Geological survey database construction method for ancient marine environment evolution

Abstract

The invention discloses a geological survey database construction method for ancient marine environment evolution, and relates to the technical field of geological survey, and the method comprises the following steps: collecting multi-source data from multiple aspects of geological structure, sediment, paleontology and geophysics, and carrying out the preprocessing of the collected multi-source data; and performing reliability and precision analysis on the preprocessed multi-source data, and dividing the collected data into different trust levels. By building the geological survey database of ancient marine environment evolution, integration and standardization of data from different channels, different formats and different accuracies are achieved, the research efficiency is remarkably improved, the data in the database can be directly used for analysis and visualization after unified processing, the research period is greatly shortened, and in addition, the research efficiency is improved. The standardization of the data also ensures the consistency and comparability among different researches, so that the research results are more reliable.

Description

Technical Field

[0001] The present invention relates to the field of geological survey technology, and in particular to a method for constructing a geological survey database for paleo-ocean environment evolution. Background Art

[0002] 70% of the Earth's surface is covered by the ocean, which is an important recorder of Earth's history. By building a geological survey database of the evolution of the ancient marine environment, scientists can systematically collect, organize and analyze marine geological data, so as to have a deeper understanding of the Earth's evolution process, including changes in the geological structure of the ocean floor, the accumulation and transformation of sediments, the rise and fall of ancient biological communities, etc., which are all important parts of Earth's history. In addition, the ocean floor is rich in mineral resources, such as oil, natural gas, hydrothermal metal deposits, etc. The exploration and development of resources need to rely on geological survey data. Building a geological survey database of the evolution of the ancient marine environment can provide an important basis for resource exploration and promote the sustainable use of energy and mineral resources.

[0003] In the existing technology, geological surveys involve a wide variety of data, including geological structure, sediments, paleontology, geophysics and other aspects. Due to the diverse sources and formats of data, and the possible contradictions and conflicts between data, how to analyze the key factors and trends in the evolution of the paleo-ocean environment so that the data in the database can timely reflect the latest research results and geological environment changes is the problem we need to solve. To this end, a method for constructing a geological survey database for paleo-ocean environment evolution is proposed. Summary of the invention

[0004] The present invention aims to provide a method for constructing a geological survey database of paleo-ocean environment evolution to solve the problems raised in the above-mentioned background technology.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: A method for constructing a geological survey database for paleo-ocean environment evolution comprises the following steps: Step 1: Collect multi-source data from geological structure, sediment, paleontology, geophysics and other aspects, and pre-process the collected multi-source data, including data cleaning, format conversion and standardization, solve problems such as data duplication, mismatch, and format inconsistency, and ensure data quality and consistency; Step 2: Analyze the reliability and accuracy of the pre-processed multi-source data, and divide the collected data into different trust levels. High-trust level data can be used as the main basis for analysis, while low-trust level data can be used for auxiliary analysis; Step 3: Use machine learning algorithms to conduct in-depth analysis of the preprocessed data, identify the key factors of the evolution of the paleo-ocean environment, and build an environmental evolution model based on historical data to predict the evolution trend of the paleo-ocean environment; Step 4: Based on the federated database technology, the pre-processed and predicted paleo-ocean environment evolution trends are integrated to obtain a geological survey database containing spatial data and attribute data for spatial query and analysis; Step 5: Use GIS software to visualize the relevant data in the geological survey database, present the analysis results in the form of graphics and charts, and regularly collect new related data to continuously update the database.

[0006] A further improvement of the technical solution of the present invention is that in step 1, the process of collecting multi-source data and preprocessing is: Clarify the types of geological data related to the evolution of the ancient marine environment, including geological structure, sediment, paleontology, and geophysical data, and collect multi-source data on geological structure, sediment, paleontology, and geophysics. The collection sources include field surveys, laboratory analysis, geological survey reports, scientific literature, and existing databases. The geological structure data comes from geological exploration reports, seismic exploration data, geological profiles, etc. Sediment data comes from sediment sample analysis, sedimentary phase research, sedimentation rate measurement, etc. Paleontological data comes from fossil records, paleontological community analysis, paleoecological research, etc. Geophysical data comes from geophysical exploration methods such as gravity, magnetism, electrical methods, and seismic methods; Preprocess the collected multi-source data, including data cleaning, format conversion, and data standardization steps; For the spatial data and time series data in the preprocessed data, spatial and temporal overlays are performed respectively to ensure the spatial consistency of spatial data between different layers and the temporal consistency of different data sets; Integrate data sets from different sources into a unified data warehouse, establish relationships between data, and associate spatial data with non-spatial data through a coordinate system to form a comprehensive data set that includes geological structures, sediments, paleontology, and geophysics; Create metadata for the resulting comprehensive dataset to record detailed information about the data, including the title, author, creation date, data source, data type, data range, and data precision of the dataset.

