.png){kind=icon}
Return
Data dependency in deep learning-based multi-scale fracture system characterization using hydrogeophysical data
.png){kind=icon}
PRE
AI
DOI：10.1016/j.jclepro.2026.148273.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Multi-scale data dependency is quantified for improved fracture system characterization. • A surrogate modeling framework enables cross-model performance evaluation. • Multi-source data fusion reduces inversion errors and improves model robustness.
Keywords:
multi-scale fracture system
deep learning
hydrogeophysical data
data dependency
surrogate modeling
Journal
IF:
10
Papers:
4.7W
Citations:
36.8W
Organization
Cited Papers
Evaluating the long-term barrier performance of fractured granite for nuclear waste disposal: Impact of fast water-conducting path.png)
ENGINEERING GEOLOGY
ENGINEERING GEOLOGYIF8.4
PREAI
ShareSaveShareSave
Uncertainty and sensitivity analysis of the chemistry of cesium sorption in deep geological repositoriesAPPLIED GEOCHEMISTRY
APPLIED GEOCHEMISTRYIF3.4
PREAI
ShareSaveDeep learning-based inversion framework by assimilating hydrogeological and geophysical data for an enhanced geothermal system characterization and thermal performance predictionENERGY
ENERGYIF9.4
PREAI
ShareSaveEvolution of fracture aperture and thermal productivity influenced by chemical reaction in enhanced geothermal systemRENEWABLE ENERGY
RENEWABLE ENERGYIF9.1
PREAI
ShareSaveShareSave
View more