A machine-learning derived model of seafloor sediment accumulation

Restreppo, G. A.; Wood, W. T.; Graw, Jordan H.; Phrampus, B. J.

doi:10.1016/j.margeo.2021.106577

Cited by 12 publications

(20 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this study, we substituted terrestrial environmental parameters and predicted continental nitrogen concentrations. The GML we are using has been described in more detail and demonstrated on a variety of geologic parameters and recently published in the marine geology and geophysics literature (e.g., Eymold et al., 2021; Graw et al., 2020; Lee et al., 2020; Lee et al., 2020; Martin et al., 2015; Obelcz et al., 2020; Phrampus et al., 2020; Restrepo et al., 2020, 2021).…”

Section: Methodsmentioning

confidence: 99%

Global Nitrogen Mass Flux From the Active Freshwater Aquifer Element Pool

Wood,

Sanford,

Cherry

et al. 2023

Global Biogeochemical Cycles

Self Cite

View full text Add to dashboard Cite

The estimated current global mean nitrogen concentration (geogenic + anthropogenic) in the active continental freshwater aquifer element pool is 1.1 mg/L as N, or between four and five times greater than the assumed geogenic mean. This concentration, combined with groundwater flux, generates a continental mass flux of 17 Tg N/y (teragrams of nitrogen, as N, per year) as a result of direct ocean discharge (0.67 Tg N/y), endorheic basins (1.2 Tg N/y), and cold‐wet (0.82 Tg N/y); cold‐dry (1.4 Tg N/y); warm‐dry (1.6 Tg N/y); and warm‐wet (11 Tg N/y) exorheic basins. These values are derived from a geospatial machine learning algorithm and combined groundwater‐modeled recharge in an ArcGIS environment. This active continental freshwater aquifer mass flux is between 35% and 40% of the continental integrated riverine system discharge, thus a significant component of the Earth's active continental freshwater nitrogen budget. We estimate the active continental freshwater aquifer volume to be between 1.4 and 2.8 million km3 suggesting a legacy of between 1.5 and 3.1 Pg as N (petagrams nitrogen as N) with mean residences of 90–180 years.

show abstract

Section: Methodsmentioning

confidence: 99%

Global Nitrogen Mass Flux From the Active Freshwater Aquifer Element Pool

Wood,

Sanford,

Cherry

et al. 2023

Global Biogeochemical Cycles

Self Cite

View full text Add to dashboard Cite

show abstract

“…This bias limits data-driven analyses and results in poorly-generalized results due to the limited feature selection capability, and fuzzy delineation between anomaly and no-anomaly locations due to the limited capability in identifying unobserved phenomena (Phrampus et al, 2020). Anomaly bias can also be observed in marine geochronology, which also omits sediment cores with zero net sediment accumulation (e.g., Restreppo et al, 2021). More representative datasets with absence data (e.g., Diesing et al, 2021) would bypass analysis limitations and result in more comprehensive examination of global phenomena.…”

Section: Challengesmentioning

confidence: 99%

The necessary optimization of the data lifecycle: Marine geosciences in the big data era

Lee

Phrampus²,

Obelcz³

2023

Front. Earth Sci.

Self Cite

View full text Add to dashboard Cite

In the marine geosciences, observations are typically acquired using research vessels to understand a given phenomenon or area of interest. Despite the plateauing of ship time and active research vessels in the last decade, the rate of marine geoscience data production has continued to increase. Simultaneously, there exists large quantities of legacy data aggregated within data repositories; however, these data are rarely curated to be both discoverable and machine-readable (i.e., accessible). This results in inefficient use, or even omission, of high-quality data, that is, both increasingly important to utilize and impractical to recollect. The proliferation of newly acquired data, and increasing importance of legacy data, has only been met with incremental evolution in the methods of data integration. This paper describes some improvements at each stage of the data lifecycle (acquisition, curation, and integration) that could align the marine geosciences better with the “big data” paradigm. We have encountered several major issues coordinating these efforts which we outline here: 1) geologic anomalies are the primary focus of data acquisition and pose difficulty in understanding the dominant (i.e., baseline) marine geology, 2) marine geoscience data are rarely curated to be accessible, and 3) aforementioned issues preclude the use of efficient integration tools that can make optimal use of data. In this paper, we discuss challenges and solutions associated with these issues to overcome these concerns in future decades of marine geoscience. The successful execution of these interconnected steps will optimize the lifecycle of marine geoscience data in the “big data” era.

show abstract

“…In recent years, various artificial intelligence (AI) algorithms have been used in many applications in the field of geology, such as seafloor sediment accumulation prediction [1], oil and gas reserves forecast [2], seafloor substrate classification [3], geological drilling [4][5][6][7][8], geological hazards prediction [9][10][11], etc. Among these applications, convolutional neural network (CNN) was also widely used for target recognition in SSS images.…”

Section: Introductionmentioning

confidence: 99%

“…A comprehensive analysis of each model's computational efficiency and difficulty was also presented. The main improvements are as follows: (1) We investigated the degree of influence of transfer learning on CNNs with different structures and the reasons for it. (2) We compared the prediction accuracy of different CNN models on the SSS dataset and analyzed the reasons for the different degrees of influence.…”

Section: Introductionmentioning

confidence: 99%

A Comparative Study of Different CNN Models and Transfer Learning Effect for Underwater Object Classification in Side-Scan Sonar Images

Sun

Song

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

With the development of deep learning techniques, convolutional neural networks (CNN) are increasingly being used in image recognition for marine surveys and underwater object classification. Automatic recognition of targets on side-scan sonar (SSS) images using CNN can improve recognition accuracy and efficiency. However, the vast selection of CNN models makes it challenging to select models for target recognition in SSS images. Therefore, this paper aims to compare different CNN models’ prediction accuracy and computational performance comprehensively. First, four traditional CNN models were applied to train and predict the same submarine SSS dataset using both the original model and models with transfer learning methods. Then, we examined and studied the prediction accuracy and computation performance of four CNN models. Results showed that transfer learning enhances the accuracy of all CNN models, with lesser improvements for AlexNet and VGG-16 and greater improvements for GoogleNet and ResNet101. GoogleNet has the highest prediction of accuracy (100% in the train dataset and 94.27% in the test dataset) and good computational difficulty. The findings of this work are useful for future model selection in target recognition in SSS images.

show abstract

A machine-learning derived model of seafloor sediment accumulation

Cited by 12 publications

References 21 publications

Global Nitrogen Mass Flux From the Active Freshwater Aquifer Element Pool

Global Nitrogen Mass Flux From the Active Freshwater Aquifer Element Pool

The necessary optimization of the data lifecycle: Marine geosciences in the big data era

A Comparative Study of Different CNN Models and Transfer Learning Effect for Underwater Object Classification in Side-Scan Sonar Images

Contact Info

Product

Resources

About