Stochastic Generator of Earthquakes for Mainland France

Mainland France is characterized by low-to-moderate seismic activity, yet it is known that major earthquakes could strike this territory (e.g., Liguria in 1887 or Basel in 1356). Assessing this French seismic hazard is thus necessary in order to support building codes and to lead prevention actions towards the population. The Probabilistic Seismic Hazard Assessment (PSHA) is the classical approach used to estimate the seismic hazard. One way to apply PSHA is to generate synthetic earthquakes by propagating information from past seismicity and building various seismic scenarios. In this paper, we present an implementation of a stochastic generator of earthquakes and discuss its relevance to mimic the seismicity of low-to-moderate seismic areas. The proposed stochastic generator produces independent events (main shocks) and their correlated seismicity (only aftershocks). Main shocks are simulated first in time and magnitude considering all available data in the area, and then localized in space with the use of a probability map and regionalization. Aftershocks are simulated around main shocks by considering both the seismic moment ratio and distribution of the aftershock’s proportion. The generator is tested with mainland France data.

MPMR: Multi-Scale Feature and Probability Map for Melanoma Recognition

Malignant melanoma (MM) recognition in whole-slide images (WSIs) is challenging due to the huge image size of billions of pixels and complex visual characteristics. We propose a novel automatic melanoma recognition method based on the multi-scale features and probability map, named MPMR. First, we introduce the idea of breaking up the WSI into patches to overcome the difficult-to-calculate problem of WSIs with huge sizes. Second, to obtain and visualize the recognition result of MM tissues in WSIs, a probability mapping method is proposed to generate the mask based on predicted categories, confidence probabilities, and location information of patches. Third, considering that the pathological features related to melanoma are at different scales, such as tissue, cell, and nucleus, and to enhance the representation of multi-scale features is important for melanoma recognition, we construct a multi-scale feature fusion architecture by additional branch paths and shortcut connections, which extracts the enriched lesion features from low-level features containing more detail information and high-level features containing more semantic information. Fourth, to improve the extraction feature of the irregular-shaped lesion and focus on essential features, we reconstructed the residual blocks by a deformable convolution and channel attention mechanism, which further reduces information redundancy and noisy features. The experimental results demonstrate that the proposed method outperforms the compared algorithms, and it has a potential for practical applications in clinical diagnosis.

A 30-Year Probability Map for Oil Spill Trajectories in the Barents Sea to Assess Potential Environmental and Socio-Economic Threats

Increasing exploration and exploitation activity in the Arctic Ocean has intensified maritime traffic in the Barents Sea. Due to the sparse population and insufficient oil spill response infrastructure on the extensive Barents Sea shoreline, it is necessary to address the possibility of offshore accidents and study hazards to the local environment and its resources. Simulations of surface oil spills were conducted in south-east of the Barents Sea to identify oil pollution trajectories. The objective of this research was to focus on one geographical location, which lies along popular maritime routes and also borders with sensitive ecological marine and terrestrial areas. As a sample of traditional heavy bunker oil, IFO-180LS (2014) was selected for the study of oil spills and used for the 30-year simulations. The second oil case was medium oil type: Volve (2006)—to give a broader picture for oil spill accident scenarios. Simulations for four annual seasons were run with the open source OpenDrift modelling tool using oceanographic and atmospheric data from the period of 1988–2018. The modelling produced a 30-year probability map, which was overlapped with environmental data of the area to discuss likely impacts to local marine ecosystems, applicable oil spill response tools and favourable shipping seasons. Based on available data regarding the environmental and socio-economic baselines of the studied region, we recommend to address potential threats to marine resources and local communities in more detail in a separate study.

