Articles | Volume 14, issue 6
https://doi.org/10.5194/gmd-14-3421-2021
© Author(s) 2021. 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-14-3421-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Sub3DNet1.0: a deep-learning model for regional-scale 3D subsurface structure mapping
Zhenjiao Jiang
CORRESPONDING AUTHOR
Key Laboratory of Groundwater Resources and Environment, Ministry of
Education, College of Environment and Resources, Jilin University, Changchun, 130021, China
CSIRO Land & Water, Locked Bag 2, Glen Osmond,
SA 5064, Australia
Dirk Mallants
CSIRO Land & Water, Locked Bag 2, Glen Osmond,
SA 5064, Australia
CSIRO Land & Water, Locked Bag 2, Glen Osmond,
SA 5064, Australia
Tim Munday
CSIRO Mineral Resources, Locked Bag 2, Glen Osmond,
SA 5064, Australia
Gregoire Mariethoz
University of Lausanne, Faculty of Geosciences and
Environment, Institute of Earth Surface Dynamics, Lausanne, Switzerland
Luk Peeters
CSIRO Mineral Resources, Locked Bag 2, Glen Osmond,
SA 5064, Australia
Related authors
No articles found.
Pau Wiersma, Jan Magnusson, Nadav Peleg, Bettina Schaefli, and Grégoire Mariéthoz
EGUsphere, https://doi.org/10.5194/egusphere-2025-3610, https://doi.org/10.5194/egusphere-2025-3610, 2025
This preprint is open for discussion and under review for Hydrology and Earth System Sciences (HESS).
Short summary
Short summary
Using a newly introduced inverse hydrological modeling framework, we demonstrate that streamflow observations have the potential to improve snow mass reconstructions, but that non-uniqueness in the snow-streamflow relationship and uncertainties in the inverse modeling chain can easily stand in the way. We also show that streamflow is most helpful in estimating catchment-aggregated properties of snow mass reconstructions, in particular catchment-aggregated melt rates.
Fatemeh Zakeri, Gregoire Mariethoz, and Manuela Girotto
EGUsphere, https://doi.org/10.5194/egusphere-2024-1943, https://doi.org/10.5194/egusphere-2024-1943, 2024
Short summary
Short summary
This study introduces a method for estimating High-Resolution Snow Water Equivalent (HR-SWE) using Low-Resolution Climate Data (LR-CD). By applying a data-driven approach, we utilize historical weather patterns from LR-CD to estimate HR-SWE maps. Our approach uses statistical relationships between LR-CD and HR-SWE data to provide HR-SWE estimates for dates when HR-SWE data is unavailable. This method improves water resource management and climate impact assessments in regions with limited data.
Mathieu Vrac, Denis Allard, Grégoire Mariéthoz, Soulivanh Thao, and Lucas Schmutz
Earth Syst. Dynam., 15, 735–762, https://doi.org/10.5194/esd-15-735-2024, https://doi.org/10.5194/esd-15-735-2024, 2024
Short summary
Short summary
We aim to combine multiple global climate models (GCMs) to enhance the robustness of future projections. We introduce a novel approach, called "α pooling", aggregating the cumulative distribution functions (CDFs) of the models into a CDF more aligned with historical data. The new CDFs allow us to perform bias adjustment of all the raw climate simulations at once. Experiments with European temperature and precipitation demonstrate the superiority of this approach over conventional techniques.
Moctar Dembélé, Mathieu Vrac, Natalie Ceperley, Sander J. Zwart, Josh Larsen, Simon J. Dadson, Grégoire Mariéthoz, and Bettina Schaefli
Proc. IAHS, 385, 121–127, https://doi.org/10.5194/piahs-385-121-2024, https://doi.org/10.5194/piahs-385-121-2024, 2024
Short summary
Short summary
This study assesses the impact of climate change on the timing, seasonality and magnitude of mean annual minimum (MAM) flows and annual maximum flows (AMF) in the Volta River basin (VRB). Several climate change projection data are use to simulate river flow under multiple greenhouse gas emission scenarios. Future projections show that AMF could increase with various magnitude but negligible shift in time across the VRB, while MAM could decrease with up to 14 days of delay in occurrence.
