A machine learning-based remaining oil prediction method

Abstract

The present application relates to the technical field of petroleum engineering, in particular to a remaining oil prediction method based on machine learning; comprising the steps of multi-source heterogeneous data acquisition, data processing, multi-modal fusion machine learning model construction, topographic and geomorphic influence evaluation, oil sampling and detection, prediction corroboration based on oil data, dynamic feedback data acquisition, model dynamic adjustment and iteration, etc. Through multi-source heterogeneous data acquisition, multi-modal fusion machine learning model and multi-dimensional influence evaluation of topography and geomorphology, the present application realizes accurate prediction of remaining oil and comprehensive control of environmental risks, which is conducive to optimizing mining schemes and reducing environmental damage. It can not only accurately determine the collectable amount of remaining oil and improve the recovery rate, but also accurately evaluate the influence of mining on topography, ecology and hydrology, and reduce environmental problems.

Description

Technical Field

[0001] The present invention relates to the field of petroleum engineering technology, and in particular to a remaining oil prediction method based on machine learning. Background Art

[0002] In the oil extraction industry, remaining oil prediction is one of the core links, and its results are directly related to the formulation of extraction plans, resource utilization efficiency and the impact on the surrounding environment.

[0003] Traditional remaining oil prediction methods are primarily based on simple geological models and statistical analysis. Early estimates relied on static reservoir data, such as reservoir thickness, porosity, and permeability. Because this approach fails to fully account for reservoir complexity, its prediction accuracy is low, typically around 60-70%. For example, in reservoirs with complex geological structures and strong heterogeneity, relying solely on these static data is far from accurate enough to reflect the true distribution of remaining oil. Furthermore, oil production is a dynamic process, with pressure, temperature, and fluid properties within the reservoir changing during production. Traditional methods struggle to incorporate these dynamic changes into the prediction system.

[0004] With technological advancements, computer simulation technology is used to predict remaining oil. By establishing a numerical simulation model of the reservoir, factors such as fluid flow and reservoir heterogeneity are taken into account to a certain extent. However, this method has obvious shortcomings. On the one hand, it requires a large amount of computing resources and precise input parameters. On the other hand, the accuracy of its model is heavily dependent on idealized assumptions about the reservoir geology and production process. More importantly, for oil fields located in areas with complex terrain and landforms, production activities may cause damage to the surrounding terrain, groundwater and ecosystems. Traditional prediction methods can rarely fully assess these impacts, making it difficult to avoid environmental risks while ensuring production volume.

[0005] In summary, the existing remaining oil prediction technology has many limitations in terms of accuracy, comprehensive consideration of factors, data utilization efficiency and data security management. A new and comprehensive remaining oil prediction method is urgently needed to solve these problems. Summary of the Invention

[0006] In order to make up for the shortcomings of the existing technology, the present invention provides a remaining oil prediction method based on machine learning to overcome the shortcomings of the existing technology. The technical solution adopted by the present invention to solve the technical problem is:

[0007] A method for predicting remaining oil based on machine learning includes the following steps:

[0008] The steps include:

[0009] S1: Multi-source heterogeneous data acquisition: This involves collecting multi-source heterogeneous data covering oilfield geology, production history, reservoir characteristics, and surrounding topography. Geological data includes the three-dimensional structure and microscopic pore structure of oil reservoirs; production history data covers production methods and oil production volumes; reservoir characteristics include crude oil and formation water chemical parameters; and topography data includes high-resolution remote sensing and geographic information system (GIS) multi-layer data.

[0010] S2: Data preprocessing: All data collected in S1 are cleaned, normalized, and dimensionally reduced to reduce impurities, unify scale and complexity, and make the data meet the requirements of subsequent processing;

[0011] S3: Multimodal feature extraction: Use deep learning methods to extract features from the data collected in S1; for example, use convolutional neural networks to extract texture and structural features from geological image data, and use recurrent neural networks to extract time-dependent features from historical mining spatiotemporal series data;

[0012] S4: Multimodal Fusion Machine Learning Model Construction: Build a model that integrates multiple machine learning algorithms, including attention-based neural networks, graph convolutional neural networks, and long short-term memory networks. Through a specific fusion mechanism, the different modal features in S3 are integrated for subsequent prediction and evaluation.

[0013] S5: Initial remaining oil prediction: The initial data after preprocessing in S2 and feature extraction in S3 are input into the model in S4, and the predicted value of the remaining oil that can be collected is output;

[0014] S6: Topography and geomorphic impact assessment: Evaluate the impact of mining on topography and geomorphology from multiple dimensions, including topographic stability, ecosystem damage risk, and groundwater hydrological change risk, and analyze the potential impact of mining on the surrounding environment;

[0015] S7: Oil sampling and testing: During the mining process, the collected oil is sampled at irregular intervals to test the physical and chemical properties of the oil;

[0016] S8: Prediction support based on oil product data: Integrate the oil product sampling and testing data in S6 into the model in S4, and verify and optimize the remaining oil prediction results from the perspective of the correlation between the changing trends of oil product characteristics and the model prediction results;

[0017] S9: Dynamic feedback data collection: Use IoT sensors to collect multi-dimensional data in real time at the mining site to provide a basis for model iteration;

[0018] S10: Dynamic model adjustment and iteration: Based on the incremental learning algorithm, the model is dynamically adjusted and retrained according to newly collected real-time data, while optimizing the learning rate and using model compression technology to improve model performance.

