Pasar al contenido principal

HACIA UNA EXPLOTACION INTELIGENTE DE LOS DATOS DE MOVIMIENTOS DEL TERRENO PARA LA PREVENCION Y MITIGACION DE RIESGOS GEOLOGICO-GEOTECNICOS

PRE2021-100044

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Desarrollar, Atraer y Retener Talento
Subprograma Subprograma Estatal de Formación
Convocatoria Contratos Predoctorales
Año convocatoria 2021
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario AGENCIA ESTATAL CONSEJO SUPERIOR DE INVESTIGACIONES CIENTIFICAS (CSIC)

Resultados relacionados

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

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

Enhancing groundwater management with GRACE-based groundwater estimates from GLDAS-2.2: a case study of the Almonte-Marismas aquifer, Spain

  • Guardiola Albert, Carolina
  • Naranjo Fernández, Nuria
  • Rivera, Jhonathan
  • Gómez-Fontalva, J.M.
  • Aguilera Alonso, Héctor
  • Ruiz Bermudo, Fernando
  • Rodríguez Rodríguez, Miguel
[EN] The Almonte-Marismas aquifer, southwestern Spain, is a critical ecohydrogeological system that features extensive groundwater monitoring. This study investigates the utility of gravity recovery and climate experiment (GRACE) satellite data, specifically obtained from the global land data assimilation system (GLDAS) version 2.2, for assessing groundwater storage variations in the Almonte-Marismas aquifer. The presented research emphasizes the practical application of readily available GLDAS products that do not require data preprocessing. The study validates the GLDAS-2.2-based ready-to-use groundwater storage (GWS) time series by correlating it with precipitation and piezometric information, highlighting its effectiveness in medium-scale aquifers. The results reveal a strong agreement between GLDAS-2.2-derived GWS anomalies and in-situ measurements, confirming GLDAS-2.2’s potential for assessing aquifer depletion. The study discusses the consistency of seasonal variations in groundwater levels and GLDAS-2.2 data, emphasizing their close alignment with precipitation and pumping activities. Importantly, the study introduces GLDAS-2.2-derived volumetric groundwater storage (VGWS) as a valuable calibration parameter for numerical groundwater flow models, enhancing their accuracy over time. Moreover, the analysis reveals disparities in annual recharge values between GLDAS-2.2-derived data and the soil-water mass balance. These variations suggest the importance of additional inputs to precipitation, possibly related to subsurface or lateral connections. Overall, this study contributes to the ongoing discourse on the practical applications of GLDAS-2.2-derived GWS data in groundwater management, offering insights into its effectiveness in diverse hydrogeological settings, particularly in areas that lack monitoring infrastructure., Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. The work performed by Jhonatan S. Rivera-Rivera has been developed thanks to the pre-doctoral grant for the Training of Research Personnel (PRE2021-100044) funded by MCIN/AEI/https://doi.org/10.13039/501100011033., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Hierarchical machine learning for the automatic classification of surface deformation from SAR observations

  • Rivera, Jhonathan
  • Aguilera Alonso, Héctor
  • Béjar Pizarro, Marta
  • Guardiola Albert, Carolina
  • Ezquerro Martín, Pablo
  • Barra, Anna
19 p., Ground deformation processes, such as landslides and subsidence, cause significant social, economic, and environmental impacts. This study aims to automatically classify ground deformation processes in Spain using a machine learning approach applied to InSAR-based datasets. The database integrates InSAR measurement points (MPs) from 20 case studies in Spain, obtained from various institutional sources, and 32 geoenvironmental variables related to ground deformation, morphometry, geology, climate, and land use. The proposed classification strategy follows a hierarchical structure with two levels: first, distinguishing between landslides and subsidence; then, identifying the specific type within each main class (mining landslide, environmental landslide, constructive subsidence, mining subsidence, and piezometric subsidence). Several machine learning algorithms (Naïve Bayes, Logistic Regression, Decision Tree, Random Forest, Extra Trees, Gradient Boosting Machine, XGBoost, LightGBM, and CatBoost) and data configurations were tested, combining different spatial resolutions and class balancing techniques. The best performance (Cohen's Kappa = 0.78) was achieved with the hierarchical approach using the 200 m grid dataset, applying XGBoost for the parental and landslide models, and CatBoost for the subsidence model. Using this approach, 70 % de test sites achieved over 88 % correctly classified cells, 20 % had between 50 % and 83 %, and only one test case was entirely misclassified. The analysis of the most relevant variables indicates that annual mean precipitation, mining activity, buildings, landslide susceptibility, and slope are key factors. These results demonstrate the potential of the hierarchical approach to improve classification and lay the groundwork for future application at national and European scales, incorporating new training cases, process types, and continental data sources. In conclusion, this study presents, for the first time, a hierarchical machine learning model capable of accurately classifying ground deformation processes in Spain, with the aim of supporting territorial management and geohazard mitigation., This work was supported by Ministry of Science, Innovation and Universities (MCIN), State Investigation Agency (AEI), and the European Social Fund through the initiative “FSE invests in your future”. This work is part of the PhD thesis of Jhonatan Rivera Rivera and was supported by Grant PRE2021-100044, funded by MCIN/AEI/10.13039/501100011033 and “FSE invests in your future”; by (SARAI) Project PID2020-116540RB-C22 funded by MCIN/AEI/10.13039/501100011033., Peer reviewed