SITS: Satellite Image Time Series Analysis for Earth Observation Data Cubes (submit R package for review)

[gilbertocamara]

Date accepted: 2025-07-01
Submitting Author Name: Gilberto Camara
Submitting Author Github Handle: @gilbertocamara
Other Package Authors Github handles: @rolfsimoes, @OldLipe, @M3nin0, @lorenalves
Repository: https://github.com/e-sensing/sits
Version submitted: 1.4.2
Submission type: Standard
Editor: @mpadge
Reviewers: @mdsumner, @loreabad6, @Nowosad, @edzer, @alexgleith

Due date for @Nowosad: 2025-04-14

Due date for @alexgleith: 2025-04-14
Archive: TBD
Version accepted: TBD
Language: en

• Paste the full DESCRIPTION file inside a code block below:

Package: sits
Type: Package
Version: 1.5.3
Title: Satellite Image Time Series Analysis for Earth Observation Data Cubes
Authors@R: c(person('Rolf', 'Simoes', role = c('aut'), email = 'rolfsimoes@gmail.com'),
             person('Gilberto', 'Camara', role = c('aut', 'cre', 'ths'), email = 'gilberto.camara.inpe@gmail.com'),
             person('Felipe', 'Souza', role = c('aut'), email = 'felipe.carvalho@inpe.br'),
             person('Felipe', 'Carlos', role = c('aut'), email = "efelipecarlos@gmail.com"),
             person('Lorena', 'Santos', role = c('aut'), email = 'lorena.santos@inpe.br')
             )
Maintainer: Gilberto Camara <gilberto.camara.inpe@gmail.com>
Description: An end-to-end toolkit for land use and land cover classification
    using big Earth observation data. Builds satellite image data cubes from cloud collections.
    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 and  
    to reduce training samples imbalance. Provides machine learning algorithms including support vector machines, 
    random forests, extreme gradient boosting, multi-layer perceptrons,
    temporal convolution neural networks, and temporal attention encoders.
    Performs efficient classification of big Earth observation data cubes and includes 
    functions for post-classification smoothing based on Bayesian inference. 
    Enables best practices for estimating area and assessing accuracy of land change. 
    Minimum recommended requirements: 16 GB RAM and 4 CPU dual-core.
Encoding: UTF-8
Language: en-US
Depends: R (>= 4.1.0)
URL: https://github.com/e-sensing/sits/, https://e-sensing.github.io/sitsbook/
BugReports: https://github.com/e-sensing/sits/issues
License: GPL-2
ByteCompile: true
LazyData: true
Imports:
    yaml (>= 2.3.0),
    dplyr (>= 1.1.0),
    grDevices,
    graphics,
    leafgl,
    leaflet (>= 2.2.2),
    lubridate,
    luz (>= 0.4.0),
    parallel,
    purrr (>= 1.0.2),
    randomForest,
    Rcpp (>= 1.0.13),
    rstac (>= 1.0.1),
    sf (>= 1.0-19),
    slider (>= 0.2.0),
    stats,
    terra (>= 1.8-5),
    tibble (>= 3.1),
    tidyr (>= 1.3.0),
    tmap (>= 4.0),
    torch (>= 0.14.0),
    units,
    utils
Suggests:
    aws.s3,
    caret,
    cli,
    cols4all (>= 0.8.0),
    covr,
    dendextend,
    dtwclust,
    DiagrammeR,
    digest,
    e1071,
    exactextractr,
    FNN,
    gdalcubes (>= 0.7.0),
    geojsonsf,
    ggplot2,
    httr2 (>= 1.1.0),
    jsonlite,
    kohonen (>= 3.0.11),
    methods,
    mgcv,
    nnet,
    openxlsx,
    proxy,
    randomForestExplainer,
    RColorBrewer,
    RcppArmadillo (>= 0.12),
    scales,
    spdep,
    stars,
    stringr,
    supercells (>= 1.0.0),
    testthat (>= 3.1.3),
    tools,
    xgboost
Config/testthat/edition: 3
Config/testthat/parallel: false
Config/testthat/start-first: cube, raster, regularize, data, ml
LinkingTo:
    Rcpp,
    RcppArmadillo
RoxygenNote: 7.3.2
Collate: 
    'api_accessors.R'
    'api_accuracy.R'
    'api_apply.R'
    'api_band.R'
    'api_bayts.R'
    'api_bbox.R'
    'api_block.R'
    'api_check.R'
    'api_chunks.R'
    'api_classify.R'
    'api_clean.R'
    'api_cluster.R'
    'api_colors.R'
    'api_combine_predictions.R'
    'api_comp.R'
    'api_conf.R'
    'api_crop.R'
    'api_csv.R'
    'api_cube.R'
    'api_data.R'
    'api_debug.R'
    'api_detect_change.R'
    'api_download.R'
