A basin glacier mass balance analysis method and system based on big data

Abstract

The present invention relates to the technical field of glacier research, and discloses a basin glacier material balance analysis method and system based on big data. Remote sensing images, ground observations, and meteorological data of the glacier basin are collected, and multi-source data are standardized and integrated. A random forest model is constructed to analyze the correlation between glacier changes and climate factors, and to determine the key driving factors. The long short-term memory network is further used to predict the dynamic response of glacier materials, and highly sensitive climate factors are determined through sensitivity analysis to optimize the prediction model. The present invention also establishes a dynamic response database for long-term monitoring, and sets up an automatic early warning mechanism to assess the risk of abnormal changes. This method realizes the precise analysis and prediction of the interaction between glacier changes and climate factors, and provides an effective tool for glacier change research and environmental risk assessment.

Description

Technical Field

[0001] The present invention relates to the technical field of glacier research, and in particular to a basin glacier material balance analysis method and system based on big data. Background Art

[0002] Glaciers, as a crucial component of Earth's climate system, play a crucial role in indicative of global water resources, ecological balance, and climate change. Their dynamic changes not only reflect the evolving trends of the natural environment but also directly impact water security and ecological stability in downstream areas. Therefore, studying glacier response mechanisms is crucial. However, current research methods rely heavily on traditional observational techniques and simple statistical models, which struggle to fully capture the complexity of glacier changes and the impact of multiple coupled factors. This significantly limits prediction accuracy and comprehensive assessment capabilities.

[0003] The field of glacier research faces significant technical challenges in existing technologies. The primary challenge is effectively integrating observational data from glacier basins with multidimensional environmental parameters to form a complete dataset that reflects the true environmental characteristics. Due to the fragmented nature of data sources and the complex dimensions, insufficient data integration directly leads to a lack of in-depth understanding of the drivers of glacier change when constructing models. This lack of understanding, in turn, makes it extremely difficult to construct predictive models that accurately simulate the dynamic response of glacier materials. This is especially true when faced with the complex interactions of climatic factors, as models often fail to accurately reveal the sensitivity of glaciers to environmental changes.

[0004] Therefore, how to build a prediction model based on the fusion of multi-source data that can accurately simulate the dynamic response of glacial materials and analyze their sensitivity to climate factors has become a key issue that needs to be overcome in current research. Summary of the Invention

[0005] The present invention provides a basin glacier material balance analysis method and system based on big data to accurately simulate the dynamics of glaciers.

[0006] In the first aspect, in order to solve the above technical problems, the present invention provides a basin glacier mass balance analysis method based on big data, comprising:

[0007] Obtain the original dataset of glaciers and obtain the initial dataset in a unified format;

[0008] Based on the initial data set, a comprehensive data set, a set of key driving factors, prediction results of simulated glacier material dynamic responses, and sensitivity distribution characteristics are obtained in sequence;

[0009] Obtain intuitive analysis results based on the prediction results, build a dynamic response database, regularly update the prediction results, and obtain long-term monitoring data;

[0010] Based on the long-term monitoring data, if it is detected that the change amplitude in one time period exceeds the preset amplitude threshold, the potential environmental parameter abnormal point is determined and a corresponding risk assessment report is generated.

[0011] Preferably, the comprehensive dataset, the key driving factor set, the prediction results of the simulated glacier material dynamic response, and the sensitivity distribution characteristics are obtained in sequence according to the initial dataset, including:

[0012] The initial data set is subjected to spatiotemporal alignment and feature extraction by data fusion technology, and data dimension reduction and integration are performed by weighted average method and principal component analysis method to obtain a fused comprehensive data set;

[0013] Based on the glacier changes and climate factors in the comprehensive dataset, a random forest model based on machine learning is constructed, and the set of key driving factors is determined through model training and feature importance ranking;

[0014] Based on the set of key driving factors and the material dynamic characteristics of glacier changes, a prediction model based on a long short-term memory network is constructed to obtain the prediction results of the simulated glacier material dynamic response;

[0015] According to the prediction results, a disturbance test is performed on the prediction model, the influence weight of the climate factor on the glacier change is calculated, and the sensitivity distribution characteristics are determined.

[0016] Preferably, the step of acquiring the original dataset of the glacier and obtaining an initial dataset in a unified format includes:

[0017] Obtaining raw data covering glacier changes, climate factors, and environmental parameters from remote sensing images, ground observations, and meteorological data platforms, and performing preliminary format adjustments on the raw data to obtain a preliminary organized data set;

[0018] Based on the initially collated data set, image processing software is used to uniformly adjust the resolution of the remote sensing images, and the sampling frequencies of the ground observations and the meteorological data platform are aligned to obtain an intermediate data set with consistent resolution;

[0019] Standardize the intermediate data set, remove outliers and missing values ​​using a data cleaning tool, and if missing values ​​in the intermediate data set exceed a preset missing threshold, fill them in using an interpolation method to obtain a cleaned, standardized data set;

[0020] Based on the standard dataset, data integration tools are used to merge data from different sources in a unified format to generate an initial dataset containing glacier changes, climate factors and environmental parameters.

[0021] Preferably, obtaining a comprehensive data set comprises:

[0022] Obtaining data source differences of the glacier changes and the climate factors in the initial dataset, and calibrating the spatial distribution and time series using a data alignment tool to obtain a calibrated aligned dataset;

[0023] Using a feature extraction tool to separate the spatial feature values ​​corresponding to the glacier changes and the temporal feature values ​​corresponding to the climate factors in the calibrated aligned dataset, and determine an extracted feature dataset;

[0024] If the eigenvalues ​​in the feature data set are unevenly distributed, balancing the spatial eigenvalues ​​and the temporal eigenvalues ​​using a weighted average tool to obtain a balanced feature data set;

[0025] According to the balanced feature data set, the principal component analysis tool is used to reduce the dimension of the feature values ​​and integrate them to obtain the final comprehensive data set.

[0026] Preferably, obtaining a set of key driving factors includes:

[0027] Obtaining correlation analysis between the glacier changes and the climate factors from the comprehensive dataset, processing missing values ​​and outliers in the comprehensive dataset using a data cleaning tool to obtain a cleaned complete dataset, and determining the variable range in the complete dataset;

[0028] Obtain variable screening and feature importance assessment through the cleaned complete data set, and use correlation calculation tools to compare the correlation coefficients between the glacier changes and the climate factors to obtain variable combinations with high correlation;

[0029] Based on the combination of variables with high correlation, a preliminary judgment of the driving factors is made, and a ranking tool is used to rank the importance of the combination of variables to obtain a ranked set of key variables.

