A real-time intelligent lithology identification method based on a dynamic felling strategy weighted random forest algorithm

Real-time intelligent lithology identification while drilling is vital to realizing downhole closed-loop drilling. The complex and changeable geological environment in the drilling makes lithology identification face many challenges. This paper studies the problems of difficult feature information extraction,low precision of thin-layer identification and limited applicability of the model in intelligent lithologic identification. The author tries to improve the comprehensive performance of the lithology identification model from three aspects: data feature extraction, class balance, and model design. A new real-time intelligent lithology identification model of dynamic felling strategy weighted random forest algorithm(DFW-RF) is proposed. According to the feature selection results, gamma ray and 2 MHz phase resistivity are the logging while drilling(LWD) parameters that significantly influence lithology identification. The comprehensive performance of the DFW-RF lithology identification model has been verified in the application of 3 wells in different areas. By comparing the prediction results of five typical lithology identification algorithms, the DFW-RF model has a higher lithology identification accuracy rate and F1 score. This model improves the identification accuracy of thin-layer lithology and is effective and feasible in different geological environments. The DFW-RF model plays a truly efficient role in the realtime intelligent identification of lithologic information in closed-loop drilling and has greater applicability, which is worthy of being widely used in logging interpretation.

Soft ground tunnel lithology classification using clustering-guided light gradient boosting machine

During tunnel boring machine(TBM)excavation,lithology identification is an important issue to understand tunnelling performance and avoid time-consuming excavation.However,site investigation generally lacks ground samples and the information is subjective,heterogeneous,and imbalanced due to mixed ground conditions.In this study,an unsupervised(K-means)and synthetic minority oversampling technique(SMOTE)-guided light-gradient boosting machine(LightGBM)classifier is proposed to identify the soft ground tunnel classification and determine the imbalanced issue of tunnelling data.During the tunnel excavation,an earth pressure balance(EPB)TBM recorded 18 different operational parameters along with the three main tunnel lithologies.The proposed model is applied using Python low-code PyCaret library.Next,four decision tree-based classifiers were obtained in a short time period with automatic hyperparameter tuning to determine the best model for clustering-guided SMOTE application.In addition,the Shapley additive explanation(SHAP)was implemented to avoid the model black box problem.The proposed model was evaluated using different metrics such as accuracy,F1 score,precision,recall,and receiver operating characteristics(ROC)curve to obtain a reasonable outcome for the minority class.It shows that the proposed model can provide significant tunnel lithology identification based on the operational parameters of EPB-TBM.The proposed method can be applied to heterogeneous tunnel formations with several TBM operational parameters to describe the tunnel lithologies for efficient tunnelling.

Crustal S-wave velocity structure across the northeastern South China Sea continental margin: implications for lithology and mantle exhumation

The northeastern margin of the South China Sea (SCS), developed from continental rifting and breakup, is usually thought of as a non-volcanic margin. However, post-spreading volcanism is massive and lower crustal high-velocity anomalies are widespread, which complicate the nature of the margin here. To better understand crustal seismic velocities, lithology, and geophysical properties, we present an S-wave velocity (VS) model and a VP/VS model for the northeastern margin by using an existing P-wave velocity (VP) model as the starting model for 2-D kinematic S-wave forward ray tracing. The Mesozoic sedimentary sequence has lower VP/VS ratios than the Cenozoic sequence;in between is a main interface of P-S conversion. Two isolated high-velocity zones (HVZ) are found in the lower crust of the continental slope, showing S-wave velocities of 4.0–4.2 km/s and VP/VS ratios of 1.73–1.78. These values indicate a mafic composition, most likely of amphibolite facies. Also, a VP/VS versus VP plot indicates a magnesium-rich gabbro facies from post-spreading mantle melting at temperatures higher than normal. A third high-velocity zone (VP : 7.0–7.8 km/s;VP/VS: 1.85–1.96), 70-km wide and 4-km thick in the continent-ocean transition zone, is most likely to be a consequence of serpentinization of upwelled upper mantle. Seismic velocity structures and also gravity anomalies indicate that mantle upwelling/ serpentinization could be the most severe in the northeasternmost continent-ocean boundary of the SCS. Empirical relationships between seismic velocity and degree of serpentinization suggest that serpentinite content decreases with depth, from 43% in the lower crust to 37% into the mantle.