GANSim-3D for conditional geomodelling: theory and field application

Geomodelling of subsurface reservoirs is important for water resources, hydrocarbon exploitation, and Carbon Capture and Storage (CCS). Traditional geostatistics-based approaches cannot abstract complex geological patterns and are thus not able to simulate very realistic earth models. We present a Generative Adversarial Networks (GANs)-based 3D reservoir simulation framework, GANSim-3D, which can capture geological patterns and relationships between various conditioning data and earth models and is thus able to directly simulate multiple 3D realistic and conditional earth models of arbitrary sizes from given conditioning data. In GANSim-3D, the generator, designed to only include 3D convolutional layers, takes various 3D conditioning data and 3D random latent cubes (composed of random numbers) as inputs and produces a 3D earth model. Two types of losses, the original GANs loss and condition-based loss, are designed to train the generator progressively from shallow to deep layers to learn the geological patterns and relationships from coarse to fine resolutions. Conditioning data can include 3D sparse well facies data, 3D low-resolution probability maps, and global features like facies proportion, channel width, etc. Once trained on a training dataset where each training sample is a 3D cube of a small fixed size, the generator can be used for geomodelling of 3D reservoirs of large arbitrary sizes by directly extending the sizes of all inputs and the output of the generator proportionally. To illustrate how GANSim-3D is used for field geomodelling and also to verify GANSim-3D, a field karst cave reservoir in Tahe area of China is used as an example. The 3D well facies data and 3D probability map of caves obtained from geophysical interpretation are used as conditioning data. First, we create a training dataset consisting of facies models of 64×64×64 cells with a process-mimicking simulation method to integrate field geological patterns. The training well facies data and the training probability map data are produced from the training facies models. Then, the 3D generator is successfully trained and evaluated in two synthetic cases with various metrics. Next, we apply the pretrained generator for conditional geomodelling of two field cave reservoirs of Tahe area. The first reservoir is 800m×800m×64m and is divided into 64×64×64 cells, while the second is 4200m×3200m×96m and is divided into 336×256×96 cells. We fix the input well facies data and cave probability maps and randomly change the input latent cubes to allow the generator to produce multiple diverse cave reservoir realizations, which prove to be consistent with the geological patterns of real Tahe cave reservoir as well as the input conditioning data. The noise in the input probability map is suppressed by the generator. Once trained, the geomodelling process is quite fast: each realization with 336×256×96 cells takes 0.988 seconds using 1 GPU (V100). This study shows that GANSim-3D is robust for fast 3D conditional geomodelling of field reservoirs of arbitrary sizes.

Detection and Classification of Skin Lesions using Probability Map-based Region Growing with BA-KNN Classifier (Preprint)

BACKGROUND Melanoma is one of the most hazardous existing diseases, and is a kind of threatening pigmented skin lesion. Appropriate automated diagnosis of skin lesions and the categorization of melanoma may be exceptionally enhancing premature identification of melanomas. OBJECTIVE However, Models of categorization based on deterministic skin lesion may influence multi-dimensional nonlinear problem provokes inaccurate and ineffective categorization. This research presents a novel hybrid BA-KNN classification approach for pigmented skin lesions in dermoscopy images. METHODS In the first step, the skin lesion is preprocessed via automatic preprocessing algorithm together with a fusion hair detection and removal strategy. Also, a new probability map based region growing and optimal thresholding algorithm is integrated in this system to enhance the rate of accuracy. RESULTS Moreover, to attain better efficacy, an estimate of ABCD as well as geometric features are considered during the feature extraction to describe the malignancy of the lesion. CONCLUSIONS The evaluation of the experiment reveals the efficiency of the proposed approach on dermoscopy images with better accuracy

“Within a minute” detection of focal cortical dysplasia

Purpose To evaluate a MRI postprocessing tool for the enhanced and rapid detection of focal cortical dysplasia (FCD). Methods MP2RAGE sequences of 40 consecutive, so far MRI-negative patients and of 32 healthy controls were morphometrically analyzed to highlight typical FCD features. The resulting morphometric maps served as input for an artificial neural network generating a FCD probability map. The FCD probability map was inversely normalized, co-registered to the MPRAGE2 sequence, and re-transferred into the PACS system. Co-registered images were scrolled through “within a minute” to determine whether a FCD was present or not. Results Fifteen FCD, three subcortical band heterotopias (SBH), and one periventricular nodular heterotopia were identified. Of those, four FCD and one SBH were only detected by MRI postprocessing while one FCD and one focal polymicrogryia were missed, respectively. False-positive results occurred in 21 patients and 22 healthy controls. However, true positive cluster volumes were significantly larger than volumes of false-positive clusters (p < 0.001). The area under the curve of the receiver operating curve was 0.851 with a cut-off volume of 0.05 ml best indicating a FCD. Conclusion Automated MRI postprocessing and presentation of co-registered output maps in the PACS allowed for rapid (i.e., “within a minute”) identification of FCDs in our clinical setting. The presence of false-positive findings currently requires a careful comparison of postprocessing results with conventional MR images but may be reduced in the future using a neural network better adapted to MP2RAGE images.

A VR-based volumetric medical image segmentation and visualization system with natural human interaction

Volume rendering produces informative two-dimensional (2D) images from a 3-dimensional (3D) volume. It highlights the region of interest and facilitates a good comprehension of the entire data set. However, volume rendering faces a few challenges. First, a high-dimensional transfer function is usually required to differentiate the target from its neighboring objects with subtle variance. Unfortunately, designing such a transfer function is a strenuously trial-and-error process. Second, manipulating/visualizing a 3D volume with a traditional 2D input/output device suffers dimensional limitations. To address all the challenges, we design NUI-VR$$^2$$ 2 , a natural user interface-enabled volume rendering system in the virtual reality space. NUI-VR$$^2$$ 2 marries volume rendering and interactive image segmentation. It transforms the original volume into a probability map with image segmentation. A simple linear transfer function will highlight the target well in the probability map. More importantly, we set the entire image segmentation and volume rendering pipeline in an immersive virtual reality environment with a natural user interface. NUI-VR$$^2$$ 2 eliminates the dimensional limitations in manipulating and perceiving 3D volumes and dramatically improves the user experience.