hilandyn is an R package that provides an implementation of the
High-dimensional detection of Landscape Dynamics algorithm (Morresi et
al. 2024) for mapping forest disturbance dynamics by segmenting
high-dimensional Landsat time series into linear trends.
High-dimensional Landsat time series include information from the spatial and spectral dimensions and are analysed using a modified version of the High-dimensional Trend Segmentation (HiTS) procedure proposed by Maeng (2019). The HiTS procedure aims to detect changepoints in a piecewise linear signal where their number and location are unknown. Changes can occur in the intercept, slope or both of linear trends.
hilandyn uses the terra package for raster and vector data
management and the future package for parallel computation.
You can install the development version of hilandyn from GitHub with:
# install.packages("devtools")
devtools::install_github("donatomorresi/hilandyn")Morresi, D., Maeng, H., Marzano, R., Lingua, E., Motta, R., & Garbarino, M. (2024). High-dimensional detection of Landscape Dynamics: a Landsat time series-based algorithm for forest disturbance mapping and beyond. GIScience & Remote Sensing, 61(1), 2365001.
Maeng, H. (2019). Adaptive multiscale approaches to regression and trend segmentation. Ph.D. thesis, London School of Economics and Political Science.