| c |
<flask.g of 'ckan.config.middleware.flask_app'> |
| current_resource_view |
None |
| dataset_type |
'metadata-form' |
| g |
<flask.g of 'ckan.config.middleware.flask_app'> |
| h |
{'redirect_to': <function redirect_to at 0x7faf60f7c5e0>, 'url': <function url at 0x7faf60f7c700>, 'get_site_protocol_and_host': <function get_site_protocol_and_host at 0x7faf60f7c670>, 'url_for': <function url_for at 0x7faf60f7c8b0>, 'url_for_static': <function url_for_static at 0x7faf60f7ca60>, 'url_for_static_or_external': <function url_for_static_or_external at 0x7faf60f7caf0>, 'is_url': <function is_url at 0x7faf60f7cb80>, 'url_is_local': <function url_is_local at 0x7faf60f7cca0>, 'full_current_url': <function full_current_url at 0x7faf60f7cd30>, 'current_url': <function current_url at 0x7faf60f7cdc0>, 'lang': <function lang at 0x7faf60f7ce50>, 'ckan_version': <function ckan_version at 0x7faf60f7cee0>, 'lang_native_name': <function lang_native_name at 0x7faf60f7cf70>, 'is_rtl_language': <function is_rtl_language at 0x7faf60f7d040>, 'get_rtl_css': <function get_rtl_css at 0x7faf60f7d0d0>, 'flash_notice': <function flash_notice at 0x7faf60f7d160>, 'flash_error': <function flash_error at 0x7faf60f7d5e0>, 'flash_success': <function flash_success at 0x7faf60f7d670>, 'are_there_flash_messages': <function are_there_flash_messages at 0x7faf60f7d700>, 'link_to': <function link_to at 0x7faf60f7db80>, 'file': <function file at 0x7faf60f7dc10>, 'submit': <function submit at 0x7faf60f7dca0>, 'nav_link': <function nav_link at 0x7faf60f7dd30>, 'wrapped': <function deprecated.<locals>.decorator.<locals>.wrapped at 0x7faf60efeca0>, 'build_nav_main': <function build_nav_main at 0x7faf60f7dee0>, 'build_nav_icon': <function build_nav_icon at 0x7faf60efe310>, 'build_nav': <function build_nav at 0x7faf60efe3a0>, 'build_extra_admin_nav': <function build_extra_admin_nav at 0x7faf60efe4c0>, 'default_group_type': <function default_group_type at 0x7faf60efe5e0>, 'get_facet_items_dict': <function get_facet_items_dict at 0x7faf60efe670>, 'has_more_facets': <function has_more_facets at 0x7faf60efe700>, 'unselected_facet_items': <function unselected_facet_items at 0x7faf60efe790>, 'get_param_int': <function get_param_int at 0x7faf60efe820>, 'sorted_extras': <function sorted_extras at 0x7faf60efea60>, 'check_access': <function check_access at 0x7faf60efeaf0>, 'linked_user': <function linked_user at 0x7faf60efeb80>, 'group_name_to_title': <function group_name_to_title at 0x7faf60efed30>, 'truncate': <function truncate at 0x7faf60efedc0>, 'markdown_extract': <function markdown_extract at 0x7faf60efee50>, 'icon_url': <function icon_url at 0x7faf60efeee0>, 'icon_html': <function icon_html at 0x7faf60efef70>, 'icon': <function icon at 0x7faf60eff040>, 'resource_icon': <function resource_icon at 0x7faf60eff0d0>, 'format_icon': <function format_icon at 0x7faf60eff160>, 'dict_list_reduce': <function dict_list_reduce at 0x7faf60eff1f0>, 'gravatar': <function gravatar at 0x7faf60eff280>, 'sanitize_url': <function sanitize_url at 0x7faf60eff310>, 'user_image': <function user_image at 0x7faf60eff3a0>, 'pager_url': <function pager_url at 0x7faf60eff430>, 'get_page_number': <function get_page_number at 0x7faf60eff4c0>, 'get_display_timezone': <function get_display_timezone at 0x7faf60eff550>, 'render_datetime': <function render_datetime at 0x7faf60eff5e0>, 'date_str_to_datetime': <function date_str_to_datetime at 0x7faf60eff670>, 'parse_rfc_2822_date': <function parse_rfc_2822_date at 0x7faf60eff700>, 'time_ago_from_timestamp': <function time_ago_from_timestamp at 0x7faf60eff790>, 'button_attr': <function button_attr at 0x7faf60effa60>, 'dataset_display_name': <function dataset_display_name at 0x7faf60effaf0>, 'dataset_link': <function dataset_link at 0x7faf60effb80>, 