Automated Classification of Estuarine Sub‐Depositional Environment Using Sediment Texture. Issue 2 (3rd February 2023)

• Record Type: Journal Article
• Authors: Houghton, J. E.; Nichols, T. E.; Griffiths, J.; Simon, N.; Utley, J. E. P.; Duller, R. A.; Worden, R. H.
• Is Part Of: Journal of geophysical research. Volume 128:Issue 2(2023)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2023-02-03
• Subjects: estuary -- sub‐depositional environment -- sediment classification -- environmental interpretation -- Holocene -- sediment texture; Geomorphology -- Periodicals; 551.3
• DOI: 10.1029/2022JF006891
• Languages: English
• ISSNs: 2169-9003

Abstract

Abstract: Interpretation of unconsolidated Quaternary sedimentary core is difficult if key diagnostic features are obscured or not present, therefore traditional facies analysis is challenging. However, sediment texture remains a universal attribute which can be used to interpret sedimentary core. Here we present an automated classification workflow which implements Extreme Gradient Boosting and Bayesian Optimization of hyperparameters to differentiate estuarine sub‐depositional environments. We use 19 textural attributes, measured using laser particle size analysis of surface sediment samples from the Ravenglass Estuary, Cumbria, northwest England, to make unbiased classification of sub‐depositional environment and estuarine zone. Two predictive models created using the automated workflow are presented and evaluated using a suite of evaluation metrics, confusion matrices, and spatial analysis to understand their geological implications. Model 1 keeps all sub‐depositional environments discrete and has an overall accuracy of 68.96%. Model 2 merges related sub‐depositional environments to form inner‐coarse and outer‐estuary zones and has an overall accuracy of 84.14%. Both models have been applied to textural data obtained at 5 cm intervals from a Holocene core drilled through a tidal bar in the Ravenglass estuarine succession, NW England, to classify palaeo sub‐depositional environment. Predictive output of the models suggests that the core consistently experienced inner estuary deposition; all inner estuary environments are represented in the core. The workflow presented here could be applied to datasets from other marginal marine depositional systems to enhance the interpretation of their subsurface deposits. Ultimately, detailed interpretations of ancient, buried deposits could be made using models derived from analogous modern systems. Plain Language Summary: Geoscientists typically rely on characteristic sedimentary structures when interpreting core. In Quaternary core, distinguishing structures can be absent or obscured as sediment is poorly consolidated (falls apart easily). In this case, a geoscientist must rely on alternative methods that can aid core interpretation. Using proven statistical links between the size, and distribution of sand grains and sedimentary environment, we have developed a new predictive machine learning model, using freely available open source software, trained to surface sediment from a well‐studied estuary in the UK. The new surface calibrated predictive model can be used to aid a geoscientist with interpretation of core drilled into the estuary to determine how depositional environment changed with time. We have applied the predictive models to a section of core, that lacks characteristic and distinguishing features, and made subtle interpretations that had been missed during traditional sedimentary core interpretation. The use of the new predictive machine learning model permits unbiased interpretations, and should be used alongside established core interpretation methods. The models produced here are flexible and can be adapted for use as part of any classification problem that uses either numerical, or categorical data. Key Points: We propose a machine learning workflow to predict sub‐depositional environment in an estuary using sediment texture (e.g., sorting) Two surface‐calibrated predictive models are presented to automatically classify estuarine core sediment samples Application of the predictive models to core data allows for an unbiased interpretation of the sandy estuarine sequence