[0030] Preferably, obtaining the prediction result of the simulated glacial material dynamic response includes:

[0031] Based on the key driving factor set and the dynamic characteristics of glacial materials, a data integration tool is used to standardize the environmental variables in the time series to obtain a sorted time series data group, and the distribution range of the time series data group is determined;

[0032] Using the sorted time series data group, a feature extraction tool is used to perform hierarchical decomposition on the time series data group to obtain separated feature units;

[0033] Determine whether the characteristic unit meets a preset characteristic threshold standard. If so, use a prediction tool to perform parameterization processing on the characteristic unit to obtain a generated prediction parameter group;

[0034] A mapping tool is used to match and integrate the forecast parameter group with the spatiotemporal distribution to obtain a final trend distribution map.

[0035] Preferably, obtaining the sensitivity distribution characteristics includes:

[0036] According to the prediction results, the input parameters are normalized using a data sorting tool to obtain a sorted parameter data set;

[0037] Determining whether the parameter data set meets a preset threshold standard, and if so, performing multiple rounds of transformation on the parameter data set to obtain a transformed disturbance parameter combination;

[0038] Associating the disturbance parameter combination with the environmental variables to obtain weight data of the climate factors;

[0039] The weight data and the change trend are integrated to obtain the final distribution feature image.

[0040] Preferably, the obtaining of intuitive analysis results includes:

[0041] Acquiring environmental variable data and climate factor data corresponding to the glacier changes from a pre-established database and performing classification processing to obtain a classified data set;

[0042] If the data set contains characteristic information of a change trend, matching the classified data set with a preset distribution characteristic template to obtain a mapped data combination;

[0043] Integrating the data combination with the visual style of the change trend to obtain rendered graphic data;

[0044] fusing the graphic data with the sensitivity distribution characteristics to obtain final chart data;

[0045] The dynamic response database is constructed, and the prediction results are regularly updated to obtain long-term monitoring data, including:

[0046] Obtaining original records related to glacier changes, combining them with historical data of the climate factors to form an initial comprehensive data set and obtain structured data grouping;

[0047] Performing feature extraction on the structured data grouping, matching the glacier change with a factor-sensitive characteristic value, marking the data grouping as highly sensitive data if the characteristic value exceeds a preset characteristic threshold, and determining correlation characteristics with a dynamic response;

[0048] Integrating the highly sensitive data with the prediction results to generate an updated version of a dynamic response database, and regularly comparing the interaction characteristics in the dynamic response database to obtain the latest trend tracking records;

[0049] The trend tracking records are integrated with the target data of long-term monitoring to generate a distribution chart reflecting the relationship between glacier changes and climate factors.

[0050] Preferably, the long-term monitoring data is used to determine potential environmental parameter anomalies and generate a corresponding risk assessment report, if it is detected that the change amplitude within a time period exceeds a preset amplitude threshold. The process includes:

[0051] Obtain real-time records of the change amplitude during the monitoring period. If the change amplitude exceeds a preset change threshold, an automatic early warning mechanism is triggered to obtain a preliminary abnormal fluctuation indicator;

[0052] Matching the abnormal fluctuation identification with the records of historical environmental parameters, mining the correlation characteristics of the historical environmental parameters, and determining the distribution of potential abnormal points;

[0053] Perform a comprehensive comparison of the distribution of the abnormal points and the correlation characteristics of the historical environmental parameters to obtain the corresponding risk level and determine the distribution range of the high-risk area;

[0054] The distribution range of the high-risk area is integrated with the abnormal fluctuation mark to generate a detailed report including the risk level and the distribution of the abnormal points.

[0055] In a second aspect, the present invention provides a basin glacier material balance analysis system based on big data, comprising:

[0056] The first acquisition module is used to obtain the original dataset of the glacier and obtain the initial dataset in a unified format;

[0057] A second acquisition module is used to sequentially obtain a comprehensive data set, a set of key driving factors, a prediction result of a simulated glacier material dynamic response, and a sensitivity distribution characteristic based on the initial data set;

[0058] An updating module is used to obtain intuitive analysis results based on the prediction results, build a dynamic response database, regularly update the prediction results, and obtain long-term monitoring data;

[0059] The generation module is used to determine potential environmental parameter anomalies based on the long-term monitoring data and generate a corresponding risk assessment report if it is detected that the change amplitude within a time period exceeds a preset amplitude threshold.

[0060] Compared to existing technologies, the present invention provides a big data-based method and system for analyzing glacier mass balance in a watershed. This method collects remote sensing images, ground observations, and meteorological data from glacier basins, standardizes and integrates multi-source data, constructs a random forest model to analyze the correlation between glacier changes and climate factors, identifies key driving factors, and uses long-short-term memory networks to predict the dynamic response of glacier materials. Sensitivity analysis identifies highly sensitive climate factors and optimizes the prediction model. The present invention also establishes a dynamic response database for long-term monitoring and provides an automatic early warning mechanism to assess the risk of abnormal changes. This method enables precise analysis and prediction of the interaction between glacier changes and climate factors, providing an effective tool for glacier change research and environmental risk assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 This is a flow chart of a basin glacier mass balance analysis method based on big data provided by the first embodiment of the present invention;

[0062] Figure 2 This is a schematic structural diagram of a basin glacier material balance analysis system based on big data provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0063] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0064] Reference Figure 1 The first embodiment of the present invention provides a flow chart of a basin glacier material balance analysis method based on big data, comprising the following steps:

[0065] S11, obtain the original dataset of the glacier and obtain the initial dataset in a unified format;

[0066] S12, sequentially obtaining a comprehensive dataset, a set of key driving factors, a prediction result of a simulated glacier material dynamic response, and a sensitivity distribution characteristic based on the initial dataset;

[0067] S13, obtaining intuitive analysis results based on the prediction results, building a dynamic response database, regularly updating the prediction results, and obtaining long-term monitoring data;

[0068] S14: Based on the long-term monitoring data, if it is detected that the change amplitude in one time period exceeds a preset amplitude threshold, a potential environmental parameter abnormal point is determined and a corresponding risk assessment report is generated.

[0069] In step S11 , the original dataset of the glacier is acquired and an initial dataset in a unified format is obtained.