'resource_display_name': <function resource_display_name at 0x7faf60effc10>, 'resource_link': <function resource_link at 0x7faf60effca0>, 'tag_link': <function tag_link at 0x7faf60effd30>, 'group_link': <function group_link at 0x7faf60effdc0>, 'organization_link': <function organization_link at 0x7faf60effe50>, 'dump_json': <function dump_json at 0x7faf60effee0>, 'auto_log_message': <function auto_log_message at 0x7faf60efff70>, 'activity_div': <function activity_div at 0x7faf60f01040>, 'snippet': <function snippet at 0x7faf60f010d0>, 'convert_to_dict': <function convert_to_dict at 0x7faf60f01160>, 'follow_button': <function follow_button at 0x7faf60f011f0>, 'follow_count': <function follow_count at 0x7faf60f01280>, 'add_url_param': <function add_url_param at 0x7faf60f013a0>, 'remove_url_param': <function remove_url_param at 0x7faf60f01430>, 'include_resource': <function include_resource at 0x7faf60f014c0>, 'urls_for_resource': <function urls_for_resource at 0x7faf60f01550>, 'debug_inspect': <function debug_inspect at 0x7faf60f015e0>, 'popular': <function popular at 0x7faf60f01670>, 'groups_available': <function groups_available at 0x7faf60f01700>, 'organizations_available': <function organizations_available at 0x7faf60f01790>, 'roles_translated': <function roles_translated at 0x7faf60f01820>, 'user_in_org_or_group': <function user_in_org_or_group at 0x7faf60f018b0>, 'dashboard_activity_stream': <function dashboard_activity_stream at 0x7faf60f01940>, 'recently_changed_packages_activity_stream': <function recently_changed_packages_activity_stream at 0x7faf60f019d0>, 'escape_js': <function escape_js at 0x7faf60f01a60>, 'get_pkg_dict_extra': <function get_pkg_dict_extra at 0x7faf60f01af0>, 'get_request_param': <function get_request_param at 0x7faf60f01b80>, 'html_auto_link': <function html_auto_link at 0x7faf60f01c10>, 'render_markdown': <function render_markdown at 0x7faf60f01ca0>, 'format_resource_items': <function format_resource_items at 0x7faf60f01d30>, 'resource_preview': <function resource_preview at 0x7faf60f01dc0>, 'get_allowed_view_types': <function get_allowed_view_types at 0x7faf60f01e50>, 'rendered_resource_view': <function rendered_resource_view at 0x7faf60f01ee0>, 'view_resource_url': <function view_resource_url at 0x7faf60f01f70>, 'resource_view_is_filterable': <function resource_view_is_filterable at 0x7faf60f03040>, 'resource_view_get_fields': <function resource_view_get_fields at 0x7faf60f030d0>, 'resource_view_is_iframed': <function resource_view_is_iframed at 0x7faf60f03160>, 'resource_view_icon': <function resource_view_icon at 0x7faf60f031f0>, 'resource_view_display_preview': <function resource_view_display_preview at 0x7faf60f03280>, 'resource_view_full_page': <function resource_view_full_page at 0x7faf60f03310>, 'remove_linebreaks': <function remove_linebreaks at 0x7faf60f033a0>, 'list_dict_filter': <function list_dict_filter at 0x7faf60f03430>, 'SI_number_span': <function SI_number_span at 0x7faf60f034c0>, 'new_activities': <function new_activities at 0x7faf60f03550>, 'uploads_enabled': <function uploads_enabled at 0x7faf60f035e0>, 'get_featured_organizations': <function get_featured_organizations at 0x7faf60f03670>, 'get_featured_groups': <function get_featured_groups at 0x7faf60f03700>, 'featured_group_org': <function featured_group_org at 0x7faf60f03790>, 'get_site_statistics': <function get_site_statistics at 0x7faf60f03820>, 'resource_formats': <function resource_formats at 0x7faf60f038b0>, 'unified_resource_format': <function unified_resource_format at 0x7faf60f03940>, 'check_config_permission': <function check_config_permission at 0x7faf60f039d0>, 'get_organization': <function get_organization at 0x7faf60f03a60>, 'license_options': <function license_options at 0x7faf60f03af0>, 'get_translated': <function