{ "fetched_at": "2026-10-24T15:33:25Z", "source_url": "https://www.kaggle.com/competitions/geolifeclef-2024/data", "pages": [ { "name": "data-description", "content": "The training data comprises **species observations** and **environmental data**. Below, we explain the data in detail.\n\nLinks\n=====\n\n❗**[New Seafile repository](https://lab.plantnet.org/seafile/d/bdb829337aa44a9489f6/)**❗: repository containing all the data. To optimize download times, see the section **data downloading** at the bottom of this page.\n\n❗**[GLC GitHub repository](https://github.com/plantnet/GLC)**❗: Useful codes to manipulate data with simple data loaders, examples, and sample data. More dataloaders can be added after the challenge starts. \n\n\nObservations data\n=================\n\nThe species related **training data** comprises:\n1. **Presence-Absence (PA) surveys**: including around 90 thousand surveys with roughly 10,000 species of the European flora. The presence-absence data (PA) is provided to compensate for the problem of false-absences of PO data and calibrate models to avoid associated biases.\n2. **Presence-Only (PO) occurrences**: combines around five million observations from numerous datasets gathered from the Global Biodiversity Information Facility (GBIF, www.gbif.org). This data constitutes the larger piece of the training data and covers all countries of our study area, but it has been sampled opportunistically (without standardized sampling protocol), leading to various sampling biases. The local absence of a species among PO data doesn't mean it is truly absent. An observer might not have reported it because it was difficult to \"see\" it at this time of the year, to identify it as not a monitoring target, or just unattractive.\n\nThere are two CSVs with species occurrence data on the Seafile available for training. The detailed description is provided again on **SeaFile** in separate ReadME files in relevant folders.\n- The PO metadata are available in `PresenceOnlyOccurences/GLC24_PO_metadata_train.csv`.\n- The PA metadata are available in `PresenceAbsenceSurveys/GLC24_PA_metadata_train.csv`.\n\nEnvironmental data\n==================\nBesides species data, we provide spatialized geographic and environmental data as additional input variables (see Figure 1). More precisely, For each species observation location, we provide:\n1. **Satellite image patches**: 3-band (RGB) and 1-band (NIR) 128x128 images at 10m resolution.\n2. **Satellite time series**: Up to 20 years of values for six satellite bands (R, G, B, NIR, SWIR1, and SWIR2).\n3. **Environmental rasters** Various climatic, pedologic, land use, and human footprint variables at the European scale. We provide scalar values, time-series, and original rasters from which you may extract local 2D images.\n\nThere are three separate folders with the relevant data on the Seafile available for training. The detailed description is provided below and again on **SeaFile** in separate \"Readme\" files in relevant folders.\n- The Satellite image patches in `./SatellitePatches/`.\n- The Satellite time series in `./SatelliteTimeSeries/`.\n- The Environmental rasters in `./EnvironmentalRasters/`.\n\n
\n\n**Figure.** Illustration of of the environmental data for an occurrence (glcID=4859165) collected in northern Switzerland (lon=8.5744;lat=47.7704) in 2021. A. The 1280x1280m satellite image patches were sampled in 2021 around the observation. B. Quarterly time series of six satellite bands at the point location since winter 1999-2000. C. Three example bioclimatic images (~65x65km) around the observation were extracted from the provided environmental rasters.\n\n## **Satellite image patches:**\n1280mx1280m RGB and NIR patches (four bands) centered at the observation geolocation and taken the same year. The patches are compressed in two zip files (patchs\\_rgb.zip, patchs\\_nir.zip) accessible in folder /SatelliteImages/.\n* _Format_: 128x128 JPEG images, a color JPEG file for RGB data and a grayscale one for Near-Infrared.