Laboratoire d'écologie et biologie aquatique : species distribution ensemble modelling for presence only data with automated jobs management on calculation server. (version: 0.1.13)


LebaMod is a tool to analyse species presence only dataset with classification models. The name come from Leba, 'Laboratoire d'écologie et biologie acquatique, (Université de Genève)', and mod, statistical modelling. It could be seen as a graphical interface to Caret package ('classification and regression training'), with automated calculation done on remote server and locally managed into a Sqlite database and R single objects for easy filtering and ensemble analysis. The focus is set on the exploration of a potentially large combinaison of models, predictors and parameterers while getting the most accurate spatial and temporal prediction data. Every parameters, method, dataset, predictors used in finals models are collected and can be downloaded for further analysis. It should be quite easy to reproduce every output produced by this application : output objects (class lebaBundle) contain a list filled with species, predictors and parameters data (class lebaData), together with a standard Caret object (class train/train.formula). The project itself is completly available in a git repository. Update are made each time new results are available.

Input data

The data used in this application is stored in a single SQLite database with two tables : species presence coordinates and predictors values at the same spatial and time extent. See in attribution part for more information.


The main form at left select and filter species, predictors and method data. Every change produce a summary in corresponding tabs : e.g. select a statistical method produce a list of method, with hyperlink to CRAN (Comprehensive R Archive Network) and set of tags, as defined by the Caret package.




Email for notification.

- Your email will be stored only to link the resulting models and send you a notifications when the process is done. No other uses will be attempted. However, this email is stored as is in a database, on our server. We can not guarantee a perfect secure transmission and storage. With this in mind, you could choose to use one from a disposable email service such as mailinator.com. For more informations on this topic, see http://en.wikipedia.org/wiki/Disposable_email_address


- Multiple selection of species to be modelled, based on a list returned by slider 'Range of distinct species sites'. Models based on species distribution with few occurence could fail or be inaccurate. In species tab, a map is updated with every records found in database. Spatial aggregation presented in this map is done by a clustering alogorithm to give a better view of sites spatial distribution.
- Slider 'Range of distinct presence sites' filters the range of distinct presence sites across whole period, for each species. A distinct site of presence is a unique coordinate for a given year. If multiple records are found with same coordinates and same year for a particular species, they are counted as one site.

Pseudo-absence generator

- Type of pseudo absence selection : to calibrate presence only model, we need to generate absences with a selection algoritm, e.g. random site sampling. The number of pseudo absence to generate depends of multiple criteria, e.g. type of model (regression/classification) or number of presences available. More informations about selection strategy in barbet2012, lobo2011 and elith2011. In this version of lebaMod, only random spatial sampling with fixed number or multiplicator of pseudo-absence are available. nPa= number of pseudo absence = fixed number, mPa: number of pseudo absence =multiplicator * presence


- Function 'caret::findCorrelation' can help to remove highly correlated predictors before modelisation, based on pair-wise absolute correlation of the training set. With this option set at 1, nothing will be removed, except identical predictors. From the documentation : If two variables have a high correlation, the function looks at the mean absolute correlation of each variable and removes the variable with the largest mean absolute correlation. Predictors with low correlation will be named 'prdLoCorr' and those considered as highly correlated 'prdHiCorr'. Only low correlated ones are used in model. See also in model details/tags to see if it use predictors auto removal internal procedure
- Multiple predictors selection. Predictors descriptions and spatialy summarized time series are available in predictors tab. The minumum number of predictors is 3.




- Compute all pseudo absences selection and models multiple times.

Compute models

Map of occurences : selected species, all years.

Display all occurences, possibly with multiple occurences at the same site and same year. Duplicate will be removed during modelling process

Summary of predictors and spatial data for each presence distribution.

Description of selected methods

List of selected method with

Time series of predictors

Display spatialy aggregated time series for predictors.

Predictor description list :

Table of jobs to be computed.

Table of jobs in queue.

Filter available results

Predictor filter

Subset models available to plot and download

(based on filtered models)

Download selected models (zip) Download predictions data (rds)

Presence probabilities bivariate plot.

(based on filtered models. Could take some time, be patient)

Download plot (lattice/rds)

R session info on local host.


R session info on remote host.



