Re: [R-sig-Geo] Random forest classification combined with spatial linear model prediction

2025-02-22 Thread Manuel Spínola 
Thank you Marcelino,

I will look at the package.

Manuel


El vie, 21 feb 2025 a las 3:01, Marcelino de la Cruz Rot via R-sig-Geo (<
[email protected]>) escribió:

> Hi,
> I'm not completely sure if this is what you are asking for but just in
> case:
>
> https://blasbenito.github.io/spatialRF/
>
> Cheers, Marcelino
>
>
> El 21/02/2025 a las 9:46, Edzer Pebesma escribió:
> > I'm not entirely sure what you mean by spatial linear model, but it
> > may be worth looking into
> > https://cran.r-project.org/web/packages/RandomForestsGLS/index.html
> >
> > The paper referenced in there,
> > https://doi.org/10.1080/01621459.2021.1950003 , is worth reading!
> >
> > On 20/02/2025 22:50, Manuel Spínola wrote:
> >> Thank you Ben,
> >>
> >> I know tidysdm, and it’s a great package, but I don’t think it
> >> accounts for
> >> spatial structure in the way I expect—though I could be wrong. It
> >> does use
> >> spatial_block_cv, which likely considers the spatial component.
> >>
> >> It is my understanding that sprflm from the spmodel package applies
> >> kriging
> >> to the residuals.
> >>
> >>
> >> Manuel
> >>
> >>
> >>
> >>
> >> El jue, 20 feb 2025 a las 15:20, Ben Tupper ()
> >> escribió:
> >>
> >>> Hi,
> >>>
> >>> I'm not sure I fully understand what you are asking for, but are
> >>> describing something like tidysdm
> >>> ?
> >>>
> >>> Cheers,
> >>> Ben
> >>>
> >>> On Thu, Feb 20, 2025 at 3:16 PM Manuel Spínola 
> >>> wrote:
> >>>
>  Dear list members,
> 
>  Is there any R package that combines random forest classification and
>  spatial linear model prediction?
> 
>  The spmodel can fit this type of model but only for random forest
>  regression according to the help document.
> 
>  My goal is to work with species distribution modelling with random
>  forest
>  but includes the spatial structure of the data.
> 
>  Manuel
> 
> 
>  --
>  *Manuel Spínola, Ph.D.*
>  Instituto Internacional en Conservación y Manejo de Vida Silvestre
>  Universidad Nacional
>  Apartado 1350-3000
>  Heredia
>  COSTA RICA
>  [email protected] 
>  [email protected]
>  Teléfono: (506) 8706 - 4662
>  Sitio web institucional: ICOMVIS
>  
>  Sitio web personal: Sitio personal
>   >
>  Blog sobre Ciencia de Datos: Blog de Ciencia de Datos
>  
> 
>   [[alternative HTML version deleted]]
> 
>  ___
>  R-sig-Geo mailing list
>  [email protected]
>  https://stat.ethz.ch/mailman/listinfo/r-sig-geo
> 
> >>>
> >>
> >
>
> --
> Marcelino de la Cruz Rot
> Coordinador funcional de Biología
> Instituto de Investigación en Cambio Global (IICG-URJC)
> Dpto. Biología y Geología, Física y Química Inorgánica
> Universidad Rey Juan Carlos (URJC)
> C. Tulipán, s/n, 28933 Móstoles, Madrid
>
> ___
> R-sig-Geo mailing list
> [email protected]
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>


-- 
*Manuel Spínola, Ph.D.*
Instituto Internacional en Conservación y Manejo de Vida Silvestre
Universidad Nacional
Apartado 1350-3000
Heredia
COSTA RICA
[email protected] 
[email protected]
Teléfono: (506) 8706 - 4662
Sitio web institucional: ICOMVIS

Sitio web personal: Sitio personal 
Blog sobre Ciencia de Datos: Blog de Ciencia de Datos


[[alternative HTML version deleted]]

___
R-sig-Geo mailing list
[email protected]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo

Re: [R-sig-Geo] Random forest classification combined with spatial linear model prediction

2025-02-22 Thread Manuel Spínola 
Thank you Marcelino,

I will look at the package.

