cophenetic indices, among others. Results from 10-fold cross-validation revealed that both logistic regression and ANN models had comparable results, with both models having average accuracy rates of over 0.75. Most of the clustering indices used resulted in 2 or 3 as the optimal number of clusters.

Using Boosted Regression Trees and Remotely Sensed Data to Drive Decision-Making

Challenges in Big Data analysis arise due to the way the data are recorded, maintained, processed and stored. We demonstrate that a hierarchical, multivariate, statistical machine learning algorithm, namely Boosted Regression Tree (BRT) can address Big Data challenges to drive decision making. The challenge of this study is lack of interoperability since the data, a collection of GIS shapefiles, remotely sensed imagery, and aggregated and interpolated spatio-temporal information, are stored in monolithic hardware components. For the modelling process, it was necessary to create one common input file. By merging the data sources together, a structured but noisy input file, showing inconsistencies and redundancies, was created. Here, it is shown that BRT can process different data granularities, heterogeneous data and missingness. In particular, BRT has the advantage of dealing with missing data by default by allowing a split on whether or not a value is missing as well as what the value is. Most importantly, the BRT offers a wide range of possibilities regarding the interpretation of results and variable selection is automatically performed by considering how frequently a variable is used to define a split in the tree. A comparison with two similar regression models (Random Forests and Least Absolute Shrinkage and Selection Operator, LASSO) shows that BRT outperforms these in this instance. BRT can also be a starting point for sophisticated hierarchical modelling in real world scenarios. For example, a single or ensemble approach of BRT could be tested with existing models in order to improve results for a wide range of data-driven decisions and applications.

Change Point Analysis to Detect the Effect of Pruning Severity on Tree Growth

The effect of pruning severity on tree growth was analyzed by change point detection using segmented regression. The present study applied this analysis to a well-known published data set including diameter growth response, tree age, pruning severity and pretreatment crown size. First, multiple regression analysis was performed to assess the effect of tree age, pruning severity and pretreatment crown size on diameter growth response. Next, segmented regression analysis was performed to assess the effect of pruning severity on diameter growth response. The results of the multiple regression showed that diameter growth response was significantly influenced by pruning severity and pretreatment crown size. The results of the segmented regression showed that in the whole data set, an abrupt change toward a decrease in diameter growth response was detected at 25% of the live crown removed. However, in the group of fully crowned and open-grown, diameter growth response continuously decreased with increasing pruning severity with no significant abrupt change, whereas in the group of 70% - 90% live crown, diameter growth response did not significantly decrease up to the break point (53% crown removed) and then abruptly decreased. This may be the first study to show the numerical evaluation of the effect of pruning severity on tree growth by change point analysis.

Point-Tree Structure Genetic Programming Method for Discontinuous Function's Regression

A new point-tree data structure genetic programming (PTGP) method is proposed. For the discontinuous function regression problem, the proposed method is able to identify both the function structure and discontinuities points simultaneously. It is also easy to be used to solve the continuous function's regression problems. The numerical experiment results demonstrate that the point-tree GP is an efficient alternative way to the complex function identification problems.

Predicting plant disease epidemics using boosted regression trees

Plant epidemics are often associated with weather-related variables.It is difficult to identify weather-related predictors for models predicting plant epidemics.In the article by Shah et al.,to predict Fusarium head blight(FHB)epidemics of wheat,they explored a functional approach using scalar-on-function regression to model a binary outcome(FHB epidemic or non-epidemic)with respect to weather time series spanning 140 days relative to anthesis.The scalar-on-function models fit the data better than previously described logistic regression models.In this work,given the same dataset and models,we attempt to reproduce the article by Shah et al.using a different approach,boosted regression trees.After fitting,the classification accuracy and model statistics are surprisingly good.