Fabio Oriani, Gregoire Mariethoz, and Manuel Chevalier
Earth Syst. Sci. Data, 16, 731–742, https://doi.org/10.5194/essd-16-731-2024, https://doi.org/10.5194/essd-16-731-2024, 2024
Short summary
Short summary
Modern and fossil pollen data contain precious information for reconstructing the climate and environment of the past. However, these data are only achieved for single locations with no continuity in space. We present here a systematic atlas of 194 digital maps containing the spatial estimation of contemporary pollen presence over Europe. This dataset constitutes a free and ready-to-use tool to study climate, biodiversity, and environment in time and space.
Mathieu Gravey and Grégoire Mariethoz
Geosci. Model Dev., 16, 5265–5279, https://doi.org/10.5194/gmd-16-5265-2023, https://doi.org/10.5194/gmd-16-5265-2023, 2023
Short summary
Short summary
Multiple‐point geostatistics are widely used to simulate complex spatial structures based on a training image. The use of these methods relies on the possibility of finding optimal training images and parametrization of the simulation algorithms. Here, we propose finding an optimal set of parameters using only the training image as input. The main advantage of our approach is to remove the risk of overfitting an objective function.
Nadav Peleg, Herminia Torelló-Sentelles, Grégoire Mariéthoz, Lionel Benoit, João P. Leitão, and Francesco Marra
Nat. Hazards Earth Syst. Sci., 23, 1233–1240, https://doi.org/10.5194/nhess-23-1233-2023, https://doi.org/10.5194/nhess-23-1233-2023, 2023
Short summary
Short summary
Floods in urban areas are one of the most common natural hazards. Due to climate change enhancing extreme rainfall and cities becoming larger and denser, the impacts of these events are expected to increase. A fast and reliable flood warning system should thus be implemented in flood-prone cities to warn the public of upcoming floods. The purpose of this brief communication is to discuss the potential implementation of low-cost acoustic rainfall sensors in short-term flood warning systems.
Moctar Dembélé, Mathieu Vrac, Natalie Ceperley, Sander J. Zwart, Josh Larsen, Simon J. Dadson, Grégoire Mariéthoz, and Bettina Schaefli
Hydrol. Earth Syst. Sci., 26, 1481–1506, https://doi.org/10.5194/hess-26-1481-2022, https://doi.org/10.5194/hess-26-1481-2022, 2022
Short summary
Short summary
Climate change impacts on water resources in the Volta River basin are investigated under various global warming scenarios. Results reveal contrasting changes in future hydrological processes and water availability, depending on greenhouse gas emission scenarios, with implications for floods and drought occurrence over the 21st century. These findings provide insights for the elaboration of regional adaptation and mitigation strategies for climate change.
Dirk Mallants, John Phalen, and Hef Griffiths
Saf. Nucl. Waste Disposal, 1, 263–264, https://doi.org/10.5194/sand-1-263-2021, https://doi.org/10.5194/sand-1-263-2021, 2021
Short summary
Short summary
In Australia, long-lived ILW from research reactors and radiopharmaceutical production represents the principal waste stream that requires deep geologic disposal. CSIRO and its partners aim to demonstrate the technical feasibility of the long-term safety of borehole disposal in deep geological formations. We will highlight the main findings from the RD&D undertaken so far.
Moctar Dembélé, Bettina Schaefli, Nick van de Giesen, and Grégoire Mariéthoz
Hydrol. Earth Syst. Sci., 24, 5379–5406, https://doi.org/10.5194/hess-24-5379-2020, https://doi.org/10.5194/hess-24-5379-2020, 2020
Short summary
Short summary
This study evaluates 102 combinations of rainfall and temperature datasets from satellite and reanalysis sources as input to a fully distributed hydrological model. The model is recalibrated for each input dataset, and the outputs are evaluated with streamflow, evaporation, soil moisture and terrestrial water storage data. Results show that no single rainfall or temperature dataset consistently ranks first in reproducing the spatio-temporal variability of all hydrological processes.
Cited articles
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M.,
Ghemawat, S., Irving, G., and Isard, M.: Tensorflow: a system for large-scale
machine learning, 12th USENIX Symposium on Operating Systems Design and Implementation, 265–283, 2016.
Alley, N., Ckarjet, T., Macphail, M., and Truswell, E.: Sedimentary infillings
and development of major Tertiary palaeodrainage systems of south-central
Australia, in: Palaeoweathering, palaeosurfaces and related continental
deposits, John Wiley and Sons, Hoboken, US, 73, 337, 2009.