Manuel


El vie, 21 feb 2025 a las 3:01, Marcelino de la Cruz Rot via R-sig-Geo (<
[email protected]>) escribió:

> Hi,
> I'm not completely sure if this is what you are asking for but just in
> case:
>
> https://blasbenito.github.io/spatialRF/
>
> Cheers, Marcelino
>
>
> El 21/02/2025 a las 9:46, Edzer Pebesma escribió:
> > I'm not entirely sure what you mean by spatial linear model, but it
> > may be worth looking into
> > https://cran.r-project.org/web/packages/RandomForestsGLS/index.html
> >
> > The paper referenced in there,
> > https://doi.org/10.1080/01621459.2021.1950003 , is worth reading!
> >
> > On 20/02/2025 22:50, Manuel Spínola wrote:
> >> Thank you Ben,
> >>
> >> I know tidysdm, and it’s a great package, but I don’t think it
> >> accounts for
> >> spatial structure in the way I expect—though I could be wrong. It
> >> does use
> >> spatial_block_cv, which likely considers the spatial component.
> >>
> >> It is my understanding that sprflm from the spmodel package applies
> >> kriging
> >> to the residuals.
> >>
> >>
> >> Manuel
> >>
> >>
> >>
> >>
> >> El jue, 20 feb 2025 a las 15:20, Ben Tupper ()
> >> escribió:
> >>
> >>> Hi,
> >>>
> >>> I'm not sure I fully understand what you are asking for, but are
> >>> describing something like tidysdm
> >>> ?
> >>>
> >>> Cheers,
> >>> Ben
> >>>
> >>> On Thu, Feb 20, 2025 at 3:16 PM Manuel Spínola 
> >>> wrote:
> >>>
>  Dear list members,
> 
>  Is there any R package that combines random forest classification and
>  spatial linear model prediction?
> 
>  The spmodel can fit this type of model but only for random forest
>  regression according to the help document.
> 
>  My goal is to work with species distribution modelling with random
>  forest
>  but includes the spatial structure of the data.
> 
>  Manuel
> 
> 
>  --
>  *Manuel Spínola, Ph.D.*
>  Instituto Internacional en Conservación y Manejo de Vida Silvestre
>  Universidad Nacional
>  Apartado 1350-3000
>  Heredia
>  COSTA RICA
>  [email protected] 
>  [email protected]
>  Teléfono: (506) 8706 - 4662
>  Sitio web institucional: ICOMVIS
>  
>  Sitio web personal: Sitio personal
>   >
>  Blog sobre Ciencia de Datos: Blog de Ciencia de Datos
>  
> 
>   [[alternative HTML version deleted]]
> 
>  ___
>  R-sig-Geo mailing list
>  [email protected]
>  https://stat.ethz.ch/mailman/listinfo/r-sig-geo
> 
> >>>
> >>
> >
>
> --
> Marcelino de la Cruz Rot
> Coordinador funcional de Biología
> Instituto de Investigación en Cambio Global (IICG-URJC)
> Dpto. Biología y Geología, Física y Química Inorgánica
> Universidad Rey Juan Carlos (URJC)
> C. Tulipán, s/n, 28933 Móstoles, Madrid
>
> ___
> R-sig-Geo mailing list
> [email protected]
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>


-- 
*Manuel Spínola, Ph.D.*
Instituto Internacional en Conservación y Manejo de Vida Silvestre
Universidad Nacional
Apartado 1350-3000
Heredia
COSTA RICA
[email protected] 
[email protected]
Teléfono: (506) 8706 - 4662
Sitio web institucional: ICOMVIS

Sitio web personal: Sitio personal 
Blog sobre Ciencia de Datos: Blog de Ciencia de Datos


[[alternative HTML version deleted]]

___
R-sig-Geo mailing list
[email protected]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo

Re: [R-sig-Geo] Random forest classification combined with spatial linear model prediction

2025-02-22 Thread Manuel Spínola 
Thank you Marcelino,

I will look at the package.