\n* _Resolution_: 10 meters per pixel\n* Source: Sentinel2 remote sensing data pre-processed by the [Ecodatacube platform](https://stac.ecodatacube.eu/)\n* _Access_: First, one must download and decompress the provided zip files. Each JPEG file corresponds to a unique observation location (via \"surveyId\"). To load the RGB or NIR patch for a selected observation, take the \"surveyId\" from any occurrence CSV and load it following this rule --> '.../CD/AB/XXXXABCD.jpeg'. For example, the image location for the surveyId 3018575 is \"./75/85/3018575.jpeg\". For all \"surveyId\" with less than four digits, you can use a similar rule. For a \"surveyId\" 1 is \"./1/1.jpeg\".\n\n## **Satellite time series**\nEach observation is associated with the time series of the satellite median point values over each season since the winter of 1999 for six satellite bands (R, G, B, NIR, SWIR1, and SWIR2). This data carries a high-resolution local signature of the past 20 years' succession of seasonal vegetation changes, potential extreme natural events (fires), or land use changes.\n* _Format1_: Six CSV files, one per band. The corresponds to the \"surveyId,\" and the columns are the 84 seasons from winter 2000 until autumn 2020.\n* _Format2_: . TimeSeries-Cubes - The above-mentioned CSV aggregated into 3d tensors with axes as BAND, QUARTER, and YEAR.\n* _Resolution_: The original satellite data has a resolution of 30m per pixel\n* _Source_: Landsat remote sensing data pre-processed by the [Ecodatacube platform](https://stac.ecodatacube.eu/)\n* _Access_: `/SatelliteTimeSeries/`\n\n## **Monthly climatic rasters**\n\nFour climatic variables computed monthly (mean, minimum and maximum temperature, and total precipitation) from January 2000 to December 2019, yielding 960 low-resolution rasters covering Europe.\n\n* _Format1_: CSV files, one per raster referenced through the \"surveyId\".\n* _Format2_: TimeSeries-Cubes - Above mentioned CSV aggregated into 3d tensors with axis as RASTER-TYPE, YEAR, and MONTH.\n* _Resolution_: ~1 kilometer\n* _Source_: [Chelsa](https://chelsa-climate.org/)\n* _Access_: `/EnvironmentalRasters/Climate/Climatic_Monthly_2000-2019`\n\n\n## **Environmental rasters** \nFor each observation, we provide additional environmental data such as GeoTIFF rasters and scalar values already extracted from the rasters. We provide CSV files, one per band raster type, i.e., Climate, Elevation, Human Footprint, LandCover, and SoilGrids.\n\n1. **Bioclimatic rasters**: 19 low-resolution rasters covering Europe; commonly used in species distribution modeling. Provided in longitude/latitude coordinates (WGS84).\n \n - _Format_: GeoTIFF files with compression and CSV file with extracted values.\n - _Resolution_: 30 arcsec (~ 1 kilometer)\n - _Source_: [CHELSA](https://chelsa-climate.org/bioclim/)\n - _Access_: `/EnvironmentalRasters/Climate/BioClimatic_Average_1981-2010`\n\n2. **Soil rasters**: Nine pedologic low-resolution rasters covering Europe. Provided variables describe the soil properties from 5 to 15cm depth and are determinant of plant species distributions. Check the `definition.txt` file about the provided variables (e.g., pH, clay, organic carbon and nitrogen contents, etc.).\n\n - _Format_: GeoTIFF files with compression and CSV file with extracted values.\n - _Resolution_: ~1 kilometer\n - _Source_: [Soilgrids](https://soilgrids.org/)\n - _Access_: `/EnvironmentalRasters/Soilgrids`\n\n3. **Elevation**: High-resolution raster covering Europe.\n\n - _Format_: GeoTIFF file with compression, Int16 numeric storage (13.2GB) and CSV file with extracted values.\n - _Resolution_: 1 arc second (~30 meter)\n - _Source_: [ASTER Global Digital Elevation Model V3](https://lpdaac.usgs.gov/products/astgtmv003/)\n - _Access_: `/EnvironmentalRasters/Elevation`\n\n4. **Land Cover**: A medium-resolution multi-band land cover raster covering Europe. Each band describes either the land cover class prediction or its confidence under various classifications. We recommend the use of IGBP (17 classes) or LCCS (43 classes) layers, often used in species distribution modeling.\n - _Format_: GeoTIFF file with compression and CSV file with extracted values.