Deep neural network application for 4D seismic inversion to changes in pressure and saturation: Optimizing the use of synthetic training datasets     

Gustavo Côrte  Jesper Dramsch  Hamed Amini  Colin MacBeth 《Geophysical Prospecting》2020,68(7):2164-2185

In this work, we tackle the challenge of quantitative estimation of reservoir dynamic property variations during a period of production, directly from four-dimensional seismic data in the amplitude domain. We employ a deep neural network to invert four-dimensional seismic amplitude maps to the simultaneous changes in pressure, water and gas saturations. The method is applied to a real field data case, where, as is common in such applications, the data measured at the wells are insufficient for properly training deep neural networks, thus, the network is trained on synthetic data. Training on synthetic data offers much freedom in designing a training dataset, therefore, it is important to understand the impact of the data distribution on the inversion results. To define the best way to construct a synthetic training dataset, we perform a study on four different approaches to populating the training set making remarks on data sizes, network generality and the impact of physics-based constraints. Using the results of a reservoir simulation model to populate our training datasets, we demonstrate the benefits of restricting training samples to fluid flow consistent combinations in the dynamic reservoir property domain. With this the network learns the physical correlations present in the training set, incorporating this information into the inference process, which allows it to make inferences on properties to which the seismic data are most uncertain. Additionally, we demonstrate the importance of applying regularization techniques such as adding noise to the synthetic data for training and show a possibility of estimating uncertainties in the inversion results by training multiple networks.  相似文献   

Intra-survey reservoir fluctuations – implications for quantitative 4D seismic analysis     

Veronica Omofoma  Colin MacBeth  Hamed Amini 《Geophysical Prospecting》2019,67(2):282-297

During the time taken for seismic data to be acquired, reservoir pressure may fluctuate as a consequence of field production and operational procedures and fluid fronts may move significantly. These variations prevent accurate quantitative measurement of the reservoir change using 4D seismic data. Modelling studies on the Norne field simulation model using acquisition data from ocean-bottom seismometer and towed streamer systems indicate that the pre-stack intra-survey reservoir fluctuations are important and cannot be neglected. Similarly, the time-lapse seismic image in the post-stack domain does not represent a difference between two states of the reservoir at a unique base and monitor time, but is a mixed version of reality that depends on the sequence and timing of seismic shooting. The outcome is a lack of accuracy in the measurement of reservoir changes using the resulting processed and stacked 4D seismic data. Even for perfect spatial repeatability between surveys, a spatially variant noise floor is still anticipated to remain. For our particular North Sea acquisition data, we find that towed streamer data are more affected than the ocean-bottom seismometer data. We think that this may be typical for towed streamers due to their restricted aperture compared to ocean-bottom seismometer acquisitions, even for a favourable time sequence of shooting and spatial repeatability. Importantly, the pressure signals on the near and far offset stacks commonly used in quantitative 4D seismic inversion are found to be inconsistent due to the acquisition timestamp. Saturation changes at the boundaries of fluid fronts appear to show a similar inconsistency across sub-stacks. We recommend that 4D data are shot in a consistent manner to optimize aerial time coverage, and that additionally, the timestamp of the acquisition should be used to optimize pre-stack quantitative reservoir analysis.  相似文献   

Wildfire impacts on education and healthcare: Paradise,California, after the Camp Fire     

Hamideh  Sara  Sen  Payel  Fischer  Erica 《Natural Hazards》2022,111(1):353-387

Natural Hazards - The 2018 Camp Fire caused significant damages to the education and healthcare systems in the town of Paradise, CA. This paper presents the findings of a qualitative case study...  相似文献   

A Method for Automatic Road Extraction of High Resolution SAR Imagery     

M. Saati  J. Amini  M. Maboudi 《Journal of the Indian Society of Remote Sensing》2015,43(4):697-707

  相似文献   

Embedment effects of flexible foundations on control of structures     

Fereidoun Amini  Masoud Shadlou 《Soil Dynamics and Earthquake Engineering》2011

  相似文献   

Recent developments of the Middle East catalog   总被引：8，自引：2，他引：6  

Mehdi Zare  Hamideh Amini  Pouye Yazdi  Karin Sesetyan  Mine Betul Demircioglu  Dogan Kalafat  Mustafa Erdik  Domenico Giardini  M. Asif Khan  Nino Tsereteli 《Journal of Seismology》2014,18(4):749-772

This article summarizes a recent study in the framework of the Global Earth model (GEM) and the Earthquake Model of the Middle East (EMME) project to establish the new catalog of seismicity for the Middle East, using all historical (pre-1900), early and modern instrumental events up to 2006. According to different seismicity, which depends on geophysical, geological, tectonic, and seismicity data, this region is subdivided to nine subregions, consisting of Alborz–Azerbaijan, Afghanistan–Pakistan, Saudi Arabia, Caucasus, Central Iran, Kopeh–Dagh, Makran, Zagros, and Turkey (Eastern Anatolia; after 30° E). After omitting the duplicate events, aftershocks, and foreshocks by using the Gruenthal method, and uniform all magnitude to Mw scale, 28,244 main events remain for the new catalog of Middle East from 1250 B.C. through 2006. The magnitude of completeness (Mc) was determined as 4.9 for five out of nine subregions, where the least values of Mc were found to be 4.2. The threshold of Mc is around 5.5, 5.0, 4.5, and 4.0, for the time after 1950, 1963, 1975, and 2000, respectively. The average of teleseismic depths in all regions is less than 15 km. Totally, majority of depth for Kopeh–Dagh and Central Iran, Zagros, and Alborz–Azerbaijan, approximately, is 15, 13, and 11 km and for Afghanistan–Pakistan, Caucasus, Makran, Turkey (after 30° E), and Saudi Arabia is about 9 km.  相似文献   

