Showing 69 of total 69 results (show query)

mikejohnson51

climateR:climateR

Find, subset, and retrive geospatial data by AOI.

Maintained by Mike Johnson. Last updated 3 months ago.

aoiclimatedatasetgeospatialgridded-climate-dataweather

5.2 match 187 stars 8.74 score 156 scripts 1 dependents

maxwell-geospatial

geodl:Geospatial Semantic Segmentation with Torch and Terra

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) <https://doi.org/10.1016/j.compmedimag.2021.102026>. We have also implemented assessment metrics using the 'luz' package including F1-score, recall, and precision. Trained models can be used to predict to spatial data without the need to generate chips from larger spatial extents. Functions are available for performing accuracy assessment. The package relies on 'torch' for implementing deep learning, which does not require the installation of a 'Python' environment. Raster geospatial data are handled with 'terra'. Models can be trained using a Compute Unified Device Architecture (CUDA)-enabled graphics processing unit (GPU); however, multi-GPU training is not supported by 'torch' in 'R'.

Maintained by Aaron Maxwell. Last updated 8 months ago.

3.5 match 12 stars 6.98 score 20 scripts

idem-lab

sdmtools:Utility tools for Species Distribution Modelling

What the package does (one paragraph).

Maintained by Gerry Ryan. Last updated 3 months ago.

3.8 match 9 stars 6.13 score 674 scripts

pik-piam

magpie4:MAgPIE outputs R package for MAgPIE version 4.x

Common output routines for extracting results from the MAgPIE framework (versions 4.x).

Maintained by Benjamin Leon Bodirsky. Last updated 2 days ago.

1.8 match 2 stars 7.87 score 254 scripts 9 dependents

rspatial

rspat:rspatial.org data -- terra version

Data to support the examples on rspatial.org

Maintained by Robert J. Hijmans. Last updated 2 years ago.

3.0 match 2 stars 2.41 score 26 scripts

dsjohnson

walk:Model Animal Movement With Continuous-Time Markov Chains

Model animal movement using continuous-time Markov chain models.

Maintained by Devin S. Johnson. Last updated 11 months ago.

openblascpp

1.7 match 2.30 score 1 scripts

stevenpawley

Rsagacmd:Linking R with the Open-Source 'SAGA-GIS' Software

Provides an R scripting interface to the open-source 'SAGA-GIS' (System for Automated Geoscientific Analyses Geographical Information System) software. 'Rsagacmd' dynamically generates R functions for every 'SAGA-GIS' geoprocessing tool based on the user's currently installed 'SAGA-GIS' version. These functions are contained within an S3 object and are accessed as a named list of libraries and tools. This structure facilitates an easier scripting experience by organizing the large number of 'SAGA-GIS' geoprocessing tools (>700) by their respective library. Interactive scripting can fully take advantage of code autocompletion tools (e.g. in 'RStudio'), allowing for each tools syntax to be quickly recognized. Furthermore, the most common types of spatial data (via the 'terra', 'sp', and 'sf' packages) along with non-spatial data are automatically passed from R to the 'SAGA-GIS' command line tool for geoprocessing operations, and the results are loaded as the appropriate R object. Outputs from individual 'SAGA-GIS' tools can also be chained using pipes from the 'magrittr' and 'dplyr' packages to combine complex geoprocessing operations together in a single statement. 'SAGA-GIS' is available under a GPLv2 / LGPLv2 licence from <https://sourceforge.net/projects/saga-gis/> including Windows x86/x64 and macOS binaries. SAGA-GIS is also included in Debian/Ubuntu default software repositories. Rsagacmd has currently been tested on 'SAGA-GIS' versions from 2.3.1 to 9.5.1 on Windows, Linux and macOS.

Maintained by Steven Pawley. Last updated 6 months ago.

0.5 match 32 stars 6.27 score 77 scripts