Hybrid forecasting: blending climate predictions with AI models
<p>Hybrid hydroclimatic forecasting systems employ data-driven (statistical or machine learning) methods to harness and integrate a broad variety of predictions from dynamical, physics-based models – such as numerical weather prediction, climate, land, hydrology, and Earth system models – into...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2023-05-01
|
| Series: | Hydrology and Earth System Sciences |
| Online Access: | https://hess.copernicus.org/articles/27/1865/2023/hess-27-1865-2023.pdf |
| _version_ | 1827947295457411072 |
|---|---|
| author | L. J. Slater L. Arnal M.-A. Boucher A. Y.-Y. Chang A. Y.-Y. Chang S. Moulds C. Murphy G. Nearing G. Shalev C. Shen L. Speight G. Villarini R. L. Wilby A. Wood M. Zappa |
| author_facet | L. J. Slater L. Arnal M.-A. Boucher A. Y.-Y. Chang A. Y.-Y. Chang S. Moulds C. Murphy G. Nearing G. Shalev C. Shen L. Speight G. Villarini R. L. Wilby A. Wood M. Zappa |
| author_sort | L. J. Slater |
| collection | DOAJ |
| description | <p>Hybrid hydroclimatic forecasting systems employ data-driven (statistical or machine learning) methods to harness and integrate a broad variety of
predictions from dynamical, physics-based models – such as numerical weather prediction, climate, land, hydrology, and Earth system models – into a final prediction product. They are recognized as a promising way of enhancing the prediction skill of meteorological and hydroclimatic variables and events, including rainfall, temperature, streamflow, floods, droughts, tropical cyclones, or atmospheric rivers. Hybrid forecasting methods are now receiving growing attention due to advances in weather and climate prediction systems at subseasonal to decadal scales, a better appreciation of the strengths of AI, and expanding access to computational resources and methods. Such systems are attractive because they may avoid the need to run a computationally expensive offline land model, can minimize the effect of biases that exist within dynamical outputs, benefit from the strengths of machine learning, and can learn from large datasets, while combining different sources of predictability with varying time horizons. Here we review recent developments in hybrid hydroclimatic forecasting and outline key challenges and opportunities for further research. These include obtaining physically explainable results, assimilating human influences from novel data sources, integrating new ensemble techniques to improve predictive skill, creating seamless prediction schemes that merge short to long lead times, incorporating
initial land surface and ocean/ice conditions, acknowledging spatial variability in landscape and atmospheric forcing, and increasing the operational uptake of hybrid prediction schemes.</p> |
| first_indexed | 2024-04-09T12:37:49Z |
| format | Article |
| id | doaj.art-a3319d8c27b9466ea2e0d6a22320a892 |
| institution | Directory Open Access Journal |
| issn | 1027-5606 1607-7938 |
| language | English |
| last_indexed | 2024-04-09T12:37:49Z |
| publishDate | 2023-05-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Hydrology and Earth System Sciences |
| spelling | doaj.art-a3319d8c27b9466ea2e0d6a22320a8922023-05-15T07:41:12ZengCopernicus PublicationsHydrology and Earth System Sciences1027-56061607-79382023-05-01271865188910.5194/hess-27-1865-2023Hybrid forecasting: blending climate predictions with AI modelsL. J. Slater0L. Arnal1M.-A. Boucher2A. Y.-Y. Chang3A. Y.-Y. Chang4S. Moulds5C. Murphy6G. Nearing7G. Shalev8C. Shen9L. Speight10G. Villarini11R. L. Wilby12A. Wood13M. Zappa14School of Geography and the Environment, University of Oxford, Oxford, UKCentre for Hydrology, University of Saskatchewan, Canmore, CanadaDepartment of Civil Engineering, Université de Sherbrooke, Sherbrooke, CanadaSwiss Federal Research Institute WSL, Birmensdorf, SwitzerlandInstitute for Atmospheric and Climate Science, ETH Zürich, Zurich, SwitzerlandSchool of Geography and the Environment, University of Oxford, Oxford, UKIrish Climate Analysis and Research Units, Department of Geography, Maynooth University, Kildare, IrelandGoogle Research, Mountain View, CA, USAGoogle