Predictability, Constancy, and Contingency of Periodic Phenomena
R. K. Colwell
Ecology  55  pp. 1148-1153  (1974)
The Works of William Paley, DD: Natural theology
W. Paley and G. W. Meadley
  1    (1810)
hexbin: Hexagonal Binning Routines
D. Carr and ported by Nicholas Lewin-Koh and M. Maechler
{Leaflet, An Open-Source JavaScript Library for Mobile-Friendly Interactive Maps}
V. Agafonkin
shiny: Web Application Framework for R
RStudio and Inc.
Effects of sample size on the performance of species distribution models
M. S. Wisz and R. Hijmans and J. Li and A. T. Peterson and C. Graham and A. Guisan
Diversity and Distributions  14  763--773  (2008)
Fast stable restricted maximum likelihood and marginal likelihood estimation of semiparametric generalized linear models
S. N. Wood
Journal of the Royal Statistical Society: Series B (Statistical Methodology)  73  3--36  (2011)
A review of methods for the assessment of prediction errors in conservation presence/absence models
A. H. Fielding and J. F. Bell
Environmental conservation  24  38--49  (1997)
BIOCLIM-a bioclimate analysis and prediction system
J. Busby
Plant Protection Quarterly  6    (1991)
Random forests
L. Breiman
Machine learning  45  5--32  (2001)
The state of boosting
G. Ridgeway
Computing Science and Statistics    172--181  (1999)
Pattern recognition and neural networks
B. D. Ripley
Classification and regression trees
L. Breiman
Multivariate adaptive regression splines
J. H. Friedman
The annals of statistics    1--67  (1991)
Generalized additive models
T. Hastie and R. Tibshirani
  43    (1990)
Generalized linear model
P. McCullagh and J. A. Nelder
  37    (1989)
Building predictive models in R using the caret package
M. Kuhn
Journal of Statistical Software  28  1--26  (2008)
Species distribution modelling---Effect of design and sample size of pseudo-absence observations
J. N. Stokland and R. Halvorsen and B. Støa
Ecological Modelling  222  1800--1809  (2011)
Exploring the effects of quantity and location of pseudo-absences and sampling biases on the performance of distribution models with limited point occurrence data
J. M. Lobo and M. F. Tognelli
Journal for Nature Conservation  19  1--7  (2011)
Selecting pseudo-absences for species distribution models: how, where and how many?
M. Barbet-Massin and F. Jiguet and C. H. Albert and W. Thuiller
Methods in Ecology and Evolution  3  327--338  (2012)
Interacting with data using the filehash package
R. D. Peng
R News  6  19--24  (2006)
Redundancy and the choice of hydrologic indices for characterizing streamflow regimes
J. D. Olden and N. Poff
River Research and Applications  19  101--121  (2003)
The ade4 package: implementing the duality diagram for ecologists
S. Dray and A. B. Dufour
Journal of Statistical Software  22  1-20  (2007)
Assessing habitat-suitability models with a virtual species
A. Hirzel and V. Helfer and F. Metral
Ecological Modelling  145  111--121  (2001)
Extended statistical approaches to modelling spatial pattern in biodiversity in northeast New South Wales. I. Species-level modelling
S. Ferrier and G. Watson and J. Pearce and M. Drielsma
Biodiversity \& Conservation  11  2275--2307  (2002)
Assessing the effects of pseudo-absences on predictive distribution model performance
R. M. Chefaoui and J. M. Lobo
Ecological modelling  210  478--486  (2008)
Soil and water assessment tool: theoretical documentation, version 2005
S. Neitsch and J. Arnold and J. Kiniry and J. Williams and K. King
Texas, USA      (2005)
Time Series Analysis Module: River Analysis Package
N March
Streamflow Modeling in a Highly Managed Mountainous Glacier Watershed Using SWAT: The Upper Rhone River Watershed Case in Switzerland
K. Rahman and C. Maringanti and M. Beniston and F. Widmer and K. Abbaspour and A. Lehmann
Water Resources Management  27  323--339  (2013)
Effects of sample size on accuracy of species distribution models
D. R. Stockwell and A. T. Peterson
Ecological modelling  148  1--13  (2002)
An introduction to ROC analysis
T. Fawcett
Pattern recognition letters  27  861--874  (2006)
A maximum entropy approach to species distribution modeling
S. J. Phillips and M. Dudík and R. E. Schapire
    83  (2004)
The problem of overfitting
D. M. Hawkins and others