    'api_dtw.R'
    'api_environment.R'
    'api_factory.R'
    'api_file_info.R'
    'api_file.R'
    'api_gdal.R'
    'api_gdalcubes.R'
    'api_grid.R'
    'api_jobs.R'
    'api_kohonen.R'
    'api_label_class.R'
    'api_mask.R'
    'api_merge.R'
    'api_mixture_model.R'
    'api_ml_model.R'
    'api_mosaic.R'
    'api_opensearch.R'
    'api_parallel.R'
    'api_patterns.R'
    'api_period.R'
    'api_plot_time_series.R'
    'api_plot_raster.R'
    'api_plot_vector.R'
    'api_point.R'
    'api_predictors.R'
    'api_preconditions.R'
    'api_raster.R'
    'api_raster_sub_image.R'
    'api_reclassify.R'
    'api_reduce.R'
    'api_regularize.R'
    'api_request.R'
    'api_request_httr2.R'
    'api_roi.R'
    'api_samples.R'
    'api_segments.R'
    'api_select.R'
    'api_sf.R'
    'api_shp.R'
    'api_signal.R'
    'api_smooth.R'
    'api_smote.R'
    'api_som.R'
    'api_source.R'
    'api_source_aws.R'
    'api_source_bdc.R'
    'api_source_cdse.R'
    'api_source_deafrica.R'
    'api_source_deaustralia.R'
    'api_source_hls.R'
    'api_source_local.R'
    'api_source_mpc.R'
    'api_source_sdc.R'
    'api_source_stac.R'
    'api_source_terrascope.R'
    'api_source_usgs.R'
    'api_space_time_operations.R'
    'api_stac.R'
    'api_stats.R'
    'api_summary.R'
    'api_texture.R'
    'api_tibble.R'
    'api_tile.R'
    'api_timeline.R'
    'api_tmap.R'
    'api_torch.R'
    'api_torch_psetae.R'
    'api_ts.R'
    'api_tuning.R'
    'api_uncertainty.R'
    'api_utils.R'
    'api_validate.R'
    'api_values.R'
    'api_variance.R'
    'api_vector.R'
    'api_vector_info.R'
    'api_view.R'
    'RcppExports.R'
    'data.R'
    'sits-package.R'
    'sits_add_base_cube.R'
    'sits_apply.R'
    'sits_accuracy.R'
    'sits_bands.R'
    'sits_bayts.R'
    'sits_bbox.R'
    'sits_classify.R'
    'sits_colors.R'
    'sits_combine_predictions.R'
    'sits_config.R'
    'sits_csv.R'
    'sits_cube.R'
    'sits_cube_copy.R'
    'sits_cube_local.R'
    'sits_clean.R'
    'sits_cluster.R'
    'sits_detect_change.R'
    'sits_detect_change_method.R'
    'sits_dtw.R'
    'sits_factory.R'
    'sits_filters.R'
    'sits_geo_dist.R'
    'sits_get_data.R'
    'sits_get_class.R'
    'sits_get_probs.R'
    'sits_histogram.R'
    'sits_imputation.R'
    'sits_labels.R'
    'sits_label_classification.R'
    'sits_lighttae.R'
    'sits_machine_learning.R'
    'sits_merge.R'
    'sits_mixture_model.R'
    'sits_mlp.R'
    'sits_mosaic.R'
    'sits_model_export.R'
    'sits_patterns.R'
    'sits_plot.R'
    'sits_predictors.R'
    'sits_reclassify.R'
    'sits_reduce.R'
    'sits_reduce_imbalance.R'
    'sits_regularize.R'
    'sits_sample_functions.R'
    'sits_segmentation.R'
    'sits_select.R'
    'sits_sf.R'
    'sits_smooth.R'
    'sits_som.R'
    'sits_stars.R'
    'sits_summary.R'
    'sits_tae.R'
    'sits_tempcnn.R'
    'sits_terra.R' 
    'sits_texture.R'
    'sits_timeline.R'
    'sits_train.R'
    'sits_tuning.R'
    'sits_utils.R'
    'sits_uncertainty.R'
    'sits_validate.R'
    'sits_view.R'
    'sits_variance.R'
    'sits_xlsx.R'
    'zzz.R'

Scope

• Please indicate which category or categories from our package fit policies this package falls under:

  • [X ] geospatial data

• Explain how and why the package falls under these categories (briefly, 1-2 sentences):
  sits is a package for satellite image time series analysis that works with big Earth observation data sets.

• Who is the target audience, and what are the scientific applications of this package?
  Remote sensing and environmental experts wanting to classify remote sensing images for applications such as deforestation detection, agricultural and land use/land cover mapping, biodiversity conservation, and land degradation monitoring comprise the target audience.

• Are there other R packages that accomplish the same thing? If so, how does yours differ or meet our criteria for best-in-category?
  There are currently no other open-source software packages that have the same capabilities.