Research, Tel Aviv, IsraelCivil and Environmental Engineering, Pennsylvania State University, State College, PA 16801, USASchool of Geography and the Environment, University of Oxford, Oxford, UKIIHR – Hydroscience and Engineering, University of Iowa, IA, USAGeography and Environment, Loughborough University, Loughborough, UKNational Center for Atmospheric Research, Climate and Global Dynamics, Boulder, CO, USASwiss Federal Research Institute WSL, Birmensdorf, Switzerland<p>Hybrid hydroclimatic forecasting systems employ data-driven (statistical or machine learning) methods to harness and integrate a broad variety of predictions from dynamical, physics-based models – such as numerical weather prediction, climate, land, hydrology, and Earth system models – into a final prediction product. They are recognized as a promising way of enhancing the prediction skill of meteorological and hydroclimatic variables and events, including rainfall, temperature, streamflow, floods, droughts, tropical cyclones, or atmospheric rivers. Hybrid forecasting methods are now receiving growing attention due to advances in weather and climate prediction systems at subseasonal to decadal scales, a better appreciation of the strengths of AI, and expanding access to computational resources and methods. Such systems are attractive because they may avoid the need to run a computationally expensive offline land model, can minimize the effect of biases that exist within dynamical outputs, benefit from the strengths of machine learning, and can learn from large datasets, while combining different sources of predictability with varying time horizons. Here we review recent developments in hybrid hydroclimatic forecasting and outline key challenges and opportunities for further research. These include obtaining physically explainable results, assimilating human influences from novel data sources, integrating new ensemble techniques to improve predictive skill, creating seamless prediction schemes that merge short to long lead times, incorporating initial land surface and ocean/ice conditions, acknowledging spatial variability in landscape and atmospheric forcing, and increasing the operational uptake of hybrid prediction schemes.</p>https://hess.copernicus.org/articles/27/1865/2023/hess-27-1865-2023.pdf |
| spellingShingle | L. J. Slater L. Arnal M.-A. Boucher A. Y.-Y. Chang A. Y.-Y. Chang S. Moulds C. Murphy G. Nearing G. Shalev C. Shen L. Speight G. Villarini R. L. Wilby A. Wood M. Zappa Hybrid forecasting: blending climate predictions with AI models Hydrology and Earth System Sciences |
| title | Hybrid forecasting: blending climate predictions with AI models |
| title_full | Hybrid forecasting: blending climate predictions with AI models |
| title_fullStr | Hybrid forecasting: blending climate predictions with AI models |
| title_full_unstemmed | Hybrid forecasting: blending climate predictions with AI models |
| title_short | Hybrid forecasting: blending climate predictions with AI models |
| title_sort | hybrid forecasting blending climate predictions with ai models |
| url | https://hess.copernicus.org/articles/27/1865/2023/hess-27-1865-2023.pdf |
| work_keys_str_mv | AT ljslater hybridforecastingblendingclimatepredictionswithaimodels AT larnal hybridforecastingblendingclimatepredictionswithaimodels AT maboucher hybridforecastingblendingclimatepredictionswithaimodels AT ayychang hybridforecastingblendingclimatepredictionswithaimodels AT ayychang hybridforecastingblendingclimatepredictionswithaimodels AT smoulds hybridforecastingblendingclimatepredictionswithaimodels AT cmurphy hybridforecastingblendingclimatepredictionswithaimodels AT gnearing hybridforecastingblendingclimatepredictionswithaimodels AT gshalev hybridforecastingblendingclimatepredictionswithaimodels AT cshen hybridforecastingblendingclimatepredictionswithaimodels AT lspeight hybridforecastingblendingclimatepredictionswithaimodels AT gvillarini hybridforecastingblendingclimatepredictionswithaimodels AT rlwilby hybridforecastingblendingclimatepredictionswithaimodels AT awood hybridforecastingblendingclimatepredictionswithaimodels AT mzappa hybridforecastingblendingclimatepredictionswithaimodels |