Hybrid AI-enhanced lightning flash prediction in the medium-range forecast horizon
Abstract Traditional fully-deterministic algorithms, which rely on physical equations and mathematical models, are the backbone of many scientific disciplines for decades. These algorithms are based on well-established principles and laws of physics, enabling a systematic and predictable approach to...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-02-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-024-44697-2 |
| _version_ | 1797274144666025984 |
|---|---|
| author | Mattia Cavaiola Federico Cassola Davide Sacchetti Francesco Ferrari Andrea Mazzino |
| author_facet | Mattia Cavaiola Federico Cassola Davide Sacchetti Francesco Ferrari Andrea Mazzino |
| author_sort | Mattia Cavaiola |
| collection | DOAJ |
| description | Abstract Traditional fully-deterministic algorithms, which rely on physical equations and mathematical models, are the backbone of many scientific disciplines for decades. These algorithms are based on well-established principles and laws of physics, enabling a systematic and predictable approach to problem-solving. On the other hand, AI-based strategies emerge as a powerful tool for handling vast amounts of data and extracting patterns and relationships that might be challenging to identify through traditional algorithms. Here, we bridge these two realms by using AI to find an optimal mapping of meteorological features predicted two days ahead by the state-of-the-art numerical weather prediction model by the European Centre for Medium-range Weather Forecasts (ECMWF) into lightning flash occurrence. The prediction capability of the resulting AI-enhanced algorithm turns out to be significantly higher than that of the fully-deterministic algorithm employed in the ECMWF model. A remarkable Recall peak of about 95% within the 0-24 h forecast interval is obtained. This performance surpasses the 85% achieved by the ECMWF model at the same Precision of the AI algorithm. |
| first_indexed | 2024-03-07T14:54:10Z |
| format | Article |
| id | doaj.art-1d6678882a9e4eb78bc7abe098e535bc |
| institution | Directory Open Access Journal |
| issn | 2041-1723 |
| language | English |
| last_indexed | 2024-03-07T14:54:10Z |
| publishDate | 2024-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj.art-1d6678882a9e4eb78bc7abe098e535bc2024-03-05T19:31:30ZengNature PortfolioNature Communications2041-17232024-02-0115111510.1038/s41467-024-44697-2Hybrid AI-enhanced lightning flash prediction in the medium-range forecast horizonMattia Cavaiola0Federico Cassola1Davide Sacchetti2Francesco Ferrari3Andrea Mazzino4DICCA, Department of Civil, Chemical and Environmental EngineeringARPAL, Regional Agency for Environmental Protection LiguriaARPAL, Regional Agency for Environmental Protection LiguriaDICCA, Department of Civil, Chemical and Environmental EngineeringDICCA, Department of Civil, Chemical and Environmental EngineeringAbstract Traditional fully-deterministic algorithms, which rely on physical equations and mathematical models, are the backbone of many scientific disciplines for decades. These algorithms are based on well-established principles and laws of physics, enabling a systematic and predictable approach to problem-solving. On the other hand, AI-based strategies emerge as a powerful tool for handling vast amounts of data and extracting patterns and relationships that might be challenging to identify through traditional algorithms. Here, we bridge these two realms by using AI to find an optimal mapping of meteorological features predicted two days ahead by the state-of-the-art numerical weather prediction model by the European Centre for Medium-range Weather Forecasts (ECMWF) into lightning flash occurrence. The prediction capability of the resulting AI-enhanced algorithm turns out to be significantly higher than that of the fully-deterministic algorithm employed in the ECMWF model. A remarkable Recall peak of about 95% within the 0-24 h forecast interval is obtained. This performance surpasses the 85% achieved by the ECMWF model at the same Precision of the AI algorithm.https://doi.org/10.1038/s41467-024-44697-2 |
| spellingShingle | Mattia Cavaiola Federico Cassola Davide Sacchetti Francesco Ferrari Andrea Mazzino Hybrid AI-enhanced lightning flash prediction in the medium-range forecast horizon Nature Communications |
| title | Hybrid AI-enhanced lightning flash prediction in the medium-range forecast horizon |
| title_full | Hybrid AI-enhanced lightning flash prediction in the medium-range forecast horizon |
| title_fullStr | Hybrid AI-enhanced lightning flash prediction in the medium-range forecast horizon |
| title_full_unstemmed | Hybrid AI-enhanced lightning flash prediction in the medium-range forecast horizon |
| title_short | Hybrid AI-enhanced lightning flash prediction in the medium-range forecast horizon |
| title_sort | hybrid ai enhanced lightning flash prediction in the medium range forecast horizon |
| url | https://doi.org/10.1038/s41467-024-44697-2 |
| work_keys_str_mv | AT mattiacavaiola hybridaienhancedlightningflashpredictioninthemediumrangeforecasthorizon AT federicocassola hybridaienhancedlightningflashpredictioninthemediumrangeforecasthorizon AT davidesacchetti hybridaienhancedlightningflashpredictioninthemediumrangeforecasthorizon AT francescoferrari hybridaienhancedlightningflashpredictioninthemediumrangeforecasthorizon AT andreamazzino hybridaienhancedlightningflashpredictioninthemediumrangeforecasthorizon |