A method for modeling spatial hysteresis relationships of geographic events

Abstract

The present invention provides a method for modeling spatial lag relationships for geographic events, belonging to the field of data processing technology. The method specifically includes: Step 1: Modeling geographic events in a target area as spatial point elements and geographic factors as spatial surface elements; Step 2: Screening valid causal edges between different geographic events in the spatial point elements based on spatiotemporal rules; Step 3: Modeling an adaptive Gaussian field based on the valid causal edges and spatial surface elements, and outputting a quantitative result of the spatial lag effect. The present invention significantly improves the accuracy and robustness of spatial causal inference through refined filtering and dynamic modeling.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of data processing technology, and in particular to a method for modeling spatial lag relationships of geographic events. Background Art

[0002] Currently, in existing technologies, spatial hysteresis effects are often quantified by the spatial distance between geographical events, but this has the following drawbacks:

[0003] Invalid distance interference: Failure to effectively distinguish between true causal relationships and random spatially adjacent noise distances, resulting in decreased model accuracy;

[0004] Heterogeneous effects are not modeled: The heterogeneity of geographical environment and event type is not incorporated into the spatial lag function, which affects the accuracy of parameter estimation.

[0005] It can be seen that there is an urgent need for a modeling method for the spatial lag relationship of geographic events that can improve the accuracy and robustness of causal inference. Summary of the Invention

[0006] In view of this, an embodiment of the present invention provides a method for modeling spatial lag relationships of geographic events, which at least partially solves the problem of poor accuracy and robustness of causal inference in the prior art.

[0007] An embodiment of the present invention provides a method for modeling spatial hysteresis relationships of geographic events, including:

[0008] Step 1: Model the geographical events in the target area as spatial point features and the geographical factors as spatial surface features;

[0009] Step 2: Screen the effective causal edges between different geographical events in the spatial point elements based on spatiotemporal rules;

[0010] Step 3: Model an adaptive Gaussian field based on the effective causal association edges and spatial surface elements, and output the quantitative results of the spatial lag effect.

[0011] According to a specific implementation method of an embodiment of the present invention, the geographical event includes longitude, latitude, occurrence time and event type, and the geographical factors include natural factors and human factors. Natural factors include topography, climate, soil type and vegetation distribution, and human factors include social and economic activities and engineering construction.

[0012] According to a specific implementation of the embodiment of the present invention, step 2 specifically includes:

[0013] Step 2.1, connect the two geographic events in the spatial point features to form spatial connection edges;

[0014] Step 2.2, set the time sequence rule as: take any geographical event as the central event, for the central event Adjacent events , if the adjacent event Time of occurrence Central events that precede Time of occurrence ,Right now , then delete the central event Adjacent events Corresponding spatial connection edges ;

[0015] Step 2.3, setting the geographic prior knowledge rule as follows: deleting the connection edges that do not conform to the geographic process logic according to the preset invalid causal type table. The invalid causal types include geological disaster events leading to rainfall events, surface deformation events leading to rainfall events, and earthquake events leading to rainfall events.

[0016] Step 2.4: Set the spatial density distribution rule as follows: divide the distance from the central event to the affected event into equal-width annular intervals, calculate the normalized spatial density of each interval, and screen valid connecting edges based on the distance decay, long-range dependency preservation, and noise edge removal rules;

[0017] In step 2.5, the spatial connection edges are screened according to the time sequence rules, geographical prior knowledge rules, and spatial density distribution rules to obtain effective causal association edges.

[0018] According to a specific implementation of an embodiment of the present invention, the expression of the normalized spatial density is:

[0019]

[0020]

[0021] in, The ring interval divided Number of geographical events affected within For the annular area The area, is the width of the divided ring, that is, the equal division step length of the ring.