Manuel


El vie, 21 feb 2025 a las 3:01, Marcelino de la Cruz Rot via R-sig-Geo (<
[email protected]>) escribió:

> Hi,
> I'm not completely sure if this is what you are asking for but just in
> case:
>
> https://blasbenito.github.io/spatialRF/
>
> Cheers, Marcelino
>
>
> El 21/02/2025 a las 9:46, Edzer Pebesma escribió:
> > I'm not entirely sure what you mean by spatial linear model, but it
> > may be worth looking into
> > https://cran.r-project.org/web/packages/RandomForestsGLS/index.html
> >
> > The paper referenced in there,
> > https://doi.org/10.1080/01621459.2021.1950003 , is worth reading!
> >
> > On 20/02/2025 22:50, Manuel Spínola wrote:
> >> Thank you Ben,
> >>
> >> I know tidysdm, and it’s a great package, but I don’t think it
> >> accounts for
> >> spatial structure in the way I expect—though I could be wrong. It
> >> does use
> >> spatial_block_cv, which likely considers the spatial component.
> >>
> >> It is my understanding that sprflm from the spmodel package applies
> >> kriging
> >> to the residuals.
> >>
> >>
> >> Manuel
> >>
> >>
> >>
> >>
> >> El jue, 20 feb 2025 a las 15:20, Ben Tupper ()
> >> escribió:
> >>
> >>> Hi,
> >>>
> >>> I'm not sure I fully understand what you are asking for, but are
> >>> describing something like tidysdm
> >>> ?
> >>>
> >>> Cheers,
> >>> Ben
> >>>
> >>> On Thu, Feb 20, 2025 at 3:16 PM Manuel Spínola 
> >>> wrote:
> >>>
>  Dear list members,
> 
>  Is there any R package that combines random forest classification and
>  spatial linear model prediction?
> 
>  The spmodel can fit this type of model but only for random forest
>  regression according to the help document.
> 
>  My goal is to work with species distribution modelling with random
>  forest
>  but includes the spatial structure of the data.
> 
>  Manuel
> 
> 
>  --
>  *Manuel Spínola, Ph.D.*
>  Instituto Internacional en Conservación y Manejo de Vida Silvestre
>  Universidad Nacional
>  Apartado 1350-3000
>  Heredia
>  COSTA RICA
>  [email protected] 
>  [email protected]
>  Teléfono: (506) 8706 - 4662
>  Sitio web institucional: ICOMVIS
>  
>  Sitio web personal: Sitio personal
>   >
>  Blog sobre Ciencia de Datos: Blog de Ciencia de Datos
>  
> 
>   [[alternative HTML version deleted]]
> 
>  ___
>  R-sig-Geo mailing list
>  [email protected]
>  https://stat.ethz.ch/mailman/listinfo/r-sig-geo
> 
> >>>
> >>
> >
>
> --
> Marcelino de la Cruz Rot
> Coordinador funcional de Biología
> Instituto de Investigación en Cambio Global (IICG-URJC)
> Dpto. Biología y Geología, Física y Química Inorgánica
> Universidad Rey Juan Carlos (URJC)
> C. Tulipán, s/n, 28933 Móstoles, Madrid
>
> ___
> R-sig-Geo mailing list
> [email protected]
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>


-- 
*Manuel Spínola, Ph.D.*
Instituto Internacional en Conservación y Manejo de Vida Silvestre
Universidad Nacional
Apartado 1350-3000
Heredia
COSTA RICA
[email protected] 
[email protected]
Teléfono: (506) 8706 - 4662
Sitio web institucional: ICOMVIS

Sitio web personal: Sitio personal 
Blog sobre Ciencia de Datos: Blog de Ciencia de Datos


[[alternative HTML version deleted]]

___
R-sig-Geo mailing list
[email protected]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo

Re: [R-sig-Geo] Random forest classification combined with spatial linear model prediction

2025-02-21 Thread Manuel Spínola 
Thank you Edzer,

I will take a look at the package.

