39 results about "Sedimentary rock" patented technology

The invention relates to the technical field of intelligent sensing systems, and provides a cross-well earthquake and VSP-based VTI anisotropic parameter inversion method, which comprises the following steps: acquiring first arrival information and speed information recorded by a zero well spacing VSP in a target exploration area, and establishing a near-well initial vertical speed model; acquiring first arrival information of excitation points at different depths of an inter-well earthquake in the area, and calculating to obtain the transverse velocity of a VTI anisotropic medium at each depth; solving the anisotropic medium value of each depth VTI; obtaining a VTI anisotropic medium delta value; and performing interpolation smoothing along a geologic horizon by using the epsilon value and the delta value of the VTI anisotropic medium to obtain an epsilon field and a delta field of the VTI anisotropic medium so as to form a VTI anisotropic body. The objective of the invention is to solve the problem of low accuracy of sedimentary rock feature analysis caused by poor matching of a velocity model and anisotropy parameters in traditional VTI anisotropy research.

A method for evaluating geological hydrogen source rock in a region is provided. The method includes: collecting magnetic susceptibility data from a plurality of subsurface locations in the region; receiving geophysical survey data of the region, wherein the geophysical survey data comprises geophysical data collected from above ground; tying the magnetic susceptibility data of the plurality of subsurface locations to the geophysical survey data; generating a geologic map of igneous rock, metamorphic rock, or mafic mineral- or iron-rich sedimentary rock within the region based on the magnetic susceptibility data using a model; and determining, based on the geologic map, a target zone of the geological hydrogen source rock with a potential for hydrogen production or with the potential for hydrogen accumulation.

This invention relates to a method for characterizing the distribution of primordial water in rocks and its application. The method includes: preparing particles from fresh rock cores as fresh samples and particles from dried rock cores as dried samples; calculating the scattering length density of the rock to be tested based on the dried sample, and preparing a deuterated toluene contrast-matching fluid with the same scattering length density as the rock to be tested; immersing the fresh sample and the dried sample in the deuterated toluene contrast-matching fluid respectively to obtain immersion samples; performing small-angle neutron scattering (SANS) experiments on the dried sample and the immersion samples respectively; obtaining pore structure information before and after immersion based on the experimental results; and determining the distribution of primordial water in the rock to be tested based on the pore structure information. This invention, based on SANS experiments, provides a novel experimental technique for characterizing the distribution and water saturation of primordial water in sedimentary rocks, with advantages such as being non-destructive, efficient, time-saving, and highly accurate.

This application provides a method, apparatus, equipment, and storage medium for quantitative evaluation of oil layers in mud-class reservoirs, belonging to the field of oil and gas exploration and development technology. In this method, based on the parameter values ​​of multiple logging parameters of a first reference block in the target block, the fine-grained sedimentary rock reservoirs in the first reference block, the effective reservoirs within the fine-grained sedimentary rock reservoirs, and the distinction between industrial and non-industrial oil flow layers within the effective reservoirs can be made, thereby determining a set of quantitative evaluation thresholds. These multiple logging parameters include natural gamma, resistivity, spontaneous potential, total organic carbon content, compensated density, NMR porosity, and NMR saturation. This set of quantitative evaluation thresholds is used to identify industrial oil flow layers in the target block. The quantitative evaluation thresholds determined by the above method can efficiently and accurately identify industrial oil flow layers in the target block, thus providing a reliable basis for subsequent oil and gas exploration and development, and improving the efficiency of oil and gas exploration and development.

