A lithospheric thermal structure inversion method based on physical constraints and event recognition

Abstract

The present application belongs to the technical field of geophysical exploration and basin analysis, and provides a lithospheric thermal structure inversion method based on physical constraints and event identification. The method builds physical constraint conditions including rheological constraints of the lithosphere, isostatic compensation constraints and thermodynamic consistency constraints, establishes a layered lithospheric thermal conduction model, solves the transient heat conduction equation by using the finite difference method, realizes automatic identification of tectonic events and parameter initialization by using a machine learning regression model, builds a multi-objective loss function and performs global optimization by using a differential evolution algorithm, and finally evaluates the parameter uncertainty by using the Monte Carlo method. The method solves the problems of strong multi-solution, lack of physical rationality and low calculation efficiency of traditional inversion methods, and realizes efficient and reliable inversion of lithospheric thermal structure parameters.

Description

Technical Field

[0001] This invention belongs to the field of geophysical exploration and basin analysis technology, specifically involving a method for inverting the thermal structure of the lithosphere based on physical constraints and event identification. Background Technology

[0002] Lithospheric thermal structure inversion is a core technology in basin analysis, hydrocarbon accumulation potential assessment, and regional tectonic evolution history reconstruction. Its core objective is to quantitatively deduce key parameters such as extensional coefficients, rifting stages, and thermal flow evolution of the lithosphere over geological timescales using currently observed geological and geophysical data (such as stratigraphic temperature, heat flow values, and tectonic subsidence history), thereby revealing the basin's formation mechanism and evolutionary dynamics.

[0003] Currently, traditional inversion methods in this field mainly rely on trial-and-error fitting strategies based on global optimization algorithms (such as differential evolution algorithms, Monte Carlo simulations, and genetic algorithms). That is, by continuously adjusting input parameters (such as crustal and mantle extension coefficients, event occurrence time, and duration), a forward model is run to simulate temperature and subsidence history, and the optimal solution is found by minimizing the difference between simulated and observed data.

[0004] However, these traditional methods have long faced the following technical bottlenecks in both theoretical models and practical applications:

[0005] 1. A significant problem is the high degree of ambiguity: different extensional histories may produce similar temperature and settlement responses. Inversion results depend on the initial model selection, leading to multiple geological interpretations based on the same set of data, thus affecting the reliability of the conclusions.

[0006] 2. Weakened physical mechanism constraints make it difficult to guarantee geological rationality: Existing inversion methods lack the embedding and constraint of the basic physical mechanisms of lithospheric deformation. For example, inversion results are prone to geologically unreasonable solutions, such as strong crustal stretching while the mantle remains unchanged, ignoring the coupling relationship between crustal and mantle extension under a pure shear model. Simultaneously, forward modeling models simplify or ignore key physical processes such as sedimentation and burial, and thermal advection, further weakening the accuracy and predictive ability of the results.

[0007] 3. Low computational efficiency: The high-precision transient heat conduction forward model has high computational costs. The global optimization algorithm based on population iteration requires tens of thousands of calls to the model, resulting in extremely long inversion times (hours to days). This makes it difficult to apply this method quickly and in batches in exploration and production, and also makes it difficult to conduct uncertainty analysis and multi-scenario comparative studies.

[0008] 4. Lack of intelligent identification capability for tectonic events: Existing methods typically require users to pre-specify the extensional event phases, but in actual research, it is difficult to accurately determine the phases of basin rifting. In addition, the inversion system lacks the ability to automatically identify and extract implicit event signals from observational data. The entire inversion process heavily relies on the researcher's prior geological knowledge, making it difficult to discover unexpected tectonic events.

[0009] 5. Difficulty in handling multi-parameter collaborative inversion and coupling relationships: A complete extensional event needs to be described by multiple parameters such as crustal extension coefficient, mantle extension coefficient, start time, and duration. Multi-stage events lead to a sharp expansion of the parameter space dimension. The complex coupling and trade-off relationships between parameters make the optimization process prone to getting trapped in local extrema and convergence difficult.