Amit, S. N. K. B., Shiraishi, S., Inoshita, T., and Aoki, Y.: Analysis of
satellite images for disaster detection, IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 5189–5192, 2016.
Davis, A., Macaulay, S., Munday, T., Sorensen, C., Shudra, J., and
Ibrahimi, T.: Uncovering the groundwater resource potential of Murchison
Region in Western Australia through targeted application of airborne
electromagnetics, ASEG Extended Abstracts, 2016, 1–6, 2016.
de Marsily, G., Delay, F., Gonçalvès, J., Renard, P., Teles, V., and Violette, S.: Dealing with spatial heterogeneity, Hydrogeol. J., 13, 161–183, 2005.
Dodds, S. and Sampson, L.: The Sustainability of Water Resources in the Anangu Pitjantjatjara Lands, South Australia, Department for Water Resources, Adelaide, 2000.
Felletti, F., Bersezio, R., and Giudici, M.: Geostatistical simulation and numerical upscaling, to model ground-water flow in a sandy-gravel, braided river, aquifer analogue, J. Sediment. Res., 76, 1215–1229, 2006.
Gallant, J., Dowling, T., and Austin, J.: Multi-resolution Valley Bottom Flatness (MrVBF), v3, CSIRO, Data Collection, https://doi.org/10.4225/08/5701C885AB4FE, 2012.
Gallant, J. C. and Dowling, T. I.: A multiresolution index of valley bottom
flatness for mapping depositional areas, Water Resour. Res., 39, 1347, https://doi.org/10.1029/2002WR001426,
2003.
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D.,
Ozair, S., Courville, A., and Bengio, Y.: Generative adversarial nets, arXiv preprint,
2672–2680, 2014.
Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X., Wang, G., and Cai, J.: Recent advances in convolutional neural networks, Pattern Recogn., 77, 354–377, 2018.
Hinton, G. E. and Salakhutdinov, R. R.: Reducing the dimensionality of data with neural networks, 313, Science,
504–507, 2006.
Hou, B. and Mauger, A.: How well does remote sensing aid palaeochannel identification?-an example from the Harris Greenstone Belt, SA, MESA J., 38, 46–52, 2005.
Hou, B., Frakes, L., Alley, N., Stamoulis, V., and Rowett, A.: Geoscientific
signatures of Tertiary palaeochannels and their significance for mineral
exploration in the Gawler Craton region, MESA J., 19, 36–39, 2000.
Hou, B., Frakes, L., Sandiford, M., Worrall, L., Keeling, J., and Alley, N.: Cenozoic Eucla Basin and associated palaeovalleys, southern Australia – climatic and tectonic influences on landscape evolution, sedimentation and heavy mineral accumulation, Sediment. Geol., 203, 112–130, 2008.
Høyer, A.-S., Jørgensen, F., Sandersen, P., Viezzoli, A., and Møller, I.: 3D geological modelling of a complex buried-valley network delineated from borehole and AEM data, J. Appl. Geophys., 122, 94–102, 2015.
Hu, L. and Chugunova, T.: Multiple-point geostatistics for modeling subsurface
heterogeneity: A comprehensive review, Water Resour. Res., 44, W11413, https://doi.org/10.1029/2008WR006993,
2008.
Jiang, Z.: A deep learning model for regional-scale 3D subsurface structure mapping, Harvard Dataverse, V1, https://doi.org/10.7910/DVN/DDEIUV, 2020.
Jiang, Z., Mallants, D., Peeters, L., Gao, L., Soerensen, C., and Mariethoz, G.: High-resolution paleovalley classification from airborne electromagnetic imaging and deep neural network training using digital elevation model data, Hydrol. Earth Syst. Sci., 23, 2561–2580, https://doi.org/10.5194/hess-23-2561-2019, 2019.
Jørgensen, F., Lykke-Andersen, H., Sandersen, P. B., Auken, E., and Nørmark, E.: Geophysical investigations of buried Quaternary valleys in Denmark: an integrated application of transient electromagnetic soundings, reflection seismic surveys and exploratory drillings, J. Appl. Geophys., 53, 215–228, 2003.
Kingma, D. P. and Ba, J.: Adam: A method for stochastic optimization, arXiv preprint, arXiv:1412.6980, 2014.
