A comparison of statistical approaches for modelling fish species distributions

SUMMARY 1. The prediction of species distributions is of primary importance in ecology and conservation biology. Statistical models play an important role in this regard; however, researchers have little guidance when choosing between competing methodologies because few comparative studies have been conducted. 2. We provide a comprehensive comparison of traditional and alternative techniques for predicting species distributions using logistic regression analysis, linear discriminant analysis, classification trees and artificial neural networks to model: (1) the presence/absence of 27 fish species as a function of habitat conditions in 286 temperate lakes located in south‐central Ontario, Canada and (2) simulated data sets exhibiting deterministic, linear and non‐linear species response curves. 3. Detailed evaluation of model predictive power showed that approaches produced species models that differed in overall correct classification, specificity (i.e. ability to correctly predict species absence) and sensitivity (i.e. ability to correctly predict speciespresence) and in terms of which of the study lakes they correctly classified. Onaverage, neural networks outperformed the other modelling approaches, although all approaches predicted species presence/absence with moderate to excellent success. 4. Based on simulated non‐linear data, classification trees and neural networks greatly outperformed traditional approaches, whereas all approaches exhibited similar correct classification rates when modelling simulated linear data. 5. Detailed evaluation of model explanatory insight showed that the relative importance of the habitat variables in the species models varied among the approaches, where habitat variable importance was similar among approaches for some species and very different for others. 6. In general, differences in predictive power (both correct classification rate and identity of the lakes correctly classified) among the approaches corresponded with differences in habitat variable importance, suggesting that non‐linear modelling approaches (i.e. classification trees and neural networks) are better able to capture and model complex, non‐linear patterns found in ecological data. The results from the comparisons using simulated data further support this notion. 7. By employing parallel modelling approaches with the same set of data and focusing on comparing multiple metrics of predictive performance, researchers can begin to choose predictive models that not only provide the greatest predictive power, but also best fit the proposed application.     

Predictive modelling of freshwater fish as a biomonitoring tool in New Zealand

SUMMARY 1. A challenge has been issued to ecologists to find quantitative ecological relationships that have predictive power. A predictive approach has been successful when applied to biomonitoring using stream invertebrates with the River Invertebrate Prediction and Classification System (RIVPACS). This approach, to our knowledge, has not been applied to freshwater fish assemblages.
2. This paper describes the initial results of the application of a regional predictive model of freshwater fish occurrence using 200 reference sites sampled in the Manawatu–Wanganui region of New Zealand over late summer/autumn 2000. In brief (i) sites were classified into biotic groups (ii) the physical and chemical characteristics that best describe variation among these groups were determined and (iii) the relationship between these environmental variables and fish communities was used to predict the fauna expected at a site.
3. Reference sites clustered into six groups based on fish density and community composition. Using 14 physical variables least influenced by human activities, a discriminant model allocated 70% of sites to the correct biological classification group. The variables that best separated the site groups were mainly large-scale variables including altitude, distance from the coast, lotic ecoregion and map co-ordinates.
4. The model was further validated by randomly removing 20% of the sites, rebuilding the model and then determining the number of removed sites correctly allocated to their original biotic groups using environmental variables. Using this process 67% of the removed sites were correctly reassigned to the six predetermined groups.
5. A further 30 sites were used to determine the ability of the model to detect anthropogenic impact. The observed over expected taxa ( O / E ) ratios were significantly lower than the reference site O / E ratios, indicating a response of the fish assemblages to the known stressors.     

Catchment- and site-scale influences of forest cover and longitudinal forest position on the distribution of a diadromous fish

1. The hydrologic connectivity between landscape elements and streams means that fragmentation of terrestrial habitats could affect the distribution of stream faunas at multiple spatial scales. We investigated how catchment‐ and site‐scale influences, including proportion and position of forest cover within a catchment, and presence of riparian forest cover affected the distribution of a diadromous fish. 2. The occurrence of koaro (Galaxias brevipinnis) in 50‐m stream reaches with either forested or non‐forested riparian margins at 172 sites in 24 catchments on Banks Peninsula, South Island, New Zealand was analysed. Proportions of catchments forested and the dominant position (upland or lowland) of forest within catchments were determined using geographical information system spatial analysis tools. 3. Multivariate analysis of variance indicated forest position and proportion forested at the catchment accounted for the majority of the variation in the overall proportion of sites in a catchment with koaro. 4. Where forest was predominantly in the lower part of the catchments, the presence of riparian cover was important in explaining the proportion of sites with koaro. However, where forest was predominantly in the upper part of the catchment, the effect of riparian forest was not as strong. In the absence of riparian forest cover, no patterns of koaro distribution with respect to catchment forest cover or forest position were detected. 5. These results indicate that landscape elements, such as the proportion and position of catchment forest, operating at catchment‐scales, influence the distribution of diadromous fish but their influence depends on the presence of riparian vegetation, a site‐scale factor.     

Prediction of the location and type of beta-turns in proteins using neural networks.

A neural network has been used to predict both the location and the type of beta-turns in a set of 300 nonhomologous protein domains. A substantial improvement in prediction accuracy compared with previous methods has been achieved by incorporating secondary structure information in the input data. The total percentage of residues correctly classified as beta-turn or not-beta-turn is around 75% with predicted secondary structure information. More significantly, the method gives a Matthews correlation coefficient (MCC) of around 0.35, compared with a typical MCC of around 0.20 using other beta-turn prediction methods. Our method also distinguishes the two most numerous and well-defined types of beta-turn, types I and II, with a significant level of accuracy (MCCs 0.22 and 0.26, respectively).     

儿童青少年肺通气功能预测的后向传播神经网络方法

本文旨在研究儿童青少年肺通气功能预测的后向传播神经网络(backpropagation neural network,BPNN)方法,以期得到更准确的肺通气功能预计值。样本数据包括内蒙古自治区10~18岁汉族健康儿童青少年999人(男性500人,女性499人),测量身高和体重,使用肺功能仪检测肺通气功能。利用BPNN和多元逐步回归,对用力肺活量(forced vital capacity,FVC)、用力呼气一秒量(forced expiratory volume in one second,FEV1)、最大呼气流量(peak expiratory flow,PEF)、用力呼出25%肺活量时呼气流量(forced expiratory flow at25%of forced vital capacity,FEF25%)、用力呼出50%肺活量时呼气流量(forced expiratoryflow at50%of forced vital capacity,FEF50%)、最大呼气中段流量(maximal mid-expiratory flow,MMEF)、用力呼出75%肺活量时呼气流量(forced expira...     

Improving the prediction of protein secondary structure in three and eight classes using recurrent neural networks and profiles

Secondary structure predictions are increasingly becoming the workhorse for several methods aiming at predicting protein structure and function. Here we use ensembles of bidirectional recurrent neural network architectures, PSI-BLAST-derived profiles, and a large nonredundant training set to derive two new predictors: (a) the second version of the SSpro program for secondary structure classification into three categories and (b) the first version of the SSpro8 program for secondary structure classification into the eight classes produced by the DSSP program. We describe the results of three different test sets on which SSpro achieved a sustained performance of about 78% correct prediction. We report confusion matrices, compare PSI-BLAST to BLAST-derived profiles, and assess the corresponding performance improvements. SSpro and SSpro8 are implemented as web servers, available together with other structural feature predictors at: http://promoter.ics.uci.edu/BRNN-PRED/.