Articles | Volume 17, issue 3
https://doi.org/10.5194/gmd-17-957-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-17-957-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
GeoPDNN 1.0: a semi-supervised deep learning neural network using pseudo-labels for three-dimensional shallow strata modelling and uncertainty analysis in urban areas from borehole data
School of Resources and Civil Engineering, Northeastern University, No. 3–11, Wenhua Road, Heping district, Shenyang 110819, China
Xuechuang Xu
School of Resources and Civil Engineering, Northeastern University, No. 3–11, Wenhua Road, Heping district, Shenyang 110819, China
Luyuan Wang
School of Resources and Civil Engineering, Northeastern University, No. 3–11, Wenhua Road, Heping district, Shenyang 110819, China
Xulei Wang
School of Resources and Civil Engineering, Northeastern University, No. 3–11, Wenhua Road, Heping district, Shenyang 110819, China
School of Geosciences and Info-Physics, Central South University, Lushan Nanlu 932, Yuelu district, Changsha 410012, China
Mark Jessell
The Centre for Exploration Targeting, School of Earth Sciences, University of Western Australia, Perth, Australia
Mineral Exploration Cooperative Research Centre (MinEx CRC), School of Earth Sciences, University of Western Australia, Perth, Australia
ARC Industrial Transformation and Training Centre in Data Analytics for Resources and the Environment (DARE), Sydney, Australia
Vitaliy Ogarko
The Centre for Exploration Targeting, School of Earth Sciences, University of Western Australia, Perth, Australia
Mineral Exploration Cooperative Research Centre (MinEx CRC), School of Earth Sciences, University of Western Australia, Perth, Australia
ARC Industrial Transformation and Training Centre in Data Analytics for Resources and the Environment (DARE), Sydney, Australia
Zhibin Liu
School of Resources and Civil Engineering, Northeastern University, No. 3–11, Wenhua Road, Heping district, Shenyang 110819, China
Yufei Zheng
School of Resources and Civil Engineering, Northeastern University, No. 3–11, Wenhua Road, Heping district, Shenyang 110819, China
Related authors
Jiateng Guo, Zhibin Liu, Xulei Wang, Lixin Wu, Shanjun Liu, and Yunqiang Li
Geosci. Model Dev., 17, 847–864, https://doi.org/10.5194/gmd-17-847-2024, https://doi.org/10.5194/gmd-17-847-2024, 2024
Short summary
Short summary
This study proposes a 3D and temporally dynamic (4D) geological modeling method. Several simulation and actual cases show that the 4D spatial and temporal evolution of regional geological formations can be modeled easily using this method with smooth boundaries. The 4D modeling system can dynamically present the regional geological evolution process under the timeline, which will be helpful to the research and teaching on the formation of typical and complex geological features.
Mark Jessell, Jiateng Guo, Yunqiang Li, Mark Lindsay, Richard Scalzo, Jérémie Giraud, Guillaume Pirot, Ed Cripps, and Vitaliy Ogarko
Earth Syst. Sci. Data, 14, 381–392, https://doi.org/10.5194/essd-14-381-2022, https://doi.org/10.5194/essd-14-381-2022, 2022
Short summary
Short summary
To robustly train and test automated methods in the geosciences, we need to have access to large numbers of examples where we know
the answer. We present a suite of synthetic 3D geological models with their gravity and magnetic responses that allow researchers to test their methods on a whole range of geologically plausible models, thus overcoming one of the fundamental limitations of automation studies.
Lawrence A. Bird, Vitaliy Ogarko, Laurent Ailleres, Lachlan Grose, Jérémie Giraud, Felicity S. McCormack, David E. Gwyther, Jason L. Roberts, Richard S. Jones, and Andrew N. Mackintosh
The Cryosphere, 19, 3355–3380, https://doi.org/10.5194/tc-19-3355-2025, https://doi.org/10.5194/tc-19-3355-2025, 2025
Short summary
Short summary
The terrain of the seafloor has important controls on the access of warm water below floating ice shelves around Antarctica. Here, we present an open-source method to infer what the seafloor looks like around the Antarctic continent and within these ice shelf cavities, using measurements of the Earth's gravitational field. We present an improved seafloor map for the Vincennes Bay region in East Antarctica and assess its impact on ice melt rates.
