sits1.5.1 package

Satellite Image Time Series Analysis for Earth Observation Data Cubes

sits_kfold_validate

Cross-validate time series samples

print.sits_accuracy

Print the values of a confusion matrix

print.sits_area_accuracy

Print the area-weighted accuracy

sits_accuracy_summary

Print accuracy summary

dot-check_date_parameter

Check is date is valid

hist.probs_cube

histogram of prob cubes

hist.raster_cube

histogram of data cubes

hist.sits

Histogram

hist.uncertainty_cube

Histogram uncertainty cubes

impute_linear

Replace NA values with linear interpolation

plot.class_cube

Plot classified images

plot.class_vector_cube

Plot Segments

plot.dem_cube

Plot DEM cubes

plot.geo_distances

Make a kernel density plot of samples distances.

plot.patterns

Plot patterns that describe classes

plot.predicted

Plot time series predictions

sits_accuracy

Assess classification accuracy (area-weighted method)

plot.probs_cube

Plot probability cubes

plot.probs_vector_cube

Plot probability vector cubes

plot.raster_cube

Plot RGB data cubes

plot

Plot time series

plot.rfor_model

Plot Random Forest model

sits_colors_show

Function to show colors in SITS

plot.sar_cube

Plot SAR data cubes

plot.sits_accuracy

Plot confusion matrix

plot.sits_cluster

Plot a dendrogram cluster

plot.som_evaluate_cluster

Plot confusion between clusters

plot.som_map

Plot a SOM map

plot.torch_model

Plot Torch (deep learning) model

sits_colors

Function to retrieve sits color table

plot.uncertainty_cube

Plot uncertainty cubes

plot.uncertainty_vector_cube

Plot uncertainty vector cubes

plot.variance_cube

Plot variance cubes

plot.vector_cube

Plot RGB vector data cubes

plot.xgb_model

Plot XGB model

sits_add_base_cube

Add base maps to a time series data cube

sits_apply

Apply a function on a set of time series

sits_as_sf

Return a sits_tibble or raster_cube as an sf object.

sits_bands

Get the names of the bands

sits_bbox

Get the bounding box of the data

sits_classify

Classify time series or data cubes

sits_factory_function

Create a closure for calling functions with and without data

sits_clean

Cleans a classified map using a local window

sits_cluster_clean

Removes labels that are minority in each cluster.

sits_cluster_dendro

Find clusters in time series samples

sits_cluster_frequency

Show label frequency in each cluster produced by dendrogram analysis

sits_colors_qgis

Function to save color table as QML style for data cube

sits_colors_reset

Function to reset sits color table

sits_colors_set

Function to set sits color table

sits_mlp

Train multi-layer perceptron models using torch

sits_combine_predictions

Estimate ensemble prediction based on list of probs cubes

sits_confidence_sampling

Suggest high confidence samples to increase the training set.

sits_config_show

Show current sits configuration

sits_config_user_file

List the cloud collections supported by sits

sits_config

Configure parameters for sits package

sits_cube_copy

Copy the images of a cube to a local directory

sits_cube

Create data cubes from image collections

sits_filter

Filter time series with smoothing filter

sits_formula_linear

Define a linear formula for classification models

sits_formula_logref

Define a loglinear formula for classification models

sits_geo_dist

Compute the minimum distances among samples and prediction points.

sits_get_data

Get time series from data cubes and cloud services

sits_impute

Replace NA values in time series with imputation function

sits_label_classification

Build a labelled image from a probability cube

sits_labels_summary

Inform label distribution of a set of time series

sits_labels

Get labels associated to a data set

sits_lighttae

Train a model using Lightweight Temporal Self-Attention Encoder

sits_list_collections

List the cloud collections supported by sits

sits_merge

Merge two data sets (time series or cubes)

sits_mgrs_to_roi

Convert MGRS tile information to ROI in WGS84

sits_mixture_model

Multiple endmember spectral mixture analysis

sits_model_export

Export classification models

sits_mosaic

Mosaic classified cubes

sits_patterns

Find temporal patterns associated to a set of time series

sits_pred_features

Obtain numerical values of predictors for time series samples

sits_pred_normalize

Normalize predictor values

sits_pred_reference

Obtain categorical id and predictor labels for time series samples

sits_pred_sample

Obtain a fraction of the predictors data frame

sits_predictors

Obtain predictors for time series samples

sits_reclassify

Reclassify a classified cube

sits_reduce_imbalance

Reduce imbalance in a set of samples

sits_reduce

Reduces a cube or samples from a summarization function

sits_regularize

Build a regular data cube from an irregular one

sits_rfor

Train random forest models

sits_run_examples

Informs if sits examples should run

sits_run_tests

Informs if sits tests should run

sits_sample

Sample a percentage of a time series

sits_sampling_design

Allocation of sample size to strata

sits_segment

Segment an image

sits_select

Filter bands on a data set (tibble or cube)

sits_sgolay

Filter time series with Savitzky-Golay filter

sits_show_prediction

Shows the predicted labels for a classified tibble

sits_slic

Segment an image using SLIC

sits_smooth

Smooth probability cubes with spatial predictors

sits_som_clean_samples

Cleans the samples based on SOM map information

sits_som_evaluate_cluster

Evaluate cluster

sits_som_remove_samples

Evaluate cluster

sits_som

Use SOM for quality analysis of time series samples

sits_stats

Obtain statistics for all sample bands

sits_stratified_sampling

Allocation of sample size to strata

sits_svm

Train support vector machine models

sits_tae

Train a model using Temporal Self-Attention Encoder

sits_tempcnn

Train temporal convolutional neural network models

sits_timeline

Get timeline of a cube or a set of time series

sits_to_csv

Export a sits tibble metadata to the CSV format

sits_to_xlsx

Save accuracy assessments as Excel files

sits_train

Train classification models

sits_tuning_hparams

Tuning machine learning models hyper-parameters

sits_tuning

Tuning machine learning models hyper-parameters

sits_uncertainty_sampling

Suggest samples for enhancing classification accuracy

sits_uncertainty

Estimate classification uncertainty based on probs cube

sits_validate

Validate time series samples

sits_variance

Calculate the variance of a probability cube

sits_view

View data cubes and samples in leaflet

sits_whittaker

Filter time series with whittaker filter

sits_xgboost

Train extreme gradient boosting models

sits-package

sits

summary.class_cube

Summarize data cubes

summary.raster_cube

Summarize data cubes

summary.sits_accuracy

Summarize accuracy matrix for training data

summary.sits_area_accuracy

Summarize accuracy matrix for area data

summary.sits

Summarize sits

summary.variance_cube

Summarise variance cubes

tick-sits_labels-set-tick

Change the labels of a set of time series

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.

  • Maintainer: Gilberto Camara
  • License: GPL-2
  • Last published: 2024-08-19