[0070] The method of obtaining the original glacier dataset and obtaining an initial dataset in a unified format includes:

[0071] Obtaining raw data covering glacier changes, climate factors, and environmental parameters from remote sensing images, ground observations, and meteorological data platforms, and performing preliminary format adjustments on the raw data to obtain a preliminary organized data set;

[0072] Based on the initially collated data set, image processing software is used to uniformly adjust the resolution of the remote sensing images, and the sampling frequencies of the ground observations and the meteorological data platform are aligned to obtain an intermediate data set with consistent resolution;

[0073] Standardize the intermediate data set, remove outliers and missing values ​​using a data cleaning tool, and if missing values ​​in the intermediate data set exceed a preset missing threshold, fill them in using an interpolation method to obtain a cleaned, standardized data set;

[0074] Based on the standard dataset, data integration tools are used to merge data from different sources in a unified format to generate an initial dataset containing glacier changes, climate factors and environmental parameters.

[0075] For example, when processing data related to glacier changes, the original data may come from remote sensing images, ground observation stations, and meteorological data platforms, and the data formats vary greatly.

[0076] For example, during the resolution unification process, remote sensing images may have inconsistent spatial resolutions, with some images having a resolution of 10 meters and others 30 meters. Low-resolution images can be upsampled to a 10-meter resolution using image processing software such as ENVI to ensure consistency of spatial information. Furthermore, the sampling frequencies of ground observation and meteorological data may differ. For example, ground observation data is collected daily, while meteorological data is collected hourly. Using a time averaging method, meteorological data can be aligned to the ground observation frequency based on the daily average, forming an intermediate dataset with consistent resolution. This alignment helps avoid temporal or spatial misalignment during subsequent data fusion, improving analysis accuracy.

[0077] For example, during the standardization and data cleaning phases, intermediate datasets may contain outliers and missing values. For example, suppose the temperature data from a weather station records a temperature of -50 degrees Celsius on a particular day, significantly deviating from the normal range. This can be marked as an anomaly and removed using a data cleaning tool, such as the Pandas library in Python. If the proportion of missing values ​​exceeds a preset threshold, such as 10%, linear interpolation can be used to fill in the missing data.

[0078] For example, if a glacier thickness observation point is missing data for three consecutive days, an interpolated estimate can be made based on the data trends from the two days before and after. This cleaning and filling operation ensures the integrity and reliability of the data, laying the foundation for subsequent analysis.

[0079] For example, during the data integration phase, after cleaning the standardized dataset, data integration tools such as ArcGIS can be used to fuse data on glacier changes, climate factors, and environmental parameters according to unified temporal and spatial coordinates. Assuming glacier area data comes from remote sensing imagery, temperature and precipitation data from meteorological stations, and soil moisture data from ground observations, these data can be matched by year and geographic location to generate an initial dataset containing multidimensional information. This integration approach can comprehensively reflect the correlation between glacier changes and environmental factors, providing data support for studying the relationship between glacier retreat and climate change.

[0080] It should be noted that the technical processing in each of the above links can significantly improve data quality.

[0081] For example, format unification avoids data reading errors, resolution alignment reduces spatial and temporal errors, cleaning and interpolation ensure data integrity, and integration facilitates comprehensive analysis. These steps work together to ensure that the final dataset is both accurate and practical, providing a reliable basis for glacier monitoring and climate research.

[0082] In step S12, a comprehensive data set, a set of key driving factors, a prediction result of simulating the dynamic response of glacier materials, and sensitivity distribution characteristics are obtained in sequence according to the initial data set.

[0083] The obtained comprehensive data set includes:

[0084] Obtaining data source differences of the glacier changes and the climate factors in the initial dataset, and calibrating the spatial distribution and time series using a data alignment tool to obtain a calibrated aligned dataset;

[0085] Using a feature extraction tool to separate the spatial feature values ​​corresponding to the glacier changes and the temporal feature values ​​corresponding to the climate factors in the calibrated aligned dataset, and determine an extracted feature dataset;

[0086] If the eigenvalues ​​in the feature data set are unevenly distributed, balancing the spatial eigenvalues ​​and the temporal eigenvalues ​​using a weighted average tool to obtain a balanced feature data set;

[0087] According to the balanced feature data set, the principal component analysis tool is used to reduce the dimension of the feature values ​​and integrate them to obtain the final comprehensive data set.

[0088] For example, when processing the initial data set, the alignment of spatial distribution and time series is particularly important due to the differences in data sources for glacier changes and climate factors. Spatial distribution alignment can be understood as matching data from different sources according to a unified geographic coordinate system, while time series alignment is to ensure the consistency of data in the time dimension. Suppose that the glacier area data comes from remote sensing images, covering the latitude and longitude grid of a certain basin, while climate factors such as temperature data come from meteorological stations, recording hourly changes at specific points. When using the data alignment tool, the meteorological station data can be expanded to the same grid range as the remote sensing image through spatial interpolation methods, such as interpolating point temperature data to grid cells per square kilometer, and at the same time summarizing the hourly data as the daily average to align with the daily update frequency of the glacier data.

[0089] For example, during the feature extraction phase, separating spatial features related to glacier change and temporal features related to climate factors from the calibrated, aligned dataset is a key step. Spatial features might include the distribution density of glacier-covered area or the magnitude of boundary changes, while temporal features might involve seasonal fluctuations in temperature or precipitation. For example, in a glacier basin, remote sensing imagery shows that the glacier edge has retreated by approximately 50 meters annually over the past decade. This could serve as a spatial feature, while meteorological data indicates an average summer temperature increase of 0.5 degrees Celsius each year. This could serve as a temporal feature. Feature extraction tools separate this data from the original dataset, forming an independent feature dataset for subsequent analysis.

[0090] For example, if the distribution of eigenvalues ​​in a feature dataset is uneven—for example, if spatial eigenvalues ​​are overly high in glacier area change data, while temporal eigenvalues, such as precipitation data, are relatively sparse—then a weighted average tool may be used to balance the distribution. A specific approach might be to assign a lower weight, such as 0.4, to spatial eigenvalues ​​and a higher weight, such as 0.6, based on the importance and coverage of the data. This would prevent one type of feature from overly influencing subsequent analysis. This balanced feature dataset can more comprehensively reflect the relationship between glaciers and climate factors.

[0091] For example, during the dimensionality reduction and integration phase, principal component analysis (PCA) is used to process the balanced feature dataset, aiming to compress high-dimensional eigenvalues ​​into a few comprehensive indicators. For example, if the original feature dataset contains multiple variables such as glacier area, thickness, temperature, and precipitation, PCA can be used to integrate these variables into two or three main components, preserving most of the information while reducing data complexity. This comprehensive dataset is more suitable for studying the correlation between glacier change and climate factors, facilitating subsequent modeling.