• (If applicable) Does your package comply with our guidance around Ethics, Data Privacy and Human Subjects Research?
  Not applicable

• If you made a pre-submission inquiry, please paste the link to the corresponding issue, forum post, or other discussion, or @tag the editor you contacted.
  Not applicable

• Explain reasons for any pkgcheck items which your package is unable to pass.

(a) Vignettes: Instead of preparing vignettes, the authors have written an online book that describes the contents of the package in detail. The book is available at the URL https://e-sensing.github.io/sitsbook/

Important notes:

(1) To run the tests, examples, and code coverage, please make
Ensure that the following environment variables are set in the R session.
Sys.setenv("SITS_RUN_TESTS" = "YES")
Sys.setenv("SITS_RUN_EXAMPLES" = "YES")
sits is a fairly large package, and the tests take a long time to run, since they access cloud services. We must manually enable testing for this reason.

(2) Please review version 1.5.3, not yet on CRAN, which is available in the "dev" branch in the GitHub repository.

Technical checks

Confirm each of the following by checking the box.

• I have read the rOpenSci packaging guide.
• I have read the author guide and I expect to maintain this package for at least 2 years or to find a replacement.

This package:

• does not violate the Terms of Service of any service it interacts with.
• has a CRAN and OSI accepted license.
• contains a README with instructions for installing the development version.
• includes documentation with examples for all functions, created with roxygen2.
• contains a vignette with examples of its essential functions and uses (see above).
• has a test suite.
• has continuous integration, including reporting of test coverage.

Publication options

• Do you intend for this package to go on CRAN?
  The package is already on CRAN.

• Do you intend for this package to go on Bioconductor?

• [ x] Do you wish to submit an Applications Article about your package to Methods in Ecology and Evolution? If so:

MEE Options

• The package is novel and will be of interest to the broad readership of the journal.
• The manuscript describing the package is no longer than 3000 words.
• You intend to archive the code for the package in a long-term repository which meets the requirements of the journal (see MEE's Policy on Publishing Code)
• (Scope: Do consider MEE's Aims and Scope for your manuscript. We make no guarantee that your manuscript will be within MEE scope.)
• (Although not required, we strongly recommend having a full manuscript prepared when you submit here.)
• (Please do not submit your package separately to Methods in Ecology and Evolution)

Code of conduct

• I agree to abide by rOpenSci's Code of Conduct during the review process and in maintaining my package should it be accepted.

[ropensci-review-bot]

Thanks for submitting to rOpenSci, our editors and @ropensci-review-bot will reply soon. Type @ropensci-review-bot help for help.

[ropensci-review-bot]

🚀

Editor check started

👋

[ropensci-review-bot]

Checks for sits (v1.4.1)

git hash: 6eac9edf

• ✖️ Package name is not available (on CRAN).
• ✔️ has a 'codemeta.json' file.
• ✔️ has a 'contributing' file.
• ✖️ The following function has no documented return value: [sits_filter]
• ✔️ uses 'roxygen2'.
• ✔️ 'DESCRIPTION' has a URL field.
• ✔️ 'DESCRIPTION' has a BugReports field.
• ✖️ Package has no HTML vignettes
• ✖️ These functions do not have examples: [plot.sits_cluster, sits_filter, sits_list_collections].
• ✔️ Package has continuous integration checks.
• ✖️ Package coverage is 0.1% (should be at least 75%).
• ✔️ R CMD check found no errors.
• ✔️ R CMD check found no warnings.

Important: All failing checks above must be addressed prior to proceeding

Package License: GPL-2

---

1. Package Dependencies

Details of Package Dependency Usage (click to open)

The table below tallies all function calls to all packages ('ncalls'), both internal (r-base + recommended, along with the package itself), and external (imported and suggested packages). 'NA' values indicate packages to which no identified calls to R functions could be found. Note that these results are generated by an automated code-tagging system which may not be entirely accurate.

type	package	ncalls
internal	base	1922
internal	sits	134
internal	datasets	3
internal	tools	1
imports	utils	259
imports	stats	178
imports	purrr	129
imports	dplyr	97
imports	tibble	67
imports	torch	60
imports	graphics	52
imports	sf	52
imports	rstac	48
imports	terra	48
imports	slider	47
imports	tidyr	43
imports	grDevices	42
imports	lubridate	18
imports	yaml	5
imports	gdalUtilities	NA
imports	parallel	NA
imports	Rcpp	NA
suggests	ggplot2	67
suggests	leaflet	16
suggests	digest	15
suggests	tmap	13
suggests	httr	12
suggests	stars	12
suggests	luz	11
suggests	mgcv	5
suggests	dtwclust	4
suggests	xgboost	4
suggests	caret	3
suggests	FNN	3
suggests	scales	3
suggests	gdalcubes	2
suggests	kohonen	2
suggests	methods	2
suggests	openxlsx	2
suggests	e1071	1
suggests	exactextractr	1
suggests	randomForest	1
suggests	randomForestExplainer	1
suggests	supercells	1
suggests	dendextend	NA
suggests	DiagrammeR	NA
suggests	future	NA
suggests	geojsonsf	NA
suggests	jsonlite	NA
suggests	leafem	NA
suggests	nnet	NA
suggests	RcppArmadillo	NA
suggests	testthat	NA
suggests	torchopt	NA
suggests	covr	NA
linking_to	Rcpp	NA
linking_to	RcppArmadillo	NA