The invention belongs to the technical field of sedimentary geology research, and discloses a quantitative sedimentary rock classification evaluation method and system based on biological disturbance. The method comprises the following steps: acquiring a high-resolution image of a unit area of a field outcrop or core sample; identifying a relics fossil or a biological disturbance area in the high-resolution image, and obtaining a biological disturbance quantity percentage of the high-resolution image by using a unit grid method; identifying the belonging number of the relics fossils in the high-resolution image; measuring to obtain the diving hole diameter of each relics fossil, and obtaining the diving hole diameter of the maximum relics fossil; obtaining the natural layer thickness of the field outcrop or rock core sample and the average particle size of the surrounding rock; calculating to obtain a biological disturbance coefficient; and based on the biological disturbance coefficient of the field outcrop or rock core sample, evaluating to obtain a classification evaluation result of the sedimentary rock. When a researcher performs classification evaluation on the same or similar sedimentary rock samples, a relatively consistent result can be obtained, and the repeatability and comparability of evaluation are enhanced.

The invention discloses a pulveryte lithofacies identification method based on deep learning, and relates to the technical field of deep learning and sedimentary rock lithofacies identification, and the method comprises the steps: collecting lithofacies curve data and microstructure image data, screening feature parameters, and generating a standardized multi-modal feature set through an exclusive analysis engine; calling a specific model to perform hierarchical feature extraction on the microstructure image to obtain a deep microstructure feature vector; inputting the two types of features into an exclusive network, and outputting a preliminary recognition result through cross-modal attention weight distribution; and performing inversion correction and dynamic adjustment on the preliminary result by adopting a specific algorithm, and constructing a lithofacies classification system in combination with feedback information to complete accurate division. According to the method, through multi-source feature deep fusion, cross-modal correlation enhancement and multi-link collaborative optimization, efficient and accurate identification of the lithofacies of the pulveryte rock is realized, complex lithologic features are adapted, and support is provided for technical application in related fields.

The application discloses a fine-grained sedimentary rock facies identification method based on deep learning, relates to the technical field of deep learning and sedimentary rock facies identification, and comprises the following steps: collecting facies curve data and microstructure image data and screening characteristic parameters, generating a standardized multi-modal feature set through a special analysis engine; calling a specific model to perform hierarchical feature extraction on the microstructure image to obtain a deep microstructure feature vector; inputting the two types of features into a special network to output a preliminary identification result through cross-modal attention weight distribution; and adopting a specific algorithm to perform inversion correction and dynamic adjustment on the preliminary result, combining feedback information to construct a facies classification system to complete accurate division. Through multi-source feature deep fusion, cross-modal correlation enhancement and multi-link collaborative optimization, the application realizes efficient and accurate identification of fine-grained sedimentary rock facies, adapts to complex lithological characteristics, and provides support for technical application in related fields.

A method for evaluating geological hydrogen source rock in a region is provided. The method includes: collecting magnetic susceptibility data from a plurality of subsurface locations in the region; receiving geophysical survey data of the region, wherein the geophysical survey data comprises geophysical data collected from above ground; tying the magnetic susceptibility data of the plurality of subsurface locations to the geophysical survey data; generating a geologic map of igneous rock, metamorphic rock, or mafic mineral-or iron-rich sedimentary rock within the region based on the magnetic susceptibility data using a model; and determining, based on the geologic map, a target zone of the geological hydrogen source rock with a potential for hydrogen production or with the potential for hydrogen accumulation.

The invention provides an ancient coastal sand dam prediction method and device, equipment and a medium, and relates to the technical field of oil-gas exploration. Comprising the following steps: acquiring fluctuation data of an ancient landform in a region, wave mark parameters in sedimentary rock, sediment particle diameter and sediment density; according to the fluctuation data of the ancient landform, determining the gradient of the ancient landform of the region; determining the sedimentary paleo-water depth according to the wave mark parameter, the sediment particle diameter and the sediment density in the sedimentary rock; and the thickness of the ancient coastal sand dam is determined according to the paleo-terrain gradient and the sedimentary paleo-water depth. According to the method, the thickness of the paleo-coastal sand dam is determined by analyzing the paleo-terrain gradient and the sedimentary paleo-water depth in the area, the potential reservoir in the area is rapidly identified in the early stage of exploration, and a basis is provided for well drilling deployment.