[0010] Therefore, there is an urgent need to develop a new inversion method that can adaptively identify tectonic events, deeply integrate physical mechanism constraints, and significantly improve inversion efficiency and robustness of results, thereby providing more reliable technical support for basin dynamics research and oil and gas exploration decisions. Summary of the Invention

[0011] To address the aforementioned technical problems, this invention provides a method for inverting the thermal structure of the lithosphere based on physical constraints and event recognition, thereby resolving the issues in the prior art. The technical solution adopted by this invention is as follows:

[0012] A method for inverting the thermal structure of the lithosphere based on physical constraints and event recognition includes the following steps:

[0013] Step S1: Data preprocessing and physical constraint construction, inputting observation data and constructing physical constraints and parameter search space;

[0014] Step S2: Multi-stage transient heat conduction forward modeling, using the finite difference method to solve the transient heat conduction equation, and calculating heat sinking based on the equilibrium principle;

[0015] Step S3, intelligent event recognition and parameter initialization, using a machine learning regression model to analyze the observed data;

[0016] Step S4, Adaptive inversion optimization under physical constraints;

[0017] Step S5: Result verification and uncertainty assessment.

[0018] Furthermore, in step S1, the input observation data includes temperature evolution history, tectonic subsidence history, sedimentary burial history, and surface temperature history; when constructing physical constraints, they include lithospheric rheological constraints, equilibrium compensation constraints, and thermodynamic consistency constraints.

[0019] The parameter search space includes: defining the crustal tension coefficient. Mantle tensile coefficient Event start time Duration The parameter range.

[0020] Furthermore, step S2 includes:

[0021] Establish a layered lithospheric heat conduction model, including sedimentary layers, crustal layers, lithospheric mantle, and asthenosphere;

[0022] Solve the transient heat conduction equation using the finite difference method:

[0023] ;

[0024] in, For thermal diffusivity, Thermal conductivity, For density, For specific heat capacity, Distribution of radioactive heat generation rate; For temperature; For time; For depth; The symbol is for partial differentials;

[0025] Based on the principle of equilibrium, thermal settlement is calculated using the following equilibrium settlement formula:

[0026] ;

[0027] in, For time Heat deposition at any given time; For time The change in mass per unit area of ​​the rock column from the surface to the equilibrium compensation depth z at any given moment; , indicating time ,depth Instantaneous rock density at the location; This represents the initial density distribution; The density of the asthenosphere; Density of the filling material;

[0028] The transient heat conduction equation is used to calculate the evolution of the temperature field under given tension event parameters;

[0029] Density of temperature field corrected by thermal expansion ρ (T) is transformed into a density field change;

[0030] The density field change was used to calculate the surface subsidence history using the equilibrium subsidence formula. .

[0031] Furthermore, step S3 includes:

[0032] The observed data were analyzed using a machine learning regression model:

[0033] ;

[0034] in, The input feature vector includes an interpolation sequence of temperature evolution history and tectonic subsidence history; The output parameter vector includes the crustal stretching coefficient. Mantle tensile coefficient Event start time Duration and event validity identifier ;

[0035] Generate a training dataset, including:

[0036] Random sampling of event parameters: Within a preset geological range, multiple phases of extensional event parameters are randomly generated, including the event phase number and the start time of each event. Duration crustal tensile coefficient With mantle stretching coefficient ;

[0037] Forward modeling to generate response: Input the parameters of multiple tensile events into step S2 to calculate the corresponding temperature evolution history. and tectonic subsidence history ;

[0038] Adding observational noise: in the generated temperature evolution history and tectonic subsidence history Superimposed random noise that conforms to a normal distribution;

[0039] Constructing training samples: Noise-added temperature evolution history and tectonic subsidence history sequences are used as input features. The original event parameter group used to generate this data is used as the output label. Together they constitute a training sample ;

[0040] Train a multi-output regression model to obtain the mapping function. Establish a mapping relationship from observation data to inversion parameters;

[0041] The objective function to generate is:

[0042] ;

[0043] in, For mathematical expectation operators; This is a vector of known real event parameters in the synthetic data; For machine learning models to synthesize input features The predicted output; for The square of the norm;

[0044] Outputs preliminary intelligent estimates of the number of events, tension coefficient, and time parameters.

