Package: sits 1.5.1

Gilberto Camara

sits: Satellite Image Time Series Analysis for Earth Observation Data Cubes

An end-to-end toolkit for land use and land cover classification using big Earth observation data, based on machine learning methods applied to satellite image data cubes, as described in Simoes et al (2021) <doi:10.3390/rs13132428>. Builds regular data cubes from collections in AWS, Microsoft Planetary Computer, Brazil Data Cube, Copernicus Data Space Environment (CDSE), Digital Earth Africa, Digital Earth Australia, NASA HLS using the Spatio-temporal Asset Catalog (STAC) protocol (<https://stacspec.org/>) and the 'gdalcubes' R package developed by Appel and Pebesma (2019) <doi:10.3390/data4030092>. Supports visualization methods for images and time series and smoothing filters for dealing with noisy time series. Includes functions for quality assessment of training samples using self-organized maps as presented by Santos et al (2021) <doi:10.1016/j.isprsjprs.2021.04.014>. Provides machine learning methods including support vector machines, random forests, extreme gradient boosting, multi-layer perceptrons, temporal convolutional neural networks proposed by Pelletier et al (2019) <doi:10.3390/rs11050523>, and temporal attention encoders by Garnot and Landrieu (2020) <doi:10.48550/arXiv.2007.00586>. Supports GPU processing of deep learning models using torch <https://torch.mlverse.org/>. Performs efficient classification of big Earth observation data cubes and includes functions for post-classification smoothing based on Bayesian inference, and methods for active learning and uncertainty assessment. Supports object-based time series analysis using package supercells <https://jakubnowosad.com/supercells/>. Enables best practices for estimating area and assessing accuracy of land change as recommended by Olofsson et al (2014) <doi:10.1016/j.rse.2014.02.015>. Minimum recommended requirements: 16 GB RAM and 4 CPU dual-core.

Authors:Rolf Simoes [aut], Gilberto Camara [aut, cre, ths], Felipe Souza [aut], Felipe Carlos [aut], Lorena Santos [ctb], Karine Ferreira [ctb, ths], Charlotte Pelletier [ctb], Pedro Andrade [ctb], Alber Sanchez [ctb], Gilberto Queiroz [ctb]

sits_1.5.1.tar.gz
sits_1.5.1.tar.gz(r-4.5-noble)sits_1.5.1.tar.gz(r-4.4-noble)
sits_1.5.1.tgz(r-4.4-emscripten)sits_1.5.1.tgz(r-4.3-emscripten)
sits.pdf |sits.html
sits/json (API)
NEWS

# Install 'sits' in R:
install.packages('sits', repos = c('https://cran.r-universe.dev', 'https://cloud.r-project.org'))

Peer review:

Bug tracker:https://github.com/e-sensing/sits/issues

Uses libs:
  • openblas– Optimized BLAS
  • c++– GNU Standard C++ Library v3
  • openmp– GCC OpenMP (GOMP) support library
Datasets:

2.86 score 366 scripts 514 downloads 89 exports 65 dependencies

Last updated 4 months agofrom:6f30a4b3a7. Checks:OK: 2. Indexed: no.

TargetResultDate
Doc / VignettesOKNov 18 2024
R-4.5-linux-x86_64OKNov 18 2024

Exports:impute_linearsits_accuracysits_accuracy_summarysits_add_base_cubesits_applysits_as_sfsits_bandssits_bands<-sits_bboxsits_classifysits_cleansits_cluster_cleansits_cluster_dendrosits_cluster_frequencysits_colorssits_colors_qgissits_colors_resetsits_colors_setsits_colors_showsits_combine_predictionssits_confidence_samplingsits_configsits_config_showsits_config_user_filesits_cubesits_cube_copysits_factory_functionsits_filtersits_formula_linearsits_formula_logrefsits_geo_distsits_get_datasits_imputesits_kfold_validatesits_label_classificationsits_labelssits_labels_summarysits_labels<-sits_lighttaesits_list_collectionssits_mergesits_mgrs_to_roisits_mixture_modelsits_mlpsits_model_exportsits_mosaicsits_patternssits_pred_featuressits_pred_normalizesits_pred_referencessits_pred_samplesits_predictorssits_reclassifysits_reducesits_reduce_imbalancesits_regularizesits_rforsits_run_examplessits_run_testssits_samplesits_sampling_designsits_segmentsits_selectsits_sgolaysits_show_predictionsits_slicsits_smoothsits_som_clean_samplessits_som_evaluate_clustersits_som_mapsits_som_remove_samplessits_statssits_stratified_samplingsits_svmsits_taesits_tempcnnsits_timelinesits_to_csvsits_to_xlsxsits_trainsits_tuningsits_tuning_hparamssits_uncertaintysits_uncertainty_samplingsits_validatesits_variancesits_viewsits_whittakersits_xgboost

