A human shadow operation information display method and system based on multi-source information fusion

Abstract

The application discloses a kind of based on multi-source information fusion's human shadow operation information display method and system, it is related to meteorological information intelligent decision-making technical field, including, utilize graph neural network to carry out inference analysis to time series knowledge graph, identify cloud system development change and infer the evolution of cloud physical characteristics, predict the spatiotemporal range of operation potential area, generate accurate forecast conclusion and human shadow operation suggestion;Accurate forecast conclusion and human shadow operation suggestion are converted into visual instruction set, and evolution path is shown through highlighting core weather index, dynamic arrow display, and color overlay marks operation potential area and operation corridor, generates visual comprehensive situation chart.The application is analyzed by utilizing graph neural network to time series knowledge graph, realizes from historical mode automatically identifying operation potential area and predicting its dynamic evolution, improves the foresight and accuracy of human shadow operation decision.

Description

Technical Field

[0001] This invention relates to the field of intelligent decision-making technology for meteorological information, and in particular to a method and system for displaying information on weather modification operations based on multi-source information fusion. Background Technology

[0002] Weather modification operations are complex decision-making activities that heavily rely on accurate meteorological information. Current information display methods in this field are mainly based on the integrated display of multi-source meteorological data. Typically, data assimilation technology is used to fuse satellite, radar, and ground station observation data with numerical weather prediction products, and then presents them in a layered overlay on a geographic information system platform. This method aims to provide commanders with a comprehensive meteorological background to help them assess operational potential and safety windows.

[0003] However, existing methods still have limitations in supporting the dynamic decision-making needs of weather modification operations. They focus on the static display of meteorological elements and lack the automated identification and structured representation of cloud evolution and triggering mechanisms, resulting in a high reliance on human experience in determining the timing and location of operations. Furthermore, they lack the ability to quantitatively analyze the causal relationships between information, making it difficult to automatically infer the evolution trend of weather processes and the effectiveness of operations, thus restricting the level of intelligence in the generation and evaluation of operation plans. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a method for displaying information on shadowing operations based on multi-source information fusion to address the problem of insufficient ability to identify key event chains and make intelligent inferences about dynamic operation schemes.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a method for displaying information on weather modification operations based on multi-source information fusion. This method includes: collecting and preprocessing multi-source meteorological observation data; repairing and super-resolution reconstructing defective data using an adversarial network model to generate a multi-source time-series dataset; extracting time-series events from the multi-source time-series dataset, identifying cloud evolution, thermal and dynamic triggering, cloud system development, and operational events related to weather modification operations as nodes, and constructing a time-series knowledge graph covering the period from before to after the operation; using a graph neural network to perform reasoning analysis on the time-series knowledge graph, identifying cloud system development and changes, inferring the evolution of cloud physical characteristics, predicting the spatiotemporal range of potential operation areas, and generating accurate forecast conclusions and weather modification operation suggestions; converting the accurate forecast conclusions and weather modification operation suggestions into a visualization instruction set, and generating a visualized comprehensive situation map by highlighting core weather indicators, displaying evolution paths with dynamic arrows, and marking potential operation areas and operation corridors with color overlays.

[0008] As a preferred embodiment of the method for displaying artificial weathering operation information based on multi-source information fusion described in this invention, the preprocessing includes outlier removal, format standardization, coordinate unification, and spatiotemporal interpolation.

[0009] As a preferred embodiment of the method for displaying weather modification operation information based on multi-source information fusion described in this invention, the steps for generating the multi-source time-series dataset are as follows:

[0010] Defective data in preprocessed multi-source meteorological observation data is identified and input into an adversarial network model for repair and super-resolution reconstruction to obtain a repaired and enhanced dataset;

[0011] The repaired and enhanced dataset is fused with the effective data from the preprocessed multi-source meteorological observation data to generate a multi-source time-series dataset.

[0012] As a preferred embodiment of the method for displaying artificial weathering operation information based on multi-source information fusion described in this invention, the step of extracting time-series events from the multi-source time-series dataset includes the following steps.

[0013] Extract variable data related to cloud microphysics, thermodynamics, and operation records from multi-source time-series datasets, and load entities, relationships, and constraint rules from the cloud weathering operation knowledge ontology to generate a time-series dataset of operation physical variables.

[0014] Using a sliding window and abrupt change detection algorithm, event detection is performed on the time series dataset of operational physical variables to identify abrupt changes in cloud water content, energy jump points, and wind shear inflection points, generating a candidate fragment set of operational decision events.

[0015] The candidate fragment set of operation decision events is matched and fused with the event patterns in the weather modification operation knowledge ontology, and clustered to form a weather modification operation event instance set.

[0016] As a preferred embodiment of the method for displaying weather modification operation information based on multi-source information fusion described in this invention, the steps for constructing a temporal knowledge graph covering the period from before to after the operation are as follows:

[0017] Define a node type and assign spatiotemporal attributes to each shadow operation event instance in the shadow operation event instance set to generate a temporal knowledge graph node set;

[0018] Based on the node set of the temporal knowledge graph, the temporal relationship between nodes is mined, and the causal relationship is inferred by combining the operation rules to generate a candidate set of events related to the weather modification operation;

[0019] Using event instance nodes of weather modification operations as vertices and candidate sets of event relationships of weather modification operations as edges, and embedding time axes and spatial coordinates, a temporal knowledge graph covering the period from before to after the operation is constructed.

[0020] As a preferred embodiment of the cloud system development and change identification method based on multi-source information fusion described in this invention, the steps are as follows:

[0021] The node attributes, edge relationships, and timestamps in the temporal knowledge graph are feature-encoded and aligned, and then transformed into temporal graph tensor objects.

[0022] The temporal graph tensor object is input into the graph neural network, and the low-dimensional vector representation of the node is obtained through forward propagation.

[0023] By analyzing the attention weights of the graph neural network, high-weight path subgraphs connecting thermal-dynamic triggering events and working cloud systems-catalytic events are identified, and a set of evolutionary subgraphs is obtained.