[0092] It's important to note that each of these steps is closely aligned with the fields of glacier monitoring and climate research, ensuring data optimization from alignment to feature extraction, balancing, and dimensionality reduction. This ensures a foundation for in-depth analysis of the relationship between glacier retreat and environmental change. In particular, during feature extraction and balancing, the specificity of glacier basin data is addressed, with appropriate weighting and feature separation, effectively improving data representativeness and analytical accuracy.

[0093] The key driving factor set obtained includes:

[0094] Obtaining correlation analysis between the glacier changes and the climate factors from the comprehensive dataset, processing missing values ​​and outliers in the comprehensive dataset using a data cleaning tool to obtain a cleaned complete dataset, and determining the variable range in the complete dataset;

[0095] Obtain variable screening and feature importance assessment through the cleaned complete data set, and use correlation calculation tools to compare the correlation coefficients between the glacier changes and the climate factors to obtain variable combinations with high correlation;

[0096] Based on the combination of variables with high correlation, a preliminary judgment of the driving factors is made, and a ranking tool is used to rank the importance of the combination of variables to obtain a ranked set of key variables.

[0097] For example, when processing a comprehensive data set, data cleaning is a key step in analyzing the correlation between glacier changes and climate factors. Data cleaning tools are mainly used to process missing values ​​and outliers in the data set to ensure the accuracy of subsequent analysis. Suppose that in a comprehensive data set of a glacier basin, the glacier area data of some years are missing due to cloud cover in remote sensing images, and some climate factors such as precipitation data have abnormally high values, which may be recording errors. The cleaning tool can fill in the missing glacier area data through interpolation, such as estimating the data of the missing years based on the average value of the previous and next years; for outliers, a reasonable range can be set. For example, if the precipitation exceeds twice the historical maximum, it is considered an anomaly and removed to obtain a complete cleaned data set.

[0098] For example, during the variable scope determination and screening phase, correlation calculation tools were used to assess the strength of associations between glacier change and climate factors. Assuming the cleaned dataset contains variables such as glacier area, glacier thickness, average annual temperature, and annual precipitation, a correlation calculation revealed that the correlation coefficient between glacier area and average annual temperature is as high as 0.8, while the correlation coefficient with precipitation is only 0.3. This suggests that temperature may be a significant variable influencing glacier change. This allows us to identify highly correlated variable combinations, such as glacier area and temperature, providing key areas for subsequent analysis.

[0099] For example, based on a preliminary assessment of driving factors, the ranking tool ranks variable combinations by importance, forming a set of key variables. Suppose, in the aforementioned set, the impact of temperature on glacier area change is assessed as 0.7, while the impact of other variables, such as wind speed, is only 0.2. Using the ranking tool, temperature can be listed as the primary key variable and a threshold requirement set, such as a weight greater than 0.5. If all variables in the key variable set meet this threshold, the analysis proceeds to the next step. This approach helps focus on the factors that most significantly influence glacier change.

[0100] For example, in environmental impact and time series analysis, data visualization tools are used to plot the spatial distribution and time series characteristics of key variables. For example, considering the correlation between temperature and glacier area, plotting a spatial distribution map within a particular watershed can visually demonstrate the overlap between areas with higher temperatures and areas with reduced glacier area. Simultaneously, a time series chart can demonstrate the trend of increasing temperatures and decreasing glacier area over the past 20 years. This charting method allows researchers to quickly grasp the correlation between variables and provides an intuitive basis for further research. This processing method can effectively improve the efficiency of data interpretation and lay the foundation for analysis of the driving mechanisms of glacier change.

[0101] The prediction results of simulating the dynamic response of glacier materials include:

[0102] Based on the key driving factor set and the dynamic characteristics of glacial materials, a data integration tool is used to standardize the environmental variables in the time series to obtain a sorted time series data group, and the distribution range of the time series data group is determined;

[0103] Using the sorted time series data group, a feature extraction tool is used to perform hierarchical decomposition on the time series data group to obtain separated feature units;

[0104] Determine whether the characteristic unit meets a preset characteristic threshold standard. If so, use a prediction tool to perform parameterization processing on the characteristic unit to obtain a generated prediction parameter group;

[0105] A mapping tool is used to match and integrate the forecast parameter group with the spatiotemporal distribution to obtain a final trend distribution map.

[0106] For example, when studying the relationship between the dynamic characteristics of glacier materials and key driving factors, the standardization processing of data integration tools is particularly important. Standardization aims to eliminate the dimensional differences of different environmental variables and ensure that time series data can be compared on the same scale. Suppose a time series dataset of a glacier basin contains variables such as temperature, precipitation, and glacier volume change. The temperature is in degrees Celsius and ranges from -5 to 10, while the precipitation is in millimeters and ranges from 200 to 800. The data integration tool can convert these variables into standard values ​​with a mean of 0 and a standard deviation of 1 to facilitate subsequent analysis. This processing method helps to unify the data distribution and avoid deviations caused by different dimensions.

[0107] For example, for the separation of nonlinear features, the hierarchical decomposition of the feature extraction tool is a key link. Nonlinear features are often hidden in complex data and difficult to observe directly. Through hierarchical decomposition, the data group can be split into multiple feature units, each representing a different change pattern. Assuming that in the above-mentioned basin data, the change in glacier volume is affected by both temperature and precipitation, the feature extraction tool can separate the rapid changes driven by temperature and the long-term trend driven by precipitation to form two feature units. If the preset threshold standard is that the explanatory power of the feature unit must reach 80% of the total variance, it is judged whether the condition is met. This separation method helps to more clearly identify the mechanism of action of each factor.

[0108] For example, in driver-correlation modeling, the prediction tool's parameterization is used to quantify the relationship between characteristic units and glacier change. Assuming that the isolated temperature-driven characteristic unit is selected as the primary analysis object, the prediction tool generates a set of prediction parameters based on historical data, such as predicting a 0.5% decrease in glacier volume for every 1°C increase in temperature. The tool then compares the historical data with the predicted results to determine whether the parameter set is appropriate for the current basin. This parameterization provides a reliable basis for subsequent trend simulations.

[0109] For example, to simulate trends, the mapping tool matches and integrates the predicted parameter set with the spatiotemporal distribution to produce a trend distribution map. For example, in the aforementioned basin, a distribution map generated based on temperature parameters shows a more pronounced glacier volume decrease in the southern region, consistent with the observed glacier retreat. If the distribution map closely matches the historical trend, the response simulation is considered satisfactory. This matching and integration helps visualize the spatial differences in glacier change and provides a reference for further research.