Journal of chemical information and computer sciences  44  1--12  (2004)
BIOMOD--a platform for ensemble forecasting of species distributions
W. Thuiller and B. Lafourcade and R. Engler and M. B. Araújo
Ecography  32  369--373  (2009)
Assessing the accuracy of species distribution models: prevalence, kappa and the true skill statistic (TSS)
O. Allouche and A. Tsoar and R. Kadmon
Journal of applied ecology  43  1223--1232  (2006)
Assessing the vulnerability of aquatic species to climate change in a mountainous watershed: supplementing presence-only data with species traits.
A. L. Monbertrand and P. Burlando and E. Castella and S. Fatichi and Y. Gonseth and A. Lehmann and F. Moser and K. Rahman
Biodiversity and Distributions      (2013)
The Measurement of Observer Agreement for Categorical Data
J. R. Landis and G. G. Koch
Biometrics  33  pp. 159-174  (1977)
Quantitative analysis of watershed geomorphology
A. N. Strahler
Transactions of the American Geophysical Union  38  913--920  (1957)
Atlas Géotechnique Suisse
Swiss Environmental Domains: A new spatial framework for reporting on the environment
A coefficient of agreement for nominal scales
J. Cohen and others
Educational and psychological measurement  20  37--46  (1960)
raster: Geographic data analysis and modeling
R. J. H. J. van Etten
spgrass6: Interface between GRASS 6 and R
R. Bivand
RStudio: Integrated development environment for R (Version 0.96.122)
caret: Classification and Regression Training
M. Kuhn and J. Wing and S. Weston and A. Williams and C. Keefer and A. Engelhardt
knitr: A general-purpose package for dynamic report generation in R
Y. Xie
R: A Language and Environment for Statistical Computing
R Core Team
Geographic Resources Analysis Support System (GRASS GIS) Software
GRASS Development Team
Ecological-Niche Factor Analysis: How to Compute Habitat-Suitability Maps without Absence Data?
A. H. Hirzel and J. Hausser and D. Chessel and N. Perrin
Ecology  83  pp. 2027-2036  (2002)
Applications of artificial neural networks for patterning and predicting aquatic insect species richness in running waters
Y. S. Park and R. Céréghino and A. Compin and S. Lek
Ecological Modelling  160  265--280  (2003)
Predicting species spatial distributions using presence-only data: a case study of native New Zealand ferns
A. E. Zaniewski and A. Lehmann and J. M. C. Overton
Ecological modelling  157  261--280  (2002)
Disruption of a longitudinal pattern in environmental factors and benthic fauna by a glacial tributary
S. Knispel and E. Castella
Freshwater Biology  48  604--618  (2003)
Invertebrate drift and physico-chemical variables in the tributaries of the Mutt, a Swiss glacial stream
C. Ilg and E. Castella and B. Lods-Crozet and P. Marmonier
Archiv für Hydrobiologie  151  335--352  (2001)
Macroinvertebrate community structure in relation to environmental variables in a Swiss glacial stream
B. Lods-Crozet and E. Castella and D. Cambin and C. Ilg and S. Knispel and H. Mayor-Simeant
Freshwater Biology  46  1641--1661  (2001)
Hydraulique et hydrologie
S. Bennis
A methodology for investigation of the seasonal evolution in proglacial hydrograph form
D. M. Hannah and A. M. Gurnell and G. R. McGregor
Hydrological Processes  13  2603--2621  (1999)
Climatic change in mountain regions: a review of possible impacts
M. Beniston
Climatic Change  59  5--31  (2003)
Mountain weather and climate: A general overview and a focus on climatic change in the Alps
M. Beniston
Hydrobiologia  562  3-16  (2006)
Use of complex hydraulic variables to predict the distribution and density of unionids in a side channel of the Upper Mississippi River
J. J. Steuer and T. J. Newton and S. J. Zigler
Hydrobiologia  610  67--82  (2008)
{Stream hydraulics as a major determinant of benthic invertebrate zonation patterns}
B. Statzner and B. Higler
{Freshwater Biology}  {16}  {127-139}  (1986)
The assessment of shear stress and bed stability in stream ecology
A. C. Schwendel and R. G. Death and I. C. Fuller
Freshwater Biology  55  261-281  (2010)
Modelling distribution and abundance with presence-only data
J. L. Pearce and M. S. Boyce
Journal of Applied Ecology  43  405--412  (2006)
Presence-absence versus presence-only modelling methods for predicting bird habitat suitability
