{"corpus_id":216519849,"paper_sha":"b8a8a56fb3a2f502af94221a66639b9ba9510ce8","doi":"10.3390/atmos11040316","arxiv_id":null,"pmid":null,"pmcid":null,"mag_id":3013592816,"dblp_id":null,"acl_id":null,"title":"The Comparison of Predicting Storm-Time Ionospheric TEC by Three Methods: ARIMA, LSTM, and Seq2Seq","year":2020,"publication_date":"2020-03-25","venue":"Atmosphere","journal":{"name":"Atmosphere","pages":null,"volume":null},"journal_issn":null,"journal_title":null,"publication_types":[],"pubmed_pub_types":null,"s2_fields_of_study":["Physics","Engineering","Environmental Science"],"reference_count":49,"citation_count":99,"influential_citation_count":0,"is_open_access":true,"arxiv_categories":null,"arxiv_license":null,"arxiv_journal_ref":null,"mesh_headings":null,"chemicals":null,"comments_corrections":null,"source_flags":1,"s2_open_access_pdf_url":"https://www.mdpi.com/2073-4433/11/4/316/pdf?version=1586430206","s2_open_access_landing_url":"https://www.semanticscholar.org/paper/b8a8a56fb3a2f502af94221a66639b9ba9510ce8","s2_open_access_license":"CCBY","s2_open_access_status":"GOLD","pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"Ionospheric structure usually changes dramatically during a strong geomagnetic storm period, which will significantly affect the short-wave communication and satellite navigation systems. It is critically important to make accurate ionospheric predictions under the extreme space weather conditions. However, ionospheric prediction is always a challenge, and pure physical methods often fail to get a satisfactory result since the ionospheric behavior varies greatly with different geomagnetic storms. In this paper, in order to find an effective prediction method, one traditional mathematical method (autoregressive integrated moving average—ARIMA) and two deep learning algorithms (long short-term memory—LSTM and sequence-to-sequence—Seq2Seq) are investigated for the short-term predictions of ionospheric TEC (Total Electron Content) under different geomagnetic storm conditions based on the MIT (Massachusetts Institute of Technology) madrigal observation from 2001 to 2016. Under the extreme condition, the performance limitation of these methods can be found. When the storm is stronger, the effective prediction horizon of the methods will be shorter. The statistical analysis shows that the LSTM can achieve the best prediction accuracy and is robust for the accurate trend prediction of the strong geomagnetic storms. In contrast, ARIMA and Seq2Seq have relatively poor performance for the prediction of the strong geomagnetic storms. This study brings new insights to the deep learning applications in the space weather forecast.","claims":[{"public_id":"cl_6f06a4a4db8ee6b25efab5614e3ac09e","status":"active","text":"ARIMA and Seq2Seq perform relatively poorly for predicting strong geomagnetic storms.","confidence":0.93,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_6f06a4a4db8ee6b25efab5614e3ac09e"},{"public_id":"cl_e48ae7e674ed960885a2087ada0687e4","status":"active","text":"LSTM achieves the best prediction accuracy and is robust for accurate trend prediction of strong geomagnetic storms.","confidence":0.97,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_e48ae7e674ed960885a2087ada0687e4"},{"public_id":"cl_aaf939e20824db9c64749de1479d992e","status":"active","text":"Short-term ionospheric TEC prediction under different geomagnetic storm conditions is feasible using ARIMA, LSTM, and Seq2Seq on MIT Madrigal observations from 2001 to 2016.","confidence":0.9,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_aaf939e20824db9c64749de1479d992e"},{"public_id":"cl_dfd186ac0d7c513bc63f8eb1c2841e41","status":"active","text":"The effective prediction horizon of the methods becomes shorter as storm strength increases.","confidence":0.95,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_dfd186ac0d7c513bc63f8eb1c2841e41"}],"concepts":[{"public_id":"co_0f0c4122ec23d076a437c58b49e1b6e3","status":"active","name":"prediction accuracy","description":"The degree to which a forecast matches the observed ionospheric TEC values.","types":["evaluation metric"],"aliases":["forecast accuracy"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_0f0c4122ec23d076a437c58b49e1b6e3"},{"public_id":"co_1406d49e595fe7207057eb9f9a542dd7","status":"active","name":"geomagnetic storm conditions","description":"Space weather conditions associated with disturbed geomagnetic activity during storm periods.","types":["condition"],"aliases":["geomagnetic storm","storm conditions"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_1406d49e595fe7207057eb9f9a542dd7"},{"public_id":"co_17b62385fd1a335e04a35d9da2c51f1d","status":"active","name":"Seq2Seq","description":"Sequence-to-sequence, a neural network approach for mapping input sequences to output sequences.","types":["method"],"aliases":["sequence-to-sequence"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_17b62385fd1a335e04a35d9da2c51f1d"},{"public_id":"co_4a37e3399ed776aff1713b472db21a21","status":"active","name":"ionospheric TEC","description":"Total Electron Content in the ionosphere, representing the integrated number of free electrons along a path.","types":["measurement"],"aliases":["TEC","Total Electron Content"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_4a37e3399ed776aff1713b472db21a21"},{"public_id":"co_a1996400cf0f782f66b6c9af6c8cb5cc","status":"active","name":"prediction horizon","description":"The time span over which a forecasting method can produce useful predictions.","types":["evaluation metric"],"aliases":["effective prediction horizon"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_a1996400cf0f782f66b6c9af6c8cb5cc"},{"public_id":"co_a6e04dabca6b99aa1cbecd557bfd644c","status":"active","name":"strong geomagnetic storms","description":"High-intensity geomagnetic storm events used as the extreme prediction setting in the comparison.","types":["event"],"aliases":["extreme geomagnetic storms"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_a6e04dabca6b99aa1cbecd557bfd644c"},{"public_id":"co_bdb5e43947aa063a079371b5b1c65391","status":"active","name":"LSTM","description":"Long short-term memory, a recurrent neural network architecture used for sequence prediction.","types":["method"],"aliases":["long short-term memory"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_bdb5e43947aa063a079371b5b1c65391"},{"public_id":"co_ef70e24b476e14145e1bdf6d142f4aff","status":"active","name":"MIT Madrigal observation","description":"An observational data source from the MIT Madrigal database used for the prediction experiments.","types":["dataset"],"aliases":["Madrigal observation"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_ef70e24b476e14145e1bdf6d142f4aff"},{"public_id":"co_fc18220cfe5345410a48aed9b465a051","status":"active","name":"ARIMA","description":"Autoregressive integrated moving average, a traditional time-series forecasting method.","types":["method"],"aliases":["autoregressive integrated moving average"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_fc18220cfe5345410a48aed9b465a051"}],"external_ids":{"DOI":"10.3390/atmos11040316","ArXiv":null,"PubMed":null,"PubMedCentral":null,"MAG":3013592816,"DBLP":null,"ACL":null},"open_access":{"is_open_access":true,"pdf_url":"https://www.mdpi.com/2073-4433/11/4/316/pdf?version=1586430206","landing_url":"https://www.semanticscholar.org/paper/b8a8a56fb3a2f502af94221a66639b9ba9510ce8","source":"semantic_scholar","pdf_url_source":"semantic_scholar_open_access_pdf","license":"CCBY","status":"GOLD","reason":null},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":false,"full_text_source":null,"count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":1},"paper_id":630886,"paper_uid":"23d483d9-a59d-4a10-bea4-3d7984d44b10","canonical_identity":{"paper_id":630886,"paper_uid":"23d483d9-a59d-4a10-bea4-3d7984d44b10","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/216519849"}