Brief communication: Training of AI-based nowcasting models for rainfall early warning should take into account user requirements
<p>In the field of precipitation nowcasting, deep learning (DL) has emerged as an alternative to conventional tracking and extrapolation techniques. However, DL struggles to adequately predict heavy precipitation, which is essential in early warning. By taking into account specific user requir...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2025-01-01
|
| Series: | Natural Hazards and Earth System Sciences |
| Online Access: | https://nhess.copernicus.org/articles/25/41/2025/nhess-25-41-2025.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841561053682466816 |
|---|---|
| author | G. Ayzel M. Heistermann |
| author_facet | G. Ayzel M. Heistermann |
| author_sort | G. Ayzel |
| collection | DOAJ |
| description | <p>In the field of precipitation nowcasting, deep learning (DL) has emerged as an alternative to conventional tracking and extrapolation techniques. However, DL struggles to adequately predict heavy precipitation, which is essential in early warning. By taking into account specific user requirements, though, we can simplify the training task and boost predictive skill. As an example, we predict the cumulative precipitation of the next hour (instead of 5 min increments) and the exceedance of thresholds (instead of numerical values). A dialogue between developers and users should identify the requirements to a nowcast and how to consider these in model training.</p> |
| format | Article |
| id | doaj-art-a5798511eab54f918e8b19468880fb42 |
| institution | Kabale University |
| issn | 1561-8633 1684-9981 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Natural Hazards and Earth System Sciences |
| spelling | doaj-art-a5798511eab54f918e8b19468880fb422025-01-03T06:40:30ZengCopernicus PublicationsNatural Hazards and Earth System Sciences1561-86331684-99812025-01-0125414710.5194/nhess-25-41-2025Brief communication: Training of AI-based nowcasting models for rainfall early warning should take into account user requirementsG. Ayzel0M. Heistermann1Institute for Environmental Sciences and Geography, University of Potsdam, Potsdam, GermanyInstitute for Environmental Sciences and Geography, University of Potsdam, Potsdam, Germany<p>In the field of precipitation nowcasting, deep learning (DL) has emerged as an alternative to conventional tracking and extrapolation techniques. However, DL struggles to adequately predict heavy precipitation, which is essential in early warning. By taking into account specific user requirements, though, we can simplify the training task and boost predictive skill. As an example, we predict the cumulative precipitation of the next hour (instead of 5 min increments) and the exceedance of thresholds (instead of numerical values). A dialogue between developers and users should identify the requirements to a nowcast and how to consider these in model training.</p>https://nhess.copernicus.org/articles/25/41/2025/nhess-25-41-2025.pdf |
| spellingShingle | G. Ayzel M. Heistermann Brief communication: Training of AI-based nowcasting models for rainfall early warning should take into account user requirements Natural Hazards and Earth System Sciences |
| title | Brief communication: Training of AI-based nowcasting models for rainfall early warning should take into account user requirements |
| title_full | Brief communication: Training of AI-based nowcasting models for rainfall early warning should take into account user requirements |
| title_fullStr | Brief communication: Training of AI-based nowcasting models for rainfall early warning should take into account user requirements |
| title_full_unstemmed | Brief communication: Training of AI-based nowcasting models for rainfall early warning should take into account user requirements |
| title_short | Brief communication: Training of AI-based nowcasting models for rainfall early warning should take into account user requirements |
| title_sort | brief communication training of ai based nowcasting models for rainfall early warning should take into account user requirements |
| url | https://nhess.copernicus.org/articles/25/41/2025/nhess-25-41-2025.pdf |
| work_keys_str_mv | AT gayzel briefcommunicationtrainingofaibasednowcastingmodelsforrainfallearlywarningshouldtakeintoaccountuserrequirements AT mheistermann briefcommunicationtrainingofaibasednowcastingmodelsforrainfallearlywarningshouldtakeintoaccountuserrequirements |