USGS Science⌕ Search
Home/Archive/USGS

USGS · 70198145

Statistical approach to neural network imaging of karst systems in 3D seismic reflection data

Daniel Ebuna·Jared W. Kluesner·Kevin J. Cunningham·Joel H. Edwards
View original source ↗Export metadata ↓

Abstract

The current lack of a robust, standardized technique for geophysical mapping of karst systems can be attributed to both the complexity of the environment and prior technological limitations. Abrupt lateral variations in physical properties that are inherent to karst systems generate significant geophysical noise, challenging conventional seismic signal processing and interpretation. Modern application of neural networks to multi-attribute seismic interpretation now provide a semiautomated method for identifying and leveraging the nonlinear relationships exhibited among seismic attributes. The ambiguity generally associated with designing neural networks for seismic object detection can be reduced via statistical analysis of the extracted attribute data. A data-driven approach to selecting the appropriate set of input seismic attributes, as well as the locations and minimum number of training examples, provides a more objective and computationally efficient method for identifying karst systems using reflection seismology. This statistically optimized neural network technique is thoroughly demonstrated using three-dimensional seismic reflection data collected from the southeastern portion of the Florida carbonate platform. Several dimensionality reduction methods are applied and the resulting karst probability models are evaluated relative to one another based on both quantitative and qualitative criteria. Comparing the preferred model, using quadratic discriminant analysis, to previously available seismic object detection workflows demonstrates the karst-specific nature of the tool. Results suggest that the karst multi-attribute workflow presented is capable of approximating the structural boundaries of karst systems with more accuracy and efficiency than a human counterpart or previously presented seismic interpretation schemes. This objective technique, using solely three-dimensional seismic reflection data, likely represents the most practical approach to mapping karst systems for subsequent hydrogeological modeling.

Explore related subjects

InterpretationArticle

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Daniel Ebuna, Jared W. Kluesner, Kevin J. Cunningham, Joel H. Edwards. 2018. Statistical approach to neural network imaging of karst systems in 3D seismic reflection data. https://doi.org/10.1190/int-2017-0197.1

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related USGS reports

USGS2022

Neural net detection of seismic features related to gas hydrates and free gas accumulations on the northern U.S. Atlantic margin

Bottom-simulating reflections (BSRs) that sometimes mark the base of the gas hydrate stability zone in marine sediments are often identified based on the reverse polarity reflections that cut across stratigraphic layering in seismic amplitude data. On the northern U.S. Atlantic margin (USAM) between Cape Hatteras and Hudson Canyon, legacy seismic data have revealed pronounced BSRs south of the deepwater extension of Hudson Canyon and more subtle ones from offshore Delaware south to Cape Hatteras, where the reflections sometimes follow stratigraphic layering. Using high-resolution seismic data acquired during the 2018 Mid-Atlantic Resource Imaging Experiment and a supervised neural net, we identify seismic features associated with gas hydrates and/or the top of gas between Hudson Canyon and Cape Hatteras. Using seismic attributes especially sensitive to the presence of gas, we train a neural network algorithm on seismic data from an area with strong BSRs and then apply the model to the rest of the data set. The results indicate that gas hydrate and/or shallow free gas are significantly more widespread on the northern part of the USAM than previously known. Seismic indicators of gas extend landward from the 2000 m isobath to the upper continental slope in sectors with (offshore Virginia) and, to a lesser extent, without (offshore New Jersey) pervasive upper slope methane seeps. Higher sand content and intermediate sediment thickness, factors related to the container size and gas charge in a petroleum systems framework, are associated with more robust gas indicators.

U.S. Atlantic margin↗
USGS2021

Multimineral petrophysics of thermally immature Eagle Ford Group and Cretaceous mudstones, U.S. Geological Survey Gulf Coast 1 research wellbore in central Texas

Traditional petrophysical methods to evaluate organic richness and mineralogy using gamma-ray and resistivity log responses are not diagnostic in source rocks. We have developed a deterministic, nonproprietary method to quantify formation variability in total organic carbon (TOC) and three key mudrock mineralogical components of nonhydrocarbon-bearing source rock strata of the Eagle Ford Group by developing a set of log-derived multimineral models calibrated with Fourier transform infrared spectroscopy core data from the research borehole U.S. Geological Survey Gulf Coast 1 West Woodway. We determined that bulk density response is a reliable indicator of organic content in these thermally immature, water-bearing source rocks. Multimineral findings indicate that a high degree of laminae-scale mineralogical heterogeneity exists due to thinly interbedded carbonate cements amid clay-rich mudstone layers. The lower part of the Eagle Ford Group contains the highest average TOC content (4.7 wt%) and the highest average carbonate volume (64.1 vol%), making it the optimal target in thermally mature areas for source-rock potential and hydraulic-fracture placement. In contrast, the uppermost portion of the Eagle Ford Group contains the highest average volume of clay minerals (42.6 vol%), which increases the potential for wellbore stability issues. Petrophysical characterization reveals that porosity is approximately 30% in this relatively uncompacted formation. In this thermally immature source rock, water saturation is nearly 100% and no free hydrocarbons were observed on the resistivity logs. No evidence of borehole ellipticity was observed on the three-arm caliper log, and horizontal stresses are presumed to be directionally uniform in the vicinity of this near-surface wellbore. This shallow wellbore has a temperature gradient of 1.87°F/100 ft (16.3°C/km) and is likely influenced by earth surface heating.

Texas↗
USGS2020

Gas hydrate quantification in Walker Ridge block 313, Gulf of Mexico, from full-waveform inversion of ocean-bottom seismic data

The Gulf of Mexico (GOM) Joint Industry Project Leg 2 logging-while-drilling data in Walker Ridge lease block 313 (WR313) in the GOM detected gas hydrate in coarse- and fine-grained sediments at sites WR313-G and WR313-H. The coarse-grained units are thin ( ⁠ < 10 m ⁠ ) and highly saturated, whereas the fine-grained unit is thick (approximately 200 m) with low saturation and fracture-filling gas hydrate. Unlike its coarse-grained counterpart, the seismic character of the fine-grained unit does not clearly indicate the presence of gas hydrate, which would likely have remained undiscovered in the absence of drilling. In this paper, through frequency-domain acoustic full-waveform inversion (FWI) of ocean-bottom seismometer data along a 2D multichannel seismic transect near sites WR313-G and WR313-H, we detect and quantify gas hydrate in the fine-grained unit. Key results are as follows: First, the base of the gas hydrate stability zone, which is not obvious in the reflection profile, can be discerned in the FWI results. Second, the gas hydrate in the fine-grained unit is mainly confined to the area between two sets of opposite-dipping normal faults implying that the fault architecture may be partially responsible for this gas hydrate accumulation and distribution.

Gulf of Mexico↗