Vitaliy Ogarko and Mark Jessell
EGUsphere, https://doi.org/10.5194/egusphere-2025-1294, https://doi.org/10.5194/egusphere-2025-1294, 2025
This preprint is open for discussion and under review for Geoscientific Model Development (GMD).
Short summary
Short summary
We developed a new method to reconstruct underground rock layers from drillhole data, using an advanced algorithm to ensure geologically realistic results. By combining data from multiple drillholes, our approach reduces uncertainty and improves accuracy. Tested on South Australian data, it successfully predicted stratigraphy and highlighted ways to enhance data quality. This innovation makes geological analysis more reliable, aiding exploration and resource management.
Mark Douglas Lindsay, Vitaliy Ogarko, Jeremie Giraud, and Mosayeb Khademi
EGUsphere, https://doi.org/10.5194/egusphere-2024-3754, https://doi.org/10.5194/egusphere-2024-3754, 2025
Preprint archived
Short summary
Short summary
Geophysical data is used to understand the Earth's structure. Geophysical inversion is an optimisation technique that constructs a model of the Earth using geophysical data. Inversion is complex and requires constraints to produce a plausible model. Overfitting is a disadvantageous effect that can affect techniques that rely on optimisation. A new feature in an inversion platform reduces overfitting by informing inversion of spatial uncertainty contained within the geophysical data.
Léonard Moracchini, Guillaume Pirot, Kerry Bardot, Mark W. Jessell, and James L. McCallum
Geosci. Model Dev. Discuss., https://doi.org/10.5194/gmd-2024-154, https://doi.org/10.5194/gmd-2024-154, 2024
Revised manuscript accepted for GMD
Short summary
Short summary
To facilitate the exploration of alternative hydrogeological scenarios, we propose to approximate costly physical simulations of contaminant transport by more affordable shortest distances computations. It enables to accept or reject scenarios within a predefined confidence interval. In particular, it can allow to estimate the probability of a fault acting as a preferential path or a barrier.
Vitaliy Ogarko, Kim Frankcombe, Taige Liu, Jeremie Giraud, Roland Martin, and Mark Jessell
Geosci. Model Dev., 17, 2325–2345, https://doi.org/10.5194/gmd-17-2325-2024, https://doi.org/10.5194/gmd-17-2325-2024, 2024
Short summary
Short summary
We present a major release of the Tomofast-x open-source gravity and magnetic inversion code that is enhancing its performance and applicability for both industrial and academic studies. We focus on real-world mineral exploration scenarios, while offering flexibility for applications at regional scale or for crustal studies. The optimisation work described in this paper is fundamental to allowing more complete descriptions of the controls on magnetisation, including remanence.
Jérémie Giraud, Guillaume Caumon, Lachlan Grose, Vitaliy Ogarko, and Paul Cupillard
Solid Earth, 15, 63–89, https://doi.org/10.5194/se-15-63-2024, https://doi.org/10.5194/se-15-63-2024, 2024
Short summary
Short summary
We present and test an algorithm that integrates geological modelling into deterministic geophysical inversion. This is motivated by the need to model the Earth using all available data and to reconcile the different types of measurements. We introduce the methodology and test our algorithm using two idealised scenarios. Results suggest that the method we propose is effectively capable of improving the models recovered by geophysical inversion and may be applied in real-world scenarios.
Jiateng Guo, Zhibin Liu, Xulei Wang, Lixin Wu, Shanjun Liu, and Yunqiang Li
Geosci. Model Dev., 17, 847–864, https://doi.org/10.5194/gmd-17-847-2024, https://doi.org/10.5194/gmd-17-847-2024, 2024
Short summary
Short summary
This study proposes a 3D and temporally dynamic (4D) geological modeling method. Several simulation and actual cases show that the 4D spatial and temporal evolution of regional geological formations can be modeled easily using this method with smooth boundaries. The 4D modeling system can dynamically present the regional geological evolution process under the timeline, which will be helpful to the research and teaching on the formation of typical and complex geological features.
Jérémie Giraud, Hoël Seillé, Mark D. Lindsay, Gerhard Visser, Vitaliy Ogarko, and Mark W. Jessell
Solid Earth, 14, 43–68, https://doi.org/10.5194/se-14-43-2023, https://doi.org/10.5194/se-14-43-2023, 2023
Short summary
Short summary
We propose and apply a workflow to combine the modelling and interpretation of magnetic anomalies and resistivity anomalies to better image the basement. We test the method on a synthetic case study and apply it to real world data from the Cloncurry area (Queensland, Australia), which is prospective for economic minerals. Results suggest a new interpretation of the composition and structure towards to east of the profile that we modelled.