Kingma, D. P. and Welling, M.: Auto-encoding variational bayes, arXiv preprint, arXiv:1312.6114, 2013.
Kitanidis, P. K.: Introduction to Geostatistics: Applications in Hydrogeology,
Cambridge University Press, Cambridge, UK, 1997.
Korus, J. T., Joeckel, R. M., Divine, D. P., and Abraham, J. D.: Three-dimensional architecture and hydrostratigraphy of cross-cutting buried valleys using airborne electromagnetics, glaciated Central Lowlands, Nebraska, USA, Sedimentology, 64, 553–581, 2017.
Krapf, C., Costar, A., Stoian, L., Keppel, M., Gordon, G., Inverarity, L., Love, A., and Munday, T.: A sniff of the ocean in the Miocene at the foothills of the Musgrave Ranges–unravelling the evolution of the Lindsay East Palaeovalley, MESA J., 90, 4–22, 2019.
Kullback, S. and Leibler, R. A.: On information and sufficiency, Ann. Math. Stat., 22, 79–86, 1951.
Laloy, E., Hérault, R., Jacques, D., and Linde, N.: Training-Image Based Geostatistical Inversion Using a Spatial Generative Adversarial Neural Network, Water Resour. Res., 54, 381–406, 2018.
Längkvist, M., Kiselev, A., Alirezaie, M., and Loutfi, A.: Classification
and segmentation of satellite orthoimagery using convolutional neural
networks, Remote Sens., 8, 329, https://doi.org/10.3390/rs8040329, 2016.
Lee, S.-Y., Carle, S. F., and Fogg, G. E.: Geologic heterogeneity and a comparison of two geostatistical models: Sequential Gaussian and transition probability-based geostatistical simulation, Adv. Water Resour., 30, 1914–1932, 2007.
Magee, J. W.: Palaeovalley groundwater resources in arid and
semi-arid Australia: A literature review, Geoscience Australia, Record 2009/03, Commonwealth of Australia,
2009.
Marcais, J. and de Dreuzy, J. R.: Prospective Interest of Deep Learning for Hydrological Inference, Groundwater, 55, 688–692, 2017.
Mariethoz, G. and Caers, J.: Multiple-point geostatistics: stochastic modeling
with training images, John Wiley and Sons, Hoboken, US, 2014.
Mey, J., Scherler, D., Zeilinger, G., and Strecker, M. R.: Estimating the fill
thickness and bedrock topography in intermontane valleys using artificial
neural networks, J. Geophys. Res.-Earth, 120, 1301–1320, https://doi.org/10.1002/2014JF003270, 2015.
Mousavi, S. M. and Beroza, G. C.: A Machine-Learning Approach for Earthquake
Magnitude Estimation, Geophys. Res. Lett., 47, e2019GL085976, https://doi.org/10.1029/2019GL085976, 2019.
Munday, T.: Musgrave Province Airborne Electromagnetic Conductivity Grids, v1, CSIRO [data collection], https://doi.org/10.25919/5d0868d48591e, 2019.
Munday, T., Abdat, T., Ley-Cooper, Y., and Gilfedder, M.: Facilitating
Long-term Outback Water Solutions (G-FLOWS Stage-1: Hydrogeological Framework, Technical Report Series,
Goyder Institute for Water Research, Adelaide, Australia,
2013.
Munday, T., Gilfedder, M Costar, A., Blaikie, T., Cahill, K., Cui, T., Davis, A., Deng, Z., Flinchum, B., Gao, L., Gogoll, M., Gordon, G., Ibrahimi, T., Inverarity, K., Irvine, J., Janardhanan, S., Jiang, Z., Keppel, M., Krapf, C., Lane, T., Love, A., Macnae, J., Mallants, D., Mariethoz, G., Martinez, J., Pagendam, D., Peeters, L., Pickett, T., Raiber, M., Ren, X., Robinson, N., Siade, A., Smolanko, N., Soerensen, C., Stoian, L., Taylor, A., Visser, G., Wallis, I., and Xie, Y.: Facilitating Long-term Outback Water Solutions (G-FLOWS Stage 3): Final Summary Report, Goyder Institute for Water Research, Adelaide, Australia, 2020a.
