| f | { | f | { |
| "agreement": "true", | | "agreement": "true", |
| n | "author": "Water Research Observatory", | n | "alternative_identifier": "10.2166/hydro.2024.268", |
| | | "author": null, |
| "author_email": null, | | "author_email": null, |
| "authors": [ | | "authors": [ |
| { | | { |
| n | "author_department": "Admin", | n | "author_department": "Department of Plant and Soil Sciences", |
| | | "author_email": "ceschutte34@gmail.com", |
| | | "author_name": "Christiaan ", |
| | | "author_organization": "University of Pretoria", |
| | | "author_surname": "Schutte", |
| | | "contact_same_as_author": "True" |
| | | }, |
| | | { |
| | | "author_department": "Department of Plant and Soil Sciences", |
| "author_email": "vanderLaanM@arc.agric.za", | | "author_email": "vanderLaanM@arc.agric.za", |
| n | "author_name": "Water Research Observatory", | n | "author_name": "Michael", |
| "author_organization": "Water Research Observatory", | | "author_organization": "University of Pretoria", |
| | | "author_surname": "van der Laan" |
| | | }, |
| | | { |
| | | "author_department": "Department of Geography, Geoinformatics |
| | | and Meteorology", |
| | | "author_email": "barend.vandermerwe@up.ac.za", |
| "author_surname": "Admin", | | "author_name": "Barend", |
| "contact_same_as_author": true | | "author_organization": "University of Pretoria", |
| | | "author_surname": "van der Merwe" |
| | | } |
| | | ], |
| | | "citation_title": "SCHUTTE C, VAN DER LAAN M and VAN DER MERWE B |
| | | (2024) Leveraging historic streamflow and weather data with deep |
| | | learning for enhanced streamflow predictions. Journal of |
| | | Hydroinformatics 26 (4) 835. http://doi.org/10.2166/hydro.2024.268.", |
| | | "contact_person": [ |
| | | { |
| | | "contact_department": "Department of Plant and Soil Sciences", |
| | | "contact_email": "ceschutte34@gmail.com", |
| | | "contact_name": "Christiaan ", |
| | | "contact_orgnization": "University of Pretoria" |
| } | | } |
| ], | | ], |
| "creator_user_id": "fa7af5b8-32a7-4df0-90a7-c49fbefb1fbd", | | "creator_user_id": "fa7af5b8-32a7-4df0-90a7-c49fbefb1fbd", |
| "data_classification": "time series", | | "data_classification": "time series", |
| "data_collection_organization": "Water Research Observatory", | | "data_collection_organization": "Water Research Observatory", |
| n | | n | "data_reference_date": [ |
| | | { |
| | | "data_reference_date_from": "1979-10-01", |
| | | "data_reference_date_to": "2002-02-22" |
| | | } |
| | | ], |
| "data_structure_category": "structured", | | "data_structure_category": "structured", |
| n | | n | "dataset_language": "English", |
| | | "dataset_license_url": " |
| | | https://creativecommons.org/licenses/by-sa/4.0/", |
| "did_author_or_contact_organization_collect_the_data": "false", | | "did_author_or_contact_organization_collect_the_data": "false", |
| "email": "vanderLaanM@arc.agric.za", | | "email": "vanderLaanM@arc.agric.za", |
| n | "extras": [ | n | |
| { | | |
| "key": "Dataset language", | | |
| "value": "English" | | |
| }, | | |
| { | | |
| "key": "topic", | | |
| "value": "hydrological_data_and_modelling" | | |
| } | | |
| ], | | |
| "groups": [], | | "groups": [], |
| "id": "4d7601c4-5742-4e9c-93c6-73f8e5814dd8", | | "id": "4d7601c4-5742-4e9c-93c6-73f8e5814dd8", |
| "isopen": false, | | "isopen": false, |
| n | "keywords": "hydrological_data_and_modelling", | n | "keywords": "GRU, LSTM, rainfall-runoff modelling, streamflow |
| | | prediction, deep learning, Steelpoort River, Olifants basin, CHIRPS, |
| | | NASA POWER, ARC", |
| "license": "Open (Creative Commons)", | | "license": "Open (Creative Commons)", |
