{"id":{"repo_id":"wvu","oai_identifier":"oai:researchrepository.wvu.edu:etd-1149"},"canonical_url":"https://search.dev.ndltd.org/etd/wvu/oai:researchrepository.wvu.edu:etd-1149","repository":{"repo_id":"wvu","name":"West Virginia University","base_url":"https://researchrepository.wvu.edu/do/oai/"},"display":{"title":"Application of Neural Network Techniques to Downscale Precipitation","abstract":"Global climate change is a major area of concern to public and climate researchers. It impacts flooding, crop yields, water based diseases, etc. Significant effort has gone into developing climate models. Global climate models use a coarse grid of 300x300 Km2, while the resolution of interest for the hydrologist is 50x50 Km2.;Downscaling is the tool to map the large-scale global climate properties to a finer grid size in order to accurately predict climate variables such as precipitation. This study utilized Artificial Neural Networks (ANN) and Hybrid Support Vector Regression (HSVR) methods to predict precipitation at a finer grid, based on the data from a coarse grid. Precipitation data for three stations (Dhaka, Comilla and Mymesnsingh in Bangladesh) was utilized. For each model, the raw data was partitioned into training and test datasets. Based on the R2 values, the HSVR technique appears to be superior to other methods.","abstract_html":"Global climate change is a major area of concern to public and climate researchers. It impacts flooding, crop yields, water based diseases, etc. Significant effort has gone into developing climate models. Global climate models use a coarse grid of 300x300 Km2, while the resolution of interest for the hydrologist is 50x50 Km2.;Downscaling is the tool to map the large-scale global climate properties to a finer grid size in order to accurately predict climate variables such as precipitation. This study utilized Artificial Neural Networks (ANN) and Hybrid Support Vector Regression (HSVR) methods to predict precipitation at a finer grid, based on the data from a coarse grid. Precipitation data for three stations (Dhaka, Comilla and Mymesnsingh in Bangladesh) was utilized. For each model, the raw data was partitioned into training and test datasets. Based on the R2 values, the HSVR technique appears to be superior to other methods.","abstract_has_math":false,"creators":["Rahimikollu, Javad"],"institution":null,"degree_name":"MS","degree_level":"Thesis","degree_discipline":"Industrial and Managements Systems Engineering","degree_department":null,"school":null,"contributors":["Rashpal S. .Ahluwalia","Robert C. Creese","Antar Jutla."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2014,"date_issued":"2014-08-01T07:00:00Z","date_published":"2014-08-01T07:00:00Z","updated_at":"2026-07-24T06:14:02Z","subjects":["Industrial engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["https://researchrepository.wvu.edu/etd/146"],"render_values":[{"text":"https://researchrepository.wvu.edu/etd/146","href":"https://researchrepository.wvu.edu/etd/146","code":true}]}]},"links":{"outbound_url":"https://doi.org/10.33915/etd.146","outbound_label":"DOI","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Rashpal S. .Ahluwalia","Robert C. Creese","Antar Jutla."]},{"key":"dc:creator","label":"Author","values":["Rahimikollu, Javad"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2018-10-29T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Industrial and Managements Systems Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Industrial engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://doi.org/10.33915/etd.146","https://researchrepository.wvu.edu/etd/146"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Global climate change is a major area of concern to public and climate researchers. It impacts flooding, crop yields, water based diseases, etc. Significant effort has gone into developing climate models. Global climate models use a coarse grid of 300x300 Km2, while the resolution of interest for the hydrologist is 50x50 Km2.;Downscaling is the tool to map the large-scale global climate properties to a finer grid size in order to accurately predict climate variables such as precipitation. This study utilized Artificial Neural Networks (ANN) and Hybrid Support Vector Regression (HSVR) methods to predict precipitation at a finer grid, based on the data from a coarse grid. Precipitation data for three stations (Dhaka, Comilla and Mymesnsingh in Bangladesh) was utilized. For each model, the raw data was partitioned into training and test datasets. Based on the R2 values, the HSVR technique appears to be superior to other methods."]},{"key":"dc:title","label":"Title","values":["Application of Neural Network Techniques to Downscale Precipitation"]}]}],"canonical_facts":{"dc:contributor":["Rashpal S. .Ahluwalia","Robert C. Creese","Antar Jutla."],"dc:creator":["Rahimikollu, Javad"],"dc:date.available":["2018-10-29T07:00:00Z"],"dc:description.abstract":["Global climate change is a major area of concern to public and climate researchers. It impacts flooding, crop yields, water based diseases, etc. Significant effort has gone into developing climate models. Global climate models use a coarse grid of 300x300 Km2, while the resolution of interest for the hydrologist is 50x50 Km2.;Downscaling is the tool to map the large-scale global climate properties to a finer grid size in order to accurately predict climate variables such as precipitation. This study utilized Artificial Neural Networks (ANN) and Hybrid Support Vector Regression (HSVR) methods to predict precipitation at a finer grid, based on the data from a coarse grid. Precipitation data for three stations (Dhaka, Comilla and Mymesnsingh in Bangladesh) was utilized. For each model, the raw data was partitioned into training and test datasets. Based on the R2 values, the HSVR technique appears to be superior to other methods."],"dc:identifier":["https://doi.org/10.33915/etd.146","https://researchrepository.wvu.edu/etd/146"],"dc:subject":["Industrial engineering"],"dc:title":["Application of Neural Network Techniques to Downscale Precipitation"],"thesis:degree_discipline":["Industrial and Managements Systems Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["MS"]},"updated_at":"2026-07-24T06:14:02Z"}