Biosorption of Cd(II), Ni(II) and Pb(II) from Aqueous Solution by Dried Biomass of Aspergillus niger: Application of Response Surface Methodology to the Optimization of Process Parameters     

Malihe Amini  Habibollah Younesi 《洁净——土壤、空气、水》2009,37(10):776-786

In this study, the biosorption of Cd(II), Ni(II) and Pb(II) on Aspergillus niger in a batch system was investigated, and optimal condition determined by means of central composite design (CCD) under response surface methodology (RSM). Biomass inactivated by heat and pretreated by alkali solution was used in the determination of optimal conditions. The effect of initial solution pH, biomass dose and initial ion concentration on the removal efficiency of metal ions by A. niger was optimized using a design of experiment (DOE) method. Experimental results indicated that the optimal conditions for biosorption were 5.22 g/L, 89.93 mg/L and 6.01 for biomass dose, initial ion concentration and solution pH, respectively. Enhancement of metal biosorption capacity of the dried biomass by pretreatment with sodium hydroxide was observed. Maximal removal efficiencies for Cd(II), Ni(III) and Pb(II) ions of 98, 80 and 99% were achieved, respectively. The biosorption capacity of A. niger biomass obtained for Cd(II), Ni(II) and Pb(II) ions was 2.2, 1.6 and 4.7 mg/g, respectively. According to these observations the fungal biomass of A. niger is a suitable biosorbent for the removal of heavy metals from aqueous solutions. Multiple response optimization was applied to the experimental data to discover the optimal conditions for a set of responses, simultaneously, by using a desirability function.  相似文献   

A single-run multi-mode pushover analysis to account for the effect of higher modes in estimating the seismic demands of tall buildings   总被引：1，自引：1，他引：0  

Mehdi Poursha  Mohamad Amin Amini 《Bulletin of Earthquake Engineering》2015,13(8):2347-2365

  相似文献   

Estimating the Shapes of Gravity Sources through Optimized Support Vector Classifier (SVC)     

Mohammad E. Hekmatian  Vahid E. Ardestani  Mohammad A. Riahi  Ayyub M. K. Bagh  Jalal Amini 《Acta Geophysica》2015,63(4):1000-1024

In gravity interpretation methods, an initial guess for the approximate shape of the gravity source is necessary. In this paper, the support vector classifier (SVC) is applied for this duty by using gravity data. It is shown that using SVC leads us to estimate the approximate shapes of gravity sources more objectively. The procedure of selecting correct features is called feature selection (FS).In this research, the proper features are selected using inter/intra class distance algorithm and also FS is optimized by increasing and decreasing the number of dimensions of features space. Then, by using the proper features, SVC is used to estimate approximate shapes of sources from the six possible shapes, including: sphere, horizontal cylinder, vertical cylinder, rectangular prism, syncline, and anticline. SVC is trained using 300 synthetic gravity profiles and tested by 60 other synthetic and some real gravity profiles (related to a well and two ore bodies), and shapes of their sources estimated properly.  相似文献   

Eocene continental dyke swarm from Central Iran (Khur area)     

Ghodrat Torabi  Shoji Arai  Hamideh Abbasi 《Petrology》2014,22(6):617-632

The Eocene dyke swarm with east-west general trend intrudes the Cretaceous sedimentary rocks in ～25 km north of the Khur city (Central Iran). Some of the studied dykes can be followed for over 7 km, but the majority of exposures in the area are less than 5 km long. The dykes commonly exhibit a chilled contact with the wall rocks. These dykes are trachybasalt and basalt in composition. The trachybasalt dykes are much more abundant. The basaltic dykes cross cut the trachybasalt dykes in some locations, indicating that trachybasalt dykes are older than the basaltic ones. Primary igneous minerals of the basaltic dykes are olivine (chrysolite), clinopyroxene (diopside, augite), plagioclase (labradorite), sanidine, magnetite, orthopyroxene (enstatite), spinel and phlogopite, and secondary minerals are zeolite (natrolite and mesolite), chlorite (diabantite), calcite and serpentine. The trachybasalt dykes are composed of clinopyroxene (diopside), plagioclase (labradorite), sanidine, mica (biotite and phlogopite), amphibole (magnesio-hastingsite) and magnetite as primary minerals, and chlorite and calcite as secondary ones. Whole rocks geochemical data of the studied dykes indicate their basic and calc-alkaline nature and suggest that these two set of dykes were derived from the same parental magma. The chondrite-normalized REE patterns and the primitive mantle-normalized multi-elemental diagram of the Khur dykes show enrichment of light rare earth elements (LREE) relative to heavy rare earth elements (HREE), and negative anomalies of high field strength elements (HFSE) (e.g. Ti, Nb and Ta). These rocks show enrichment of the large ion lithophile elements (LILE) (e.g. Cs, Ba, Th and U) and depletion of the HREE and Y relative to MREE, Zr and Hf. In the chondrite-normalized REE diagram, the basalts show elevated REE abundances relative to the trachybasalt samples. Geochemical analyses of the studied samples suggest a spinel lherzolite from the mantle as the source rock and confirm the role of subduction in their generation. The chemical characteristics of the Khur dykes resemble those of continental arc rocks, and they were possibly formed by subduction of the Central-East Iranian microcontinent (CEIM) confining oceanic crust and decompression melting of a lithospheric subcontinental mantle spinel lherzolite enriched by subduction.  相似文献