\n - _Resolution_: ~500m\n - _Source_: [MODIS Terra+Aqua 500m](https://ladsweb.modaps.eosdis.nasa.gov/missions-and-measurements/products/MCD12Q1/#overview)\n - _Access_: `/EnvironmentalRasters/LandCover/`\n\n5. **Humand footprint**: Several low-resolution rasters describing human footprint, encapsulating seven pressures on the environment (e.g., nighlight level, population density) induced by human presence and activity, are provided for two time periods, the early 90's (~1993) and late 2000' (~2009). We provide two summary rasters combining all human pressures and two detailed rasters per pressure, which avoid an arbitrary degradation of the original data.\n\n - _Format_: GeoTIFF files with compression and CSV file with extracted values.\n - _Resolution_: ~1km\n - _Source_: [Venter et al., 2016](https://datadryad.org/stash/dataset/doi:10.5061/dryad.052q5)\n - _Access_: The folder `/EnvironmentalRasters/HumanFootprint/` contains a readme file with detailed information about this data and two subfolders: summarized/ contains the two summary rasters (for 1993 and 2009) and detailed/ contains the 2\\*7 single pressure raster.\n\nData downloading\n================\nAll PA-related data are already provided through Kagle; however, all the original rasters are provided on the Seafile. To download the full dataset, we recommend downloading each group separately using zipped archives.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Competition Description", "content": "Predicting plant species composition and its change in space and time at a fine resolution is useful for many scenarios related to biodiversity management and conservation, improving species identification and inventory tools, and educational purposes.\n\nThis challenge aims to predict plant species in a given location and time using various possible predictors: satellite images and time series, climatic time series, and other rasterized environmental data: land cover, human footprint, bioclimatic, and soil variables.\n\nTo do so, we provide a large-scale training set of about 5M plant occurrences in Europe (single-label, presence-only data) as well as a validation set of about 5K plots and a test set with 20K plots, with all the present species (multi-label, presence-absence data).\n\nThe difficulties of the challenge include multi-label learning from single positive labels, strong class imbalance, multi-modal learning, and large-scale.\n\n![graphical abstract](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F1518097%2F4243b1e3ef9713ebcb27eb0a9614993d%2FGeoLifeCLEF2024.png?generation=1701864222703739&alt=media)", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "## One account per participant\n\nYou cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.\n\n\n## No private sharing outside teams\n\nPrivately sharing code or data outside of teams is not permitted. It is okay to share code if made available to all participants on the forums.\n\n\n## Team Mergers\n\nTeam mergers are allowed and can be performed by the team leader. In order to merge, the combined team must have a total submission count less than or equal to the maximum allowed as of the merge date. The maximum allowed is the number of submissions per day multiplied by the number of days the competition has been running.\n\n## Team Limits\n\nMaximum team size is 5.\n\n\n## Submission Limits\n\nYou may submit a maximum of 3 entries per day. You may select up to 5 final submissions for judging.\n\n\n## Competition Timeline\n\nCompetition Timeline dates are reflected on the competition’s Overview > Timeline page.\n\n\n# COMPETITION-SPECIFIC TERMS\n\nCompetition Name (the 'Competition'): GeoLifeCLEF 2024 - [LifeCLEF 2024](https://www.imageclef.org/LifeCLEF2024) x [FGVC11](https://sites.google.com/view/fgvc11)\n\nCompetition Sponsors: Horizon Europe project [MAMBO](https://www.mambo-project.eu/), [FGVC11](https://sites.google.com/view/fgvc11), [LifeCLEF 2024](https://www.imageclef.org/LifeCLEF2024) and Inria\n\nCompetition Acknowledgements: Alexis Joly, Christophe Botella, Benjamin Deneu, Diego Marcos, Théo Larcher, Joachim Estopinan, César Leblanc, Maximilien Servajean (hosts)\n\nCompetition Website: [Kaggle](https://www.kaggle.com/competitions/geolifeclef-2024/), [LifeCLEF 2024](https://www.imageclef.org/GeoLifeCLEF2024) and [FGVC11](https://sites.google.com/view/fgvc11/competitions/geolifeclef2024)\n\nWorkshop Sponsors: Horizon Europe project [MAMBO](https://www.mambo-project.eu/), COS4CLOUD and Inria (LifeCLEF 2024), Visipedia and Google (FGVC11)\n\n\n## INDIVIDUALS AND TEAMS.