Click below for tallies of functions used in each package. Locations of each call within this package may be generated locally by running 's <- pkgstats::pkgstats(<path/to/repo>)', and examining the 'external_calls' table.

base

list (172), source (167), c (162), labels (100), nrow (72), length (62), file (55), scale (41), names (39), row (39), seq_len (38), unlist (37), col (32), date (31), unique (28), lapply (25), unname (25), q (23), sum (23), toupper (23), for (22), paste (22), return (19), as.Date (18), options (18), as.numeric (17), paste0 (17), seq_along (17), ceiling (15), class (15), apply (14), dim (14), environment (13), round (12), which (12), as.character (11), as.matrix (11), Sys.time (10), try (10), factor (9), rep (9), seq (9), sqrt (9), suppressMessages (9), url (9), array (8), do.call (8), format (8), matrix (8), ncol (8), rbind (8), sample (8), substitute (8), t (8), table (8), by (7), colnames (7), mean (7), Sys.getenv (7), tryCatch (7), character (6), data.frame (6), floor (6), formals (6), gamma (6), levels (6), strsplit (6), structure (6), version (6), which.min (6), as.integer (5), if (5), missing (5), replace (5), suppressWarnings (5), which.max (5), abs (4), any (4), as.list (4), choose (4), grepl (4), inherits (4), list2env (4), mode (4), rev (4), row.names (4), setdiff (4), tempdir (4), args (3), cbind (3), colSums (3), diag (3), eval (3), get (3), is.na (3), path.expand (3), plot (3), prop.table (3), raw (3), readRDS (3), signif (3), socketSelect (3), split (3), switch (3), system.file (3), vapply (3), as.factor (2), debug (2), deparse (2), double (2), exp (2), gsub (2), I (2), is.logical (2), log (2), logical (2), max.col (2), parent.env (2), pmin (2), quote (2), range (2), rawConnection (2), rowSums (2), sort (2), subset (2), substring (2), summary (2), tolower (2), write (2), all (1), all.vars (1), as.vector (1), basename (1), cat (1), cut (1), difftime (1), dir (1), dir.exists (1), dirname (1), drop (1), exists (1), file.exists (1), gc (1), integer (1), is.null (1), kappa (1), lengths (1), list.files (1), new.env (1), numeric (1), open (1), order (1), parent.frame (1), rbind.data.frame (1), remove (1), sample.int (1), srcfile (1), svd (1), sys.frames (1), tapply (1), tempfile (1), vector (1), within (1)

utils

data (249), txtProgressBar (3), head (2), write.csv (2), getTxtProgressBar (1), read.csv (1), tail (1)

stats

ts (44), offset (36), formula (14), D (8), kernel (8), time (8), runif (6), predict (5), dt (4), na.action (4), quantile (4), sd (4), df (3), step (3), weights (3), as.formula (2), end (2), median (2), rbeta (2), rf (2), rlnorm (2), rnorm (2), start (2), addmargins (1), as.dendrogram (1), cutree (1), filter (1), reshape (1), smooth (1), var (1), window (1)

sits

sits_bands (25), sits_labels (21), sits_timeline (19), sits_select (10), train_fun (8), C_mask_na (3), mixture_fn (3), C_label_max_prob (2), C_max_sampling (2), comb_fn (2), download_fn (2), filter_call (2), label_fn (2), reclassify_fn (2), sits_train (2), sits_values (2), smooth_fn (2), .debug (1), C_entropy_probs (1), C_fill_na (1), C_kernel_max (1), C_kernel_mean (1), C_kernel_median (1), C_kernel_min (1), C_kernel_sd (1), C_least_probs (1), C_margin_probs (1), C_nnls_solver_batch (1), C_normalize_data (1), C_normalize_data_0 (1), create_iqr (1), impute_fun (1), plot_samples (1), replace_na (1), result_fun (1), seg_fun (1), sits_as_sf (1), sits_colors (1), sits_som_map (1), sits_validate (1), sits_view.sits (1), submit (1)

purrr

map (63), map_chr (16), map_dfr (12), map_dfc (7), map2_dfr (7), pmap_dfr (6), map_lgl (5), pmap (4), is_character (2), map_dbl (2), imap_dfc (1), map_int (1), map2 (1), pmap_lgl (1), transpose (1)