L. Brotons and W. Thuiller and M. B. Araújo and A. H. Hirzel
Ecography  27  437--448  (2004)
Patterns of macroinvertebrate traits along three glacial stream continuums
C. Ilg and E. Castella
Freshwater Biology  51  840--853  (2006)
Modelling primary production in a coastal embayment affected by upwelling using dynamic ecosystem models and artificial neural networks
R. Barciela and E. Garcia and E. Fernandez
Ecological Modelling  120  199--211  (1999)
Microsatellites and artificial neural networks: tools for the discrimination between natural and hatchery brown trout (Salmo trutta, L.) in Atlantic populations
D. Aurelle and S. Lek and J. Giraudel and P. Berrebi
Ecological Modelling  120  313--324  (1999)
Water and carbon fluxes above European coniferous forests modelled with artificial neural networks
M. van Wijk and W. Bouten
Ecological Modelling  120  181--197  (1999)
Support vector machines for optimal classification and spectral unmixing
M. Brown and S. Gunn and H. Lewis
Ecological Modelling  120  167--179  (1999)
Neural network models to study relationships between lead concentration in grasses and permanent urban descriptors in Athens city (Greece)
I. Dimopoulos and J. Chronopoulos and A. Chronopoulou-Sereli and S. Lek
Ecological Modelling  120  157--165  (1999)
Software sensor design based on empirical data
M. Masson and S. Canu and Y. Grandvalet and A. Lynggaard-Jensen
Ecological Modelling  120  131--139  (1999)
Neural network architecture selection: new Bayesian perspectives in predictive modelling - Application to a soil hydrology problem
J. Vila and V. Wagner and P. Neveu and M. Voltz and P. Lagacherie
Ecological Modelling  120  119--130  (1999)
pH modelling by neural networks. Application of control and validation data series in the Middle Loire river
F. Moatar and F. Fessant and A. Poirel
Ecological Modelling  120  141--156  (1999)
State-of-the-art of ecological modelling with emphasis on development of structural dynamic models
S. Jorgensen
Ecological Modelling  120  75--96  (1999)
Radial basis function networks with partially classified data
I. Morlini
Ecological Modelling  120  109--118  (1999)
Applications of the self-organising feature map neural network in community data analysis
G. Foody
Ecological Modelling  120  97--107  (1999)
Use of artificial neural networks for predicting rice crop damage by greater flamingos in the Camargue, France
C. Tourenq and S. Aulagnier and F. Mesleard and L. Durieux and A. Johnson and G. Gonzalez and S. Lek
Ecological Modelling  120  349--358  (1999)
Comparing discriminant analysis, neural networks and logistic regression for predicting species distributions: a case study with a Himalayan river bird
S. Manel and J. Dias and S. Ormerod
Ecological Modelling  120  337--347  (1999)
Predicting fish yield of African lakes using neural networks
R. Lae and S. Lek and J. Moreau
Ecological Modelling  120  325--335  (1999)
Developing an empirical model of phytoplankton primary production: a neural network case study
M. Scardi and L. Harding
Ecological Modelling  120  213--223  (1999)
Wedding connectionist and algorithmic modelling towards forecasting Caulerpa taxifolia development in the north-western Mediterranean sea
A. Aussem and D. Hill
Ecological Modelling  120  225--236  (1999)
Applying artificial neural network methodology to ocean color remote sensing
L. Gross and S. Thiria and R. Frouin
Ecological Modelling  120  237--246  (1999)
Individual-based modelling of fishermen search behaviour with neural networks and reinforcement learning
M. J. Dreyfus-León
Ecological Modelling  120  287--297  (1999)
Predictive models of collembolan diversity and abundance in a riparian habitat
S. Lek-Ang and L. Deharveng and S. Lek
Ecological Modelling  120  247--260  (1999)
Prediction of response of zooplankton biomass to climatic and oceanic changes
I. Aoki and T. Komatsu and K. Hwang
Ecological modelling  120  261--270  (1999)
Modelling water quality, bioindication and population dynamics in lotic ecosystems using neural networks
I. M. Schleiter and D. Borchardt and R. Wagner and T. Dapper and K. D. Schmidt and H. H. Schmidt and H. Werner
Ecological modelling  120  271--286  (1999)