Guillaume Pirot, Ranee Joshi, Jérémie Giraud, Mark Douglas Lindsay, and Mark Walter Jessell
Geosci. Model Dev., 15, 4689–4708, https://doi.org/10.5194/gmd-15-4689-2022, https://doi.org/10.5194/gmd-15-4689-2022, 2022
Short summary
Short summary
Results of a survey launched among practitioners in the mineral industry show that despite recognising the importance of uncertainty quantification it is not very well performed due to lack of data, time requirements, poor tracking of interpretations and relative complexity of uncertainty quantification. To alleviate the latter, we provide an open-source set of local and global indicators to measure geological uncertainty among an ensemble of geological models.
Richard Scalzo, Mark Lindsay, Mark Jessell, Guillaume Pirot, Jeremie Giraud, Edward Cripps, and Sally Cripps
Geosci. Model Dev., 15, 3641–3662, https://doi.org/10.5194/gmd-15-3641-2022, https://doi.org/10.5194/gmd-15-3641-2022, 2022
Short summary
Short summary
This paper addresses numerical challenges in reasoning about geological models constrained by sensor data, especially models that describe the history of an area in terms of a sequence of events. Our method ensures that small changes in simulated geological features, such as the position of a boundary between two rock layers, do not result in unrealistically large changes to resulting sensor measurements, as occur presently using several popular modeling packages.
Mark Jessell, Jiateng Guo, Yunqiang Li, Mark Lindsay, Richard Scalzo, Jérémie Giraud, Guillaume Pirot, Ed Cripps, and Vitaliy Ogarko
Earth Syst. Sci. Data, 14, 381–392, https://doi.org/10.5194/essd-14-381-2022, https://doi.org/10.5194/essd-14-381-2022, 2022
Short summary
Short summary
To robustly train and test automated methods in the geosciences, we need to have access to large numbers of examples where we know
the answer. We present a suite of synthetic 3D geological models with their gravity and magnetic responses that allow researchers to test their methods on a whole range of geologically plausible models, thus overcoming one of the fundamental limitations of automation studies.
Ranee Joshi, Kavitha Madaiah, Mark Jessell, Mark Lindsay, and Guillaume Pirot
Geosci. Model Dev., 14, 6711–6740, https://doi.org/10.5194/gmd-14-6711-2021, https://doi.org/10.5194/gmd-14-6711-2021, 2021
Short summary
Short summary
We have developed a software that allows the user to extract and standardize drill hole information from legacy datasets and/or different drilling campaigns. It also provides functionality to upscale the lithological information. These functionalities were possible by developing thesauri to identify and group geological terminologies together.
Jérémie Giraud, Vitaliy Ogarko, Roland Martin, Mark Jessell, and Mark Lindsay
Geosci. Model Dev., 14, 6681–6709, https://doi.org/10.5194/gmd-14-6681-2021, https://doi.org/10.5194/gmd-14-6681-2021, 2021
Short summary
Short summary
We review different techniques to model the Earth's subsurface from geophysical data (gravity field anomaly, magnetic field anomaly) using geological models and measurements of the rocks' properties. We show examples of application using idealised examples reproducing realistic features and provide theoretical details of the open-source algorithm we use.
Mahtab Rashidifard, Jérémie Giraud, Mark Lindsay, Mark Jessell, and Vitaliy Ogarko
Solid Earth, 12, 2387–2406, https://doi.org/10.5194/se-12-2387-2021, https://doi.org/10.5194/se-12-2387-2021, 2021
Short summary
Short summary
One motivation for this study is to develop a workflow that enables the integration of geophysical datasets with different coverages that are quite common in exploration geophysics. We have utilized a level set approach to achieve this goal. The utilized technique parameterizes the subsurface in the same fashion as geological models. Our results indicate that the approach is capable of integrating information from seismic data in 2D to guide the 3D inversion results of the gravity data.
