A machine learning approach to tracking crustal thickness variations in the eastern North China Craton

Zou, Shaohao; Chen, Xilian; Xu, Deru; Brzozowski, Matthew J.; Feng, Lai; Bian, Yubing; Wang, Zhilin; Deng, Teng

doi:10.1016/j.gsf.2021.101195

Cited by 13 publications

(18 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The prediction deviation of our ERT model for crustal thickness is slightly smaller than that of Zou et al (2021), which has an R 2 score of 0.82 and a RMSE of 5.8 km. As we have incorporated the samples from orogenic belts into the training data, another advantage of our model compared to that of Zou et al (2021) is that it can not only be applied to magmatic arcs but also to collisional orogens.…”

Section: The Trained Extremely Randomized-trees (Ert) Machine Learnin...mentioning

confidence: 69%

“…For example, Miocene rocks were not excluded from building their prediction model, but the thickness of the present crust may be different from the crustal thickness during the Miocene (Mamani et al, 2009). Another possible limitation of the Zou et al (2021) model is that the intermediate rocks used for modeling are all from subduction-related arcs, and it remains unclear if the model can be applied to continental collisional orogens.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Quantifying Continental Crust Thickness Using the Machine Learning Method

Guo

Yang

2023

JGR Solid Earth

View full text Add to dashboard Cite

In addition, crustal thickness through time in the continental crust can be used to track changes in global or regional scale tectonic settings Tang, Ji, et al., 2021). Although present crustal thickness is well constrained from oceanic regions (5-10 km) to continental orogens (over 70 km, such as in the Himalaya-Tibet) (Laske et al., 2013), quantifying crustal thickness in the geologic past remains challenging.Proxies used to calculate crustal thickness include maximum Ce/Y in basalts (Mantle & Collins, 2008), Sr/Y and (La/Yb) N of intermediate rocks (Chapman et al., 2015;F. Y. Hu et al., 2017;Profeta et al., 2015) and europium anomalies (Eu/Eu*) in detrital zircons (Tang, Ji, et al., 2021). These proxies are all calibrated by correlations between the geochemical indices of young magmatic rocks and geophysically determined crustal thickness.

show abstract

Section: The Trained Extremely Randomized-trees (Ert) Machine Learnin...mentioning

confidence: 69%

mentioning

confidence: 99%

Quantifying Continental Crust Thickness Using the Machine Learning Method

Guo

Yang

2023

JGR Solid Earth

View full text Add to dashboard Cite

show abstract

“…The detailed processes of hyperparameters selection and model construction can be found in Zou et al. (2021).…”

Section: Methodsmentioning

confidence: 99%

“…Machine learning is the science of using computational algorithms to identify patterns in data and applying them to make predictions; it provides a powerful toolset for decoding hidden information in high‐dimensional data. Over the past decade, machine learning algorithms have been widely applied in the Earth sciences to solve complex problems, including determining the temperature and pressure of magma crystallization (e.g., Petrelli et al., 2020), estimating crustal thickness (e.g., Zou et al., 2021), identifying the tectonic setting in which rocks were generated (e.g., Kuwatani et al., 2015; Petrelli & Perugini, 2016; R. Zhong et al., 2021), predicting geothermal heat flux (e.g., Lösing & Ebbing, 2021; Rezvanbehbahani et al., 2017), and aiding in geochemical exploration (e.g., Nathwani et al., 2022). In this contribution, two popular, supervised machine learning algorithms, Random Forest and Deep Neural Network, were utilized to evaluate the fertility of magmas related to porphyry Cu deposits.…”

Section: Introductionmentioning

confidence: 99%

Application of Machine Learning to Characterizing Magma Fertility in Porphyry Cu Deposits

et al. 2022

Self Cite

View full text Add to dashboard Cite

With the global community moving toward a low-carbon future, the demand for minerals and metals has surged in the past decade (Ali et al., 2017). Despite the increased investment in mineral exploration, however, the rate of discovery of mineral deposits has steadily decreased (Lusty & Gunn, 2015). One of the main reasons for this is that large, shallow, and high-grade deposits have largely been identified and exploited, requiring exploration geologists to identify variably mineralized "blind" systems that are overlain by tens to hundreds of meters of barren cover (Brugger et al., 2010). To circumvent these challenges, new exploration methods and technologies are urgently needed to assist geologists in discovering new mineral deposits (Holliday & Cooke, 2007).Porphyry Cu deposits provide most of world's copper, as well as significant quantities of gold, molybdenum, and rhenium (Sillitoe, 2010), making them key exploration targets for the mining industry (Richards, 2016). These deposits form as a result of fluid exsolution derived from hydrous and oxidized magmas (Richards, 2015;Sillitoe, 2010) that are characterized by high Sr/Y, V/Sc, Sr/MnO, Ta/Nb, and Eu/Eu* ratios (Baldwin &

show abstract

“…Thus, effective connections between several different disciplines are necessitated, for which. machine learning is contributory because the system starts when it receives the required algorithms [7] . Machine learning offers consistent prediction and simple parameter structures in the early stages of design, allowing designers and engineers to rapidly change their designs and the consequences of performance in the design space exploration (DSE) process [8] .…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Theory in Building Energy Modeling and Optimization: A Bibliometric Analysis

2022

J Mod Green Energy

View full text Add to dashboard Cite

In recent decades, the machine learning theory has been developed in the field of artificial intelligence (AI), as it excludes all shortcomings of manpower, performs complex calculations without rest, and provides prediction benefits for projects. Machine learning models and algorithms extract natural models from the data set, which offers increased problem insight, better decisions, and more accurate predictions. Machine learning has a variety of methods, including supervised, unsupervised, and reinforcement learning, and has been used for building energy modeling in recent years. In this review paper, machine learning in building energy modeling was examined to demonstrate the publications in this area and the relationship between these topics. This paper investigated machine learning methods for building energy modeling using bibliometric analysis and data mining. Therefore, the objective of this research was to give insight into the status of machine learning uses for energy systems in the construction industry. Scientometric software was used for analysis. Deep learning is also a cutting-edge topic of machine learning in 2018 onwards, so a brief explanation in this research was provided to explore a proper connection between machine learning, deep learning, and construction energy modeling.

show abstract

A machine learning approach to tracking crustal thickness variations in the eastern North China Craton

Cited by 13 publications

References 63 publications

Quantifying Continental Crust Thickness Using the Machine Learning Method

Quantifying Continental Crust Thickness Using the Machine Learning Method

Application of Machine Learning to Characterizing Magma Fertility in Porphyry Cu Deposits

Machine Learning Theory in Building Energy Modeling and Optimization: A Bibliometric Analysis

Contact Info

Product

Resources

About