The use of artificial neural networks to assess fish abundance and spatial occupancy in the littoral zone of a mesotrophic lake
S. Brosse and J.-F. Guegan and J.-N. Tourenq and S. Lek
Ecological Modelling  120  299--311  (1999)
{Patterns and uncertainties of species' range shifts under climate change}
W. Thuiller
Global Change Biology  10  2020--2027  (2004)
{Validation of species--climate impact models under climate change}
M. B. Araujo and R. G. Pearson and W. Thuiller and M. Erhard
Global Change Biology  11  1504--1513  (2005)
{Five (or so) challenges for species distribution modelling}
M. B. Araujo and A. Guisan
Journal of Biogeography  33  1677--1688  (2006)
{The importance of biotic interactions for modelling species distributions under climate change}
M. B. Araujo and M. Luoto
Global Ecology and Biogeography  16  743--753  (2007)
{Ensemble forecasting of species distributions.}
M. B. Araujo and M. New
Trends in ecology \& evolution  22  42--7  (2007)
Introduction to Kohonen's Self-Organizing Maps
F. Bacão and V. Lobo
Characterization of biological responses under different environmental conditions: A hierarchical modeling approach
D. Bedoya and E. S. Manolakos and V. Novotny
Ecological Modelling  222  532--545  (2011)
Utilisation of non-supervised neural networks and principal component analysis to study fish assemblages
S. Brosse and J. Giraudel and S. Lek
Ecological Modelling  146  159--166  (2001)
Vulnerability Of Alpine Stream Biodiversity To Shrinking Glaciers And Snowpacks
L. E. Brown and D. M. Hannah and A. M. Milner
Global Change Biology  13  958--966  (2007)
Model selection and multimodel inference: a practical information-theoretic approach
K. P. Burnham and D. R. Anderson
{The R book}
M. J. Crawley
{Novel methods improve prediction of species' distributions from occurrence data}
J. Elith and C. H. Graham* and R. P. Anderson and M. Dudik and S. Ferrier and A. Guisan and R. J. Hijmans and F. Huettmann and J. R. Leathwick and A. Lehmann and Others
Ecography  29  129--151  (2006)
{Do they? How do they? WHY do they differ? On finding reasons for differing performances of species distribution models}
J. Elith and C. H. Graham
Ecography  32  66--77  (2009)
{The art of modelling range-shifting species}
J. Elith and M. Kearney and S. Phillips
Methods in Ecology and Evolution  1  330--342  (2010)
{Species distribution models: ecological explanation and prediction across space and time}
J. Elith and J. R. Leathwick
Annual Review of Ecology, Evolution, and Systematics  40  677--697  (2009)
{A statistical explanation of MaxEnt for ecologists}
J. Elith and S. J. Phillips and T. Hastie and M. Dud\ik and Y. E. Chee and C. J. Yates
Diversity and Distributions  17  43--57  (2011)
{Linear models with R}
J. J. Faraway
  63    (2005)
Predicting habitat suitability with machine learning models: the potential area of Pinus sylvestris L. in the Iberian Peninsula
M. B. Garzon and R. Blazek and M. Neteler and R. S. Dios and H. S. Ollero and C. Furlanello
ecological modelling  197  383--393  (2006)
Stream hydrology: an introduction for ecologists
N. D. Gordon
Macroinvertebrate instream flow studies after 20 years: a role in stream management and restoration
J. A. Gore and J. B. Layzer and J. Mead
Regulated Rivers: Research \& Management  17  527--542  (2001)
{Generalized linear and generalized additive models in studies of species distributions : setting the scene}
A. Guisan and T. C. Edwards and T. Hastie
Ecological Modelling  157    (2002)
{Making better biogeographical predictions of species' distributions}
A. Guisan and A. Lehmann and S. Ferrier and M. Austin and J. M. C. Overton and R. Aspinall and T. Hastie
Journal of Applied Ecology  43  386--392  (2006)
{Predicting species distribution: offering more than simple habitat models}
A. Guisan and W. Thuiller
Ecology Letters  8  993--1009  (2005)
{Predictive habitat distribution models in ecology}
A. Guisan and N. E. Zimmermann
Ecological modelling  135  147--186  (2000)
{What Matters For Predicting The Occurrences Of Trees: Techniques, Data, Or Species'characteristics?}
A. Guisan and N. E. Zimmermann and J. Elith and C. H. Graham and S. Phillips and A. T. Peterson
Ecological Monographs  77  615--630  (2007)
{Elements of Statistical Learning: Data Mining, Inference and Prediction}