\n\nA. Individual Account.\n\nYou may make Submissions only under one, unique Kaggle.com account. You will be disqualified if you make Submissions through more than one Kaggle account, or attempt to falsify an account to act as your proxy. You may submit up to the maximum number of Submissions per day as specified on the Competition Website.\n\nB. Teams.\n\nIf permitted under the Competition Website guidelines, multiple individuals may collaborate as a team (a \"Team\"); however, you may join or form only one Team. Each Team member must be a single individual with a separate Kaggle account. You must register individually for the Competition before joining a Team. You must confirm your Team membership to make it official by responding to the Team notification message sent to your Kaggle account. Team membership may not exceed the Maximum Team Size stated on the Competition Website.\n\nC. Team Merger.\n\nTeams may request to merge via the Competition Website. Team mergers may be allowed provided that: (i) the combined Team does not exceed the Maximum Team Size; (ii) the number of Submissions made by the merging Teams does not exceed the number of Submissions permissible for one Team at the date of the merger request; (iii) the merger is completed before the earlier of: any merger deadline or the Competition deadline; and (iv) the proposed combined Team otherwise meets all the requirements of these Rules.\n\n## External Data.\n\nDo not cheat. \n\nThe general rule is that participants should only use the provided training and validation data for training models to classify the test images. We do not want participants crawling the web in search of additional data. Pretrained models may be used to construct the algorithms from publicly available academic datasets (e.g., ImageNet, GeoLifeCLEF 2020-2022). Please specify any and all external data and/or models used for training when uploading results.\n\nParticipants are allowed to collect additional annotations on the provided training sets. Participants are not allowed to collect annotations on the test set. Teams should specify that they collected additional annotations when submitting results.\n\n## DETERMINING WINNERS.\n\nEach Submission will be scored and ranked by the evaluation metric stated on the Competition Website. During the Competition Period, the current ranking will be visible on the Competition Website's public leaderboard. The potential winner(s) are determined solely by the leaderboard ranking on the private leaderboard, subject to compliance with these Rules. The public leaderboard will be based on the public test set and the private leaderboard will be based on the private test set.\n\nIn the event of a tie, the Submission that was entered first to the Competition will be the winner. In the event a potential winner is disqualified for any reason, the Submission that received the next highest score rank will be chosen as the potential winner.\n\nParticipants are encouraged to register to LifeCLEF 2024 lab and submit a working note describing your methodology to maximize their visibility. This can be done using this form (and checking \"Task 3 - GeoLifeCLEF\" of \"LifeCLEF\" section). This registration is free of charge. This registration will give you the opportunity to present your results to the CLEF community, during the LifeCLEF session of CLEF 2024, if you win the challenge AND submit a working note. By doing so, you are guaranteed that your results will be documented in the vhallenge overvieww publication.\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Motivation", "content": "Predicting the plant species present at a given location is helpful for many biodiversity management and conservation scenarios.\n\nFirst, it allows for building high-resolution maps of species composition and related biodiversity indicators such as species diversity, endangered species, and invasive species. In scientific ecology, the problem is known as Species Distribution Modelling.\n\nMoreover, it could significantly improve the accuracy of species identification tools - such as [Pl@ntNet](https://plantnet.org/) - by reducing the list of candidate species observable at a given site.