The invention relates to the technical field of geology and sedimentary data analysis, in particular to a sedimentary rock particle analysis method and system based on an opencv visual library. The method comprises the following steps: firstly, acquiring a high-resolution digital image of a sedimentary rock sample, and preprocessing to enhance the characteristics of clastic particles; processing the image by using an opencv library, automatically identifying and segmenting a single debris particle, and calculating the equivalent diameter of the single debris particle; finally, an analysis report containing particle distribution and particle size statistical information is automatically generated. According to the method, image acquisition, processing, analysis and report generation are integrated into a continuous automatic process, a traditional manual microscope observation and manual measurement mode is replaced, the analysis efficiency is remarkably improved, and the method is suitable for large-scale sample processing. Recognition and measurement are executed through a standardized algorithm, subjective errors are effectively reduced, objectivity and consistency of analysis results are guaranteed, and an efficient and reliable technical means is provided for sedimentary rock granularity analysis.

The invention discloses high-pressure jet grouting pile equipment for a sedimentary rock pebble bed and a construction method of the high-pressure jet grouting pile equipment, and belongs to the field of foundation construction.The high-pressure jet grouting pile equipment comprises a crawler provided with a guide rail stand column and a mounting mechanism, a rotary chuck and a positioning mechanism are arranged on the guide rail stand column in a sliding mode, and a drill rod is detachably connected with a power head arranged on the rotary chuck; the positioning mechanism is used for limiting and driving a protective sleeve arranged on a drill rod in a sleeving mode, the protective sleeve is formed by sequentially connecting sleeve units end to end, the mounting mechanism is used for mounting the sleeve units to be mounted to be coaxial with the drill rod, the mounting mechanism comprises a base, a supporting frame and a hydraulic cylinder, and the base is arranged above the positioning mechanism; the lower end of the supporting frame is rotationally arranged on the base, the upper end of the supporting frame is used for temporarily fixing a sleeve unit to be installed, one end of the hydraulic cylinder is rotationally arranged on the base, and the other end of the hydraulic cylinder is rotationally connected with the supporting frame. When the sleeve units are installed, non-stop operation can be achieved, each sleeve unit limits the drill rod, and the perpendicularity of the drill rod is guaranteed.

This application provides an experimental method for testing the permeation efficiency of mixed sedimentary rock cores, including: cutting the mixed sedimentary rock core into thin sections for clay mineral analysis; weighing a standard core and recording the weight as m1; performing a displacement experiment on the standard core and saturating it with oil; immersing the standard core in oil and aging it in a constant temperature chamber, then weighing it and recording the weight as m2; measuring the T2 spectrum of the standard core at its spatial location and calculating the peak area S1; weighing the heat-shrink tubing and recording the weight as m0; wrapping the standard core circumferentially with heat-shrink tubing, placing it in a hanging ring and suspending it on an electronic balance, immersing it in the permeation fluid, and recording the weight data at permeation equilibrium as m3; measuring the T2 spectrum of the standard core at its spatial location and calculating the peak area S2; calculating the permeation efficiency based on the gravimetric method; calculating the permeation efficiency using the nuclear magnetic resonance peak areas before and after the permeation experiment; and calculating the permeation efficiency of the mixed sedimentary rock core. This method can accurately guide the effective development of mixed sedimentary rock reservoirs.

The invention relates to the technical field of geological evaluation, in particular to a stratified pulveryte core geology rapid experimental evaluation method which comprises the following steps: establishing a sample lithology characteristic table according to the color, mineral type and sedimentary structure of a stratified pulveryte core; determining a sampling layer section of the lithologic layer section of the lamina type pulveryte rock to be evaluated, and collecting and preparing a rock core sample; testing the collected rock core sample to obtain test data, wherein the test comprises slice identification, total rock X diffraction analysis, porosity determination and pyrolysis analysis experiment; the test data is extracted, homing comparison is carried out according to the test data and the sampling position, and core homing processing of the test data is achieved; and evaluating and analyzing the core potential of the lamina type pulveryte rock based on test data. According to the method, the rapid evaluation of the hydrocarbon source rock and the oiliness is realized, the sampling heterogeneity problem in the evaluation process is solved, and guidance is provided for the fine evaluation of the shale oil reservoir.

