.sits_class_info

Description on the data being classified.

data.tb

Samples used for training the classification model.

samples.tb

Interval between two sucessive classifications.

interval

Time series classification requires that users do a series of steps:
(a) Provide labelled samples that will be used as training data.
(b) Provide information on how the classification will be performed, including data timeline,
temporal interval, and start and end dates per interval.
(c) Clean the training data to ensure it meets the specifications of the classification info.
(d) Use the clean data to train a machine learning classifier.
(e) Classify non-labelled data sets.
In this set of steps, this function provides support for step (b). It requires the user
to provide a timeline, the classification interval, and the start and end dates of
the reference period. The results is a tibble with information that allows the user
to perform steps (c) to (e).

A set of tools for working with satellite image time series.
Supports data retrieval from a WTSS (web time series service) and other data sets.
Provides different visualisation methods for image time series.
Provides smoothing methods for noisy time series.
Enables different clustering methods, including dendrograms and SOM.
Matches noiseless patterns with noisy time series using the TWDTW method for shape recognition.
Provide machine learning methods for time series classification, including SVM, LDA, QDA, GLM, Lasso, Random Forests and Deep Learning.

Pedro Andrade

sits

Satellite Image Time Series Analysis

.sits_class_info: Define the information required for classifying time series

Description

Usage

Arguments

Value