Search

There is an increasing interest in creating high-resolution 3D subsurface geo-models using multisource retrieved data, i.e., borehole, geophysical techniques, geological maps, and rock properties, for emergency managements. However, dedicating meaningful, and thus interpretable 3D subsurface views from such integrated heterogeneous data requires developing a new methodology for convenient post-modeling analyses. To this end, in the current paper a hybrid ensemble-based automated deep learning approach for 3D modeling of subsurface geological bedrock using multisource data is proposed. The uncertainty then was quantified using a novel ensemble randomly automated deactivating process implanted on the jointed weight database. The applicability of the automated process in capturing the optimum topology is then validated by creating 3D subsurface geo-model using laser-scanned bedrock-level data from Sweden. In comparison with intelligent quantile regression and traditional geostatistical interpolation algorithms, the proposed hybrid approach showed higher accuracy for visualizing and post-analyzing the 3D subsurface model. Due to the use of integrated multi-source data, the approach presented here and the subsequently created 3D model can be a representative reconcile for geoengineering applications., QC 20240807

Uncertainty quantification (UQ) is an important benchmark to assess the performance of artificial intelligence (AI) and particularly deep learning ensembled-based models. However, the ability for UQ using current AI-based methods is not only limited in terms of computational resources but it also requires changes to topology and optimization processes, as well as multiple performances to monitor model instabilities. From both geo-engineering and societal perspectives, a predictive groundwater table (GWT) model presents an important challenge, where a lack of UQ limits the validity of findings and may undermine science-based decisions. To overcome and address these limitations, a novel ensemble, an automated random deactivating connective weights approach (ARDCW), is presented and applied to retrieved geographical locations of GWT data from a geo-engineering project in Stockholm, Sweden. In this approach, the UQ was achieved via a combination of several derived ensembles from a fixed optimum topology subjected to randomly switched off weights, which allow predictability with one forward pass. The process was developed and programmed to provide trackable performance in a specific task and access to a wide variety of different internal characteristics and libraries. A comparison of performance with Monte Carlo dropout and quantile regression using computer vision and control task metrics showed significant progress in the ARDCW. This approach does not require changes in the optimization process and can be applied to already trained topologies in a way that outperforms other models., QC 20230116