\n\nMore generally, it could facilitate biodiversity inventories by developing location-based recommendation services (e.g., on mobile phones), encouraging citizen scientist observers' involvement, and accelerating the annotation and validation of species observations to produce large, high-quality data sets.\n\nFinally, this could be used for educational purposes through biodiversity exploration applications with features such as quests or contextualized educational pathways.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Timeline", "content": "- **December 2023**: [Registration opens for all LifeCLEF challenges (free of charge)] (https://clef2024-labs-registration.dei.unipd.it/registrationForm.php)\n- **28 February 2024**: Training and test data release\n- **24 May 2024**: Competition Deadline.\n- **7 June 2024**: Deadline for submission of working note papers [CEUR-WS proceedings].\n- **21 June 2024**: Notification of acceptance - working note papers [CEUR-WS proceedings].\n- **8 July 2024**: Camera-ready deadline for working note papers.\n- **9-12 Sept 2024**: CLEF 2024 Grenoble - France.\n\n_All deadlines are at 11:59 PM CET of the corresponding day unless otherwise stated._ \n\n**The competition organizers reserve the right to update the contest timeline if they deem it necessary.**", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Other Resources", "content": "**Besides this Kaggle page, make sure to check these other resources:**\n- [GLC GitHub](https://github.com/plantnet/GLC) allowing easy access and loading of data.\n- [Malpolon](https://github.com/plantnet/malpolon): A deep learning framework to help participants build their species distribution models.\n- [LifeCLEF 2024 webpage](https://www.imageclef.org/LifeCLEF2024) for more information about LifeCLEF challenges and working notes submission procedure.\n- [FGVC11 page](https://sites.google.com/view/fgvc11) for more information about the FGVC10 workshop.\n- Our protocol note explaining the data sources and procedure used to build the dataset will soon be published and made available on this page, stay tuned.\n- Last editions winning solutions working notes:\n\n + [GeoLifeCLEF 2021 winner, S. Seneviratne](http://ceur-ws.org/Vol-2936/paper-140.pdf)\n + [GeoLifeCLEF 2022 2nd, B. Kellenberg et T. Devis](https://ceur-ws.org/Vol-3180/paper-167.pdf)\n + [GeoLifeCLEF 2023 winner, H.Q. Ung et al.](https://ceur-ws.org/Vol-3497/paper-181.pdf)\n\n- [Overview paper of GeoLifeCLEF 2023](https://ceur-ws.org/Vol-3497/paper-166.pdf).\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "CVPR24 and CLEF24 Context", "content": "**This competition is held jointly as part of:**\n\n- the [LifeCLEF 2024](https://www.imageclef.org/LifeCLEF2024) lab of the [CLEF 2024](http://clef2024.clef-initiative.eu) conference, and of\n- the [FGVC11](https://sites.google.com/view/fgvc11) workshop organized in conjunction with [CVPR 2024](http://cvpr.thecvf.com) conference.
\n\n*Being part of scientific research, the participants are encouraged to participate to both events.\nIn particular, only participants who submitted a working note paper to LifeCLEF (see below) will be part of the officially published ranking used for scientific communication.*\n\n\nFGVC11 at CVPR 2024\n-------------------\n\nThis competition is part of the **Fine-Grained Visual Categorization [FGVC11](https://sites.google.com/view/fgvc11) workshop on the 18th of June** at the Computer Vision and Pattern Recognition Conference [CVPR 2024](http://cvpr.thecvf.com). The task results will be presented at the workshop, and the contribution of the winning team(s) will be highlighted. Attending the workshop is not required to participate in the competition.\n\n**CVPR 2024 will take place in Seattle, USA, on June 17-21, 2024.** \nPLEASE NOTE: CVPR frequently sells out early; we cannot guarantee CVPR registration after the competition's end. If you are interested in attending, please plan ahead.\n\nYou can see a list of the FGVC11 competitions [here](https://sites.google.com/view/fgvc11/competitions).