Modelling the abundance of three key plant species in New Zealand hill-pasture using a decision tree approach

Decision tree models were developed to investigate and predict the relative abundance of three key pasture plants [ryegrass (Lolium perenne), browntop (Agrostis capillaris), and white clover (Trifolium repens)] with integration of a geographical information system (GIS) in a naturalised hill-pasture in the North Island, New Zealand, and were compared with regression models with respect to model fit and predictive accuracy. The results indicated that the decision tree models had a better model fit in terms of average squared error (ASE) and a higher percentage of adequately predicted cases in model validation than the corresponding regression models. These decision tree models clearly revealed the relative importance of environmental and management variables in influencing the abundance of these three species. Hill slope was the most significant environmental factor influencing the abundance of ryegrass while soil Olsen P and annual P fertilizer input were the most significant factors influencing the abundance of browntop, and white clover, respectively. Soil Olsen P of approximately 10 μg/g, or a slope of about 10.5° was critical points where the competition between ryegrass and browntop tended to come to an equilibrium. Integrating the decision tree models with a GIS in this study not only facilitated the model development and analyses, but also provided a useful decision support tool in pasture management such as in assisting precision fertilizer placement. The insights obtained from the decision tree models also have important implications for pasture management, for example, it is important to maintain a soil Olsen P higher than 10 μg/g in order to keep the dominance of ryegrass in the hill-pasture.     

Testing the Generality of Bird-Habitat Models

Bird-habitat models are frequently used as predictive modeling tools—for example, to predict how a species will respond to habitat modifications. We investigated the generality of the predictions from this type of model. Multivariate models were developed for Golden Eagle (Aquila chrysaetos), Raven (Corvus corax), and Buzzard (Buteo buteo) living in northwest Scotland. Data were obtained for all habitat and nest locations within an area of 2349 km². This assemblage of species is relatively static with respect to both occupancy and spatial positioning. The area was split into five geographic subregions: two on the mainland and three on the adjacent Island of Mull, which has one of United Kingdom's richest raptor fauna assemblages. Because data were collected for all nest locations and habitats, it was possible to build models that did not incorporate sampling error. A range of predictive models was developed using discriminant analysis and logistic regression. The models differed with respect to the geographical origin of the data used for model development. The predictive success of these models was then assessed by applying them to validation data. The models showed a wide range of predictive success, ranging from only 6% of nest sites correctly predicted to 100% correctly predicted. Model validation techniques were used to ensure that the models' predictions were not statistical artefacts. The variability in prediction success seemed to result from methodological and ecological processes, including the data recording scheme and interregional differences in nesting habitat. The results from this study suggest that conservation biologists must be very careful about making predictions from such studies because we may be working with systems that are inherently unpredictable.     

Predicting constant decay rates of coarse woody debris—A meta-analysis approach with a mixed model

The aim of the study is the estimation of decay rates for coarse woody debris in large forest regions. These rates, together with estimations of the amount of deadwood, can be used to calculate the release of carbon from that pool into the atmosphere. The model can be used for predictions of decomposition rate constants in a wide range of forest areas (e.g. in process based ecological models, reporting of GHG-emissions), as only easily available predictor variables were used in the regression.Based on an intensive literature research a meta-analysis on influencing factors controlling the constant decay rate of coarse woody debris was set up. The included studies differed significantly in the survey methods as well as in the geographical origin. 39 studies were collected, 30 appeared in North America and nine in Europe. Based on these studies 291 observations of the remaining fraction of coarse woody debris were collected.To quantify the effects that influence the decomposition rates a nonlinear mixed effects model was constructed. Only physiologically interpretable variables were included. With this approach it was possible to determine influencing effects from mean temperature in July, annual rainfall (as quadratic term), diameter of woody material and grouping into hardwoods or conifers and mass- or density loss were significant variables. The mixed effects model also allowed an estimation of the species-specific effects on the decomposition process. These random effects are given for 42 tree species. The degrees of freedom were used efficiently. The model explains 79.6% of the variance and is superior to a comparable multiple regression model.     

