اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدLearning 3D Mineral Prospectivity from 3D Geological Models with Convolutional Neural Networks: Application to a Structure-controlled Hydrothermal Gold Deposit
121
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
The three-dimensional (3D) geological models are the typical and key data source in the 3D mineral prospecitivity modeling. Identifying prospectivity-informative predictor variables from the 3D geological models is a challenging and tedious task. Motivated by the ability of convolutional neural networks (CNNs) to learn the intrinsic features, in this paper, we present a novel method that leverages CNNs to learn 3D mineral prospectivity from the 3D geological models. By exploiting the learning ability of CNNs, the presented method allows for disentangling complex correlation to the mineralization and thus opens a door to circumvent the tedious work for designing the predictor variables. Specifically, to explore the unstructured 3D geological models with the CNNs whose input should be structured, we develop a 2D CNN framework in which the geometry of geological boundary is compiled and reorganized into multi-channel images and fed into the CNN. This ensures an effective and efficient training of CNNs while allowing the prospective model to approximate the ore-forming process. The presented method is applied to a typical structure-controlled hydrothermal deposit, the Dayingezhuang gold deposit, eastern China, in which the presented method was compared with the prospectivity modeling methods using hand-designed predictor variables. The results demonstrate the presented method capacitates a performance boost of the 3D prospectivity modeling and empowers us to decrease work-load and prospecting risk in prediction of deep-seated orebodies.
قيم البحث
اقرأ أيضاً
Adequate blood supply is critical for normal brain function. Brain vasculature dysfunctions such as stalled blood flow in cerebral capillaries are associated with cognitive decline and pathogenesis in Alzheimers disease. Recent advances in imaging te
chnology enabled generation of high-quality 3D images that can be used to visualize stalled blood vessels. However, localization of stalled vessels in 3D images is often required as the first step for downstream analysis, which can be tedious, time-consuming and error-prone, when done manually. Here, we describe a deep learning-based approach for automatic detection of stalled capillaries in brain images based on 3D convolutional neural networks. Our networks employed custom 3D data augmentations and were used weight transfer from pre-trained 2D models for initialization. We used an ensemble of several 3D models to produce the winning submission to the Clog Loss: Advance Alzheimers Research with Stall Catchers machine learning competition that challenged the participants with classifying blood vessels in 3D image stacks as stalled or flowing. In this setting, our approach outperformed other methods and demonstrated state-of-the-art results, achieving 0.85 Matthews correlation coefficient, 85% sensitivity, and 99.3% specificity. The source code for our solution is made publicly available.
To improve the performance of most neuroimiage analysis pipelines, brain extraction is used as a fundamental first step in the image processing. But in the case of fetal brain development, there is a need for a reliable US-specific tool. In this work
we propose a fully automated 3D CNN approach to fetal brain extraction from 3D US clinical volumes with minimal preprocessing. Our method accurately and reliably extracts the brain regardless of the large data variation inherent in this imaging modality. It also performs consistently throughout a gestational age range between 14 and 31 weeks, regardless of the pose variation of the subject, the scale, and even partial feature-obstruction in the image, outperforming all current alternatives.
Regional characterization of the continental crust has classically been performed through either geologic mapping, geochemical sampling, or geophysical surveys. Rarely are these techniques fully integrated, due to limits of data coverage, quality, an
d/or incompatible datasets. We combine geologic observations, geochemical sampling, and geophysical surveys to create a coherent 3-D geologic model of a 50 x 50 km upper crustal region surrounding the SNOLAB underground physics laboratory in Canada, which includes the Southern Province, the Superior Province, the Sudbury Structure and the Grenville Front Tectonic Zone. Nine representative aggregate units of exposed lithologies are geologically characterized, geophysically constrained, and probed with 109 rock samples supported by compiled geochemical databases. A detailed study of the lognormal distributions of U and Th abundances and of their correlation permits a bivariate analysis for a robust treatment of the uncertainties. A downloadable 3D numerical model of U and Th distribution defines an average heat production of 1.5$^{+1.4}_{-0.7}$$mu$W/m$^{3}$, and predicts a contribution of 7.7$^{+7.7}_{-3.0}$TNU (a Terrestrial Neutrino Unit is one geoneutrino event per 10$^{32}$ target protons per year) out of a crustal geoneutrino signal of 31.1$^{+8.0}_{-4.5}$TNU. The relatively high local crust geoneutrino signal together with its large variability strongly restrict the SNO+ capability of experimentally discriminating among BSE compositional models of the mantle. Future work to constrain the crustal heat production and the geoneutrino signal at SNO+ will be inefficient without more detailed geophysical characterization of the 3D structure of the heterogeneous Huronian Supergroup, which contributes the largest uncertainty to the calculation.
Reprocessing of regional-scale airborne electromagnetic data (AEM) is used to build a 3D geomodel of the Nasia sub-basin. The resulting 3D geomodel integrates all the prior pieces of information brought by electromagnetic data, lithologic logs, and p
rior geological knowledge. The AEM data, consisting of GEOTEM B-field data, were originally collected for mineral exploration. Thus, those B-field data had to be (re)processed and properly inverted as the original survey and data handling were designed for the detection of potential mineral targets and not for detailed geological mapping. These new
Anomalous activity recognition deals with identifying the patterns and events that vary from the normal stream. In a surveillance paradigm, these events range from abuse to fighting and road accidents to snatching, etc. Due to the sparse occurrence o
f anomalous events, anomalous activity recognition from surveillance videos is a challenging research task. The approaches reported can be generally categorized as handcrafted and deep learning-based. Most of the reported studies address binary classification i.e. anomaly detection from surveillance videos. But these reported approaches did not address other anomalous events e.g. abuse, fight, road accidents, shooting, stealing, vandalism, and robbery, etc. from surveillance videos. Therefore, this paper aims to provide an effective framework for the recognition of different real-world anomalies from videos. This study provides a simple, yet effective approach for learning spatiotemporal features using deep 3-dimensional convolutional networks (3D ConvNets) trained on the University of Central Florida (UCF) Crime video dataset. Firstly, the frame-level labels of the UCF Crime dataset are provided, and then to extract anomalous spatiotemporal features more efficiently a fine-tuned 3D ConvNets is proposed. Findings of the proposed study are twofold 1)There exist specific, detectable, and quantifiable features in UCF Crime video feed that associate with each other 2) Multiclass learning can improve generalizing competencies of the 3D ConvNets by effectively learning frame-level information of dataset and can be leveraged in terms of better results by applying spatial augmentation.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
