{"created":"2026-09-09T20:00:43.527201+00:00","links":{},"metadata":{"_buckets":{"deposit":"e3ab2a34-c835-4668-a378-5fe6a6b6434f"},"_deposit":{"created_by":155,"id":"13020.1","owner":"155","owners":[155],"pid":{"revision_id":0,"type":"depid","value":"13020.1"},"status":"published"},"_oai":{"id":"oai:meral.edu.mm:recid/00013020.1","sets":["1608151108672:1608152118915"]},"author_link":[],"item_1583103067471":{"attribute_name":"Title","attribute_value_mlt":[{"subitem_1551255647225":"Wave Height Forecasting in the Bay of Bengal Using Multivariate Hybrid Deep Learning Models","subitem_1551255648112":"en"}]},"item_1583103085720":{"attribute_name":"Description","attribute_value_mlt":[{"interim":"This research focuses on developing accurate regional wave height prediction models for the Bay of Bengal to support coastal engineering and maritime transportation. The study investigates the effectiveness of hybrid deep learning techniques, including CNN-LSTM, CNN-BiLSTM, CNN-GRU, and CNN-BiGRU, using multiple environmental parameters such as wave height, wind stress, water depth, pressure, and sea surface temperature (SST). The models are evaluated using statistical performance measures, including correlation coefficient, RMSE, and MAE, across different forecast horizons. Sensitivity analysis using the integrated gradient method is also conducted to determine the contribution of each environmental factor to wave height prediction. The results show that multivariate models provide improved prediction performance, particularly for longer forecast horizons, with the CNN-BiGRU model achieving the best overall performance across different forecast horizons. The study provides a useful framework for improving regional wave forecasting and understanding the influence of environmental variables on wave dynamics in the Bay of Bengal."}]},"item_1583103108160":{"attribute_name":"Keywords","attribute_value_mlt":[{"interim":"CNN-LSTM; CNN-BiLSTM; CNN-GRU; CNN-BiGRU; univariate; multivariate; wave height; Bay of Bengal"}]},"item_1583103120197":{"attribute_name":"Files","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_access","date":[{"dateType":"Available","dateValue":"2026-09-09"}],"filename":"Wave Height Forecasting in the Bay of Bengal Using Multivariate.pdf","filesize":[{"value":"2.2 MB"}],"format":"application/pdf","mimetype":"application/pdf","url":{"url":"https://meral.edu.mm/record/13020.1/files/Wave Height Forecasting in the Bay of Bengal Using Multivariate.pdf"},"version_id":"23d1bb61-b687-4335-8000-55db5a8c2991"}]},"item_1583103131163":{"attribute_name":"Journal articles","attribute_value_mlt":[{"subitem_issue":"Issue 8 (July 2025)","subitem_journal_title":"Journal of Marine Science and Engineering","subitem_pages":"pp.1412","subitem_volume":"Volume 13"}]},"item_1583105942107":{"attribute_name":"Authors","attribute_value_mlt":[{"subitem_authors":[{"subitem_authors_fullname":"Phyusin Thet, Aifeng Tao, Tao Lv, Jinhai Zheng"}]}]},"item_1583108359239":{"attribute_name":"Upload type","attribute_value_mlt":[{"interim":"Publication"}]},"item_1583108428133":{"attribute_name":"Publication type","attribute_value_mlt":[{"interim":"Journal article"}]},"item_1583159729339":{"attribute_name":"Publication date","attribute_value":"2025-07-24"},"item_1583159847033":{"attribute_name":"Identifier","attribute_value":"https:// doi.org/10.3390/jmse1308141"},"item_title":"Wave Height Forecasting in the Bay of Bengal Using Multivariate Hybrid Deep Learning Models","item_type_id":"21","owner":"155","path":["1608152118915"],"publish_date":"2026-09-10","publish_status":"0","recid":"13020.1","relation_version_is_last":true,"title":["Wave Height Forecasting in the Bay of Bengal Using Multivariate Hybrid Deep Learning Models"],"weko_creator_id":"155","weko_shared_id":-1},"updated":"2026-09-09T20:01:13.352943+00:00"}