Predicting Bird Species Distributions in Reconstructed Landscapes

Abstract:  Landscape optimization for biodiversity requires prediction of species distributions under alternative revegetation scenarios. We used Bayesian model averaging with logistic regression to predict probabilities of occurrence for 61 species of birds within highly fragmented box–ironbark forests of central Victoria, Australia. We used topographic, edaphic, and climatic variables as predictors so that the models could be applied to areas where vegetation has been cleared but may be replanted. Models were evaluated with newly acquired, independent data collected in large blocks of remnant native vegetation. Successful predictions were obtained for 18 of 45 woodland species (40%). Model averaging produced more accurate predictions than "single best" models. Models were most successful for smaller-bodied species that probably depend on particular vegetation types. Predictions for larger, generalist species, and seasonal migrants were less successful, partly because of changes in species distributions between model building (1995–1997) and validation (2004–2005) surveys. We used validated models to project occurrence probabilities for individual species across a 12,000-km² region, assuming native vegetation was present. These predictions are intended to be used as inputs, along with landscape context and temporal dynamics, into optimization algorithms to prioritize revegetation. Longer-term data sets to accommodate temporal dynamics are needed to improve the predictive accuracy of models.     

有机化合物生物富集因子的计算机预测研究

有机化合物在生物体内的富集,通常用生物富集因子(bioconcentration factor,简称BCF)来表达,这是化合物生态环境毒性评估的重要指标。为合理预测有机化合物是否易于生物富集,首先从美国环保局网站收集了624个具有不同BCF值的化合物,然后采用7种分子指纹结合5种机器学习方法(包括支持向量机、C4.5决策树、k最近邻法、随机森林法和朴素贝叶斯法),构建了化合物BCF的分类预测模型,所有模型均采用独立外部验证集进行验证。其中,使用Chemo Typer分子指纹结合支持向量机方法得到的二分类模型,整体预测准确度最好,达到了85.4%。通过采用信息增益、频率分析等方法,进一步确定了化合物中易于引起生物富集的关键子结构,包括芳基氯、二芳基醚、氯代烷烃等。研究中所用到的方法为有毒化学品的生态风险评价提供了良好可靠的预测工具。     

The roles of climate, phylogenetic relatedness, introduction effort, and reproductive traits in the establishment of non-native reptiles and amphibians

We developed a method to predict the potential of non-native reptiles and amphibians (herpetofauna) to establish populations. This method may inform efforts to prevent the introduction of invasive non-native species. We used boosted regression trees to determine whether nine variables influence establishment success of introduced herpetofauna in California and Florida. We used an independent data set to assess model performance. Propagule pressure was the variable most strongly associated with establishment success. Species with short juvenile periods and species with phylogenetically more distant relatives in regional biotas were more likely to establish than species that start breeding later and those that have close relatives. Average climate match (the similarity of climate between native and non-native range) and life form were also important. Frogs and lizards were the taxonomic groups most likely to establish, whereas a much lower proportion of snakes and turtles established. We used results from our best model to compile a spreadsheet-based model for easy use and interpretation. Probability scores obtained from the spreadsheet model were strongly correlated with establishment success as were probabilities predicted for independent data by the boosted regression tree model. However, the error rate for predictions made with independent data was much higher than with cross validation using training data. This difference in predictive power does not preclude use of the model to assess the probability of establishment of herpetofauna because (1) the independent data had no information for two variables (meaning the full predictive capacity of the model could not be realized) and (2) the model structure is consistent with the recent literature on the primary determinants of establishment success for herpetofauna. It may still be difficult to predict the establishment probability of poorly studied taxa, but it is clear that non-native species (especially lizards and frogs) that mature early and come from environments similar to that of the introduction region have the highest probability of establishment.     