Manuel

El vie, 21 feb 2025 a las 2:46, Edzer Pebesma (<
[email protected]>) escribió:

> I'm not entirely sure what you mean by spatial linear model, but it may
> be worth looking into
> https://cran.r-project.org/web/packages/RandomForestsGLS/index.html
>
> The paper referenced in there,
> https://doi.org/10.1080/01621459.2021.1950003 , is worth reading!
>
> On 20/02/2025 22:50, Manuel Spínola wrote:
> > Thank you Ben,
> >
> > I know tidysdm, and it’s a great package, but I don’t think it accounts
> for
> > spatial structure in the way I expect—though I could be wrong. It does
> use
> > spatial_block_cv, which likely considers the spatial component.
> >
> > It is my understanding that sprflm from the spmodel package applies
> kriging
> > to the residuals.
> >
> >
> > Manuel
> >
> >
> >
> >
> > El jue, 20 feb 2025 a las 15:20, Ben Tupper ()
> > escribió:
> >
> >> Hi,
> >>
> >> I'm not sure I fully understand what you are asking for, but are
> >> describing something like tidysdm
> >> ?
> >>
> >> Cheers,
> >> Ben
> >>
> >> On Thu, Feb 20, 2025 at 3:16 PM Manuel Spínola 
> >> wrote:
> >>
> >>> Dear list members,
> >>>
> >>> Is there any R package that combines random forest classification and
> >>> spatial linear model prediction?
> >>>
> >>> The spmodel can fit this type of model but only for random forest
> >>> regression according to the help document.
> >>>
> >>> My goal is to work with species distribution modelling with random
> forest
> >>> but includes the spatial structure of the data.
> >>>
> >>> Manuel
> >>>
> >>>
> >>> --
> >>> *Manuel Spínola, Ph.D.*
> >>> Instituto Internacional en Conservación y Manejo de Vida Silvestre
> >>> Universidad Nacional
> >>> Apartado 1350-3000
> >>> Heredia
> >>> COSTA RICA
> >>> [email protected] 
> >>> [email protected]
> >>> Teléfono: (506) 8706 - 4662
> >>> Sitio web institucional: ICOMVIS
> >>> 
> >>> Sitio web personal: Sitio personal <
> https://mspinola-sitioweb.netlify.app
> 
> >>> Blog sobre Ciencia de Datos: Blog de Ciencia de Datos
> >>> 
> >>>
> >>>  [[alternative HTML version deleted]]
> >>>
> >>> ___
> >>> R-sig-Geo mailing list
> >>> [email protected]
> >>> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
> >>>
> >>
> >
>
> --
> Edzer Pebesma (he/him)
> Universität Münster, Institute for Geoinformatics
> Heisenbergstrasse 2, 48149 Münster, Germany
> Phone: +49 251 8333081
>
>

-- 
*Manuel Spínola, Ph.D.*
Instituto Internacional en Conservación y Manejo de Vida Silvestre
Universidad Nacional
Apartado 1350-3000
Heredia
COSTA RICA
[email protected] 
[email protected]
Teléfono: (506) 8706 - 4662
Sitio web institucional: ICOMVIS

Sitio web personal: Sitio personal 
Blog sobre Ciencia de Datos: Blog de Ciencia de Datos


[[alternative HTML version deleted]]

___
R-sig-Geo mailing list
[email protected]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo

Re: [R-sig-Geo] Random forest classification combined with spatial linear model prediction

2025-02-21 Thread Marcelino de la Cruz Rot via R-sig-Geo 

Hi,
I'm not completely sure if this is what you are asking for but just in case:

https://blasbenito.github.io/spatialRF/

Cheers, Marcelino


El 21/02/2025 a las 9:46, Edzer Pebesma escribió:
I'm not entirely sure what you mean by spatial linear model, but it 
may be worth looking into 
https://cran.r-project.org/web/packages/RandomForestsGLS/index.html


The paper referenced in there, 
https://doi.org/10.1080/01621459.2021.1950003 , is worth reading!