[0019] Furthermore, the collection of geological data described in S1 includes:

[0020] 3D geological exploration data, using high-precision seismic exploration technology, can obtain 3D spatial distribution information of underground oil layers with sub-meter resolution, including detailed parameters of oil layer boundaries, fault locations, rock layer thickness and geometry, to fully describe the structural characteristics of the oil layer;

[0021] Microscopic pore structure image data uses high-resolution electron microscopy combined with micro-CT scanning technology to obtain detailed information on the pores of reservoir rocks at the microscale, including the size range, average size, shape classification (such as spherical, elliptical, irregular), degree of connectivity (measured by the ratio of the number of connected pores to the total number of pores), and the distribution of mineral components on the pore surface and inside, providing a basis for analyzing the oil flow mechanism.

[0022] Furthermore, the dimensionality reduction process in S2 includes the following:

[0023] The three-dimensional geological exploration data and microscopic pore structure image data are subjected to dimensionality reduction processing using a method combining principal component analysis (PCA) and local linear embedding (LLE); PCA is first used to remove linear correlations in the data, and then LLE is used to maintain the local geometric structure of the data, thereby reducing the data dimension while retaining key geological and pore characteristic information;

[0024] The historical spatiotemporal sequence data of mining is subjected to dimensionality reduction processing through wavelet transform, the data is decomposed into wavelet coefficients of different frequencies, and the coefficients corresponding to the frequency components that are important for remaining oil prediction are selected, thereby reducing the data dimension and highlighting the key time series characteristics;

[0025] The multi-layered geographic information system (GIS) data and high-resolution remote sensing data of topography and landforms are subjected to dimensionality reduction processing using a feature selection algorithm, such as the ReliefF algorithm, to evaluate the importance of each geographic feature for remaining oil prediction and topography and landform impact assessment, remove unimportant feature dimensions, and retain key features such as terrain elevation, slope, aspect, and land use type.

[0026] Furthermore, feature extraction in S3 includes feature extraction of historical spatiotemporal series data using the following method:

[0027] Using a recurrent neural network (RNN), we introduce a temporal attention mechanism and combine it with a gating mechanism to extract features. By setting update gates, forget gates, and output gates, we control the transmission and updating of information in the time series, enabling the model to better capture the long-term dependencies and dynamic changes of data at different stages of the mining process.

[0028] Divide the data at different time scales and perform multi-scale feature extraction on spatiotemporal series data. For example, aggregate data by different time intervals such as days, weeks, and months, then extract features separately. These multi-scale features are then fused to obtain more comprehensive time series features and improve the model's ability to understand complex change patterns in historical mining data.

[0029] Furthermore, the multimodal fusion machine learning model in S4 is constructed, and the attention weight of each modal feature is calculated through a multi-head attention mechanism. The attention calculation path of multiple heads is set, and each head focuses on a different feature subspace. The results of multiple heads are then spliced ​​together to further enrich and refine the calculation of attention weights, enabling the model to more comprehensively capture the complex interactive relationships between different modal features.

[0030] The contribution of different modal features is adjusted through a dynamic weight update strategy; according to the error feedback and data changes during model training, the update step and direction of the attention weight are adjusted in real time to ensure that the model can quickly adapt to new data patterns and changes, thereby improving the accuracy and stability of fusion.

[0031] Furthermore, during the initial remaining oil prediction in S5 and the topography and geomorphology impact assessment in S6, the model construction for ecosystem damage risk assessment includes:

[0032] Based on vegetation indices (such as NDVI) and land cover type data, a vegetation coverage and vegetation health assessment model was constructed. By analyzing the spatiotemporal variations of vegetation indices in high-resolution remote sensing data and combining them with information on land use types (such as farmland, forest, grassland, etc.), the direct damage and potential impacts of mining activities on vegetation were assessed.

[0033] Using multi-parameter reservoir geochemical data and soil type data, a soil pollution diffusion model was developed. This model considers the migration and transformation patterns of harmful substances in crude oil (such as heavy metals and organic pollutants) in different soil types, and predicts the scope and extent of soil pollution that may result from mining, as well as the impact on surrounding vegetation growth and ecosystem function.

[0034] Indicators such as vegetation coverage, vegetation health, and soil pollution level are input into the comprehensive ecological risk assessment model, and the risk level of damage to the surrounding ecosystem caused by mining activities is determined through multi-criteria decision-making methods such as hierarchical analysis method or fuzzy comprehensive evaluation method.

[0035] Furthermore, the sampling point selection criteria for the oil sampling test in S7 include:

[0036] According to the geological structure of the oil reservoir and the distribution of production wells, sampling points are set at the production wellheads of different oil layers to ensure that the oil products produced in oil layers of different depths are covered to reflect the differences in crude oil characteristics in different areas within the oil reservoir;

[0037] Sampling points are set up at key nodes of the gathering and transportation pipelines, such as the convergence point of the oil pipelines from different oil wells, and before and after the oil-water separation equipment, to detect changes in the properties of oil products during transportation and preliminary treatment, as well as the characteristics of oil products from different wells after mixing;

[0038] Taking into account the dynamic factors in the mining process, such as the progress of the mining stage, the position of the sampling point should be adjusted in time according to the changes in reservoir pressure, the effects of water and gas injection, etc., to ensure that the sampled oil can accurately represent the characteristics of the remaining oil under the current mining status.

[0039] Furthermore, the specific method of correlation analysis based on prediction evidence of oil product data described in S8 includes:

[0040] Use correlation analysis methods to identify oil parameters that have a significant linear relationship with remaining oil reserves, such as density and water content, and determine the direction and strength of the correlation;

[0041] For nonlinear correlations, data mining technology and machine learning algorithms are used to explore the complex nonlinear mapping relationship between oil parameters and the amount of remaining oil that can be collected, providing a more accurate basis for model prediction;

[0042] By combining a variety of data analysis methods, a comprehensive analysis of multiple oil parameters is conducted to find the comprehensive characteristics of the oil that can best explain the changes in residual oil.

[0043] Furthermore, the model compression technology in S10 includes:

[0044] Network pruning technology, during the model retraining process, removes neurons and connections that have little impact on the model's prediction results based on the importance evaluation indicators of neurons and connections, thereby reducing the model's complexity and computational complexity.

[0045] Quantization technology converts the weights and activation values ​​in the model from high-precision data representation to low-precision representation. While ensuring that the loss of model accuracy is within an acceptable range, it greatly reduces the resources required for model storage and calculation, and improves the operating efficiency of the model on edge computing devices.

[0046] The beneficial effects of the present invention are as follows:

[0047] 1. The present invention discloses a method for predicting remaining oil based on machine learning. By collecting multi-source heterogeneous data and integrating a multimodal fusion machine learning model, the method improves the accuracy of remaining oil prediction, provides accurate guidance for optimizing mining plans, avoids over- or under-mining, more accurately determines the recoverable amount of remaining oil, reduces resource waste or increased mining costs due to inaccurate predictions, improves recovery rates, and effectively utilizes petroleum resources.

[0048] 2. The machine learning-based remaining oil prediction method described in the present invention achieves comprehensive environmental risk control through multi-dimensional impact assessment of topography and landforms. It can plan environmental protection measures before mining to reduce damage to the surrounding ecology, and accurately assess terrain stability, ecosystem damage risks and groundwater changes. It can reduce landslides, soil pollution, vegetation destruction and other problems caused by mining, and achieve coordinated development of oil extraction and environmental protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The present invention will be further described below with reference to the accompanying drawings.

[0050] Figure 1 It is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0051] In order to make the technical means, creative features, objectives and effects achieved by the present invention easier to understand, the present invention is further described below in conjunction with specific implementation methods.

[0052] like Figure 1 As shown, the present invention proposes a remaining oil prediction method based on machine learning, which includes the following:

[0053] Multi-source heterogeneous data acquisition: Multi-source heterogeneous data covering oilfield geology, production history, reservoir characteristics, and surrounding topography are collected from various channels. Among them, geological data includes the three-dimensional structure and microscopic pore structure data of the oil layer; production history data covers information such as production methods and oil production volume; reservoir characteristic data includes crude oil and formation water chemical parameters; topography data includes high-resolution remote sensing and geographic information system (GIS) multi-layer data.

[0054] Data preprocessing: All collected data are cleaned, normalized, and dimensionally reduced to reduce impurities, unify scale and complexity, and make the data meet the requirements of subsequent processing; let the original data be x, and its minimum value be x min , the maximum value is x max , the normalized formula is For dimensionality reduction, a method combining principal component analysis (PCA) and local linear embedding (LLE) is used for geological exploration three-dimensional data and microscopic pore structure image data. PCA is first used to remove linear correlation in the data. The covariance matrix of the original data is set as ∑. The principal components are obtained by solving the characteristic equation |λI-∑|=0, where λ is the eigenvalue and I is the unit matrix. LLE is then used to maintain the local geometric structure of the data. For the mining history spatiotemporal series data, wavelet transform is used for dimensionality reduction. The wavelet function is set as ψ(t) and the scaling function is The discrete wavelet transform formula is m and n are scale and translation parameters, a0 and b0 are constants, and x(t) is the historical spatiotemporal series data of mining. For geographic information system (GIS) multi-layer data and high-resolution remote sensing data of topography and landforms, based on feature selection algorithms such as the ReliefF algorithm, the importance of each geographical feature for remaining oil prediction and topography and landform impact assessment is evaluated, and unimportant feature dimensions are removed while retaining key features such as terrain elevation, slope, aspect, and land use type.

[0055] Multimodal feature extraction: For different types of data, specific deep learning methods are used to extract features; for example, convolutional neural networks are used to extract texture and structural features from geological image data, and recursive neural networks are used to extract time-dependent features from mining history spatiotemporal series data. In convolutional neural networks, the input data is x ij , i and j represent the position index of the data in the image, and the convolution kernel is k rs , r and s represent the position index of the convolution kernel element, the convolution kernel size is a×b, then the feature map y pq The calculation is done through convolution operation

[0056] Modal fusion machine learning model construction: Build a model that integrates multiple machine learning algorithms, including neural networks based on attention mechanisms, graph convolutional neural networks, long short-term memory networks, etc., and integrate different modal features through a specific fusion mechanism for subsequent prediction and evaluation; use a multi-head attention mechanism when calculating attention weights, assuming that the query matrix is ​​Q, the key matrix is ​​K, the value matrix is ​​V, and the dimension of the key is d k , the attention weight calculation formula is MultiHead(Q, K, V) = Concat(head1, ..., head h )W O , where h is the number of heads, W O is the output weight matrix, head i Represents the attention calculation result of the i-th head; Q, K, and V are obtained by linear transformation of different modal features and are used to measure the correlation between different modal features; in the process of adjusting the contribution of different modal features, a dynamic weight update strategy is introduced. According to the error feedback and data changes during the model training process, the update step and direction of the attention weight are adjusted in real time to ensure that the model can quickly adapt to new data patterns and changes, thereby improving the accuracy and stability of fusion.

[0057] Initial remaining oil prediction: Input the initial data after preprocessing and feature extraction into the model and output the predicted value Q of the remaining oil that can be collected predicted ; Let the input data be X, and the prediction model can be expressed as Q predicted=f(X), where f is a mapping function constructed based on multiple machine learning algorithms, which is used to map the input data features to the predicted value of the remaining oil that can be collected.

[0058] Topography and geomorphic impact assessment: The impact of mining on topography and geomorphology is assessed from multiple dimensions, including terrain stability, ecosystem damage risk, and groundwater hydrological change risk, and the potential impact of mining on the surrounding environment is analyzed. In the terrain stability assessment, stress σ and strain ∈ are calculated through finite element analysis, and the stability index S is calculated based on the specific function S = g(σ, ∈), where g is a function determined based on geomechanics principles and experience, and is used to measure the stability of the terrain under the action of mining stress.

[0059] Oil sampling and testing: The collected oil is sampled at key locations and time points during the extraction process. Scientific sampling methods and advanced testing equipment are used to test multiple physical and chemical properties of the oil. Let a physical or chemical property parameter of the oil be P, and its measured value is obtained using the corresponding instrument according to the standard measurement method. For example, the density of the oil is measured by a densitometer, and the chemical composition is measured by instruments such as gas chromatography-mass spectrometry (GC-MS).

[0060] Prediction support based on oil product data: Incorporating oil product sampling test data into the model, the remaining oil prediction results are supported and optimized from the perspective of the correlation between the oil product characteristic change trend and the model prediction results, including trend analysis, correlation analysis and anomaly detection; in the correlation analysis, let the oil product parameter be x i , i=1,2,…,n, its mean is The remaining oil that can be collected is y i , whose mean is By calculating the Pearson correlation coefficient Linear correlations were analyzed, and the linear relationship between oil parameters and the amount of remaining oil that could be recovered was determined based on the size and sign of the correlation coefficient. For nonlinear correlations, a support vector machine regression (SVR) algorithm was used, with oil data as input and the amount of remaining oil that could be recovered as output. By training the SVR model, the complex nonlinear mapping relationship between oil parameters and remaining oil reserves was explored, providing a more accurate basis for model prediction. In addition, principal component analysis (PCA) and canonical correlation analysis (CCA) methods were combined to conduct a comprehensive analysis of multiple oil parameters. The principal components of the oil data were extracted through PCA, and then the correlation between the principal components and the amount of remaining oil that could be recovered was analyzed using CCA to identify the comprehensive characteristics of the oil that can best explain the changes in remaining oil.

[0061] Dynamic feedback data collection: IoT sensors are used to collect multi-dimensional data in real time at the mining site to provide a basis for model iteration; the data collected by the downhole pressure sensor is set to P(t), where t is time. P(t) represents the pressure value measured by the downhole pressure sensor at time t, and its value range is determined according to the actual downhole pressure situation; the data collected by the temperature sensor is T(t), which represents the temperature value measured by the temperature sensor at time t, and its value range is determined according to the actual downhole temperature situation, as well as data collected by other types of sensors, such as flow data collected by flow sensors.

[0062] Dynamic adjustment and iteration of the model: Based on the incremental learning algorithm, the model is dynamically adjusted and retrained according to the newly collected real-time data, while optimizing the learning rate and using model compression technology to improve model performance; assuming the original learning rate is η old , the error change is ΔE, and the learning rate adjustment formula is η new =η old ×h(ΔE), where h is an adjustment function determined based on model training experience and data variation characteristics, used to adjust the learning rate according to the error variation; in terms of model compression technology, it includes network pruning technology and quantization technology; in network pruning technology, let the activation value of neuron i be a i , with weight w ij (j represents the index of other neurons connected to neuron i), and according to a certain threshold θ, (θ is determined according to the model structure and training data, and is used to measure the importance of neurons or connections to the model prediction results), it is determined whether to prune, and neurons and connections that have little impact on the model prediction results are removed to reduce the complexity and computational complexity of the model; in the quantization technology, the quantization function is set as (s is the quantization step size, determined according to the data type and accuracy requirements of the model parameters), the weights and activation values ​​in the model are converted from high-precision data representations (such as 32-bit floating-point numbers) to low-precision representations (such as 8-bit integers). While ensuring that the loss of model accuracy is within an acceptable range, the resources required for model storage and calculation are greatly reduced, thereby improving the operating efficiency of the model on edge computing devices.

[0063] As a specific embodiment of the present invention, the collection of geological data includes:

[0064] For geological exploration three-dimensional data, high-precision seismic exploration technology is used to obtain three-dimensional spatial distribution information of underground oil layers with sub-meter resolution, including detailed parameters such as oil layer boundaries, fault locations, rock layer thickness and geometric shapes, so as to fully describe the structural characteristics of the oil layer; assuming that the coordinate ranges of the oil layer in the x, y, and z directions are [x min , x max ]、[y min ,y max ]、[zmin , z max ], then the oil layer volume This integral is used to calculate the volume of the oil layer in three-dimensional space, providing basic data for related analyses such as reservoir reserve estimation, where dx, dy, and dz represent small length increments in the x, y, and z directions.

[0065] For the microscopic pore structure image data, high-resolution electron microscopy combined with micro-CT scanning technology is used to obtain detailed information on the pores of reservoir rocks at the microscopic scale, including the size range, average size, shape classification (such as spherical, elliptical, irregular), degree of connectivity (measured by the ratio of the number of connected pores to the total number of pores), and the distribution of mineral components on the pore surface and inside. Assume that the number of connected pores is n c , the total number of pores is n t , degree of connectivity This ratio is used to describe the degree of interconnectivity between pores and is of great significance for analyzing the flow characteristics of oil in rocks.