According to the method for measuring the true density of the coal rock, provided by the invention, different evolution stages experienced by the coal rock in a complex geological history can be efficiently and accurately identified. The stages cover the initial diagenesis to the later metamorphism, and each stage is accompanied by significant changes of physical and chemical properties of the coal rock. Besides, the method also has excellent distinguishing capability, the carbonaceous mudstone can be clearly and effectively distinguished from other types of coal rocks, and the carbonaceous mudstone is used as a special sedimentary rock, has complex components, often contains relatively high organic matters, and has significant difference from conventional coal rocks in multiple aspects. Therefore, the method not only contributes to deepening the understanding of the formation cause and the evolution process of the coal rock, but also provides important technical support and scientific basis for the fields of exploration and development of coal resources, environmental protection and the like.

The present application relates to the technical field of architectural decoration coatings, and particularly relates to a new type of sedimentary rock-imitating coating, a preparation method thereof and a construction process. The unique formula of the primer, the intermediate coating, the main paint and the topcoat can simulate the unique texture effect of the sedimentary rock more realistically through convenient construction operation, and the effect is controllable.

The invention relates to the technical field of mineral extraction, particularly discloses a method for efficiently extracting barite single mineral in black mudstone rich in organic matters, and solves the technical problems that micron-sized barite in black mudstone cannot be efficiently extracted in the prior art, lattice destruction / isotope fractionation of barite is easily caused in the extraction process, the purity and the recovery rate are low and the like. The purity of the extracted barite single mineral is larger than or equal to 99%, the recovery rate of fine-fraction barite is larger than or equal to 90%, crystal lattices are complete and free of damage, isotope fractionation and component change are avoided, and the high-precision geochemical test requirement can be met; meanwhile, the method is suitable for various sedimentary rocks such as marine / continental black mudstone, shale and siliceous mudstone, and the applicability is wide.

The application discloses a sample preparation method and a heterogeneity research method for a fine-grained heterogeneous sedimentary rock sample. The sample preparation method comprises the following steps: determining a reference surface direction according to the extension direction of the bedding plane of the fine-grained heterogeneous sedimentary rock sample, cutting and flattening the top surface and the bottom surface of the sample along the direction parallel to the reference surface direction, cutting the side surface of the sample along the direction perpendicular to the reference surface, so that the shapes of the cross sections of the sample parallel to the reference surface are consistent; cutting the sample into a first rock sample and a second rock sample along the direction perpendicular to the reference surface; obtaining an XRF scanning map of the cutting surface of the second rock sample, obtaining a sequence of segmentation lines arranged in an up-down order according to the data difference in the scanning map, and the segmentation lines being consistent with the direction of the bedding plane at the corresponding positions; and cutting the first rock sample according to the sequence of segmentation lines in sequence to obtain a plurality of rock samples. The rock samples prepared by the method are full in types, good in heterogeneity representation, and the rock samples are homogeneous bodies.

The invention discloses an agent, modified resin, system and method for removing heavy metal in sintering machine head ash washing wastewater, and relates to the technical field of wastewater treatment. Through the synergistic effect of sedimentary rock particles and an alkaline sulfide solution, the chemical adsorption capacity can be enhanced, the adsorption capacity to heavy metal ions is improved, the dispersing agent is beneficial to improving the dispersity of the sedimentary rock particles in the solution and preventing agglomeration, and therefore it is guaranteed that the sedimentary rock particles effectively participate in the reaction; and the flocculating agent promotes the generated precipitate and the particulate matters adsorbing the heavy metals to quickly flocculate and settle, so that the solid-liquid separation efficiency is improved. The reagent formula provided by the invention is obtained by optimizing the water quality characteristics (such as high-concentration suspended solids, thallium and lead) of the sintering machine head ash washing wastewater, realizes efficient and stable removal of heavy metals in the sintering machine head ash washing wastewater, meets the water inlet requirement of subsequent deep treatment, and has practical application value.

