The Value of Large‐Scale Climatic Indices for Monthly Forecasting Severity of Widespread Flooding Using Dilated Convolutional Neural Networks
Abstract Spatially co‐occurring floods pose a threat to the resilience and recovery of the communities. Their timely forecasting plays a crucial role for increasing flood preparedness and limiting associated losses. In this study we investigated the potential of a dilated Convolutional Neural Networ...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-02-01
|
| Series: | Earth's Future |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2023EF003680 |
| _version_ | 1797276972090392576 |
|---|---|
| author | Larisa Tarasova Bodo Ahrens Amelie Hoff Upmanu Lall |
| author_facet | Larisa Tarasova Bodo Ahrens Amelie Hoff Upmanu Lall |
| author_sort | Larisa Tarasova |
| collection | DOAJ |
| description | Abstract Spatially co‐occurring floods pose a threat to the resilience and recovery of the communities. Their timely forecasting plays a crucial role for increasing flood preparedness and limiting associated losses. In this study we investigated the potential of a dilated Convolutional Neural Network (dCNN) model conditioned on large‐scale climatic indices and antecedent precipitation to forecast monthly severity of widespread flooding (i.e., spatially co‐occurring floods) in Germany with 1 month lead time. The severity was estimated from 63 years of daily streamflow series as the sum of concurrent exceedances of at‐site 2‐year return periods within a given month across 172 mesoscale catchments (median area 516 km2). The model was trained individually for the whole country and three diverse hydroclimatic regions to provide insights on heterogeneity of model performance and flood drivers. Our results showed a considerable potential for forecasting widespread flood severity using dCNN especially as the length of training series increases. However, event‐based evaluation of model skill indicates large underestimation for rainfall‐generated floods during dry conditions despite overall lower severity of these events compared to the rain‐on‐snow floods. Feature attribution and wavelet coherence analyses both indicated considerable difference in the major flood drivers in three regions. While the flooding in North‐Eastern region is strongly affected by the Baltic Sea, the North‐Western region is affected more by global patterns associated with the El‐Niño activity. In the Southern region in addition to global patterns we detected the effect of the Mediterranean Sea, while antecedent precipitation plays a less important role in this region. |
| first_indexed | 2024-03-07T15:37:03Z |
| format | Article |
| id | doaj.art-c33d48560869430d893540345f34cc82 |
| institution | Directory Open Access Journal |
| issn | 2328-4277 |
| language | English |
| last_indexed | 2024-03-07T15:37:03Z |
| publishDate | 2024-02-01 |
| publisher | Wiley |
| record_format | Article |
| series | Earth's Future |
| spelling | doaj.art-c33d48560869430d893540345f34cc822024-03-05T11:10:50ZengWileyEarth's Future2328-42772024-02-01122n/an/a10.1029/2023EF003680The Value of Large‐Scale Climatic Indices for Monthly Forecasting Severity of Widespread Flooding Using Dilated Convolutional Neural NetworksLarisa Tarasova0Bodo Ahrens1Amelie Hoff2Upmanu Lall3Department Catchment Hydrology Helmholtz Centre for Environmental Research—UFZ Halle (Saale) GermanyInstitute for Atmospheric and Environmental Sciences Goethe University Frankfurt am Main Frankfurt am Main GermanyInstitute for Atmospheric and Environmental Sciences Goethe University Frankfurt am Main Frankfurt am Main GermanyDepartment of Earth and Environmental Engineering Columbia University in the City of New York New York NY USAAbstract Spatially co‐occurring floods pose a threat to the resilience and recovery of the communities. Their timely forecasting plays a crucial role for increasing flood preparedness and limiting associated losses. In this study we investigated the potential of a dilated Convolutional Neural Network (dCNN) model conditioned on large‐scale climatic indices and antecedent