| "license_id": null, | | "license_id": null, |
| "license_title": null, | | "license_title": null, |
| n | "maintainer": "Water Research Observatory", | n | "maintainer": null, |
| "maintainer_email": "vanderLaanM@arc.agric.za", | | "maintainer_email": null, |
| "metadata_created": "2025-10-22T11:55:59.470668", | | "metadata_created": "2025-10-22T11:55:59.470668", |
| n | "metadata_modified": "2025-11-11T08:47:16.270749", | n | "metadata_modified": "2026-02-19T10:13:40.893471", |
| | | "minimum_maximum_extent": [ |
| | | { |
| | | "maximum_vertical_extent": "2263", |
| | | "minimum_vertical_extent": "1336" |
| | | } |
| | | ], |
| "name": "deep-learning-for-streamflow-prediction-project-data", | | "name": "deep-learning-for-streamflow-prediction-project-data", |
| n | "notes": "Auto-imported dataset for | n | "notes": "This study evaluates deep learning methods for daily |
| deep-learning-for-streamflow-prediction-project-data", | | streamflow prediction in data-scarce contexts, using two headwater |
| | | catchments of the Steelpoort River (Olifants River basin, South |
| | | Africa) as case studies. Gated Recurrent Unit (GRU) and Long |
| | | Short-Term Memory (LSTM) networks are trained using daily rainfall and |
| | | temperature data, together with historic streamflow in an |
| | | autoregressive manner. The approach incorporates predicted streamflow |
| | | values into the look-back window to generate continuous predictions |
| | | across the testing period, enabling both gap-filling and short-term |
| | | forecasting. To ensure physically consistent outputs, the authors |
| | | modify standard GRU/LSTM architectures by (i) changing the activation |
| | | function in the final hidden layer and (ii) applying a non-negative |
| | | constraint in the dense layer to prevent negative streamflow |
| | | simulations. Weather inputs are sourced from (1) an ARC station record |
| | | and (2) gridded products (CHIRPS rainfall and NASA POWER/NASAP |
| | | variables), combined with DWS streamflow data from gauging stations |
| | | B4H007 and B4H001. Training spans 1 Oct 1979\u201330 Sep 1997 and |
| | | testing spans 1 Oct 1997\u201322 Feb 2002. Results show that models |
| | | using ARC station data achieve reliable predictions, while models |
| | | using gridded datasets provide moderately accurate predictions, |
| | | indicating potential for low-cost streamflow estimation where gauges |
| | | are inactive or incomplete. The work contributes a practical method |
| | | for southern Africa where monitoring networks have declined.", |
| "num_resources": 4, | | "num_resources": 4, |
| "num_tags": 0, | | "num_tags": 0, |
| "organization": { | | "organization": { |
| "approval_status": "approved", | | "approval_status": "approved", |
| "created": "2025-10-13T09:33:45.492986", | | "created": "2025-10-13T09:33:45.492986", |
| "description": "", | | "description": "", |
| "id": "5bb446d5-d272-4b69-9a6d-79733926291a", | | "id": "5bb446d5-d272-4b69-9a6d-79733926291a", |
| n | "image_url": "", | n | "image_url": "2025-11-17-153438.690384CWR-square.JPG", |
| "is_organization": true, | | "is_organization": true, |
| "name": "wro", | | "name": "wro", |
| "state": "active", | | "state": "active", |
| "title": "Water Research Observatory", | | "title": "Water Research Observatory", |
| "type": "organization" | | "type": "organization" |
| }, | | }, |
| "owner_org": "5bb446d5-d272-4b69-9a6d-79733926291a", | | "owner_org": "5bb446d5-d272-4b69-9a6d-79733926291a", |
| "private": false, | | "private": false, |
| n | "publication_date": "2025-10-22", | n | "publication_date": "2024-02-28", |