[0110] For example, within the aforementioned steps, standardization, hierarchical decomposition, parameterization, and mapping integration form a complete analytical chain. From data collation to trend presentation, each step closely revolves around the relationship between glacier changes and environmental factors, ensuring the logic and consistency of the analysis. This systematic approach can effectively reveal the driving mechanisms behind glacier dynamics and provide support for related research.

[0111] The obtaining of the sensitivity distribution characteristics includes:

[0112] According to the prediction results, the input parameters are normalized using a data sorting tool to obtain a sorted parameter data set;

[0113] Determining whether the parameter data set meets a preset threshold standard, and if so, performing multiple rounds of transformation on the parameter data set to obtain a transformed disturbance parameter combination;

[0114] Associating the disturbance parameter combination with the environmental variables to obtain weight data of the climate factors;

[0115] The weight data and the change trend are integrated to obtain the final distribution feature image.

[0116] For example, when studying the interaction between climate factors and glacier changes, the normalization processing of data sorting tools is particularly critical. Normalization aims to unify input parameters of different dimensions onto a comparable scale for subsequent analysis. Suppose that in a study of a glacier basin, the input parameters include average annual temperature, precipitation, and wind speed, with the temperature ranging from -8 to 5 degrees Celsius, the precipitation ranging from 300 to 900 mm, and the wind speed ranging from 2 to 10 meters per second. Through data sorting tools, these parameters can be converted into standardized data with a mean of 0 and a standard deviation of 1, ensuring that different variables will not be biased due to dimensional differences in the analysis. This processing method lays the foundation for subsequent judgment of whether the parameter data set meets the preset threshold standard.

[0117] For example, a specific criterion can be set to determine whether a parameter dataset meets a preset threshold, such as requiring the dataset's normalized variance to account for at least 85% of the total variance. For example, if, after normalization, the variance explanation rate for the aforementioned watershed data reaches 88%, this condition is considered met. This approach helps select representative parameter sets, providing reliable input for subsequent disturbance response analysis.

[0118] For example, in a parameter perturbation response adjustment test, the adjustment test tool can perform multiple rounds of transformations on a parameter dataset to generate perturbation parameter combinations. Assuming temperature is the primary perturbation factor, with a perturbation range of ±2 degrees Celsius, the tool simulates glacier volume changes under different perturbations, generating a set of perturbation parameter combinations. This approach can help analyze the impact of perturbations on glacier changes and provide data support for further research.

[0119] For example, to analyze impact weights, data matching tools can correlate perturbation parameter combinations with environmental variables to obtain weighted data for each climate factor. For example, if the analysis of the aforementioned data reveals that temperature has a weight of 0.6 on glacier change, precipitation has a weight of 0.3, and wind speed has a weight of 0.1, then the weighted data can be determined to reflect dynamic response characteristics. This correlation helps clarify the impact of each factor and provides a basis for subsequent analysis.

[0120] For example, when generating sensitivity distributions, spatial mapping tools integrate weighted data with trends to produce an image of distribution characteristics. For example, in the aforementioned basin, if the image generated based on weighted data shows that the northern region is more sensitive to temperature changes, which is consistent with the observed distribution of glacier retreat, then the image is considered to reflect the characteristics of the response mechanism. This integration method intuitively presents the spatial differences in glacier change and provides an important reference for research.

[0121] It's important to note that the aforementioned steps, from data collation to the generation of distribution feature maps, form a complete analytical chain. Each step closely revolves around the interaction between climate factors and glacier change, ensuring logical rigor. Through normalization, perturbation testing, weight analysis, and spatial mapping, the driving mechanisms of glacier change can be gradually revealed, providing support for related research. This systematic analysis has the beneficial effect of improving data processing accuracy and the visualization of results.

[0122] In step S13, intuitive analysis results are obtained based on the prediction results, a dynamic response database is constructed, and the prediction results are regularly updated to obtain long-term monitoring data.

[0123] The intuitive analysis results include:

[0124] Acquiring environmental variable data and climate factor data corresponding to the glacier changes from a pre-established database and performing classification processing to obtain a classified data set;

[0125] If the data set contains characteristic information of a change trend, matching the classified data set with a preset distribution characteristic template to obtain a mapped data combination;

[0126] Integrating the data combination with the visual style of the change trend to obtain rendered graphic data;

[0127] fusing the graphic data with the sensitivity distribution characteristics to obtain final chart data;

[0128] The dynamic response database is constructed, and the prediction results are regularly updated to obtain long-term monitoring data, including:

[0129] Obtaining original records related to glacier changes, combining them with historical data of the climate factors to form an initial comprehensive data set and obtain structured data grouping;

[0130] Performing feature extraction on the structured data grouping, matching the glacier change with a factor-sensitive characteristic value, marking the data grouping as highly sensitive data if the characteristic value exceeds a preset characteristic threshold, and determining correlation characteristics with a dynamic response;

[0131] Integrating the highly sensitive data with the prediction results to generate an updated version of a dynamic response database, and regularly comparing the interaction characteristics in the dynamic response database to obtain the latest trend tracking records;

[0132] The trend tracking records are integrated with the target data of long-term monitoring to generate a distribution chart reflecting the relationship between glacier changes and climate factors.

[0133] According to the association between the sensitivity distribution and the climatic factors, a data screening tool is used to classify the multiple climatic factors, and a set of highly sensitive factors that meet the preset threshold standards is obtained from them, and it is determined whether the highly sensitive factor set is associated with the environmental variables. If the highly sensitive factor set is associated with the environmental variables, then for the prediction optimization process, a parameter calibration tool is used to adjust the parameters of the highly sensitive factor set to obtain an adjusted parameter data set, and it is determined whether the parameter data set meets the response characteristic standard. Through the adjusted parameter data set, for the adjustment of the weight distribution, a data mapping tool is used to integrate the parameter data set with the change trend, and an optimized weight distribution combination is obtained to determine whether the weight distribution combination reflects the distribution image characteristics. According to the optimized weight distribution combination, for the optimization process of the highly sensitive factors, a data fusion tool is used to match the weight distribution combination with a pre-established prediction template to obtain the final prediction optimization data, and it is determined whether the prediction optimization data reflects the sensitivity distribution characteristics.

[0134] If the influence weight of one of the climate factors exceeds the preset weight threshold, it is marked as a highly sensitive factor, and the highly sensitive factor is input into the prediction model for secondary optimization, and the parameters and weight distribution of the prediction model are adjusted to obtain the optimized prediction results.