The invention discloses a post-stack seismic amplitude compensation method. The post-stack seismic amplitude compensation method comprises the following specific steps: S100, obtaining amplitude data of a geological marker interval from post-stack seismic data; s200, carrying out median filtering and normalization processing on the seismic amplitude data to obtain correction coefficient data; and S300, performing amplitude compensation based on the correction coefficient data. The geological marker bed in the step S100 is a rock stratum which has obvious characteristics and can be used as a stratigraphic contrast mark; the geological marker bed section refers to a stable sedimentary rock section, and mainly refers to a stable sedimentary mudstone section. According to the seismic amplitude compensation method, the correction coefficient data is obtained by performing median filtering and normalization processing on the amplitude data of the geological marker interval, so that amplitude compensation is realized, amplitude compensation of the interval to be corrected can be simply and efficiently realized, and the seismic amplitude compensation method is high in operability; amplitude compensation is achieved, the condition that the seismic amplitude corresponding to the geological marker interval is relatively uniform is considered, and the proportion of real stratum information in seismic attributes is increased.

The application provides a method for quantitatively characterizing three ancient main control factors of a lacustrine mixed sedimentary facies belt, which comprises the following steps: Step 1, mixed sedimentary rock type division is performed to identify the mixed sedimentary facies belt type; Step 2, ancient topography analysis is performed to establish a quantitative relationship template of the mixed sedimentary facies belt development and the ancient topography; Step 3, ancient climate analysis is performed to establish a quantitative relationship template of the mixed sedimentary facies belt development and the ancient climate; Step 4, ancient salinity analysis is performed to establish a quantitative relationship template of the mixed sedimentary facies belt development and the ancient salinity; and Step 5, a comprehensive quantitative characterization template of the three ancient main control factors of the mixed sedimentary facies belt is established. The method for quantitatively characterizing the three ancient main control factors of the lacustrine mixed sedimentary facies belt has a good effect on the analysis of the three ancient main control factors of the mixed sedimentary facies belt, and can provide technical guidance for the analysis of the control factors of the mixed sedimentary facies belt development and the research on the development law of the mixed sedimentary facies belt under the same sedimentary background.

The invention discloses a sedimentary rock sample nanoindentation test layering preprocessing method and system, and the method comprises the steps: after the preparation of a sedimentary rock sample is completed, carrying out local non-mean filtering to remove illumination interference, retaining the texture and color difference of the rock sample, separating image channels, extracting features to obtain multi-dimensional data, dividing image lines through k-means clustering, determining an original layer boundary, and then removing a pseudo layer; and then visual layering of the stratification line is completed. Through a coordinate resetting function, coordinate selection and pairing of the pricking points and the physical control points are completed, a two-dimensional affine model is constructed and solved, and a coordinate transformation relation is obtained and used for positioning an indentation measuring area. In order to correlate the colors of the images under the mirror and the macroscopic image, different types of images under the mirror are converted to 8-bit depth, corresponding adaptation is completed, foreground and background are segmented, adhesive particles are separated based on Euclidean distance transformation and a watershed method, qualified particles are obtained through filtering, physical property parameters are imported, and a sample visual image is obtained. And an accurate basis is provided for measuring point selection of the nanoindentation test.