Reproduction of olive tree habitat suitability for global change impact assessment

The olive tree is so typical of the Mediterranean climate that its presence in a territory qualifies the climate of this as Mediterranean. Many clues indicated that in the past olive cultivation limits moved northward or southward in the Northern Hemisphere according to warmer or cooler climate, respectively. This makes the olive tree cultivation area a possible biological indicator of changes in climate and the identification of the climatological parameters that limit its cultivation plays an important role for climate change impact assessment. In this work, three different approaches were compared, with the aim to compare methodologies suited to predict olive tree distribution over the Mediterranean basin: two classifiers (Random Forest, RF and an Artificial Neural Network, ANN) and a spatial model to infer climatic limiters of plant distribution (CLPD). These methodologies were applied within a framework including a geographical information system (GIS), which spatially defined olive tree cultivated area, and climatological informative layers (average temperature and cumulated rainfall, 50 km × 50 km), which were used as predictor variables. The results indicated that RF achieved on the whole, the lowest classification error (113 misclassified cases on 1906 test cases) followed by ANN (128 cases) and CLPD (153 cases). A validation test, performed over areas out of the Mediterranean basin where olive tree is cultivated (i.e. California and Southern Australia), confirmed the goodness of the RF fitted model in predicting olive tree suitable areas. In general, climatic predictor variables of the coldest and warmest periods of the year were the most significant in determining the limits of suitable olive cultivation area for these methodologies. In particular, temperature of January and July and rainfall of October and July were the climatic predictor variables having highest significance for both RF and ANN. Temperature of January >2 °C, of July >20 °C and cumulated annual rainfall >240 mm were the bounds found in the spatial model. The fitted RF model, coupled with the results of both Regional and General Circulation Model, was finally proposed to assess climate change impact on olive tree cultivated area in the Mediterranean basin.     

Comparison and ranking of different modelling techniques for prediction of site index in Mediterranean mountain forests

Forestry science has a long tradition of studying the relationship between stand productivity and abiotic and biotic site characteristics, such as climate, topography, soil and vegetation. Many of the early site quality modelling studies related site index to environmental variables using basic statistical methods such as linear regression. Because most ecological variables show a typical non-linear course and a non-constant variance distribution, a large fraction of the variation remained unexplained by these linear models. More recently, the development of more advanced non-parametric and machine learning methods provided opportunities to overcome these limitations. Nevertheless, these methods also have drawbacks. Due to their increasing complexity they are not only more difficult to implement and interpret, but also more vulnerable to overfitting. Especially in a context of regionalisation, this may prove to be problematic. Although many non-parametric and machine learning methods are increasingly used in applications related to forest site quality assessment, their predictive performance has only been assessed for a limited number of methods and ecosystems.In this study, five different modelling techniques are compared and evaluated, i.e. multiple linear regression (MLR), classification and regression trees (CART), boosted regression trees (BRT), generalized additive models (GAM), and artificial neural networks (ANN). Each method is used to model site index of homogeneous stands of three important tree species of the Taurus Mountains (Turkey): Pinus brutia, Pinus nigra and Cedrus libani. Site index is related to soil, vegetation and topographical variables, which are available for 167 sample plots covering all important environmental gradients in the research area. The five techniques are compared in a multi-criteria decision analysis in which different model performance measures, ecological interpretability and user-friendliness are considered as criteria.When combining these criteria, in most cases GAM is found to outperform all other techniques for modelling site index for the three species. BRT is a good alternative in case the ecological interpretability of the technique is of higher importance. When user-friendliness is more important MLR and CART are the preferred alternatives. Despite its good predictive performance, ANN is penalized for its complex, non-transparent models and big training effort.     

Chihuahuan Desert kangaroo rats: nonlinear effects of population dynamics, competition, and rainfall

Using long-term data on two kangaroo rats in the Chihuahuan Desert of North America, we fitted logistic models including the exogenous effects of seasonal rainfall patterns. Our aim was to test the effects of intraspecific interactions and seasonal rainfall in explaining and predicting the numerical fluctuations of these two kangaroo rats. We found that logistic models fit both data sets quite well; Dipodomys merriami showed lower maximum per capita growth rates than Dipodomys ordii, and in both cases logistic models were nonlinear. Summer rainfall appears to be the most important exogenous effect for both rodent populations; models including this variable were able to predict independent data better than models including winter rainfall. D. merriami was also negatively affected by another kangaroo rat (Dipodomys spectabilis), consistent with previous experimental evidence. We hypothesized that summer rainfall influences the carrying capacity of the environment by affecting seed availability and the intensity of intraspecific competition.     