数据挖掘算法在作业车间调度问题中的应用

为了从与日俱增的车间生产数据中提取调度规则来指导生产调度任务,提出一种基于数据挖掘的调度算法。将最小化最大完工时间设置为性能指标,从作业车间的离线生产数据中建立合适的调度样本集;将建立的调度样本集按合适的比例分为训练集和测试集;用数据挖掘算法中的分类回归树(CART)从训练集中获取有效的调度知识,形成CART树状调度规则库;为了验证所得调度规则的有效性,将调度规则与遗传算法结合,设计了一种基于数据挖掘和调度规则的遗传算法作为调度算法来求解作业车间调度问题。通过对不同作业车间经典算例进行仿真与测试,验证了所提调度规则和调度算法的有效性与优越性。

一种基于贝叶斯优化和XGBoost的膏体流变参数预测模型

探究膏体充填料浆流变特性,对矿山合理布置充填管路,高效进行充填作业有重要意义。目的:将繁琐且影响因素众多的膏体流变参数测量试验与先进的机器学习回归预测模型相结合,实现膏体流变参数的准确预测。方法:利用不同物料配合比条件下共128组膏体流变特性试验数据作为模型数据集,选择极度梯度提升回归树(XGBoost)模型,结合贝叶斯算法(BO)对模型进行超参数寻优设置,建立了多目标参数回归预测模型。结果:研究结果表明:经贝叶斯算法优化后的BO-XGBoost模型较XGBoost模型性能显著提升,决定系数R^(2)提高6%。所构建BO-XGBoost模型真实值与预测值在屈服应力数据集上相对误差维持在0.02水平;黏度数据集维持在0.1水平。结论:BO-XGBoost模型可实现膏体流变参数的高效准确预测,创新性地使用了多目标回归模型,为矿山充填作业设计提供参考,具有一定实际工程应用意义。

基于梯度提升回归树的气井油管积液高度预测

气井油管积液高度预测是气藏开发的重要环节,更是排水采气不可或缺的一部分。气井开采后期,气井底部会出现积液聚集现象,积液过多会造成气井停产,为了避免停产问题,必须对气井油管积液高度进行预测,但传统石油工程模型预测气井油管积液高度,存在着具体计算需要大量经验参数等问题。提出一个基于梯度提升回归树模型预测气井油管积液高度的方法,以气井的套压、油压、油管下深、油层中深、日产气、日产水、井口温度7种生产数据为特征,采用集成学习方法,结合多个决策树的预测结果,以迭代逐步改进的方式来提高模型的整体性能,从而精确预测气井油管积液高度。通过与32口井仪器探测实测值、回归决策树和随机森林对比分析,梯度提升回归树模型预测值与实测值相符,预测效果也最好,平均相对误差仅3.87%,调整后的相关系数R2为0.85。梯度提升回归树模型与现有的油管内积液量和环空积液量预测模型相比较,平均相对误差降低了1.9%。

基于Stacking算法集成学习的页岩油储层总有机碳含量评价方法

总有机碳含量(TOC)是页岩油储层评价的重要参数,而传统总有机碳含量测井评价方法精度较低且普适性较差,机器学习模型在一定程度上提高了总有机碳含量预测精度,但结果存在不稳定性。为了进一步提高页岩油储层总有机碳含量预测精度,基于有机质岩石物理特征和不同总有机碳含量测井响应特征的深入分析,优选出深侧向电阻率、声波时差、补偿中子和密度测井曲线作为总有机碳含量的敏感测井响应,并将其作为输入特征,以岩心分析总有机碳含量作为期望输出值,分别建立了决策树模型、支持向量回归机模型、BP(Back Propagation)神经网络模型,并建立了以决策树模型为基模型、支持向量回归机模型为元模型的Stacking算法集成学习模型。利用B油田A区块的岩心样本数据和实际井数据对不同模型预测总有机碳含量结果进行了验证,结果表明,基于Stacking算法的集成学习模型的总有机碳含量预测精度最高,相较于决策树模型、支持向量回归机模型、BP神经网络模型和改进的ΔlgR法,预测精度有较大提高。因此,基于Stacking算法的集成学习模型为该研究区最有效的总有机碳含量计算方法,这为准确地评估页岩油储层的生烃潜力、确保页岩油储层的高效开采及资源利用奠定了基础。

