Provides tools for semantic segmentation of geospatial data using convolutional neural
network-based deep learning. Utility functions allow for creating masks, image chips, data frames listing image
chips in a directory, and DataSets for use within DataLoaders. Additional functions are provided to serve as checks
during the data preparation and training process. A UNet architecture can be defined with 4 blocks in the encoder, a
bottleneck block, and 4 blocks in the decoder. The UNet can accept a variable number of input channels, and the user
can define the number of feature maps produced in each encoder and decoder block and the bottleneck. Users can also
choose to (1) replace all rectified linear unit (ReLU) activation functions with leaky ReLU or swish, (2) implement attention gates along the
skip connections, (3) implement squeeze and excitation modules within the encoder blocks, (4) add residual connections
within all blocks, (5) replace the bottleneck with a modified atrous spatial pyramid pooling (ASPP) module, and/or
(6) implement deep supervision using predictions generated at each stage in the decoder. A unified focal loss framework is implemented after
Yeung et al. (2022)

geodl provides tools for geospatial semantic segmentation using convolutional neural network-based deep learning, built on torch and terra. It includes several configurable UNet-family model architectures, utilities for preparing and augmenting image chips, loss functions and training metrics for use with luz, and functions for generating spatial predictions and assessing accuracy. Models can be trained using a CUDA-enabled GPU and do not require a Python environment.
Full details are described in:
Maxwell, A.E., Farhadpour, S., Das, S. and Yang, Y., 2024. geodl: An R package for geospatial deep learning semantic segmentation using torch and terra. PLoS One, 19(12), p.e0315127. https://doi.org/10.1371/journal.pone.0315127
You can install the development version of geodl from GitHub with:
# install.packages("devtools")
devtools::install_github("maxwell-geospatial/geodl")
Full documentation, including a function reference, is available at the pkgdown website.
Chapters 22, 23, 24, and 25 of the free and openly available online text Geospatial Supervised Learning using R provide detailed workflows and explanations.