[0135] For example, when studying the dynamic response characteristics of glacier changes, the application of data collection tools is a critical first step. By extracting data on environmental variables and climatic factors from pre-established databases, a foundation can be laid for subsequent analysis. For example, in a glacier basin study, environmental variables include terrain height and slope aspect, and climatic factors include average annual temperature and rainfall. The data collection tool preliminarily organizes this data into time series and spatial distribution to form a raw dataset. This process ensures the comprehensiveness and systematic nature of the data, providing reliable input for classification processing.

[0136] For example, for data classification processing, the data can be divided according to the degree of impact through grouping methods.

[0137] In one possible implementation, assuming that annual average temperature has a significant impact on glacier melt, while rainfall plays a significant role in glacier replenishment, classification processing would divide the data into primary and secondary impact groups. In this classified data set, the annual average temperature data might show a year-over-year upward trend, while the rainfall data exhibits seasonal fluctuations. When determining whether trend characteristics are present, if the temperature data has consistently increased by more than 2 degrees Celsius over the past 10 years, it is considered to have a significant trend characteristic, providing a basis for subsequent matching.

[0138] For example, in data mapping tools, a categorized data set is matched to a pre-defined distributional template. Assuming the template is based on historical glacier retreat rates, the mapping process correlates rising temperature trends with glacier area reduction. If the mapped data combination shows a roughly 5% decrease in glacier area for every 1°C increase in temperature, this is considered to reflect a weighted correlation. This matching approach helps reveal the key drivers of glacier change.

[0139] For example, graphics rendering tools integrate data composition with visual style to create trend charts. For example, if a line graph shows the relationship between temperature change and glacier area, the rendered data will show a synchronized trend between the temperature curve and the area reduction curve. If the graph clearly demonstrates the correlation between the two, it is considered to reflect the dynamic response of the correlation. This visual presentation method allows researchers to intuitively understand the connections between the data.

[0140] For example, in generating heat maps, visualization tools integrate graphical data with the distribution characteristics of impact weights. Suppose a heat map uses color to represent the impact of temperature on different glacier regions. In the chart data, darker colors near lower altitudes indicate a greater temperature impact. If the chart data is consistent with the actual distribution of glacier melt, it is considered to reflect the correlation characteristics of environmental variables. This graphical method provides researchers with an intuitive reference to spatial distribution and helps identify key impact areas.

[0141] For example, in the logical progression from the core solution to the extended solution, the above links form a complete data processing and visualization chain. The core solution focuses on data collection and classification, while the extended solution gradually deepens the understanding of the relationship between glacier changes and climate factors through mapping, rendering, and fusion. Suppose in a glacier study, through this chain, it is found that the influence of temperature on the edge of the glacier is greater than that on the central area, which provides a direction for subsequent research. This multi-link collaborative approach not only enhances the depth of data analysis, but also provides a multi-dimensional perspective for the study of glacier dynamic response.

[0142] In step S14, based on the long-term monitoring data, if it is detected that the change amplitude in one time period exceeds the preset amplitude threshold, a potential environmental parameter abnormal point is determined and a corresponding risk assessment report is generated.

[0143] According to the long-term monitoring data, if it is detected that the change amplitude in one time period exceeds the preset amplitude threshold, the potential environmental parameter abnormal point is determined and a corresponding risk assessment report is generated, including:

[0144] Obtain real-time records of the change amplitude during the monitoring period. If the change amplitude exceeds a preset change threshold, an automatic early warning mechanism is triggered to obtain a preliminary abnormal fluctuation indicator;

[0145] Matching the abnormal fluctuation identification with the records of historical environmental parameters, mining the correlation characteristics of the historical environmental parameters, and determining the distribution of potential abnormal points;

[0146] Perform a comprehensive comparison of the distribution of the abnormal points and the correlation characteristics of the historical environmental parameters to obtain the corresponding risk level and determine the distribution range of the high-risk area;

[0147] The distribution range of the high-risk area is integrated with the abnormal fluctuation mark to generate a detailed report including the risk level and the distribution of the abnormal points.

[0148] For example, when building a data collection framework, raw records related to glacier changes can be obtained from multiple sources of environmental variables. For example, in a glacier monitoring project, data sources include satellite remote sensing imagery, ground-based meteorological station records, and historical archival data. These sources provide information on glacier area changes, surface temperature fluctuations, and precipitation. By integrating these data, a comprehensive dataset with both time series and spatial distribution can be formed. This approach ensures data diversity and coverage, laying a solid foundation for subsequent analysis.

[0149] For example, for the classification and organization of data sets, comprehensive data sets can be grouped according to the types of environmental variables and climate factors.

[0150] In one possible implementation, consider a dataset containing variables such as altitude, slope, average annual temperature, and annual precipitation. Classification and organization would categorize these data into terrain-related and climate-related groups. The terrain group might reveal a higher concentration of glaciers at higher altitudes, while the climate group might indicate more pronounced temperature variations at lower altitudes. This grouping helps clarify the hierarchical relationships between the data, facilitating subsequent feature extraction.

[0151] For example, during feature extraction and matching analysis, data processing tools can perform sensitivity analysis on structured data groups. For example, if the extracted feature values ​​include temperature change rate and glacier area reduction rate, if the temperature change rate of a data set exceeds a preset threshold of 0.5 degrees Celsius per year, it will be marked as highly sensitive. This labeling method can highlight key influencing factors, clarify the dynamic relationship between glacier change and climate factors, and provide targeted basis for further research.

[0152] For example, by integrating highly sensitive data with forecast results through data storage tools, a dynamically responsive database can be generated. Suppose, during a database update, new data reveals that a particular glacier region has decreased in size by 10% over the past five years, strongly correlated with rising temperatures. Regular comparisons of this data can track changing trends and promptly update monitoring priorities. This continuous updating approach helps maintain data currency and supports long-term research.

[0153] For example, when using visualization tools to generate distribution charts, trend tracking records can be integrated with long-term monitoring data. Imagine a chart using color shading to show the relationship between glacier change and temperature in different regions, with darker areas indicating a more pronounced temperature impact. If the chart shows darker colors at lower elevations, consistent with actual monitoring data, it demonstrates a good representation of the interactive nature of the integrated dataset. This intuitive presentation allows researchers to quickly identify key areas and improve analytical efficiency.

[0154] For example, in the long-term monitoring of glacier changes, identifying and addressing unusual fluctuations is particularly important. The real-time recording function of data collection tools can help capture changes in glacier area or thickness. For example, in a monitoring project, the preset threshold for glacier area change is 5% per year. If a region decreases by 3% in six months, the data collection tool will immediately record this change and trigger an automatic warning mechanism, generating a preliminary abnormal fluctuation indicator. This real-time monitoring method enables rapid response to potential issues and provides timely information for subsequent analysis.