[0045] Furthermore, step S4 includes:

[0046] Based on the intelligent estimate obtained in step S3, global optimization is performed within the parameter search space of step S1 using a differential evolution algorithm, including:

[0047] Using the temperature evolution history and tectonic subsidence history input in step S1 as the fitting objectives, a multi-objective loss function is constructed:

[0048] ;

[0049] in:

[0050] Temperature fitting error:

[0051] ;

[0052] Settlement fitting error:

[0053] ;

[0054] Coupling penalty term:

[0055] ;

[0056] in, The value of the multi-objective loss function; These are the weighting coefficients; This is the penalty coefficient; This represents the temperature fitting error in the temperature history. This represents the number of temperature observation data points; For the first One observed temperature value; For the first One simulated temperature value; The settlement fitting error in the settlement history; This represents the number of settlement observation data points; For the first One observed settlement value; For the first One simulated settlement value; To calculate the crustal extension coefficient for all identified tectonic events. With mantle stretching coefficient The sum of squares of the differences.

[0057] Furthermore, step S5 includes:

[0058] Perform a physical consistency check on the inversion results:

[0059] ;

[0060] in, The overall score is the physical consistency score; the higher the score, the better the inversion result conforms to the preset physical constraints. For the first The weight of each physical constraint; For the first Scoring of the degree to which physical constraints are satisfied;

[0061] The Monte Carlo method is used to assess parameter uncertainty:

[0062] ;

[0063] in, is the posterior standard deviation of the inversion parameters; The number of valid sample groups obtained from Monte Carlo sampling; For the first The value of this parameter in the Monte Carlo sample group; For this parameter in all The mean of the group sample;

[0064] Generate multiple sets of equivalent solutions, analyze the degree of ambiguity of the inversion results, and output the final inversion parameters and their confidence intervals.

[0065] The present invention has the following beneficial effects:

[0066] (1) Intelligent event recognition capability: Automatically identify the period and time of tectonic events through machine learning technology, reducing reliance on prior geological knowledge;

[0067] (2) Physical constraint guarantee: The physical mechanism of lithospheric deformation is introduced as a constraint condition to ensure the geological rationality of the inversion results;

[0068] (3) Improved computational efficiency: Machine learning-assisted fast estimation provides a high-quality initial solution for global optimization, significantly reducing the number of iterations required for convergence;

[0069] (4) Mitigation of multiple solutions: By reducing the dimension of the solution space through physical constraints and intelligent recognition, the generation of incompatible solutions is effectively suppressed;

[0070] (5) Adaptive inversion capability: Automatically adjust the inversion strategy according to the data quality and type to achieve coordinated constraints on temperature and settlement data. Attached Figure Description

[0071] Figure 1 This is a flowchart. Detailed Implementation

[0072] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Unless otherwise specified, the technical means used in the embodiments are conventional means well known to those skilled in the art.

[0073] like Figure 1 A method for inverting the thermal structure of the lithosphere based on physical constraints and event recognition includes the following steps:

[0074] Step S1: Data preprocessing and physical constraint construction, including:

[0075] Input observational data: including temperature evolution history, tectonic subsidence history, sedimentary burial history, and surface temperature history;

[0076] The physical constraints are constructed, including lithospheric rheological constraints, isostatic compensation constraints, and thermodynamic consistency constraints. The lithospheric rheological constraints are used to ensure that the lithospheric strength corresponding to the inversion parameters is mechanically reasonable, specifically including the upper limit constraint of the crustal stretching factor. ≤3.0), constraints on the coupling relationship between mantle stretching factor and crustal stretching factor ( ≥ (preferring a pure shear deformation mechanism), and the lower limit constraint of crustal thickness after stretching ( (>15km); The equilibrium compensation constraint requires that the inverted thermal structure can produce a settlement consistent with the observation through the equilibrium principle. Specifically, it includes the mass column conservation constraint before and after stretching, the consistency constraint between theoretical tectonic settlement and actual settlement, and the matching constraint between sedimentary load and settlement response. The thermodynamic consistency constraint mainly includes the surface heat flow range constraint (30-120mW / m²), the temperature range constraint of the lithosphere floor (1300±100℃), the rationality constraint of crustal temperature gradient (15-35℃ / km), and the monotonically increasing temperature field constraint, to ensure that the inversion results conform to the physical laws of the heat conduction equation and the thermal structure characteristics of a typical continental lithosphere.