[0024] As a preferred embodiment of the method for displaying weather modification operation information based on multi-source information fusion described in this invention, the steps for generating accurate forecast conclusions and weather modification operation suggestions are as follows:

[0025] Decode the evolutionary patterns of cloud systems, operational window thresholds, and corridor constraints from the low-dimensional vector representations of nodes in the evolutionary subgraph set to generate a fusion-quantified rule set;

[0026] Based on the fusion quantification rule set, the spatiotemporal range of the operational potential area is obtained by extrapolating the terminal nodes representing hazardous weather events in time and space. The operational window time interval and the geographical range of the operational corridor are obtained by extrapolating the terminal nodes representing operational cloud systems in time and space.

[0027] By integrating the time interval of the operation window with the geographical range of the operation corridor, suggestions for artificial weather modification operations are generated.

[0028] Based on the preset forecast level standards, the spatiotemporal range of the potential operational area is matched with rules and the severity is assessed to generate accurate forecast conclusions.

[0029] As a preferred embodiment of the method for displaying weather modification operation information based on multi-source information fusion described in this invention, the steps for converting accurate forecast conclusions and weather modification operation suggestions into a visual instruction set are as follows:

[0030] Extract target cloud system parameters, evolution paths, and polygon coordinates of potential operation areas from accurate forecast conclusions, and generate a set of visual elements by combining artificial weathering operation suggestions;

[0031] Based on preset visualization rules, the set of visualization elements is mapped to specific commands that the graphics rendering engine can execute, generating a visualization instruction set.

[0032] As a preferred embodiment of the method for displaying weather modification operation information based on multi-source information fusion described in this invention, the steps for generating a visualized comprehensive situation map are as follows:

[0033] Execute the visualization instruction set to drive the graphics rendering engine to create a color overlay layer for the potential area of ​​the task, a dynamic arrow layer for the evolution path, a highlight layer for the indicator parameters, a semi-transparent pipe layer for the task corridor, and a countdown marker layer for the task window, thereby generating a set of visualization layers.

[0034] Data matching the spatiotemporal range of the operational potential area is extracted from the multi-source time-series dataset and rendered to generate a multi-source data background layer;

[0035] By overlaying and merging the visualization layer set with the multi-source data background layer, a comprehensive visualization situation map is generated.

[0036] Secondly, the present invention provides a data acquisition and repair module, a map construction module, an inference and analysis module, and a visualization display module based on multi-source information fusion.

[0037] The data acquisition and repair module is used to collect multi-source meteorological observation data for preprocessing, and to repair and super-resolution reconstruct defective data through an adversarial network model to generate multi-source time series datasets.

[0038] The graph construction module is used to extract time-series events from multi-source time-series datasets, identify cloud evolution, thermal and dynamic triggering, cloud system development and operation action events related to the weathering operation and use them as nodes to build a time-series knowledge graph covering the period from before to after the operation.

[0039] The reasoning and analysis module is used to perform reasoning and analysis on the time-series knowledge graph using graph neural networks, identify the development and changes of cloud systems and reason about the evolution of cloud physical characteristics, predict the spatiotemporal range of potential operation areas, and generate accurate forecast conclusions and suggestions for artificial weather modification operations.

[0040] The visualization module is used to transform accurate forecast conclusions and suggestions for artificial weather modification operations into a set of visual instructions. It generates a comprehensive visual situation map by highlighting key weather indicators, displaying evolution paths with dynamic arrows, and marking potential operation areas and operation corridors with color overlays.

[0041] The beneficial effects of this invention are as follows: by constructing a temporal knowledge graph covering the period from before to after the operation, a semantic representation of the entire chain of weather evolution and weather modification operation is realized, providing an interpretable data foundation for subsequent intelligent reasoning; by using graph neural networks to perform reasoning analysis on the temporal knowledge graph, the potential areas for operation can be automatically identified from historical patterns and their dynamic evolution can be predicted, thereby improving the foresight and accuracy of weather modification operation decisions. Attached Figure Description

[0042] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a flowchart of a method for displaying information on weather modification operations based on multi-source information fusion.

[0044] Figure 2 This is a schematic diagram of a weather modification operation information display system based on multi-source information fusion.

[0045] Figure 3 A flowchart for generating accurate forecast conclusions.

[0046] Figure 4 A flowchart for generating a comprehensive situational awareness map. Detailed Implementation

[0047] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0048] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0049] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0050] Reference Figures 1-4 This is one embodiment of the present invention, which provides a method for displaying information on weather modification operations based on multi-source information fusion, including the following steps:

[0051] S1. Collect multi-source meteorological observation data, preprocess it, and use an adversarial network model to repair defective data and perform super-resolution reconstruction to generate a multi-source time series dataset.

[0052] Multi-source meteorological observation data includes multi-channel cloud images, brightness temperature, cloud top temperature, precipitation, air pressure, wind speed, wind direction, and surface temperature and humidity;

[0053] It should be noted that multi-channel cloud images are directly captured by multiple spectral channel sensors of meteorological satellites and are used to display water vapor, cloud particles, and surface features at different altitudes; brightness temperature is calculated from the radiation values ​​detected by the satellite's infrared and microwave channels using Planck's formula, representing the radiation temperature of the cloud top or surface in a specific band; cloud top temperature is obtained by inverting brightness temperature data from the meteorological satellite's infrared channels; precipitation is obtained by directly measuring it with ground rain gauges or by inverting it using weather radar reflectivity factors; air pressure is directly measured by air pressure sensors (such as silicon capacitive aneroid barometers) in ground meteorological stations; wind speed is directly measured by wind speed sensors (such as ultrasonic anemometers) in ground meteorological stations; wind direction is directly measured by wind vanes in ground meteorological stations; and surface temperature and humidity are directly measured by temperature and humidity sensors in Stevenson screens in ground meteorological stations.

[0054] Preprocessing includes outlier removal, format standardization, coordinate unification, and spatiotemporal interpolation;

[0055] It should be noted that outlier removal refers to filtering multi-source meteorological observation data using statistical methods (such as the 3σ criterion) to remove erroneous data points that significantly deviate from the reasonable range; format standardization refers to converting multi-source meteorological observation data into the same data format (such as NetCDF) to ensure that data field definitions and units are consistent; coordinate unification refers to converting all spatial reference information from different data sources in multi-source meteorological observation data to a unified geographic coordinate system (such as WGS-84) and projection method (such as Lambert projection) to achieve spatial alignment; and spatiotemporal interpolation refers to interpolating time-series data with inconsistent sampling frequencies and spatial locations in multi-source meteorological observation data onto a unified spatiotemporal grid using the Kriging method.

