Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
16
datasets available to search
ShareScore release 0.9.0
Dataset results
16 results for “cropland mapping”
Indicative distribution map for Ecosystem Functional Group T7.1 Annual croplands
<p>This archive contains indicative distribution maps and profiles for <strong>T7.1 Annual croplands</strong>, a ecosystem functional group (EFG, level 3) of the <a href="https://global-ecosystems.org/">IUCN Global Ecosystem Typology</a> (v2.0). Please refer to Keith <em>et al.</em> (2020) for details.</p> <p>The descriptive profiles provide brief summaries of key ecological traits and processes, maps are indicative of global distribution patterns, and are not intended to represent fine-scale patterns. The maps show areas of the world containing major (value of 1, coloured red) or minor occurrences (value of 2, coloured yellow) of each ecosystem functional group. Minor occurrences are areas where an ecosystem functional group is scattered in patches within matrices of other ecosystem functional groups or where they occur in substantial areas, but only within a segment of a larger region. Given bounds of resolution and accuracy of source data, the maps should be used to query which EFG are likely to occur within areas, rather than which occur at particular point locations. Detailed methods and references for the maps are included in the profile (xml format).</p>
Global maps of area suitability for solar photovoltaics on rooftops and cropland
<p>This dataset consists of the following global maps:</p> <p>1. The suitable area for installing agri-photovoltaics or agrivoltaics on agricultural land cover in about 10 km x 10 km resolution for three scenarios of policy and social acceptance (optimistic, neutral and conservative)</p> <p>2. The percentage of PV-suitable building area of total area in 10km x 10km resolution</p> <p>3. The area suitability of rooftop-photovoltaics in a 10km x 10km resolution </p> <p>The maps are based on the land cover data from the Copernicus Land Monitoring Service from 2019 and the Open Street Map accessed in 2021.</p> <p>Updates from Version 1.0 :</p> <p>- New maps of agrivoltaic suitability due to updated methodology : inclusion of regional crop distribution </p>
Landsat-based dataset for mapping annual center-pivot irrigated cropland in Brazil
<p>Center-pivot irrigated cropland (CPIC) is a critical component of irrigation and plays an essential role in improving water use efficiency and increasing food production. To automatically extract the spatial distribution of CPIC in Brazil based on the remote sensing technology, we constructed a training dataset that supports the semantic segmentation models.</p><p>The dataset were built with the <a href="https://www.sciencedirect.com/topics/earth-and-planetary-sciences/landsat-5">Landsat 5</a> , 7 and 8<a href="https://www.sciencedirect.com/topics/earth-and-planetary-sciences/landsat-7"> </a> images as well as the CPIC maps from <a href="https://metadados.snirh.gov.br/geonetwork/srv/por/catalog.search#/metadata/e2d38e3f-5e62-41ad-87ab-990490841073">ANA reference</a> data. We used the Landsat images in 2005, 2010 and 2015 to build the dataset.</p><p>The samples in train_images and train_masks were used to train and valid the Convolutional Neural Network models; </p><p>The samples in valid_data were used to test the model's prediction accuracy.</p><p>Pixels with values 255 and 0 in the mask samples represent the CPIC and background categories.</p><p><strong>For technical details that used to create the dataset, please refer to </strong><i><strong>https://doi.org/</strong></i><strong>10.1016/j.isprsjprs.2023.10.007.</strong></p>
Annual maps of cropland abandonment, land cover, and other derived data for time-series analysis of cropland abandonment
<p>This archive contains raw annual land cover maps, cropland abandonment maps, and accompanying derived data products to support:</p> <blockquote> <p>Crawford C.L., Yin, H., Radeloff, V.C., and Wilcove, D.S. 2022. Rural land abandonment is too ephemeral to provide major benefits for biodiversity and climate. <em>Science Advances</em> <a href="https://doi.org/10.1126/sciadv.abm8999">doi.org/10.1126/sciadv.abm8999</a><em>.</em></p> </blockquote> <p>An archive of the analysis scripts developed for this project can be found at: <a href="https://github.com/chriscra/abandonment_trajectories">https://github.com/chriscra/abandonment_trajectories</a> (<a href="https://doi.org/10.5281/zenodo.6383127">https://doi.org/10.5281/zenodo.6383127</a>).</p> <p>Note that the label "_2022_02_07" in many file names refers to the date of the primary analysis. "dts” or “dt” refer to “data.tables," large .csv files that were manipulated using the data.table package in R (Dowle and Srinivasan 2021, <a href="http://r-datatable.com/">http://r-datatable.com/</a>). “Rasters” refer to “.tif” files that were processed using the raster and terra packages in R (Hijmans, 2022; <a href="https://rspatial.org/terra/">https://rspatial.org/terra/</a>; <a href="https://rspatial.org/raster">https://rspatial.org/raster</a>).</p> <p>Data files fall into one of four categories of data derived during our analysis of abandonment: <strong>observed</strong>, <strong>potential</strong>, <strong>maximum</strong>, or <strong>recultivation</strong>. Derived datasets also follow the same naming convention, though are aggregated across sites. These four categories are as follows (using “age_dts” for our site in Shaanxi Province, China as an example):</p> <ol> <li><strong>observed</strong> abandonment identified through our primary analysis, with a threshold of five years. These files do not have a specific label beyond the description of the file and the date of analysis (e.g., shaanxi_age_2022_02_07.csv);</li> <li><strong>potential</strong> abandonment for a scenario without any recultivation, in which abandoned croplands are left abandoned from the year of initial abandonment through the end of the time series, with the label “_potential” (e.g., shaanxi_potential_age_2022_02_07.csv);</li> <li><strong>maximum</strong> age of abandonment over the course of the time series, with the label “_max” (e.g., shaanxi_max_age_2022_02_07.csv);</li> <li><strong>recultivation </strong>periods, corresponding to the lengths of recultivation periods following abandonment, given the label “_recult” (e.g., shaanxi_recult_age_2022_02_07.csv).