Lachlan Grose, Laurent Ailleres, Gautier Laurent, Guillaume Caumon, Mark Jessell, and Robin Armit
Geosci. Model Dev., 14, 6197–6213, https://doi.org/10.5194/gmd-14-6197-2021, https://doi.org/10.5194/gmd-14-6197-2021, 2021
Short summary
Short summary
Fault discontinuities in rock packages represent the plane where two blocks of rock have moved. They are challenging to incorporate into geological models because the geometry of the faulted rock units are defined by not only the location of the discontinuity but also the kinematics of the fault. In this paper, we outline a structural geology framework for incorporating faults into geological models by directly incorporating kinematics into the mathematical framework of the model.
Mark Jessell, Vitaliy Ogarko, Yohan de Rose, Mark Lindsay, Ranee Joshi, Agnieszka Piechocka, Lachlan Grose, Miguel de la Varga, Laurent Ailleres, and Guillaume Pirot
Geosci. Model Dev., 14, 5063–5092, https://doi.org/10.5194/gmd-14-5063-2021, https://doi.org/10.5194/gmd-14-5063-2021, 2021
Short summary
Short summary
We have developed software that allows the user to extract sufficient information from unmodified digital maps and associated datasets that we are able to use to automatically build 3D geological models. By automating the process we are able to remove human bias from the procedure, which makes the workflow reproducible.
Lachlan Grose, Laurent Ailleres, Gautier Laurent, and Mark Jessell
Geosci. Model Dev., 14, 3915–3937, https://doi.org/10.5194/gmd-14-3915-2021, https://doi.org/10.5194/gmd-14-3915-2021, 2021
Short summary
Short summary
LoopStructural is an open-source 3D geological modelling library with a model design allowing for multiple different algorithms to be used for comparison for the same geology. Geological structures are modelled using structural geology concepts and techniques, allowing for complex structures such as overprinted folds and faults to be modelled. In the paper, we demonstrate automatically generating a 3-D model from map2loop-processed geological survey data of the Flinders Ranges, South Australia.
Cited articles
Avalos, S. and Ortiz, J. M.: Recursive Convolutional Neural Networks in a Multiple-Point Statistics Framework, Comput. Geosci., 141, 104522, https://doi.org/10.1016/j.cageo.2020.104522, 2020.
Batista, G. E. A. P., Prati, R. C., and Monard, M. C.: A Study of the Behavior of Several Methods for Balancing Machine Learning Training Data, Sigkdd Explor. Newsl., 6, 20–29, https://doi.org/10.1145/1007730.1007735, 2004.
Burrough, P. A., van Gaans, P. F. M., and Hootsmans, R.: Continuous classification in soil survey: Spatial correlation, confusion and boundaries, Geoderma, 77, 115–135, https://doi.org/10.1016/S0016-7061(97)00018-9, 1997.
Caers, J.: Modeling Uncertainty in the Earth Sciences, Wiley, https://doi.org/10.1002/9781119995920, 2011.
Calcagno, P., Chiles, J. P., Courrioux, G., and Guillen, A.: Geological modelling from field data and geological knowledge Part I. Modelling method coupling 3D potential-field interpolation and geological rules, Phys. Earth Planet. In., 171, 147–157, https://doi.org/10.1016/j.pepi.2008.06.013, 2008.
Caumon, G., Antoine, C., and Tertois, A.: Building 3D Geological Surfaces From Field Data Using Implicit Surfaces, Proceedings of the 27Th Gocad Meeting, Proceedings of the 27th Gocad Meeting, Nancy, 1–6, 2007a.
Caumon, G., Tertois, L. A., and Zhang, L.: Elements for Stochastic Structural Perturbation of Stratigraphic Models, European Association of Geoscientists & Engineers, https://doi.org/10.3997/2214-4609.201403041, 2007b.
Caumon, G., Gray, G., Antoine, C., and Titeux, M. O.: Three-Dimensional Implicit Stratigraphic Model Building From Remote Sensing Data on Tetrahedral Meshes: Theory and Application to a Regional Model of La Popa Basin, NE Mexico, IEEE T. Geosci. Remote, 51, 1613–1621, https://doi.org/10.1109/TGRS.2012.2207727, 2013.
Chawla, N. V., Bowyer, K. W., Hall, L. O., and Kegelmeyer, W. P.: Smote: Synthetic Minority Over-Sampling Technique, J. Artif. Int. Res., 16, 321–357, 2002.