Deep learning of rock microscopic images for intelligent lithology identification: Neural network comparison and selection

An intelligent lithology identification method is proposed based on deep learning of the rock microscopic images.Based on the characteristics of rock images in the dataset,we used Xception,MobileNet_v2,Inception_ResNet_v2,Inception_v3,Densenet121,ResNet101_v2,and ResNet-101 to develop microscopic image classification models,and then the network structures of seven different convolutional neural networks(CNNs)were compared.It shows that the multi-layer representation of rock features can be represented through convolution structures,thus better feature robustness can be achieved.For the loss function,cross-entropy is used to back propagate the weight parameters layer by layer,and the accuracy of the network is improved by frequent iterative training.We expanded a self-built dataset by using transfer learning and data augmentation.Next,accuracy(acc)and frames per second(fps)were used as the evaluation indexes to assess the accuracy and speed of model identification.The results show that the Xception-based model has the optimum performance,with an accuracy of 97.66%in the training dataset and 98.65%in the testing dataset.Furthermore,the fps of the model is 50.76,and the model is feasible to deploy under different hardware conditions and meets the requirements of rapid lithology identification.This proposed method is proved to be robust and versatile in generalization performance,and it is suitable for both geologists and engineers to identify lithology quickly.

Predicting formation lithology from log data by using a neural network

In order to increase drilling speed in deep complicated formations in Kela-2 gas field, Tarim Basin, Xinjiang, west China, it is important to predict the formation lithology for drilling bit optimization. Based on the conventional back propagation （BP） model, an improved BP model was proposed, with main modifications of back propagation of error, self-adapting algorithm, and activation function, also a prediction program was developed. The improved BP model was successfully applied to predicting the lithology of formations to be drilled in the Kela-2 gas field.

Source Lithology and Magmatic Processes Recorded in the Mineral of Basalts from the Parece Vela Basin

Since the Early Cenozoic,the Philippine Sea Plate(PSP)has undergone a complex tectonic evolution.During this period the Parece Vela Basin(PVB)was formed by seafloor spreading in the back-arc region of the proto-Izu-Bonin-Mariana(IBM)arc.However,until now,studies of the geological,geophysical,and tectonic evolution of the PVB have been rare.In this study,we obtained in situ trace element and major element compositions of minerals in basalts collected from two sites in the southern part of the PVB.The results reveal that the basalts from site CJ09-63 were likely formed via~10%partial melting of spinel-garnet lherzolite,while the basalts from site CJ09-64 were likely formed via 15%–25%partial melting of garnet lherzolite.The order of mineral crystallization for the basalts from site CJ09-64 was olivine,spinel,clinopyroxene,and plagioclase,while the plagioclase in the basalts from site CJ09-63 crystallized earlier than the clinopyroxene.Using a plagioclase-liquid hygrometer and an olivine-liquid oxybarometer,we determined that the basalts in this study have high H2O contents and oxygen fugacities,suggesting that the magma source of the Parece Vela basalts was affected by subduction components,which is consistent with the trace element composition of whole rock.

Porosity and Lithology Prediction in Eve Field, Niger Delta Using Compaction Curves and Rock Physics Models

The primary objective of this study is to investigate the porosity-depth trends of shales and sands and how they affect lithologies. Compaction curves from well logs of five wells were determined using interval transit time from sonic logs. The depth of investigation lies between 1087 m and 2500 m. Based on the shale and sand trend modeling, the study intends to determine the model to be used for lithology prediction at various depths given the interplay between shale and sand compaction. The improved understanding of the physical properties of shales and sands as a function of burial depth was demonstrated, in conjunction with a good understanding of how compaction affects lithology. The compaction curve for shale and sand lithologies varies with shale being parabolic in form, and sands with linear and exponential in nature. Plots of sonic porosity against depth show great dispersion in porosity values while plotting porosity values against depth for different lithologies produced well-defined porosity trends. This shows decrease in porosity with depth. The negative porosity trend is less marked in sandstones, and faster in shale which suggests that it is possible to make accurate porosity predictions using compaction trend. The porosity trend showed exponential relationship at small depth less than 2500m. The linear and exponential models are not dependable at large depth. The result shows that the compaction models applicable for sandstones do not necessary apply for shales.