This invention relates to a method and system for calculating pyrite content in sedimentary rocks considering their occurrence morphology, and pertains to the field of oil and gas reservoir logging evaluation technology. The method includes: Step 1: acquiring conventional logging data, core observation data, scanning electron microscopy data, micron-CT data, and core analysis data of the target formation; Step 2: calculating the pyrite resistivity response parameter PRR and the pyrite volume ratio conversion parameter V. PRYZ Step 3: Calculate the pyrite occurrence morphology index (PYI) and classify the pyrite occurrence morphology types according to the preset PYI threshold; Step 4: Establish a PYI prediction model; Step 5: Establish quantitative calculation models for pyrite content based on deep lateral resistivity; Step 6: Calculate the continuous pyrite content in the target formation. This invention can provide reliable technical support for resistivity correction, accurate calculation of oil saturation, and evaluation of reservoir sweet spots in pyrite-bearing reservoirs such as shale oil, and has significant application value and promotion prospects.

The present application relates to a kind of polyacrylamide modified reinforced geopolymer gel materials and its preparation method and use method, the gel material is mixed by geopolymer base material and polyacrylamide, and the polyacrylamide additive amount is 3.5% to 5% of the mass of geopolymer base material.The advantage of the present application is that geopolymer base material is fully mixed with the appropriate proportion of polyacrylamide, without arraying treatment, the flowability of the suitable adhesion capacity can be obtained, which can be immediately mixed and stirred with sedimentary rock aggregate, which can not only uniformly cover aggregate, but also adhere to the surface of aggregate without sinking, and then directly coated and maintained for more than 144h to obtain reinforced aggregate, compared with the aggregate obtained by mixing aggregate with geopolymer base material without adding polyacrylamide and increasing adhesion capacity by arraying, the compressive strength can be increased by 3.1% to 8.2%, and the bending tensile strength can be increased by 44.4% to 61.1%.

The invention belongs to the technical field of sedimentology and artificial intelligence crossing, and particularly relates to a sediment source tracking method based on multi-dimensional morphological characteristics of heavy minerals. According to the method, a'high roundness-fresh fracture 'combined judgment mechanism is established, the key geological evidence of'a fresh fracture surface overlapped on the surface of highly rounded particles' is accurately captured through a double-headed neural network, a standard geological fingerprint logic library is established, and the neural network is combined to train standardized'multi-cycle 'heavy mineral characteristics, so that the high roundness-fresh fracture is obtained. Therefore, under the condition of not depending on expensive geochemical testing, the extraction depth of the mineral morphological characteristics is improved, the ancient sedimentary rock re-cycle component and the far-source direct carrying component are effectively distinguished, the sedimentary dynamics quantitative material source tracking based on the population statistics law is realized, and the method is suitable for mass production. And a more objective, macroscopic and repeatable quantitative data support is provided for basin analysis, paleogeography reconstruction and oil and gas reservoir prediction.

The present application provides a kind of low exploration degree area mud shale organic matter abundance prediction method, comprising: step 1: determine the distribution of each strata layer system and sedimentary center;Step 2: carry out sedimentary facies, element and organic matter abundance related geochemical analysis test;Step 3: establish the change model of different sample points deposition rate;Step 4: establish the change model of each sample point paleo-productivity;Step 5: evaluate the change model of each sample point redox degree;Step 6: establish the correlation model of each sedimentary environment index and organic matter abundance;Step 7: establish the quantitative prediction model of the applicable multi-element organic matter abundance of the study area;Step 8: predict the planar distribution of organic matter abundance.The low exploration degree area mud shale organic matter abundance prediction method improves the precision of mud shale quality prediction, and lays a solid theoretical basis for continental lacustrine basin hydrocarbon source rock evaluation, oil and gas distribution rule and shale oil and gas exploration and development.