| "publisher": "Water Research Observatory", | | "publisher": "Journal of Hydroinformatics", |
| "relationships_as_object": [], | | "relationships_as_object": [], |
| "relationships_as_subject": [], | | "relationships_as_subject": [], |
| "resources": [ | | "resources": [ |
| { | | { |
| "cache_last_updated": null, | | "cache_last_updated": null, |
| "cache_url": null, | | "cache_url": null, |
| "created": "2025-10-22T11:55:59.688311", | | "created": "2025-10-22T11:55:59.688311", |
| "description": null, | | "description": null, |
| "format": "zip", | | "format": "zip", |
| "hash": "", | | "hash": "", |
| "id": "b865b864-11ed-4ba0-9a99-131e95cc7af1", | | "id": "b865b864-11ed-4ba0-9a99-131e95cc7af1", |
| "is_data_supplementary": "False", | | "is_data_supplementary": "False", |
| "last_modified": "2025-10-22T11:55:59.659251", | | "last_modified": "2025-10-22T11:55:59.659251", |
| "metadata_modified": "2025-10-22T11:55:59.681498", | | "metadata_modified": "2025-10-22T11:55:59.681498", |
| "mimetype": "application/zip", | | "mimetype": "application/zip", |
| "mimetype_inner": null, | | "mimetype_inner": null, |
| "name": "Data_and_Code-8669.zip", | | "name": "Data_and_Code-8669.zip", |
| "package_id": "4d7601c4-5742-4e9c-93c6-73f8e5814dd8", | | "package_id": "4d7601c4-5742-4e9c-93c6-73f8e5814dd8", |
| "position": 0, | | "position": 0, |
| "resource_type": null, | | "resource_type": null, |
| "size": 182163782, | | "size": 182163782, |
| "state": "active", | | "state": "active", |
| "url": | | "url": |
| b865b864-11ed-4ba0-9a99-131e95cc7af1/download/data_and_code-8669.zip", | | b865b864-11ed-4ba0-9a99-131e95cc7af1/download/data_and_code-8669.zip", |
| "url_type": "upload", | | "url_type": "upload", |
| "zipped_file": "False" | | "zipped_file": "False" |
| }, | | }, |
| { | | { |
| "cache_last_updated": null, | | "cache_last_updated": null, |
| "cache_url": null, | | "cache_url": null, |
| "created": "2025-10-22T11:56:00.990793", | | "created": "2025-10-22T11:56:00.990793", |
| "description": null, | | "description": null, |
| "format": "zip", | | "format": "zip", |
| "hash": "", | | "hash": "", |
| "id": "1ffcc4b6-01d5-4d53-9370-5ddd3d65b96b", | | "id": "1ffcc4b6-01d5-4d53-9370-5ddd3d65b96b", |
| "is_data_supplementary": "False", | | "is_data_supplementary": "False", |
| "last_modified": "2025-10-22T11:56:00.951126", | | "last_modified": "2025-10-22T11:56:00.951126", |
| "metadata_modified": "2025-10-22T11:56:00.986798", | | "metadata_modified": "2025-10-22T11:56:00.986798", |
| "mimetype": "application/zip", | | "mimetype": "application/zip", |
| "mimetype_inner": null, | | "mimetype_inner": null, |
| "name": "Data_and_Code/CatchmentA.zip", | | "name": "Data_and_Code/CatchmentA.zip", |
| "package_id": "4d7601c4-5742-4e9c-93c6-73f8e5814dd8", | | "package_id": "4d7601c4-5742-4e9c-93c6-73f8e5814dd8", |
| "position": 1, | | "position": 1, |
| "resource_type": null, | | "resource_type": null, |
| "size": 90861991, | | "size": 90861991, |
| "state": "active", | | "state": "active", |
| "url": | | "url": |
| esource/1ffcc4b6-01d5-4d53-9370-5ddd3d65b96b/download/catchmenta.zip", | | esource/1ffcc4b6-01d5-4d53-9370-5ddd3d65b96b/download/catchmenta.zip", |
| "url_type": "upload", | | "url_type": "upload", |
| "zipped_file": "False" | | "zipped_file": "False" |
| }, | | }, |
| { | | { |
| "cache_last_updated": null, | | "cache_last_updated": null, |
| "cache_url": null, | | "cache_url": null, |
| "created": "2025-10-22T11:56:01.279738", | | "created": "2025-10-22T11:56:01.279738", |
| "description": null, | | "description": null, |