dplyr

filter (16), mutate (16), bind_rows (11), bind_cols (9), all_of (7), select (6), n (5), group_by (4), slice_sample (4), distinct (3), slice_head (3), left_join (2), select_if (2), starts_with (2), tibble (2), cur_group_id (1), inner_join (1), matches (1), summarise (1), transmute (1)

ggplot2

ggplot (12), aes (9), element_text (7), scale_fill_manual (5), element_rect (3), geom_line (3), labs (3), theme (3), .pt (2), element_blank (2), facet_grid (2), geom_point (2), geom_rect (2), guide_legend (2), position_dodge (2), scale_x_continuous (2), facet_wrap (1), geom_histogram (1), guides (1), scale_color_brewer (1), scale_x_date (1), scale_x_log10 (1)

tibble

tibble (49), as_tibble_row (10), as_tibble (7), lst (1)

torch

nn_module (20), torch_tensor (11), nn_cross_entropy_loss (5), nn_softmax (5), nn_batch_norm1d (4), torch_matmul (3), torch_zeros (3), nn_init_normal_ (2), torch_stack (2), torch_transpose (2), nn_dropout (1), torch_exp (1), torch_mean (1)

graphics

segments (15), title (12), points (10), legend (9), plot (3), abline (2), grid (1)

sf

st_crs (8), st_sample (7), st_transform (7), st_as_sf (5), st_drop_geometry (3), st_intersects (3), st_coordinates (2), st_geometry (2), st_geometry_type (2), st_intersection (2), st_write (2), read_sf (1), st_bbox (1), st_convex_hull (1), st_distance (1), st_is_empty (1), st_polygon (1), st_sf (1), st_sfc (1), st_within (1)

rstac

post_request (15), items_reap (11), items_fetch (9), items_matched (6), sign_planetary_computer (3), ext_query (2), stac (1), stac_search (1)

terra

rast (7), ext (4), spatSample (4), xFromCol (4), yFromRow (4), readValues (3), crop (2), crs (2), expanse (2), extract (2), freq (2), fileBlocksize (1), ncol (1), nlyr (1), nrow (1), readStart (1), values (1), xmax (1), xmin (1), xres (1), ymax (1), ymin (1), yres (1)

slider

slide (18), slide_dfr (16), slide_dbl (4), slide_lgl (4), slide2_dfr (3), slide_chr (1), slide2_lgl (1)

tidyr

nest (14), unnest (11), expand_grid (9), pivot_longer (6), starts_with (2), everything (1)

grDevices

colors (30), palette (9), hcl.colors (3)

lubridate

as_date (13), fast_strptime (1), mday (1), month (1), year (1), ymd (1)

leaflet

layersControlOptions (12), colorFactor (2), leaflet (1), providers$GeoportailFrance.orthos (1)

digest

digest (15)

tmap

tm_borders (5), tm_shape (3), tm_layout (2), tm_facets (1), tm_raster (1), tmap_options (1)

httr

add_headers (4), write_disk (3), parse_url (2), build_url (1), content (1), GET (1)

stars

read_stars (8), st_warp (4)

luz

luz_metric_accuracy (5), setup (5), luz_callback_early_stopping (1)

mgcv

gam (3), predict.gam (2)

yaml

yaml.load_file (4), as.yaml (1)

dtwclust

hierarchical_control (2), cvi (1), tsclust (1)

xgboost

xgb.plot.tree (3), xgboost (1)

caret

confusionMatrix (3)

datasets

trees (3)

FNN

knnx.index (3)

scales

date_format (1), label_number (1), pretty_breaks (1)

gdalcubes

gdalcubes_options (1), image_collection (1)

kohonen

somgrid (1), supersom (1)

methods

S3Part (2)

openxlsx

createWorkbook (1), saveWorkbook (1)

e1071

svm (1)

exactextractr

exact_extract (1)

randomForest

randomForest (1)

randomForestExplainer

plot_min_depth_distribution (1)

supercells

supercells (1)

tools

file_path_sans_ext (1)

NOTE: Some imported packages appear to have no associated function calls; please ensure with author that these 'Imports' are listed appropriately.

---

2. Statistical Properties

This package features some noteworthy statistical properties which may need to be clarified by a handling editor prior to progressing.

