Forecast of Convective Events Via Hybrid Model: Wrf and Machine Learning Algorithms

da Silva, Yasmin Uchoa; França, Gutemberg Borges; Ruivo, Heloisa Musetti; de Campos Velho, Haroldo Fraga

doi:10.2139/ssrn.4113508

Cited by 2 publications

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using historical AD data from TMA-Brasilia and METAR messages from Brasilia's airport (SBBR), ten days were chosen, three without CME and seven with CME, in which the horizontal visibility falls below 1,000 meters, were recorded in SBBR due to precipitation (rain) and there was an AD rate > 1,000 rate for these events in the TD interval. The selected days were numerically reconstructed using WRF-ICEA, as described in step 3 of the method, with two con gurations, namely: (I) the default WRF-ICEA as column 5 in Table 4, and (II) the result of the sensitivity test suggested by Da Silva et al (2022) to forecast CME using WRF in Southeastern Brazil (column 6 in Table 4). Following that, the hourly modeled-TIIs in the TD period were determined and used as input in the optimum models (trained with 12 UTC data) to forecast 30-h CME in the TD period, which corresponds to a 7-hour period between 15 and 21:59 pm (local), which represents the TD.…”

Section: Use Of Optimal Models With Modeled-tiismentioning

confidence: 99%

“…It is well known that aviation is extremely sensitive to atmospheric conditions, as landing and takeoff procedures at airports are frequently hampered by low visibility caused by heavy rain, shear, and gust wind associated with convective events, particularly in tropical regions. On route, atmospheric conditions can cause deviations and, as a result, increased fuel consumption by aircraft, as well as discomfort for the crew due sometimes to convection-induced clear air turbulence (Gultepe et al, 2019;Da Silva et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of Machine Learning Models for Convective Meteorological Events

Pereira-Nunes,

França,

de Almeida

2024

Pure Appl. Geophys.

Self Cite

View full text Add to dashboard Cite

This research developed models, based on machine learning (MA), for forecasting 16 hours and 4 hours of occurrence of a convective meteorological event (CME), 4 hours for forecasting severity and evaluating the applicability of the optimal models of 12 UTC using thermodynamic instability indices (TII) data extracted from the WRF model with two different types of parameterization con guration in an attempt to develop a30-hour CME forecast model. In the training and testing of the MA algorithms, the classic TIIs (input) were used, obtained from the atmospheric pro les of the Brasilia upper air sounding and atmospheric discharges (output) detected in the study area for the characterization of CME, considering the period from 2012 to 2017. The optimal models applied to the modeled TIIs were evaluated through statistical metrics with con guration II obtaining signi cant results. For CME detection, the results showed that the best models obtained POD, 1-FAR, F-MEASURE and KAPPA with values respectively greater than 0.90, 0.80, 0.90, 0.80 and BIAS ranging from 0 .89 and 1.12. For the detection of event severity, the model presented the following statistical values (in parentheses): POD (0.82), 1-FAR (0.78), F-MEASURE (0.82), KAPPA (0.59 ) and BIAS (0.97). The results of 16-h and 4-h CME prediction hindcasts (30 days) with developed models demonstrated acceptable performance in identifying the occurrence or non-occurrence of CME and its severity for the study area.

show abstract

Section: Use Of Optimal Models With Modeled-tiismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Application of Machine Learning Models for Convective Meteorological Events

Pereira-Nunes,

França,

de Almeida

2024

Pure Appl. Geophys.

Self Cite

View full text Add to dashboard Cite

show abstract

Convective Meteorological Events Forecast using Machine Learning models

Pereira-Nunes

França

Almeida

2023

Preprint

Self Cite

View full text Add to dashboard Cite

This research developed models, based on machine learning (MA), for forecasting 16 hours and 4 hours of occurrence of a convective meteorological event (CME), 4 hours for forecasting severity and evaluating the applicability of the optimal models of 12 UTC using thermodynamic instability indices (TII) data extracted from the WRF model with two different types of parameterization configuration in an attempt to develop a30-hour CME forecast model. In the training and testing of the MA algorithms, the classic TIIs (input) were used, obtained from the atmospheric profiles of the Brasilia upper air sounding and atmospheric discharges (output) detected in the study area for the characterization of CME, considering the period from 2012 to 2017. The optimal models applied to the modeled TIIs were evaluated through statistical metrics with configuration II obtaining significant results. For CME detection, the results showed that the best models obtained POD, 1-FAR, F-MEASURE and KAPPA with values respectively greater than 0.90, 0.80, 0.90, 0.80 and BIAS ranging from 0 .89 and 1.12. For the detection of event severity, the model presented the following statistical values (in parentheses): POD (0.82), 1-FAR (0.78), F-MEASURE (0.82), KAPPA (0.59 ) and BIAS (0.97). The results of 16-h and 4-h CME prediction hindcasts (30 days) with developed models demonstrated acceptable performance in identifying the occurrence or non-occurrence of CME and its severity for the study area.

show abstract

Forecast of Convective Events Via Hybrid Model: Wrf and Machine Learning Algorithms

Cited by 2 publications

References 24 publications

Application of Machine Learning Models for Convective Meteorological Events

Application of Machine Learning Models for Convective Meteorological Events

Convective Meteorological Events Forecast using Machine Learning models

Contact Info

Product

Resources

About