[0155] For example, data comparison tools can play a key role in matching abnormal fluctuation indicators with historical environmental parameters. Suppose historical records show that temperatures in a certain region have been rising steadily over the past decade, with an average annual increase of 0.3 degrees Celsius, while precipitation has decreased by 20%. By comparing the abnormal fluctuation indicators with these parameters, a strong correlation between the decrease in glacier area and the temperature increase can be found. Combining trend analysis tools to further explore the correlation between these parameters can identify the area as a potential anomaly. This approach helps to screen key areas from massive amounts of data, improving the targeted nature of the analysis.

[0156] For example, during the risk assessment phase, the risk assessment generation tool comprehensively compares the distribution of anomaly points with the correlation characteristics of environmental parameters. For example, if a high-altitude area experiences significant glacier changes, highly correlated with temperature and precipitation fluctuations, the tool will classify it as high risk based on pre-set criteria. Further analysis revealed that this area, covering approximately 15% of the total monitored area and located in the core glacier zone, is a key area of ​​concern. This risk classification clearly defines the distribution of high-risk areas, providing important reference for subsequent decision-making.

[0157] For example, using a report generation tool, a detailed risk assessment report can be generated by integrating the distribution of high-risk areas with indicators of abnormal fluctuations. For example, a report might indicate that a particular area has the highest risk level, with abnormal points concentrated above 4,000 meters above sea level. This report would also include a five-year glacier change trend chart and records of environmental parameter fluctuations. This integrated approach ensures comprehensive and intuitive reporting, allowing researchers to quickly understand the situation and formulate countermeasures. Potential influencing factors, such as the potential for increased risk due to continued temperature increases, can also be identified in the report to support long-term planning.

[0158] For example, throughout the entire process, the implementation methods of various technical topics are closely integrated, forming a complete chain from data collection to risk assessment. From the real-time recording of abnormal fluctuations, to the matching analysis of historical parameters, to the classification of risk levels and the generation of the final report, each link revolves around the interaction between glacier changes and environmental factors. This systematic approach not only improves monitoring efficiency but also provides reliable data support for glacier protection and climate change research, ensuring timely attention and effective management of key areas.

[0159] It will be apparent to those skilled in the art that the present application is not limited to the details of the exemplary embodiments described above and that the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the present application is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

[0160] In summary, the present invention discloses a basin glacier material balance analysis method based on big data. By collecting remote sensing images, ground observations and meteorological data of the glacier basin, the multi-source data is standardized and integrated, and a random forest model is constructed to analyze the correlation between glacier changes and climate factors, and to determine the key driving factors. The long short-term memory network is further used to predict the dynamic response of glacier materials, and the highly sensitive climate factors are determined through sensitivity analysis to optimize the prediction model. The present invention also establishes a dynamic response database for long-term monitoring, and sets up an automatic early warning mechanism to assess the risk of abnormal changes. This method realizes the precise analysis and prediction of the interaction between glacier changes and climate factors, and provides an effective tool for glacier change research and environmental risk assessment.

[0161] Reference Figure 2 The second embodiment of the present invention provides a structure diagram of a basin glacier material balance analysis system based on big data, including:

[0162] The first acquisition module 201 is used to acquire the original data set of the glacier and obtain an initial data set in a unified format;

[0163] The second acquisition module 202 is used to sequentially obtain a comprehensive data set, a set of key driving factors, a prediction result of a simulated glacier material dynamic response, and a sensitivity distribution characteristic based on the initial data set;

[0164] An updating module 203 is configured to obtain intuitive analysis results based on the prediction results, construct a dynamic response database, regularly update the prediction results, and obtain long-term monitoring data;

[0165] The generating module 204 is configured to determine potential environmental parameter anomalies based on the long-term monitoring data and generate a corresponding risk assessment report if it is detected that the change amplitude within a time period exceeds a preset amplitude threshold.

[0166] It should be noted that the basin glacier material balance analysis system based on big data provided in an embodiment of the present invention is used to execute all the process steps of the basin glacier material balance analysis method based on big data in the above embodiment. The working principles and beneficial effects of the two correspond one to one, so they will not be repeated here.

[0167] An embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a big data-based basin glacier material balance analysis program. When the processor executes the computer program, the steps of each of the above-mentioned big data-based basin glacier material balance analysis method embodiments are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, such as the first acquisition module.

[0168] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0169] The electronic device may be a computing device such as a desktop computer, notebook, PDA, or smart tablet. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will appreciate that the aforementioned components are merely examples of electronic devices and do not constitute a limitation of the electronic device. The electronic device may include more or fewer components than those described above, or a combination of certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, and the like.

[0170] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor. The processor is the control center of the electronic device and connects various parts of the entire electronic device using various interfaces and lines.

[0171] The memory can be used to store the computer programs and / or modules. The processor implements the various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and accessing the data stored in the memory. The memory may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as a sound playback function or an image playback function); the data storage area may store data generated based on the use of the mobile phone (such as audio data, a phone book, etc.). Furthermore, the memory may include high-speed random access memory and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0172] If the module / unit integrated into the electronic device is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. It should be noted that the content of the computer-readable medium can be appropriately increased or decreased based on the requirements of legislation and patent practice in a jurisdiction. For example, in some jurisdictions, based on legislation and patent practice, computer-readable media does not include electric carrier signals and telecommunication signals.

[0173] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement the present invention without inventive effort.

[0174] The specific embodiments described above further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A basin glacier mass balance analysis method based on big data, characterized by: include: Obtaining raw glacier data sets and obtaining an initial data set in a unified format. The raw data sets include raw data covering glacier changes, climate factors, and environmental parameters obtained from remote sensing images, ground observations, and meteorological data platforms; Based on the initial data set, a comprehensive data set, a set of key driving factors, prediction results of simulated glacier material dynamic responses, and sensitivity distribution characteristics are obtained in sequence; Obtain intuitive analysis results based on the prediction results, build a dynamic response database, regularly update the prediction results, and obtain long-term monitoring data; Based on the long-term monitoring data, if it is detected that the change amplitude in one time period exceeds the preset amplitude threshold, the potential environmental parameter abnormal point is determined and a corresponding risk assessment report is generated; The comprehensive dataset, key driving factor set, prediction results of simulated glacier material dynamic response, and sensitivity distribution characteristics are obtained in sequence based on the initial dataset, including: The initial data set is subjected to spatiotemporal alignment and feature extraction by data fusion technology, and data dimension reduction and integration are performed by weighted average method and principal component analysis method to obtain a fused comprehensive data set; Based on the glacier changes and climate factors in the comprehensive dataset, a random forest model based on machine learning is constructed, and the set of key driving factors is determined through model training and feature importance ranking; Based on the set of key driving factors and the material dynamic characteristics of glacier changes, a prediction model based on a long short-term memory network is constructed to obtain the prediction results of the simulated glacier material dynamic response; According to the prediction results, a perturbation test is performed on the prediction model, the influence weight of the climate factor on the glacier change is calculated, and the sensitivity distribution characteristics are determined; Wherein, determining the sensitivity distribution characteristics includes: According to the prediction results, the input parameters are normalized using a data sorting tool to obtain a sorted parameter data set; Determining whether the parameter data set meets a preset threshold standard, and if so, performing multiple rounds of transformation on the parameter data set to obtain a transformed disturbance parameter combination; Associating the disturbance parameter combination with the environmental variables to obtain weight data of the climate factors; Integrating the weight data with the change trend to obtain a final distribution feature image; The environmental variables include terrain height and slope.