[0056] Defective data in preprocessed multi-source meteorological observation data is identified and input into an adversarial network model for repair and super-resolution reconstruction to obtain a repaired and enhanced dataset;

[0057] Furthermore, the preprocessed multi-source meteorological observation data is scanned pixel by pixel. Sequence points with consecutive missing values ​​exceeding a specific duration, values ​​exceeding reasonable physical ranges (such as negative precipitation), and outliers exhibiting drastic abrupt changes from surrounding data are marked as defective data. The multi-source meteorological observation data containing defective data, along with valid data from the preprocessed multi-source meteorological observation data, are input into an adversarial network model. The generator in the adversarial network model generates repair content based on the location of the defective data and the contextual information of the surrounding valid data, and merges it with the original valid data. Simultaneously, the data is upsampled to a higher spatial resolution. The discriminator then distinguishes the repaired and reconstructed data from the real, complete, high-resolution data. Through multiple adversarial iterations between the generator and the discriminator, a repaired and enhanced dataset conforming to physical laws is output.

[0058] It should be noted that, in the specific operation of pre-training the adversarial network model, complete and high-quality multi-source meteorological observation data from historical periods are used as training samples. Various types of defect patterns (such as random missing points, block missing data, and noise addition) are randomly generated in the training samples to simulate defects in real data. The training samples with simulated defects are input into the generator of the adversarial network model, and the generator outputs the repaired data. The repaired data and the original complete high-resolution training samples are input into the discriminator of the adversarial network model. The discriminator learns to distinguish between real data and generated data. Through repeated iterative adversarial processes, the reconstruction error of the generated data is minimized and the discriminator's discrimination ability is maximized until the adversarial network model can stably output high-quality repair results, thus completing the pre-training of the adversarial network model.

[0059] The repaired and enhanced dataset is fused with the effective data from the preprocessed multi-source meteorological observation data to generate a multi-source time-series dataset;

[0060] Furthermore, within a unified spatiotemporal grid framework, precise spatiotemporal matching is performed on the effective data in the repaired and enhanced dataset and the preprocessed multi-source meteorological observation data to ensure that the latitude and longitude coordinates of each data point are perfectly aligned with the timestamp. A weighted fusion strategy based on data source quality and spatiotemporal integrity is adopted. For grid points with effective observations in the preprocessed multi-source meteorological observation data, the values ​​in the preprocessed multi-source meteorological observation data are retained first. For grid points marked as defective and repaired by the adversarial network model, the interpolated values ​​in the repaired and enhanced dataset are used. All effective values ​​from the repaired and enhanced dataset and the preprocessed multi-source meteorological observation data are merged to generate a multi-source time-series dataset.

[0061] S2. Extract time-series events from the multi-source time-series dataset, identify cloud evolution, thermal and dynamic triggering, cloud system development and operation action events related to the weathering operation, and use them as nodes to construct a time-series knowledge graph covering the period from before to after the operation.

[0062] Extract variable data related to cloud microphysics, thermodynamics, and operation records from multi-source time-series datasets, and load entities, relationships, and constraint rules from the cloud weathering operation knowledge ontology to generate a time-series dataset of operation physical variables.

[0063] Furthermore, based on the entity attributes defined in the cloud weathering operation knowledge ontology, corresponding physical variables are selected from multi-source time-series datasets, including cloud microphysical categories (such as cloud water content and cloud ice content), thermodynamic categories (such as convective available potential energy and wind shear), and operation record categories (such as catalyst seeding amount and operation platform location). Entity types (such as operable cloud systems and operation windows), inter-entity relationships (such as "having operation conditions" and "belonging to operation type"), and constraint rules (such as temperature thresholds for catalytic operations and atmospheric stability conditions for safe operations) defined in the cloud weathering operation knowledge ontology are loaded. The selected physical variables are mapped and associated with the entity types, inter-entity relationships, and physical constraint rules defined in the cloud weathering operation knowledge ontology to ensure that each physical variable is given a clear meteorological meaning and operational context. The mapped and associated physical variables with operational semantic annotations are integrated to generate an operational physical variable time-series dataset containing cloud water content time-series data, energy time-series data (convective available potential energy), and wind shear time-series data.

[0064] It should be noted that the knowledge ontology of weather modification operations defines the core concepts, conceptual attributes, relationships between concepts, and constraint rules in the field of weather modification. The constraint rules are logical judgment conditions (such as triggering conditions, safety thresholds, and operating procedures) derived from meteorological principles and operational experience. The temperature threshold refers to the critical value of cloud top temperature or cloud interior temperature required for catalytic operations. It is set based on the temperature conditions required for the presence of supercooled water in cloud microphysics processes, with an exemplary value range of ≤-4℃, to ensure that catalytic operations can effectively induce ice crystal growth in a suitable thermal stratification. The atmospheric stability condition for safe operations refers to the maximum permissible wind speed to ensure the safety of weather modification operations. It is set based on the stability requirements of the operation platform (such as aircraft or rockets) and the accuracy requirements of catalyst dissemination, with an exemplary value range of KI<32, to prevent severe convective weather from affecting operational safety.

[0065] Using a sliding window and abrupt change detection algorithm, event detection is performed on the time series dataset of operational physical variables to identify abrupt changes in cloud water content, energy jump points, and wind shear inflection points, generating a candidate fragment set of operational decision events.

[0066] Furthermore, a sliding window of fixed time length is set and moves sequentially along the time axis of the time series dataset of operational physical variables. A mutation point detection algorithm is applied to the time series data of cloud water content, energy, and vertical wind shear within each sliding window to identify points where cloud water content values ​​change abruptly, energy values ​​jump, and wind shear values ​​reverse their trends. A fixed time interval is extended forward and backward around each identified mutation point, jump point, and inflection point to form an event segment. All identified event segments centered on cloud water content mutation points, energy jump points, and wind shear inflection points are collected to form a candidate segment set for operational decision events.