[0007] A further improvement of the technical solution of the present invention is that in step 2, the process of dividing different trust levels is as follows: Traverse the preprocessed multi-source data, perform data analysis on each data source, and evaluate the reliability and accuracy of the data; According to the reliability and accuracy analysis of the data, the error range of the data is estimated, the trust evaluation indicators of multi-source data and the benchmark score values ​​of the trust evaluation indicators are determined, and each trust evaluation indicator is scored to calculate the data reliability evaluation index and the data accuracy evaluation index respectively. Among them, the trust evaluation indicators of data reliability are data integrity, data consistency, data accuracy, data timeliness and data source credibility, and the trust evaluation indicators of data accuracy are measurement accuracy, classification accuracy and time accuracy; A trust assessment model is constructed based on the scoring results of each trust assessment indicator to quantitatively evaluate the data. The trust assessment coefficient is calculated for each data set based on the constructed trust assessment model and the scores of the trust assessment indicators, and the data reliability assessment index and data accuracy assessment index are integrated. The data is divided into different trust levels based on the trust assessment coefficient, namely low trust level, medium trust level and high trust level, and the corresponding trust assessment threshold is matched for each trust level. Divide each data set into a corresponding trust level according to its trust assessment coefficient, and annotate it to explain its trust level and assessment basis. Develop a data integration strategy, establish a usage guide for each trust level data, and guide how to use it for auxiliary analysis. For high-trust level data, use it as the main basis for analysis, for building models, making predictions and decision support. For medium-trust level data, use it for auxiliary analysis, provide additional information or verify the accuracy of high-trust level data. For low-trust level data, use it only for reference or as background information and avoid using it in key analysis.

[0008] A further improvement of the technical solution of the present invention is that the calculation formula of the data reliability evaluation index is: ; Among them, RI is the data reliability evaluation index, is the score of the dataset on the i-th trust evaluation indicator, is the benchmark score value of the i-th trust evaluation indicator, is the full score of the i-th trust evaluation indicator, is the consistency score of the i-th trust evaluation indicator, In order to adjust the parameters and control the influence of consistency score on overall reliability, the value range of RI is ,The closer the RI value is to 1, the higher the data reliability; The calculation formula of the data accuracy evaluation index is: ; Among them, AI is the data accuracy assessment index, Score the actual measured value of the dataset on the jth accuracy evaluation metric, Score the expected measurement value of the jth accuracy evaluation metric, is the benchmark accuracy ratio of the jth accuracy evaluation indicator, is the adjustment parameter of the jth accuracy evaluation index, which is used to control the weight of the result after logarithm calculation. The value range of AI is , the closer the AI ​​value is to 1, the higher the data accuracy is.

[0009] A further improvement of the technical solution of the present invention is that the calculation formula of the trust evaluation coefficient is: ; Among them, TAC is the trust assessment coefficient, is the reliability evaluation index of the i-th data set, is the precision evaluation index of the jth data set, is the weight of the i-th reliability evaluation index, is the weight of the jth accuracy evaluation index, It is a parameter between 0 and 1, which is used to balance the relative importance of reliability and accuracy in the final evaluation. The value range of TAC is ,The closer the TAC value is to 1, the higher the trust level of the data.

[0010] A further improvement of the technical solution of the present invention is that: the multiple trust levels correspond to the multiple trust evaluation thresholds, wherein the trust evaluation thresholds include an upper threshold and a lower threshold; The multiple trust levels and the multiple trust assessment thresholds satisfy the following relationship: Low Trust Level ; Medium Trust Level ; High trust level ; Among them, TAC is the trust assessment coefficient, is the lower threshold corresponding to the medium trust level and the upper threshold corresponding to the low trust level, is the lower threshold corresponding to the high trust level and the upper threshold corresponding to the medium trust level, , .

[0011] The further improvement of the technical solution of the present invention is that: in the step 3, the construction process of the environment evolution model is: Extract the historical data of the paleo-ocean environment that have been pre-processed and trusted, covering different time scales, geographical regions and environmental variables, and perform feature analysis on the extracted historical data of the paleo-ocean environment, select the features related to the evolution of the paleo-ocean environment, namely temperature, salinity, redox state and biological productivity characteristics, and obtain the feature data set; The feature data set is divided into a training set and a test set. The training set data is combined with the neural network model to build an environmental evolution model, and the test set data is used to evaluate the performance of the model in order to adjust the model parameters and improve the accuracy and generalization ability of the model. The trained environmental evolution model is used to predict the evolution trend of the paleo-ocean environment and understand the dynamic change trend of the paleo-ocean environment. Based on the trained environmental evolution model and relevant data of the characteristic data set, the environmental evolution coefficient is calculated, the trend of paleo-ocean environmental evolution is analyzed, and key environmental change nodes and trends are identified, such as temperature rise, salinity changes, fluctuations in redox states, and increases and decreases in biological productivity; Interpret the results predicted by the environmental evolution model, analyze the results of environmental change predictions at different time scales, analyze whether the trends predicted by the environmental evolution model are consistent with known geological events and environmental changes, and adjust the environmental evolution model based on the verification results to improve the accuracy of the prediction.

[0012] A further improvement of the technical solution of the present invention is that the calculation formula of the environmental evolution coefficient is: ; Where EC is the environmental evolution coefficient, is the current value of the kth feature, where k ranges from 1 to 4, corresponding to temperature, salinity, redox state, and biological productivity, respectively. is the benchmark value of the kth feature, which is the historical average level. is the weight of the kth feature, reflecting the importance of this feature in environmental evolution, S is the current value of biological productivity, is the historical maximum value of biological productivity. and To adjust the parameters to balance the impact of different parts, the larger the EC value, the greater the degree of environmental change.

[0013] A further improvement of the technical solution of the present invention is that in step 4, the process of acquiring the geological survey database containing spatial data and attribute data is as follows: Identify and record all pre-processed data sources, including spatial data and attribute data, and integrate the confidence level of each data set and the predicted paleo-ocean environment evolution trend results; Design the federated database architecture, including local database, global database, and middleware, and define the integration process of data sources, build a federated database system, and configure middleware and global database to access and manage data in the local database to form a geological survey database; Import the preprocessed spatial data into the local database in the geological survey database to ensure the accuracy and integrity of the spatial data, perform format conversion and coordinate system unification, import the predicted paleo-ocean environment evolution trend data into the geological survey database as attribute data, and associate the attribute data with the spatial data for spatial analysis and query; A spatial query function is set up in the geological survey database to query paleo-ocean environment data based on geographical location, and a query and analysis function for attribute data is set up to query the evolution trend of the paleo-ocean environment based on the time scale.

[0014] A further improvement of the technical solution of the present invention is that in step 5, the process of visualization processing is: Extract the spatial data and attribute data to be visualized from the geological survey database, convert the extracted data into data format, and import it into the GIS software to ensure that the data can be correctly displayed and analyzed in the GIS software; Use the mapping function of GIS software to create maps based on spatial data, overlay attribute data on the map, display the distribution and changes of data through colors, symbols, and legends, display the statistical characteristics and evolution trends of attribute data, and output the visualization results in the form of graphics and charts, and mark the necessary instructions and explanations in the output results for users to understand and use; According to the data update cycle, new related data is collected regularly, and the newly collected data is quality checked and preprocessed to ensure the accuracy and completeness of the data; Import new data into the geological survey database, update existing data records, and integrate new and existing data to ensure data consistency and integrity. Re-perform visualization based on the updated database content, compare old and new visualization results, and analyze data changes and trends.

[0015] Due to the adoption of the above technical solution, the present invention has the following technical advances compared with the prior art: The present invention provides a method for constructing a geological survey database for the evolution of paleo-ocean environments. By constructing a geological survey database for the evolution of paleo-ocean environments, the integration and standardization of data from different channels, in different formats, and with different precisions are realized, which significantly improves the research efficiency. The data in the database are processed uniformly and can be directly used for analysis and visualization, which greatly shortens the research cycle. In addition, the standardization of the data also ensures the consistency and comparability between different studies, making the research results more reliable.

[0016] The present invention provides a method for constructing a geological survey database of paleo-ocean environment evolution. By constructing the geological survey database of paleo-ocean environment evolution, geological data scattered in different studies, different regions and different time scales can be integrated into a unified platform. The database not only includes spatial data and attribute data, but also integrates the trust level of the data and the results of the prediction model. Through the federated database technology, users can access data across different database systems and formats, which greatly improves the accessibility of the data. In addition, the visualization function of the GIS software enables complex geological data and analysis results to be presented in the form of graphics and charts, thereby improving the utilization rate of the data.

[0017] The present invention provides a method for constructing a geological survey database of paleo-ocean environmental evolution. During the database construction process, trust evaluation is performed on pre-processed data to ensure the reliability and accuracy of the data. By calculating the environmental evolution coefficient, the trend of paleo-ocean environmental evolution can be quantitatively analyzed, thereby improving the scientific value of the data. In addition, the design of the database allows regular updates, so that the data can reflect the latest research results and geological environment changes, ensuring the timeliness of the data. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0019] Figure 1 is a flow chart of the method of the present invention; Figure 2 A flow chart for classifying different trust levels for the present invention; Figure 3 The figure is a flow chart for constructing the environmental evolution model of the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Embodiment 1, as Figure 1 , Figure 2 As shown, the present invention provides a method for constructing a geological survey database for paleo-ocean environment evolution, comprising the following steps: Step 1: Collect multi-source data from geological structure, sediment, paleontology, geophysics and other aspects, and pre-process the collected multi-source data, including data cleaning, format conversion and standardization, solve problems such as data duplication, mismatch, and inconsistent format, ensure data quality and consistency, clarify the relevant geological data types of paleo-ocean environment evolution, including geological structure, sediment, paleontology, and geophysical data, and collect multi-source data of geological structure, sediment, paleontology, and geophysics. The collection sources include field surveys, laboratory analysis, geological survey reports, scientific literature, and existing databases. Geological structure data comes from geological exploration reports, seismic exploration data, geological profiles, etc. Sediment data comes from sediment sample analysis, sedimentary phase research, sedimentation rate measurement, etc. Paleontological data comes from fossil records, paleontological community analysis, paleoecological research, etc. Geophysical data comes from geophysical exploration methods such as gravity, magnetism, electrical method, and seismic. Pre-process the collected multi-source data, including data cleaning, format conversion, and data standardization steps. Data cleaning identifies and processes missing values, identifies and deletes duplicate data, ensures the uniqueness of each data, and corrects erroneous data. Through format conversion, data from different sources are converted into a unified format for easy integration and analysis. Ensure that all data files meet the preset standards in size, type and attributes. Through data standardization, unify data units and classification standards, and name and encode standardized data to ensure data consistency and comparability. For spatial data and time series data in the preprocessed data, perform spatial and temporal overlays respectively to ensure spatial consistency of spatial data between different layers, and ensure temporal consistency of different data sets. Integrate data sets from different sources into a unified data warehouse and establish relationships between data. Associate spatial data with non-spatial data through a coordinate system to form a comprehensive data set that includes geological structure, sediments, paleontology, and geophysics. Create metadata for the formed comprehensive data set to record detailed data, including the title, author, creation date, data source, data type, data range, and data accuracy of the data set. Step 2: Analyze the reliability and accuracy of the preprocessed multi-source data, and divide the collected data into different trust levels. High-trust level data can be used as the main basis for analysis, while low-trust level data can be used for auxiliary analysis. Traverse the preprocessed multi-source data, analyze each data source, and evaluate the reliability and accuracy of the data. For data reliability, perform data verification, compare data from different sources, check the consistency and accuracy of the data, and check whether the data is complete, including whether the necessary fields, records and related information are complete. Evaluate the degree and impact of data missing, reasonably process or mark the missing data, and check the data. Collection time and update frequency to ensure the timeliness and freshness of data. Mark or remove outdated or invalid data. Analyze data accuracy, including measurement accuracy, classification accuracy and time accuracy. Measurement accuracy is for data obtained through experiments or instruments, and its measurement accuracy and error range are evaluated. Classification accuracy is for classified data, and its classification accuracy and consistency are evaluated. Time accuracy is for time series data, and its timestamp accuracy and consistency are evaluated. According to the reliability and accuracy analysis of the data, the error range of the data is estimated, and the trust evaluation indicators of multi-source data and the benchmark score values ​​of the trust evaluation indicators are determined. Each trust evaluation indicator is scored and divided. The data reliability evaluation index and data accuracy evaluation index are calculated separately. The trust evaluation indicators of data reliability are data integrity, data consistency, data accuracy, data timeliness and data source credibility. The trust evaluation indicators of data accuracy are measurement accuracy, classification accuracy and time accuracy. A trust evaluation model is constructed based on the scoring results of each trust evaluation indicator to quantitatively evaluate the data. The trust evaluation coefficient is calculated for each data set based on the constructed trust evaluation model and the scores of the trust evaluation indicators. The data reliability evaluation index and the data accuracy evaluation index are then combined to calculate the trust evaluation coefficient. The data is then divided into different trust levels according to the trust evaluation coefficient, namely low trust level, medium trust level and trust level. The trust level and high trust level are matched to the corresponding trust assessment threshold for each trust level. Each data set is divided into the corresponding trust level according to its trust assessment coefficient, and annotated to explain its trust level and assessment basis. A data integration strategy is formulated, and a usage guide is established for each trust level data to guide how to use it for auxiliary analysis. For high trust level data, it is used as the main basis for analysis to build models, make predictions and support decisions. For medium trust level data, it is used for auxiliary analysis to provide additional information or verify the accuracy of high trust level data. For low trust level data, it is only used for reference or as background information and should not be used in key analysis. Furthermore, the calculation formula of the data reliability evaluation index is: ; Among them, RI is the data reliability evaluation index, is the score of the dataset on the i-th trust evaluation indicator, is the benchmark score value of the i-th trust evaluation indicator, is the full score of the i-th trust evaluation indicator, is the consistency score of the i-th trust evaluation indicator, In order to adjust the parameters and control the influence of consistency score on overall reliability, the value range of RI is , the closer the RI value is to 1, the higher the data reliability is. The gap between each trust evaluation indicator score and the benchmark score is calculated, and the gap is normalized by considering the full score of each indicator. Then, the exponential decay function of the consistency score is introduced to adjust the weight of each indicator score, and finally a comprehensive reliability evaluation index is obtained by summing and square rooting; The calculation formula of the data accuracy evaluation index is: ; Among them, AI is the data accuracy assessment index, Score the actual measured value of the dataset on the jth accuracy evaluation metric, Score the expected measurement value of the jth accuracy evaluation metric, is the benchmark accuracy ratio of the jth accuracy evaluation indicator, is the adjustment parameter of the jth accuracy evaluation index, which is used to control the weight of the result after logarithm calculation. The value range of AI is The closer the AI ​​value is to 1, the higher the data accuracy is. The ratio between the actual measurement score and the expected measurement score of each accuracy evaluation indicator is calculated and the logarithm is taken to reduce the impact of the high ratio on the overall accuracy evaluation. Then, the results of each indicator are weighted and adjusted by the benchmark accuracy ratio and adjustment parameters, and finally a comprehensive accuracy evaluation index is obtained by summing them up; Furthermore, the calculation formula of the trust evaluation coefficient is: ; Among them, TAC is the trust assessment coefficient, is the reliability evaluation index of the i-th data set, is the precision evaluation index of the jth data set, is the weight of the i-th reliability evaluation index, is the weight of the jth accuracy evaluation index, It is a parameter between 0 and 1, which is used to balance the relative importance of reliability and accuracy in the final evaluation. The value range of TAC is ,The closer the TAC value is to 1, the higher the trust level of the data; Furthermore, the multiple trust levels correspond to multiple trust assessment thresholds, wherein the trust assessment threshold includes an upper threshold and a lower threshold; Multiple trust levels and multiple trust evaluation thresholds satisfy the following relationship: Low Trust Level ; Medium Trust Level ; High trust level ; Among them, TAC is the trust assessment coefficient, is the lower threshold corresponding to the medium trust level and the upper threshold corresponding to the low trust level, is the lower threshold corresponding to the high trust level and the upper threshold corresponding to the medium trust level, , ; Step 3: Use machine learning algorithms to conduct in-depth analysis of the preprocessed data, identify the key factors of the evolution of the paleo-ocean environment, and build an environmental evolution model based on historical data to predict the evolution trend of the paleo-ocean environment; Step 4: Based on the federated database technology, the pre-processed and predicted paleo-ocean environment evolution trends are integrated to obtain a geological survey database containing spatial data and attribute data for spatial query and analysis; Step 5: Use GIS software to visualize the relevant data in the geological survey database, present the analysis results in the form of graphics and charts, and regularly collect new related data to continuously update the database.

[0022] Embodiment 2, as Figure 3 As shown, based on Example 1, the present invention provides a technical solution: Preferably, in step three, the process of constructing the environment evolution model is: The historical data of the ancient marine environment that have been preprocessed and trusted are extracted, covering different time scales, geographical regions and environmental variables. The extracted historical data of the ancient marine environment are analyzed for characteristics, and the characteristics related to the evolution of the ancient marine environment are selected, namely temperature, salinity, redox state and biological productivity characteristics, to obtain a characteristic data set. By analyzing the isotope and organic matter content indicators in the sediments, the temperature change history of the ancient ocean can be reconstructed. The change in salinity is closely related to factors such as evaporation, precipitation, and river input in the ocean. It is also affected by global factors such as glacial activity and sea level change. Changes in salinity can affect the osmotic pressure and metabolic process of marine organisms, and thus affect the evolution of the ancient marine ecosystem. The redox state refers to the equilibrium state of the redox reaction in the ancient ocean, reflecting the content and distribution of oxygen in the ocean. Changes in the redox state can affect the physiological processes of marine organisms such as respiration and photosynthesis, as well as sedimentation and element cycling in the ocean. By analyzing the content and distribution of redox-sensitive elements (such as iron, manganese, etc.) in the sediments, the redox state of the ancient ocean can be inferred. Biological productivity refers to the production of organisms in the ancient ocean through photosynthesis, chemoenzyme, etc. The amount of organic matter produced by the ancient marine ecosystem. The change of biological productivity can reflect the prosperity and decline of the ancient marine ecosystem, as well as the adaptation and evolution of marine organisms to the environment. By analyzing the organic carbon content in the sediments, biological fossils and other indicators, the biological productivity history of the ancient ocean can be reconstructed. The characteristic data set is divided into a training set and a test set. The environmental evolution model is constructed by combining the training set data with the neural network model, and the performance of the model is evaluated using the test set data to adjust the model parameters and improve the accuracy and generalization ability of the model. The evolution trend of the ancient marine environment is predicted by the trained environmental evolution model to understand the dynamic change trend of the ancient marine environment. Based on the trained environmental evolution model and the relevant data of the characteristic data set, the environmental evolution coefficient is calculated, the trend of the evolution of the ancient marine environment is analyzed, and the key environmental change nodes and trends are identified, such as temperature rise, salinity change, fluctuation of redox state, and increase or decrease of biological productivity. The results predicted by the environmental evolution model are explained, and the results of environmental change prediction are analyzed from different time scales. It is analyzed whether the trend predicted by the environmental evolution model is consistent with the known geological events and environmental changes. The environmental evolution model is adjusted according to the verification results to improve the accuracy of the prediction; Furthermore, the calculation formula of the environmental evolution coefficient is: ; Where EC is the environmental evolution coefficient, is the current value of the kth feature, where k ranges from 1 to 4, corresponding to temperature, salinity, redox state, and biological productivity, respectively. is the benchmark value of the kth feature, which is the historical average level. is the weight of the kth feature, reflecting the importance of this feature in environmental evolution, S is the current value of biological productivity, is the historical maximum value of biological productivity. and To adjust the parameters and balance the influence of different parts, the larger the EC value, the greater the degree of environmental change. If EC is a positive value, it means that the environment is evolving towards a more extreme or different state. If EC is a negative value, it means that the environmental change is small or tends to be stable. The difference between the current value and the baseline value of each feature is calculated, and the sum of squares is calculated to emphasize the features with large deviations. The difference of each feature is synthesized through the sum function and the radical formula to obtain a value that reflects the overall environmental change. The weight is introduced. , allowing different traits to have different effects according to their contribution to environmental evolution, through the exponential function Adjust the impact of biological productivity to reflect the impact of changes in biological productivity relative to historical maximum on environmental evolution; In step 4, the process of obtaining the geological survey database containing spatial data and attribute data is as follows: Identify and record all pre-processed data sources, including spatial data and attribute data, integrate the trust levels of each data set and the predicted paleo-ocean environment evolution trend results, design a federated database architecture, including local database, global database, and middleware, and define the data source integration process, build a federated database system, and configure middleware and global database at the same time to access and manage data in the local database to form a geological survey database, import the pre-processed spatial data into the local database in the geological survey database, ensure the accuracy and integrity of the spatial data, perform format conversion and coordinate system unification, import the predicted paleo-ocean environment evolution trend data as attribute data into the geological survey database, and associate the attribute data with the spatial data for spatial analysis and query, set up a spatial query function in the geological survey database, query paleo-ocean environment data based on geographic location, and set up query and analysis functions for attribute data to query the evolution trend of the paleo-ocean environment based on time scale; In step 5, the visualization process is as follows: Extract the spatial data and attribute data to be visualized from the geological survey database, convert the extracted data into data format, and import it into GIS software to ensure that the data can be correctly displayed and analyzed in GIS software. Use the mapping function of GIS software to create maps based on spatial data, overlay attribute data on the map, display the distribution and changes of data through color, symbols, and legends, display the statistical characteristics and evolution trends of attribute data, and output the visualization results in the form of graphics and charts, annotate the output results with necessary instructions and explanations to facilitate user understanding and use. According to the data update cycle, regularly collect new related data, perform quality checks and preprocessing on the newly collected data to ensure the accuracy and completeness of the data, import the new data into the geological survey database, update the existing data records, and integrate the new and existing data to ensure the consistency and completeness of the data. Re-perform visualization based on the updated database content, compare the new and old visualization results, and analyze the changes and trends of the data.

[0023] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for constructing a geological survey database for paleo-ocean environmental evolution, characterized in that: The following steps are involved: Step 1: Collect multi-source data from geological structure, sediment, paleontology, geophysics and other aspects, and pre-process the collected multi-source data; Step 2: Analyze the reliability and accuracy of the preprocessed multi-source data, and divide the collected data into different trust levels; Step 3: Use machine learning algorithms to conduct in-depth analysis of the preprocessed data, identify the key factors of the evolution of the paleo-ocean environment, and build an environmental evolution model based on historical data to predict the evolution trend of the paleo-ocean environment; Step 4: Based on the federated database technology, the pre-processed and predicted paleo-ocean environment evolution trends are integrated to obtain a geological survey database containing spatial data and attribute data; Step 5: Use GIS software to visualize the relevant data in the geological survey database and present the analysis results in the form of graphics and charts.

2. The method for constructing a geological survey database of paleo-ocean environment evolution according to claim 1, characterized in that: In step 1, the process of collecting multi-source data and preprocessing is as follows: Clarify the types of geological data related to the evolution of the ancient marine environment, including geological structure, sediments, paleontology, and geophysical data, and collect multi-source data on geological structure, sediments, paleontology, and geophysics; Preprocess the collected multi-source data, including data cleaning, format conversion, and data standardization steps; For the spatial data and time series data in the preprocessed data, spatial and temporal overlays are performed respectively to ensure the spatial consistency of spatial data between different layers and the temporal consistency of different data sets; Integrate data sets from different sources into a unified data warehouse, establish relationships between data, and associate spatial data with non-spatial data through a coordinate system to form a comprehensive data set that includes geological structures, sediments, paleontology, and geophysics; Create metadata for the resulting comprehensive dataset to record detailed information about the data, including the title, author, creation date, data source, data type, data range, and data precision of the dataset.

3. The method for constructing a geological survey database of paleo-ocean environment evolution according to claim 2, characterized in that: In step 2, the process of dividing different trust levels is as follows: Traverse the preprocessed multi-source data, perform data analysis on each data source, and evaluate the reliability and accuracy of the data; According to the reliability and accuracy analysis of the data, the error range of the data is estimated, the trust evaluation indicators of multi-source data and the benchmark score values ​​of the trust evaluation indicators are determined, and each trust evaluation indicator is scored to calculate the data reliability evaluation index and the data accuracy evaluation index respectively. Among them, the trust evaluation indicators of data reliability are data integrity, data consistency, data accuracy, data timeliness and data source credibility, and the trust evaluation indicators of data accuracy are measurement accuracy, classification accuracy and time accuracy; A trust assessment model is constructed based on the scoring results of each trust assessment indicator to quantitatively evaluate the data. The trust assessment coefficient is calculated for each data set based on the constructed trust assessment model and the scores of the trust assessment indicators, and the data reliability assessment index and data accuracy assessment index are integrated. The data is divided into different trust levels based on the trust assessment coefficient, namely low trust level, medium trust level and high trust level, and the corresponding trust assessment threshold is matched for each trust level. Each data set is divided into corresponding trust levels according to its trust assessment coefficient, and annotated to explain its trust level and assessment basis, formulate a data integration strategy, and establish a usage guide for data of each trust level.

4. The method for constructing a geological survey database of paleo-ocean environment evolution according to claim 3, characterized in that: The calculation formula of the data reliability evaluation index is: ； Among them, RI is the data reliability evaluation index, is the score of the dataset on the i-th trust evaluation indicator, is the benchmark score value of the i-th trust evaluation indicator, is the full score of the i-th trust evaluation indicator, is the consistency score of the i-th trust evaluation indicator, To adjust the parameters, the value range of RI is ,The closer the RI value is to 1, the higher the data reliability; The calculation formula of the data accuracy evaluation index is: ； Among them, AI is the data accuracy assessment index, Score the actual measured value of the dataset on the jth accuracy evaluation metric, Score the expected measurement value of the jth accuracy evaluation metric, is the benchmark accuracy ratio of the jth accuracy evaluation indicator, is the adjustment parameter of the jth accuracy evaluation index, and the value range of AI is , the closer the AI ​​value is to 1, the higher the data accuracy is.

5. The method for constructing a geological survey database of paleo-ocean environment evolution according to claim 4, characterized in that: The calculation formula of the trust evaluation coefficient is: ； Among them, TAC is the trust assessment coefficient, is the reliability evaluation index of the i-th data set, is the precision evaluation index of the jth data set, is the weight of the i-th reliability evaluation index, is the weight of the jth accuracy evaluation index, is a parameter between 0 and 1. The value range of TAC is ,The closer the TAC value is to 1, the higher the trust level of the data.

6. The method for constructing a geological survey database of paleo-ocean environment evolution according to claim 5, characterized in that: The multiple trust levels correspond to the multiple trust assessment thresholds, wherein the trust assessment thresholds include an upper threshold and a lower threshold; The multiple trust levels and the multiple trust assessment thresholds satisfy the following relationship: Low Trust Level ; Medium Trust Level ; High trust level ; Among them, TAC is the trust assessment coefficient, is the lower threshold corresponding to the medium trust level and the upper threshold corresponding to the low trust level, is the lower threshold corresponding to the high trust level and the upper threshold corresponding to the medium trust level, , .

7. The method for constructing a geological survey database of paleo-ocean environment evolution according to claim 6, characterized in that: In step 3, the construction process of the environmental evolution model is as follows: Extract the historical data of the paleo-ocean environment that have been pre-processed and trusted, covering different time scales, geographical regions and environmental variables, and perform feature analysis on the extracted historical data of the paleo-ocean environment, select the features related to the evolution of the paleo-ocean environment, namely temperature, salinity, redox state and biological productivity characteristics, and obtain the feature data set; The feature data set is divided into a training set and a test set. The training set data is combined with a neural network model to build an environmental evolution model, and the test set data is used to evaluate the performance of the model. The trained environmental evolution model is used to predict the evolution trend of the paleo-ocean environment and understand the dynamic change trend of the paleo-ocean environment. Based on the trained environmental evolution model and relevant data of the characteristic data set, the environmental evolution coefficient is calculated, the trend of paleo-ocean environmental evolution is analyzed, and key environmental change nodes and trends are identified; Interpret the results predicted by the environmental evolution model, analyze the results of environmental change predictions at different time scales, analyze whether the trends predicted by the environmental evolution model are consistent with known geological events and environmental changes, and adjust the environmental evolution model based on the verification results.

8. The method for constructing a geological survey database of paleo-ocean environment evolution according to claim 7, characterized in that: The calculation formula of the environmental evolution coefficient is: ； Among them, EC is the environmental evolution coefficient, is the current value of the kth feature, where k ranges from 1 to 4, corresponding to temperature, salinity, redox state, and biological productivity, respectively. is the reference value of the kth feature, is the weight of the kth feature, S is the current value of biological productivity, is the historical maximum value of biological productivity. and For parameter adjustment, the larger the EC value, the greater the degree of environmental change.

9. The method for constructing a geological survey database of paleo-ocean environment evolution according to claim 8, characterized in that: In step 4, the process of acquiring the geological survey database containing spatial data and attribute data is as follows: Identify and record all pre-processed data sources, including spatial data and attribute data, and integrate the confidence level of each data set and the predicted paleo-ocean environment evolution trend results; Design the federated database architecture, including local database, global database, and middleware, and define the integration process of data sources, build a federated database system, and configure the middleware and global database to form a geological survey database; Import the preprocessed spatial data into the local database in the geological survey database, convert the format and unify the coordinate system, import the predicted paleo-ocean environment evolution trend data into the geological survey database as attribute data, and associate the attribute data with the spatial data; A spatial query function is set up in the geological survey database to query paleo-ocean environment data based on geographic location, and a query and analysis function for attribute data is set up to query the evolution trend of the paleo-ocean environment based on time scale.

10. The method for constructing a geological survey database of paleo-ocean environment evolution according to claim 9, characterized in that: In step 5, the process of visualization is as follows: Extract the spatial data and attribute data to be visualized from the geological survey database, convert the extracted data into data format, and import it into the GIS software; Use the mapping function of GIS software to create maps based on spatial data, overlay attribute data on the map, display the distribution and changes of data through colors, symbols, and legends, display the statistical characteristics and evolution trends of attribute data, and output the visualization results in the form of graphics and charts; According to the data update cycle, new related data is collected regularly, and the newly collected data is quality checked and preprocessed; Import new data into the geological survey database, update existing data records, and integrate new and existing data. Re-visualize based on the updated database content, compare old and new visualization results, and analyze data changes and trends.

Images