Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Include a new function for detecting changes #1099

Open
gilbertocamara opened this issue Mar 27, 2024 · 0 comments
Open

Include a new function for detecting changes #1099

gilbertocamara opened this issue Mar 27, 2024 · 0 comments
Assignees
Milestone

Comments

@gilbertocamara
Copy link
Contributor

Describe the new API function requested
Time series analysis has problems that are not related to classification but to change detection. They involve the identification of breaks and discontinuities in image time series, using algorithms such as BFAST and CCDC to find places where there is a change in signal. One example is the detection of real-time deforestation alerts used in the DETER system by INPE. In such cases, we need a function which can compare subsets of a longer time series with a short time series that contains a pattern of change.

Algorithms such as TWDTW and RADD are better suited to such tasks than ML/DL classifiers such as RF and TempCNN. Therefore, we need a different API.

Associated sits API function

#' @title Detect changes in time series
#' @name sits_detect_change
#' @description Given a set of time series or an image, this function compares each time series
#'                         with a set of change/no-change patterns, and indicates places and dates where
#'                          change has been detected
#' @param data         Set of time series 
#' @param  cd_ method        Change detection method (with parameters)
#' @return                  Set of time series where significant change has been detected
#'  @export
sits_detect_change <- function(
            data,
            cd_method = sits_twdtw(...)
}
                  

*** Context
Each cd_method function will have methods that have to be parametrised differently. The assumption is that few pixels will represent change and this the output will be a set of time series, with additional predicted column.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

2 participants