{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/the-proper-care-and-feeding-of-camels-how","title":"The Proper Care and Feeding of CAMELS: How Limited Training Data Affects Streamflow Prediction","arxiv_id":"1911.07249","date":"2019-11-17","proceeding":null,"authors":["Martin Gauch","Juliane Mai","Jimmy Lin"],"abstract":"Accurate streamflow prediction largely relies on historical meteorological records and streamflow measurements. For many regions, however, such data are only scarcely available. Facing this problem, many studies simply trained their machine learning models on the region's available data, leaving possible repercussions of this strategy unclear. In this study, we evaluate the sensitivity of tree- and LSTM-based models to limited training data, both in terms of geographic diversity and different time spans. We feed the models meteorological observations disseminated with the CAMELS dataset, and individually restrict the training period length, number of training basins, and input sequence length. We quantify how additional training data improve predictions and how many previous days of forcings we should feed the models to obtain best predictions for each training set size. Further, our findings show that tree- and LSTM-based models provide similarly accurate predictions on small datasets, while LSTMs are superior given more training data.","url_abs":"https://arxiv.org/abs/1911.07249v3","url_pdf":"https://arxiv.org/pdf/1911.07249v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"the-proper-care-and-feeding-of-camels-how","repo_url":"https://github.com/gauchm/ealstm_regional_modeling","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1911.07249","atlas_url":"https://app.syntology.ai/?focus=1911.07249","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.07249"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gauchm/ealstm_regional_modeling","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":14},"by_repo_kind":{"official":{"samples":14,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"1991f7b4961d51bd","entry":"calc_alpha_nse","repo":"gauchm/ealstm_regional_modeling","repo_kind":"official","path":"papercode/metrics.py","file_url":"https://github.com/gauchm/ealstm_regional_modeling/blob/HEAD/papercode/metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1991f7b4961d51bd"}},{"code_sha256_prefix":"12340ba2e594bd55","entry":"calc_beta_nse","repo":"gauchm/ealstm_regional_modeling","repo_kind":"official","path":"papercode/metrics.py","file_url":"https://github.com/gauchm/ealstm_regional_modeling/blob/HEAD/papercode/metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"12340ba2e594bd55"}},{"code_sha256_prefix":"755c08582e820958","entry":"calc_nse","repo":"gauchm/ealstm_regional_modeling","repo_kind":"official","path":"papercode/metrics.py","file_url":"https://github.com/gauchm/ealstm_regional_modeling/blob/HEAD/papercode/metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"755c08582e820958"}},{"code_sha256_prefix":"56d870f7584b3428","entry":"ecdf","repo":"gauchm/ealstm_regional_modeling","repo_kind":"official","path":"papercode/plotutils.py","file_url":"https://github.com/gauchm/ealstm_regional_modeling/blob/HEAD/papercode/plotutils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"56d870f7584b3428"}},{"code_sha256_prefix":"040feb3b499435ae","entry":"get_clusters","repo":"gauchm/ealstm_regional_modeling","repo_kind":"official","path":"papercode/clusterutils.py","file_url":"https://github.com/gauchm/ealstm_regional_modeling/blob/HEAD/papercode/clusterutils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"040feb3b499435ae"}},{"code_sha256_prefix":"1a855e3ea0dd9718","entry":"get_label_2_color","repo":"gauchm/ealstm_regional_modeling","repo_kind":"official","path":"papercode/clusterutils.py","file_url":"https://github.com/gauchm/ealstm_regional_modeling/blob/HEAD/papercode/clusterutils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1a855e3ea0dd9718"}},{"code_sha256_prefix":"7a44dc282997b5eb","entry":"get_morris_gradient","repo":"gauchm/ealstm_regional_modeling","repo_kind":"official","path":"papercode/morris.py","file_url":"https://github.com/gauchm/ealstm_regional_modeling/blob/HEAD/papercode/morris.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7a44dc282997b5eb"}},{"code_sha256_prefix":"4c446d543ab69d8f","entry":"get_run_dirs","repo":"gauchm/ealstm_regional_modeling","repo_kind":"official","path":"papercode/evalutils.py","file_url":"https://github.com/gauchm/ealstm_regional_modeling/blob/HEAD/papercode/evalutils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4c446d543ab69d8f"}},{"code_sha256_prefix":"ecbb2deb80bb3950","entry":"get_run_dirs_gridEvaluation","repo":"gauchm/ealstm_regional_modeling","repo_kind":"official","path":"papercode/evalutils.py","file_url":"https://github.com/gauchm/ealstm_regional_modeling/blob/HEAD/papercode/evalutils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ecbb2deb80bb3950"}},{"code_sha256_prefix":"f48dd78c80f393e6","entry":"get_shape_collections","repo":"gauchm/ealstm_regional_modeling","repo_kind":"official","path":"papercode/plotutils.py","file_url":"https://github.com/gauchm/ealstm_regional_modeling/blob/HEAD/papercode/plotutils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f48dd78c80f393e6"}},{"code_sha256_prefix":"938143c5ecc5641d","entry":"get_silhouette_scores","repo":"gauchm/ealstm_regional_modeling","repo_kind":"official","path":"papercode/clusterutils.py","file_url":"https://github.com/gauchm/ealstm_regional_modeling/blob/HEAD/papercode/clusterutils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"938143c5ecc5641d"}},{"code_sha256_prefix":"0d729ca958fc0d3a","entry":"load_attributes","repo":"gauchm/ealstm_regional_modeling","repo_kind":"official","path":"papercode/datautils.py","file_url":"https://github.com/gauchm/ealstm_regional_modeling/blob/HEAD/papercode/datautils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0d729ca958fc0d3a"}},{"code_sha256_prefix":"c37a05f06f05d465","entry":"normalize_features","repo":"gauchm/ealstm_regional_modeling","repo_kind":"official","path":"papercode/datautils.py","file_url":"https://github.com/gauchm/ealstm_regional_modeling/blob/HEAD/papercode/datautils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c37a05f06f05d465"}},{"code_sha256_prefix":"b62b4383d90e0390","entry":"rescale_features","repo":"gauchm/ealstm_regional_modeling","repo_kind":"official","path":"papercode/datautils.py","file_url":"https://github.com/gauchm/ealstm_regional_modeling/blob/HEAD/papercode/datautils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b62b4383d90e0390"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}