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.

In the context of geo-infrastructures and specifically tunneling projects, analyzing the large-scale sensor-based measurement-while-drilling (MWD) data plays a pivotal role in assessing rock engineering conditions. However, handling the big MWD data due to multiform stacking is a time-consuming and challenging task. Extracting valuable insights and improving the accuracy of geoengineering interpretations from MWD data necessitates a combination of domain expertise and data science skills in an iterative process. To address these challenges and efficiently normalize and filter out noisy data, an automated processing approach integrating the stepwise technique, mode, and percentile gate bands for both single and peer group-based holes was developed. Subsequently, the mathematical concept of a novel normalizing index for classifying such big datasets was also presented. The visualized results from different geo-infrastructure datasets in Sweden indicated that outliers and noisy data can more efficiently be eliminated using single hole-based normalizing. Additionally, a relational unified PostgreSQL database was created to store and automatically transfer the processed and raw MWD as well as real time grouting data that offers a cost effective and efficient data extraction tool. The generated database is expected to facilitate in-depth investigations and enable application of the artificial intelligence (AI) techniques to predict rock quality conditions and design appropriate support systems based on MWD data.

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. 

Due to associated uncertainties, modelling the spatial distribution of depth to bedrock (DTB) is an important and challenging concern in many geo-engineering applications. The association between DTB, the safety and economy of design structures implies that generating more precise predictive models can be of vital interest. In the present study, the challenge of applying an optimally predictive three-dimensional (3D) spatial DTB model for an area in Stockholm, Sweden was addressed using an automated intelligent computing design procedure. The process was developed and programmed in both C++ and Python to track their performance in specified tasks and also to cover a wide variety of different internal characteristics and libraries. In comparison to the ordinary Kriging (OK) geostatistical tool, the superiority of the developed automated intelligence system was demonstrated through the analysis of confusion matrices and the ranked accuracies of different statistical errors. The results showed that in the absence of measured data, the intelligence models as a flexible and efficient alternative approach can account for associated uncertainties, thus creating more accurate spatial 3D models and providing an appropriate prediction at any point in the subsurface of the study area.

Delineatingand mapping the bedrockand overlaid deposits due to 8complex spatial patterns, associated uncertainties and sparse data is a vital diffi-9cult task in geo-engineering applications. Modern computing techniques such as 10artificial intelligence-based models (AIM) are appropriate alternative to over-11come the deficiencies of previous methods. The objective of this study is to in-12vestigatethe feasibility of AIM in prediction of 3D spatial distribution of subsur-13face bedrock in a large area in Stockholm, Sweden. The predictive artificial in-14telligence models were developed using 1968 processed soil-rock soundings 15comprising the geographical coordinates and ground surface elevation. The opti-16mum topology was captured through the examining of wide variety of internal 17characteristics.It was observed that in sparse dataset, the developed AIMs effi-18ciently can provide much more accurate prediction than traditionally applied 19techniques such as geostatistical approaches. This implies that the developed 20AIM due to significant capacities and acceptable predictability level can decrease 21the residuals between the predicted and measured data.