get_translated at 0x7faf60f03b80>, 'facets': <function facets at 0x7faf60f03c10>, 'mail_to': <function mail_to at 0x7faf60f03ca0>, 'radio': <function radio at 0x7faf60f03d30>, 'clean_html': <function clean_html at 0x7faf60f03dc0>, 'flash': <ckan.lib.helpers._Flash object at 0x7faf61090e50>, 'localised_number': <function localised_number at 0x7faf61066c10>, 'localised_SI_number': <function localised_SI_number at 0x7faf61066d30>, 'localised_nice_date': <function localised_nice_date at 0x7faf61066b80>, 'localised_filesize': <function localised_filesize at 0x7faf61066ca0>, 'get_available_locales': <function get_available_locales at 0x7faf6231aca0>, 'get_locales_dict': <function get_locales_dict at 0x7faf6231ac10>, 'literal': <class 'ckan.lib.helpers.literal'>, 'asbool': <function asbool at 0x7faf6299fa60>, 'urlencode': <function urlencode at 0x7faf639dda60>, 'include_asset': <function include_asset at 0x7faf60f7c0d0>, 'render_assets': <function render_assets at 0x7faf60f7c1f0>, 'sanitize_id': <function sanitize_id at 0x7faf60f03ee0>, 'compare_pkg_dicts': <function compare_pkg_dicts at 0x7faf60f03f70>, 'activity_list_select': <function activity_list_select at 0x7faf60f04040>, 'get_collaborators': <function get_collaborators at 0x7faf60f040d0>, 'can_update_owner_org': <function can_update_owner_org at 0x7faf60f04160>, 'parse_cloud_tabular_data': <function parse_cloud_tabular_data at 0x7faf5083d310>, 'get_data': <function make_query at 0x7faf4b7cb700>, 'get_spatial_data': <function make_spatial_query at 0x7faf488ab0d0>, 'get_reference_date': <function get_reference_date at 0x7faf4841b5e0>, 'get_responsible_party': <function get_responsible_party at 0x7faf4841b670>, 'get_common_map_config': <function get_common_map_config at 0x7faf4841b700>, 'package_list_for_source': <function package_list_for_source at 0x7faf4841b9d0>, 'package_count_for_source': <function package_count_for_source at 0x7faf4841ba60>, 'harvesters_info': <function harvesters_info at 0x7faf4841baf0>, 'harvester_types': <function harvester_types at 0x7faf4841bb80>, 'harvest_frequencies': <function harvest_frequencies at 0x7faf4841bc10>, 'link_for_harvest_object': <function link_for_harvest_object at 0x7faf4841bca0>, 'harvest_source_extra_fields': <function harvest_source_extra_fields at 0x7faf4841bd30>, 'bootstrap_version': <function bootstrap_version at 0x7faf4841bdc0>, 'get_harvest_source': <function get_harvest_source at 0x7faf4841b820>, 'get_bigquery_table_name': <function get_bigquery_table_name at 0x7faf5083d0d0>, 'get_package_name': <function get_package_name at 0x7faf5083d160>, 'convert_geojson_to_bbox': <function convert_geojson_to_bbox at 0x7faf50824ca0>, 'get_default_bounding_box': <function get_default_bounding_box at 0x7faf524654c0>, 'resource_read_helper': <function resource_read_helper at 0x7faf5083d1f0>, 'get_package_count': <function get_packages_count at 0x7faf5083d4c0>, 'get_org_count': <function get_organizations_count at 0x7faf5083d550>, 'get_default_spatial_search_extent': <function get_default_spatial_search_extent at 0x7faf5f4f93a0>, 'scheming_language_text': <function scheming_language_text at 0x7faf5074fca0>, 'scheming_field_choices': <function scheming_field_choices at 0x7faf5074fee0>, 'scheming_choices_label': <function scheming_choices_label at 0x7faf5074ff70>, 'scheming_datastore_choices': <function scheming_datastore_choices at 0x7faf506d4040>, 'scheming_field_required': <function scheming_field_required at 0x7faf506d40d0>, 'scheming_dataset_schemas': <function scheming_dataset_schemas at 0x7faf506d4160>, 'scheming_get_presets': <function scheming_get_presets at 0x7faf506d41f0>, 'scheming_get_preset': <function scheming_get_preset at 0x7faf506d4280>, 'scheming_get_dataset_schema': <function scheming_get_dataset_schema at 