Comparisons on Mineralogy and Lithology between Paleozoic Marine and Lacustrine Dolostones, Northern China

1 Introduction Dolomite[Ca Mg(CO3)2],a common mineral in carbonate rocks,can be found in various geological settings from Precambrian to modern age,and is widely reported in almost all sedimentary and digenetic

Adaptive Identification of Logging Lithology Based on VPSO-ENN Hybrid Algorithm

Particle swarm optimization （PSO） was modified by variation method of particle velocity, and a variation PSO （VPSO） algorithm was proposed to overcome the shortcomings of PSO, such as premature convergence and local optimization. The VPSO algorithm is combined with Elman neural network （ENN） to form a VPSO-ENN hybrid algorithm. Compared with the hybrid algorithm of genetic algorithm （GA） and BP neural network （GA-BP）, VPSO-ENN has less adjustable parameters, faster convergence speed and higher identification precision in the numerical experiment. A system for identifying logging parameters was established based on VPSO-ENN. The results of an engineering case indicate that the intelligent identification system is effective in the lithology identification.

SPATIAL CORRELATION ANALYSIS BETWEEN KARST ROCKY DESERTIFICATION AND LITHOLOGY IN DU'AN YAO AUTONOMOUS COUNTY IN GUANGXI

Du’an Yao Autonomous County is a typical area for the distribution of karst rocky desertification in Guangxi. The indices for the grades of rocky desertification are selected according to the scientific meaning of karst rocky desertification and after the interpretative symbol system of rocky desertification. RS images are established by the landscape characteristics of Du’an karst and its TM image. Relying on RS & GIS means and taking land use map as base map, this paper conducts synthetic analysis on the 1999a TM image (126-043) and the correlation data involving landform, soil, geological map and GPS—database and photo on the spot, and brings forth a map showing the Du’an rocky desertification grades and a digital lithology map. As can be viewed from spatial correlation, the inherent connection is also illuminated between the various levels of rocky desertification and the carbonate lithology.

LATE CENOZOIC LITHOLOGY AND MAGNETIC POLARITY STRATIGRAPHY IN THE JIUXI BASIN: IMPLICATIONS FOR TECTONIC EVENTS OF THE WEST QILIAN MT

The synorogenic sediments in the foreland basins preserve a potential record of varied depositional environments that respond to and are largely controlled by tectonic events of the mountain along the basin margin. In the exploration of the uplift process of the Qinghai—Tibet Plateau, research on the foreland basins around the plateau is of vital significance. Much work have been carried out on the southern margin along the Himalayas and on the eastern margin, however, seldom work was reported along the northern boundary of the plateau, this have blocked the generation of an integrative image of the evolution of the entire plateau. The Gansu Corridor, located on the northeast margin of the Qinghai—Tibet Plateau, is a Cenozoic foreland basin system formed due to the northward overthrust and overload of the plateau. Thousand of meters detrital sediments derived mainly from denudation of the Qilian orogen have deposited in the basin since Oligocene. Here we report a detailed lithologic and magnetostratigraphic work carried out on the late Cenozoic sedimentary sequences in the Jiuxi Basin, western Gansu Corridor, to investigate the neotectonism of the western Qilian Mt.