| "format": "txt", | | "format": "txt", |
| "hash": "", | | "hash": "", |
| "id": "7b2380d0-2694-483c-99b8-215c25efd391", | | "id": "7b2380d0-2694-483c-99b8-215c25efd391", |
| "is_data_supplementary": "False", | | "is_data_supplementary": "False", |
| "last_modified": "2025-10-22T11:56:01.244307", | | "last_modified": "2025-10-22T11:56:01.244307", |
| "metadata_modified": "2025-10-22T11:56:01.272033", | | "metadata_modified": "2025-10-22T11:56:01.272033", |
| "mimetype": "text/plain", | | "mimetype": "text/plain", |
| "mimetype_inner": null, | | "mimetype_inner": null, |
| "name": "Data_and_Code/readMe.txt", | | "name": "Data_and_Code/readMe.txt", |
| "package_id": "4d7601c4-5742-4e9c-93c6-73f8e5814dd8", | | "package_id": "4d7601c4-5742-4e9c-93c6-73f8e5814dd8", |
| "position": 2, | | "position": 2, |
| "resource_type": null, | | "resource_type": null, |
| "size": 2437, | | "size": 2437, |
| "state": "active", | | "state": "active", |
| "url": | | "url": |
| d8/resource/7b2380d0-2694-483c-99b8-215c25efd391/download/readme.txt", | | d8/resource/7b2380d0-2694-483c-99b8-215c25efd391/download/readme.txt", |
| "url_type": "upload", | | "url_type": "upload", |
| "zipped_file": "False" | | "zipped_file": "False" |
| }, | | }, |
| { | | { |
| "cache_last_updated": null, | | "cache_last_updated": null, |
| "cache_url": null, | | "cache_url": null, |
| "created": "2025-10-22T11:56:01.522228", | | "created": "2025-10-22T11:56:01.522228", |
| "description": null, | | "description": null, |
| "format": "zip", | | "format": "zip", |
| "hash": "", | | "hash": "", |
| "id": "fce0c251-7c53-4b34-9183-5705dfd7e59c", | | "id": "fce0c251-7c53-4b34-9183-5705dfd7e59c", |
| "is_data_supplementary": "False", | | "is_data_supplementary": "False", |
| "last_modified": "2025-10-22T11:56:01.481064", | | "last_modified": "2025-10-22T11:56:01.481064", |
| "metadata_modified": "2025-10-22T11:56:01.517435", | | "metadata_modified": "2025-10-22T11:56:01.517435", |
| "mimetype": "application/zip", | | "mimetype": "application/zip", |
| "mimetype_inner": null, | | "mimetype_inner": null, |
| "name": "Data_and_Code/CatchmentB.zip", | | "name": "Data_and_Code/CatchmentB.zip", |
| "package_id": "4d7601c4-5742-4e9c-93c6-73f8e5814dd8", | | "package_id": "4d7601c4-5742-4e9c-93c6-73f8e5814dd8", |
| "position": 3, | | "position": 3, |
| "resource_type": null, | | "resource_type": null, |
| "size": 91300326, | | "size": 91300326, |
| "state": "active", | | "state": "active", |
| "url": | | "url": |
| esource/fce0c251-7c53-4b34-9183-5705dfd7e59c/download/catchmentb.zip", | | esource/fce0c251-7c53-4b34-9183-5705dfd7e59c/download/catchmentb.zip", |
| "url_type": "upload", | | "url_type": "upload", |
| "zipped_file": "False" | | "zipped_file": "False" |
| } | | } |
| ], | | ], |
| n | | n | "spatial": "{\"type\": \"Polygon\", \"coordinates\": [[[30.1, |
| | | -24.65], [30.7, -24.65], [30.7, -25.3], [30.1, -25.3], [30.1, |
| | | -24.65]]]}", |
| "state": "active", | | "state": "active", |
| "tags": [], | | "tags": [], |
| n | "title": "Deep Learning For Streamflow Prediction Project Data", | n | "title": "Leveraging historic streamflow and weather data with deep |
| | | learning for enhanced streamflow predictions", |
| "type": "dataset", | | "type": "dataset", |
| "uploader_estimation_of_extent_of_processing": "access", | | "uploader_estimation_of_extent_of_processing": "access", |
| "url": null, | | "url": null, |
| "version": null, | | "version": null, |
| t | | t | "vertical_extent_datum": "masl", |
| | | "wrc_project_number": "WRC Project C2020/2021-00440", |
| "wro_theme": "Hydrology" | | "wro_theme": "streamflow" |
| } | | } |