2. The basin glacier mass balance analysis method based on big data according to claim 1 is characterized in that: The method of obtaining the original glacier dataset and obtaining an initial dataset in a unified format includes: Obtaining raw data covering glacier changes, climate factors, and environmental parameters from remote sensing images, ground observations, and meteorological data platforms, and performing preliminary format adjustments on the raw data to obtain a preliminary organized data set; Based on the initially collated data set, image processing software is used to uniformly adjust the resolution of the remote sensing images, and the sampling frequencies of the ground observations and the meteorological data platform are aligned to obtain an intermediate data set with consistent resolution; Standardize the intermediate data set, remove outliers and missing values ​​using a data cleaning tool, and if missing values ​​in the intermediate data set exceed a preset missing threshold, fill them in using an interpolation method to obtain a cleaned, standardized data set; Based on the standard dataset, data integration tools are used to merge data from different sources in a unified format to generate an initial dataset containing glacier changes, climate factors and environmental parameters.

3. The basin glacier mass balance analysis method based on big data according to claim 1 is characterized in that: The fused comprehensive data set includes: Obtaining data source differences of the glacier changes and the climate factors in the initial dataset, and calibrating the spatial distribution and time series using a data alignment tool to obtain a calibrated aligned dataset; Using a feature extraction tool to separate the spatial feature values ​​corresponding to the glacier changes and the temporal feature values ​​corresponding to the climate factors in the calibrated aligned dataset, and determine an extracted feature dataset; If the eigenvalues ​​in the feature data set are unevenly distributed, balancing the spatial eigenvalues ​​and the temporal eigenvalues ​​using a weighted average tool to obtain a balanced feature data set; According to the balanced feature data set, the principal component analysis tool is used to reduce the dimension of the feature values ​​and integrate them to obtain the final comprehensive data set.

4. The method for analyzing basin glacier mass balance based on big data according to claim 3 is characterized in that: Obtaining the prediction result of the simulated glacial material dynamic response includes: Based on the key driving factor set and the dynamic characteristics of glacial materials, a data integration tool is used to standardize the environmental variables in the time series to obtain a sorted time series data group, and the distribution range of the time series data group is determined; Using the sorted time series data group, a feature extraction tool is used to perform hierarchical decomposition on the time series data group to obtain separated feature units; Determine whether the characteristic unit meets a preset characteristic threshold standard. If so, use a prediction tool to perform parameterization processing on the characteristic unit to obtain a generated prediction parameter group; A mapping tool is used to match and integrate the forecast parameter group with the spatiotemporal distribution to obtain a final trend distribution map.

5. The basin glacier mass balance analysis method based on big data according to claim 1 is characterized in that: The intuitive analysis results include: Acquiring environmental variable data and climate factor data corresponding to the glacier changes from a pre-established database and performing classification processing to obtain a classified data set; If the data set contains characteristic information of a change trend, matching the classified data set with a preset distribution characteristic template to obtain a mapped data combination; Integrating the data combination with the visual style of the change trend to obtain rendered graphic data; fusing the graphic data with the sensitivity distribution characteristics to obtain final chart data; The dynamic response database is constructed, and the prediction results are regularly updated to obtain long-term monitoring data, including: Obtaining original records related to glacier changes, combining them with historical data of the climate factors to form an initial comprehensive data set and obtain structured data grouping; Performing feature extraction on the structured data grouping, matching the glacier change with a factor-sensitive characteristic value, marking the data grouping as highly sensitive data if the characteristic value exceeds a preset characteristic threshold, and determining correlation characteristics with a dynamic response; Integrating the highly sensitive data with the prediction results to generate an updated version of a dynamic response database, and regularly comparing the interaction characteristics in the dynamic response database to obtain the latest trend tracking records; The trend tracking records are integrated with the target data of long-term monitoring to generate a distribution chart reflecting the relationship between glacier changes and climate factors.

6. The basin glacier mass balance analysis method based on big data according to claim 1 is characterized in that: According to the long-term monitoring data, if it is detected that the change amplitude in one time period exceeds the preset amplitude threshold, the potential environmental parameter abnormal point is determined and a corresponding risk assessment report is generated, including: Obtain real-time records of the change amplitude during the monitoring period. If the change amplitude exceeds a preset change threshold, an automatic early warning mechanism is triggered to obtain a preliminary abnormal fluctuation indicator; Matching the abnormal fluctuation identification with the records of historical environmental parameters, mining the correlation characteristics of the historical environmental parameters, and determining the distribution of potential abnormal points; Perform a comprehensive comparison of the distribution of the abnormal points and the correlation characteristics of the historical environmental parameters to obtain the corresponding risk level and determine the distribution range of the high-risk area; The distribution range of the high-risk area is integrated with the abnormal fluctuation mark to generate a detailed report including the risk level and the distribution of the abnormal points.

7. A basin glacier material balance analysis system based on big data, characterized by: A method for implementing a basin glacier material balance analysis method based on big data as claimed in any one of claims 1 to 6, comprising: The first acquisition module is used to obtain the original dataset of the glacier and obtain the initial dataset in a unified format; A second acquisition module is used to sequentially obtain a comprehensive data set, a set of key driving factors, a prediction result of a simulated glacier material dynamic response, and a sensitivity distribution characteristic based on the initial data set; An updating module is used to obtain intuitive analysis results based on the prediction results, build a dynamic response database, regularly update the prediction results, and obtain long-term monitoring data; The generation module is used to determine potential environmental parameter anomalies based on the long-term monitoring data and generate a corresponding risk assessment report if it is detected that the change amplitude within a time period exceeds a preset amplitude threshold.

Images