Pasar al contenido principal

Un servicio web para la evaluación sectorial del cambio climático a medida

CPP2021-008510

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprograma Subprograma Estatal de Transferencia de Conocimiento
Convocatoria Proyectos en Colaboración Público-Privada
Año convocatoria 2021
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario PREDICTIA INTELLIGENT DATA SOLUTIONS SL

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

A data-driven approach for the assessment of the thermal stratification of reservoirs based on readily available data

  • Castrillo, María
  • Aguilar, Fernando
  • García Díaz, Daniel
A data-driven approach to assess the occurrence of thermal stratification and the depth of the thermocline in water masses has been developed and tested in the Spanish reservoir of El Val. The novelty of this approach is that it relies only on readily available data that can be collected for almost any reservoir, providing water managers with a transferable tool that can be easily adapted for any other reservoirs or lakes. The input variables were meteorological data, the water level and the output flow. A non-supervised clustering technique, k-means, was used to identify the stratification period with unlabelled data, that is to say inferring patterns when data from the target variable is not available. As a supervised method, Artificial Neural Networks were used to classify a given day as having or not having stratification and, in the positive case, to infer the depth of the thermocline. The classification showed a very high accuracy (96%) and the estimation of the thermocline depth showed a mean absolute error (MAE) of 1.94 m and 1.99 m in the training and test fractions, respectively. Shapley Additive Explanations (SHAP) values were used to improve the explainability and they revealed that the most important features to infer the depth of the thermocline were the water level, the daily average solar irradiance and the air temperature., The authors acknowledge the support from the Project CPP2021-008510 “Un Servicio Web Para la evaluación Sectorial del Cambio Climático a Medida”, funded by the Ministerio de Ciencia e Innovación. The authors also would like to acknowledge the data availability from the Confederación Hidrográfica del Ebro (CHE) through the SAICA Ebro and the SAIH Ebro., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Are deep learning methods suitable for downscaling global climate projections? An intercomparison for temperature and precipitation over Spain

  • González-Abad, Jose
  • Gutiérrez, José M.
Data availability statement: All the data necessary to reproduce the experiments in this study are publicly available. ERA5 data can be downloaded from the C3S Climate Data Store after registration and acceptance of the licensing terms (https://doi.org/10.24381/cds.50314f4c). Data from EC-Earth3-Veg, MPI-ESM1-2-LR, and CMCC-CM2-SR5 can be accessed through the Earth System Grid Federation (ESGF) portal (https://esgf-data.dkrz.de) by selecting the CMIP6 project and the CMIP activity. The ROCIO-IBEB dataset is available on the AEMET website (https://www.aemet.es/en/serviciosclimaticos/cambio_climat/datos_diarios?w=2); however, please note that this web page is only available in Spanish. To download minimum and maximum temperature data, locate the tar.gz files under section 2, Rejillas ROCIO_IBEB de temperaturas diarias extremas. For precipitation data, refer to section 1, Rejilla ROCIO_IBEB de precipitación. The code used to reproduce these experiments is publicly accessible at https://doi.org/10.5281/zenodo.14016954., Deep learning (DL) has shown promise for downscaling global climate change projections under different approaches, including perfect prognosis (PP) and regional climate model (RCM) emulation. Unlike emulators, PP downscaling models are trained on observational data, so it remains an open question whether they can plausibly extrapolate unseen conditions and changes in future emissions scenarios. Here, we focus on this problem as the main drawback for the operationalization of these methods and present the results of an intercomparison experiment to evaluate the performance and extrapolation capability of existing models using a common experimental framework, taking into account the sensitivity of results to different training replicas. We focus on minimum and maximum temperatures and precipitation over Spain, a region with a range of climatic conditions with different influential regional processes. We conclude with a discussion of the findings, limitations of existing methods, and prospects for future development., [Significance Statement] Deep learning techniques have recently emerged as a promising approach to enhance the spatial resolution of coarse climate models, a process known as statistical downscaling. In this study, we review current methods and evaluate two popular models, ensemble of convolutional neural network (CNN)-based downscaled projections (DeepESD) and U-Net, to assess their ability to project future climate changes over Spain, a region characterized by diverse and complex climates. While both models perform well with historical data, their effectiveness in projecting future periods varies. DeepESD demonstrates particular promise when tailored to focus on extreme events, though challenges persist in accurately modeling such events under changing climate conditions. This work provides guidance for advancing climate downscaling with deep learning, identifying the key areas for further research., This work was partially supported by the project ATLAS (PID2019-717 111481RB-I00) funded by MCIN/AEI/10.13039/501100011033. González-Abad acknowledges support from Grant CPP2021-008510 funded by MICIU/AEI/10.13039/501100011033 and by the “European Union” and the “European Union NextGenerationEU/PRTR,” as well as from Project COMPOUND (TED2021-131334A-I00) funded by MCIU/AEI/10.13039/501100011033 and by the European Union NextGenerationEU/PRTR., Peer reviewed