0x7faf506d4310>, 'scheming_group_schemas': <function scheming_group_schemas at 0x7faf506d43a0>, 'scheming_get_group_schema': <function scheming_get_group_schema at 0x7faf506d4430>, 'scheming_organization_schemas': <function scheming_organization_schemas at 0x7faf506d44c0>, 'scheming_get_organization_schema': <function scheming_get_organization_schema at 0x7faf506d4550>, 'scheming_get_schema': <function scheming_get_schema at 0x7faf506d45e0>, 'scheming_field_by_name': <function scheming_field_by_name at 0x7faf506d4670>, 'scheming_datetime_to_utc': <function scheming_datetime_to_utc at 0x7faf506d4790>, 'scheming_datetime_to_tz': <function scheming_datetime_to_tz at 0x7faf506d4820>, 'scheming_get_timezones': <function scheming_get_timezones at 0x7faf506d48b0>, 'scheming_display_json_value': <function scheming_display_json_value at 0x7faf506d4940>, 'scheming_render_from_string': <function scheming_render_from_string at 0x7faf506d49d0>, 'scheming_flatten_subfield': <function scheming_flatten_subfield at 0x7faf506d4a60>, 'datastore_dictionary': <function datastore_dictionary at 0x7faf507b2ca0>, 'get_map_config': <function get_mapview_config at 0x7faf50850430>, 'get_dataproxy_url': <function get_dataproxy_url at 0x7faf508504c0>} |
| is_activity_archive |
False |
| package |
{'agreement': 'true', 'alternative_identifier': 'https://doi.org/10.2166/hydro.2024.268', 'author': None, 'author_email': None, 'citation_title': 'Schutte, C., Van der Laan, M., & Van der Merwe, B. (2024). Leveraging historic streamflow and weather data with deep learning for enhanced streamflow predictions. Journal of Hydroinformatics.', 'creator_user_id': '7ceb61ee-8458-44bd-9990-62b71be18dd4', 'data_classification': 'time series', 'data_collection_organization': '', 'data_structure_category': 'structured', 'dataset_language': '', 'dataset_license_url': '', 'did_author_or_contact_organization_collect_the_data': 'true', 'email': 'ceschutte34@gmail.com', 'id': '52d35ec0-4d95-49a3-b596-fa7e109dca75', 'isopen': False, 'keywords': 'GRU, LSTM, Rainfall-runoff modelling', 'license': 'Open (Creative Commons)', 'license_id': None, 'license_title': None, 'maintainer': None, 'maintainer_email': None, 'metadata_created': '2023-07-27T15:17:57.228411', 'metadata_modified': '2024-08-17T16:40:18.609565', 'name': 'deep-learning-for-streamflow-prediction-project-data', 'notes': 'This dataset contains daily streamflow and weather data and the python code that was used to developed deep learning models for streamflow prediction. The data and code can be used to replicate the experiment on Google Drive using Google Colaboratory.\r\n\r\nStreamflow information is crucial for effectively managing water resources. The declining number of active gauging stations in many rivers is a global concern, necessitating the need for reliable streamflow estimates. Deep learning (DL) techniques offer potential solutions, but their application in southern Africa remains largely underexplored. To fill this gap, this study evaluated the predictive performance of Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) networks using two headwater catchments of the Steelpoort River, South Africa, as case studies. The model inputs included rainfall, maximum and minimum temperature, as well as past streamflow, which was utilized in an autoregressive sense. The inclusion of streamflow in this way allowed for the incorporation of simulated streamflow values into the look-back window (LBW) for predicting the streamflow of the testing set. Two modifications were required to the GRU and LSTM architectures to ensure physically consistent predictions. Including a change in activation function of the GRU/LSTM cells in the final hidden layer, and a non-negative constraint that was used in the dense layer. Models