进港航班滑入时间预测

准确预测进港航班滑入时间对合理调配航班保障资源和提高机场场面运行效率具有重要意义,可有效克服各大机场粗放式预测航班进港时刻的不足,为此提出一种基于机器学习模型的滑入时间预测方法。以首都机场为具体研究对象,分析进港航班滑入时间的影响因素并构建特征集;将线性回归、K-最近邻、支持向量机、决策树、随机森林和梯度提升回归树6种在滑出时间预测方面得到广泛应用的机器学习模型用于进港航班滑入时间预测。研究结果表明:在误差范围±3 min内6种机器学习模型的预测精度均超过90%,表明特征集的构建和模型的选择是有效的;综合预测性能与模型拟合评估结果,梯度提升回归树模型的预测效果最好;在梯度提升回归树模型上场面流量特征的贡献度最大,新引入的跨区特征对预测模型的贡献度超过了大部分传统特征。

土地利用与城市轨道交通客流的非线性关系

城市轨道交通站点影响范围内土地利用对客流影响具有时空分异特征且存在类型差异,为针对性探讨不同站点两者的复杂非线性关系,提出一种基于土地利用空间分布规律、对站点实际影响范围进行差异化识别的方法;并通过分时段多尺度地理加权回归,获取能够表征土地利用对客流影响时空变化特征的站点聚类指标,采用K-means++算法将研究区域内的站点划分为4类;进而基于改进的梯度提升决策树模型分类定量探讨不同类别下土地利用与轨道交通客流的复杂非线性关系。研究表明:通过捕捉不同站点土地利用与客流的时空分异特征对站点进行分类识别,可有效提升两者非线性关系模型的解释度。根据模型输出结果,发现不同类别站点影响轨道交通客流的关键土地利用要素不同,第1类中关键变量为相对重要性分别为61.35%和30.08%的公交站点数量和慢行密度;第4类的情况类似但相对数值有所变化,公交站点数量的相对重要性由61.35%下降至30.31%;建筑密度在第2类中以66.57%的相对重要度占据最大比例;但在第3类中仅占5.59%。此外,不同类别站点影响范围内土地利用与轨道交通客流的关系存在较为显著且各异的阈值效应。研究表明,对于不同类别站点的用地开发应各有侧重,且应结合实际将土地利用设计指标控制在相应的合理范围内。研究为差异化的站点周边土地利用开发策略的制定提供了理论支持和量化指导。

基于机器学习的马铃薯叶片叶绿素含量估算

为了提高马铃薯叶绿素含量估算模型的精度,使用无人机平台搭载多光谱相机,获取对照处理和干旱处理下马铃薯关键生育期的遥感影像,选取13种植被指数作为叶绿素含量反演模型的输入变量,使用多元线性回归(MLR)、支持向量回归(SVR)、随机森林回归(RFR)、决策树回归(DTR)构建马铃薯叶绿素含量估算模型。首先分析了植被指数与叶绿素含量之间的相关性,结果表明,在对照处理块茎形成期,CIre、GNDVI、NDVIre、NDWI、GRVI、LCI与叶绿素含量之间的相关系数绝对值在0.5以上,且存在显著(p<0.05)或极显著(p<0.01)相关性;在马铃薯其他生育时期,13种植被指数与叶绿素含量之间的相关系数绝对值均在0.5以上,且存在极显著(p<0.001)相关性。然后对MLR、SVR、RFR和DTR等模型的精度进行比较,结果表明:SVR模型在对照处理块茎形成期、块茎膨大期和淀粉积累期的预测效果均是最佳,R 2和RMSE在块茎形成期为0.89和2.11,块茎膨大期为0.59和4.03,淀粉积累期为0.80和3.18;RFR模型在干旱处理块茎形成期、块茎膨大期和淀粉积累期的预测效果均是最佳,R 2和RMSE在块茎形成期为0.90和1.57,在块茎膨大期为0.87和2.16,在淀粉积累期为0.63和3.01。该研究为马铃薯叶绿素含量监测提供一种新的方法,后期可根据不同试验处理选择相应的估算模型。

