A Tree‐Based Direct Sampling Method for Stochastic Surface and Subsurface Hydrological Modeling

Zuo, Chen; Yin, Zhen Yu; Pan, Zhibin; MacKie, Emma J.; Caers, Jef

doi:10.1029/2019wr026130

Cited by 33 publications

(22 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Stochastic modeling is thus a promising tool for ice-sheet investigations, which has prompted several previous studies on subglacial topographic simulation methods and applications (Goff and others, 2014; Graham and others, 2017; MacKie and others, 2020; Zuo and others, 2020). MacKie and others (2020) generated multiple topographic realizations and used these to investigate uncertainty in the surface area and locations of subglacial lakes.…”

Section: Introductionmentioning

confidence: 99%

“…MacKie and others (2020) generated multiple topographic realizations and used these to investigate uncertainty in the surface area and locations of subglacial lakes. Zuo and others (2020) simulated long-wavelength (>10 km) topography and found that, on average, the water flowpath locations in simulated topography differed significantly from those with kriged topography. However, evaluating the sensitivity of water routing to small-scale roughness requires further investigation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Stochastic modeling of subglacial topography exposes uncertainty in water routing at Jakobshavn Glacier

et al. 2020

Self Cite

View full text Add to dashboard Cite

Subglacial topography is an important feature in numerous ice-sheet analyses and can drive the routing of water at the bed. Bed topography is primarily measured with ice-penetrating radar. Significant gaps, however, remain in data coverage that require interpolation. Topographic interpolations are typically made with kriging, as well as with mass conservation, where ice flow dynamics are used to constrain bed geometry. However, these techniques generate bed topography that is unrealistically smooth at small scales, which biases subglacial water flowpath models and makes it difficult to rigorously quantify uncertainty in subglacial drainage patterns. To address this challenge, we adapt a geostatistical simulation method with probabilistic modeling to stochastically simulate bed topography such that the interpolated topography retains the spatial statistics of the ice-penetrating radar data. We use this method to simulate subglacial topography using mass conservation topography as a secondary constraint. We apply a water routing model to each of these realizations. Our results show that many of the flowpaths significantly change with each topographic realization, demonstrating that geostatistical simulation can be useful for assessing confidence in subglacial flowpaths.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Stochastic modeling of subglacial topography exposes uncertainty in water routing at Jakobshavn Glacier

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Originally, Goodfellow, Pouget-Abadie [9] proposed the loss function given below in (2), where the last layer of is a sigmoid function.…”

Section: Gan Lossmentioning

confidence: 99%

“…These traditional methods have various advantages and disadvantages. Some of them are still under research, such as the development of tree-based direct sampling MPS method [2] and many variations of forward stratigraphic modelling (e.g. [3]).…”

Section: Introductionmentioning

confidence: 99%

Geological Facies modeling based on progressive growing of generative adversarial networks (GANs)

Song

Mukerji

2021

Comput Geosci

View full text Add to dashboard Cite

Progressive growing of GANs is used for geological facies modeling, where geological features are learned from large scales to fine scales.• Multi-scale sliced Wasserstein distance, multi-dimensional scaling plot, facies proportion, variogram, and channel sinuosity and width are proposed as metrics to evaluate GANs.• Progressive growing of GANs behaves better than conventional training processes in many metrics including computation time.

show abstract

“…These approaches have various advantages and disadvantages, and they have been widely used in different scenarios. Some of them are still under research, such as the recent development of the tree-based direct sampling MPS method (Zuo et al 2020).…”

Section: Introductionmentioning

confidence: 99%

GANSim: Conditional Facies Simulation Using an Improved Progressive Growing of Generative Adversarial Networks (GANs)

Song

Mukerji

2021

Math Geosci

View full text Add to dashboard Cite

Conditional facies modeling combines geological spatial patterns with different types of observed data, to build earth models for predictions of subsurface resources. Recently, researchers have used generative adversarial networks (GANs) for conditional facies modeling, where an unconditional GAN is first trained to learn the geological patterns using the original GANs loss function, then appropriate latent vectors are searched to generate facies models that are consistent with the observed conditioning data. A problem with this approach is that the time-consuming search process needs to be conducted for every new conditioning data. As an alternative, we improve GANs for conditional facies simulation (GANSim) by introducing an extra condition-based loss function and adjusting the architecture of the generator to take the conditioning data as inputs, based on progressive growing of GANs. The condition-based loss function is defined as the inconsistency between the input conditioning value and the corresponding characteristics exhibited by the output facies model, and forces the generator to learn the ability of being consistent with the input conditioning data, together with the learning of geological patterns. Our input conditioning factors include global features (e.g. the mud facies proportion) alone, local features such as sparse well facies data alone, and joint combination of global features and well facies data.After training, we evaluate both the quality of generated facies models and the conditioning ability of the generators, by manual inspection and quantitative assessment. The trained generators are quite robust in generating high-quality facies models conditioned to various types of input conditioning information.

show abstract

A Tree‐Based Direct Sampling Method for Stochastic Surface and Subsurface Hydrological Modeling

Cited by 33 publications

References 63 publications

Stochastic modeling of subglacial topography exposes uncertainty in water routing at Jakobshavn Glacier

Stochastic modeling of subglacial topography exposes uncertainty in water routing at Jakobshavn Glacier

Geological Facies modeling based on progressive growing of generative adversarial networks (GANs)

GANSim: Conditional Facies Simulation Using an Improved Progressive Growing of Generative Adversarial Networks (GANs)

Contact Info

Product

Resources

About