trained using commercial weather station data produced reliable streamflow estimates, while moderately accurate predictions were obtained using freely available gridded weather data.', 'num_resources': 1, 'num_tags': 0, 'organization': {'id': '4e8a617a-148a-4440-adde-e503f9346fcd', 'name': 'university-of-pretoria', 'title': 'University of Pretoria', 'type': 'organization', 'description': 'The University of Pretoria (UP) is one of Africa’s top universities and the largest contact university in South Africa. ', 'image_url': '2022-05-24-062305.772520UP-logo24May2022.JPG', 'created': '2022-05-24T06:23:05.795364', 'is_organization': True, 'approval_status': 'approved', 'state': 'active'}, 'owner_org': '4e8a617a-148a-4440-adde-e503f9346fcd', 'private': False, 'publication_date': '2024-04-30', 'publisher': 'Water Research Commission', 'spatial': '{"type": "Polygon", "coordinates": [[[16.4699, -22.1265], [32.8931, -22.1265], [32.8931, -34.8212], [16.4699, -34.8212], [16.4699, -22.1265]]]}', 'state': 'active', 'title': 'Deep recurrent neural networks for daily streamflow prediction', 'type': 'metadata-form', 'uploader_estimation_of_extent_of_processing': 'access', 'url': None, 'version': None, 'vertical_extent_datum': '1800', 'wrc_project_number': 'C2020/2021-00440', 'wro_theme': 'hydrological_data_and_modelling', 'authors': [{'author_department': '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'}], 'contact_person': [{'contact_department': '', 'contact_email': '', 'contact_name': '', 'contact_orgnization': ''}, {'contact_department': '', 'contact_email': '', 'contact_name': '', 'contact_orgnization': ''}], 'data_reference_date': [{'data_reference_date_from': '1979-10-01', 'data_reference_date_to': '2002-02-22'}], 'extras': [{'key': 'cloud_path', 'value': 'Hydrological_Data_And_Modelling/Structured/Access/Time Series'}], 'minimum_maximum_extent': [{'maximum_vertical_extent': '2263', 'minimum_vertical_extent': '1336'}], 'resources': [{'cache_last_updated': None, 'cache_url': None, 'created': '2024-02-13T15:39:11.287624', 'dataset_description': 'The folder contains the data needed to train GRU and LSTM models for streamflow prediction. See the ReadMe note inside the zipped folder for details on how to tun the experiment from Google Drive using Google Colab.\r\n\r\nDaily weather data, consisting of rainfall (mm), minimum and maximum temperature (̊C), and streamflow data (m3s-1) were used as input variables. The data included both in-situ measured data and gridded products. Daily weather data were obtained from three sources: 1) a weather station operated by the Agricultural Research Council (referred to as ARC in this study), 2) the Climate Hazards Group InfraRed Precipitation with Station (CHIRPS) data (Funk et al. 2015) (https://www.chc.ucsb.edu/data/chirps), and 3) the National Aeronautics and Space Administration Prediction of Worldwide Energy Resources (NASAP) project (https://power.larc.nasa.gov/). Streamflow data were obtained from the DWS website (https://www.dws.gov.za/Hydrology/Verified/hymain.aspx) for stations B4H007 and B4H001 for Catchment A and Catchment B, respectively.', 'datastore_active': False, 'description': None, 'file_to_bigquery_table': 'False', 'format': 'zip', 'hash': '', 'id': 'd5e90237-e8f0-40e9-996e-2a19ea158669', 'is_bigquery_table': False, 'is_data_supplementary': 'False', 'last_modified': None, 'metadata_modified': '2024-02-13T15:39:13.933620', 'mimetype': None, 'mimetype_inner': None, 'name': 'Data_and_Code.zip', 'package_id': '52d35ec0-4d95-49a3-b596-fa7e109dca75', 'position': 0, 'resource_name': 'Project Data and Code', 'resource_type': None, 'size': None, 'state': 'active', 'url': 'https://storage.cloud.google.com/wrc_wro_datasets/hydrological_data_and_modelling/structured/access/time series/deep-learning-for-streamflow-prediction-project-data/Data_and_Code-8669.zip', 'url_type': 'link', 'zipped_file': 'False', 'has_views': False, 'on_same_domain': False}], 'tags': [], 'groups': [], 'relationships_as_subject': [], 'relationships_as_object': []} |