腰椎间盘突出症病人术后发生恐动症的影响因素

目的:探讨腰椎间盘突出症(LDH)病人术后发生恐动症的危险因素,并基于Logistic回归模型和决策树模型建立LDH病人术后发生恐动症的风险预测模型。方法:回顾性分析2021年3月—2022年8月在我院行手术治疗的355例LDH病人的临床资料,根据病人术后是否发生恐动症分为恐动症组和非恐动症组,采用多因素Logistic回归分析筛选LDH病人术后发生恐动症的危险因素,运用SPSS Modeler软件建立预测LDH病人术后发生恐动症的决策树模型,并分析模型的预测效能。结果:本研究恐动症发生率为37.46%;恐动症组和非恐动症组病人受教育程度、疼痛视觉模拟评分(VAS)、医院焦虑抑郁量表(HADS)评分、自我效能、家庭人均月收入以及医疗费用支付方式比较,差异有统计学意义(P<0.05)。多因素Logistic回归分析结果显示,受教育程度、VAS评分、HADS评分、自我效能、家庭人均月收入以及医疗费用支付方式均为LDH病人术后发生恐动症的独立危险因素(P<0.05)。决策树结果显示,自我效能是LDH病人术后发生恐动症的主要危险因素,其次为医疗费用支付方式、VAS评分、HADS评分以及家庭人均月收入;受试者工作特征曲线(ROC)显示,决策树模型的预测能力高于多因素Logistic回归分析(P<0.05)。结论:受教育程度、VAS评分、HADS评分、自我效能、家庭人均月收入以及医疗费用支付方式为LDH病人术后发生恐动症的独立危险因素,医务人员可结合上述模型从不同层面发现LDH病人术后发生恐动症的影响因素,有助于评估病人病情,及时给予相应的干预指导。

应用机器学习算法模型预测兴安落叶松地上生物量

为了准确预测兴安落叶松地上生物量,以小兴安岭201株兴安落叶松地上生物量作为研究对象,以胸径(D)和树高(H)为变量,构建随机森林(RF)、人工神经网络(ANN)、支持向量回归(SVR)和梯度提升回归树(GBRT)等4种机器学习模型,并将机器学习算法的预测结果与传统二元生物量模型的预测结果进行对比分析。结果表明:对比传统生物量模型,4种机器学习算法的拟合效果与检验精度均有了大幅度提高。模型拟合精度由高到低的顺序为随机森林、梯度提升回归树、人工神经网络、支持向量回归、传统生物量模型;RF模型在各模型中的拟合精度最高,相对于传统生物量模型,RF模型的确定系数(R~2)提升了3.72%,均方根误差(R_(MSE))降低了44.47%,平均绝对误差(M_(AE))降低了42.81%,相对误差绝对值(M_(PB))降低了42.80%,赤池信息准则值降低了18.17%。模型检验精度由高到低的顺序为随机森林、人工神经网络、梯度提升回归树、支持向量回归、传统生物量模型;RF模型在各模型中的预测精度最高,与传统生物量模型相比,RF模型的确定系数(R~2)提升了1.08%,均方根误差(R_(MSE))降低了10.95%,平均绝对误差(M_(AE))降低了10.34%,相对误差绝对值(M_(PB))降低了10.34%,赤池信息准则值降低了5.20%。因此,相对于传统生物量模型,4种机器学习算法模型均可以提高兴安落叶松地上生物量的预测精度,RF模型的预测精度最高。