A Machine Learning-Based Parameterized Tropical Cyclone Precipitation Model
Abstract Current simulation models considerably underestimate local-scale, short-duration extreme precipitation induced by tropical cyclones (TCs). This problem needs to be addressed to establish active response policies for TC-induced disasters. Taking Shanghai, a coastal megacity, as a study area...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-12-01
|
| Series: | International Journal of Disaster Risk Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s13753-024-00606-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846112962197061632 |
|---|---|
| author | Yi Lu Jie Yin Peiyan Chen Hui Yu Sirong Huang |
| author_facet | Yi Lu Jie Yin Peiyan Chen Hui Yu Sirong Huang |
| author_sort | Yi Lu |
| collection | DOAJ |
| description | Abstract Current simulation models considerably underestimate local-scale, short-duration extreme precipitation induced by tropical cyclones (TCs). This problem needs to be addressed to establish active response policies for TC-induced disasters. Taking Shanghai, a coastal megacity, as a study area and based on the observations from 192 meteorological stations in the city during 2005–2018, this study optimized the parameterized Tropical Cyclone Precipitation Model (TCPM) initially designed for TCs at the national scale (China) to the local or regional scales by using machine learning (ML) methods, including the random forest (RF), extreme gradient boosting (XGBoost), and ensemble learning (EL) algorithms. The TCPM-ML was applied for multiple temporal scale hazard assessment. The results show that: (1) The TCPM-ML not only improved TCPM performance for simulating hourly extreme precipitations, but also preserved the physical meaning of the results, contrary to ML methods; (2) Machine learning algorithms enhanced the TCPM ability to reproduce observations, although the hourly extreme precipitations remained slightly underestimated; (3) Best performance was obtained with the XGBoost or EL algorithms. Combining the strengths of both XGBoost and RF, the EL algorithm yielded the best overall performance. This study provides essential model support for TC disaster risk assessment and response at the local and regional scales in China. |
| format | Article |
| id | doaj-art-f6e01c65de2147df9d2e8cefdb39c1db |
| institution | Kabale University |
| issn | 2095-0055 2192-6395 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | International Journal of Disaster Risk Science |
| spelling | doaj-art-f6e01c65de2147df9d2e8cefdb39c1db2024-12-22T12:11:50ZengSpringerOpenInternational Journal of Disaster Risk Science2095-00552192-63952024-12-0115697298510.1007/s13753-024-00606-1A Machine Learning-Based Parameterized Tropical Cyclone Precipitation ModelYi Lu0Jie Yin1Peiyan Chen2Hui Yu3Sirong Huang4Shanghai Typhoon Institute, China Meteorological AdministrationSchool of Geographic Sciences, East China Normal UniversityShanghai Typhoon Institute, China Meteorological AdministrationShanghai Typhoon Institute, China Meteorological AdministrationShanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal UniversityAbstract Current simulation models considerably underestimate local-scale, short-duration extreme precipitation induced by tropical cyclones (TCs). This problem needs to be addressed to establish active response policies for TC-induced disasters. Taking Shanghai, a coastal megacity, as a study area and based on the observations from 192 meteorological stations in the city during 2005–2018, this study optimized the parameterized Tropical Cyclone Precipitation Model (TCPM) initially designed for TCs at the national scale (China) to the local or regional scales by using machine learning (ML) methods, including the random forest (RF), extreme gradient boosting (XGBoost), and ensemble learning (EL) algorithms. The TCPM-ML was applied for multiple temporal scale hazard assessment. The results show that: (1) The TCPM-ML not only improved TCPM performance for simulating hourly extreme precipitations, but also preserved the physical meaning of the results, contrary to ML methods; (2) Machine learning algorithms enhanced the TCPM ability to reproduce observations, although the hourly extreme precipitations remained slightly underestimated; (3) Best performance was obtained with the XGBoost or EL algorithms. Combining the strengths of both XGBoost and RF, the EL algorithm yielded the best overall performance. This study provides essential model support for TC disaster risk assessment and response at the local and regional scales in China.https://doi.org/10.1007/s13753-024-00606-1Extreme precipitationMachine learningParameterized modelShanghaiTropical cyclone |
| spellingShingle | Yi Lu Jie Yin Peiyan Chen Hui Yu Sirong Huang A Machine Learning-Based Parameterized Tropical Cyclone Precipitation Model International Journal of Disaster Risk Science Extreme precipitation Machine learning Parameterized model Shanghai Tropical cyclone |
| title | A Machine Learning-Based Parameterized Tropical Cyclone Precipitation Model |
| title_full | A Machine Learning-Based Parameterized Tropical Cyclone Precipitation Model |
| title_fullStr | A Machine Learning-Based Parameterized Tropical Cyclone Precipitation Model |
| title_full_unstemmed | A Machine Learning-Based Parameterized Tropical Cyclone Precipitation Model |
| title_short | A Machine Learning-Based Parameterized Tropical Cyclone Precipitation Model |
| title_sort | machine learning based parameterized tropical cyclone precipitation model |
| topic | Extreme precipitation Machine learning Parameterized model Shanghai Tropical cyclone |
| url | https://doi.org/10.1007/s13753-024-00606-1 |
| work_keys_str_mv | AT yilu amachinelearningbasedparameterizedtropicalcycloneprecipitationmodel AT jieyin amachinelearningbasedparameterizedtropicalcycloneprecipitationmodel AT peiyanchen amachinelearningbasedparameterizedtropicalcycloneprecipitationmodel AT huiyu amachinelearningbasedparameterizedtropicalcycloneprecipitationmodel AT sironghuang amachinelearningbasedparameterizedtropicalcycloneprecipitationmodel AT yilu machinelearningbasedparameterizedtropicalcycloneprecipitationmodel AT jieyin machinelearningbasedparameterizedtropicalcycloneprecipitationmodel AT peiyanchen machinelearningbasedparameterizedtropicalcycloneprecipitationmodel AT huiyu machinelearningbasedparameterizedtropicalcycloneprecipitationmodel AT sironghuang machinelearningbasedparameterizedtropicalcycloneprecipitationmodel |