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.     

烷基苯磺酸钠对水生动物的生物效应研究

本文通过洗涤剂的主要成分—烷基苯磺酸钠对大型蚤和鲤鱼的毒性试验,说明烷基苯磺酸钠的毒性属中等。对大型蚤２４ｈＥＣ５０为７．２３ｍｇ／Ｌ,４８ｈＥＣ５０为３．８３ｍｇ／Ｌ;对鲤鱼４８ｈＬＣ５０为３．７４ｍｇ／Ｌ,９６ｈＬＣ５０为２．２３ｍｇ／Ｌ。鲤鱼生活在０．５ｍｇ／Ｌ的烷基苯磺酸钠溶液中,１５ｄ就能引起鳃的损伤。     

长江下游重点江段水质污染及对鱼类的毒性影响

通过对长江下游安庆、南京、镇江、南通４江段水质污染及其对鱼类毒性影响的调查监测可发现,长江下游江段主航道水质较好,符合国家地面水Ⅱ类水质标准．但近岸带水质由于受污染带的影响,水质污染较严重,其主要污染物为石油类和挥发酚等．上述这些污染物质对鱼类具有一定的毒性影响,其不但可引起鱼类的急性中毒,而且可诱发鱼类产生微核,并对鼠伤寒沙门氏菌ＴＡ９８菌株表现出一定的致突变性．同时在上述几个江段鱼体内可检出较高的蓄积性污染物的残留量．研究结果显示,长江下游江段正在遭受沿江诸多工业废水的污染,尤其是污染带的作用,并且这种污染对区域性渔业有一定的影响     

水中五氯酚钠对发光细菌毒性测定的影响因素

应用发光细菌检测法,考察了不同的影响因素对水体中典型的有机污染物五氯酚钠的生物毒性测定结果的影响.结果表明,五氯酚钠对发光细菌的EC₅₀值随着pH值和硬度的增加而增加;五氯酚钠的15 min EC₅₀和20 min EC₅₀基本相符;与水体中相同浓度的常规有机污染物相比,五氯酚钠表现出更强的毒性,实验中常规有机污染物的存在对五氯酚钠毒性测定的结果影响较小.原水毒性检测实验显示一定毒性(相对发光率降低14%),原水水质对测定结果影响程度与去离子水相似.     

环境污染物的分子毒理机制研究进展

以分子生物学技术为基础研究污染物的毒理机制．从分子水平揭示了污染物毒作用的本质。综述了国内外分子毒理机制的研究进展。详细阐述了毒理芯片、单细胞凝胶电泳等分子生物学技术应用与毒理学研究中的特点、应用前景以及存在的问题。提出了分子毒理机制今后的研究方向。     

饮食业复合油烟吸收剂的研制开发

分析了饮食油烟的成分 ,结合饮食油烟气的治理方法 ,采用正交设计法进行新型复合油烟吸收剂的实验 ,快速、有效、准确地优化确定了油烟吸收剂的配方和工艺 ,并设计了该吸收剂的油污相溶性、环境毒性、生物降解性实验 ,科学地论证了该产品的性能。结果表明 ,本实验研制的油烟吸收剂能够全面包络、粘合、皂化、附着和分离油烟废气中的油类物质 ,对饮食油烟具有快速、高效、彻底的治理效果 ,而且无毒、易降解。     

大型蚤毒理试验应用与研究进展

大型蚤作为国际公认的标准试验生物 ,其毒理试验被许多国家定为毒性必测项目 ,各国纷纷建立了自己的标准方法 ,因此有着广阔的应用前景。在分析中 ,主要介绍了大型蚤的试验培养技术和国内外对其毒理试验方面的研究概况。     

数据仓库在水环境质量评价系统中的应用前景

水环境质量评价工作涉及的数据量大,数据分散,评价标准多,分析模型多。现有的基于数据库系统的水环境质量评价系统面向的对象单一,分析功能弱。数据仓库系统可以把分散的数据经过抽取、转换,装载进中心数据仓库,建立多维数据模型,利用OLAP的分析功能完成各种水质评价工作,更好的辅助决策者决策。介绍了基于数据库的水环境质量评价系统的缺点,数据仓库的特点,初步设想了其在评价系统中的具体实现。     

Boosting large-scale river connectivity restoration by planning for the presence of unrecorded barriers

Conservation decisions are invariably made with incomplete data on species’ distributions, habitats, and threats, but frameworks for allocating conservation investments rarely account for missing data. We examined how explicit consideration of missing data can boost return on investment in ecosystem restoration, focusing on the challenge of restoring aquatic ecosystem connectivity by removing dams and road crossings from rivers. A novel way of integrating the presence of unmapped barriers into a barrier optimization model was developed and applied to the U.S. state of Maine to maximize expected habitat gain for migratory fish. Failing to account for unmapped barriers during prioritization led to nearly 50% lower habitat gain than was anticipated using a conventional barrier optimization approach. Explicitly acknowledging that data are incomplete during project selection, however, boosted expected habitat gains by 20–273% on average, depending on the true number of unmapped barriers. Importantly, these gains occurred without additional data. Simply acknowledging that some barriers were unmapped, regardless of their precise number and location, improved conservation outcomes. Given incomplete data on ecosystems worldwide, our results demonstrate the value of accounting for data shortcomings during project selection.