Approximation of a Convective-Event-Monitoring System Using GOES-R Data and Ensemble ML Models
The presence of deep convective clouds is directly related to potential convective hazards, such as lightning strikes, hail, severe storms, flash floods, and tornadoes. On the other hand, Mexico has a limited and heterogeneous network of instruments that allow for efficient and reliable monitoring a...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/4/675 |
| _version_ | 1797297090504687616 |
|---|---|
| author | Rodrigo Dávila-Ortiz José Noel Carbajal-Pérez Juan Alberto Velázquez-Zapata José Tuxpan-Vargas |
| author_facet | Rodrigo Dávila-Ortiz José Noel Carbajal-Pérez Juan Alberto Velázquez-Zapata José Tuxpan-Vargas |
| author_sort | Rodrigo Dávila-Ortiz |
| collection | DOAJ |
| description | The presence of deep convective clouds is directly related to potential convective hazards, such as lightning strikes, hail, severe storms, flash floods, and tornadoes. On the other hand, Mexico has a limited and heterogeneous network of instruments that allow for efficient and reliable monitoring and forecasting of such events. In this study, a quasi-real-time framework for deep convective cloud identification and modeling based on machine learning (ML) models was developed. Eight different ML models and model assembly approaches were fed with Interest Fields estimated from Advanced Baseline Imager (ABI) sensor data on the Geostationary Operational Environmental Satellite-R Series (GOES-R) for one region in central Mexico and another in northeastern Mexico, both selected for their intense convective activity and high levels of vulnerability to severe weather. The results indicate that a simple approach such as Logistic Regression (LR) or Random Forest (RF) can be a good alternative for the identification and simulation of deep convective clouds in both study areas, with a probability of detection of (POD) ≈ 0.84 for Los Mochis and POD of ≈ 0.72 for Mexico City. Similarly, the false alarm ratio (FAR) ≈ 0.2 and FAR ≈ 0.4 values were obtained for Los Mochis and Mexico City, respectively. Finally, a post-processing filter based on lightning incidence (Lightning Filter) was applied with data from the Geostationary Lightning Mapper (GLM) of the GOES-16 satellite, showed great potential to improve the probability of detection (POD) of the ML models. This work sets a precedent for the implementation of an early-warning system for hazards associated with intense convective activity in Mexico. |
| first_indexed | 2024-03-07T22:16:14Z |
| format | Article |
| id | doaj.art-b066e22d130e4f6fa89bcce6f6b09d20 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-07T22:16:14Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-b066e22d130e4f6fa89bcce6f6b09d202024-02-23T15:33:04ZengMDPI AGRemote Sensing2072-42922024-02-0116467510.3390/rs16040675Approximation of a Convective-Event-Monitoring System Using GOES-R Data and Ensemble ML ModelsRodrigo Dávila-Ortiz0José Noel Carbajal-Pérez1Juan Alberto Velázquez-Zapata2José Tuxpan-Vargas3Instituto Potosino de Investigación Científica y Tecnológica, A.C. División de Geociencias Aplicadas, Camino a la Presa San José 2055, San Luis Potosí, MexicoInstituto Potosino de Investigación Científica y Tecnológica, A.C. División de Geociencias Aplicadas, Camino a la Presa San José 2055, San Luis Potosí, MexicoCONAHCYT-El Colegio de San Luis, A.C., Parque Macul 155, San Luis Potosí, MexicoCONAHCYT-Instituto Potosino de Investigación Científica y Tecnológica, A.C. División de Geociencias Aplicadas, Camino a la Presa San José 2055, San Luis Potosí, MexicoThe presence of deep convective clouds is directly related to potential convective hazards, such as lightning strikes, hail, severe storms, flash floods, and tornadoes. On the other hand, Mexico has a limited and heterogeneous network of instruments that allow for efficient and reliable monitoring and forecasting of such events. In this study, a quasi-real-time framework for deep convective cloud identification and modeling based on machine learning (ML) models was developed. Eight different ML models and model assembly approaches were fed with Interest Fields estimated from Advanced Baseline Imager (ABI) sensor data on the Geostationary Operational Environmental Satellite-R Series (GOES-R) for one region in central Mexico and another in northeastern Mexico, both selected for their intense convective activity and high levels of vulnerability to severe weather. The results indicate that a simple approach such as Logistic Regression (LR) or Random Forest (RF) can be a good alternative for the identification and simulation of deep convective clouds in both study areas, with a probability of detection of (POD) ≈ 0.84 for Los Mochis and POD of ≈ 0.72 for Mexico City. Similarly, the false alarm ratio (FAR) ≈ 0.2 and FAR ≈ 0.4 values were obtained for Los Mochis and Mexico City, respectively. Finally, a post-processing filter based on lightning incidence (Lightning Filter) was applied with data from the Geostationary Lightning Mapper (GLM) of the GOES-16 satellite, showed great potential to improve the probability of detection (POD) of the ML models. This work sets a precedent for the implementation of an early-warning system for hazards associated with intense convective activity in Mexico.https://www.mdpi.com/2072-4292/16/4/675ABI-GOES dataconvective-hazard forecastingdeep convective cloudsmachine learningquasi-real-time framework |
| spellingShingle | Rodrigo Dávila-Ortiz José Noel Carbajal-Pérez Juan Alberto Velázquez-Zapata José Tuxpan-Vargas Approximation of a Convective-Event-Monitoring System Using GOES-R Data and Ensemble ML Models Remote Sensing ABI-GOES data convective-hazard forecasting deep convective clouds machine learning quasi-real-time framework |
| title | Approximation of a Convective-Event-Monitoring System Using GOES-R Data and Ensemble ML Models |
| title_full | Approximation of a Convective-Event-Monitoring System Using GOES-R Data and Ensemble ML Models |
| title_fullStr | Approximation of a Convective-Event-Monitoring System Using GOES-R Data and Ensemble ML Models |
| title_full_unstemmed | Approximation of a Convective-Event-Monitoring System Using GOES-R Data and Ensemble ML Models |
| title_short | Approximation of a Convective-Event-Monitoring System Using GOES-R Data and Ensemble ML Models |
| title_sort | approximation of a convective event monitoring system using goes r data and ensemble ml models |
| topic | ABI-GOES data convective-hazard forecasting deep convective clouds machine learning quasi-real-time framework |
| url | https://www.mdpi.com/2072-4292/16/4/675 |
| work_keys_str_mv | AT rodrigodavilaortiz approximationofaconvectiveeventmonitoringsystemusinggoesrdataandensemblemlmodels AT josenoelcarbajalperez approximationofaconvectiveeventmonitoringsystemusinggoesrdataandensemblemlmodels AT juanalbertovelazquezzapata approximationofaconvectiveeventmonitoringsystemusinggoesrdataandensemblemlmodels AT josetuxpanvargas approximationofaconvectiveeventmonitoringsystemusinggoesrdataandensemblemlmodels |