[0067] The candidate fragment set of operation decision events is matched and fused with the event patterns in the knowledge ontology of weather modification operations, and clustered to form a set of weather modification operation event instances;

[0068] Furthermore, each event fragment in the candidate event fragment set containing cloud water content mutation points, energy jump points, and wind shear inflection points is semantically and spatiotemporally matched with predefined event patterns in the cloud weathering operation knowledge ontology to determine whether the features of the event fragment meet the triggering conditions of a specific event pattern: when the cloud water content mutation point value in the event fragment exceeds the cloud water content threshold, the energy jump point value exceeds the convective effective potential energy threshold, and the value at the wind shear inflection point also exceeds the vertical wind shear threshold, the event fragment is determined to meet the triggering condition of the specific event pattern "possessing operational catalytic conditions" defined in the cloud weathering operation knowledge ontology; for multiple event fragments that are spatiotemporally close and meet the same event pattern or multiple event patterns, clustering is performed based on the continuity of timestamps and the proximity of spatial locations, merging multiple event fragments describing the same physical process into a composite event and assigning a unique identifier, while recording the start and end times, spatial range, and event fragment type to generate a cloud weathering operation event instance set.

[0069] It should be noted that the event pattern is a standard template that is pre-formulated in the artificial weather modification operation knowledge ontology, based on meteorological principles and experience in artificial weather modification operations, and represents typical weather processes or operational scenarios. The cloud water content threshold is set based on the supercooled water conditions required for catalytic operations. An exemplary value range is greater than 0.01 g / m³. If it is less than 0.01 g / m³, there is insufficient supercooled water in the cloud, and the catalytic operation cannot induce effective ice crystal growth and precipitation.

[0070] Define a node type and assign spatiotemporal attributes to each shadow operation event instance in the shadow operation event instance set to generate a temporal knowledge graph node set;

[0071] Furthermore, each weather modification event instance in the set of weather modification event instances is traversed. Based on the event pattern matched when the weather modification event instance is clustered, a node type is defined for the weather modification event instance (including "operable cloud system event node", "power-triggered event node", and "catalytic operation event node"). The start time, end time, and spatial range coordinates of the weather modification event instance are extracted from the event fragments in the weather modification event instance as spatiotemporal attributes and assigned to the corresponding weather modification event instance node. A globally unique node identifier is also assigned, and the nodes are aggregated to generate a temporal knowledge graph node set.

[0072] Based on the node set of the temporal knowledge graph, the temporal relationship between nodes is mined, and the causal relationship is inferred by combining the operation rules to generate a candidate set of events related to the weather modification operation;

[0073] Furthermore, the temporal attributes of each pair of weather modification event instance nodes in the temporal knowledge graph node set are compared, and the temporal relationship between them (including "before", "after", and "overlap") is determined. For weather modification event instance node pairs with temporal relationships, the constraint rules defined in the weather modification operation knowledge ontology are loaded. The constraint rules stipulate the temporal logic that must be satisfied between events. It is determined whether the weather modification event instance node that occurred earlier may cause the occurrence of the weather modification event instance node that occurred later (e.g., whether "nodes with operation catalytic conditions" may trigger "operable cloud system event nodes"). For each pair of weather modification event instance nodes that satisfy the temporal relationship and are verified by the constraint rules to have causal possibility, a directed edge is created. The edge type is causal relationship, and the edges are aggregated to generate a candidate set of weather modification operation event relationships.

[0074] Using event instance nodes of weather modification operations as vertices and candidate sets of relationships of weather modification operations as edges, embedding time axis and spatial coordinates, a temporal knowledge graph covering the period from before to after the operation is constructed.

[0075] Furthermore, the event instance nodes of human shadowing operations in the temporal knowledge graph node set are set as vertices, and the node type and spatiotemporal attributes of each event instance node are used as attributes of the vertex; each edge in the candidate set of human shadowing operation event relations is used as a directed edge connecting the corresponding vertex, and the edge attribute is the causal relationship type; the temporal attributes (start time and end time) of each event instance node of human shadowing operations are embedded into the vertex as the vertex's time axis attribute, and the spatial range coordinates of each event instance node of human shadowing operations are embedded into the vertex as the vertex's spatial coordinate attribute; through vertices and edges, a graph structure is constructed, containing all event instance nodes of human shadowing operations and causal relationship edges from before the operation (such as dynamic triggering events) to during the operation (such as catalytic operation events) and after the operation (such as precipitation enhancement events), forming a temporal knowledge graph covering the period from before the operation to after the operation.

[0076] S3. Utilize graph neural networks to perform reasoning analysis on time-series knowledge graphs, identify cloud system development and changes, infer the evolution of cloud microphysical characteristics, predict the spatiotemporal range of potential operation areas, and generate accurate forecast conclusions and suggestions for artificial weather modification operations.

[0077] The node attributes, edge relationships, and timestamps in the temporal knowledge graph are feature-encoded and aligned, and then transformed into temporal graph tensor objects.

[0078] Furthermore, the attributes of each shadow operation event instance node in the temporal knowledge graph are numerically encoded. Node attributes include node type and spatiotemporal attributes. The node type is converted into a vector using one-hot encoding, the spatial coordinates in the spatiotemporal attributes are converted into latitude and longitude values, and the time attribute is converted into a relative timestamp relative to the start time of the operation. The edge relationships in the temporal knowledge graph are encoded, mapping the causal relationship type to a specific integer index. The absolute timestamps associated with each node and edge in the temporal knowledge graph are standardized and converted into a unified relative time representation. The encoded node attribute vectors are combined into a node feature matrix, the encoded edge relationship indexes are combined with the start and end node indices of the edges to form an edge index tensor, and the processed timestamps are combined into a time tensor. The node feature matrix, edge index tensor, edge relationship type tensor, and time tensor are aligned and encapsulated to generate a temporal graph tensor object.

[0079] The temporal graph tensor object is input into the graph neural network, and the low-dimensional vector representation of the node is obtained through forward propagation.

[0080] Furthermore, the node feature matrix, edge index tensor, edge relation type tensor, and time tensor from the time sequence graph tensor object are loaded into the input layer of the graph neural network. The graph neural network, through a message passing mechanism, transmits and aggregates information between adjacent shadowing operation event instance nodes along the connection relationships defined by the edge index tensor in the time sequence graph tensor object. During the aggregation process, different weights are assigned to different types of causal relationships in combination with the edge relation type tensor, and the time tensor is used to weighted integrate the information in the temporal neighborhood. After iterative message passing and feature transformation of the multi-layer graph neural network, the features of each shadowing operation event instance node are updated and condensed into a low-dimensional vector representation of the node.

