Comparing discriminant analysis, neural networks and logistic regression for predicting species distributions: a case study with a Himalayan river bird

We assessed the occurrence of a common river bird, the Plumbeous Redstart Rhyacornis fuliginosus, along 180 independent streams in the Indian and Nepali Himalaya. We then compared the performance of multiple discrimant analysis (MDA), logistic regression (LR) and artificial neural networks (ANN) in predicting this species’ presence or absence from 32 variables describing stream altitude, slope, habitat structure, chemistry and invertebrate abundance. Using the entire data (=training set) and a threshold for accepting presence in ANN and LR set to P≥0.5, ANN correctly classified marginally more cases (88%) than either LR (83%) or MDA (84%). Model performance was assessed from two methods of data partitioning. In a ‘leave-one-out’ approach, LR correctly predicted more cases (82%) than MDA (73%) or ANN (69%). However, in a holdout procedure, all the methods performed similarly (73–75%). All methods predicted true absence (i.e. specificity in holdout: 81–85%) better than true presence (i.e. sensitivity: 57–60%). These effects reflect species’ prevalence (=frequency of occurrence), but are seldom considered in distribution modelling. Despite occurring at only 36% of the sites, Plumbeous Redstarts are one of the most common Himalayan river birds, and problems will be greater with less common species. Both LR and ANN require an arbitrary threshold probability (often P=0.5) at which to accept species presence from model prediction. Simulations involving varied prevalence revealed that LR was particularly sensitive to threshold effects. ROC plots (received operating characteristic) were therefore used to compare model performance on test data at a range of thresholds; LR always outperformed ANN. This case study supports the need to test species’ distribution models with independent data, and to use a range of criteria in assessing model performance. ANN do not yet have major advantages over conventional multivariate methods for assessing bird distributions. LR and MDA were both more efficient in the use of computer time than ANN, and also more straightforward in providing testable hypotheses about environmental effects on occurrence. However, LR was apparently subject to chance significant effects from explanatory variables, emphasising the well-known risks of models based purely on correlative data.     

Uncovering the evolution of tin use in the United States and its implications

• US tin use decreases as the GDP value added by manufacturing sector increases. • Global and China’s tin use increases as the GDP added by manufacturing increases. • A sigmoid curve can fit the US tin use data well. • US tin use patterns is not due to the finite tin reserves or resources. • Policies, substitutions, etc. play key roles in the changing tin use patterns. Tin is of key importance to daily life and national security; it is considered an essential industrial metal. The United States (US) is the world’s largest economy and consumer of natural resources. Therefore, the analysis of historical tin use in the US is helpful for understanding future tin use trends in the world as a whole and in developing countries. Time series analysis, regression analysis with GDP or GDP/capita, and historical data fitted with logistic and Gompertz models are employed in this study. Historical tin use in the US shows three stages—increase-constant-decrease, as GDP per capita has increased. Tin use in the US is negatively correlated with the GDP value added by the manufacturing sector, while the use of tin worldwide and in China continues to increase along with the GDP value added by the manufacturing sector. Although a sigmoid curve can fit the US tin use data well, that use is not directly related to the limited tin reserves or resources. Rather, policies, economic restructuring, substitutions, new end-use markets, etc. have played key roles in the changing tin use patterns. This work contributes to understanding future tin use at both the global and national levels: tin use will continue to increase with GDP at the global level, but use patterns of tin at the national level can be changed through human intervention.     

