[R-sig-eco] Do You Have Anything Against Using ISO DATA?

2021-01-24 Thread Skipton Woolley 
Hi Alexandre,


If you are interested in model-based bioregionalisation there are several 
attractive options

available in R. With colleagues, I have been trying to develop and implement 
model-based

bioregionalisation to maintain species information and uncertainty throughout 
the modelling

process.


Here are a few papers which might be of interest to you.

Model-based bioregionalisation perspective piece:

https://academic.oup.com/bioscience/article/70/1/48/5670754?login=true

Comparison of model-based methods:

https://besjournals.onlinelibrary.wiley.com/doi/abs/10./2041-210X.13447

Vegetation classification (bioregionalisation) using Regions of Common Profiles.

https://onlinelibrary.wiley.com/doi/abs/10./jbi.13088

[https://onlinelibrary.wiley.com/cms/asset/2bdffdcb-f397-4884-a522-117552992254/jbi.2017.44.issue-12.cover.gif]
Simultaneous vegetation classification and mapping at large spatial 
scales
Aim Multivariate mixture models offer the ability to streamline the typically 
multi�\stage process of vegetation classification and mapping into a single, 
simultaneous analytical step. Our aim is to ...
onlinelibrary.wiley.com



[https://besjournals.onlinelibrary.wiley.com/cms/asset/660a90cf-3de4-44bc-aac9-6b796528810d/mee3.v11.10.cover.gif]
Determining marine bioregions: A comparison of quantitative approaches - Hill - 
2020 - Methods in Ecology and Evolution - Wiley Online 
Library
Areas that contain ecologically distinct biological content, called bioregions, 
are a central component to spatial and ecosystem�\based management. We review 
and describe a variety of commonly used...
besjournals.onlinelibrary.wiley.com
There is code available for the second paper here:
https://github.com/Hillna-IMAS/Bioregion_Methods/tree/v1.1

The RCP approach can be implemented using the RCPmod package (on cran) or the 
updated ecomix package https://github.com/skiptoniam/ecomix which is still in 
development - but should be on cran soon.
ecomix has all the functionality of RCPmod, but with some additional functions 
to make interpretation of these models a little easier.

Anyway, I hope your bioregionalisation work goes well. I'd be happy to help 
with ecomix related questions if you decide to apply such methods.

Cheers,

Skip.




Dear R-Sig Colleagues,


I am performing a bioregionalization of the Cerrado woody flora in central

Brazil.


I am following the steps


Produce a dissimilarity matrix from species x site matrix

Perform a NMDS on the dissimilarity matrix

Interpolate each NMDS axis with Kriging

Partition the stacked interpolated rasters with K-means


I am willing to change the k-means by the ISO DATA method implemented in

ArcGis, which takes an initial number of groups (the same used for the

k-means classification). The ISODATA algorithm has some further refinements

by splitting and merging of clusters. Clusters are merged if either the

number of members (pixel) in a cluster is less than a certain threshold or

if the centers of two clusters are closer than a certain threshold.

Clusters are split into two different clusters if the cluster standard

deviation exceeds a predefined value and the number of members (pixels) is

twice the threshold for the minimum number of members. It implements a set

of rule-of-thumb procedures that have been incorporated into an iterative

classification algorithm. Many of the steps used in the algorithm are based

on the experience obtained through experimentation. The ISODATA algorithm

is a modification of the k-means clustering algorithm and is supposed to

overcome the disadvantages of k-means.


The classification produced preserved the main patterns found in kmeans

while reducing the number of groups.


However, I have not found anything in the literature of bioregionalization

using ISO DATA, only kmeans. Do you know of any reasons I should not use

ISO DATA for this aim?


Thank you very much in advance for any inputs,


Best,


Alexandre


--

Dr. Alexandre F. Souza

Professor Associado

Chefe do Departamento de Ecologia

Universidade Federal do Rio Grande do Norte

CB, Departamento de Ecologia

Campus Universit��rio - Lagoa Nova

59072-970 - Natal, RN - Brasil

lattes: lattes.cnpq.br/7844758818522706

http://www.esferacientifica.com.br

https://www.youtube.com/user/alexfadigas

http://www.docente.ufrn.br/alexsouza

orcid.org/-0001-7468-3631 
>


Dr. Skipton Woolley
IMAS, University of Tasmania.
Ph: 0419 990

[R-sig-eco] Do You Have Anything Against Using ISO DATA?

2021-01-20 Thread Alexandre F. Souza 
Dear R-Sig Colleagues,

I am performing a bioregionalization of the Cerrado woody flora in central
Brazil.

I am following the steps

Produce a dissimilarity matrix from species x site matrix
Perform a NMDS on the dissimilarity matrix
Interpolate each NMDS axis with Kriging
Partition the stacked interpolated rasters with K-means

I am willing to change the k-means by the ISO DATA method implemented in
ArcGis, which takes an initial number of groups (the same used for the
k-means classification). The ISODATA algorithm has some further refinements
by splitting and merging of clusters. Clusters are merged if either the
number of members (pixel) in a cluster is less than a certain threshold or
if the centers of two clusters are closer than a certain threshold.
Clusters are split into two different clusters if the cluster standard
deviation exceeds a predefined value and the number of members (pixels) is
twice the threshold for the minimum number of members. It implements a set
of rule-of-thumb procedures that have been incorporated into an iterative
classification algorithm. Many of the steps used in the algorithm are based
on the experience obtained through experimentation. The ISODATA algorithm
is a modification of the k-means clustering algorithm and is supposed to
overcome the disadvantages of k-means.

The classification produced preserved the main patterns found in kmeans
while reducing the number of groups.

However, I have not found anything in the literature of bioregionalization
using ISO DATA, only kmeans. Do you know of any reasons I should not use
ISO DATA for this aim?

Thank you very much in advance for any inputs,

Best,

Alexandre

-- 
Dr. Alexandre F. Souza
Professor Associado
Chefe do Departamento de Ecologia
Universidade Federal do Rio Grande do Norte
CB, Departamento de Ecologia
Campus Universitário - Lagoa Nova
59072-970 - Natal, RN - Brasil
lattes: lattes.cnpq.br/7844758818522706
http://www.esferacientifica.com.br
https://www.youtube.com/user/alexfadigas
http://www.docente.ufrn.br/alexsouza
orcid.org/-0001-7468-3631 

[[alternative HTML version deleted]]

___
R-sig-ecology mailing list
R-sig-ecology@r-project.org
https://stat.ethz.ch/mailman/listinfo/r-sig-ecology