Details of statistical properties (click to open)

The package has:

• code in C++ (5% in 14 files) and R (95% in 131 files)
• 8 authors
• no vignette
• 4 internal data files
• 18 imported packages
• 164 exported functions (median 11 lines of code)
• 1988 non-exported functions in R (median 7 lines of code)
• 73 R functions (median 11 lines of code)

---

Statistical properties of package structure as distributional percentiles in relation to all current CRAN packages
The following terminology is used:

• loc = "Lines of Code"
• fn = "function"
• exp/not_exp = exported / not exported

All parameters are explained as tooltips in the locally-rendered HTML version of this report generated by the checks_to_markdown() function

The final measure (fn_call_network_size) is the total number of calls between functions (in R), or more abstract relationships between code objects in other languages. Values are flagged as "noteworthy" when they lie in the upper or lower 5th percentile.

measure	value	percentile	noteworthy
files_R	131	99.5
files_src	14	95.0
files_vignettes	0	0.0	TRUE
files_tests	46	99.0
loc_R	18106	99.6	TRUE
loc_src	1021	62.7
loc_tests	5220	98.3	TRUE
num_vignettes	0	0.0	TRUE
data_size_total	186830	86.9
data_size_median	50517	88.2
n_fns_r	2152	99.9	TRUE
n_fns_r_exported	164	97.9	TRUE
n_fns_r_not_exported	1988	99.9	TRUE
n_fns_src	73	74.2
n_fns_per_file_r	9	84.0
n_fns_per_file_src	5	49.3
num_params_per_fn	4	54.6
loc_per_fn_r	8	20.0
loc_per_fn_r_exp	11	25.1
loc_per_fn_r_not_exp	7	18.0
loc_per_fn_src	11	28.5
rel_whitespace_R	12	98.9	TRUE
rel_whitespace_src	13	56.8
rel_whitespace_tests	14	97.2	TRUE
doclines_per_fn_exp	44	55.5
doclines_per_fn_not_exp	0	0.0	TRUE
fn_call_network_size	3546	99.5	TRUE

---

2a. Network visualisation

Click to see the interactive network visualisation of calls between objects in package

---

3. goodpractice and other checks

Details of goodpractice checks (click to open)

3a. Continuous Integration Badges

GitHub Workflow Results

id	name	conclusion	sha	run_number	date
5438924419	R-CMD-check	success	bc5d6c	116	2023-07-02

---

3b. goodpractice results

R CMD check with rcmdcheck

R CMD check generated the following note:

1. checking installed package size ... NOTE
   installed size is 16.7Mb
   sub-directories of 1Mb or more:
   libs 14.1Mb

R CMD check generated the following check_fail:

1. rcmdcheck_reasonable_installed_size

Test coverage with covr

Package coverage: 0.08

The following files are not completely covered by tests:

file	coverage
R/api_accessors.R	0%
R/api_accuracy.R	0%
R/api_apply.R	0%
R/api_band.R	0%
R/api_bbox.R	0%
R/api_block.R	0%
R/api_check.R	0%
R/api_chunks.R	0%
R/api_classify.R	0%
R/api_cluster.R	0%
R/api_combine_predictions.R	0%
R/api_comp.R	0%
R/api_conf.R	0%
R/api_csv.R	0%
R/api_cube.R	0%
R/api_data.R	0%
R/api_debug.R	0%
R/api_download.R	0%
R/api_expressions.R	0%
R/api_factory.R	0%
R/api_file_info.R	0%
R/api_file.R	0%
R/api_gdal.R	0%
R/api_gdalcubes.R	0%
R/api_imputation.R	0%
R/api_jobs.R	0%
R/api_label_class.R	0%
R/api_mixture_model.R	0%
R/api_ml_model.R	0%
R/api_mosaic.R	0%
R/api_parallel.R	0%
R/api_period.R	0%
R/api_plot_raster.R	0%
R/api_plot_time_series.R	0%
R/api_point.R	0%
R/api_predictors.R	0%
R/api_raster_sub_image.R	0%
R/api_raster_terra.R	0%
R/api_raster.R	0%
R/api_reclassify.R	0%
R/api_roi.R	0%
R/api_samples.R	0%
R/api_segments.R	0%
R/api_sf.R	0%
R/api_shp.R	0%
R/api_signal.R	0%
R/api_smooth.R	0%
R/api_smote.R	0%
R/api_som.R	0%
R/api_source_aws.R	0%
R/api_source_bdc.R	0%
R/api_source_deafrica.R	0%
R/api_source_hls.R	0%
R/api_source_local.R	0%
R/api_source_mpc.R	0%
R/api_source_sdc.R	0%
R/api_source_stac.R	0%
R/api_source_usgs.R	0%
R/api_source.R	0%
R/api_space_time_operations.R	0%
R/api_stac.R	0%
R/api_stats.R	0%
R/api_summary.R	0%
R/api_tibble.R	0%
R/api_tile.R	0%
R/api_timeline.R	0%
R/api_torch.R	0%
R/api_ts.R	0%
R/api_tuning.R	0%
R/api_uncertainty.R	0%
R/api_utils.R	0%
R/api_variance.R	0%
R/api_view.R	0%
R/sits_accuracy.R	0%
R/sits_active_learning.R	0%
R/sits_apply.R	0%
R/sits_bands.R	0%
R/sits_bbox.R	0%
R/sits_classify.R	0%
R/sits_cluster.R	0%
R/sits_colors.R	0%
R/sits_combine_predictions.R	0%
R/sits_config.R	0%
R/sits_csv.R	0%
R/sits_cube_copy.R	0%
R/sits_cube.R	0%
R/sits_factory.R	0%
R/sits_filters.R	0%
R/sits_geo_dist.R	0%
R/sits_get_data.R	0%
R/sits_label_classification.R	0%
R/sits_labels.R	0%
R/sits_lighttae.R	0%
R/sits_machine_learning.R	0%
R/sits_merge.R	0%
R/sits_mixture_model.R	0%
R/sits_mlp.R	0%
R/sits_model_export.R	0%
R/sits_mosaic.R	0%
R/sits_patterns.R	0%
R/sits_plot.R	0%
R/sits_predictors.R	0%
R/sits_reclassify.R	0%
R/sits_regularize.R	0%
R/sits_resnet.R	0%
R/sits_sample_functions.R	0%
R/sits_segmentation.R	0%
R/sits_select.R	0%
R/sits_sf.R	0%
R/sits_smooth.R	0%
R/sits_som.R	0%
R/sits_summary.R	0%
R/sits_tae.R	0%
R/sits_tempcnn.R	0%
R/sits_temporal_segmentation.R	0%
R/sits_timeline.R	0%
R/sits_train.R	0%
R/sits_tuning.R	0%
R/sits_uncertainty.R	0%
R/sits_utils.R	12.5%
R/sits_validate.R	0%
R/sits_values.R	0%
R/sits_variance.R	0%
R/sits_view.R	0%
R/sits_xlsx.R	0%
src/combine_data.cpp	0%
src/kernel.cpp	0%
src/label_class.cpp	0%
src/linear_interp.cpp	0%
src/nnls_solver.cpp	0%
src/normalize_data_0.cpp	0%
src/normalize_data.cpp	0%
src/sampling_window.cpp	0%
src/smooth_bayes.cpp	0%
src/smooth_sgp.cpp	0%
src/smooth_whit.cpp	0%
src/smooth.cpp	0%
src/uncertainty.cpp	0%