| pkg |
<Package id=52d35ec0-4d95-49a3-b596-fa7e109dca75 name=deep-learning-for-streamflow-prediction-project-data title=Deep recurrent neural networks for daily streamflow prediction version=None url=None author=None author_email=None maintainer=None maintainer_email=None notes=This dataset contains daily streamflow and weather data and the python code that was used to developed deep learning models for streamflow prediction. The data and code can be used to replicate the experiment on Google Drive using Google Colaboratory.
Streamflow information is crucial for effectively managing water resources. The declining number of active gauging stations in many rivers is a global concern, necessitating the need for reliable streamflow estimates. Deep learning (DL) techniques offer potential solutions, but their application in southern Africa remains largely underexplored. To fill this gap, this study evaluated the predictive performance of Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) networks using two headwater catchments of the Steelpoort River, South Africa, as case studies. The model inputs included rainfall, maximum and minimum temperature, as well as past streamflow, which was utilized in an autoregressive sense. The inclusion of streamflow in this way allowed for the incorporation of simulated streamflow values into the look-back window (LBW) for predicting the streamflow of the testing set. Two modifications were required to the GRU and LSTM architectures to ensure physically consistent predictions. Including a change in activation function of the GRU/LSTM cells in the final hidden layer, and a non-negative constraint that was used in the dense layer. Models trained using commercial weather station data produced reliable streamflow estimates, while moderately accurate predictions were obtained using freely available gridded weather data. license_id=None type=metadata-form owner_org=4e8a617a-148a-4440-adde-e503f9346fcd creator_user_id=7ceb61ee-8458-44bd-9990-62b71be18dd4 metadata_created=2023-07-27 15:17:57.228411 metadata_modified=2024-08-17 16:40:18.609565 private=False state=active> |
| pkg_dict |
{'agreement': 'true', 'alternative_identifier': 'https://doi.org/10.2166/hydro.2024.268', 'author': None, 'author_email': None, 'citation_title': 'Schutte, C., Van der Laan, M., & Van der Merwe, B. (2024). Leveraging historic streamflow and weather data with deep learning for enhanced streamflow predictions. Journal of Hydroinformatics.', 'creator_user_id': '7ceb61ee-8458-44bd-9990-62b71be18dd4', 'data_classification': 'time series', 'data_collection_organization': '', 'data_structure_category': 'structured', 'dataset_language': '', 'dataset_license_url': '', 'did_author_or_contact_organization_collect_the_data': 'true', 'email': 'ceschutte34@gmail.com', 'id': '52d35ec0-4d95-49a3-b596-fa7e109dca75', 'isopen': False, 'keywords': 'GRU, LSTM, Rainfall-runoff modelling', 'license': 'Open (Creative Commons)', 'license_id': None, 'license_title': None, 'maintainer': None, 'maintainer_email': None, 'metadata_created': '2023-07-27T15:17:57.228411', 'metadata_modified': '2024-08-17T16:40:18.609565', 'name': 'deep-learning-for-streamflow-prediction-project-data', 'notes': 'This dataset contains daily streamflow and weather data and the python code that was used to developed deep learning models for streamflow prediction. The data and code can be used to replicate the experiment on Google Drive using Google Colaboratory.