Che, D. F., Wu, L. X., and Yin, Z. R.: 3D Spatial Modeling for Urban Surface and Subsurface Seamless Integration, 2009 IEEE International Geoscience and Remote Sensing Symposium, 1–5, 1694, https://doi.org/10.1109/IGARSS.2009.5417787, 2009.
Chen, G., Zhu, J., Qiang, M., and Gong, W.: Three-Dimensional Site Characterization with Borehole Data – a Case Study of Suzhou Area, Eng. Geol., 234, 65–82, https://doi.org/10.1016/j.enggeo.2017.12.019, 2018.
Cuomo, S., Galletti, A., Giunta, G., and Marcellino, L.: Reconstruction of Implicit Curves and Surfaces Via Rbf Interpolation, Appl. Numer. Math., 116, 157–171, https://doi.org/10.1016/j.apnum.2016.10.016, 2017.
de la Varga, M., Schaaf, A., and Wellmann, F.: GemPy 1.0: open-source stochastic geological modeling and inversion, Geosci. Model Dev., 12, 1–32, https://doi.org/10.5194/gmd-12-1-2019, 2019.
Fawcett, T.: An introduction to ROC analysis, Pattern Recogn. Lett., 27, 861–874, 2006.
Giraud, J., Lindsay, M., Jessell, M., and Ogarko, V.: Towards plausible lithological classification from geophysical inversion: honouring geological principles in subsurface imaging, Solid Earth, 11, 419–436, https://doi.org/10.5194/se-11-419-2020, 2020.
Guo, J. and Xu, X.: Semisupervised Deep Learning Neural Network Using Pseudolabels for Three-dimensional Urban Geological Modelling and Uncertainty Analysis from Borehole Data, Google Drive [video], https://drive.google.com/file/d/13VERDXM6YJmP7xMabQy3IjhCExuQSWzk/view?usp=sharing, last access: 13 December 2022.
Guo, J. and Xu, X.: GeoPDNN 1.0: a semi-supervised deep learning neural network using pseudo-labels for three-dimensional shallow strata modelling and uncertainty analysis in urban areas from borehole data, Zenodo [code, data set and video], https://doi.org/10.5281/zenodo.10604091, 2023.
Guo, J., Zhou, W., and Wu, L.: Implicit Three-Dimensional Geo-Modelling Based On Hrbf Surface, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII-2/W2, 63–66, https://doi.org/10.5194/isprs-archives-XLII-2-W2-63-2016, 2016.
Guo, J., Wang, J., Wu, L., Liu, C., Li, C., Li, F., Lin, M., Jessell, M. W., Li, P., Dai, X., and Tang, J.: Explicit-Implicit-Integrated 3-D Geological Modelling Approach: A Case Study of the Xianyan Demolition Volcano (Fujian, China), Tectonophysics, 795, 228648, https://doi.org/10.1016/j.tecto.2020.228648, 2020.
Guo, J., Wang, Z., Li, C., Li, F., Jessell, M. W., Wu, L., and Wang, J.: Multiple-Point Geostatistics-Based Three-Dimensional Automatic Geological Modeling and Uncertainty Analysis for Borehole Data, Natural Resources Research, 31, 2347–2367, https://doi.org/10.1007/s11053-022-10071-6, 2022.
Guo, J. T., Wang, X. L., Wang, J. M., Dai, X. W., Wu, L. X., Li, C. L., Li, F. D., Liu, S. J., and Jessell, M. W.: Three-dimensional geological modeling and spatial analysis from geotechnical borehole data using an implicit surface and marching tetrahedra algorithm, Eng. Geol., 284, 106047, https://doi.org/10.1016/j.enggeo.2021.106047, 2021.
Hellman, K., Ronczka, M., Günther, T., Wennermark, M., Rücker, C., and Dahlin, T.: Structurally Coupled Inversion of Ert and Refraction Seismic Data Combined with Cluster-Based Model Integration, J. Appl. Geophys., 143, 169–181, https://doi.org/10.1016/j.jappgeo.2017.06.008, 2017.
Hillier, M., Wellmann, F., Brodaric, B., de Kemp, E., and Schetselaar, E.: Three-Dimensional Structural Geological Modeling Using Graph Neural Networks, Math. Geosci., 53, 1725–1749, https://doi.org/10.1007/s11004-021-09945-x, 2021.