\n\nLifeCLEF 2024 at CLEF 2024\n-------------\n\nLifeCLEF lab is part of the Conference and Labs of the Evaluation Forum ([CLEF](http://www.clef-initiative.eu)). \nCLEF consists of independent peer-reviewed workshops on a broad range of challenges in multilingual and multimodal information access evaluation and benchmarking activities in various labs designed to test different aspects of mono and cross-language Information retrieval systems. \n**CLEF 2024 will take place in Grenoble, France, on September 9-12, 2024.** \nYou can find more details on the [CLEF 2024 website](http://clef2024.clef-initiative.eu).", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "The evaluation metric for this competition is the samples-averaged \\\\(F\\_1\\\\)-score (called F-Score Beta (Micro) on Kaggle) computed on the test set made of species presence-absence (PA) samples. In terms of machine learning, it is a multi-label classification task. The \\\\(F\\_1\\\\)-score is an average measure of overlap between the predicted and actual set of species present at a given location and time. \nEach test PA sample \\\\( i \\\\) is associated with a set of ground-truth labels \\\\( Y\\_i \\\\), namely the set of plant species (=speciesId) associated with a given combination of the columns **patchID** and **dayOfYear** (see the Data tab for details on the species observation data structure). \nFor each sample, the submission will provide a list of labels, i.e. the set of species predicted present \\\\( \\\\widehat{Y}\\_{i,1}, \\\\widehat{Y}\\_{i,2}, \\\\dots, {\\\\widehat{Y}}\\_{i,R\\_i} \\\\). \nThe micro \\\\(F\\_1\\\\)-score is then computed using\n\n\\\\\\[ F\\_1 = \\\\frac{1}{N} \\\\sum\\_{i=1}^N \\\\frac{\\\\text{TP}\\_i}{\\\\text{TP}\\_i+(\\\\text{FP}\\_i+\\\\text{FN}\\_i)/2} \\\\\\\\ \\\\quad \\\\text{Where} \\\\begin{cases} \\\\text{TP}\\_i =\\\\text{ Number of predicted species truly present, i.e. }|\\\\widehat{Y}\\_i \\\\cap Y\\_i |\\\\\\\\ \\\\text{FP}\\_i =\\\\text{ Number of species predicted but absent, i.e. } |\\\\widehat{Y}\\_i \\\\setminus Y\\_i | \\\\\\\\ \\\\text{FN}\\_i =\\\\text{ Number of species not predicted but present, i.e. } | Y\\_i \\\\setminus \\\\widehat{Y}\\_i |\\\\\\\\ \\\\end{cases} \\\\\\]\n\nSubmission Format\n=================\n\nFor each id in the test set, you must predict a set of species that occur at the given location. The file should contain a header and have the following format:\n```\nsurveyId,predictions\n1,1 52 10231\n2,78 201 1243 1333 2310 4841\n...\n```\nThe submission format is a CSV file containing two columns for each sample (row):\n* `surveyId` column containing integers corresponding to the test sample ids, corresponding to unique combinations of patchID and dayOfYear column values.\n* `predictions` column containing space-delimited lists of the predicted species identifiers (column spId in training/validation datasets)\n\n**For each sample (row), the predicted species identifiers must be ordered by increasing the value from left to right. No test sample is empty, and the test set only contains species from the train or validation set.**", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Organizers and contributors", "content": "- Lukas Picek, INRIA, LIRMM, Montpellier \n- Christophe Botella, INRIA, LIRMM, Montpellier \n- Diego Marcos, INRIA , Montpellier \n- Théo Larcher, INRIA, LIRMM, Montpellier \n- Joachim Estopinan, INRIA, LIRMM, Montpellier \n- César Leblanc, INRIA, LIRMM, Montpellier \n- Maximilien Servajean, Université Paul Valéry, LIRMM, Montpellier \n- Alexis Joly, INRIA, LIRMM, Montpellier", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Acknowledgement", "content": "This project has received funding from the European Union’s Horizon Research and Innovation program under grant agreements No. 101060639 (MAMBO project) and No. 101060693 (GUARDEN project).\n\n\n
\n \"MAMBO_logo\"\n \"GUARDEN_logo\"\n \"europ_commission_logo\"\n
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "abstract", "content": "This challenge aims to predict plant species in a given location and time using various possible predictors: satellite images and time series, climatic time series, and other rasterized environmental data: land cover, human footprint, bioclimatic, and soil variables.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }