Optimizing Radar-Based Rainfall Estimation Using Machine Learning Models
Weather radar research has produced numerous radar-based rainfall estimators based on climate, rainfall intensity, a variety of ground-truthing instruments and sensors (e.g., rain gauges, disdrometers), and techniques. Although each research direction gives improvement, their collective application...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/20/5188 |
| _version_ | 1827648096902840320 |
|---|---|
| author | Diar Hassan George A. Isaac Peter A. Taylor Daniel Michelson |
| author_facet | Diar Hassan George A. Isaac Peter A. Taylor Daniel Michelson |
| author_sort | Diar Hassan |
| collection | DOAJ |
| description | Weather radar research has produced numerous radar-based rainfall estimators based on climate, rainfall intensity, a variety of ground-truthing instruments and sensors (e.g., rain gauges, disdrometers), and techniques. Although each research direction gives improvement, their collective application in an operational sense still yields uncertainty in rainfall estimation at times. This study aims to explore the concept of implementing Machine Learning (ML) models in optimizing the radar-based rainfall estimations at the bin level from a group of estimator. The Canadian King City C-Band radar was used with a GEONOR T-200B rain gauge (a total of 263 sample points) to establish a group of polarimetric-based rainfall estimators (R(Z), R(Z, Z<sub>DR</sub>), R(KDP)). The estimators were used to train three ML models, namely Decision Tree, Random Forest, and Gradient Boost, to choose the optimal rainfall estimators based on radar variables (Z, Z<sub>DR</sub>, KDP). Data from the Canadian Exeter C-Band radar and a Texas Electronics TE525 tipping bucket gauge at a different location were used to verify the ML models and compare their results to the most commonly used Z-R relations. The verification process shows promising results for the ML models, specifically the Gradient Boost model. These encouraging results need to be further explored with more sample points to further refine the ML models. |
| first_indexed | 2024-03-09T19:31:38Z |
| format | Article |
| id | doaj.art-6108ec117d8a4fe6b30f36589d25b918 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T19:31:38Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-6108ec117d8a4fe6b30f36589d25b9182023-11-24T02:21:00ZengMDPI AGRemote Sensing2072-42922022-10-011420518810.3390/rs14205188Optimizing Radar-Based Rainfall Estimation Using Machine Learning ModelsDiar Hassan0George A. Isaac1Peter A. Taylor2Daniel Michelson3WSP Global Inc., Ottawa, ON K2E 7K5, CanadaWeather Impacts Consulting Incorporated, Barrie, ON L4M 4Y8, CanadaCenter for Research in Earth and Space Science, York University, Toronto, ON M3J 1P3, CanadaEnvironment and Climate Change Canada, Toronto, ON L7B 1A3, CanadaWeather radar research has produced numerous radar-based rainfall estimators based on climate, rainfall intensity, a variety of ground-truthing instruments and sensors (e.g., rain gauges, disdrometers), and techniques. Although each research direction gives improvement, their collective application in an operational sense still yields uncertainty in rainfall estimation at times. This study aims to explore the concept of implementing Machine Learning (ML) models in optimizing the radar-based rainfall estimations at the bin level from a group of estimator. The Canadian King City C-Band radar was used with a GEONOR T-200B rain gauge (a total of 263 sample points) to establish a group of polarimetric-based rainfall estimators (R(Z), R(Z, Z<sub>DR</sub>), R(KDP)). The estimators were used to train three ML models, namely Decision Tree, Random Forest, and Gradient Boost, to choose the optimal rainfall estimators based on radar variables (Z, Z<sub>DR</sub>, KDP). Data from the Canadian Exeter C-Band radar and a Texas Electronics TE525 tipping bucket gauge at a different location were used to verify the ML models and compare their results to the most commonly used Z-R relations. The verification process shows promising results for the ML models, specifically the Gradient Boost model. These encouraging results need to be further explored with more sample points to further refine the ML models.https://www.mdpi.com/2072-4292/14/20/5188rainfall estimationradar QPEpolarimetric radarC-band radar algorithmsMachine LearningDecision Tree |
| spellingShingle | Diar Hassan George A. Isaac Peter A. Taylor Daniel Michelson Optimizing Radar-Based Rainfall Estimation Using Machine Learning Models Remote Sensing rainfall estimation radar QPE polarimetric radar C-band radar algorithms Machine Learning Decision Tree |
| title | Optimizing Radar-Based Rainfall Estimation Using Machine Learning Models |
| title_full | Optimizing Radar-Based Rainfall Estimation Using Machine Learning Models |
| title_fullStr | Optimizing Radar-Based Rainfall Estimation Using Machine Learning Models |
| title_full_unstemmed | Optimizing Radar-Based Rainfall Estimation Using Machine Learning Models |
| title_short | Optimizing Radar-Based Rainfall Estimation Using Machine Learning Models |
| title_sort | optimizing radar based rainfall estimation using machine learning models |
| topic | rainfall estimation radar QPE polarimetric radar C-band radar algorithms Machine Learning Decision Tree |
| url | https://www.mdpi.com/2072-4292/14/20/5188 |
| work_keys_str_mv | AT diarhassan optimizingradarbasedrainfallestimationusingmachinelearningmodels AT georgeaisaac optimizingradarbasedrainfallestimationusingmachinelearningmodels AT peterataylor optimizingradarbasedrainfallestimationusingmachinelearningmodels AT danielmichelson optimizingradarbasedrainfallestimationusingmachinelearningmodels |