[0081] It should be noted that the pre-trained graph neural network (GNN) involves using a historical temporal knowledge graph containing labeled event instance nodes and causal relationship edges for weather modification operations covering various typical weather scenarios. This historical temporal knowledge graph is converted into a temporal graph tensor object and directly input into the GNN for forward propagation computation to obtain low-dimensional vector representations of the nodes. Link prediction is used as a self-supervised pre-training task, which involves randomly removing some causal relationship edges from the historical temporal knowledge graph and requiring the GNN to predict the probability of the removed causal relationship edges existing based on the learned node representations. By calculating the loss between the predicted results and the actual causal relationship edges, the parameters of the GNN are iteratively optimized using the backpropagation algorithm. Training ends when the performance of the GNN on the link prediction task stabilizes, resulting in a GNN that has learned knowledge of the weather modification operation domain.

[0082] By analyzing the attention weights of the graph neural network, high-weight path subgraphs connecting thermal-dynamic triggering events and working cloud systems-catalytic events are identified, and a set of evolutionary subgraphs is obtained.

[0083] Furthermore, the edge attention weight matrix is ​​extracted from the last convolutional layer of the graph neural network. The edge attention weight matrix is ​​an N×N sparse matrix (N is the total number of nodes), and each non-zero element represents the attention weight value of an edge. Each edge in the edge attention weight matrix is ​​traversed, and if the attention weight of an edge is greater than or equal to a preset attention weight threshold, it is marked as a high-weight edge. For all marked high-weight edges, a depth-first search-based connected subgraph extraction is performed: starting from any high-weight edge, other high-weight edges connected to the node are recursively searched until no further expansion is possible, thus forming a connected path subgraph. The subgraph is classified according to the type of nodes connected by the edges: if the edges in the path subgraph mainly connect "thermal triggering event" nodes and "dynamic triggering event" nodes, it is classified as a thermal-dynamic triggering event high-weight path subgraph; if the edges in the path subgraph mainly connect "workable cloud system" nodes and "catalytic event" nodes, it is classified as a workable cloud system-catalytic event high-weight path subgraph. All extracted and classified high-weight path subgraphs are collected to form an evolutionary subgraph set.

[0084] It should be noted that the attention weight threshold is determined by grid search based on the performance of the link prediction task (such as F1 score) on the reserved validation set in the historical time-series knowledge graph. An exemplary value range is 0.5-0.9. Below 0.5, too many low-weight edges will be retained, resulting in the subgraph containing a large number of irrelevant connections and reducing the accuracy of pattern recognition. Above 0.9, effective edges will be over-filtered, resulting in the breakage of important causal paths and the loss of key evolutionary patterns.

[0085] Decode the evolutionary patterns of cloud systems, operational window thresholds, and corridor constraints from the low-dimensional vector representations of nodes in the evolutionary subgraph set to generate a fusion-quantified rule set;

[0086] Furthermore, for the high-weighted path subgraph of thermal-dynamic triggering events in the evolutionary subgraph set, low-dimensional vector representations of all "thermal triggering event" nodes and "dynamic triggering event" nodes are collected, and attention weights of the edges connecting the nodes are obtained. Based on the attention weights of the edges, a weighted average is performed on the original convective effective potential energy peak value corresponding to each "thermal triggering event" node to obtain the thermal condition threshold, and a weighted average is performed on the original vertical wind shear peak value corresponding to each "dynamic triggering event" node to obtain the dynamic condition threshold. The thermal condition threshold and the dynamic condition threshold directly constitute the quantitative judgment criteria for the operational catalytic conditions. When the real-time observed convective effective potential energy and vertical wind shear values ​​exceed these two thresholds, the operational catalytic conditions are determined to be met. The event nodes in the high-weighted path subgraph of thermal-dynamic triggering events are statistically analyzed. The time difference sequence between events is used to calculate the mean and standard deviation as time constraints for the evolution law. The spatial distance sequence between event nodes is statistically analyzed, and the mean is calculated as the spatial scale of the evolution law. For the high-weight path subgraph of the workable cloud system-catalytic event, the low-dimensional vector representations of all "workable cloud system" nodes and the attention weights of the edges connected to the "catalytic event" nodes are collected. The original cloud water content peak and cloud top temperature extreme value corresponding to the "workable cloud system" node are weighted and averaged according to the attention weight to obtain the work window threshold. The spatial offset vector of the "catalytic event" node relative to the connected "workable cloud system" nodes is statistically analyzed, and the typical values ​​of direction and distance are calculated as work corridor constraints. All the decoding trigger conditions, evolution laws, work window thresholds and corridor constraints are integrated to generate a fusion quantification rule set.

[0087] The expression for obtaining the job corridor constraints is:

[0088] ;

[0089] in, It is a work corridor constraint; Represents a point in geographic space, used to define the boundary of the work corridor; It is the path centerline, representing the movement path of the operable cloud system nodes; This is the lateral safety distance, used to define the width of the work corridor; Point To the center line of the path The distance; It is a two-dimensional plane in Euclidean space, used to represent a continuous geographic coordinate space;

[0090] It should be noted that before obtaining the operational corridor constraints, the latitude and longitude coordinates (unit: degrees) are uniformly converted to plane rectangular coordinates (unit: meters or kilometers) through map projection transformation (such as UTM or Lambert projection) to ensure the consistency of spatial dimensions before performing distance calculation and buffer analysis. The derivation process of the expression for obtaining the operational corridor constraints is as follows: Based on the spatiotemporal attributes (current position and movement vector) of the operational cloud system event nodes, the path centerline is generated by linear extrapolation. According to the constraint rules in the artificial weathering operation knowledge ontology, buffer analysis is performed on the path centerline. By calculating the Euclidean distance from any point in the geographic space to the path centerline, the set of points whose Euclidean distance is less than or equal to the lateral safety distance is selected, and the altitude constraint conditions (such as a fan-shaped area with an altitude between 3-5 kilometers) are superimposed to form the three-dimensional geographic range of the operational corridor.

