model_opt_r.Rd 1.68 KB
Newer Older
1
2
3
4
5
6
7
8
9
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/model_opt.r
\name{model_opt_r}
\alias{model_opt_r}
\title{Perform Habitat Sampling and Probability Mapping}
\usage{
model_opt_r(
  k,
  raster,
10
  col_names,
11
12
13
14
15
16
17
18
19
  sample_type,
  buffer,
  model,
  seed,
  n,
  sample_size,
  n_channel,
  seed2,
  mtry,
Daniela Rabe's avatar
Daniela Rabe committed
20
  mod.error,
21
22
23
24
25
26
27
28
29
  pbtn1,
  max_samples_per_class
)
}
\arguments{
\item{k}{Iteration value for the models.}

\item{raster}{satellite time series stack (rasterBrickObject) or just any type of image (*rasterObject)}

30
31
\item{col_names}{layer names}

32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
\item{sample_type}{distribution of spatial locations c("random","regular")}

\item{buffer}{distance (in m) for new sample collection around initial samples (depends on pixel size)}

\item{model}{which machine learning classifier to use c("rf", "svm") for random forest or support vector machine implementation}

\item{seed}{set seed for reproducible results}

\item{n}{number of iterations for model accuracy}

\item{sample_size}{number of spatial locations}

\item{n_channel}{number of channels}

\item{seed2}{spatial points sample}

\item{mtry}{number of predictor used at random forest splitting nodes (mtry << n predictors)}

Daniela Rabe's avatar
Daniela Rabe committed
50
\item{mod.error}{threshold for model error until which iteration is being executed}
51

Daniela Rabe's avatar
Daniela Rabe committed
52
\item{pbtn1}{matrix for points}
53
54
55
56
57
58
59
60

\item{max_samples_per_class}{maximum number of samples per class}
}
\value{
a list with 4 elements:
\enumerate{
\item k To identify the used model \cr
\item model The model - mmax \cr
61
\item points List of points used part of the sample. \cr
62
63
64
65
66
67
68
\item oobe The accuracy achieved by the model \cr
}
}
\description{
This function finds the best model (mmax) for a set of sampled points.
}
\keyword{internal}