Cyclocomplexity with cyclocomp

The following function have cyclocomplexity >= 15:

function	cyclocomplexity
sits_cube.stac_cube	16

Static code analyses with lintr

lintr found the following 23 potential issues:

message	number of times
Avoid library() and require() calls in packages	16
Lines should not be more than 80 characters.	3
Use <-, not =, for assignment.	4

---

Package Versions

package	version
pkgstats	0.1.3.4
pkgcheck	0.1.1.26

---

Editor-in-Chief Instructions:

Processing may not proceed until the items marked with ✖️ have been resolved.

[gilbertocamara]

Many thanks for your response. Please see below the following explanation, which was included as an "Important Note" in the submission, but maybe it has failed to catch the attention of the reviewers.

• Explain reasons for any pkgcheck items which your package is unable to pass.
  ✖️ Package name is not available (on CRAN).
  Package in already on CRAN. See

https://cran.r-project.org/web/packages/sits/index.html

✖️ The following function has no documented return value: [sits_filter]
✖️ These functions do not have examples: [plot.sits_cluster, sits_filter, sits_list_collections].
These problems have been fixed in version 1.4.2 of the package, which is available in the "dev" branch on GitHub. To clone the "dev" branch please use the command

git clone https://github.com/e-sensing/sits.git --branch dev

✖️ Package has no HTML vignettes
Instead of preparing vignettes, the authors have written an on-line book that describes the contents of the package in detail. The book is available at the URL

https://e-sensing.github.io/sitsbook/

✖️ Package coverage is 0.1% (should be at least 75%).
Package coverage is actually 95%. Please see

https://app.codecov.io/github/e-sensing/sits/tree/dev/R

sits is a large package. There are more than 1,100 individual tests that take a long time to run. Some of these tests access cloud services, which might be temporarily offline. For this reason, testing needs to be manually enabled. To run the tests, examples, and code coverage, please set the following environment variables in the R session:

Sys.setenv("SITS_RUN_TESTS" = "YES")
Sys.setenv("SITS_RUN_EXAMPLES" = "YES")

We are confident that sits meets the required criteria for ROpenSci review.

We would also like to respond to the lintr message:

Avoid library() and require() calls in packages - 16 

The package imports directly 17 packages, which are required for most functions. It also suggests 33 packages, which are typically used only in a few function, and need to be included only in "as-is" basis. This is based on CRAN policies that restrict the number of imported packages.

[maelle]

Thank you for your submission @gilbertocamara! As well as your careful response to the automatic checks. We agree with all your responses above.

However, as this a package that implements statistical and ML methods of geospatial data, rather than just the “accessing, manipulating, converting” and converting in our scope, it falls under under our newer statistical peer review program, which has its own time series and [geospatial standards](https://stats-devguide.ropensci.org/standards.html#standards-spatial. Submission requirements are different for this as authors need to document their standards compliance with our code annotation system.