Tree cover in sub-Saharan Africa: rainfall and fire constrain forest and savanna as alternative stable states

Savannas are known as ecosystems with tree cover below climate-defined equilibrium values. However, a predictive framework for understanding constraints on tree cover is lacking. We present (a) a spatially extensive analysis of tree cover and fire distribution in sub-Saharan Africa, and (b) a model, based on empirical results, demonstrating that savanna and forest may be alternative stable states in parts of Africa, with implications for understanding savanna distributions. Tree cover does not increase continuously with rainfall, but rather is constrained to low (<50%, "savanna") or high tree cover (>75%, "forest"). Intermediate tree cover rarely occurs. Fire, which prevents trees from establishing, differentiates high and low tree cover, especially in areas with rainfall between 1000 mm and 2000 mm. Fire is less important at low rainfall (<1000 mm), where rainfall limits tree cover, and at high rainfall (>2000 mm), where fire is rare. This pattern suggests that complex interactions between climate and disturbance produce emergent alternative states in tree cover. The relationship between tree cover and fire was incorporated into a dynamic model including grass, savanna tree saplings, and savanna trees. Only recruitment from sapling to adult tree varied depending on the amount of grass in the system. Based on our empirical analysis and previous work, fires spread only at tree cover of 40% or less, producing a sigmoidal fire probability distribution as a function of grass cover and therefore a sigmoidal sapling to tree recruitment function. This model demonstrates that, given relatively conservative and empirically supported assumptions about the establishment of trees in savannas, alternative stable states for the same set of environmental conditions (i.e., model parameters) are possible via a fire feedback mechanism. Integrating alternative stable state dynamics into models of biome distributions could improve our ability to predict changes in biome distributions and in carbon storage under climate and global change scenarios.     

Predicting abundance of desert riparian birds: validation and calibration of the Effective Area Model.

Reliable prediction of the effects of landscape change on species abundance is critical to land managers who must make frequent, rapid decisions with long-term consequences. However, due to inherent temporal and spatial variability in ecological systems, previous attempts to predict species abundance in novel locations and/or time frames have been largely unsuccessful. The Effective Area Model (EAM) uses change in habitat composition and geometry coupled with response of animals to habitat edges to predict change in species abundance at a landscape scale. Our research goals were to validate EAM abundance predictions in new locations and to develop a calibration framework that enables absolute abundance predictions in novel regions or time frames. For model validation, we compared the EAM to a null model excluding edge effects in terms of accurate prediction of species abundance. The EAM outperformed the null model for 83.3% of species (N=12) for which it was possible to discern a difference when considering 50 validation sites. Likewise, the EAM outperformed the null model when considering subsets of validation sites categorized on the basis of four variables (isolation, presence of water, region, and focal habitat). Additionally, we explored a framework for producing calibrated models to decrease prediction error given inherent temporal and spatial variability in abundance. We calibrated the EAM to new locations using linear regression between observed and predicted abundance with and without additional habitat covariates. We found that model adjustments for unexplained variability in time and space, as well as variability that can be explained by incorporating additional covariates, improved EAM predictions. Calibrated EAM abundance estimates with additional site-level variables explained a significant amount of variability (P < 0.05) in observed abundance for 17 of 20 species, with R2 values >25% for 12 species, >48% for six species, and >60% for four species when considering all predictive models. The calibration framework described in this paper can be used to predict absolute abundance in sites different from those in which data were collected if the target population of sites to which one would like to statistically infer is sampled in a probabilistic way.     

Litter decomposition and nitrogen mineralization from an annual to a monthly model