[0022] According to a specific implementation of the embodiment of the present invention, step 3 specifically includes:

[0023] Step 3.1, calculate the distance of each effective causal relationship edge and the ring interval index ;

[0024] Step 3.2, calculate the hysteresis intensity parameter according to the distance and the index of the ring interval to which it belongs;

[0025] Step 3.3, optimize the standard deviation based on MLE , and combined the hysteresis intensity parameters and spatial surface elements to fit the Gaussian field function and model the adaptive Gaussian field;

[0026] In step 3.4, the spatial hysteresis effect is quantified by outputting the adaptive Gaussian field.

[0027] According to a specific implementation of the embodiment of the present invention, the optimized standard deviation The steps include:

[0028] Construct a likelihood function based on the filtered effective connection edge dataset;

[0029] Optimization via gradient descent or expectation maximization algorithms , so that it maximizes the probability distribution of the observed data.

[0030] According to a specific implementation of an embodiment of the present invention, the expression of the hysteresis intensity parameter is:

[0031]

[0032] in, Indicates the number of divided ring intervals.

[0033] According to a specific implementation of an embodiment of the present invention, the expression of the adaptive Gaussian field is:

[0034]

[0035] in, A spatial polygon feature representing where distances are spatially contained.

[0036] The spatial hysteresis relationship modeling scheme for geographic events in an embodiment of the present invention includes: step 1, modeling the geographic events in the target area as spatial point elements, and modeling the geographic factors as spatial surface elements; step 2, screening the effective causal correlation edges between different geographic events in the spatial point elements based on spatiotemporal rules; step 3, modeling an adaptive Gaussian field based on the effective causal correlation edges and spatial surface elements, and outputting the quantitative results of the spatial hysteresis effect.

[0037] The beneficial effects of the embodiments of the present invention are as follows: through the scheme of the present invention, valid spatial connection edges are screened through a three-level filtering mechanism: 1) the time sequence rule deletes invalid edges whose results are earlier than the causes; 2) the geographical prior rule eliminates edges that violate geographical logic, such as geological disasters causing rainfall; 3) the spatial density distribution rule is combined with the annular interval normalized density calculation to retain edges that meet the distance attenuation and long-range dependency characteristics and eliminate noise. Subsequently, an adaptive Gaussian field model is constructed to quantify the spatial lag effect, whose intensity parameter is dynamically determined by the annular interval density mean, and the standard deviation is optimized by maximum likelihood estimation to characterize the scope of influence. The present invention significantly improves the accuracy of spatial causal inference through refined filtering and dynamic modeling. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0039] Figure 1 A schematic diagram of a flow chart of a method for modeling spatial hysteresis relationships of geographic events provided by an embodiment of the present invention;

[0040] Figure 2 A schematic diagram of a spatial connection edge filtering process provided by an embodiment of the present invention, wherein (a) represents a time sequence rule, (b) represents a geographic prior knowledge rule, and (c) represents a spatial density distribution rule;

[0041] Figure 3 A schematic diagram of parameter fitting of an adaptive Gaussian field model provided by an embodiment of the present invention;

[0042] Figure 4 A schematic diagram of the spatial lag effect of heavy rain events on landslide events provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0044] The following describes the embodiments of the present invention through specific examples. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0045] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present invention, those skilled in the art will appreciate that an aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement an apparatus and / or practice a method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this apparatus and / or practice this method.

[0046] It should also be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. The illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0047] Additionally, in the following description, specific details are provided to provide a thorough understanding of the examples. However, one skilled in the art will appreciate that the aspects described can be practiced without these specific details.

[0048] The shortcomings of existing technologies include: (1) Experimental dependency limitations: The Potential Outcomes Framework requires intervention experiments to estimate causal effects, but geographical events (such as rainfall and earthquakes) are non-interventional, making the model difficult to apply in practice; (2) Insufficient time series data: The Granger Causality model relies on continuous time series data, while geological disaster data (such as landslides and mudslides) usually only provide the spatial distribution and sparse timestamps of events, which cannot meet the needs of time series analysis; (3) Spatial lag and geographical environment neglect: Although structural causal models can express causal relationships through graphical models, they do not quantify spatial lag effects (such as the propagation distance of seismic waves in fragile rock formations) and geographical environment heterogeneity (such as the impact of steep slopes and flat land on rainfall lag distance), resulting in deviations in causal network construction.