Hillier, M., Wellmann, F., de Kemp, E. A., Brodaric, B., Schetselaar, E., and Bédard, K.: GeoINR 1.0: an implicit neural network approach to three-dimensional geological modelling, Geosci. Model Dev., 16, 6987–7012, https://doi.org/10.5194/gmd-16-6987-2023, 2023.
Hillier, M. J., Schetselaar, E. M., de Kemp, E. A., and Perron, G.: Three-Dimensional Modelling of Geological Surfaces Using Generalized Interpolation with Radial Basis Functions, Math. Geosci., 46, 931–953, https://doi.org/10.1007/s11004-014-9540-3, 2014.
Houlding, S. W.: Geological Interpretation and Modeling. In S. W. Houlding (Ed.), 3D Geoscience Modeling: Computer Techniques for Geological Characterization, Springer Berlin Heidelberg, 113–129, https://doi.org/10.1007/978-3-642-79012-6_7, 1994.
Høyer, A. S., Klint, K. E. S., Fiandaca, G., Maurya, P. K., Christiansen, A. V., Balbarini, N., Bjerg, P. L., Hansen, T. B., and Møller, I.: Development of a High-Resolution 3D Geological Model for Landfill Leachate Risk Assessment, Eng. Geol., 249, 45–59, https://doi.org/10.1016/j.enggeo.2018.12.015, 2019.
Huang, X. R., Dai, Y., Xu, Y. G., and Tang, J.: Seismic Inversion Experiments Based on Deep Learning Algorithm Using Different Datasets, Journal of Soutwest Petroleum University (Science & Technology Edition), 42, 16–25, 2020.
Jessell, M.: Three-Dimensional Geological Modelling of Potential-Field Data, Comput. Geosci., 27, 455–465. https://doi.org/10.1016/S0098-3004(00)00142-4, 2001.
Jessell, M., Guo, J., Li, Y., Lindsay, M., Scalzo, R., Giraud, J., Pirot, G., Cripps, E., and Ogarko, V.: Into the Noddyverse: a massive data store of 3D geological models for machine learning and inversion applications, Earth Syst. Sci. Data, 14, 381–392, https://doi.org/10.5194/essd-14-381-2022, 2022.
Jia, R., Lv, Y., Wang, G., Carranza, E., Chen, Y., Wei, C., and Zhang, Z.: A Stacking Methodology of Machine Learning for 3D Geological Modeling with Geological-Geophysical Datasets, Laochang Sn Camp, Gejiu (China), Comput. Geosci., 151, 104754, https://doi.org/10.1016/j.cageo.2021.104754, 2021.
Laloy, E., Herault, R., Lee, J., Jacques, D., and Linde, N.: Inversion using a new low-dimensional representation of complex binary geological media based on a deep neural network, Adv. Water Resour., 110, 387–405, https://doi.org/10.1016/j.advwatres.2017.09.029, 2017.
Liu, H., Chen, S. Z., Hou, M. Q., and He, L.: Improved inverse distance weighting method application considering spatial autocorrelation in 3D geological modeling, Earth Sci. Inform., 13, 619–632, https://doi.org/10.1007/s12145-019-00436-6, 2020.
Liu, Z., Zhang, Z., Zhou, C., Ming, W., and Du, Z.: An Adaptive Inverse-Distance Weighting Interpolation Method Considering Spatial Differentiation in 3D Geological Modeling, Geosciences, 11, 51, https://doi.org/10.3390/geosciences11020051, 2021.
Livani, M., Scrocca, D., Gaudiosi, I., Mancini, M., Cavinato, G. P., de Franco, R., Caielli, G., Vignaroli, G., Romi, A., and Moscatelli, M.: A Geology-Based 3D Velocity Model of the Amatrice Basin (Central Italy), Eng. Geol., 306, 106741, https://doi.org/10.1016/j.enggeo.2022.106741, 2022.
Lysdahl, A. K., Christensen, C. W., Pfaffhuber, A. A., Vöge, M., Andresen, L., Skurdal, G. H., and Panzner, M.: Integrated Bedrock Model Combining Airborne Geophysics and Sparse Drillings Based On an Artificial Neural Network, Eng. Geol., 297, 106484, https://doi.org/10.1016/j.enggeo.2021.106484, 2022.
Lyu, M., Ren, B., Wu, B., Tong, D., Ge, S., and Han, S.: A Parametric 3D Geological Modeling Method Considering Stratigraphic Interface Topology Optimization and Coding Expert Knowledge, Eng. Geol., 293, 106300, https://doi.org/10.1016/j.enggeo.2021.106300, 2021.