[0091] It should be noted that the evolution pattern refers to the inherent pattern of the evolution of thermal and dynamic triggering events in time and space during severe convective weather processes. Specifically, it is quantified as the typical time difference between the successive occurrence of key events and the typical spatial scale of the spread of the event's impact range. The operational window threshold refers to the critical value that the key meteorological parameters must reach to determine whether an entity is qualified to carry out artificial weather modification operations. Specifically, it is quantified as cloud microphysical and thermodynamic indicators (such as cloud water content needing to be consistently ≥0.01g / m³ and the temperature in the operational area needing to be between -4℃ and 15℃). The corridor constraint refers to the spatial range restrictions that catalytic operations must follow to ensure operational safety and effectiveness, and is limited by the safety radiation boundaries of each operational point.

[0092] Based on the fusion quantification rule set, the spatiotemporal range of the operational potential area is obtained by extrapolating the terminal nodes representing hazardous weather events in time and space. The operational window time interval and the geographical range of the operational corridor are obtained by extrapolating the terminal nodes representing operational cloud systems in time and space.

[0093] Furthermore, the latest-occurring terminal node in the evolutionary subgraph set, whose node type is "dangerous weather event" (such as heavy precipitation event), is identified. Based on the evolutionary pattern decoded by the fusion quantization rules (i.e., the movement speed and direction of the event node's influence range), a linear extrapolation method is used to extrapolate the current spatial range of the terminal node along the movement direction and speed to obtain its spatial location within a future period, i.e., the spatiotemporal range of the operational potential area. Terminal nodes of the node type "operable cloud system" are identified. If the physical attributes of the terminal node at the current moment (such as cloud water content and cloud top temperature) simultaneously reach or exceed the operational window threshold, it is determined to be... If the conditions for operation catalysis are met, the time interval from the current moment to the end of the life cycle of the terminal node is determined as the operation window time interval. If any attribute fails to meet the standard, the conditions are not met and no operation window is generated. For terminal nodes that meet the conditions, the vector extrapolation method is used. The current position of the terminal node is taken as the starting point of the path, and the endpoint is calculated based on the movement speed and the effective operation duration in the fusion quantification rule set. The starting point and the endpoint are connected to form a centerline. Based on the centerline, the horizontal safety distance given in the fusion quantification rule set is extended to both sides to generate a strip area with the centerline as the central axis and a total width of twice the horizontal safety distance as the geographical range of the operation corridor.

[0094] By integrating the time interval of the operation window with the geographical range of the operation corridor, suggestions for artificial weather modification operations are generated.

[0095] Furthermore, the operation window time interval is aligned with the geographical range of the operation corridor in the spatiotemporal dimension; each moment of the operation window time interval is bound to the spatial location of the geographical range of the operation corridor at the corresponding moment, generating a continuous spatial region that dynamically changes over time as the spatiotemporal domain of the operation; preset operation action parameters are assigned to the spatiotemporal domain of the operation, generating suggestions for artificial weathering operations.

[0096] It should be noted that the operational parameters include catalyst type, catalyst quantity per unit time, and operating platform cruising altitude, which are determined based on historical operational performance evaluation data by statistically analyzing the median of the parameters corresponding to the optimal operational performance.

[0097] Based on the preset forecast level standards, the spatiotemporal range of the potential operation area is matched with rules and the severity is assessed to generate accurate forecast conclusions;

[0098] Furthermore, based on the preset forecast level standards, the intensity of predicted weather phenomena (such as maximum wind speed in the next hour and cumulative precipitation in the next 3 hours) within each spatiotemporal grid of the operational potential area is determined one by one: if the hourly maximum wind speed predicted by the spatiotemporal grid reaches or exceeds the wind speed threshold of the blue gale forecast, the spatiotemporal grid is determined to reach the blue gale forecast level; if the cumulative precipitation predicted by the spatiotemporal grid in 3 hours simultaneously reaches the rainfall threshold of the orange rainstorm forecast, the spatiotemporal grid is determined to be a higher-level orange rainstorm forecast according to the principle of choosing the higher threshold. The proportion of spatiotemporal grids reaching the orange or higher forecast level within the spatiotemporal range of the operational potential area is counted to the total number of spatiotemporal grids. The duration of high-level forecasts continuously covering the same geographical area is calculated. If the proportion exceeds the preset spatial coverage threshold and the duration exceeds the preset time range, the overall risk is assessed as high severity. The spatial boundaries, risk types, forecast level distribution, and severity of the spatiotemporal range of the operational potential area are integrated to generate accurate forecast conclusions.

[0099] S4. Transform accurate forecast conclusions and suggestions for artificial weather modification operations into a set of visual instructions, and generate a comprehensive visual situation map by highlighting core weather indicators, displaying evolution paths with dynamic arrows, and marking potential operation areas and operation corridors with color coverage.

[0100] Extract target cloud system parameters, evolution paths, and polygon coordinates of potential operation areas from accurate forecast conclusions, and generate a set of visual elements by combining artificial weathering operation suggestions;

[0101] Furthermore, the key meteorological element numerical fields in the accurate forecast conclusions are read, and the "maximum wind speed value" and "cumulative precipitation value" are directly extracted as cloud system index parameters for the operation target. The data segments in the accurate forecast conclusions used to describe the movement trajectory of the operation catalytic phenomenon (usually composed of a series of geographic coordinate points arranged in chronological order) are analyzed, and the geographic coordinate points are connected in chronological order to form an evolution path. At the same time, the set of geographic coordinates used in the accurate forecast conclusions to define the boundary of the operation potential area is located as the polygon coordinates of the operation potential area. The cloud system index parameters of the operation target, the evolution path, the polygon coordinates of the operation potential area are integrated with the operation window time interval, the geographic boundary coordinates of the operation corridor, and the operation action parameters in the artificial weather modification operation suggestions to form a set of visualized elements.

[0102] Based on preset visualization rules, the set of visualization elements is mapped to specific commands that the graphics rendering engine can execute, generating a visualization instruction set;

[0103] Furthermore, based on preset visualization rules, the polygon coordinates of the potential work area are mapped to a drawing command with red semi-transparent fill, the evolution path coordinate sequence is mapped to a drawing command with blue gradient lines with arrows, the cloud system index parameters of the work target are mapped to a rendering command with text labels at specific locations, the geographical boundary coordinates of the work corridor are mapped to a drawing command with green dashed borders, and the time interval of the work window is mapped to a marking command with highlighted segments on the time axis. All the commands generated for different visualization elements are combined in the rendering order to generate a visualization command set.