</li> </ol> <p> </p> <p><strong>This archive includes multiple .zip files, the contents of which are described below:</strong></p> <ul> <li><strong>age_dts.zip</strong> - Maps of abandonment age (i.e., how long each pixel has been abandoned for, as of that year, also referred to as length, duration, etc.), for each year between 1987-2017 for all 11 sites. These maps are stored as .csv files, where each row is a pixel, the first two columns refer to the x and y coordinates (in terms of longitude and latitude), and subsequent columns contain the abandonment age values for an individual year (where years are labeled with "y" followed by the year, e.g., "y1987"). Maps are given with a latitude and longitude coordinate reference system. Folder contains observed age, potential age (“_potential”), maximum age (“_max”), and recultivation lengths (“_recult”) for all sites. Maximum age .csv files include only three columns: x, y, and the maximum length (i.e., “max age”, in years) for each pixel throughout the entire time series (1987-2017). Files were produced using the custom functions "cc_filter_abn_dt()," “cc_calc_max_age()," “cc_calc_potential_age(),” and “cc_calc_recult_age();” see "_util/_util_functions.R."</li> <li><strong>age_rasters.zip</strong> - Maps of abandonment age (i.e., how long each pixel has been abandoned for), for each year between 1987-2017 for all 11 sites. Maps are stored as .tif files, where each band corresponds to one of the 31 years in our analysis (1987-2017), in ascending order (i.e., the first layer is 1987 and the 31st layer is 2017). Folder contains observed age, potential age (“_potential”), and maximum age (“_max”) rasters for all sites. Maximum age rasters include just one band (“layer”). These rasters match the corresponding .csv files contained in "age_dts.zip.”</li> <li><strong>derived_data.zip</strong> - summary datasets created throughout this analysis, listed below.</li> <li><strong>diff.zip</strong> - .csv files for each of our eleven sites containing the year-to-year lagged differences in abandonment age (i.e., length of time abandoned) for each pixel. The rows correspond to a single pixel of land, and the columns refer to the year the difference is in reference to. These rows do not have longitude or latitude values associated with them; however, rows correspond to the same rows in the .csv files in "input_data.tables.zip" and "age_dts.zip." These files were produced using the custom function "cc_diff_dt()" (much like the base R function "diff()"), contained within the custom function "cc_filter_abn_dt()" (see "_util/_util_functions.R"). Folder contains diff files for observed abandonment, potential abandonment (“_potential”), and recultivation lengths (“_recult”) for all sites.</li> <li><strong>input_dts.zip</strong> - annual land cover maps for eleven sites with four land cover classes (see below), adapted from Yin et al. 2020 <em>Remote Sensing of Environment </em>(<a href="https://doi.org/10.1016/j.rse.2020.111873">https://doi.org/10.1016/j.rse.2020.111873</a>)<em>. </em>Like “age_dts,” these maps are stored as .csv files, where each row is a pixel and the first two columns refer to x and y coordinates (in terms of longitude and latitude). Subsequent columns contain the land cover class for an individual year (e.g., "y1987"). Note that these maps were recoded from Yin et al. 2020 so that land cover classification was consistent across sites (see below). This contains two files for each site: the raw land cover maps from Yin et al. 2020 (after recoding), and a “clean” version produced by applying 5- and 8-year temporal filters to the raw input (see custom function “cc_temporal_filter_lc(),” in “_util/_util_functions.R” and “1_prep_r_to_dt.R”). These files correspond to those in "input_rasters.zip," and serve as the primary inputs for the analysis.</li> <li><strong>input_rasters.zip</strong> - annual land cover maps for eleven sites with four land cover classes (see below), adapted from Yin et al. 2020 <em>Remote Sensing of Environment. </em>Maps are stored as ".tif" files, where each band corresponds one of the 31 years in our analysis (1987-2017), in ascending order (i.e., the first layer is 1987 and the 31st layer is 2017). Maps are given with a latitude and longitude coordinate reference system. Note that these maps were recoded so that land cover classes matched across sites (see below). Contains two files for each site: the raw land cover maps (after recoding), and a “clean” version that has been processed with 5- and 8-year temporal filters (see above). These files match those in "input_dts.zip."</li> <li><strong>length.zip</strong> - .csv files containing the length (i.e., age or duration, in years) of each distinct individual period of abandonment at each site. This folder contains length files for observed and potential abandonment, as well as recultivation lengths. Produced using the custom function "cc_filter_abn_dt()" and “cc_extract_length();” see "_util/_util_functions.R."</li> </ul> <p><strong>derived_data.zip</strong> contains the following files:</p> <ul> <li>"<strong>site_df.csv</strong>" - a simple .csv containing descriptive information for each of our eleven sites, along with the original land cover codes used by Yin et al. 2020 (updated so that all eleven sites in how land cover classes were coded; see below).</li> <li><strong>Primary derived datasets </strong>for both observed abandonment (“area_dat”) and potential abandonment (“potential_area_dat”). <ul> <li><strong>area_dat</strong> - Shows the area (in ha) in each land cover class at each site in each year (1987-2017), along with the area of cropland abandoned in each year following a five-year abandonment threshold (abandoned for >=5 years) or no threshold (abandoned for >=1 years). Produced using custom functions "cc_calc_area_per_lc_abn()" via "cc_summarize_abn_dts()". See scripts "cluster/2_analyze_abn.R" and "_util/_util_functions.R."