Influence of borehole quantity and distribution on lithology field simulation

This paper aims to study the influence of the number and distribution of drill samples on the simulation accuracy of the lithology field. This research mainly applies the variation function method in geo-statistics, and determines important indicators such as the variation, and then the lithology field is simulated by sequence index simulation. It is shown that(1) simulation error decreases with the increase of sampling density;(2) at the scale and complexity of this study, when the sampling density reaches 40/km^2, the average error of the lithology field simulation can be less than 2.0%;(3) in the study mode of examples, the simulation results of random sampling in the whole region are the most ideal, with an average error of 5.4%. The average error of the simulation results of the centralized sampling is about 10 times that of the random sampling method;(4) known from the influence analysis of the degree of study sample unevenness influence on the imitation results, under the same sample size, the simulation error decreases with the increase of the most adjacent index. When the nearest index reaches 1, the simulation error will be less than 6%, and the error variable range is within 3%.

Experimental Geotechnical Characterization Campaign of the Matam Soil for Lithology: Application to the Study of Supports of the Balterdi Bridge

This paper presents a geotechnical study whose objective is to determine the lithology of the soil of Balterdi village (Matam, Senegal). A bridge-type structure with six supports is to be built on the studied site. The drilling program consisted of six core drillings (SC) each 30 m deep with sampling and six destructive drillings with pressuremeter tests (SP) every 1.5 m up to 30 m deep. A pair of core and pressuremeter tests was carried out under each support. From the results of the core drill holes and the geological model of the site, it can be seen that the lithology of the soil along the structure consists essentially of soft clay layers, becoming firm at depth over the first 18 m on average (with some incursions of sandy layers) resting on medium to compacted sand up to 30 m. Brown clayey fill is also present between piers P3 and P5. The presence of a watercourse along the structure is noted. The foundations will therefore be carried out in the water. The results of the pressuremeter tests confirm the homogeneity of the soil over the whole area. Indeed, the values obtained are almost similar for all the tests. According to the limit pressures obtained, the clayey-sandy formations encountered along the structure are respectively soft to firm and moderately compact to compact. Their limit pressures are high enough to allow good bearing capacities.

Evaluating Sediment Production Caused by the Lithology of the Geological Formations in Sedimentary Basins (Case Study: Lali Area, Khuzestan, Iran)

As sediments are produced and accumulated in sedimentary basins especially in dams’ reservoirs and they highly affect the reservoirs life span, it is essential to scrutinize the effect of lithology and types of geological formations of an area on the life span of reservoirs specifically from the viewpoints of the erodability of these formations due to their lithology type. Lali area, Khuzestan, Iran and the water catchment of the intended area (based on geological situation and Taraz dam situation) are placed in the sedimentary-structural zone of the folded Zagros. The method of this research is based on analyzing the topography and geology maps and field work in order to identify the lithology of the geological formations. In fact, the amount of its erodability has been characterized by the type of the geological formations. The current research aims at putting the geological results, lithological data of the formations types and the outcrop of the soil-lithological units together in order to evaluate the sedimentary and erosive factors of these units and precisely identify the area’s geological formations to remove the ambiguities in this issue. Studies indicate that formations made of looser gypsum and marl like Pabde-Gurpi and Gachsaran are exposed to more sedimentation and erosion than the formations made of compacted lime stone and conglomerate with silica-lime cement such as Bakhtiary and Asmari formations and the sand stones of Aghajari formation reveal the moderate to high resistance. Thus, the lithological identification of the formations, the type of sediments and their looseness and hardness contribute to detect the amount and type of deposits entering into the dam reservoir. The type and amount of these transported and deposited sediments are assessed to predict more suitable optimized ways to exploit dams’ reservoirs.

Hard-rock tunnel lithology identification using multiscale dilated convolutional attention network based on tunnel face images

For real-time classification of rock-masses in hard-rock tunnels,quick determination of the rock lithology on the tunnel face during construction is essential.Motivated by current breakthroughs in artificial intelligence technology in machine vision,a new automatic detection approach for classifying tunnel lithology based on tunnel face images was developed.The method benefits from residual learning for training a deep convolutional neural network(DCNN),and a multi-scale dilated convolutional attention block is proposed.The block with different dilation rates can provide various receptive fields,and thus it can extract multi-scale features.Moreover,the attention mechanism is utilized to select the salient features adaptively and further improve the performance of the model.In this study,an initial image data set made up of photographs of tunnel faces consisting of basalt,granite,siltstone,and tuff was first collected.After classifying and enhancing the training,validation,and testing data sets,a new image data set was generated.A comparison of the experimental findings demonstrated that the suggested approach outperforms previous classifiers in terms of various indicators,including accuracy,precision,recall,F1-score,and computing time.Finally,a visualization analysis was performed to explain the process of the network in the classification of tunnel lithology through feature extraction.Overall,this study demonstrates the potential of using artificial intelligence methods for in situ rock lithology classification utilizing geological images of the tunnel face.