The forest litter decomposition model (FLDM) described in this paper provides an important basis for assessing the impacts of forest management on seasonal stream water quality and export of dissolved organic carbon (DOC). By definition, models with annual time steps are unable to capture seasonal, within-year variation. In order to simulate seasonal variation in litter decomposition and DOC production and export, we have modified an existing annual FLDM to account for monthly dynamics of decomposition and residual mass in experimental litterbags placed in 21 different forests across Canada.The original annual FLDM was formulated with three main litter pools (fast, slow, and very slow decomposing litter) to address the fact that forest litter is naturally composed of a mixture of organic compounds that decompose at different rates. The annual FLDM was shown to provide better simulations than more complex models like CENTURY and SOMM.The revised monthly model retains the original structure of the annual FLDM, but separates litter decomposition from nitrogen (N) mineralization. In the model, monthly soil temperature, soil moisture, and mean January soil temperature are shown to be the most important controlling variables of within-year variation in decomposition. Use of the three variables in a process-based definition of litter decomposition is a significant departure from the empirical definition in the annual model. The revised model is shown to give similar calculations of residual mass and N concentration as the annual model (r² = 0.91, 0.78), despite producing very different timeseries of decomposition over six years. It is shown from a modelling perspective that (i) forest litter decomposition is independent of N mineralization, whereas N mineralization is dependent on litter decomposition, and (ii) mean January soil temperature defines litter decomposition in the summer because of winter-temperatures’ role in modifying forest-floor microorganism community composition and functioning in the following summer.     

Consequences of Buffelgrass Pasture Development for Primary Productivity,Perennial Plant Richness,and Vegetation Structure in the Drylands of Sonora,Mexico

Abstract: In large parts of northern Mexico native plant communities are being converted to non‐native buffelgrass (Pennisetum ciliare) pastures, and this conversion could fundamentally alter primary productivity and species richness. In Sonora, Mexico land conversion is occurring at a regional scale along a rainfall‐driven gradient of primary productivity, across which native plant communities transition from desert scrub to thorn scrub. We used a paired sampling design to compare a satellite‐derived index of primary productivity, richness of perennial plant species, and canopy‐height profiles of native plant communities with buffelgrass pastures. We sampled species richness across a gradient of primary productivity in desert scrub and thorn scrub vegetation to examine the influence of site productivity on the outcomes of land conversion. We also examined the influence of pasture age on species richness of perennial plants. Index values of primary productivity were lower in buffelgrass pastures than in native vegetation, which suggests a reduction in primary productivity. Land conversion reduced species richness by approximately 50% at local and regional scales, reduced tree and shrub cover by 78%, and reduced canopy height. Land conversion disproportionately reduced shrub species richness, which reflects the common practice among Sonoran ranchers of conserving certain tree and cactus species. Site productivity did not affect the outcomes of land conversion. The age of a buffelgrass pasture was unrelated to species richness within the pasture, which suggests that passive recovery of species richness to preconversion levels is unlikely. Our findings demonstrate that land conversion can result in large losses of plant species richness at local and regional scales and in substantial changes to primary productivity and vegetation structure, which casts doubt on the feasibility of restoring native plant communities without active intervention on the part of land managers.     

基于GWR的中国地级城市SO2年均质量浓度模拟

中国城市空气污染问题已经引起广泛关注。目前相关研究很多,但是以空间位置为拟合参数,对空气质量进行回归模拟的研究较少。以2010年中国地级以上城市SO2年均质量浓度为因变量,分别应用普通线性回归和地理加权回归（GWR）模型模拟SO2年均质量浓度,其中地理加权回归方法考虑了空间位置的影响并以此作为回归参数。回归的自变量指标体系包括气象要素（多年平均温度、光照、降水）、植被覆盖（NDVI）、地形要素（坡度、坡向、起伏度）、人为因素（GDP、能源消费）几个方面。由于各指标之间存在较强的相关性,用主成分分析方法计算得到温度、日照、降水、NDVI表征的气象植被综合指标,高程、坡度、起伏度表征的地形综合指标,和GDP、能源消费表征的人为因素综合指标。用3个综合指标值作为自变量进行回归模拟。普通回归结果较差,其r^2为0.11,矫正的r^2为0.10;GWR模型模拟结果相对较好,其拟合优度显著提高,r^2为0.66,矫正的r^2为0.47。因此,地理加权回归适合进行此类拟合,普通线性回归不适合。通过对比地理加权回归模拟的各个城市的拟合优度,发现年均质量浓度数值较高的地区拟合效果较差,这些地区主要集中在中国华北和南部部分地区。与基于机理的模型相比,GWR 模型和其各具优缺点,GWR 的优势主要表现在数据及其格式化要求低,计算机软硬件条件要求低,运算速度快等。     

