Machine-Learning-Based Precipitation Reconstructions: A Study on Slovenia’s Sava River Basin
The Sava River Basin (SRB) includes six countries (Slovenia, Croatia, Bosnia and Herzegovina, Serbia, Albania, and Montenegro), with the Sava River (SR) being a major tributary of the Danube River. The SR originates in the mountains (European Alps) of Slovenia and, because of a recent Slovenian gove...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Hydrology |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5338/10/11/207 |
| _version_ | 1797459110558433280 |
|---|---|
| author | Abel Andrés Ramírez Molina Nejc Bezak Glenn Tootle Chen Wang Jiaqi Gong |
| author_facet | Abel Andrés Ramírez Molina Nejc Bezak Glenn Tootle Chen Wang Jiaqi Gong |
| author_sort | Abel Andrés Ramírez Molina |
| collection | DOAJ |
| description | The Sava River Basin (SRB) includes six countries (Slovenia, Croatia, Bosnia and Herzegovina, Serbia, Albania, and Montenegro), with the Sava River (SR) being a major tributary of the Danube River. The SR originates in the mountains (European Alps) of Slovenia and, because of a recent Slovenian government initiative to increase clean, sustainable energy, multiple hydropower facilities have been constructed within the past ~20 years. Given the importance of this river system for varying demands, including hydropower (energy production), information about past (paleo) dry (drought) and wet (pluvial) periods would provide important information to water managers and planners. Recent research applying traditional regression techniques and methods developed skillful reconstructions of seasonal (April–May–June–July–August–September or AMJJAS) streamflow using tree-ring-based proxies. The current research intends to expand upon these recent research efforts and investigate developing reconstructions of seasonal (AMJJAS) precipitation applying novel Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) techniques. When comparing the reconstructed AMJJAS precipitation datasets, the AI/ML/DL techniques statistically outperformed traditional regression techniques. When comparing the SRB AMJJAS precipitation reconstruction developed in this research to the SRB AMJJAS streamflow reconstruction developed in previous research, the temporal variability of the two reconstructions compared favorably. However, pluvial magnitudes of extreme periods differed, while drought magnitudes of extreme periods were similar, confirming drought is likely better captured in tree-ring-based proxy reconstructions of hydrologic variables. |
| first_indexed | 2024-03-09T16:46:44Z |
| format | Article |
| id | doaj.art-333eb59e89ba4c26a09d5188c28d1af7 |
| institution | Directory Open Access Journal |
| issn | 2306-5338 |
| language | English |
| last_indexed | 2024-03-09T16:46:44Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Hydrology |
| spelling | doaj.art-333eb59e89ba4c26a09d5188c28d1af72023-11-24T14:45:25ZengMDPI AGHydrology2306-53382023-11-01101120710.3390/hydrology10110207Machine-Learning-Based Precipitation Reconstructions: A Study on Slovenia’s Sava River BasinAbel Andrés Ramírez Molina0Nejc Bezak1Glenn Tootle2Chen Wang3Jiaqi Gong4Department of Computer Science, University of Alabama, Tuscaloosa, AL 35487, USAFaculty of Civil Engineering and Geodesy, University of Ljubljana, 1000 Ljubljana, SloveniaDepartment of Civil, Construction and Environmental Engineering, University of Alabama, Tuscaloosa, AL 35487, USADepartment of Computer Science, University of Alabama, Tuscaloosa, AL 35487, USADepartment of Computer Science, University of Alabama, Tuscaloosa, AL 35487, USAThe Sava River Basin (SRB) includes six countries (Slovenia, Croatia, Bosnia and Herzegovina, Serbia, Albania, and Montenegro), with the Sava River (SR) being a major tributary of the Danube River. The SR originates in the mountains (European Alps) of Slovenia and, because of a recent Slovenian government initiative to increase clean, sustainable energy, multiple hydropower facilities have been constructed within the past ~20 years. Given the importance of this river system for varying demands, including hydropower (energy production), information about past (paleo) dry (drought) and wet (pluvial) periods would provide important information to water managers and planners. Recent research applying traditional regression techniques and methods developed skillful reconstructions of seasonal (April–May–June–July–August–September or AMJJAS) streamflow using tree-ring-based proxies. The current research intends to expand upon these recent research efforts and investigate developing reconstructions of seasonal (AMJJAS) precipitation applying novel Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) techniques. When comparing the reconstructed AMJJAS precipitation datasets, the AI/ML/DL techniques statistically outperformed traditional regression techniques. When comparing the SRB AMJJAS precipitation reconstruction developed in this research to the SRB AMJJAS streamflow reconstruction developed in previous research, the temporal variability of the two reconstructions compared favorably. However, pluvial magnitudes of extreme periods differed, while drought magnitudes of extreme periods were similar, confirming drought is likely better captured in tree-ring-based proxy reconstructions of hydrologic variables.https://www.mdpi.com/2306-5338/10/11/207Sava River Basintree-ring reconstructionprecipitationmachine learning |
| spellingShingle | Abel Andrés Ramírez Molina Nejc Bezak Glenn Tootle Chen Wang Jiaqi Gong Machine-Learning-Based Precipitation Reconstructions: A Study on Slovenia’s Sava River Basin Hydrology Sava River Basin tree-ring reconstruction precipitation machine learning |
| title | Machine-Learning-Based Precipitation Reconstructions: A Study on Slovenia’s Sava River Basin |
| title_full | Machine-Learning-Based Precipitation Reconstructions: A Study on Slovenia’s Sava River Basin |
| title_fullStr | Machine-Learning-Based Precipitation Reconstructions: A Study on Slovenia’s Sava River Basin |
| title_full_unstemmed | Machine-Learning-Based Precipitation Reconstructions: A Study on Slovenia’s Sava River Basin |
| title_short | Machine-Learning-Based Precipitation Reconstructions: A Study on Slovenia’s Sava River Basin |
| title_sort | machine learning based precipitation reconstructions a study on slovenia s sava river basin |
| topic | Sava River Basin tree-ring reconstruction precipitation machine learning |
| url | https://www.mdpi.com/2306-5338/10/11/207 |
| work_keys_str_mv | AT abelandresramirezmolina machinelearningbasedprecipitationreconstructionsastudyonsloveniassavariverbasin AT nejcbezak machinelearningbasedprecipitationreconstructionsastudyonsloveniassavariverbasin AT glenntootle machinelearningbasedprecipitationreconstructionsastudyonsloveniassavariverbasin AT chenwang machinelearningbasedprecipitationreconstructionsastudyonsloveniassavariverbasin AT jiaqigong machinelearningbasedprecipitationreconstructionsastudyonsloveniassavariverbasin |