precipitation to forecast monthly severity of widespread flooding (i.e., spatially co‐occurring floods) in Germany with 1 month lead time. The severity was estimated from 63 years of daily streamflow series as the sum of concurrent exceedances of at‐site 2‐year return periods within a given month across 172 mesoscale catchments (median area 516 km2). The model was trained individually for the whole country and three diverse hydroclimatic regions to provide insights on heterogeneity of model performance and flood drivers. Our results showed a considerable potential for forecasting widespread flood severity using dCNN especially as the length of training series increases. However, event‐based evaluation of model skill indicates large underestimation for rainfall‐generated floods during dry conditions despite overall lower severity of these events compared to the rain‐on‐snow floods. Feature attribution and wavelet coherence analyses both indicated considerable difference in the major flood drivers in three regions. While the flooding in North‐Eastern region is strongly affected by the Baltic Sea, the North‐Western region is affected more by global patterns associated with the El‐Niño activity. In the Southern region in addition to global patterns we detected the effect of the Mediterranean Sea, while antecedent precipitation plays a less important role in this region.https://doi.org/10.1029/2023EF003680flood forecastingneural networksdeep learningflood generation processesclimatic driversclimatic indices |
| spellingShingle | Larisa Tarasova Bodo Ahrens Amelie Hoff Upmanu Lall The Value of Large‐Scale Climatic Indices for Monthly Forecasting Severity of Widespread Flooding Using Dilated Convolutional Neural Networks Earth's Future flood forecasting neural networks deep learning flood generation processes climatic drivers climatic indices |
| title | The Value of Large‐Scale Climatic Indices for Monthly Forecasting Severity of Widespread Flooding Using Dilated Convolutional Neural Networks |
| title_full | The Value of Large‐Scale Climatic Indices for Monthly Forecasting Severity of Widespread Flooding Using Dilated Convolutional Neural Networks |
| title_fullStr | The Value of Large‐Scale Climatic Indices for Monthly Forecasting Severity of Widespread Flooding Using Dilated Convolutional Neural Networks |
| title_full_unstemmed | The Value of Large‐Scale Climatic Indices for Monthly Forecasting Severity of Widespread Flooding Using Dilated Convolutional Neural Networks |
| title_short | The Value of Large‐Scale Climatic Indices for Monthly Forecasting Severity of Widespread Flooding Using Dilated Convolutional Neural Networks |
| title_sort | value of large scale climatic indices for monthly forecasting severity of widespread flooding using dilated convolutional neural networks |
| topic | flood forecasting neural networks deep learning flood generation processes climatic drivers climatic indices |
| url | https://doi.org/10.1029/2023EF003680 |
| work_keys_str_mv | AT larisatarasova thevalueoflargescaleclimaticindicesformonthlyforecastingseverityofwidespreadfloodingusingdilatedconvolutionalneuralnetworks AT bodoahrens thevalueoflargescaleclimaticindicesformonthlyforecastingseverityofwidespreadfloodingusingdilatedconvolutionalneuralnetworks AT ameliehoff thevalueoflargescaleclimaticindicesformonthlyforecastingseverityofwidespreadfloodingusingdilatedconvolutionalneuralnetworks AT upmanulall thevalueoflargescaleclimaticindicesformonthlyforecastingseverityofwidespreadfloodingusingdilatedconvolutionalneuralnetworks AT larisatarasova valueoflargescaleclimaticindicesformonthlyforecastingseverityofwidespreadfloodingusingdilatedconvolutionalneuralnetworks AT bodoahrens valueoflargescaleclimaticindicesformonthlyforecastingseverityofwidespreadfloodingusingdilatedconvolutionalneuralnetworks AT ameliehoff valueoflargescaleclimaticindicesformonthlyforecastingseverityofwidespreadfloodingusingdilatedconvolutionalneuralnetworks AT upmanulall valueoflargescaleclimaticindicesformonthlyforecastingseverityofwidespreadfloodingusingdilatedconvolutionalneuralnetworks |