Munday, T., Taylor, A., Raiber, M., Soerensen, C., Peeters, L., Krapf, C., Cui, T., Cahill, K., Flinchum, B., Smolanko, N., Martinez, J., Ibrahimi, T. and Gilfedder, M: Integrated regional hydrogeophysical conceptualisation of the Musgrave Province, South Australia, Technical Report, Goyder Institute for Water Research, Adelaide, Australia, 2020b.
Munday, T. J., Macnae, J., Bishop, J., and Sattel, D.: A geological interpretation of observed electrical structures in the regolith: Lawlers, Western Australia, Explor. Geophys., 32, 36–47, 2001.
Munday, T. J., Cahill, K., Sorensen, C., Davis, A., and Ibrahimi, T.:
Uncovering the Musgraves – a different perspective on an old landscape, Goyder Institute for Water Research,
Adelaide, December, 2016.
Niu, C., Li, J., and Xu, K.: Im2Struct: Recovering 3D Shape Structure from a
Single RGB Image, Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., 80, 4096, 2018.
Oldenborger, G. A., Pugin, A. J. M., and Pullan, S. E.: Airborne time-domain electromagnetics, electrical resistivity and seismic reflection for regional three-dimensional mapping and characterization of the Spiritwood Valley Aquifer, Manitoba, Canada, Near Surf. Geophys., 11, 63–74, 2013.
Pawley, M. J., Dutch, R. A., Werner, M., and Krapf, C. B.: Repeated failure: long-lived faults in the eastern Musgrave Province, MESA J., 75, 45–55, 2014.
Perol, T., Gharbi, M., and Denolle, M.: Convolutional neural network for
earthquake detection and location, Sci. Adv., 4, e1700578, https://doi.org/10.1126/sciadv.1700578,
2018.
Roach, I., Jaireth, S., and Costelloe, M.: Applying regional airborne electromagnetic (AEM) surveying to understand the architecture of sandstone-hosted uranium mineral systems in the Callabonna Sub-basin, Lake Frome region, South Australia, Aust. J. Earth Sci., 61, 659–688, 2014.
Siemon, B., Eberle, D., Rehli, H.-J., Voß, W., and Pielawa, J.: Airborne geophysical investigation of buried valleys – survey area Ellerbeker Rinne, Germany, BGR Report, Hannover, 2006.
Sinha, A., Unmesh, A., Huang, Q., and Ramani, K.: SurfNet: Generating 3D shape surfaces using deep residual networks, Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., 1, 6040, 2017.
Soerensen, C. C., Munday, T. J., Ibrahimi, T., Cahill, K., and Gilfedder, M.:
Musgrave Province, South Australia: processing and inversion of airborne
electromagnetic (AEM) data: Preliminary results, Technical Report Series,
1839-2725, Goyder Institute for Water Research, Adelaide, Australia, 2016.
Strebelle, S.: Conditional simulation of complex geological structures using multiple-point statistics, Math. Geol., 34, 1–21, 2002.
Taylor, A., Pichler, M., Olifent, V., Thompson, J., Bestland, E., Davies, P., Lamontagne, S., Suckow, A., Robinson, N., and Love, A.: Groundwater Flow Systems of North-eastern Eyre Peninsula (G-FLOWS Stage-2): Hydrogeology, geophysics and environmental tracers, Technical Report Series, Goyder Institute for Water Research, Adelaide, Australia, 2015.
Weissmann, G. S. and Fogg, G. E.: Multi-scale alluvial fan heterogeneity modeled with transition probability geostatistics in a sequence stratigraphic framework, J. Hydrol., 226, 48–65, 1999.
Wu, J., Zhang, C., Xue, T., Freeman, B., and Tenenbaum, J.: Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling, arXiv [preprint], arXiv:1610.07584, 2016.
Yi, L., Shao, L., Savva, M., Huang, H., Zhou, Y., Wang, Q., Graham, B., Engelcke, M., Klokov, R., and Lempitsky, V.: Large-scale 3d shape reconstruction and segmentation from shapenet core55, arXiv [preprint], arXiv:1710.06104, 2017.
Short summary
Fast and reliable tools are required to extract hidden information from big geophysical and remote sensing data. A deep-learning model in 3D image construction from 2D image(s) is here developed for paleovalley mapping from globally available digital elevation data. The outstanding performance for 3D subsurface imaging gives confidence that this generic novel tool will make better use of existing geophysical and remote sensing data for improved management of limited earth resources.
Fast and reliable tools are required to extract hidden information from big geophysical and...