On 20/02/2025 22:50, Manuel Spínola wrote:

Thank you Ben,

I know tidysdm, and it’s a great package, but I don’t think it 
accounts for
spatial structure in the way I expect—though I could be wrong. It 
does use

spatial_block_cv, which likely considers the spatial component.

It is my understanding that sprflm from the spmodel package applies 
kriging

to the residuals.


Manuel




El jue, 20 feb 2025 a las 15:20, Ben Tupper ()
escribió:


Hi,

I'm not sure I fully understand what you are asking for, but are
describing something like tidysdm
?

Cheers,
Ben

On Thu, Feb 20, 2025 at 3:16 PM Manuel Spínola 
wrote:


Dear list members,

Is there any R package that combines random forest classification and
spatial linear model prediction?

The spmodel can fit this type of model but only for random forest
regression according to the help document.

My goal is to work with species distribution modelling with random 
forest

but includes the spatial structure of the data.

Manuel


--
*Manuel Spínola, Ph.D.*
Instituto Internacional en Conservación y Manejo de Vida Silvestre
Universidad Nacional
Apartado 1350-3000
Heredia
COSTA RICA
[email protected] 
[email protected]
Teléfono: (506) 8706 - 4662
Sitio web institucional: ICOMVIS

Sitio web personal: Sitio personal 


 [[alternative HTML version deleted]]

___
R-sig-Geo mailing list
[email protected]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo









--
Marcelino de la Cruz Rot
Coordinador funcional de Biología
Instituto de Investigación en Cambio Global (IICG-URJC)
Dpto. Biología y Geología, Física y Química Inorgánica
Universidad Rey Juan Carlos (URJC)
C. Tulipán, s/n, 28933 Móstoles, Madrid

___
R-sig-Geo mailing list
[email protected]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo

Re: [R-sig-Geo] Random forest classification combined with spatial linear model prediction

2025-02-21 Thread Edzer Pebesma 
I'm not entirely sure what you mean by spatial linear model, but it may 
be worth looking into 
https://cran.r-project.org/web/packages/RandomForestsGLS/index.html


The paper referenced in there, 
https://doi.org/10.1080/01621459.2021.1950003 , is worth reading!


On 20/02/2025 22:50, Manuel Spínola wrote:

Thank you Ben,

I know tidysdm, and it’s a great package, but I don’t think it accounts for
spatial structure in the way I expect—though I could be wrong. It does use
spatial_block_cv, which likely considers the spatial component.

It is my understanding that sprflm from the spmodel package applies kriging
to the residuals.


Manuel




El jue, 20 feb 2025 a las 15:20, Ben Tupper ()
escribió:


Hi,

I'm not sure I fully understand what you are asking for, but are
describing something like tidysdm
?

Cheers,
Ben

On Thu, Feb 20, 2025 at 3:16 PM Manuel Spínola 
wrote:


Dear list members,

Is there any R package that combines random forest classification and
spatial linear model prediction?

The spmodel can fit this type of model but only for random forest
regression according to the help document.

My goal is to work with species distribution modelling with random forest
but includes the spatial structure of the data.