\r\n\r\nStreamflow information is crucial for effectively managing water resources. The declining number of active gauging stations in many rivers is a global concern, necessitating the need for reliable streamflow estimates. Deep learning (DL) techniques offer potential solutions, but their application in southern Africa remains largely underexplored. To fill this gap, this study evaluated the predictive performance of Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) networks using two headwater catchments of the Steelpoort River, South Africa, as case studies. The model inputs included rainfall, maximum and minimum temperature, as well as past streamflow, which was utilized in an autoregressive sense. The inclusion of streamflow in this way allowed for the incorporation of simulated streamflow values into the look-back window (LBW) for predicting the streamflow of the testing set. Two modifications were required to the GRU and LSTM architectures to ensure physically consistent predictions. Including a change in activation function of the GRU/LSTM cells in the final hidden layer, and a non-negative constraint that was used in the dense layer. Models trained using commercial weather station data produced reliable streamflow estimates, while moderately accurate predictions were obtained using freely available gridded weather data.', 'num_resources': 1, 'num_tags': 0, 'organization': {'id': '4e8a617a-148a-4440-adde-e503f9346fcd', 'name': 'university-of-pretoria', 'title': 'University of Pretoria', 'type': 'organization', 'description': 'The University of Pretoria (UP) is one of Africa’s top universities and the largest contact university in South Africa. ', 'image_url': '2022-05-24-062305.772520UP-logo24May2022.JPG', 'created': '2022-05-24T06:23:05.795364', 'is_organization': True, 'approval_status': 'approved', 'state': 'active'}, 'owner_org': '4e8a617a-148a-4440-adde-e503f9346fcd', 'private': False, 'publication_date': '2024-04-30', 'publisher': 'Water Research Commission', 'spatial': '{"type": "Polygon", "coordinates": [[[16.4699, -22.1265], [32.8931, -22.1265], [32.8931, -34.8212], [16.4699, -34.8212], [16.4699, -22.1265]]]}', 'state': 'active', 'title': 'Deep recurrent neural networks for daily streamflow prediction', 'type': 'metadata-form', 'uploader_estimation_of_extent_of_processing': 'access', 'url': None, 'version': None, 'vertical_extent_datum': '1800', 'wrc_project_number': 'C2020/2021-00440', 'wro_theme': 'hydrological_data_and_modelling', 'authors': [{'author_department': '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'}], 'contact_person': [{'contact_department': '', 'contact_email': '', 'contact_name': '', 'contact_orgnization': ''}, {'contact_department': '', 'contact_email': '', 'contact_name': '', 'contact_orgnization': ''}], 'data_reference_date': [{'data_reference_date_from': '1979-10-01', 'data_reference_date_to': '2002-02-22'}], 'extras': [{'key': 'cloud_path', 'value': 'Hydrological_Data_And_Modelling/Structured/Access/Time Series'}], 'minimum_maximum_extent': [{'maximum_vertical_extent': '2263', 'minimum_vertical_extent': '1336'}], 'resources': [{'cache_last_updated': None, 'cache_url': None, 'created': '2024-02-13T15:39:11.287624', 'dataset_description': 'The folder contains the data needed to train GRU and LSTM models for streamflow prediction. See the ReadMe note inside the zipped folder for details on how to tun the experiment from Google Drive using Google Colab.