[0066] As a specific embodiment of the present invention, the specific method of dimensionality reduction processing in the data preprocessing step is:

[0067] For geological exploration three-dimensional data and microscopic pore structure image data, a method combining principal component analysis (PCA) and local linear embedding (LLE) is used. PCA is first used to remove linear correlation in the data. The original data covariance matrix ∑ is a matrix composed of the covariance between data vectors, and its elements σ ij Represents the covariance of the i-th and j-th data vectors, and obtains the principal components by solving the characteristic equation |λI-∑|=0 (λ is the eigenvalue, I is the unit matrix, and the unit matrix is ​​a square matrix with the main diagonal elements being 1 and the remaining elements being 0). These principal components are the projections of the original data onto the new linearly independent dimensions. Then, LLE is used to maintain the local geometric structure of the data, retaining key geological and pore characteristic information while reducing the data dimension. LLE maintains the local geometric structure of the data by finding the local linear relationship of each data point, so that the reduced-dimensional data has a similar structure to the original data locally.

[0068] For the historical spatiotemporal series data of mining, wavelet transform is used to reduce the dimension. By decomposing the data into wavelet coefficients of different frequencies, the coefficients corresponding to the frequency components that are important for the prediction of remaining oil are selected, thereby reducing the data dimension and highlighting the key time series characteristics. The wavelet function ψ(t) is a function with localization characteristics, which has good localization performance in both the time domain and the frequency domain. The scaling function Used to generate wavelet basis, discrete wavelet transform formula In the formula, m and n control the scale and position of the wavelet respectively, a0 and b0 are constants, and x(t) is the mining historical spatiotemporal series data. By changing m and n, wavelet coefficients of different scales and positions can be obtained, thereby achieving data decomposition and dimensionality reduction.

[0069] For geographic information system (GIS) multi-layer data and high-resolution remote sensing data of topography and landforms, feature selection algorithms, such as the ReliefF algorithm, are used to evaluate the importance of each geographic feature for remaining oil prediction and topography and landform impact assessment, remove unimportant feature dimensions, and retain key features such as terrain elevation, slope, aspect, and land use type. The ReliefF algorithm evaluates the importance of features by calculating the ability of each feature to distinguish sample classifications (which can be understood here as different categories of remaining oil prediction and topography and landform impact assessment). Features with strong distinguishing abilities are retained, while features with weak distinguishing abilities are considered to contribute less to prediction and assessment and are removed.

[0070] As a specific embodiment of the present invention, feature extraction optimization for mining historical spatiotemporal series data includes:

[0071] When using recurrent neural network (RNN) to extract features, in addition to introducing the time attention mechanism, it also combines the gating mechanism; by setting the update gate zt and the forget gate r t and output gate o t , controls the transmission and update of information in the time series, so that the model can better capture the long-term dependencies and dynamic change characteristics of data at different stages in the mining process; let the current moment be t, and the hidden state at the previous moment be h t-1 , the current input is x t , the weight matrices are W z , W r , W h , the bias vectors are b z , b r , b h , the activation function is σ (σ can be a common sigmoid function, used to map the input to the (0, 1) interval), and the nonlinear function is (For example, it can be the hyperbolic tangent function tanh), the calculation formula is z t =σ(W z [h t-1 , x t ]+b z ), r t =σ(W r [h t-1 , x t ]+b r ), Where ⊙ represents element-wise multiplication; update gate z tDetermines the proportion of new input information in the current state update, the forget gate r t Determines how much past information to forget, output gate o t This mechanism can better capture the long-term dependencies and dynamic change characteristics of data at different stages of the mining process.

[0072] Perform multi-scale feature extraction on spatiotemporal series data; divide the data at different time scales, such as aggregating data by different time intervals such as days, weeks, and months, and then extract features separately. These multi-scale features are then fused to obtain more comprehensive time series features and improve the model's ability to understand complex change patterns in historical mining data. When aggregating data at different time scales, group the data according to time intervals. For example, daily aggregation treats the data for each day as a group, and then extracts features from each group of data. The features extracted at these different scales contain information at different time granularities, which can more comprehensively describe the change pattern of historical mining data after fusion.

[0073] As a specific embodiment of the present invention, in the construction of a multimodal fusion machine learning model, the details of the fusion method based on the attention mechanism are as follows:

[0074] A multi-head attention mechanism is used to calculate the attention weight for each modal feature. By setting up multiple attention calculation paths, each head focuses on a different feature subspace. The results from these multiple heads are then concatenated to further enrich and refine the attention weight calculation, enabling the model to more comprehensively capture the complex interactions between different modal features. Each head performs attention calculations independently, and the number of heads, h, is determined based on model complexity and data diversity. In a multimodal fusion scenario, different modal features (such as geological features, mining history features, and topographic features) undergo linear transformations to obtain their own Q, K, and V matrices. The dimensions and element values ​​of these matrices are determined by the dimensions of the modal features and the data content. For example, for a geological feature modality, each row vector of the Q matrix represents the query information of the geological feature on other modal features in a certain dimension, while the column vectors of the K matrix are the key values ​​used to match the query information. The attention weights calculated reflect the correlation between different modalities in that subspace.

[0075] In the process of adjusting the contribution of different modal features, a dynamic weight update strategy is introduced. According to the error feedback and data changes during model training, the update step size and direction of the attention weight are adjusted in real time; let the error feedback information be ΔE t (t represents the number of training rounds), the data change is represented by the difference ΔD between the newly collected data and the historical data; the update step size α and direction According to ΔE tand ΔD are determined by the following formula: α=g(ΔE t , ΔD), (g and h are functions designed based on model characteristics and training experience) to ensure the model can quickly adapt to new data patterns and changes, improving the accuracy and stability of fusion. This dynamic update mechanism enables the model to more accurately adjust the importance of different modal features in the fusion process when faced with complex and changing data during reservoir development (such as data changes caused by geological structure changes and production process adjustments).

[0076] As a specific embodiment of the present invention, the model construction for ecosystem damage risk assessment in the initial remaining oil prediction and topographic impact assessment includes:

[0077] Based on vegetation index (such as NDVI) and land cover type data, a vegetation coverage and vegetation health assessment model is constructed; by analyzing the spatiotemporal changes of vegetation index in high-resolution remote sensing data and combining it with information on land use types (such as farmland, forest, grassland, etc.), the direct damage degree and potential impact of mining activities on vegetation are assessed; NDVI is set i is the vegetation index of the i-th pixel, which is calculated through remote sensing data and generally ranges from [-1, 1]. Positive values ​​indicate vegetation coverage, and the larger the value, the denser and healthier the vegetation. (V is the vegetation pixel set, N V The vegetation coverage is obtained by calculating the ratio of the sum of the NDVI of all vegetation pixels in the area to the total number of vegetation pixels. This indicator directly reflects the coverage of vegetation in the area. In addition to coverage, the time series changes of the vegetation index can also be combined to assess the health of vegetation. For example, a continuous decline in the vegetation index may indicate that the vegetation is under stress or damage.

[0078] A soil pollution diffusion model was established using reservoir geochemical multi-parameter data and soil type data. The migration and transformation patterns of harmful substances in crude oil (such as heavy metals and organic pollutants) in different soil types were considered to predict the scope and extent of soil pollution that may result from mining, as well as its impact on surrounding vegetation growth and ecosystem function. The concentration of pollutants in the soil, C(x, y, t), was assumed to satisfy the diffusion equation: (D diffusion coefficient, its value depends on the physical properties of the soil (such as porosity, permeability, etc.) and the nature of the pollutant, v x 、v yis the velocity component, whose direction and magnitude are related to factors such as soil slope, groundwater flow direction and velocity. R is the reaction term, which represents the rate of chemical reaction generation or consumption of pollutants in the soil and is related to the chemical properties of the soil (such as pH, redox potential, etc.) and the type of pollutants. The soil type and initial pollutant concentration are determined by sampling and analyzing the soil around the oil reservoir, and D and v are determined by combining information such as topography and groundwater flow. x 、v y The value of is determined, and R is determined according to the chemical properties of the pollutants in the crude oil. The diffusion equation is solved to obtain the pollutant concentration C(x, y, t) at different time t and spatial position (x, y).

[0079] Indicators such as vegetation coverage, vegetation health, and soil pollution level are input into a comprehensive ecological risk assessment model. Multi-criteria decision-making methods such as the analytic hierarchy process (AHP) or the fuzzy comprehensive evaluation method are then used to determine the risk level of damage to the surrounding ecosystem caused by mining activities. In the AHP, a hierarchical model is first constructed, with ecosystem damage risk as the target layer and vegetation coverage, vegetation health, and soil pollution level as the criterion layer. A judgment matrix is ​​then constructed (the relative importance of each criterion is determined based on expert experience or historical data) to calculate the weight vector for each criterion. Finally, the indicators under each criterion are quantitatively scored and weighted summed to obtain a comprehensive evaluation value for ecosystem damage risk. In the fuzzy comprehensive evaluation method, a set of evaluation factors (such as vegetation coverage, vegetation health, and soil pollution level) and a set of evaluation levels (such as low risk, medium risk, and high risk) are determined. A fuzzy relationship matrix (representing the fuzzy relationship between evaluation factors and evaluation levels) is then established. A fuzzy synthesis operation is used to obtain a fuzzy evaluation result of ecosystem damage risk, and the risk level is then determined based on the maximum membership principle.

[0080] As a specific embodiment of the present invention, in oil sampling and testing, the sampling points are selected based on:

[0081] According to the geological structure of the oil reservoir and the distribution of production wells, sampling points are set at the production wellheads of different oil layers to ensure that the oil products produced in oil layers of different depths are covered to reflect the differences in crude oil characteristics in different areas within the oil reservoir. Suppose the oil reservoir has n oil layers of different depths, and the depth of the i-th oil layer is h i , then the sampling points should cover different h i Corresponding wellhead; oil layer depth h iThe sampling frequency of each wellhead is determined by geological exploration data and the production rate and dynamic changes of the reservoir. For example, the sampling frequency can be appropriately increased for wellheads of oil layers with fast production rates or large changes in reservoir properties. By sampling at wellheads of oil layers at different depths, information on changes in crude oil properties in the vertical direction of the reservoir can be obtained. For example, density, viscosity, chemical composition, etc. may change with depth. This information is crucial for a comprehensive understanding of the characteristics of crude oil in the reservoir and an accurate prediction of the remaining oil situation.

[0082] Sampling points are set up at key nodes of gathering and transportation pipelines, such as the convergence points of oil pipelines from different oil wells, before and after oil-water separation equipment, etc., to detect changes in the properties of oil products during transportation and preliminary treatment, as well as the characteristics of oil products from different oil wells after mixing; sampling at the convergence points of oil pipelines can analyze the changes in the physical and chemical properties of oil products produced from different oil wells after mixing, because crude oil from different oil wells may have different characteristics; sampling before and after oil-water separation equipment can monitor changes in the water content of oil products during the separation process, impurity removal, etc.; the sampling frequency is determined according to factors such as the oil flow rate in the pipeline and the frequency of changes in the treatment process. For example, for pipeline nodes with large flow rates or frequent adjustments to the treatment process, the sampling frequency can be increased accordingly to ensure that changes in oil properties are grasped in a timely and accurate manner.

[0083] Consider the dynamic factors in the production process. For example, as the production stage progresses, the sampling point position should be adjusted in time according to the changes in reservoir pressure, the effects of water and gas injection, etc., to ensure that the sampled oil can accurately represent the remaining oil characteristics under the current production status; when the reservoir pressure drops, dissolved gas may be precipitated in the crude oil, affecting the properties of the oil. At this time, sampling points can be added in the areas that may be affected (such as pipelines near oil layers with large pressure changes); during the water and gas injection process, the injected materials may interact with the crude oil and change the composition and properties of the oil. Therefore, the sampling point position and sampling frequency should be appropriately adjusted in the pipelines or wellheads within the influence range of water and gas injection to ensure that the sampled oil can reflect the remaining oil characteristics under such dynamic changes.

[0084] As a specific embodiment of the present invention, in the prediction evidence based on oil product data, the specific method of correlation analysis includes:

[0085] First, the Pearson correlation coefficient is used to analyze the linear correlation between the physical and chemical properties of oil products and the amount of remaining oil that can be recovered. The oil parameters with significant linear correlation with the remaining oil reserves, such as density and water content, are identified, and their correlation direction and strength are determined. Let the oil parameter vector be X = (x1, x2, ..., x n ), the remaining oil that can be collected is y, n is the number of oil parameters; the mean (m is the sample size) Pearson correlation coefficient The value range of r is between [-1, 1]. r>0 indicates positive correlation, that is, when the oil parameters increase, the amount of remaining oil that can be collected also increases; r<0 indicates negative correlation. For example, density and the amount of remaining oil that can be collected may be negatively correlated, that is, the greater the density, the less the amount of remaining oil that can be collected; r=0 indicates no linear correlation. By calculating the values ​​between different oil parameters and the amount of remaining oil that can be collected, key parameters that have a linear impact on the prediction of remaining oil can be screened out.

[0086] For nonlinear correlation, support vector machine regression (SVR) algorithm is used; oil product data is used as input and the remaining oil that can be collected is used as output. By training the SVR model, the complex nonlinear mapping relationship between oil product parameters and remaining oil reserves is explored, providing a more accurate basis for model prediction; in the SVR model, the input oil product data is x = (x1, x2, ..., x n ), through the kernel function K(x, x i ) (Common kernel functions include linear kernel, polynomial kernel, Gaussian kernel, etc., which are selected according to the characteristics of the data) Map the input data to a high-dimensional feature space and build a linear regression model in the high-dimensional space (ω is the weight vector, The model is trained by minimizing the loss function (such as the ∈-insensitive loss function) to find the optimal ω and b, thereby establishing a nonlinear mapping relationship between oil parameters and the amount of remaining oil that can be collected.

[0087] Combining principal component analysis (PCA) and canonical correlation analysis (CCA) methods, a comprehensive analysis of multiple oil product parameters was conducted. PCA was used to extract the principal components of the oil product data. Let the oil product data matrix be X and its covariance matrix be C. By solving the eigenvalues ​​and eigenvectors of C, the eigenvectors were sorted from large to small according to the corresponding eigenvalues, and the first k eigenvectors were selected to form the projection matrix P, so that the principal component Z = XP. CCA was then used to analyze the correlation between the principal components and the amount of remaining oil that could be collected. Let the principal component matrix be Z and the amount of remaining oil that could be collected be y. By calculating the canonical correlation coefficient and canonical variate between Z and y, the comprehensive oil product characteristics that can best explain the changes in remaining oil were found, further optimizing the model's prediction ability for remaining oil.

[0088] As a specific embodiment of the present invention, the specific application of model compression technology in dynamic model adjustment and iteration includes:

[0089] Using network pruning technology, during the model retraining process, neurons and connections with less impact on the model prediction results are removed according to the importance evaluation indicators of neurons and connections, reducing the complexity and computational complexity of the model; assuming that the activation value of neuron i is a i , with weight w ij(j represents the index of other neurons connected to neuron i), and whether to prune is determined based on a certain threshold θ; the threshold θ can be determined by a variety of methods. One is based on statistical analysis. In the early stage of model training, the activation values ​​and weight distributions of different neurons and connections are observed, and an initial threshold is determined based on the statistical characteristics of the distribution (such as mean, standard deviation, etc.). Then, during the training process, it is dynamically adjusted according to the changes in model performance. If the model overfits at a certain stage, the threshold can be appropriately lowered and the pruning intensity can be increased; if the model performance degrades too quickly, the threshold can be appropriately increased; another method is to add an auxiliary loss function to integrate the importance evaluation of neurons and connections into the overall training goal of the model, and automatically adjust the threshold according to the optimization result of the loss function; during the pruning process, for neurons and connections whose activation values ​​are close to zero for a long time or whose absolute weight values ​​are small, it is considered that they have little impact on the model prediction results and can be deleted, thereby simplifying the model structure and improving the computational efficiency and generalization ability of the model.