Potential aboveground biomass in drought-prone forest used for rangeland pastoralism

The restoration of cleared dry forest represents an important opportunity to sequester atmospheric carbon. In order to account for this potential, the influences of climate, soils, and disturbance need to be deciphered. A data set spanning a region defined the aboveground biomass of mulga (Acacia aneura) dry forest and was analyzed in relation to climate and soil variables using a Bayesian model averaging procedure. Mean annual rainfall had an overwhelmingly strong positive effect, with mean maximum temperature (negative) and soil depth (positive) also important. The data were collected after a recent drought, and the amount of recent tree mortality was weakly positively related to a measure of three-year rainfall deficit, and maximum temperature (positive), soil depth (negative), and coarse sand (negative). A grazing index represented by the distance of sites to watering points was not incorporated by the models. Stark management contrasts, including grazing exclosures, can represent a substantial part of the variance in the model predicting biomass, but the impact of management was unpredictable and was insignificant in the regional data set. There was no evidence of density-dependent effects on tree mortality. Climate change scenarios represented by the coincidence of historical extreme rainfall deficit with extreme temperature suggest mortality of 30.1% of aboveground biomass, compared to 21.6% after the recent (2003-2007) drought. Projections for recovery of forest using a mapping base of cleared areas revealed that the greatest opportunities for restoration of aboveground biomass are in the higher-rainfall areas, where biomass accumulation will be greatest and droughts are less intense. These areas are probably the most productive for rangeland pastoralism, and the trade-off between pastoral production and carbon sequestration will be determined by market forces and carbon-trading rules.     

Age and spatial distribution of the world's oldest trees

Extremely old trees have important roles in providing insights about historical climatic events and supporting cultural values, yet there has been limited work on their global distribution and conservation. We extracted information on 197,855 tree cores from 4854 sites and combined it with other tree age (e.g., the OLDLIST) data from a further 156 sites to determine the age of the world's oldest trees and quantify the factors influencing their global distribution. We found that extremely old trees >1000 years were rare. Among 30 individual trees that exceeded 2000 years old, 27 occurred in high mountains. We modeled maximum tree age with climatic, soil topographic, and anthropogenic variables, and our regression models demonstrated that elevation, human population density, soil carbon content, and mean annual temperature were key determinants of the distribution of the world's oldest trees. Specifically, our model predicted that many of the oldest trees will occur in high-elevation, cold, and arid mountains with limited human disturbance. This pattern was markedly different from that of the tallest trees, which were more likely to occur in relatively more mesic and productive locations. Global warming and expansion of human activities may induce rapid population declines of extremely old trees. New strategies, including targeted establishment of conservation reserves in remote regions, especially those in western parts of China and the United States, are required to protect these trees.     

New approaches to modelling fish-habitat relationships

Ecologists often develop models that describe the relationship between faunal communities and their habitat. Coral reef fishes have been the focus of numerous such studies, which have used a wide range of statistical tools to answer an equally wide range of questions. Here, we apply a series of both conventional statistical techniques (linear and generalized additive regression models) and novel machine-learning techniques (the support vector machine and three ensemble techniques used with regression trees) to predict fish species richness, biomass, and diversity from a range of habitat variables. We compare the techniques in terms of their predictive performance, and we compare a subset of the models in terms of the influence each habitat variable has for the predictions. Prediction errors are estimated by cross-validation, and variable importance is assessed using permutations of individual variable values. For predictions of species richness and diversity the tree-based models generally and the random forest model specifically are superior (produce the lowest errors). These model types are all able to model both nonlinear and interaction effects. The linear model, unable to model either effect type, performs the worst (produces the highest errors). For predictions of biomass, the generalized additive model is superior, and the support vector machine performs the worst. Depth range, the difference between maximum and minimum water depth at a given site, is identified as the most important variable in the majority of models predicting the three fish community variables. However, variable importance is highly dependent upon model type, which leads to questions regarding the interpretation of variable importance and its proper use as an indicator of causality. The representation of ecological relationships by tree-based ensemble learners will improve predictive performance, and provide a new avenue for exploring ecological relationships, both statistical and causal.