Mallet, J. L.: Discrete Modeling for Natural Objects, Math. Geol., 29, 199–219, https://doi.org/10.1007/BF02769628, 1997.
Manchuk, J. G. and Deutsch, C. V.: Boundary Modeling with Moving Least Squares, Comput. Geosci., 126, 96–106, https://doi.org/10.1016/j.cageo.2019.02.006, 2019.
Martin, R. and Boisvert, J. B.: Iterative Refinement of Implicit Boundary Models for Improved Geological Feature Reproduction, Comput. Geosci., 109, 1–15, https://doi.org/10.1016/j.cageo.2017.07.003, 2017.
Marzan, I., Martí, D., Lobo, A., Alcalde, J., Ruiz, M., Alvarez-Marron, J., and Carbonell, R.: Joint Interpretation of Geophysical Data: Applying Machine Learning to the Modeling of an Evaporitic Sequence in Villar De Cañas (Spain), Eng. Geol., 288, 106126, https://doi.org/10.1016/j.enggeo.2021.106126, 2021.
Olivier, R. and Hanqiang, C.: Nearest Neighbor Value Interpolation, International Journal of Advanced Computer Science & Application, 3, 25–30, 2012.
Pakyuz-Charrier, E., Giraud, J., Ogarko, V., Lindsay, M., and Jessell, M.: Drillhole Uncertainty Propagation for Three-Dimensional Geological Modeling Using Monte Carlo, Tectonophysics, 747–748, 16–39, https://doi.org/10.1016/j.tecto.2018.09.005, 2018.
Ran, X. J. and Xue, L. F.: The research of method and system of regional three-dimensional geological modeling, Doctor Thesis, Jilin University, 2020.
Ray, P., Manach, Y. L., Riou, B., and Houle, T. T.: Statistical evaluation of a biomarker, Anesthesiology, 112, 1023–1040, https://doi.org/10.1097/ALN.0b013e3181d47604, 2010.
Shi, T., Zhong, D., and Wang, L.: Geological Modeling Method Based On the Normal Dynamic Estimation of Sparse Point Clouds, Mathematics, 9, 1819, https://doi.org/10.3390/math9151819, 2021.
Skala, V.: Rbf Interpolation with Csrbf of Large Data Sets, Proced. Comput. Sci., 108, 2433–2437, https://doi.org/10.1016/j.procs.2017.05.081, 2017.
Sun, H., Zhong, D., Wu, Z., and Wang, L.: Multi-Labeled Regularized Marching Tetrahedra Method for Implicit Geological Modeling, Math. Geosci., https://doi.org/10.1007/s11004-023-10075-9, 2023.
Thanh, H. V., Sugai, Y., Nguele, R., and Sasaki, K.: Integrated Workflow in 3D Geological Model Construction for Evaluation of Co2 Storage Capacity of a Fractured Basement Reservoir in Cuu Long Basin, Vietnam, Int. J. Greenh. Gas Con., 90, 102826, https://doi.org/10.1016/j.ijggc.2019.102826, 2019.
Thibaut, R., Laloy, E., and Hermans, T.: A New Framework for Experimental Design Using Bayesian Evidential Learning: The Case of Wellhead Protection Area, J. Hydrol., 603, 126903, https://doi.org/10.1016/j.jhydrol.2021.126903, 2021.
Titos, M., Bueno, A., Garcia, L., and Benitez, C.: A Deep Neural Networks Approach to Automatic Recognition Systems for Volcano-Seismic Events, IEEE J. Sel. Top. Appl. Earth Obs., 11, 1533–1544, https://doi.org/10.1109/JSTARS.2018.2803198, 2018.
Wang, G. and Huang, L.: 3D Geological Modeling for Mineral Resource Assessment of the Tongshan Cu Deposit, Heilongjiang Province, China, Geosci. Front., 3, 483–491, https://doi.org/10.1016/j.gsf.2011.12.012, 2012.
Wang, J. M., Zhao, H., Bi, L. and Wang, L. G.: Implicit 3D Modeling of Ore Body from Geological Boreholes Data Using Hermite Radial Basis Functions, Minerals, 8, 443, https://doi.org/10.3390/min8100443, 2018.