T. Hastie and R. Tibshirani and J. Friedman
{Species distribution modeling with R}
R. J. Hijmans and J. Elith
Using Self-Organizing Maps to explore patterns in species richness and protection
M. E. Hopton and A. L. Mayer
Biodiversity and Conservation  15  4477--4494  (2006)
{Ecology and Conservation of freshwater gastropods in the Upper Rh\^{o}ne oodplain , with special emphasis on the threatened par}
D. Hug Peter
Stream modification patterns in a river basin: Field survey and self-organizing map (SOM) application
K. S. Jeong and D. G. Hong and M. S. Byeon and J. C. Jeong and H. G. Kim and D. K. Kim and G. J. Joo
Ecological Informatics  5  293--303  (2010)
Hydraulic constraints on habitat suitability for benthic invertebrates in gravel-bed rivers
I. Jowett
River Research and Applications  19  495--507  (2003)
Review of the self-organizing map (SOM) approach in water resources: Analysis, modelling and application
A. M. Kalteh and P. Hjorth and R. Berndtsson
Environmental Modelling \& Software  23  835--845  (2008)
{Self-organizing maps}
T. Kohonen
  21    (2001)
Patterning the distribution of threatened crayfish and their exotic analogues using self-organizing maps
D. Kopp and F. Santoul and N. Poulet and A. Compin and R. Céréghino
Environmental Conservation  37  147--154  (2010)
Generalized instream habitat models
N. Lamouroux and I. G. Jowett
Canadian Journal of Fisheries and Aquatic Sciences  62  7--14  (2005)
Use of generalised dissimilarity modelling to improve the biological discrimination of river and stream classifications
J. Leathwick and T. Snelder and W. Chadderton and J. Elith and K. Julian and S. Ferrier
Freshwater Biology  56  21--38  (2011)
Modelling community structure in freshwater ecosystems
S. Lek
  1    (2005)
Artificial neural networks as a tool in ecological modelling, an introduction
S. Lek and J. F. Guégan
Ecological modelling  120  65--73  (1999)
A comparison of SOM neural network and hierarchical clustering methods
P. Mangiameli and S. K. Chen and D. West
European Journal of Operational Research  93  402--417  (1996)
Trends of macroinvertebrate community structure in glacier-fed rivers in relation to environmental conditions: a synthesis
A. M. Milner and J. E. Brittain and E. Castella and G. E. Petts
Freshwater Biology  46  1833--1847  (2001)
Hydroecological response of river systems to shrinking glaciers
A. M. Milner and L. E. Brown and D. M. Hannah
Hydrological Processes  23  62--77  (2009)
{Using Self-Organizing Maps To Define The Types Of Swiss Ponds By Abiotic Variables And Macrophytes Communities}
L. Sager
Self-organizing mapping of benthic macroinvertebrate communities implemented to community assessment and water quality evaluation
M. Y. Song and H. J. Hwang and I. S. Kwak and C. W. Ji and Y. N. Oh and B. J. Youn and T. S. Chon
ecological modelling  203  18--25  (2007)
{Patterns and uncertainties of species' range shifts under climate change}
W. Thuiller
Global Change Biology  10  2020--2027  (2004)
{BIOMOD -- optimizing predictions of species distributions and projecting potential future shifts under global change}
W. Thuiller
Global Change Biology    1353--1362  (2003)
{Generalized models vs. classification tree analysis: Predicting spatial distributions of plant species at different scales}
W. Thuiller and M. B. Araujo and S. Lavorel
Journal of Vegetation Science  14  669  (2003)
{Effects of restricting environmental range of data to project current and future species distributions}
W. Thuiller and L. Brotons
Ecography  2    (2004)
Typology of diatom communities and the influence of hydro-ecoregions: A study on the French hydrosystem scale
J. Tison and Y. S. Park and M. Coste and J. Wasson and L. Ector and F. Rimet and F. Delmas
Water research  39  3177--3188  (2005)
Self-and super-organizing maps in R: the Kohonen package
R. Wehrens and L. M. C. Buydens
Journal of Statistical Software  21  19  (2007)
{A beginner's Guide to R}
A. F. Zuur and E. N. Ieno and E. H. H. G. Meesters
    219  (2009)
{Analysing ecological data}
A. F. Zuur and E. N. Ieno and G. M. Smith
    672  (2007)
{Mixed Effects Models and Extensions in Ecology with R.}
A. F. Zuur and E. N. Ieno and N. J. Walker and A. A. Saveliev and G. M. Smith
    574  (2009)