Multi-scale data joint inversion of minerals and porosity in altered igneous reservoirs—A case study in the South China Sea

There are abundant igneous gas reservoirs in the South China Sea with significant value of research,and lithology classification,mineral analysis and porosity inversion are important links in reservoir evaluation.However,affected by the diverse lithology,complicated mineral and widespread alteration,conventional logging lithology classification and mineral inversion become considerably difficult.At the same time,owing to the limitation of the wireline log response equation,the quantity and accuracy of minerals can hardly meet the exploration requirements of igneous formations.To overcome those issues,this study takes the South China Sea as an example,and combines multi-scale data such as micro rock slices,petrophysical experiments,wireline log and element cutting log to establish a set of joint inversion methods for minerals and porosity of altered igneous rocks.Specifically,we define the lithology and mineral characteristics through core slices and mineral data,and establish an igneous multi-mineral volumetric model.Then we determine element cutting log correction method based on core element data,and combine wireline log and corrected element cutting log to perform the lithology classification and joint inversion of minerals and porosity.However,it is always difficult to determine the elemental eigenvalues of different minerals in inversion.This paper uses multiple linear regression methods to solve this problem.Finally,an integrated inversion technique for altered igneous formations was developed.The results show that the corrected element cutting log are in good agreement with the core element data,and the mineral and porosity results obtained from the joint inversion based on the wireline log and corrected element cutting log are also in good agreement with the core data from X-ray diffraction.The results demonstrate that the inversion technique is applicable and this study provides a new direction for the mineral inversion research of altered igneous formations.

Lithology, kinematics and geochronology related to Late Mesozoic basin-mountain evolution in the Nanxiong-Zhuguang area, South China

The Nanxiong red-bed basin and its adjacent Zhuguang granite form a distinctive basin-mountain landform in the Nanling region, South China. Research results suggest that the Zhuguang granite is a polyphase composite pluton developed on the metamorphic basement of the paleo-Tethys-paleo-Asian tectonic regime and possesses geometrical and kinematic features of hot-doming extensional tectonics at the middle-upper crustal level, which is considered as a magmatic complex that resulted from the collision-orogeny during the Indosinian Period, the subduction-consuming during the Early Yanshanian Period and the intra-continental basaltic underplating and deep-seated geodynamics during the Late Yanshanian Period. The Nanxiong basin is a Late Cretaceous-Paleogene asymmetric faulted basin that is characterized by a fault boundary on the northern side and an uncomformable boundary on the southern side, its deposit center was migrated gradually from south to north. Structural kinematic results on the ba-sin-mountain coupled zone demonstrate that the ductile and the brittle rheological layers show a quite coincident sense of shear, implying that it is a continuous process from the ductile exten-sional deformation followed by locally sinistral strike-slip shear at a middle-crustal level to the brittle tensional deformation at a upper-crustal level during formation of granitic doming exten-sional tectonics. The Zhuguang granite and the Nanxiong faulted basin constructed a semi-graben tectonic system. Lithological and geochemical results suggest that the Late Triassic to Jurassic granitic bodies in the Zhuguang have some similar features: high SiO2, Al2O3, K2O contents, alkalinity index > 2.8, ANKC value > 1.1, LREE-enriched pattern with high REE con-tents, marked negative Eu anomalies, enrichment in Rb and Th, depletion in Ba and Nb, showing a K-rich and Al-rich calc-alkaline affinity, which suggest a continuous magmatic evolution from Late Triassic to Jurassic. Formation of Nanxiong basin and evolution of basin-mountain system were controlled both by the Zhuguang granitic-doming and the regional extensional tectonics. Development of the olivine basalt in the basin suggests that tension action was very strong dur-ing lava eruption. The magma-type zircon grains of basalt from the Nanxiong basin yielded the SHRIMP age of 96?Ma, providing reliable geochronological constraint on the tectono-thermal event and basin-mountain evolution in the Nanling region, South China.