Refining logistic regression models for wildlife habitat suitability modeling—A case study with muntjak and goral in the Central Himalayas, India

High quality habitat suitability maps are indispensable for the management and planning of wildlife reserves. This is particularly important for megadiverse developing countries where shortages in skilled manpower and funding may preclude the use of mathematically complex modeling techniques and resource-intensive field surveys. In this study, we propose a simulation based k-fold partitioning and re-substitution approach to refine and update logistic regression models that are widely used for habitat suitability assessment and modeling. We test the modeling strategy using data from a rapid field survey conducted for habitat suitability assessment for muntjak (Muntiacus muntjak) and goral (Naemorrhaedus goral) in the central Himalayas, India. Results obtained from simulations match expectations in terms of model behavior and in terms of published habitat associations of the investigated species. Qualitative comparisons with predictions from the GARP, MaxEnt and Bioclimatic Envelopes modeling systems also show broad agreement with predictions obtained from the proposed technique. The proposed technique is suggested as a rapid-assessment precursor to detailed habitat studies such as patch occupancy modeling in situations where funds or trained manpower are not available.     

A Bayesian approach to multi-source forest area estimation

In efforts such as land use change monitoring, carbon budgeting, and forecasting ecological conditions and timber supply, there is increasing demand for regional and national data layers depicting forest cover. These data layers must permit small area estimates of forest area and, most importantly, provide associated error estimates. This paper presents a model-based approach for coupling mid-resolution satellite imagery with plot-based forest inventory data to produce estimates of probability of forest and associated error at the pixel-level. The proposed Bayesian hierarchical model provides access to each pixel’s posterior predictive distribution allowing for a highly flexible analysis of pixel and multi-pixel areas of interest. The paper presents a trial using multiple dates of Landsat imagery and USDA Forest Service Forest Inventory and Analysis plot data. The results describe the spatial dependence structure within the trial site, provide pixel and multi-pixel summaries of probability of forest land use, and explore discretization schemes of the posterior predictive distributions to forest and non-forest classes. Model prediction results of a holdout set analysis suggest the proposed model provides high classification accuracy, 88%, for the trial site.

快速城市化背景下不同建设用地扩张的驱动差异探讨：以浙江省义乌市为例

已有城市扩张文献多将建设用地视为单一对象,而较少考虑不同类型的建设用地可能受差别化的驱动因素的影响。针对此,论文以浙江义乌为例,采用无序多分类Logistic回归模型,分析了2006—2014年间义乌商住用地与工业用地扩张所受驱动力的差异。结果表明：商住用地与工业用地扩张均受到自然环境、社会经济区位、邻域状态及空间政策等多重因素的综合影响,但也存在明显的内部差异：一是驱动商住用地扩张的因素并不必然作用于工业用地,反之亦然;二是作用于两类用地扩张的同一驱动因素,其作用方向也可能截然相反;三是对两类用地扩张具有相同作用方向的驱动因素,其作用强度也往往不同,并形成了义乌“产城分离”的城市发展格局。论文揭示了城市化背景下不同建设用地扩张的驱动差异特征,对现有驱动力研究进行了一定拓展,能够为城市规划和城市用地分类管理提供科学依据和直接参考。     

农村水污染治理驱动因素的利益相关者识别

引入利益相关者理论对我国农村水污染治理减低污染风险的驱动因素进行了识别。通过对农村水污染系统内的利益相关者进行界定,划分了政府、农村社区居民和社会力量3个利益群体,并通过Binary Logistic回归模型对3个利益群体的驱动力进行量化分析,经实证模型检验表明,反映政府作用的考核机制(含财政投入与监管能力)、反映社会力量的社会资金投入以及反映农村社区作用的自主管理能力和居民环保投入所占比重的发生比(OR值)分别为2.248、1.725、1.525和1.236,表明政府主导对减轻农村水污染起关键作用,社会力量和农民社区自身多方发挥作用对降低农村水污染风险的影响也是显著的。     

Assessment of carbon leakage in multiple carbon-sink projects: a case study in Jambi Province,Indonesia