[0104] It should be noted that the visualization rules are specifications set by defining the mapping relationship between data attributes and visual channels, based on meteorological industry mapping standards and human-computer interaction cognitive principles.

[0105] Execute the visualization instruction set to drive the graphics rendering engine to create a color overlay layer for the potential area of ​​the task, a dynamic arrow layer for the evolution path, a highlight layer for the indicator parameters, a semi-transparent pipe layer for the task corridor, and a countdown marker layer for the task window, thereby generating a set of visualization layers.

[0106] Furthermore, the instructions in the visualization instruction set regarding drawing the color overlay layer of the task potential area are parsed, and the underlying graphics application interface is called to create a new layer. The layer is filled and rendered according to the polygon coordinates and color parameters of the task potential area in the instructions, generating the color overlay layer of the task potential area. At the same time, the instructions regarding drawing the dynamic arrow layer of the evolution path, the indicator parameter highlight layer, the semi-transparent pipe layer of the task corridor, and the countdown marker layer of the task window are parsed in turn. For each instruction, the graphics rendering engine creates a new layer and generates the dynamic arrow layer of the evolution path according to the coordinate sequence and arrow style of the evolution path in the instructions. It generates the indicator parameter highlight layer according to the indicator parameters and location of the task target cloud system in the instructions. It generates the semi-transparent pipe layer of the task corridor according to the geographical boundary coordinates and transparency of the task corridor in the instructions. It generates the countdown marker layer of the task window according to the time interval and marker style of the task window in the instructions. The rendered task potential area color overlay layer, dynamic arrow layer of the evolution path, indicator parameter highlight layer, semi-transparent pipe layer of the task corridor, and countdown marker layer of the task window are then combined into a visualization layer set.

[0107] Data matching the spatiotemporal range of the operational potential area is extracted from the multi-source time-series dataset and rendered to generate a multi-source data background layer;

[0108] Furthermore, using the spatiotemporal range of the operational potential area in the accurate forecast conclusion as a screening criterion, a subset of data (including meteorological radar reflectivity, satellite cloud image brightness temperature, and ground station observation data) that completely overlaps or intersects with the spatiotemporal range of the operational potential area in time and space is extracted from the multi-source time-series dataset. The extracted multi-source data subsets are then subjected to standardized rendering processing, with the meteorological radar reflectivity data rendered as a color patch map, the satellite cloud image brightness temperature data rendered as a grayscale map, and the ground station observation data rendered as a station symbol-filled map. The rendered multi-source data subsets are then combined into a composite image according to a preset layer overlay order to generate a multi-source data background layer.

[0109] It should be noted that the layer stacking order is set based on the perspective relationship of the data source (such as geographic information as the bottom layer, satellite cloud imagery covering it, and radar echo at the top layer) and visual importance.

[0110] By overlaying and merging the visualization layer set with the multi-source data background layer, a comprehensive visualization situation map is generated;

[0111] Furthermore, the multi-source data background layer is loaded as the underlying base image. Following the defined order of each layer in the visualization layer set, the color overlay layer of the operational potential area, the dynamic arrow layer of the evolution path, the highlight layer of the indicator parameters, the semi-transparent pipe layer of the operational corridor, and the countdown marker layer of the operational window are sequentially overlaid on the multi-source data background layer. During the overlay process, it is ensured that the geographic coordinates of each layer are strictly aligned with the multi-source data background layer. During the fusion process, a semi-transparent blending mode is used for the color overlay layer of the operational potential area to ensure that it does not affect the display of the underlying multi-source data background layer, a brightening blending mode is used for the semi-transparent pipe layer of the operational corridor to highlight it, and an overlay mode is used for the dynamic arrow layer and the countdown marker layer to ensure that the dynamic effect is clearly visible, generating a comprehensive visualization situation map.

[0112] This embodiment also provides a data display system for weather modification operations based on multi-source information fusion, including: a data acquisition and repair module, a map construction module, an inference and analysis module, and a visualization display module;

[0113] The data acquisition and repair module is used to collect multi-source meteorological observation data for preprocessing, and to repair and super-resolution reconstruct defective data through an adversarial network model to generate multi-source time series datasets.

[0114] The graph construction module is used to extract time-series events from multi-source time-series datasets, identify cloud evolution, thermal and dynamic triggering, cloud system development and operation action events related to the weathering operation and use them as nodes to build a time-series knowledge graph covering the period from before to after the operation.

[0115] The reasoning and analysis module is used to perform reasoning and analysis on the time-series knowledge graph using graph neural networks, identify the development and changes of cloud systems and reason about the evolution of cloud microphysical characteristics, predict the spatiotemporal range of potential operation areas, and generate accurate forecast conclusions and suggestions for artificial weather modification operations.

[0116] The visualization module is used to transform accurate forecast conclusions and suggestions for artificial weather modification operations into a set of visual instructions. It generates a comprehensive visual situation map by highlighting key weather indicators, displaying evolution paths with dynamic arrows, and marking potential operation areas and operation corridors with color overlays.

[0117] This embodiment also provides a computer device applicable to the method for displaying information on weather modification operations based on multi-source information fusion, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the method for displaying information on weather modification operations based on multi-source information fusion as proposed in the above embodiment.

[0118] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0119] This embodiment also provides a storage medium storing a computer program. When executed by a processor, the program implements the method for displaying artificial weather modification operation information based on multi-source information fusion as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0120] In summary, this invention achieves a full-chain semantic representation of weather evolution and weather modification operations by constructing a temporal knowledge graph covering the entire process from before to after the operation, providing an interpretable data foundation for subsequent intelligent reasoning; and by using graph neural networks to perform reasoning analysis on the temporal knowledge graph, it enables the automatic identification of potential operation areas from historical patterns and the prediction of their dynamic evolution, thereby improving the foresight and accuracy of weather modification operation decisions.