Manuel


--
*Manuel Spínola, Ph.D.*
Instituto Internacional en Conservación y Manejo de Vida Silvestre
Universidad Nacional
Apartado 1350-3000
Heredia
COSTA RICA
[email protected] 
[email protected]
Teléfono: (506) 8706 - 4662
Sitio web institucional: ICOMVIS

Sitio web personal: Sitio personal 

 [[alternative HTML version deleted]]

___
R-sig-Geo mailing list
[email protected]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo







--
Edzer Pebesma (he/him)
Universität Münster, Institute for Geoinformatics
Heisenbergstrasse 2, 48149 Münster, Germany
Phone: +49 251 8333081

___
R-sig-Geo mailing list
[email protected]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo

Re: [R-sig-Geo] Random forest classification combined with spatial linear model prediction

2025-02-20 Thread Manuel Spínola 
Thank you Ben,

I know tidysdm, and it’s a great package, but I don’t think it accounts for
spatial structure in the way I expect—though I could be wrong. It does use
spatial_block_cv, which likely considers the spatial component.

It is my understanding that sprflm from the spmodel package applies kriging
to the residuals.


Manuel




El jue, 20 feb 2025 a las 15:20, Ben Tupper ()
escribió:

> Hi,
>
> I'm not sure I fully understand what you are asking for, but are
> describing something like tidysdm
> ?
>
> Cheers,
> Ben
>
> On Thu, Feb 20, 2025 at 3:16 PM Manuel Spínola 
> wrote:
>
>> Dear list members,
>>
>> Is there any R package that combines random forest classification and
>> spatial linear model prediction?
>>
>> The spmodel can fit this type of model but only for random forest
>> regression according to the help document.
>>
>> My goal is to work with species distribution modelling with random forest
>> but includes the spatial structure of the data.
>>
>> Manuel
>>
>>
>> --
>> *Manuel Spínola, Ph.D.*
>> Instituto Internacional en Conservación y Manejo de Vida Silvestre
>> Universidad Nacional
>> Apartado 1350-3000
>> Heredia
>> COSTA RICA
>> [email protected] 
>> [email protected]
>> Teléfono: (506) 8706 - 4662
>> Sitio web institucional: ICOMVIS
>> 
>> Sitio web personal: Sitio personal > >
>> Blog sobre Ciencia de Datos: Blog de Ciencia de Datos
>> 
>>
>> [[alternative HTML version deleted]]
>>
>> ___
>> R-sig-Geo mailing list
>> [email protected]
>> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>>
>

-- 
*Manuel Spínola, Ph.D.*
Instituto Internacional en Conservación y Manejo de Vida Silvestre
Universidad Nacional
Apartado 1350-3000
Heredia
COSTA RICA
[email protected] 
[email protected]
Teléfono: (506) 8706 - 4662
Sitio web institucional: ICOMVIS

Sitio web personal: Sitio personal 
Blog sobre Ciencia de Datos: Blog de Ciencia de Datos


[[alternative HTML version deleted]]

___
R-sig-Geo mailing list
[email protected]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo

Re: [R-sig-Geo] Random forest classification combined with spatial linear model prediction

2025-02-20 Thread Ben Tupper via R-sig-Geo 
Hi,

I'm not sure I fully understand what you are asking for, but are describing
something like tidysdm ?

Cheers,
Ben

On Thu, Feb 20, 2025 at 3:16 PM Manuel Spínola  wrote:

> Dear list members,
>
> Is there any R package that combines random forest classification and
> spatial linear model prediction?
>
> The spmodel can fit this type of model but only for random forest
> regression according to the help document.
>
> My goal is to work with species distribution modelling with random forest
> but includes the spatial structure of the data.
>
> Manuel
>
>
> --
> *Manuel Spínola, Ph.D.*
> Instituto Internacional en Conservación y Manejo de Vida Silvestre
> Universidad Nacional
> Apartado 1350-3000
> Heredia
> COSTA RICA
> [email protected] 
> [email protected]
> Teléfono: (506) 8706 - 4662
> Sitio web institucional: ICOMVIS
> 
> Sitio web personal: Sitio personal 
> Blog sobre Ciencia de Datos: Blog de Ciencia de Datos
> 
>
> [[alternative HTML version deleted]]
>
> ___
> R-sig-Geo mailing list
> [email protected]
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>

[[alternative HTML version deleted]]

___
R-sig-Geo mailing list
[email protected]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo