Geological survey whole-process data aggregation system for ancient marine environment evolution

Abstract

The invention discloses a geological survey whole-process data aggregation system for ancient marine environment evolution, and relates to the technical field of marine geological survey. The data management platform is in communication connection with a data acquisition module, a data preprocessing module, a data integration module, a data space-time interpolation module, a data quality evaluation module, an evolution analysis module and a result display module, and all the modules are in electric signal connection. By integrating deep-sea sediment, seabed rock, marine organism fossil and ocean surface environment parameter multi-source data, the data integration and processing capacity is improved, the evolution of the ancient ocean environment is simulated and predicted by utilizing the constructed random forest model, a comprehensive and deep analysis result is provided, and the analysis efficiency is improved. Not only is the evolution rule and trend of the ancient marine environment disclosed, but also a scientific basis can be provided for future environmental protection and resource management.

Description

Technical Field

[0001] The present invention relates to the technical field of marine geological survey, and in particular to a full-process data aggregation system for geological survey of paleo-ocean environmental evolution. Background Art

[0002] With the continuous deepening of global climate change research, unstable climate and environmental systems have an important impact on the future survival and development of mankind. In order to scientifically predict future environmental changes, it is particularly important to deeply explore the laws of environmental changes in different time scales, reveal their causal mechanisms, and restore and reconstruct environmental evolution in the geological history. As a discipline that studies the changes in ancient climate and ancient ocean environment in the geological history, paleoceanography has important research results for understanding the changes in the earth's environment, revealing the internal connections between various environmental systems, and predicting future environmental evolution trends. Paleooceanography combines the research results of multiple disciplines such as marine geology, physical oceanography, chemical oceanography and biological oceanography to jointly promote the study of the evolution of the ancient ocean environment.

[0003] In the existing technology, the marine environment is complex and changeable, and due to the diverse data sources, it is difficult for the data to cover all key areas or time periods, resulting in data missing problems when predicting the evolution of the paleo-ocean environment. Therefore, how to expand the data coverage and time scale and improve the comprehensiveness and accuracy of the prediction results is the problem we need to solve. To this end, a full-process data aggregation system for geological surveys of paleo-ocean environmental evolution is proposed. Summary of the invention

[0004] The purpose of the present invention is to provide a full-process data aggregation system for geological survey 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 full-process data aggregation system for geological survey of paleo-ocean environment evolution includes a data management platform, wherein the data management platform is communicatively connected with a data acquisition module, a data preprocessing module, a data integration module, a data spatiotemporal interpolation module, a data quality assessment module, an evolution analysis module and a result display module, wherein the modules are connected by electrical signals; The data acquisition module is used to collect different types of original paleo-ocean environment data, including deep-sea sediments, seafloor rocks, and marine fossils, and to obtain marine environment information using remote sensing data and historical documents, ensuring the diversity and richness of the data, and providing a basis for subsequent data analysis and prediction; The data preprocessing module is used to preprocess the collected original paleo-ocean environment data, including data cleaning, data conversion and data standardization operations, and integrate the preprocessed paleo-ocean environment data to provide high-quality data for subsequent data analysis; The data spatiotemporal interpolation module uses a spatiotemporal interpolation algorithm to fill in the areas and time periods where data is missing, thereby expanding the data coverage and time scale and improving the integrity and continuity of the data; The data quality assessment module is used to check and evaluate the quality of the integrated and interpolated data, and to classify the data quality levels to ensure the accuracy and reliability of the data, improve the data quality, and provide strong support for subsequent prediction and analysis; The evolution analysis module uses machine learning technology to conduct in-depth analysis of the integrated data, combines historical data and analysis results, builds an evolution simulation model, simulates the evolution laws and trends of the ancient marine environment, and provides support for decision-making; The results display module is used to integrate the evolution analysis results into an analysis report and display it to the user intuitively, collect user feedback, enhance the usability and interactivity of the system, promote user understanding and application of prediction results, and continuously optimize system performance based on feedback.

[0006] A further improvement of the technical solution of the present invention is that in the data acquisition module, the process of acquiring the original paleo-ocean environment data is as follows: Clarify the data collection objectives of the geological survey of paleo-ocean environment evolution, including deep-sea sediments, seafloor rocks and marine fossils, and define the geographical scope, time span and data resolution requirements for data collection to obtain original paleo-ocean environment data; For deep-sea sediments and seafloor rocks, deep-sea sediment samples and seafloor rock samples are obtained through ocean drilling and submersible sampling. For marine fossils, marine fossils are collected during marine geological surveys, and the types, forms and distribution of fossils are analyzed to understand the ecology and evolutionary history of ancient marine organisms. Using satellite remote sensing technology, we can obtain environmental parameters such as ocean surface temperature, salinity, sea level, and chlorophyll content, analyze geographical information of seabed topography and landforms, and obtain text descriptions and image data of ancient marine environments by consulting historical documents such as logbooks, marine exploration reports, and geological survey reports; The collected data is recorded and marked in detail, including the collection location, time, conditions and methods, to facilitate subsequent data management and analysis. The collected data is digitally stored and transferred to the data management platform for backup to prevent data loss.

[0007] A further improvement of the technical solution of the present invention is that in the data preprocessing module, the process of preprocessing the original paleo-ocean environment data is: Preprocess the collected raw paleo-ocean environment data, including data cleaning, data conversion and data standardization; Use label encoding to convert non-numeric data into numeric data, perform dimensionality reduction, reduce the dimension of the data, add timestamps to time series data, and add coordinate information to geographic data; Identify and distinguish data from different data sources, use data source metadata and data source connection information to identify data sources, and use data source connection strings and data source drivers to connect to data sources, so that data can be transferred from data sources to the data management platform; Use Python's pandas library method to convert data from different data sources into a unified format, and use Python's pandas library's concat method to integrate the converted data into the data warehouse.

[0008] A further improvement of the technical solution of the present invention is that in the data spatiotemporal interpolation module, the process of filling using the spatiotemporal interpolation algorithm is as follows: Organize the known data points, including spatial location and time information, analyze the spatiotemporal correlation between the known data points, that is, the interdependence between the data points in space and time, and determine the factors and weights that need to be considered in the interpolation algorithm based on the spatiotemporal correlation; Combined with the spatiotemporal Kriging interpolation algorithm, the data values ​​of unknown spatiotemporal locations are determined by calculating the variogram and covariance function according to the spatiotemporal distribution characteristics of known data points; Verify the interpolation results, compare them with the nearby actual observation points, and evaluate the accuracy of the interpolation; The interpolation results are output as continuous data sets and integrated back into the original data sets to form a complete data set for subsequent data analysis and application, and the interpolated data are stored in the data warehouse for further analysis.

[0009] A further improvement of the technical solution of the present invention is that the calculation formula of the variation function is: ; in, is the variance function value at the lag distance h, where h is the lag distance, For location The observed value at For location Add the observed value at the lag distance h, represents the logarithm of data with a lag distance of h; The calculation formula of the covariance function is: ; in, is the covariance function value at the lag distance h, is the average of all observations.

[0010] A further improvement of the technical solution of the present invention is that in the data quality assessment module, the data quality level classification process is as follows: Define data quality evaluation indicators, including completeness, accuracy, consistency, timeliness, and interpretability, and determine the standard score for each evaluation indicator; Based on the determined data quality assessment indicators, the quality of the integrated and interpolated data is checked and evaluated; Combine the standard scoring values ​​of each evaluation indicator, calculate the scoring value of each evaluation indicator, comprehensively analyze and calculate the quality evaluation coefficient, evaluate the quality status of the data, and divide the data into different quality levels according to the quality evaluation coefficient, namely poor quality level, general quality level, good quality level and excellent quality level, and match the corresponding evaluation threshold for each quality level; Record the quality assessment results of each dataset and generate a data quality report including assessment results, problem descriptions, and recommendations.

[0011] A further improvement of the technical solution of the present invention is that the calculation formula of the quality assessment coefficient is: ; Where Q is the data quality assessment coefficient, is the standard score value of the jth evaluation indicator, The value range is 0 to 10. is the benchmark value of the jth evaluation indicator, indicating the minimum acceptable score of the indicator. k is a constant used to adjust the influence of the exponential function on the score. The value range of Q is 0 to 1. The closer the value is to 1, the better the data quality.

[0012] A further improvement of the technical solution of the present invention is that: the multiple quality levels correspond to multiple evaluation thresholds, wherein the evaluation thresholds include an upper threshold and a lower threshold; The multiple quality levels and the multiple evaluation thresholds satisfy the following relationship: Poor quality grade ; General quality grade ; Good quality grade ; Excellent quality grade ; Where Q is the quality assessment coefficient, is the lower threshold corresponding to the general quality level and the upper threshold corresponding to the poor quality level, is the lower threshold corresponding to the good quality level and the upper threshold corresponding to the general quality level, is the lower threshold corresponding to the excellent quality level and the upper threshold corresponding to the good quality level, , , .

[0013] A further improvement of the technical solution of the present invention is that in the evolution analysis module, the construction process of the evolution simulation model is: Integrate the collected data on deep-sea sediments, seafloor rocks and marine fossils, as well as environmental parameter data on ocean surface temperature, salinity, sea level, and chlorophyll content to form a dataset on the evolution of the ancient marine environment; The features related to the evolution of the ancient ocean environment are extracted from the ancient ocean environment evolution dataset. For deep-sea sediments, the sediment type, sedimentation rate and sediment composition characteristics are extracted. The sediment type characteristics indicate the type of deep-sea sediments (such as clay, silt, sand, gravel, etc.) and their distribution, reflecting the sedimentary environment and material source of the ancient ocean. The sedimentation rate characteristics indicate the accumulation rate of sediments on the seabed, reflecting the productivity, material circulation and sedimentation process of the ancient ocean. The sediment composition characteristics indicate the content and proportion of particulate matter, organic matter and chemical substances in the sediments, revealing the biological activities, redox conditions and climate change of the ancient ocean. For seabed rocks, the rock type, rock age and rock composition characteristics are extracted. The rock type characteristics indicate the type of seabed rocks (such as basalt, granite, sedimentary rocks, etc.) and their distribution, reflecting the tectonic background and crustal evolution of the ancient ocean. The seabed rock age determined by radioactive isotope dating and other methods reveals the geological history and time frame of the ancient ocean. The rock composition characteristics indicate the mineral composition, chemical composition and isotope composition in the rock, reflecting the ancient Geochemical processes and material cycles of the ocean. For marine fossils, the types, morphology and distribution characteristics of fossils are extracted. The types and quantities of marine fossils are represented by the types of fossils, reflecting the biodiversity and community structure of the ancient ocean. The morphology of fossils represents the shape and size of fossils, revealing the life habits, ecological niche and evolutionary trends of ancient marine organisms. The distribution characteristics of fossils represent the distribution and stratigraphic position of fossils in sediments, reflecting the sedimentary environment and biogeographic distribution of the ancient ocean. For ocean surface environmental parameters, the temperature, salinity, sea level and chlorophyll content characteristics are extracted. The temperature characteristics represent the temperature record of the ocean surface, reflecting the heat balance, climate change and ocean circulation of the ancient ocean. The salinity characteristics represent the salinity changes of the ocean surface, revealing the hydrological cycle, freshwater input and evaporation of the ancient ocean. The sea level characteristics represent the changes in sea level, reflecting the glacial activity, crustal movement and sea level rise and fall of the ancient ocean. The chlorophyll content characteristics indicate that chlorophyll content is an important indicator of marine productivity, reflecting the biological activity, nutrient content and light conditions of the ancient ocean. Based on the extracted paleo-ocean environment evolution characteristics and historical data, an evolution simulation model was constructed through a random forest model to predict and analyze the future evolution of the paleo-ocean environment; Combining the trained evolution simulation model with the associated data of paleo-ocean environment evolution characteristics, the evolution evaluation coefficient is calculated, the evolution law of the paleo-ocean environment is analyzed, and the evolution trends and key turning points are identified.

[0014] A further improvement of the technical solution of the present invention is that the calculation formula of the evolution evaluation coefficient is: ; Among them, E is the evolution assessment coefficient, which is used to measure the overall trend and key turning points of the evolution of the ancient marine environment, M is the number of features, is the weight of the u-th feature, reflecting the importance of this feature in the evolution assessment, is the predicted value of the u-th feature, obtained by the random forest model, is the actual value of the u-th feature, It is the benchmark value used to adjust the impact of the difference between the predicted value and the actual value. The smaller the value of E is, the closer the predicted value is to the actual value, and the more stable the evolution evaluation coefficient is.

[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 full-process data aggregation system for geological survey of paleo-ocean environment evolution. By integrating multi-source data of deep-sea sediments, seabed rocks, marine fossils and ocean surface environmental parameters, the data integration and processing capabilities are improved, and the evolution of the paleo-ocean environment is simulated and predicted using a constructed random forest model, providing comprehensive and in-depth analysis results, which not only helps to reveal the evolution laws and trends of the paleo-ocean environment, but also provides a scientific basis for future environmental protection and resource management.

[0016] The present invention provides a full-process data aggregation system for geological survey of paleo-ocean environment evolution. By integrating multi-source data of deep-sea sediments, seabed rocks, marine fossils and ocean surface environmental parameters, the data integration and processing capabilities are improved, and a random forest model is used to simulate and predict the evolution of the paleo-ocean environment, providing comprehensive and in-depth analysis results, which not only helps to reveal the evolution laws and trends of the paleo-ocean environment, but also provides a scientific basis for future environmental protection and resource management.

[0017] The present invention provides a full-process data aggregation system for geological survey of paleo-ocean environmental evolution. Through a data management platform, centralized storage, efficient retrieval and convenient sharing of data are realized, data quality is evaluated, quality evaluation coefficients are automatically calculated, and data quality levels are divided according to the evaluation results. This not only improves the efficiency of data management, but also reduces the possibility of human errors, ensuring the reliability and stability 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 It is a module structure diagram of the present invention; Figure 2 This is a flow chart of filling using a spatiotemporal interpolation algorithm in the present invention; Figure 3 The flowchart of dividing the data quality level of the present invention; Figure 4 The flowchart for constructing the evolution simulation 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 3 As shown, the present invention provides a full-process data aggregation system for geological survey of paleo-ocean environment evolution, including a data management platform, wherein the data management platform is communicatively connected with a data acquisition module, a data preprocessing module, a data integration module, a data spatiotemporal interpolation module, a data quality assessment module, an evolution analysis module and a result display module, wherein the modules are connected by electrical signals; The data acquisition module is used to collect different types of original paleo-ocean environment data, including deep-sea sediments, seabed rocks, and marine fossils, and to obtain marine environmental information using remote sensing data and historical documents to ensure data diversity and richness, provide a basis for subsequent data analysis and prediction, and clarify the data acquisition objectives of geological surveys on paleo-ocean environment evolution, including deep-sea sediments, seabed rocks, and marine fossils, and define the geographical scope, time span, and data resolution requirements for data acquisition to obtain original paleo-ocean environment data. For deep-sea sediments and seabed rocks, deep-sea sediment samples and seabed rock samples are obtained through ocean drilling and submersible sampling. For marine fossils, samples are collected by sampling in the sea. During the ocean geological survey, marine fossils are collected, and the types, forms and distribution information of fossils are analyzed to understand the ecology and evolutionary history of ancient marine organisms. Satellite remote sensing technology is used to obtain environmental parameters such as ocean surface temperature, salinity, sea level height, and chlorophyll content. Geographic information of seabed topography and landforms is analyzed. By consulting historical documents such as logbooks, ocean exploration reports, geological survey reports, etc., text descriptions and image data of ancient marine environments are obtained. The collected data are recorded and marked in detail, including the collection location, time, conditions and methods, for subsequent data management and analysis. The collected data are digitally stored and transmitted to the data management platform for backup to prevent data loss; The data preprocessing module is used to preprocess the collected original paleo-ocean environment data, including data cleaning, data conversion and data standardization operations, and integrate the preprocessed paleo-ocean environment data to provide high-quality data for subsequent data analysis. The collected original paleo-ocean environment data is preprocessed, including data cleaning, data conversion and data standardization. Among them, data cleaning is used to identify and process missing values ​​in the data, identify outliers in the data, analyze their causes, decide whether to delete, correct or retain, check duplicate records in the data set, delete or merge duplicates, and correct obvious errors or inconsistencies. Data conversion is used to convert data into a unified format for easy processing and analysis, and perform data type conversion to ensure that the data type is correct and the data is consistent. Data standardization is used to scale data to a small, specified range, ensure that all data uses the same unit of measurement, use label encoding to convert non-numeric data to numeric data, perform dimensionality reduction to reduce the dimension of the data, add timestamps to time series data, add coordinate information to geographic data, identify and distinguish data from different data sources, use data source metadata and data source connection information to identify data sources, and use data source connection strings and data source drivers to connect data sources, so that data can be transferred from data sources to data management platforms, use Python's pandas library methods to convert data from different data sources into a unified format, and use Python's pandas library concat method to integrate the converted data into the data warehouse; The data spatiotemporal interpolation module uses the spatiotemporal interpolation algorithm to fill in the areas and time periods where data is missing, expands the data coverage and time scale, improves the integrity and continuity of the data, organizes the known data points, including spatial location and time information, analyzes the spatiotemporal correlation between known data points, that is, the mutual dependence between data points in space and time, and determines the factors and weights that need to be considered in the interpolation algorithm based on the spatiotemporal correlation. Combined with the spatiotemporal Kriging interpolation algorithm, according to the spatiotemporal distribution characteristics of known data points, the data value of the unknown spatiotemporal position is determined by calculating the variation function and covariance function, the interpolation result is verified, the interpolation result is compared with the actual observation points nearby, the accuracy of the interpolation is evaluated, the interpolation result is output as a continuous data set, integrated back into the original data set to form a complete data set for subsequent data analysis and application, and the interpolated data is stored in the data warehouse for further analysis; Furthermore, the calculation formula of the variation function is: ; in, is the variance function value at the lag distance h, where h is the lag distance, For location The observed value at For location Add the observed value at the lag distance h, represents the logarithm of data with a lag distance of h; The calculation formula of the covariance function is: ; in, is the covariance function value at the lag distance h, is the average of all observations; In space-time Kriging interpolation, considering the joint influence of space and time, the expression of space-time variation function is: ; in, and is the space-time position, is the logarithm of data at a given time and space lag distance; The data quality assessment module is used to check and evaluate the quality of the integrated and interpolated data, and divide the data into quality levels to ensure the accuracy and reliability of the data, improve the data quality, and provide strong support for subsequent predictions and analysis. It defines the evaluation indicators of data quality, including completeness, accuracy, consistency, timeliness, and interpretability, and determines the standard score value of each evaluation indicator. Based on the determined data quality evaluation indicators, the integrated and interpolated data are checked and evaluated for quality. For the completeness check, it is ensured that there are no missing values ​​or null values ​​in the data set. For the accuracy check, the accuracy of the data is verified, including whether the data is within a reasonable range and whether it complies with business rules or common sense. For the consistency check, it is ensured that the data is consistent between different sources, different times or different dimensions. Keep consistency without contradiction or conflict. For timeliness check, evaluate the timeliness of data to ensure that the data is up to date or at least within an acceptable timeliness range. For interpretability check, check whether the data is easy to understand and whether there is sufficient metadata or documentation to explain the meaning and source of the data. Combine the standard score values ​​of each evaluation indicator to calculate the score value of each evaluation indicator, comprehensively analyze and calculate the quality assessment coefficient, evaluate the quality status of the data, and divide the data into different quality levels according to the quality assessment coefficient, namely poor quality level, general quality level, good quality level and excellent quality level, match the corresponding assessment threshold for each quality level, record the quality assessment results of each data set, and generate a data quality report, including assessment results, problem description and suggestions; Furthermore, the calculation formula of the quality assessment coefficient is: ; Where Q is the data quality assessment coefficient, is the standard score value of the jth evaluation indicator, The value range is 0 to 10. is the benchmark value of the jth evaluation indicator, indicating the lowest acceptable score for the indicator. k is a constant used to adjust the influence of the exponential function on the score. The value range of Q is 0 to 1. The closer the value is to 1, the better the data quality. When all are close to 10, the value of Q will be close to 1, indicating excellent data quality. Below the benchmark The exponential part will cause the value of Q to decrease rapidly, indicating poor data quality. Normalize the score of each indicator so that the score is relative to the benchmark value. Conduct evaluation, index part Used to amplify the impact of scores below the benchmark, making the value of Q more sensitive to low scores; Furthermore, the multiple quality levels correspond to multiple evaluation thresholds, wherein the evaluation thresholds include an upper threshold and a lower threshold; Multiple quality levels and multiple evaluation thresholds satisfy the following relationship: Poor quality grade ; General quality grade ; Good quality grade ; Excellent quality grade ; Where Q is the quality assessment coefficient, is the lower threshold corresponding to the general quality level and the upper threshold corresponding to the poor quality level, is the lower threshold corresponding to the good quality level and the upper threshold corresponding to the general quality level, is the lower threshold corresponding to the excellent quality level and the upper threshold corresponding to the good quality level, , , ; The evolution analysis module uses machine learning technology to conduct in-depth analysis of the integrated data, combines historical data and analysis results, builds an evolution simulation model, simulates the evolution laws and trends of the ancient marine environment, and provides support for decision-making; The results display module is used to integrate the evolution analysis results into an analysis report and display it to users intuitively, collect user feedback, enhance the usability and interactivity of the system, promote user understanding and application of prediction results, and continuously optimize system performance based on feedback.

[0022] Embodiment 2, as Figure 4 As shown, based on Example 1, the present invention provides a technical solution: Preferably, in the evolution analysis module, the construction process of the evolution simulation model is: The collected data on deep-sea sediments, seafloor rocks and marine fossils, as well as environmental parameter data on ocean surface temperature, salinity, sea level, and chlorophyll content, are integrated to form a paleo-ocean environmental evolution dataset. Features related to paleo-ocean environmental evolution are extracted from the paleo-ocean environmental evolution dataset. For deep-sea sediments, sediment type, sedimentation rate, and sediment composition characteristics are extracted. Sediment type characteristics indicate the type of deep-sea sediments (such as clay, silt, sand, gravel, etc.) and their distribution, reflecting the sedimentary environment and material source of the paleo-ocean. Sediment rate characteristics indicate the accumulation rate of sediments on the seabed, reflecting the productivity, material circulation, and sedimentation process of the paleo-ocean. Sediment composition The composition characteristics indicate the content and proportion of particulate matter, organic matter and chemical substances in the sediments, revealing the biological activities, redox conditions and climate change of the ancient ocean. For the seabed rocks, the rock type, rock age and rock composition characteristics are extracted. The rock type characteristics indicate the type of seabed rocks (such as basalt, granite, sedimentary rock, etc.) and their distribution, reflecting the tectonic background and crustal evolution of the ancient ocean. The age of the seabed rocks determined by methods such as radioactive isotope dating reveals the geological history and time frame of the ancient ocean. The rock composition characteristics indicate the mineral composition, chemical composition and isotope composition of the rocks, reflecting the geochemical process and material cycle of the ancient ocean. For marine fossils, The fossil species, fossil morphology and fossil distribution characteristics are extracted. The fossil species characteristics indicate the types and quantities of marine fossils, reflecting the biodiversity and community structure of the ancient ocean. The fossil morphology characteristics indicate the shape and size of the fossils, revealing the life habits, ecological niche and evolutionary trends of the ancient marine organisms. The fossil distribution characteristics indicate the distribution and stratigraphic position of the fossils in the sediments, reflecting the sedimentary environment and biogeographic distribution of the ancient ocean. For the ocean surface environmental parameters, the temperature, salinity, sea level and chlorophyll content characteristics are extracted. The temperature characteristics indicate the temperature record of the ocean surface, reflecting the heat balance, climate change and ocean circulation of the ancient ocean. The salinity characteristics indicate the salinity changes on the ocean surface, revealing the ancient ocean. The characteristics of sea level height indicate the change of sea level height, reflecting the glacial activity, crustal movement and sea level rise and fall of the ancient ocean. The characteristics of chlorophyll content indicate that chlorophyll content is an important indicator of marine productivity, reflecting the biological activity, nutrient content and light conditions of the ancient ocean. Based on the extracted evolution characteristics of the ancient ocean environment and historical data, an evolution simulation model is constructed through the random forest model to predict and analyze the future evolution of the ancient ocean environment. Combined with the trained evolution simulation model and the associated data of the evolution characteristics of the ancient ocean environment, the evolution evaluation coefficient is calculated, the evolution law of the ancient ocean environment is analyzed, and the evolution trend and key turning points are identified. Furthermore, the calculation formula of the evolution evaluation coefficient is: ; Among them, E is the evolution assessment coefficient, which is used to measure the overall trend and key turning points of the evolution of the ancient marine environment, M is the number of features, is the weight of the u-th feature, reflecting the importance of this feature in the evolution assessment, is the predicted value of the u-th feature, obtained by the random forest model, is the actual value of the u-th feature, It is the benchmark value used to adjust the impact of the difference between the predicted value and the actual value. The smaller the value of E is, the closer the predicted value is to the actual value, and the more stable the evolution evaluation coefficient is. near When , the exponential term is close to 1 and the E value is small, indicating that the evolution trend is relatively stable. and When the difference is large, the exponential term increases rapidly and the E value increases, indicating that the evolution trend is unstable or there is a key turning point. The exponential function It is used to amplify the difference between the predicted value and the actual value, making the evaluation coefficient more sensitive to the prediction error.

[0023] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present 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. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A full-process data aggregation system for geological survey of paleo-ocean environmental evolution, including a data management platform, characterized by: The data management platform is communicatively connected with a data acquisition module, a data preprocessing module, a data integration module, a data spatiotemporal interpolation module, a data quality assessment module, an evolution analysis module and an achievement display module, wherein the modules are connected by electrical signals; The data acquisition module is used to collect different types of original paleo-ocean environment data, including deep-sea sediments, seafloor rocks, and marine fossils, and to obtain marine environment information using remote sensing data and historical documents; The data preprocessing module is used to preprocess the collected original paleo-ocean environment data and integrate the preprocessed paleo-ocean environment data; The data spatiotemporal interpolation module uses a spatiotemporal interpolation algorithm to fill in the areas and time periods where data is missing, thereby expanding the data coverage and time scale; The data quality assessment module is used to check and assess the quality of the integrated and interpolated data, and to classify the quality level of the data; The evolution analysis module uses machine learning technology to conduct in-depth analysis of the integrated data, combines historical data and analysis results, builds an evolution simulation model, and simulates the evolution laws and trends of the ancient marine environment; The result display module is used to integrate the evolution analysis results into an analysis report and display it to the user intuitively.

2. The full-process data aggregation system for geological survey of paleo-ocean environment evolution according to claim 1 is characterized by: In the data acquisition module, the process of acquiring the original paleo-ocean environment data is as follows: Clarify the data collection objectives of the geological survey of paleo-ocean environment evolution, including deep-sea sediments, seafloor rocks and marine fossils, and define the geographical scope, time span and data resolution requirements for data collection to obtain original paleo-ocean environment data; For deep-sea sediments and seafloor rocks, deep-sea sediment samples and seafloor rock samples are obtained through ocean drilling and submersible sampling. For marine fossils, marine fossils are collected during marine geological surveys and the types, forms and distribution information of the fossils are analyzed; Using satellite remote sensing technology, we can obtain environmental parameters such as ocean surface temperature, salinity, sea level, and chlorophyll content, analyze geographical information on seabed topography and landforms, and obtain text descriptions and image data of ancient marine environments by consulting historical documents; The collected data are recorded and marked in detail, including the collection location, time, conditions and methods, and the collected data are digitally stored and transmitted to the data management platform for backup.

3. The full-process data aggregation system for geological survey of paleo-ocean environment evolution according to claim 2 is characterized by: In the data preprocessing module, the process of preprocessing the original paleo-ocean environment data is as follows: Preprocess the collected raw paleo-ocean environment data, including data cleaning, data conversion and data standardization; Use label encoding to convert non-numeric data into numeric data, perform dimensionality reduction, reduce the dimension of the data, add timestamps to time series data, and add coordinate information to geographic data; Identify and distinguish data from different data sources, use data source metadata and data source connection information to identify data sources, and use data source connection strings and data source drivers to connect to data sources, so that data can be transferred from data sources to the data management platform; Use Python's pandas library method to convert data from different data sources into a unified format, and use Python's pandas library's concat method to integrate the converted data into the data warehouse.

4. The full-process data aggregation system for geological survey of paleo-ocean environment evolution according to claim 3 is characterized by: In the data space-time interpolation module, the process of filling using the space-time interpolation algorithm is as follows: Organize known data points, including spatial location and time information, and analyze the spatiotemporal correlation between known data points, that is, the interdependence between data points in space and time; Combined with the spatiotemporal Kriging interpolation algorithm, the data values ​​of unknown spatiotemporal locations are determined by calculating the variogram and covariance function according to the spatiotemporal distribution characteristics of known data points; Verify the interpolation results, compare them with the nearby actual observation points, and evaluate the accuracy of the interpolation; The interpolation results are output as continuous data sets, integrated back into the original data sets to form a complete data set, and the interpolated data are stored in the data warehouse.

5. The full-process data aggregation system for geological survey of paleo-ocean environment evolution according to claim 4 is characterized by: The calculation formula of the variation function is: ； in, is the variance function value at the lag distance h, where h is the lag distance, For location The observed value at For location Add the observed value at the lag distance h, represents the logarithm of data with a lag distance of h; The calculation formula of the covariance function is: ； in, is the covariance function value at the lag distance h, is the average of all observations.

6. The full-process data aggregation system for geological survey of paleo-ocean environment evolution according to claim 5 is characterized by: In the data quality assessment module, the data quality level classification process is as follows: Define data quality evaluation indicators, including completeness, accuracy, consistency, timeliness, and interpretability, and determine the standard score for each evaluation indicator; Based on the determined data quality assessment indicators, the quality of the integrated and interpolated data is checked and evaluated; Combine the standard scoring values ​​of each evaluation indicator, calculate the scoring value of each evaluation indicator, comprehensively analyze and calculate the quality evaluation coefficient, evaluate the quality status of the data, and divide the data into different quality levels according to the quality evaluation coefficient, namely poor quality level, general quality level, good quality level and excellent quality level, and match the corresponding evaluation threshold for each quality level; Record the quality assessment results of each dataset and generate a data quality report including assessment results, problem descriptions, and recommendations.

7. The full-process data aggregation system for geological survey of paleo-ocean environment evolution according to claim 6 is characterized by: The calculation formula of the quality assessment coefficient is: ； Where Q is the data quality assessment coefficient, is the standard score value of the jth evaluation indicator, The value range is 0 to 10. is the benchmark value of the jth evaluation indicator, k is a constant used to adjust the influence of the exponential function on the score, and the value range of Q is 0 to 1. The closer the value is to 1, the better the data quality.

8. The full-process data aggregation system for geological survey of paleo-ocean environment evolution according to claim 7 is characterized by: The multiple quality levels correspond to the multiple evaluation thresholds, wherein the evaluation thresholds include an upper threshold and a lower threshold; The multiple quality levels and the multiple evaluation thresholds satisfy the following relationship: Poor quality grade ; General quality grade ; Good quality grade ; Excellent quality grade ; Where Q is the quality assessment coefficient, is the lower threshold corresponding to the general quality level and the upper threshold corresponding to the poor quality level, is the lower threshold corresponding to the good quality level and the upper threshold corresponding to the general quality level, is the lower threshold corresponding to the excellent quality level and the upper threshold corresponding to the good quality level, , , .

9. The full-process data aggregation system for geological survey of paleo-ocean environment evolution according to claim 8 is characterized by: In the evolution analysis module, the construction process of the evolution simulation model is: Integrate the collected data on deep-sea sediments, seafloor rocks and marine fossils, as well as environmental parameter data on ocean surface temperature, salinity, sea level, and chlorophyll content to form a dataset on the evolution of the ancient marine environment; Extract features related to the evolution of the paleo-ocean environment from the paleo-ocean environment evolution dataset. For deep-sea sediments, extract sediment type, sedimentation rate, and sediment composition characteristics; for seafloor rocks, extract rock type, rock age, and rock composition characteristics; for marine fossils, extract fossil type, fossil morphology, and fossil distribution characteristics; for ocean surface environmental parameters, extract temperature, salinity, sea level, and chlorophyll content characteristics; Based on the extracted paleo-ocean environment evolution characteristics and historical data, an evolution simulation model was constructed through a random forest model to predict and analyze the future evolution of the paleo-ocean environment; Combining the trained evolution simulation model with the associated data of paleo-ocean environment evolution characteristics, the evolution evaluation coefficient is calculated, the evolution law of the paleo-ocean environment is analyzed, and the evolution trends and key turning points are identified.

10. The full-process data aggregation system for geological survey of paleo-ocean environment evolution according to claim 9 is characterized by: The calculation formula of the evolution evaluation coefficient is: ； Among them, E is the evolution assessment coefficient, which is used to measure the overall trend and key turning points of the evolution of the ancient marine environment, M is the number of features, is the weight of the u-th feature, is the predicted value of the u-th feature, obtained by the random forest model, is the actual value of the u-th feature, The smaller the value of E is, the closer the predicted value is to the actual value, and the more stable the evolution evaluation coefficient is.

Images