[0090] Use quantization technology to convert the weights and activation values ​​in the model from high-precision data representation (such as 32-bit floating point numbers) to low-precision representation (such as 8-bit integers); let the quantization function be (s is the quantization step size), the selection of the quantization step size s is determined according to the data type, numerical range and accuracy requirements of the model parameters; for the weight parameters, an appropriate s value can be selected by analyzing their distribution range during the training process, so that the quantized weights can minimize data storage and calculation while ensuring that the loss of model accuracy is within an acceptable range; for activation values, since they may have different distribution characteristics in different layers and different training stages, an adaptive quantization method can be used to adjust the quantization step size according to the dynamic changes of the activation values ​​of each layer; for example, when the activation value range of some layers is narrow, a smaller quantization step size is selected to ensure quantization accuracy; when the activation value range is wide, the quantization step size is appropriately increased, and some compensation mechanisms (such as quantization-aware training) are used to reduce the impact of quantization error on model performance, thereby maintaining the prediction accuracy and stability of the model while compressing the model, and improving the operating efficiency of the model on edge computing devices.

[0091] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the foregoing embodiments. The foregoing embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for predicting remaining oil based on machine learning, characterized in that: The steps include: S1: Multi-source heterogeneous data acquisition: This involves collecting multi-source heterogeneous data covering oilfield geology, production history, reservoir characteristics, and surrounding topography. Geological data includes the three-dimensional structure and microscopic pore structure of oil reservoirs; production history data covers production methods and oil production volumes; reservoir characteristics include crude oil and formation water chemical parameters; and topography data includes high-resolution remote sensing and geographic information system multi-layer data. S2: Data preprocessing: Clean, normalize and reduce the dimension of all data collected in S1; S3: Multimodal feature extraction: Use deep learning methods to extract features from the data collected in S1; S4: Multimodal fusion machine learning model construction: Build a model that integrates multiple machine learning algorithms and integrates the different modal features in S3 for subsequent prediction and evaluation; S5: Initial remaining oil prediction: The initial data after preprocessing in S2 and feature extraction in S3 are input into the model in S4, and the predicted value of the remaining oil that can be collected is output; S6: Topography and geomorphic impact assessment: Evaluate the impact of mining on topography and geomorphology from multiple dimensions, including topographic stability, ecosystem damage risk, and groundwater hydrological change risk, and analyze the potential impact of mining on the surrounding environment; S7: Oil sampling and testing: During the mining process, the collected oil is sampled at irregular intervals to test the physical and chemical properties of the oil; S8: Prediction support based on oil product data: Integrate the oil product sampling and testing data in S6 into the model in S4, and verify and optimize the remaining oil prediction results from the perspective of the correlation between the changing trends of oil product characteristics and the model prediction results; S9: Dynamic feedback data collection: Use IoT sensors to collect multi-dimensional data in real time at the mining site to provide a basis for model iteration; S10: Dynamic model adjustment and iteration: Based on the incremental learning algorithm, the model is dynamically adjusted and retrained according to newly collected real-time data, while optimizing the learning rate and using model compression technology to improve model performance.

2. The method for predicting residual oil based on machine learning according to claim 1, wherein: The collection of geological data described in S1 includes: 3D geological exploration data, i.e., 3D spatial distribution information of underground oil layers with sub-meter resolution; Microscopic pore structure image data, that is, detailed information on the pores of reservoir rocks at the microscopic scale, provides a basis for analyzing the oil flow mechanism.

3. The method for predicting residual oil based on machine learning according to claim 2, wherein: The dimensionality reduction process in S2 includes the following: The three-dimensional geological exploration data and microscopic pore structure image data are subjected to dimensionality reduction processing by combining principal component analysis with local linear embedding; The mining history spatiotemporal sequence data is subjected to dimensionality reduction processing by wavelet transform; The multi-layer data of the geographic information system and the high-resolution remote sensing data of topography and landform are subjected to dimensionality reduction processing by a feature selection algorithm.

4. The method for predicting residual oil based on machine learning according to claim 1, wherein: Feature extraction in S3 involves extracting features from historical spatiotemporal series data using the following methods: Use recurrent neural networks, introduce a temporal attention mechanism, and combine it with a gating mechanism to extract features; The data is divided into different time scales, and multi-scale features are extracted from spatiotemporal series data.

5. The method for predicting residual oil based on machine learning according to claim 1, wherein: The multimodal fusion machine learning model in S4 is constructed, and the attention weight of each modality feature is calculated through the multi-head attention mechanism; And the contribution of different modal features is adjusted through a dynamic weight update strategy.

6. The method for predicting residual oil based on machine learning according to claim 1, characterized in that: During the initial remaining oil prediction in S5 and the topography and geomorphology impact assessment in S6, the model construction for ecosystem damage risk assessment includes: Based on vegetation index and land cover type data, a vegetation coverage and vegetation health assessment model was constructed; Using reservoir geochemical multi-parameter data and soil type data, a soil pollution diffusion model was established; Vegetation coverage, vegetation health status, and soil pollution level indicators are input into the comprehensive ecological risk assessment model, and the risk level of damage to the surrounding ecosystem caused by mining activities is determined through analysis.

7. The method for predicting residual oil based on machine learning according to claim 1, characterized in that: The sampling points for oil sampling and testing as described in S7 are selected based on: According to the geological structure of the oil reservoir and the distribution of production wells, sampling points are set at the production wellheads of different oil layers, and sampling points are set at key nodes of the gathering and transportation pipelines.

8. The method for predicting residual oil based on machine learning according to claim 1, characterized in that: The model compression technology described in S10 includes: network pruning technology and quantization technology, and the quantization technology is used to convert the weights and activation values ​​in the model from a high-precision data representation to a low-precision representation.

Images