Dependencies:askpassbitbit64callrclassclassIntclicorocpp11crayoncurlDBIdescdplyre1071ellipsisfansigdalUtilitiesgenericsgluehttrjpegjsonliteKernSmoothlifecyclelubridatemagrittrMASSmimeopensslpillarpkgconfigpngprocessxproxypspurrrR6RcppRcppArmadillorlangrstacs2safetensorssfshowtextshowtextdbsliderstringistringrsyssysfontsterratibbletidyrtidyselecttimechangetorchunitsutf8vctrswarpwithrwkyaml

Readme and manuals

Help Manual

Help pageTopics
sitssits-package sits
Change the labels of a set of time seriessits_labels<- sits_labels<-.class_cube sits_labels<-.default sits_labels<-.probs_cube sits_labels<-.sits `sits_labels<-`
Samples of classes Cerrado and Pasturecerrado_2classes
histogram of prob cubeshist.probs_cube
histogram of data cubeshist.raster_cube
Histogramhist.sits
Histogram uncertainty cubeshist.uncertainty_cube
Replace NA values with linear interpolationimpute_linear
Plot time seriesplot plot.sits
Plot classified imagesplot.class_cube
Plot Segmentsplot.class_vector_cube
Plot DEM cubesplot.dem_cube
Make a kernel density plot of samples distances.plot.geo_distances
Plot patterns that describe classesplot.patterns
Plot time series predictionsplot.predicted
Plot probability cubesplot.probs_cube
Plot probability vector cubesplot.probs_vector_cube
Plot RGB data cubesplot.raster_cube
Plot Random Forest modelplot.rfor_model
Plot SAR data cubesplot.sar_cube
Plot confusion matrixplot.sits_accuracy
Plot a dendrogram clusterplot.sits_cluster
Plot confusion between clustersplot.som_evaluate_cluster
Plot a SOM mapplot.som_map
Plot Torch (deep learning) modelplot.torch_model
Plot uncertainty cubesplot.uncertainty_cube
Plot uncertainty vector cubesplot.uncertainty_vector_cube
Plot variance cubesplot.variance_cube
Plot RGB vector data cubesplot.vector_cube
Plot XGB modelplot.xgb_model
A time series sample with data from 2000 to 2016point_mt_6bands
Samples of Amazon tropical forest biome for deforestation analysissamples_l8_rondonia_2bands
Samples of nine classes for the state of Mato Grossosamples_modis_ndvi
Assess classification accuracy (area-weighted method)sits_accuracy sits_accuracy.class_cube sits_accuracy.default sits_accuracy.derived_cube sits_accuracy.raster_cube sits_accuracy.sits sits_accuracy.tbl_df
Add base maps to a time series data cubesits_add_base_cube
Apply a function on a set of time seriessits_apply sits_apply.default sits_apply.derived_cube sits_apply.raster_cube sits_apply.sits
Return a sits_tibble or raster_cube as an sf object.sits_as_sf sits_as_sf.raster_cube sits_as_sf.sits
Get the names of the bandssits_bands sits_bands.default sits_bands.patterns sits_bands.raster_cube sits_bands.sits sits_bands.sits_model sits_bands<- sits_bands<-.default sits_bands<-.raster_cube sits_bands<-.sits
Get the bounding box of the datasits_bbox sits_bbox.default sits_bbox.raster_cube sits_bbox.sits sits_bbox.tbl_df
Classify time series or data cubessits_classify sits_classify.default sits_classify.derived_cube sits_classify.raster_cube sits_classify.segs_cube sits_classify.sits sits_classify.tbl_df
Cleans a classified map using a local windowsits_clean sits_clean.class_cube sits_clean.default sits_clean.derived_cube sits_clean.raster_cube
Removes labels that are minority in each cluster.sits_cluster_clean
Find clusters in time series samplessits_cluster_dendro sits_cluster_dendro.default sits_cluster_dendro.sits
Show label frequency in each cluster produced by dendrogram analysissits_cluster_frequency
Function to retrieve sits color tablesits_colors
Function to save color table as QML style for data cubesits_colors_qgis
Function to reset sits color tablesits_colors_reset
Function to set sits color tablesits_colors_set
Function to show colors in SITSsits_colors_show
Estimate ensemble prediction based on list of probs cubessits_combine_predictions sits_combine_predictions.average sits_combine_predictions.default sits_combine_predictions.uncertainty
Suggest high confidence samples to increase the training set.sits_confidence_sampling
Configure parameters for sits packagesits_config
Show current sits configurationsits_config_show
List the cloud collections supported by sitssits_config_user_file
Create data cubes from image collectionssits_cube sits_cube.local_cube sits_cube.sar_cube sits_cube.stac_cube
Copy the images of a cube to a local directorysits_cube_copy
Create a closure for calling functions with and without datasits_factory_function
Filter time series with smoothing filtersits_filter
Define a linear formula for classification modelssits_formula_linear
Define a loglinear formula for classification modelssits_formula_logref
Compute the minimum distances among samples and prediction points.sits_geo_dist
Get time series from data cubes and cloud servicessits_get_data sits_get_data.csv sits_get_data.data.frame sits_get_data.default sits_get_data.sf sits_get_data.shp sits_get_data.sits
Replace NA values in time series with imputation functionsits_impute