[0077] Setting the parameter search space: Defining the crustal tensile coefficient Mantle tensile coefficient Event start time Duration The parameter range, this search space defines the parameter optimization boundary for subsequent global optimization algorithms.

[0078] Step S2: Multi-stage transient heat conduction forward modeling, including:

[0079] A layered lithospheric heat conduction model was established, including sedimentary layers, crustal layers, lithospheric mantle, and asthenosphere;

[0080] Solving the transient heat conduction equation using the finite difference method (assuming thermal conductivity) (constant)

[0081] ;

[0082] in, Thermal diffusivity, in km. 2 / Ma, Thermal conductivity, in W / (m•K). Density, unit: kg / m³ 3 ; Specific heat capacity, unit: J / (kg•K); Temperature, in °C or K; Time, in Ma; Depth, in km; This represents the distribution of radioactive heat generation rate, in μW / m³. 3 , The surface radioactive heat generation rate, in μW / m² 3 , D The radioactive heat generation rate decay depth is expressed in km.

[0083] A Lagrange depth tracking method is introduced to handle the material advection effect during the stretching process;

[0084] This transient heat conduction equation is the core governing equation for lithospheric thermal evolution simulation. Its purpose is to calculate the evolution of the temperature field within the lithosphere over time and depth. This is achieved by providing an initial temperature field, boundary conditions (surface temperature history and lithosphere floor temperature), and extensional event parameters (…). Solving this equation yields the simulated temperature history. This refers to the temperature distribution at different depths within the lithosphere during different geological periods. This temperature field forms the basis for subsequent calculations of thermal expansion, density changes, and isostatic settlement.

[0085] Thermal settlement is calculated based on the principle of equilibrium. The formula for calculating equilibrium settlement is:

[0086] ;

[0087] Formula parameter description: For time The amount of heat settlement at any given time, expressed in meters (m). For time The change in mass per unit area of ​​the rock column from the surface to the equilibrium compensation depth z at any given moment; , indicating time ,depth The instantaneous rock density at a given location, expressed in kg / m³; this density is a function of temperature, expressed by the thermal expansion equation. Calculated, where The solution is obtained from the transient heat conduction model. For reference temperature, the unit is the same. , Reference temperature The density of the rock below is expressed in kg / m³. The coefficient of thermal expansion is K. -1 ; To ensure balanced compensation depth, the unit is meters (m). The initial density distribution specifically refers to the moment after the tectonic stretching event ends and the thermal relaxation process begins. The density of the lithosphere varies with depth. The distribution is expressed in kg / m³, which serves as the baseline reference state for settlement calculation. This represents the density of the asthenosphere, expressed in kg / m³. Density of the filling material, in kg / m³;

[0088] The purpose of this equilibrium subsidence formula is to transform the evolution of the temperature field into an observable history of surface tectonic subsidence. Its calculation principle is: temperature changes cause thermal expansion or contraction of rocks, thereby altering the rock density (formula). Changes in density lead to variations in the mass per unit area of ​​the rock column, resulting in surface subsidence or uplift under an isostatic compensation mechanism. The calculation results of this formula represent a simulated subsidence history. This refers to the tectonic subsidence of the basin basement over time. This subsidence history can be compared with observed tectonic subsidence history and is one of the key observational data for constraining inversion parameters.

[0089] The connection between the two formulas and model construction: The two formulas mentioned above together constitute a complete thermodynamic coupled forward model. The transient heat conduction equation simulates the thermal process, and the equilibrium sedimentation formula simulates the mechanical response. The two are closely coupled through the temperature-density relationship (thermal expansion effect). Specifically:

[0090] The transient heat conduction equation calculates the temperature field evolution under given tension event parameters. ;

[0091] Density formula for temperature field corrected by thermal expansion This is transformed into a change in the density field;

[0092] The density field change was used to calculate the surface subsidence history using the equilibrium subsidence formula. .

[0093] This coupling process ensures that the model simultaneously satisfies the physical laws of heat conduction and the principle of equilibrium compensation, giving the simulation results (temperature history and sedimentation history) clear physical meaning and providing a solid physical foundation for subsequent inversion.

[0094] Step S3: Intelligent event recognition and parameter initialization, including:

[0095] Machine learning regression models are used to quickly analyze the observed data:

[0096] ;

[0097] in, The input feature vector contains an interpolation sequence of temperature evolution history and tectonic subsidence history; The output parameter vector contains (Crustal tensile coefficient) (Mantle stretching coefficient) (Event start time) (Duration) and (Event validity identifier) ​​and other parameters.

[0098] The strategy for generating the training dataset is as follows:

[0099] 1. Random sampling of event parameters: Within a preset reasonable geological range, multiple phases of extensional event parameters are randomly generated, including the event phase (phases 1-4) and the start time of each event. Duration crustal tensile coefficient With mantle stretching coefficient .

[0100] 2. Forward modeling to generate response: Input the parameters of multiple tensile events into the forward model described in step S2 to calculate the corresponding temperature evolution history. and tectonic subsidence history .

[0101] 3. Add observation noise: To simulate the uncertainty of real observation data, in the generated... and Random noise that follows a normal distribution is superimposed on top.

[0102] 4. Construct training samples: Use the noisy temperature evolution history and tectonic subsidence history sequences as input features. The original event parameter set used to generate this data will be used as the output label. Together they constitute a training sample By repeating the above process tens of thousands to hundreds of thousands of times, a large-scale synthetic training dataset covering a wide range of geological scenarios was constructed.

[0103] 5. Train the multi-output regression model to obtain the mapping function. In a specific form, a rapid mapping relationship is established from observation data to inversion parameters.

[0104] The objective function for generating synthetic data is:

[0105] ;

[0106] Formula parameter description: is the mathematical expectation operator, which represents averaging over all samples in the synthetic training dataset. The vector of known real event parameters (labels) in the synthetic data. For machine learning models to synthesize input features The predicted output. for The square of the norm is the sum of the squares of the errors.

[0107] The system outputs preliminary intelligent estimates of the number of events, the tension coefficient, and time parameters; the number of events is determined by the model output. The number of parameter groups is determined, and the tension coefficient and time parameter define the spatial and temporal attributes of each recognition event;

[0108] Event effectiveness evaluation mechanism:

[0109] When the event parameters predicted by the machine learning model meet the following conditions:

[0110] (Significant tension event);

[0111] Ma (duration in a geological sense);

[0112] Prediction confidence (Model output probability);

[0113] The parameter combination conforms to prior geological knowledge (such as...) );

[0114] When the predicted event parameters do not meet the above conditions, or are identified as false signals caused by data noise / measurement error;

[0115] In subsequent optimization steps, only for Physical constraint optimization is performed on valid events. Such events are excluded to avoid interference from the spurious solution space;

[0116] The intelligent estimate output in this step will serve as a high-quality initial solution for subsequent global optimization.

[0117] Step S4: Adaptive inversion optimization under physical constraints, including:

[0118] Based on the intelligent estimate obtained in step S3, global optimization is performed within the parameter search space of step S1 using a differential evolution algorithm, including:

[0119] Using the temperature evolution history and tectonic subsidence history input in step S1 as fitting targets, a multi-objective loss function is constructed. This function simultaneously measures the fitting error between the simulation results and the observed temperature evolution history and the observed tectonic subsidence history.

[0120] The multi-objective loss function is:

[0121] ;

[0122] in,

[0123] Temperature fitting error:

[0124] ;

[0125] Settlement fitting error:

[0126] ;

[0127] Coupling penalty term:

[0128] ;

[0129] in, It is a multi-objective loss function, which is the objective of optimization (minimization). , These are the weighting coefficients. This is the penalty coefficient. The baseline weights for temperature fitting ensure that the basic constraints of the thermal structure are met. The weighting of subsidence fitting is higher than that of temperature, reflecting the importance of tectonic subsidence data for basin analysis (subsidence data usually has higher measurement accuracy and geological significance). Sensitivity analysis revealed that this range can effectively constrain the consistency of crust-mantle deformation while avoiding excessive punishment of reasonable deformation differences. This represents the temperature fitting error, specifically the root mean square error of the temperature history. This represents the number of temperature observation data points. For the first One observed temperature value. For the first A simulated temperature value. This represents the settlement fitting error of the settlement history, i.e., the root mean square error of the settlement history. This represents the number of settlement observation data points. For the first One observed settlement value. For the first One simulated settlement value. For all identified construction events (subscripts) Calculate its crustal tensile coefficient. With mantle stretching coefficient The sum of squares of the differences is used to penalize geologically unreasonable strong decoupling events.

[0130] During the optimization process, each evaluation of the loss function requires calling the forward model in step S2 to calculate the simulated temperature history and sedimentation history based on the current parameters. The differential evolution algorithm continuously updates the parameter population within the parameter search space to minimize the loss function, thereby obtaining the optimal inversion parameters.

[0131] A differential evolution algorithm is used for global optimization, incorporating physical constraints as boundary conditions;

[0132] Implement adaptive parameter adjustments and dynamically adjust the search strategy according to the inversion progress;

[0133] Step S5: Result Validation and Uncertainty Assessment

[0134] Perform a physical consistency check on the inversion results:

[0135] ;

[0136] in, Physical consistency score: The higher the score, the better the inversion result conforms to the preset physical constraints. , , These are the weights of the lithospheric rheological constraints, the equilibrium compensation constraints, and the thermodynamic consistency constraints, respectively. , , Each constraint satisfaction level is scored. The specific calculation method is as follows:

[0137] Lithospheric rheological constraint score ( ):

[0138] ;

[0139] in: (Reasonableness score of crustal extension coefficient);

[0140] (Score of mantle-crust coupling relationship);

[0141] (Score for the rationality of crustal thickness after stretching).

[0142] Equilibrium compensation constraint score ( ):

[0143] ;

[0144] in: (Mass conservation score) This is the integral result of the change in mass per unit area of ​​the rock column, in kg / m². , represents the initial mass of the rock column, in kg / m²;

[0145] (Settlement consistency score);

[0146] (Load-settlement matching score);

[0147] Thermodynamic consistency constraint score ( ):

[0148] ;

[0149] in: (Surface heat flow rationality score)

[0150] (Reasonableness score for temperature at the base of the lithosphere);

[0151] (Temperature gradient rationality score)

[0152] Weighting:

[0153] (Rheological constraint weights);

[0154] (Balance constraint weights);

[0155] (Thermodynamic constraint weights);

[0156] in, The value ranges from 0 to 1, where 1.0 indicates that it fully complies with all physical constraints, and 0.0 indicates that it seriously violates the laws of physics.

[0157] The Monte Carlo method is used to assess parameter uncertainty:

[0158] ;

[0159] Formula parameter description: For a certain inversion parameter (e.g.) The posterior standard deviation of is used to measure its uncertainty. The number of valid sample groups obtained from Monte Carlo sampling. : No. The value of this parameter in the Monte Carlo sample group. This parameter is in all The average value of the sample group. Generate multiple equivalent solutions, analyze the degree of ambiguity of the inversion results; output the final inversion parameters and their confidence intervals.

[0160] Preferably, the machine learning regression model described in step S3 uses random forest, gradient boosting, or neural network algorithms to establish a nonlinear mapping relationship from temperature-sedimentation sequence to tension parameters through synthetic data training.

[0161] The above embodiments are merely descriptions of preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Any modifications, alterations, alterations, or substitutions made by those skilled in the art to the technical solutions of the present invention without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

Claims

1. A method for inverting the thermal structure of the lithosphere based on physical constraints and event recognition, characterized in that, Includes the following steps: Step S1: Data preprocessing and physical constraint construction, inputting observation data and constructing physical constraints and parameter search space; Step S2: Multi-stage transient heat conduction forward modeling, using the finite difference method to solve the transient heat conduction equation, and calculating heat sinking based on the equilibrium principle; Step S3, intelligent event recognition and parameter initialization, using a machine learning regression model to analyze the observed data; Step S4, Adaptive inversion optimization under physical constraints; Step S5: Result verification and uncertainty assessment; In step S1, the input observation data includes temperature evolution history, tectonic subsidence history, sedimentary burial history, and surface temperature history; when constructing physical constraints, they include lithospheric rheological constraints, isostatic compensation constraints, and thermodynamic consistency constraints. The parameter search space includes: defining the crustal tension coefficient. Mantle tensile coefficient Event start time Duration The parameter range; Step S3 includes: Machine learning regression models are used to model the observed data: in, The input feature vector includes an interpolation sequence of temperature evolution history and tectonic subsidence history; The output parameter vector includes the crustal stretching coefficient. Mantle tensile coefficient Event start time Duration ; Generate a training dataset, including: Random sampling of event parameters: Within a preset geological range, multiple phases of extensional event parameters are randomly generated, including the event phase number and the start time of each event. Duration crustal tensile coefficient With mantle stretching coefficient ; Forward modeling to generate response: Input the parameters of multiple tensile events into step S2 to calculate the corresponding temperature evolution history. and tectonic subsidence history ; Adding observational noise: in the generated temperature evolution history and tectonic subsidence history Superimposed random noise that conforms to a normal distribution; Constructing training samples: Noise-added temperature evolution history and tectonic subsidence history sequences are used as input features. The original event parameter group used to generate this data is used as the output label. Together they constitute a training sample ; Train a multi-output regression model to obtain the mapping function. Establish a mapping relationship from observation data to inversion parameters; The objective function to generate is: in, For mathematical expectation operators; This is a vector of known real event parameters in the synthetic data; For machine learning models to synthesize input features The predicted output; for The square of the norm; Outputs preliminary intelligent estimates of the number of events, tension coefficient, and time parameters.

2. The method for inverting lithospheric thermal structure based on physical constraints and event recognition according to claim 1, characterized in that, Step S2 includes: Establish a layered lithospheric heat conduction model, including sedimentary layers, crustal layers, lithospheric mantle, and asthenosphere; Solve the transient heat conduction equation using the finite difference method: in, For thermal diffusivity, Thermal conductivity, For density, For specific heat capacity, Distribution of radioactive heat generation rate; For temperature; For time; For depth; The symbol is for partial differentials; Based on the principle of equilibrium, thermal settlement is calculated using the following equilibrium settlement formula: in, For time Heat deposition at any given time; For time The change in mass per unit area of ​​the rock column from the surface to the equilibrium compensation depth L at any time; , indicating time ,depth Instantaneous rock density at the location; This represents the initial density distribution; The density of the asthenosphere; Density of the filling material; The transient heat conduction equation is used to calculate the evolution of the temperature field under given tension event parameters; Density of temperature field corrected by thermal expansion ρ (T) is transformed into a density field change; The density field variation was used to calculate the tectonic subsidence history using the equilibrium subsidence formula.

3. The method for inverting lithospheric thermal structure based on physical constraints and event recognition according to claim 1, characterized in that, Step S4 includes: Based on the intelligent estimate obtained in step S3, global optimization is performed within the parameter search space of step S1 using a differential evolution algorithm, including: Using the temperature evolution history and tectonic subsidence history input in step S1 as the fitting objectives, a multi-objective loss function is constructed: in: Temperature fitting error: Settlement fitting error: Coupling penalty term: in, The value of the multi-objective loss function; These are the weighting coefficients; This is the penalty coefficient; This represents the temperature fitting error in the temperature history. This represents the number of temperature observation data points; For the first One observed temperature value; For the first One simulated temperature value; The settlement fitting error in the settlement history; This represents the number of settlement observation data points; For the first One observed settlement value; For the first One simulated settlement value; To calculate the crustal extension coefficient for all identified tectonic events. With mantle stretching coefficient The sum of squares of the differences.

4. The method for inverting lithospheric thermal structure based on physical constraints and event recognition according to claim 1, characterized in that, Step S5 includes: Perform a physical consistency check on the inversion results: in, The overall score is the physical consistency score; the higher the score, the better the inversion result conforms to the preset physical constraints. For the first The weight of each physical constraint; For the first Scoring of the degree to which physical constraints are satisfied; The Monte Carlo method is used to assess parameter uncertainty: in, is the posterior standard deviation of the inversion parameters; The number of valid sample groups obtained from Monte Carlo sampling; For the first The value of this parameter in the Monte Carlo sample group; For this parameter in all The mean of the group sample; Generate multiple sets of equivalent solutions, analyze the degree of ambiguity of the inversion results, and output the final inversion parameters and their confidence intervals.

Images