Lithology Classification Based on Set-Valued Identification Method

Lithology classification using well logs plays a key role in reservoir exploration.This paper studies the problem of lithology identification based on the set-valued method(SV),which uses the SV model to establish the relation between logging data and lithologic types at a certain depth point.In particular,the system model is built on the assumption that the noise between logging data and lithologic types is normally distributed,and then the system parameters are estimated by SV method based on the existing identification criteria.The logging data of Shengli Oilfield in Jiyang Depression are used to verify the effectiveness of SV method.The results indicate that the SV model classifies lithology more accurately than the Logistic Regression model(LR)and more stably than uninterpretable models on imbalanced dataset.Specifically,the Macro-F1 of the SV models(i.e.,SV(3),SV(5),and SV(7))are higher than 85%,where the sandstone samples account for only 22%.In addition,the SV(7)lithology identification system achieves the best stability,which is of great practical significance to reservoir exploration.

A Real-time Lithological Identification Method based on SMOTE-Tomek and ICSA Optimization

In petroleum engineering,real-time lithology identification is very important for reservoir evaluation,drilling decisions and petroleum geological exploration.A lithology identification method while drilling based on machine learning and mud logging data is studied in this paper.This method can effectively utilize downhole parameters collected in real-time during drilling,to identify lithology in real-time and provide a reference for optimization of drilling parameters.Given the imbalance of lithology samples,the synthetic minority over-sampling technique(SMOTE)and Tomek link were used to balance the sample number of five lithologies.Meanwhile,this paper introduces Tent map,random opposition-based learning and dynamic perceived probability to the original crow search algorithm(CSA),and establishes an improved crow search algorithm(ICSA).In this paper,ICSA is used to optimize the hyperparameter combination of random forest(RF),extremely random trees(ET),extreme gradient boosting(XGB),and light gradient boosting machine(LGBM)models.In addition,this study combines the recognition advantages of the four models.The accuracy of lithology identification by the weighted average probability model reaches 0.877.The study of this paper realizes high-precision real-time lithology identification method,which can provide lithology reference for the drilling process.

Development of a convolutional neural network based geomechanical upscaling technique for heterogeneous geological reservoir

Geomechanical assessment using coupled reservoir-geomechanical simulation is becoming increasingly important for analyzing the potential geomechanical risks in subsurface geological developments.However,a robust and efficient geomechanical upscaling technique for heterogeneous geological reservoirs is lacking to advance the applications of three-dimensional(3D)reservoir-scale geomechanical simulation considering detailed geological heterogeneities.Here,we develop convolutional neural network(CNN)proxies that reproduce the anisotropic nonlinear geomechanical response caused by lithological heterogeneity,and compute upscaled geomechanical properties from CNN proxies.The CNN proxies are trained using a large dataset of randomly generated spatially correlated sand-shale realizations as inputs and simulation results of their macroscopic geomechanical response as outputs.The trained CNN models can provide the upscaled shear strength(R^(2)>0.949),stress-strain behavior(R^(2)>0.925),and volumetric strain changes(R^(2)>0.958)that highly agree with the numerical simulation results while saving over two orders of magnitude of computational time.This is a major advantage in computing the upscaled geomechanical properties directly from geological realizations without the need to perform local numerical simulations to obtain the geomechanical response.The proposed CNN proxybased upscaling technique has the ability to(1)bridge the gap between the fine-scale geocellular models considering geological uncertainties and computationally efficient geomechanical models used to assess the geomechanical risks of large-scale subsurface development,and(2)improve the efficiency of numerical upscaling techniques that rely on local numerical simulations,leading to significantly increased computational time for uncertainty quantification using numerous geological realizations.