A note - SITS is a package that is very large in scope and code base, as exemplified by the fact that it has a whole book for its documentation. As such, we anticipate that it will be challenging to find reviewers and we will need to give them considerably longer than usual to review the code base and documentation in full. Most of our submissions are not as large or mature at the point of review and up for significant API or architecture changes in response to review. For something in an earlier stage we would likely have suggested breaking functionality up into smaller, more focused packages. Nonetheless, we are up for the challenge if you are up for the higher statistical submission requirements and potential changes.

One last note regarding check results: As of now we can't set any environment variables when running the checks automatically, so they'd have to be set on your side, maybe using the withr::local_envvar() function or similar.

Thanks again! We're happy to answer further questions.

[gilbertocamara]

Dear @maelle, many thanks for your response. Please see my comments below:

Nonetheless, we are up for the challenge if you are up for the higher statistical submission requirements and potential changes.

Good! Looking at the specific requirements for ROpenSci statistical packages, the sits package meets most of them, such as G.2 (related to data input), G.3 (algorithms), G.4 (output data). We will have to review the sits package carefully as for requirements G.1 (documentation), G.5 (testing) and those for machine learning.

At a first glance, sits complies with requirements SP (spatial software) and TS (time series) and UL (unsupervised learning) . Since these requirements are very detailed, we will carefully review them to ensure compliance. We believe we meet the PD reqs (probability distr).

One last note regarding check results: As of now we can't set any environment variables when running the checks automatically, so they'd have to be set on your side, maybe using the [withr::local_envvar()](https://withr.r-lib.org/reference/with_envvar.html) function or similar.

Allow me to propose an alternative: please consider that the information provided in "codecov.io" to be sufficient to assert that sits meets the code coverage requirements of ROpenSci. If you accept this proposal, it will save us both time and work.

https://app.codecov.io/github/e-sensing/sits/tree/dev/R

We will work on improving sits so that it meets the specifications for ROpenSci statistical packages. We will report back to you when we have a new version that fully meets such specs.

Thanks,
Gilberto

[maelle]

Thank you! 🎉 Here's a direct link to the author guide for stat submissions: https://stats-devguide.ropensci.org/pkgdev.html

[maelle]

@gilbertocamara just a clarification: your package will have to comply with one of the category standards of the statistical review system, probably spatial (because time series is for class-based manipulation of time-series data, which is not what your package does as far as I understand).

Probability distributions should be considered an "additional' category that may be complied with in addition to the main categories.

Thank you!

[gilbertocamara]

Dear @maelle, thanks for the clarification. As part of the pre-submission process of the package "sits" to the ROpenSci statistical review, as recommended by you, I tried to run autotest_package . I made sure that all the examples and tests run OK. However, when running autotest_package, I am finding an error, which I reported in

https://github.com/ropensci-review-tools/autotest/issues/81

[maelle]

@gilbertocamara thanks for the report. I installed the dependencies of the dev branch, and I'm working with the dev branch itself. When running the examples I got

Error: No BDC_ACCESS_KEY defined in environment

Is there a comprehensive list of credentials needed to run the examples and tests? If there's such a list and one can create free accounts easily, I can get the credentials. If not, could these examples be skipped? For examples, see the @examplesIf tag https://roxygen2.r-lib.org/articles/rd.html?q=examplesIf#examples I see tests are skipped, but a list of steps necessary to run all tests could be useful (even if, for instance, a reviewer might not create an AWS account).

A good place to add setup info would be the installation instructions, and/or the file .github/CONTRIBUTING.md.

Thank you!

[maelle]

R CMD check output attached, I'm getting a test failure as well as some warnings. What can have caused this failure?

Once you add example skipping / a list of credentials to create, I can look into the autotest problem. Thanks for your patience. 😸

output.txt

I'd also recommend tackling the deprecation warnings from the tests before a full submission.

[gilbertocamara]

Dear @maelle, many thanks. One of the problems with the examples is that they assume the user has obtained a key to access the Brazil Data Cube (BDC). I have fixed the problem and removed this restriction. I ran R CMD CHECK with these changes, and now everything should work for you. Please use the new "dev" version that I have just uploaded.

[gilbertocamara]

Dear @maelle, one of the main challenges of the sits package is to provide a single point of access to different cloud services of Earth observation data, including AWS, Microsoft, NASA, and Digital Earth Africa, to name a few. Each provider requires different kinds of access credentials. In the on-line book, Chapter 4, we explain how to access each services. We recognized that information needs to be put somewhere else. We will improve the "Setup" chapter in the on-line book, an also prepare a new CONTRIBUTING.md. Thanks again!

[maelle]

@gilbertocamara the CONTRIBUTING guide could link to the book chapter, as long as it's easy to find all information.

I'm still waiting for R CMD check to finish, but examples ran without error (tests now running).

[gilbertocamara]

Thanks for the tips!