{"success":true,"data":{"author":"GroundTruth and International Water Management Institute (IWMI), CGIAR Initiative on Digital Innovation","bucketAccessType":"public","bucketName":"CGIAR/aquatic-macroinvertebrate-images","bucketPrefix":"","category":"Environmental Science","cloudProvider":"huggingface","createdAt":"2026-11-17T14:12:17.997Z","description":"A photo dataset of freshwater aquatic macroinvertebrates assembled to train machine-learning models that support the mini Stream Assessment Scoring System (miniSASS), a citizen-science biomonitoring method for scoring the ecological condition of streams and rivers in southern Africa. It holds 1,300 images, one hundred for each of the thirteen miniSASS groups, which are identified at roughly Order level (bugs and beetles, caddisflies, crabs and shrimps, damselflies, dragonflies, flat worms, leeches, minnow mayflies, other mayflies, snails, clams and mussels, stoneflies, true flies, and worms), each of which carries a sensitivity score in the index. Annotation was done by R.C.J. and F.J.K. Koen of North-West University; curation by Nicholas Pattinson of GroundTruth with the International Water Management Institute (IWMI) under the CGIAR Initiative on Digital Innovation. Images sit in one folder per group (for example caddisflies/, stoneflies/, snails_clams_mussels/), so they load as an image-folder classification set with Hugging Face datasets or torchvision. The data accompany the IWMI working paper by Koen et al. (2023), 'Digitally improving the identification of aquatic macroinvertebrates for indices used in biomonitoring' (hdl.handle.net/10568/138246), and are also deposited on Harvard Dataverse (doi:10.7910/DVN/1QQPJ5). Licensed CC BY 4.0.","displayTitle":"Aquatic Macroinvertebrate Images for miniSASS Stream Biomonitoring (13 Groups)","doi":"10.7910/DVN/1QQPJ5","huggingFaceUrl":"https://huggingface.co/datasets/CGIAR/aquatic-macroinvertebrate-images","id":"3f5969a1-b33b-5704-bc7b-a5c078310e9f","license":"CC-BY-4.0","licenseEvidenceUrl":"https://huggingface.co/datasets/CGIAR/aquatic-macroinvertebrate-images","objectCountEstimate":1302,"probeStatus":"ok","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"CGIAR/aquatic-macroinvertebrate-images\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"CGIAR/aquatic-macroinvertebrate-images\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=CGIAR, license:cc-by-4.0, size_categories:1K<n<10K, format:imagefolder, downloads=2729"],"format":"mixed","generatedAt":"2026-11-17T14:23:34.973Z","layout":{"example":"bugs_and_beetles/20220903_133958.jpg","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"bugs_and_beetles/20220903_133958.jpg","truncatedAt":512}],"sampleObjects":["bugs_and_beetles/20220903_133958.jpg","bugs_and_beetles/IMG_0265.JPG","bugs_and_beetles/IMG_0266.JPG","bugs_and_beetles/IMG_2736.JPG","bugs_and_beetles/IMG_2737.JPG"],"sidecars":[{"bytes":"---\nlicense: cc-by-4.0\ntask_categories:\n- image-classification\nlanguage:\n- en\ntags:\n- biology\npretty_name: Aquatic macroinvertebrate images\nsize_categories:\n- 1K<n<10K\nannotations_creators:\n- expert-generated\nsource_datasets:\n- CGIAR\n- International Water Management Institute (IWMI)\n---\n\n# Dataset Card for Aquatic Macroinvertebrate Images\nThis image dataset contains 1,300 photos (one hundred images of each of the thirteen mini stream assessment scoring system, or miniSASS aquatic macroinvertebrate groups), used in the development of machine learning models to automatically assess the water quality score.\n\n### Dataset Description\n\nThis dataset accompanies the working paper, [Digitally improving the identification of aquatic macroinvertebrates for indices used in biomonitoring](https://hdl.handle.net/10568/138246).\n\n> Koen, R. C. J.; Koen, F. J.; Pattinson, N. B.; Dickens, Chris W. S.; Graham, P. M. 2023. Digitally improving the identification of aquatic macroinvertebrates for indices used in biomonitoring. Colombo, Sri Lanka: International Water Management Institute (IWMI). CGIAR Initiative on Digital Innovation. 10p. [https://hdl.handle.net/10568/138246](https://hdl.handle.net/10568/138246)\n\nThe report provides an overview of the mini Stream Assessment Scoring System (miniSASS) and South African Scoring System Version 5 (SASS5) \nas biomonitoring techniques for assessing the ecological condition of streams and rivers based on the identification of aquatic macroinvertebrates. \nWhile miniSASS relies on minimally trained citizen scientists to identify macroinvertebrates at the Order-level, SASS5 utilizes expertly accredited practitioners for finer resolution, even up to the family-level. \nHowever, the reliance on citizen scientists for miniSASS identification introduces limitations in terms of precision, accuracy, and reliability. \nTo address these limitations, ongoing developments within the CGIAR Initiative on Digital Innovation include the creation of a miniSASS smartphone application, \nan upgraded website, an interactive online course, and a machine-learning identification algorithm to assist with photo identification. \nAdditionally, a revised dichotomous key has been developed to improve operator identification during miniSASS surveys. \nThe outcomes of these developments and explorations presented in the paper aim to enhance the overall effectiveness and reliability of both \nthe miniSASS and SASS5 techniques. \nBy leveraging digital innovation and incorporating machine-learning technology, we anticipate the efficiency, accuracy, and accessibility of \nbiomonitoring assessments will significantly improve, ultimately contributing to a better understanding and management of our aquatic ecosystems.\n\n- **Curated by:** Nicholas Pattinson, GroundTruth\n- **Funded by:** CGIAR Initiative on Digital Innovation\n- **Shared by:** Chris Dickens, CGIAR/IWMI\n- **License:** CC-BY-4.0\n\n### Dataset Sources\n- **Repository:** [https://doi.org/10.7910/DVN/1QQPJ5](https://doi.org/10.7910/DVN/1QQPJ5)\n- **Paper:** [https://hdl.handle.net/10568/138246](https://hdl.handle.net/10568/138246)\n- **Demo:** [https://minisass.org](https://minisass.org)\n\n### Source data producers\n* GroundTruth [https://www.groundtruth.co.za](https://www.groundtruth.co.za)\n* Internatoinal Water Management Institute [https://iwmi.org](https://iwmi.org)\n\n### Annotators\n* R.C.J. Koen (North-West University, South Africa)\n* F.J.K Koen (North-West University, South Africa)\n\n### Dataset Card Contact\n* Jawoo Koo, CGIAR/IFPRI","encoding":"utf8","key":"README.md","name":"README.md","size":3528,"truncated":false}],"sourceObjectKey":"bugs_and_beetles/20220903_133958.jpg","starterCell":"from huggingface_hub import hf_hub_download\npath = hf_hub_download(repo_id=\"CGIAR/aquatic-macroinvertebrate-images\", filename=\"bugs_and_beetles/20220903_133958.jpg\", repo_type=\"dataset\")\nprint(path)","starterSamplePath":"bugs_and_beetles/20220903_133958.jpg","totalObjects":1302},"summary":"A photo dataset of freshwater aquatic macroinvertebrates assembled to train machine-learning models that support the mini Stream Assessment Scoring System (miniSASS), a…","title":"Aquatic Macroinvertebrate Images for miniSASS Stream Biomonitoring (13 Groups)","updatedAt":"2026-11-17T20:18:44.009Z","visibility":"public","websiteUrl":"https://minisass.org"}}