</li> <li><strong>persistence_dat</strong> - A .csv containing the area of cropland abandoned (ha) for a given "cohort" of abandoned cropland (i.e., a group of cropland abandoned in the same year, also called "year_abn") in a specific year. This area is also given as a proportion of the initial area abandoned in each cohort, or the area of each cohort when it was first classified as abandoned at year 5 ("initial_area_abn"). The "age" is given as the number of years since a given cohort of abandoned cropland was last actively cultivated, and "time" is marked relative to the 5th year, when our five-year definition first classifies that land as abandoned (and where the proportion of abandoned land remaining abandoned is 1). Produced using custom functions "cc_calc_persistence()" via "cc_summarize_abn_dts()". See scripts "cluster/2_analyze_abn.R" and "_util/_util_functions.R." This serves as the main input for our linear models of recultivation (“decay”) trajectories.</li> <li><strong>turnover_dat</strong> - A .csv showing the annual gross gain, annual gross loss, and annual net change in the area (in ha) of abandoned cropland at each site in each year of the time series. Produced using custom functions "cc_calc_abn_diff()" via "cc_summarize_abn_dts()" (see "_util/_util_functions.R"), implemented in "cluster/2_analyze_abn.R." This file is only produced for observed abandonment.</li> </ul> </li> <li><strong>Area summary files </strong>(for observed abandonment only) <ul> <li><strong>area_summary_df</strong> - Contains a range of summary values relating to the area of cropland abandonment for each of our eleven sites. All area values are given in hectares (ha) unless stated otherwise. It contains 16 variables as columns, including 1) "site," 2) "total_site_area_ha_2017" - the total site area (ha) in 2017, 3) "cropland_area_1987" - the area in cropland in 1987 (ha), 4) "area_abn_ha_2017" - the area of cropland abandoned as of 2017 (ha), 5) "area_ever_abn_ha" - the total area of those pixels that were abandoned at least once during the time series (corresponding to the area of potential abandonment, as of 2017), 6) "total_crop_extent_ha" - the total area of those pixels that were classified as cropland at least once during the time series, 7) "total_area_abn_remaining_2017" - duplicate of "area_abn_ha_2017," the area abandoned as of 2017 (ha), taken from "area_recult_threshold," 8) "total_initial_area_abn" - the sum of the initial area of each cohort of abandonment when it is first classified as "abandoned," i.e., at the 5 year mark (note that this is cumulative, and because it counts those pixels that were abandoned more than once, it is therefore larger than "area_ever_abn_ha"), taken from "area_recult_threshold" 9) "total_area_abn_recultivated_2017" - the area of abandoned land that was recultivated as of 2017 (cumulatively, i.e., "total_initial_area_abn" - "area_abn_ha_2017"), taken from "area_recult_threshold," 10) "proportion_recultivated" - the proportion of all abandoned cropland (including multiple periods per pixel) that was recultivated by 2017, taken from "area_recult_threshold," 11) "area_2017_as_prop_site" - area abandoned as of 2017 as a proportion of the total site area, 12) "area_2017_as_prop_total_crop" - area abandoned as of 2017 as a proportion of the total crop extent, 13) "area_2017_as_prop_crop87" - area abandoned as of 2017 as a proportion of cropland area in 1987, 14) "area_ever_abn_as_prop_site" - area ever abandoned as a proportion of the total site area, 15) "area_ever_abn_as_prop_total_crop" - area ever abandoned as a proportion of the total crop extent, 16) "area_ever_abn_as_prop_crop87" - area ever abandoned as a proportion of cropland area in 1987. See script "1_summary_stats.Rmd."</li> <li><strong>area_recult_threshold</strong> - Contains data on the proportion of observed abandoned cropland area that is recultivated by the end of our time series. This includes the area of abandoned cropland as of 2017 ("total_area_abn_remaining_2017") and the sum of the initial area of each cohort of abandonment when it is first classified as abandoned (at year 5; "total_initial_area_abn"). This "total_initial_area_abn" is cumulative, and allows for pixels that were abandoned multiple times during the time series to be counted multiple times. The difference between these two columns yields the "total_area_abn_recultivated_2017," which in turn is used to calculate the "proportion_recultivated," and the (ascending) "order" of sites based on this proportion. This file includes recultivation stats for each site for three abandonment definitions: 5, 7, and 10 years. See script "1_summary_stats.Rmd."</li> <li><strong>abn_lc_area_2017</strong> - Contains the number of pixels and corresponding area (in ha) of abandoned cropland in the year 2017 at each site, according to the land cover class (either woody vegetation [2], or herbaceous vegetation [4]) and the age in 2017 (5 to 30 years). See script "cluster/6_lc_of_abn.R."</li> <li><strong>abn_prop_lc_2017 </strong>- Contains the number of pixels and corresponding area (ha) of cropland abandoned in the year 2017 in each land cover type (woody vegetation [2], or herbaceous vegetation [4]). It also shows this area as a proportion of the total area abandoned at each site (i.e., in either land cover class: 2 or 4). See script "cluster/6_lc_of_abn.R."</li> </ul> </li> <li><strong>Carbon</strong> <ul> <li><strong>carbon_df </strong>– contains the observed and potential carbon accumulation in abandoned croplands in each site in each year (in Mg C), for two abandonment thresholds: 5 years (our default abandonment definition) and 1 year (i.e., no threshold). Each data point corresponds to one of two scenarios (“type” column), either “observed” or “potential.” Carbon accumulation figures are for both the sum of forest and soil carbon at each site in a given year. Carbon accumulation is listed in three columns: 1) “C_up_to_20” contains the total carbon accumulated in those abandoned croplands with abandonment durations between 5 and 20 years. 2) “C_21_30” contains the total carbon accumulation in croplands with durations between 21 and 30 years, which are differentiated in order to account for non-linear carbon accumulation rates in soils over time, and 3) “total_C_Mg” contains the sum of the previous two columns, representing the total carbon accumulated across all abandoned croplands in each year.</li> <li><strong>soc_mean</strong> – contains mean soil organic carbon accumulation rates for years 1-20 and years 21-80, derived from Sanderman et al. 2020 (in Mg C; <a href="https://doi.org/10.7910/DVN/HA17D3">https://doi.org/10.7910/DVN/HA17D3</a>). These values correspond to accumulation rates in croplands upon abandonment and regeneration to natural vegetation (Sanderman et al. 2020’s “rewilding” scenario). These mean values are calculated across those pixels identified as cropland by Sanderman et al. 2020 at each site. Mean values in year 20 and 80 are contained in columns “mean_soc_20” and “mean_soc_80” respectively, and the annualized rate over the first 20 years and the subsequent years 21 through 80 are contained in columns “mean_annual_soc_1_20” and “mean_annual_soc_21_80” respectively.</li> </ul> </li> <li><strong>Decay model data</strong> – two R data files containing data products for our linear models of abandonment recultivation trajectories. <ul> <li><strong>decay_endpoints_files</strong> – an R data file (.rds) containing seven data products produced as part of our common endpoint analysis, which calculated mean trajectories for each site across a range of common endpoints, ensuring that means were based on coefficient estimates derived from a consistent number of observations for each cohort. These files are: <ul> <li><strong>common_endpoint_dat – </strong>a .csv containing subsets of “persistence_dat” for each “endpoint” (7 through 29).</li> <li><strong>endpoint_n – </strong>a .csv describing, for each endpoint, the corresponding number of observations per cohort (“n_obs”), the number of cohorts (“n_cohorts”), the total number of observations across cohorts included (“total_obs”), and the cohorts that meet the endpoint threshold (“cohorts”).</li> <li><strong>coef_l3_endpoints – </strong>corresponding model coefficients for our primary model (“l3”) parameterized by the range of subsets across endpoints.</li> <li><strong>augment_endpoints – </strong>fitted values (i.e., model predictions) for linear models produced across the full range of endpoint subsets.</li> <li><strong>fitted_endpoints – </strong>a simplified .csv containing the mean linear and log coefficients for each site at each endpoint, and the corresponding predicted proportion remaining abandoned through time (based on the “age,” or duration, of abandonment).</li> <li><strong>time_to_endpoints – </strong>a .csv containing, for mean trajectories for each endpoint at each site, the estimated time required for a given amount of abandoned cropland in a cohort to be recultivated (deciles, 10% through 100%).</li> <li><strong>endpoint_half_lives – </strong>a .csv containing the half-lives calculated for the mean trajectories for each endpoint at each site.</li> </ul> </li> <li><strong>decay_mod_archive</strong> - an R data file (.rds) containing eleven data products derived from linear models of abandonment recultivation ("decay"): <ul> <li><strong>lm_mega_lin_log_lin_l</strong> – the primary linear model produced in our analysis. This model is referred to as “lin_log_lin” (or “l3”) because the model predicts linear persistence (“lin”) as a function of a log term of time (“log”) and a linear term of time (“lin”). “mega” refers to the fact that this model is run for the full dataset, pooled across all 11 sites.</li> <li><strong>coef_l3_mega</strong> – a .csv containing model coefficients for our primary linear model of recultivation (“lin_log_lin”, or “l3”), with a single row each for the linear term of time and the log term of time, for 26 cohorts at 11 sites.</li> <li><strong>mean_coef_l3_mega</strong> – a data frame containing the mean coefficient values for the log and linear terms of time across cohorts at each site. This also contains the mean of the low and high coefficient estimates, based on the 95% confidence interval.</li> <li><strong>half_lives_all_cohorts_l3</strong> – half-lives calculated for each cohort at each site, for our primary model.</li> <li><strong>half_life_mean_coefs_l3</strong> – half-lives calculated based on the mean trajectory for each site (based on the mean log coefficients and mean linear coefficients across all cohorts), for our primary model.</li> <li><strong>mod_AIC_mega</strong> – Akaike Information Criterion (AIC) values for all tested model specifications.</li> <li><strong>fitted_combo</strong> – fitted values (i.e., model predictions) for our primary model (“l3”) and a series of alternative model specifications (“l3_trim” – excluding cohorts with fewer than 5 observations; “lin_log” – a model including only one log time term; “log2_lin” – in which the log of persistence is predicted by log and linear time terms; and “l3_no_cohort” – our primary model, predicting linear persistence as a function of log time and linear time, but without cohort-level fixed effects).</li> <li><strong>time_to_combo</strong> – contains the estimated time required for a certain amount of abandoned cropland in a cohort to be recultivated (deciles, 10% through 100%). See script "2_decay_models.Rmd." These values are calculated for a range of alternative model specifications ("l3_trim", “lin_log”, "log2_lin", and "l3_no_cohort"; see above).</li> </ul> </li> </ul> </li> <li><strong>Length data</strong> – includes “_distill_df” files and “mean_length_df” files for observed, potential, and recultivation. <ul> <li><strong>length_distill_df</strong> - .csvs containing the number ("freq") of abandonment periods of a specific "length" of time (i.e., age) at each site over the course of the entire time series. Derived from the "length" files in "length.zip." See script "cluster/5_distill_lengths.R."</li> <li><strong>mean_length_df</strong> - .csvs with the mean, median, and standard deviation, for each site, for both "all" lengths or just the "max" length per pixel, and for a range of abandonment definitions (1, 3, 5, 7, and 10 years). Derived from "length_distill_df." See script "1_summary_stats.Rmd."</li> </ul> </li> <li><strong>Duration summary files</strong> – includes “summary_stats_all_sites” and “summary_stats_all_sites_pooled,” for observed and potential abandonment, and recultivation periods following abandonment. <ul> <li><strong>“summary_stats_all_sites”</strong> - A simple .csv derived from "mean_length_df" files containing summary stats across the 11 sites. This includes the mean of the mean abandonment duration ("length", in years) for each of our 11 sites ("mean_of_means"), the standard deviation of these site mean abandonment lengths ("sd_of_means"), the mean of the standard deviation at each site ("mean_of_sds"), the mean median ("mean_of_medians"), and the mean number of abandonment periods ("mean_n_abn_periods"). Note that length "all" indicates that these stats account for all periods (including multiple per pixel), rather than just the max duration per pixel. See script "1_summary_stats.Rmd."</li> <li><strong>“summary_stats_all_sites_pooled”</strong> - A summary .csv similar to "summary_stats_all_sites," but calculated by pooling all distinct periods of abandonment across all eleven sites, and then calculating the mean, median, and standard deviation of abandonment duration. See script "1_summary_stats.Rmd."</li> </ul> </li> <li><strong>Comparing annual approach to identifying abandonment to a two-timepoint (“2yr”) approach:</strong> <ul> <li><strong>abn_2yr_ages_df</strong> - Contains the age of former croplands identified as "abandoned" using a two-timepoint method (i.e., 2017 - 1987), where age values (as of 2017) are derived from our map of abandonment identified using the full annual time series. This includes the area in hectares (ha), in each age class (along with the number of pixels), at each of our 11 sites. This dataset is used to calculate the percent of cropland "abandonment" identified using the two-year method that is actually too "young," i.e., less than 5 years old, and therefore not truly abandonment according to our five-year abandonment definition</li> <li><strong>abn_2yr_overestimation</strong> - Compares the area (in hectares) of cropland abandonment at each site identified with our full annual time series (and a five-year abandonment definition) and the "abandonment" identified using a two-timepoint method (2017-1987). This also includes the percent difference in area between the two methods, the Jaccard similarity of the areas identified as abandonment, and the percent of "young" (i.e., <5-year-old) "abandonment" identified by the two-timepoint method.</li> </ul> </li> </ul> <p><strong>Input land cover maps:</strong></p> <p>As noted, the file "input_rasters.zip" contain the raw annual land cover maps for eleven sites generated by:</p> <blockquote> <p>Yin, H., A. Brandão, J. Buchner, D. Helmers, B. G. Iuliano, N. E. Kimambo, K. E. Lewińska, E. Razenkova, A. Rizayeva, N. Rogova, S. A. Spawn, Y. Xie, and V. C. Radeloff. 2020. Monitoring cropland abandonment with Landsat time series. <em>Remote Sensing of Environment</em> 246:111873. https://doi.org/10.1016/j.rse.2020.111873</p> </blockquote> <p>These land cover maps served as raw inputs for this project and form the basis of the analysis.</p> <p>All land cover maps have a resolution of 30-m and exist for each year from 1987 through 2017. The exceptions are Nebraska / Wyoming (1986-2018) and Wisconsin (1987-2018); these additional years were excluded from our analysis of abandonment duration.</p> <p><strong>Land cover categories in these maps are coded as follows:</strong></p> <ol> <li>Non-vegetated area (e.g., water, urban, barren land)</li> <li>Woody vegetation (e.g., forests)</li> <li>Cropland</li> <li>Herbaceous vegetation (e.g., grassland)</li> </ol> <p><strong>Site file names correspond to the following geographic locations:</strong></p> <ul> <li>belarus = Vitebsk, Belarus / Smolensk, Russia</li> <li>bosnia_herzegovina = Bosnia & Herzegovina</li> <li>chongqing = Chongqing, China</li> <li>goias = Goiás, Brazil</li> <li>iraq = Iraq</li> <li>mato_grosso = Mato Grosso, Brazil</li> <li>nebraska = Nebraska / Wyoming, USA</li> <li>orenburg = Orenburg, Russia / Uralsk, Kazakhstan</li> <li>shaanxi = Shaanxi/Shanxi, China</li> <li>volgograd = Volgograd, Russia</li> <li>wisconsin = Wisconsin, USA</li> </ul> <p>This dataset is minimally altered from Yin et al. 2020. However, land cover codes were updated for five sites (Iraq, Nebraska/Wyoming, Orenburg/Uralsk, Volgograd, and Wisconsin) in order to maintain consistency in how land cover was coded across all sites. The original land cover codes (matching Yin et al. 2020) are described in the file "site_df.csv" and are as follows:</p> <ol> <li>Iraq: 1 Non-vegetated; 2 Cropland; 3 Woody; 4 Herbaceous</li> <li>Nebraska / Wyoming (USA): 1 Cropland; 2 Woody; 3 Non-vegetated; 4 Herbaceous</li> <li>Orenburg, Russia / Uralsk, Kazakhstan: 1 Non-vegetated; 2 Cropland; 3 Herbaceous; 4 Woody</li> <li>Volgograd (Russia): 1 Non-vegetated; 2 Cropland; 3 Herbaceous; 4 Woody</li> <li>Wisconsin (USA): 1 Cropland; 2 Herbaceous; 3 Woody; 4 Non-vegetated</li> </ol>
A map of active cropland and short-term fallows across Northern Mozambique derived from PlanetScope data
<p><strong>Overview</strong></p> <p>A map of smallholder-dominated landscapes covering the provinces Niassa, Zambezia, Cabo Delgado, and Nampula in Northern Mozambique. The map includes active cropland and short-term fallows as separate classes, as well as five land cover classes (herbaceous vegetation, open woodlands, closed woodlands, non-vegetated land, water). The map is based on PlanetScope mosaics and consequently comes at 4.77m spatial resolution.</p> <p>The download contains the following files:</p> <ul> <li>ps_lc_nmoz.tif / .qml: land cover map and associated QGIS style file</li> <li>ps_lc_nmoz_probmargins.tif / .qml: probability margins and associated QGIS style file</li> <li>training.gpkg: training samples with class labels</li> <li>LICENSE.pdf: NICFI data program user license</li> </ul> <p><strong>Map accuracy</strong></p> <p>We conducted an area-adjusted accuracy assessment based on a stratified random sample, which yielded important insights regarding accuracies and error types. The area-adjusted overall accuracy of the map is 88.9%, but users should be aware of the most important error types:</p> <ul> <li>Active cropland were overestimated, whereas local topographical depressions with moist soils, and regions with exposed soils/rocks and sparse vegetation cover were found to be falsely classified.</li> <li>Short-term fallows were underestimated, particularly in regions with high growth rates and extensive land management, such as parts of the northern and north-eastern study region.</li> </ul> <p><strong>Further resources</strong></p> <p>The production of this map was made possible through the <a href="https://www.planet.com/nicfi/">NICFI data program</a>, providing the PlanetScope mosaics and the Google Earth Engine cloud computing platform for preprocessing of the satellite data and classification. As such, the use of the map falls under the <a href="https://assets.planet.com/docs/Planet_ParticipantLicenseAgreement_NICFI.pdf">NICFI data program license agreement</a> included in the download. The code for preprocessing the PlanetScope mosaics is based on the Google Earth Engine Python API and made available at <a href="https://github.com/philipperufin/eepypr/">https://github.com/philipperufin/eepypr/</a>.</p> <p>We advise map users to read the <a href="https://eartharxiv.org/repository/view/3174/">preprint</a> or the <a href="https://doi.org/10.1016/j.jag.2022.102937">open access paper</a> for detailed insights. In case of questions please consult these resources or contact the lead author of the work.</p>
High resolution cropland agreement map (30 m) circa 2020
<p>Accurate and precise measurements of global cropland extent are needed for monitoring the sustainability of agriculture at all scales. Recent advancement in remote sensing and land cover mapping methods have greatly increased the ability to estimate cropland area distribution and trends. Here the FAO presents a map of cropland agreement produced by consolidating information at pixel level from six high-resolutions maps for <em>circa </em>2020. The following six high resolution layers were used: ESRI 10 meter LU/LC, FROM-GLC, GLAD, GLC-FCS30, Globeland30 and Worldcover.</p> <p>Two bands are included in the dataset:</p> <ol> <li>Simple agreement (values between 1 and 6)</li> <li>Detailed agreement (values between 1 and 63)</li> </ol> <p>The map, developed in the Google Earth Engine platform, combines the 6 land cover/cropland layers to show their cropland agreement on pixel level at a spatial resolution of 30 meters. The simple agreement has pixel values that range from 1 (only 1 dataset classifies as cropland) to 6 (all datasets agree on presence of cropland). Pixels with a value of 0 indicate pixels where all datasets agree on absence of cropland. The second band includes a detailed agreement, showing which combination of the 6 datasets classify a pixel as cropland. The overview table (<em>DetailedAgreement_LookupTable.xlsx</em>) shows what the pixel values of this detailed agreement (from 1 to 63) correspond to.</p> <p>The dataset has been uploaded in 16 tiles, in the preview below and in the file "A<em>CroplandAgreement_30m_Tiles.png</em>" the extent of each tile can be found.</p> <p>For more information on FAO statistics on land cover and land use:</p> <p>FAO. 2022. <em>Land use statistics and indicators. Global, regional and country trends, 2000–2020</em>. FAOSTAT Analytical Brief, no. 48. Rome. <a href="https://doi.org/10.4060/cc0963en">https://doi.org/10.4060/cc0963en</a></p> <p>FAO. 2021. <em>Land cover statistics. Global, regional and country trends, 2000–2019</em>. FAOSTAT Analytical Brief Series No. 37. Rome. </p>
Togo Cropland Map and Labeled Dataset
<p>This dataset provides a 10 m resolution map of cropland in Togo (togo_cropland_2019.zip). Each pixel represents a posterior probability (ranging 0 to 1) that the pixel contains crops, predicted using an LSTM classifier and multi-spectral time series of Sentinel-2 satellite observations. For more details on the method, please see Kerner and Tseng, et al. (full reference below).</p> <p>This dataset also provides the hand-labeled polygons used for training (crop_merged_v2.zi, noncrop_merged_v2.zip) and testing (togo_test_majority.zip) the model, which were created by experts based on photointerpretation of high-resolution imagery (primarily SkySat and PlanetScope) in QGIS and Google Earth Pro.</p> <p>If you use any part of this dataset, please cite the following paper: Hannah Kerner, Gabriel Tseng, Inbal Becker-Reshef, Catherine Nakalembe, Brian Barker, Blake Munshell, Madhava Paliyam, and Mehdi Hosseini. 2020. Rapid Response Crop Maps in Data Sparse Regions. In review for <em>KDD ’20: ACMSIGKDD Conference on Knowledge Discovery and Data Mining Workshops</em>, August 22–27, 2020, San Diego, CA. </p>
Kenya Cropland Map and Non-Crop Labelled dataset
<p>This dataset provides a 10m resolution map of cropland in Kenya for the 2019-2020 growing season (kenya_cropland_binary_2019.tif.zip) and a 10m resolution map of cropland in Busia County, Kenya for the 2020-2021 growing season (busia_cropland_binary_2020.tif.zip). Each pixel has a binary value, 0 if it does not contain crops and 1 if it does. These values were obtained by thresholding the predictions of an LSTM classifier trained on multi-spectral time series of Sentinel-2 satellite observations. A thresholding value of 0.5 was used.</p> <p>This dataset also provides the hand-labelled non-crop points used for training, which were created by labelling high-resolution satellite imagery in QGIS and Google Earth Pro.</p> <p>For more information, or if you use any part of this dataset, please refer to / cite the following paper: Gabriel Tseng, Hannah Kerner, Catherine Nakalembe and Inbal Becker-Reshef. 2020. Annual and in-season mapping of cropland at field scale with sparse labels. Tackling Climate Change with Machine Learning workshop at NeurIPS ’20: December 11th, 2020</p>
Comparison of Cropland Maps Derived from Land Cover Maps in Sub-Saharan Africa
<p>This data repository provides the datasets associated with analysis conducted in Kerner et al. (2024), citation below.</p> <p>The CSV file `intercomparison-results.csv` gives a table metrics for each of 11 land cover maps (plus a majority vote ensemble of all maps) evaluated using the reference dataset for each of 8 countries (Kenya, Rwanda, Uganda, Tanzania, Mali, Malawi, Togo, and Zambia). The reference datasets are provided as zip files. To ensure these datasets can be used for independent evaluation and comparison between maps in the future, the reference datasets should ONLY be used for final, independent evaluation of data products/model outputs; they should NOT be used for training models, tuning hyperparameters, or any other decisions during model/map development. </p> <p>The provided tif files contain the consensus maps (sum of all 11 maps) used to compute consensus statistics in Kerner et al. (2024).</p> <p>Kerner, H., Nakalembe, C., Yang, A., Zvonkov, I., McWeeny, R., Tseng, G., and Becker-Reshef, I. (2024). How accurate are existing land cover maps for agriculture in Sub-Saharan Africa? <em>Under review</em>. </p>
Reference data set used to validate the hybrid cropland map at 500m (Fritz, S. 2024)
<p>This is a reference data set for validation of the hybrid cropland map at 500m resolution for the year 2019 (Fritz, 2024, map <a title="Hybrid cropland map (GLAD/WorldCereal)" href="../doi/10.5281/zenodo.10818823" target="_blank" rel="noopener">available here</a>)</p> <p>Sampling design: random whithin areas of improvement, where the WorldCereal map is performing better (less errors) than the GLAD cropland map 2019. </p> <p>Number of sample sites: 500</p> <p>Method of data collection: visual interpreation of various sources of information, including very high resolution images and photos. </p> <p><br>Tool for data collection: <a href="https://www.geo-wiki.org" target="_blank" rel="noopener">Geo-Wiki</a></p>
ChinaSoybean10:An Annual 10-m Soybean cropland Mapping Dataset in China from 2019 to 2022
<p>This dataset consists of soybean annual maps from 2019 to 2022 in China's main soybean producing areas with a pixel size of 10 m x 10 m, including Heilongjiang, Inner Mongolia, Jilin, Liaoning, Anhui, Henan, Shandong, Hubei, Jiangsu, and Sichuan.The maps use the ESPG: 4326 (WGS_1984) spatial reference system. The maps contain values of null and 1, representing non-crop land (including other crops) and soybeans. The maps are shown at the provincial administrative unit level, including the four prefecture-level cities in Eastern Inner Mongolia. You can analyze and visualize these maps with software like ArcGIS, QGIS, or similar applications.</p>
Validating NISAR's cropland mapping approach and the USDA/NASS Cropland Data Layer against ground truth data in a fragmented urban agricultural region
<p>Field data used in manuscript:</p> <p>1 shapefile containing the ROI outline for which Sentinel-1 data was cropped</p> <p>1 shapefile containing the 93 fields investigated with their names, types and sizes as attributes </p> <p>8 annual csv data for active fields, consisting of 3 harvest dates and 5 planting dates. This list is after translating data from Farmlogic Report (not conducive to analysis in the format) and filtering for fields greater 1 acre. The study lateron further screened to use only fields greater than 2 acreas (0.81 hectares). </p> <p> </p>
Hcropland30: A hybrid 30-m global cropland map by leveraging global land cover products and Landsat data based on a deep learning model
<p><strong>Hcropland30</strong><strong>:</strong><strong>A 30-m global cropland map by leveraging global land cover products and Landsat data based on a deep learning model</strong></p> <p><strong>***Please note this dataset is undergoing peer review***</strong></p> <p><strong>Version</strong>: <strong>1.0</strong></p> <p><strong>Authors</strong>: Qiong Hu <sup>a, 1</sup>, Zhiwen Cai<sup> b, 1</sup>, Liangzhi You<sup> c, d</sup>, Steffen Fritz<sup> e</sup>, Xinyu Zhang<sup> c</sup>, He Yin<sup> f</sup>, Haodong Wei<sup>c</sup>, Jingya Yang<sup> g</sup>, Zexuan Li<sup> a</sup>, Qiangyi Yu<sup> g</sup>, Hao Wu<sup> a</sup>, Baodong Xu<sup> b *</sup>, Wenbin Wu<sup> g, *</sup></p> <p><em><sup>a</sup></em><em> Key Laboratory for Geographical Process Analysis & Simulation of Hubei Province/College of Urban and Environmental Sciences, Central China Normal University, Wuhan 430079, China</em></p> <p><em><sup>b</sup></em><em> College of Resources and Environment, Huazhong Agricultural University, Wuhan 430070, China</em></p> <p><em><sup>c</sup></em><em> Macro Agriculture Research Institute, College of Plant Science and Technology, Huazhong Agricultural University, Wuhan 430070, China</em></p> <p><em><sup>d </sup></em><em>International Food Policy Research Institute, 1201 I Street, NW, Washington, DC 20005, USA</em></p> <p><em><sup>e </sup></em><em>Novel Data Ecosystems for sustainability Research Group, International Institute for Applied Systems Analysis (IIASA), Schlossplatz 1, Laxenburg A-2361, Austria</em></p> <p><em><sup>f </sup></em><em>Department of Geography, Kent State University, 325 S. Lincoln Street, Kent, OH 44242, USA</em></p> <p><a name="_Hlk166672711"></a><em><sup>g </sup></em><em>State Key Laboratory of Efficient Utilization of Arid and Semi-arid Arable Land in Northern China, the Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, China</em></p> <p><strong> </strong></p> <p><strong>Introduction</strong></p> <p>We are pleased to introduce a comprehensive global cropland mapping dataset (named Hcropland30) in 2020, meticulously curated to support a wide range of research and analysis applications related to agricultural land and environmental assessment. This dataset encompasses the entire globe, divided into 16,284 grids, each measuring an area of 1°×1°. Hcropland30 was produced by leveraging global land cover products and Landsat data based on a deep learning model. Initially, we established a hierarchal sampling strategy that used the simulated annealing method to identify the representative 1°×1° grids globally and the sparse point-level samples within these selected 1°×1°grids. Subsequently, we employed an ensemble learning technique to expand these sparse point-level samples into the densely pixel-wise labels, creating the area-level 1°×1° cropland labels. These area-level labels were then used to train a U-Net model for predicting global cropland distribution, followed by a comprehensive evaluation of the mapping accuracy.</p> <p> </p> <p><strong>Dataset</strong></p> <p><strong><em><u>1. Hcropland30</u></em></strong><strong>:</strong> A hybrid 30-m global cropland map in 2020</p> <p>****<strong>Data format</strong>: GeoTiff</p> <p>****<strong>Spatial resolution</strong>: 30 m</p> <p>****<strong>Projection</strong>: EPSG: 4326 (WGS84)</p> <p>****<strong>Values</strong>: 1 denotes cropland and 0 denotes non-cropland</p> <p>The dataset has been uploaded in 16,284 tiles. The extent of each tile can be found in the file of “Grids.shp”. Each file is named according to the grid’s Id number. For example, “000015.tif” corresponds to the cropland mapping result for the 15-th 1°×1° grid. This systematic naming convention ensures easy identification and retrieval of the specific grid data.</p> <p><strong><em><u>2. </u></em></strong><strong><em><u>1°×1° </u></em></strong><strong><em><u>Grids</u></em></strong><strong>:</strong> This file contains all 16,284 1°×1° grids used in the dataset. The vector file includes 18 attribute fields, providing comprehensive metadata for each grid. These attributes are essential for users who need detailed information about each grid’s characteristics.</p> <p>****<strong>Data format</strong>: ESRI shapefile</p> <p>****<strong>Projection</strong>: EPSG: 4326 (WGS84)</p> <p>****<strong>Attribute Fields</strong>:</p> <p><strong>Id:</strong> The grid’s ID number.</p> <p><strong>area:</strong> The area of the grid.</p> <p><strong>mode:</strong> Indicates the representative sample grid.</p> <p><strong>climate:</strong> The climate type the grid belongs to.</p> <p><strong>dem: </strong>Average DEM value of the grid.</p> <p><strong>ndvi_s1 to ndvi_s4:</strong> Average NDVI values for four seasons within the grid.</p> <p><strong>esa, esri, fcs30, fromglc, glad, globeland30:</strong> Proportion of cropland pixels of different publicly available cropland products.</p> <p><strong>inconsistent:</strong> Proportion of inconsistent pixels within the grid according to different public cropland products.</p> <p><strong>hcropland30:</strong> Proportion of cropland pixels of our Hcropland30 dataset.</p> <p><strong><em><u>3. Samples</u></em></strong>: The selected representative pixel-level samples, including 32,343 cropland and 67657 non-cropland samples. The category information of each sample was determined based on visual interpretation on Google Earth image and three-year NDVI time series curves from 2019-2021.</p> <p>****<strong>Data format</strong>: ESRI shapefile</p> <p>****<strong>Projection</strong>: EPSG: 4326 (WGS84)</p> <p>****<strong>Attribute Fields</strong>:</p> <p><strong>type:</strong> 1 denotes cropland sample and 0 denotes non-cropland sample.</p> <p><strong>Citation</strong></p> <p>If you use this dataset, please cite the following paper:</p> <p>Hu, Q., Cai, Z., You, L., Fritz, S., Zhang, X., Yin, H., Wei, H., Yang, J., Li, Z., Yu, Q., Wu, H., Xu, B., Wu, W. (2024). Hcropland30: A 30-m global cropland map by leveraging global land cover products and Landsat data based on a deep learning model, Remote Sensing of Environment, submitted.</p> <p><strong>License</strong></p> <p>The data is licensed under Creative Commons Attribution 4.0 International (CC BY 4.0).</p> <p><strong>Disclaimer</strong></p> <p>This dataset is provided as-is, without any warranty, express or implied. The dataset author is not</p> <p>responsible for any errors or omissions in the data, or for any consequences arising from the use</p> <p>of the data.</p> <p><strong>Contact</strong></p> <p>If you have any questions or feedback regarding the dataset, please contact the dataset author</p> <p>Qiong Hu (huqiong@ccnu.edu.cn)</p>
NACP Integrated Wildland and Cropland 30-m Fuel Characteristics Map, U.S.A., 2010
The data set provides a 30-m comprehensive fuelbed characteristics map for both the wildland and cropland areas of the conterminous United States (CONUS) for 2010. This integrated product is the result of combining the spatially discrete Fuel Characteristic Classification System (FCCS) data of the US Forest Service (USFS) with the crop-and grassland-specific information of the US Department of Agriculture?'s (USDA's) Cropland Data Layer (CDL). By combining the spatially discrete details of the FCCS data set with the crop-and grassland-specific information of the CDL, a more robust map of fuelbed characteristics is available. The merged product has an advantage over the original FCCS map for estimating emissions from burned areas due to the integration of the fuelbed characteristics for agricultural areas from the CDL.There are three GeoTIFF format files and three comma-separated companion files distributed with this data set. The three tif files provided are very large and exceed the size limits of a standard GeoTIFF file format (4 GB). File sizes range from 20 to 30 GB. Compressed file sizes range from 2 to 3 GB. They are in a format that is called a BigTIFF file. ArcGIS 10.0 and ERDAS Imagine are able to read these files.
A new global hybrid map of annual herbaceous cropland at a 500 m resolution for the year 2019: Accompanying file.
<p>The zip file contains the map accompanying the publication "A new global hybrid map of annual herbaceous cropland at a 500 m resolution for the year 2019" (in submission).<br><br>The hybrid map of global cropland extent has a 500 m resolution and was created by fusing two of the latest high resolution remotely sensed cropland products: the European Space Agency’s WorldCereal and the cropland layer from the University of Maryland.<br><br>The data set used for the validation of this map is <a href="../doi/10.5281/zenodo.11517295" target="_blank" rel="noopener">available here</a>.<br><br></p>
U.S. annual cultivated extent and maps of cropland expansion and cropland abandonment
<p>This repository will eventually contain the data layers of several connected products related to U.S. cropland extent and dynamics, including:</p> <p><br> A set of 30-m resolution maps of <strong>annual cultivated extent </strong>for the conterminous US (CONUS) for the years 1986-2018</p> <p>A 30-m resolution nationwide map of <strong>abandoned croplands </strong>in the U.S., as described by Xie et al. (in review).</p> <p>A 30-m resolution nationwide map of <strong>stable croplands</strong> in the U.S., as described by Uludere-Aragon et al. (in review).</p> <p>A 30-m resolution nationwide map of <strong>cropland expansion</strong> in the U.S. for the period 1986-2018 (in prep). </p> <p> </p> <p> </p> <p>These data were also utilized in related publications, including:</p> <p>Xie and Lark (2021). Mapping annual irrigation from Landsat imagery and environmental variables across the conterminous United States. https://doi.org/10.1016/j.rse.2021.112445</p> <p>Xie et al. (2021). Landsat-based Irrigation Dataset (LANID): 30 m resolution maps of irrigation distribution, frequency, and change for the US, 1997–2017. https://doi.org/10.5194/essd-13-5689-2021</p> <p>O'neil et al. (in prep) Effect of marginal land definitions on biofuel supply chain optimization outcomes.</p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.