The application discloses a kind of complex fine-grained sedimentary rock reservoir evaluation method, which comprises the following steps: step 1: the reservoir to be studied as target reservoir;Step 2: target reservoir is stratified according to lithology category and thickness;Step 3: gas-bearing property in target reservoir is analyzed, and favorable stratigraphic system is preliminarily selected according to gas-bearing property characteristics;Step 4: favorable stratigraphic system, carry out stratigraphic system development scale characterization, stratigraphic system reservoir property characterization, organic matter abundance characterization and gas-bearing property characterization analysis, according to reservoir evaluation parameter and the weight corresponding to each parameter and determine the gas-bearing property evaluation index REI value of the stratigraphic system type;Step 5: according to the type of target reservoir, establish the evaluation system of complex fine-grained sedimentary rock reservoir.The application considers the heterogeneity of fine-grained sedimentary rock reservoir internal structure, and proposes a reasonable reservoir property evaluation parameter calculation method.

The present application belongs to the technical field of the cross of sedimentology and artificial intelligence, and particularly relates to a sediment source tracking method based on multi-dimensional morphological characteristics of heavy minerals. The present application establishes a "high roundness-fresh fracture" combined discrimination mechanism, accurately captures the key geological evidence of "highly round particle surface superimposed fresh fracture surface" through a double-head neural network, establishes a standard geological fingerprint logic library, and combines neural network training standardization "multi-cycle" heavy mineral characteristics, so as to improve the extraction depth of mineral morphological characteristics without relying on expensive geochemical tests, effectively distinguish the old sedimentary rock re-circulation components and the far-source direct transport components, realize the quantitative source tracking of sediment dynamics based on the population statistical law, and provide more objective, macroscopic and repeatable quantitative data support for basin analysis, paleogeographic reconstruction and oil and gas reservoir prediction.

The present application provides a complex lithology mixtite reservoir sweet spot comprehensive evaluation method based on logging combination, comprising the following steps, S1: collecting various data of the block; S2: using logging while drilling and gas logging to establish a mixtite reservoir effectiveness evaluation index E; S3: using logging while drilling capture spectroscopy to establish a variable mineral weight mixtite reservoir compressibility index BRIT; S4: using logging while drilling capture spectroscopy to establish a variable mineral weight acidification index ACID. Through the mixtite reservoir effectiveness evaluation index E, the variable mineral weight compressibility index BRIT and the acidification index ACID, the mixtite reservoir geology and engineering sweet spot can be effectively found, which provides a basis for exploration stage testing and sampling, oilfield development stage perforation scheme formulation and later measures. The present application has wide application range, strong effectiveness and high prediction accuracy, has important guiding significance for exploration and development, and can also be appropriately popularized to other types of reservoirs.

The invention provides an ancient environment quantitative reconstruction system and method based on a multi-output neural network. The system comprises a training data set construction module, a sedimentary rock core data set construction module, a data integration and preprocessing module, a multi-output neural network model construction and training module, a model cross validation module, a model interpretability analysis module and an ancient environment quantitative reconstruction module. According to the system disclosed by the invention, modern biological-environmental data are collected, water environment indexes are measured at the same time, and a sedimentary rock core is adopted for an environment which needs to be subjected to quantitative environment reconstruction for sample separation and dating; according to the method, biocenosis composition and water environment indexes obtained in surface sediments are preprocessed, then multi-output neural network model training is carried out, and SHAP interpretability analysis is carried out. And then inputting biocenosis data of a time sequence in the sedimentary rock core into the trained model, and outputting a result of environment quantitative reconstruction.

This invention provides a method for determining the lithology of silty-fine sandy tuff based on quartz crystallinity, belonging to the field of sedimentary rock petrological analysis technology. This invention obtains two quantitative indicators—quartz crystallinity index and clay mineral content—of the sample using X-ray diffraction technology, establishing clear quantitative discrimination criteria. This enables quantitative and precise lithological discrimination between tuff and clastic silty-fine sandstone, improving the objectivity and reliability of the results. Simultaneously, it achieves high efficiency and convenience in the discrimination method. The standardized XRD testing procedure shortens the lithological identification cycle, allowing lithological discrimination to be completed using only a single testing method, reducing over-reliance on the professional skills of operators. It is suitable for batch identification of silty-fine sandy tuff at the core scale.