Forecast of convective events via hybrid model: WRF and machine learning algorithms
This presents a novel hybrid 24-h forecasting model of convective weather events based on numerical simulation and machine learning algorithms. To characterize the convective events, 13-year from 2008 up to 2020 of precipitation data from the main airport stations in Rio de Janeiro, Brazil, and atmo...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-12-01
|
| Series: | Applied Computing and Geosciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590197422000210 |
| _version_ | 1797985419736907776 |
|---|---|
| author | Yasmin Uchôa da Silva Gutemberg Borges França Heloisa Musetti Ruivo Haroldo Fraga de Campos Velho |
| author_facet | Yasmin Uchôa da Silva Gutemberg Borges França Heloisa Musetti Ruivo Haroldo Fraga de Campos Velho |
| author_sort | Yasmin Uchôa da Silva |
| collection | DOAJ |
| description | This presents a novel hybrid 24-h forecasting model of convective weather events based on numerical simulation and machine learning algorithms. To characterize the convective events, 13-year from 2008 up to 2020 of precipitation data from the main airport stations in Rio de Janeiro, Brazil, and atmospheric discharges from the surrounding area of around 150 km are investigated. The Weather Research and Forecasting (WRF) model was used to numerically simulate atmospheric conditions for every day in February, as it is the month with the greatest daily rate of atmospheric discharge for the data period. The p-value hypothesis test (with α=0.05) was applied to each grid point of the numerically predicted variables (defined as an independent attribute) to find those most associated with convective events using the output of the 3-D WRF grid. This one identified 36 attributes (or predictors) that were used as input in the machine learning algorithms' training-test process in this study. Several cross-validation training and testing experiments were carried out using the nine-selected categorical machine learning algorithms and the 36 defined predictors. After applying the boosting technique to the nine previously trained-tested algorithms, the results of the 24-h predictions of convective occurrences were deemed satisfactory. The RandomForest method produced the best results, with statistics values close to perfection, such as POD = 1.00, FAR = 0.02, and CSI = 0.98. The 24-h hindcast utilizing the nine algorithms for the 28 days of February 2019 was very encouraging because it was able to almost recreate the maturation phase of events and their eventual failures were noted during the formation and dissipation phases. The best and worst 24-h hindcast had POD = 0.97 and 0.88, FAR = 0.02 and 0.12, and CSI = 0.94 and 0.78, respectively. |
| first_indexed | 2024-04-11T07:17:46Z |
| format | Article |
| id | doaj.art-6e92180e3e554e60a821b52f5020ba20 |
| institution | Directory Open Access Journal |
| issn | 2590-1974 |
| language | English |
| last_indexed | 2024-04-11T07:17:46Z |
| publishDate | 2022-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Applied Computing and Geosciences |
| spelling | doaj.art-6e92180e3e554e60a821b52f5020ba202022-12-22T04:37:52ZengElsevierApplied Computing and Geosciences2590-19742022-12-0116100099Forecast of convective events via hybrid model: WRF and machine learning algorithmsYasmin Uchôa da Silva0Gutemberg Borges França1Heloisa Musetti Ruivo2Haroldo Fraga de Campos Velho3Laboratório de Meteorologia Aplicada, Departamento de Meteorologia-IGEO-CCMN, Universidade Federal do Rio de Janeiro (UFRJ), Rio De Janeiro, Brazil; Corresponding author.Laboratório de Meteorologia Aplicada, Departamento de Meteorologia-IGEO-CCMN, Universidade Federal do Rio de Janeiro (UFRJ), Rio De Janeiro, BrazilInstituto Nacional de Pesquisas Espaciais (INPE), São Paulo, BrazilInstituto Nacional de Pesquisas Espaciais (INPE), São Paulo, BrazilThis presents a novel hybrid 24-h forecasting model of convective weather events based on numerical simulation and machine learning algorithms. To characterize the convective events, 13-year from 2008 up to 2020 of precipitation data from the main airport stations in Rio de Janeiro, Brazil, and atmospheric discharges from the surrounding area of around 150 km are investigated. The Weather Research and Forecasting (WRF) model was used to numerically simulate atmospheric conditions for every day in February, as it is the month with the greatest daily rate of atmospheric discharge for the data period. The p-value hypothesis test (with α=0.05) was applied to each grid point of the numerically predicted variables (defined as an independent attribute) to find those most associated with convective events using the output of the 3-D WRF grid. This one identified 36 attributes (or predictors) that were used as input in the machine learning algorithms' training-test process in this study. Several cross-validation training and testing experiments were carried out using the nine-selected categorical machine learning algorithms and the 36 defined predictors. After applying the boosting technique to the nine previously trained-tested algorithms, the results of the 24-h predictions of convective occurrences were deemed satisfactory. The RandomForest method produced the best results, with statistics values close to perfection, such as POD = 1.00, FAR = 0.02, and CSI = 0.98. The 24-h hindcast utilizing the nine algorithms for the 28 days of February 2019 was very encouraging because it was able to almost recreate the maturation phase of events and their eventual failures were noted during the formation and dissipation phases. The best and worst 24-h hindcast had POD = 0.97 and 0.88, FAR = 0.02 and 0.12, and CSI = 0.94 and 0.78, respectively.http://www.sciencedirect.com/science/article/pii/S2590197422000210Convective eventData miningMachine learningAtmospheric dischargeForecast |
| spellingShingle | Yasmin Uchôa da Silva Gutemberg Borges França Heloisa Musetti Ruivo Haroldo Fraga de Campos Velho Forecast of convective events via hybrid model: WRF and machine learning algorithms Applied Computing and Geosciences Convective event Data mining Machine learning Atmospheric discharge Forecast |
| title | Forecast of convective events via hybrid model: WRF and machine learning algorithms |
| title_full | Forecast of convective events via hybrid model: WRF and machine learning algorithms |
| title_fullStr | Forecast of convective events via hybrid model: WRF and machine learning algorithms |
| title_full_unstemmed | Forecast of convective events via hybrid model: WRF and machine learning algorithms |
| title_short | Forecast of convective events via hybrid model: WRF and machine learning algorithms |
| title_sort | forecast of convective events via hybrid model wrf and machine learning algorithms |
| topic | Convective event Data mining Machine learning Atmospheric discharge Forecast |
| url | http://www.sciencedirect.com/science/article/pii/S2590197422000210 |
| work_keys_str_mv | AT yasminuchoadasilva forecastofconvectiveeventsviahybridmodelwrfandmachinelearningalgorithms AT gutembergborgesfranca forecastofconvectiveeventsviahybridmodelwrfandmachinelearningalgorithms AT heloisamusettiruivo forecastofconvectiveeventsviahybridmodelwrfandmachinelearningalgorithms AT haroldofragadecamposvelho forecastofconvectiveeventsviahybridmodelwrfandmachinelearningalgorithms |