[0121] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for displaying information on weather modification operations based on multi-source information fusion, characterized in that: include, Multi-source meteorological observation data were collected and preprocessed. Then, an adversarial network model was used to repair defective data and perform super-resolution reconstruction, generating a multi-source time-series dataset, including: Defective data in preprocessed multi-source meteorological observation data is identified and input into an adversarial network model for repair and super-resolution reconstruction to obtain a repaired and enhanced dataset; The repaired and enhanced dataset is fused with the effective data from the preprocessed multi-source meteorological observation data to generate a multi-source time-series dataset; Extracting time-series events from multi-source time-series datasets, including: Extract variable data related to cloud microphysics, thermodynamics, and operation records from multi-source time-series datasets, and load entities, relationships, and constraint rules from the cloud weathering operation knowledge ontology to generate a time-series dataset of operation physical variables. Using a sliding window and abrupt change detection algorithm, event detection is performed on the time series dataset of operational physical variables to identify abrupt changes in cloud water content, energy jump points, and wind shear inflection points, generating a candidate fragment set of operational decision events. The candidate fragment set of operation decision events is matched and fused with the event patterns in the knowledge ontology of weather modification operations, and clustered to form a set of weather modification operation event instances; Identify cloud evolution, thermal and dynamic triggering, cloud system development, and operational events related to cloud weathering operations and use them as nodes to construct a temporal knowledge graph covering the period from before to after the operation. By utilizing graph neural networks to perform reasoning analysis on time-series knowledge graphs, we can identify cloud system development and changes, infer the evolution of cloud physical characteristics, predict the spatiotemporal extent of potential weather modification areas, and generate accurate forecast conclusions and weather modification operation suggestions, including: Decode the evolutionary patterns of cloud systems, operational window thresholds, and corridor constraints from the low-dimensional vector representations of nodes in the evolutionary subgraph set to generate a fusion-quantified rule set; Based on the fusion quantification rule set, the spatiotemporal range of the operational potential area is obtained by extrapolating the terminal nodes representing hazardous weather events in time and space. The operational window time interval and the geographical range of the operational corridor are obtained by extrapolating the terminal nodes representing operational cloud systems in time and space. By integrating the time interval of the operation window with the geographical range of the operation corridor, suggestions for artificial weather modification operations are generated. Based on the preset forecast level standards, the spatiotemporal range of the potential operation area is matched with rules and the severity is assessed to generate accurate forecast conclusions; The accurate forecast conclusions and suggestions for artificial weather modification operations are transformed into a set of visual instructions. By highlighting key weather indicators, displaying evolution paths with dynamic arrows, and marking potential operation areas and operation corridors with color coverage, a comprehensive visual situation map is generated.

2. The method for displaying artificial weathering operation information based on multi-source information fusion as described in claim 1, characterized in that: The preprocessing includes outlier removal, format standardization, coordinate unification, and spatiotemporal interpolation.

3. The method for displaying artificial weathering operation information based on multi-source information fusion as described in claim 1, characterized in that: The steps for constructing a time-series knowledge graph covering the period from before to after the task are as follows. Define a node type and assign spatiotemporal attributes to each shadow operation event instance in the shadow operation event instance set to generate a temporal knowledge graph node set; Based on the node set of the temporal knowledge graph, the temporal relationship between nodes is mined, and the causal relationship is inferred by combining the operation rules to generate a candidate set of events related to the weather modification operation; Using event instance nodes of weather modification operations as vertices and candidate sets of event relationships of weather modification operations as edges, and embedding time axes and spatial coordinates, a temporal knowledge graph covering the period from before to after the operation is constructed.

4. The method for displaying artificial weathering operation information based on multi-source information fusion as described in claim 1, characterized in that: The steps for identifying the development and changes of cloud systems are as follows: The node attributes, edge relationships, and timestamps in the temporal knowledge graph are feature-encoded and aligned, and then transformed into temporal graph tensor objects. The temporal graph tensor object is input into the graph neural network, and the low-dimensional vector representation of the node is obtained through forward propagation. By analyzing the attention weights of the graph neural network, high-weight path subgraphs connecting thermal-dynamic triggering events and working cloud systems-catalytic events are identified, and a set of evolutionary subgraphs is obtained.

5. The method for displaying information on weather modification operations based on multi-source information fusion as described in claim 1, characterized in that: The steps for converting accurate forecast conclusions and artificial weather modification operation suggestions into a visual instruction set are as follows. Extract target cloud system parameters, evolution paths, and polygon coordinates of potential operation areas from accurate forecast conclusions, and generate a set of visual elements by combining artificial weathering operation suggestions; Based on preset visualization rules, the set of visualization elements is mapped to specific commands that the graphics rendering engine can execute, generating a visualization instruction set.

6. The method for displaying information on weather modification operations based on multi-source information fusion as described in claim 5, characterized in that: The steps for generating the visualized comprehensive situation map are as follows: Execute the visualization instruction set to drive the graphics rendering engine to create a color overlay layer for the potential area of ​​the task, a dynamic arrow layer for the evolution path, a highlight layer for the indicator parameters, a semi-transparent pipe layer for the task corridor, and a countdown marker layer for the task window, thereby generating a set of visualization layers. Data matching the spatiotemporal range of the operational potential area is extracted from the multi-source time-series dataset and rendered to generate a multi-source data background layer; By overlaying and merging the visualization layer set with the multi-source data background layer, a comprehensive visualization situation map is generated.

7. A system for displaying information on weather modification operations based on multi-source information fusion, comprising the method for displaying information on weather modification operations based on multi-source information fusion as described in any one of claims 1 to 6, characterized in that: include, Data acquisition and repair module, map construction module, reasoning and analysis module, visualization display module; The data acquisition and repair module is used to collect multi-source meteorological observation data for preprocessing, and to repair and super-resolution reconstruct defective data through an adversarial network model to generate multi-source time series datasets. The graph construction module is used to extract time-series events from multi-source time-series datasets, identify cloud evolution, thermal and dynamic triggering, cloud system development and operation action events related to the weathering operation and use them as nodes to build a time-series knowledge graph covering the period from before to after the operation. The reasoning and analysis module is used to perform reasoning and analysis on the time-series knowledge graph using graph neural networks, identify the development and changes of cloud systems and reason about the evolution of cloud physical characteristics, predict the spatiotemporal range of potential operation areas, and generate accurate forecast conclusions and suggestions for artificial weather modification operations. The visualization module is used to transform accurate forecast conclusions and suggestions for artificial weather modification operations into a set of visual instructions. It generates a comprehensive visual situation map by highlighting key weather indicators, displaying evolution paths with dynamic arrows, and marking potential operation areas and operation corridors with color overlays.

Images