Rehabilitation of degraded forest land through implementation of carbon-sink projects can increase terrestrial carbon (C) stock. However, carbon emissions outside the project boundary, which is commonly referred to as leakage, may reduce or negate the sequestration benefits. This study assessed leakage from carbon-sink projects that could potentially be implemented in the study area comprised of 11 sub-districts in the Batanghari District, Jambi Province, Sumatra, Indonesia. The study estimates the probability of a given land use/cover being converted into other uses/cover, by applying a logit model. The predictor variables were: proximity to the center of the land use area, distance to transportation channel (road or river), area of agricultural land, unemployment (number of job seekers), job opportunities, population density and income. Leakage was estimated by analyzing with and without carbon-sink projects scenarios. Most of the predictors were estimated as being significant in their contribution to land use cover change. The results of the analysis show that leakage in the study area can be large enough to more than offset the project’s carbon sequestration benefits during the period 2002–2012. However, leakage results are very sensitive to changes of carbon density of the land uses in the study area. By reducing C-density of lowland and hill forest by about 10% for the baseline scenario, the leakage becomes positive. Further data collection and refinement is therefore required. Nevertheless, this study has demonstrated that regional analysis is a useful approach to assess leakage.     

大气消光系数垂直分布模型及其适用性研究

大气消光系数垂直分布模型是利用卫星反演近地面颗粒物质量浓度的关键技术环节,同时也是分析边界层湍流场结构的重要途径,但其适用性问题至今尚不清晰.基于Logistic曲线模拟大气消光系数廓线的初步研究成果,结合太阳光度计（CE-318）观测的大气光学厚度（AOD）资料以及近地面能见度数据,提出了大气消光系数垂直分布Logistic模型的参数计算方法.针对成都市2013年6月~2014年5月期间的实例应用结果表明,在不稳定和中性层结条件下,Logistic模型和目前通用的负指数模型对大气消光系数垂直分布的模拟效果总体相当;但在持续稳定层结条件下,Logistic模型的模拟效果则显著占优.进一步分析指出,大气消光系数垂直分布Logistic模型更优的适用性主要在于其对近地层大气消光的复杂垂直形态具有良好的表征能力.     

铁路水害特征与致灾概率预测模型研究

我国铁路水害频发且损失巨大,如何有效防范,已成业界难题,更为运营部门汛期工作重点。但铁路水害泛指由降水或其他水源造成断道、限速事故的灾害,预测预报缺乏针对性。鉴于此,首先,借鉴水利学水害概念,丰富了铁路水害的机理内涵,再结合铁路调研,明确了预测目标的外延;其次,基于京广线湖(南)广(东)区段水害气象、地质与设施条件统计,分析了铁路水害的时空分布特征,建立了致灾因子指标体系;最后,针对降水这一关键诱发因子,筛选出1 h与日降雨量两个相关性最强的计算参数,建立了logistic概率预测模型。模型检验表明:其统计学检验通过,且对于灾害实际情况预测效果较好,可为铁路水害风险管理及防范措施的制定提供参考。     

Learning Machines Applied to Potential Forest Distribution

The clearing of forests to obtain land for pasture and agriculture and the replacement of autochthonous species by other faster-growing varieties of trees for timber have both led to the loss of vast areas of forest worldwide. At present, many developed countries are attempting to reverse these effects, establishing policies for the restoration of older woodland systems. Reforestation is a complex matter, planned and carried out by experts who need objective information regarding the type of forest that can be sustained in each area. This information is obtained by drawing up feasibility models constructed using statistical methods that make use of the information provided by morphological and environmental variables (height, gradient, rainfall, etc.) that partially condition the presence or absence of a specific kind of forestation in an area. The aim of this work is to construct a set of feasibility models for woodland located in the basin of the River Liébana (NW Spain), to serve as a support tool for the experts entrusted with carrying out the reforestation project. The techniques used are multilayer perceptron neural networks and support vector machines. Their results will be compared to the results obtained by traditional techniques (such as discriminant analysis and logistic regression) by measuring the degree of fit between each model and the existing distribution of woodlands. The interpretation and problems of the feasibility models are commented on in the Discussion section.