Cross-validate time series samplessits_kfold_validate
Build a labelled image from a probability cubesits_label_classification sits_label_classification.default sits_label_classification.derived_cube sits_label_classification.probs_cube sits_label_classification.probs_vector_cube sits_label_classification.raster_cube
Get labels associated to a data setsits_labels sits_labels.default sits_labels.derived_cube sits_labels.derived_vector_cube sits_labels.patterns sits_labels.raster_cube sits_labels.sits sits_labels.sits_model
Inform label distribution of a set of time seriessits_labels_summary sits_labels_summary.sits
Train a model using Lightweight Temporal Self-Attention Encodersits_lighttae
List the cloud collections supported by sitssits_list_collections
Merge two data sets (time series or cubes)sits_merge sits_merge.default sits_merge.raster_cube sits_merge.sar_cube sits_merge.sits
Convert MGRS tile information to ROI in WGS84sits_mgrs_to_roi
Multiple endmember spectral mixture analysissits_mixture_model sits_mixture_model.default sits_mixture_model.derived_cube sits_mixture_model.raster_cube sits_mixture_model.sits sits_mixture_model.tbl_df
Train multi-layer perceptron models using torchsits_mlp
Export classification modelssits_model_export sits_model_export.sits_model
Mosaic classified cubessits_mosaic
Find temporal patterns associated to a set of time seriessits_patterns
Obtain numerical values of predictors for time series samplessits_pred_features
Normalize predictor valuessits_pred_normalize
Obtain categorical id and predictor labels for time series samplessits_pred_reference sits_pred_references
Obtain a fraction of the predictors data framesits_pred_sample
Obtain predictors for time series samplessits_predictors
Reclassify a classified cubesits_reclassify sits_reclassify.class_cube sits_reclassify.default
Reduces a cube or samples from a summarization functionsits_reduce sits_reduce.raster_cube sits_reduce.sits
Reduce imbalance in a set of samplessits_reduce_imbalance
Build a regular data cube from an irregular onesits_regularize sits_regularize.default sits_regularize.dem_cube sits_regularize.derived_cube sits_regularize.raster_cube sits_regularize.sar_cube
Train random forest modelssits_rfor
Informs if sits examples should runsits_run_examples
Informs if sits tests should runsits_run_tests
Sample a percentage of a time seriessits_sample
Allocation of sample size to stratasits_sampling_design
Segment an imagesits_segment
Filter bands on a data set (tibble or cube)sits_select sits_select.default sits_select.patterns sits_select.raster_cube sits_select.sits
Filter time series with Savitzky-Golay filtersits_sgolay
Segment an image using SLICsits_slic
Smooth probability cubes with spatial predictorssits_smooth sits_smooth.default sits_smooth.derived_cube sits_smooth.probs_cube sits_smooth.raster_cube
Use SOM for quality analysis of time series samplessits_som sits_som_map
Cleans the samples based on SOM map informationsits_som_clean_samples
Evaluate clustersits_som_evaluate_cluster
Evaluate clustersits_som_remove_samples
Obtain statistics for all sample bandssits_stats
Allocation of sample size to stratasits_stratified_sampling
Train support vector machine modelssits_svm
Train a model using Temporal Self-Attention Encodersits_tae
Train temporal convolutional neural network modelssits_tempcnn
Get timeline of a cube or a set of time seriessits_timeline sits_timeline.default sits_timeline.derived_cube sits_timeline.raster_cube sits_timeline.sits sits_timeline.sits_model sits_timeline.tbl_df
Export a sits tibble metadata to the CSV formatsits_to_csv sits_to_csv.default sits_to_csv.sits sits_to_csv.tbl_df
Save accuracy assessments as Excel filessits_to_xlsx sits_to_xlsx.list sits_to_xlsx.sits_accuracy
Train classification modelssits_train
Tuning machine learning models hyper-parameterssits_tuning
Tuning machine learning models hyper-parameterssits_tuning_hparams
Estimate classification uncertainty based on probs cubesits_uncertainty sits_uncertainty.default sits_uncertainty.probs_cube sits_uncertainty.probs_vector_cube
Suggest samples for enhancing classification accuracysits_uncertainty_sampling
Validate time series samplessits_validate
Calculate the variance of a probability cubesits_variance sits_variance.default sits_variance.derived_cube sits_variance.probs_cube sits_variance.raster_cube
View data cubes and samples in leafletsits_view sits_view.class_cube sits_view.data.frame sits_view.default sits_view.probs_cube sits_view.raster_cube sits_view.sits sits_view.som_map
Filter time series with whittaker filtersits_whittaker
Train extreme gradient boosting modelssits_xgboost
Summarize data cubessummary.class_cube
Summarize data cubessummary.raster_cube
Summarize sitssummary.sits
Summarize accuracy matrix for training datasummary.sits_accuracy
Summarize accuracy matrix for area datasummary.sits_area_accuracy
Summarise variance cubessummary.variance_cube