\r\n\r\nDaily weather data, consisting of rainfall (mm), minimum and maximum temperature (̊C), and streamflow data (m3s-1) were used as input variables. The data included both in-situ measured data and gridded products. Daily weather data were obtained from three sources: 1) a weather station operated by the Agricultural Research Council (referred to as ARC in this study), 2) the Climate Hazards Group InfraRed Precipitation with Station (CHIRPS) data (Funk et al. 2015) (https://www.chc.ucsb.edu/data/chirps), and 3) the National Aeronautics and Space Administration Prediction of Worldwide Energy Resources (NASAP) project (https://power.larc.nasa.gov/). Streamflow data were obtained from the DWS website (https://www.dws.gov.za/Hydrology/Verified/hymain.aspx) for stations B4H007 and B4H001 for Catchment A and Catchment B, respectively.', 'datastore_active': False, 'description': None, 'file_to_bigquery_table': 'False', 'format': 'zip', 'hash': '', 'id': 'd5e90237-e8f0-40e9-996e-2a19ea158669', 'is_bigquery_table': False, 'is_data_supplementary': 'False', 'last_modified': None, 'metadata_modified': '2024-02-13T15:39:13.933620', 'mimetype': None, 'mimetype_inner': None, 'name': 'Data_and_Code.zip', 'package_id': '52d35ec0-4d95-49a3-b596-fa7e109dca75', 'position': 0, 'resource_name': 'Project Data and Code', 'resource_type': None, 'size': None, 'state': 'active', 'url': 'https://storage.cloud.google.com/wrc_wro_datasets/hydrological_data_and_modelling/structured/access/time series/deep-learning-for-streamflow-prediction-project-data/Data_and_Code-8669.zip', 'url_type': 'link', 'zipped_file': 'False', 'has_views': False, 'on_same_domain': False}], 'tags': [], 'groups': [], 'relationships_as_subject': [], 'relationships_as_object': []} |
| request |
<Request 'http://data.waterresearchobservatory.org/metadata-form/deep-learning-for-streamflow-prediction-project-data/resource/d5e90237-e8f0-40e9-996e-2a19ea158669' [GET]> |
| resource |
{'cache_last_updated': None, 'cache_url': None, 'created': '2024-02-13T15:39:11.287624', 'dataset_description': 'The folder contains the data needed to train GRU and LSTM models for streamflow prediction. See the ReadMe note inside the zipped folder for details on how to tun the experiment from Google Drive using Google Colab.\r\n\r\nDaily weather data, consisting of rainfall (mm), minimum and maximum temperature (̊C), and streamflow data (m3s-1) were used as input variables. The data included both in-situ measured data and gridded products. Daily weather data were obtained from three sources: 1) a weather station operated by the Agricultural Research Council (referred to as ARC in this study), 2) the Climate Hazards Group InfraRed Precipitation with Station (CHIRPS) data (Funk et al. 2015) (https://www.chc.ucsb.edu/data/chirps), and 3) the National Aeronautics and Space Administration Prediction of Worldwide Energy Resources (NASAP) project (https://power.larc.nasa.gov/). Streamflow data were obtained from the DWS website (https://www.dws.gov.za/Hydrology/Verified/hymain.aspx) for stations B4H007 and B4H001 for Catchment A and Catchment B, respectively.', 'datastore_active': False, 'description': None, 'file_to_bigquery_table': 'False', 'format': 'zip', 'hash': '', 'id': 'd5e90237-e8f0-40e9-996e-2a19ea158669', 'is_bigquery_table': False, 'is_data_supplementary': 'False', 'last_modified': None, 'metadata_modified': '2024-02-13T15:39:13.933620', 'mimetype': None, 'mimetype_inner': None, 'name': 'Data_and_Code.zip', 'package_id': '52d35ec0-4d95-49a3-b596-fa7e109dca75', 'position': 0, 'resource_name': 'Project Data and Code', 'resource_type': None, 'size': None, 'state': 'active', 'url': 'https://storage.cloud.google.com/wrc_wro_datasets/hydrological_data_and_modelling/structured/access/time series/deep-learning-for-streamflow-prediction-project-data/Data_and_Code-8669.zip', 'url_type': 'link', 'zipped_file': 'False', 'has_views': False, 'on_same_domain': False} |
| resource_views |
[] |
| session |
{'_domain': None, '_path': '/', '_accessed_time': 1728308116.4265447, '_creation_time': 1728308116.4265447} |
| ungettext |
<function ungettext at 0x7faf6299f280> |