Whiteley, J. S., Watlet, A., Uhlemann, S., Wilkinson, P., Boyd, J. P., Jordan, C., Kendall, J. M., and Chambers, J. E.: Rapid Characterisation of Landslide Heterogeneity Using Unsupervised Classification of Electrical Resistivity and Seismic Refraction Surveys, Eng. Geol., 290, 106189, https://doi.org/10.1016/j.enggeo.2021.106189, 2021.
Wu, L. X.: Topological relations embodied in a generalized tri-prism (GTP) model for a 3D geoscience modeling system, Comput. Geosci., 30, 405–418, https://doi.org/10.1016/j.cageo.2003.06.005, 2004.
Xiong, Z., Guo, J., Xia, Y., Lu, H., Wang, M., and Shi, S.: A 3D Multi-Scale Geology Modeling Method for Tunnel Engineering Risk Assessment, Tunn. Undergr. Sp. Tech., 73, 71–81, https://doi.org/10.1016/j.tust.2017.12.003, 2018.
Xu, S. T. and Zhou, Y. Z.: Artificial intelligence identification of ore minerals under microscope based on deep learning algorithm, Acta Petrol. Sin., 34, 3244–3252, 2018.
Yang, Y. S., Li, Y. Y., Liu, T. Y., Zhan, Y. L., and Feng, J.: Interactive 3D forward modeling of total field surface and three-component borehole magnetic data for the Daye iron-ore deposit (Central China), J. Appl. Geophys., 75, 254–263, https://doi.org/10.1016/j.jappgeo.2011.07.010, 2011.
Zhang, T. F., Tilke, P., Dupont, E., Zhu, L.C., Liang, L., and Bailey, W.: Generating geologically realistic 3D reservoir facies models using deep learning of sedimentary architecture with generative adversarial networks, Pet. Sci., 16, 541–549, https://doi.org/10.1007/s12182-019-0328-4, 2019.
Zhang, X. Y., Ye, P., Wang, S., and Du, M.: Geological entity recognition method based on Deep Belief Networks, Acta Petrol. Sin., 34, 343–351, 2018.
Zhang, Z., Wang, G., Liu, C., Cheng, L., and Sha, D.: Bagging-Based Positive-Unlabeled Learning Algorithm with Bayesian Hyperparameter Optimization for Three-Dimensional Mineral Potential Mapping, Comput. Geosci., 154, https://doi.org/10.1016/j.cageo.2021.104817, 2021.
Zhang, Z., Wang, G., Carranza, E. J. M., Yang, S., Zhao, K., Yang, W., and Sha, D.: Three-Dimensional Pseudo-Lithologic Modeling Via Adaptive Feature Weighted K-Means Algorithm From Multi-Source Geophysical Datasets, Qingchengzi Pb–Zn–Ag–Au District, China, Natural Resources Research, 31, 2163–2179, https://doi.org/10.1007/s11053-021-09927-0, 2022.
Zhang, Z., Wang, G., Carranza, E. J. M., Liu, C., Li, J., Fu, C., Liu, X., Chen, C., Fan, J., and Dong, Y.: An Integrated Machine Learning Framework with Uncertainty Quantification for Three-Dimensional Lithological Modeling From Multi-Source Geophysical Data and Drilling Data, Eng. Geol., 324, 107255, https://doi.org/10.1016/j.enggeo.2023.107255, 2023.
Zhong, D. Y., Wang, L. G., Bi, L., and Jia, M. T.: Implicit Modeling of Complex Orebody with Constraints of Geological Rules, T. Nonfer. Metal. Soc., 29, 2392–2399, https://doi.org/10.1016/S1003-6326(19)65145-9, 2019.
Zhong, D. Y., Wang, L. G., and Wang, J. M.: Combination Constraints of Multiple Fields for Implicit Modeling of Ore Bodies, Appl. Sci., 11, 1321, https://doi.org/10.3390/app11031321, 2021.
Short summary
This study proposes a semi-supervised learning algorithm using pseudo-labels for 3D geological modelling. We establish a 3D geological model using borehole data from a complex real urban local survey area in Shenyang and make an uncertainty analysis of this model. The method effectively expands the sample space, which is suitable for geomodelling and uncertainty analysis from boreholes. The modelling results perform well in terms of spatial morphology and geological semantics.
This study proposes a semi-supervised learning algorithm using pseudo-labels for 3D geological...