[0049] An embodiment of the present invention provides a method for modeling spatial lag relationships of geographic events, which can be applied to geographic time causal inference processes in scenarios such as geological disaster warning and environmental monitoring.

[0050] See also Figure 1 , which is a flow chart of a method for modeling spatial hysteresis relationships of geographic events provided by an embodiment of the present invention. Figure 1 As shown, the method mainly includes the following steps:

[0051] Step 1: Model the geographical events in the target area as spatial point features and the geographical factors as spatial surface features;

[0052] In specific implementation, geographic entities are modeled. Geographic events are specific, observable phenomena within geographic processes, possessing a specific spatial and temporal scope and influence. They are the fundamental units for describing and modeling geographic processes, and therefore are modeled as spatial point features. The geographic environment refers to the spatial context that influences the occurrence of geographic events, including natural factors such as topography, climate, soil type, and vegetation distribution, as well as human factors such as socioeconomic activities and engineering construction. The geographic environment not only spatially constrains the occurrence of geographic events but also, through its interaction with geographic events, influences the formation of spatial lag relationships. Therefore, it is modeled as spatial surface features.

[0053] Step 2: Screen the effective causal edges between different geographical events in the spatial point elements based on spatiotemporal rules;

[0054] When implementing it specifically, Figure 2 As shown in the figure, spatial connection edge filtering is to filter the effective causal edges between geographic events based on spatiotemporal rules. The specific steps include:

[0055] Chronological rules: For central events Adjacent events ,like Time of occurrence , that is, the result is earlier than the cause, then delete the corresponding spatial connection edge ;

[0056] Geographic prior knowledge rules: Delete the connection edges that do not conform to the logic of the geographic process based on the preset invalid causal type table. The invalid causal types include geological disaster events leading to rainfall events, surface deformation events leading to rainfall events, and earthquake events leading to rainfall events. For example, the invalid causal types in the geographic prior knowledge rules include: landslides, debris flows, collapses, ground fissures, ground subsidence or unstable slope events as the connection edges of the cause events and rainfall events as the result events; surface deformation events as the cause events and rainfall events as the result events; earthquake events as the cause events and rainfall events as the result events. The rules for deleting invalid causal connection edges based on geographic prior knowledge are explained in Table 1. Taking geological disaster prior knowledge as an example, invalid causal connection edges are deleted according to the listed rules:

[0057] Table 1

[0058]

[0059] Spatial density distribution rule: Divide the distance from the central event to the affected event into equal-width annular intervals

[0060]

[0061] The equal-width annular interval The partitioning step size is fixed to , and the number of intervals Dynamically adjusted according to the maximum observation distance.

[0062] Calculate the normalized spatial density of each interval:

[0063]

[0064] in:

[0065]

[0066] And based on the distance attenuation, long-range dependency retention and noise edge removal rules, effective spatial lagging edges are screened.

[0067] Specifically, the spatial density distribution rules for screening effective connection edges are explained as shown in Table 2. The rules for screening effective connection edges include:

[0068] Distance decay and proximity: If the normalized density of the neighboring annular interval (small value) If it is significantly higher than the distant neighbor interval, the corresponding connection edge is retained;

[0069] Long-range dependency preservation: If the long-distance interval ( The normalized density of the larger value Exceeding the preset threshold , then keep the corresponding connection edge;

[0070] Noise edge removal: If the density of the nearest neighbor interval approaches zero and the density of the distant neighbor interval is significantly non-zero, the corresponding connecting edge is deleted.

[0071] Table 2

[0072]

[0073] Step 3: Model an adaptive Gaussian field based on the effective causal association edges and spatial surface elements, and output the quantitative results of the spatial lag effect.

[0074] In specific implementation, an adaptive Gaussian function is used to quantify the impact of spatial lag. According to the first law of geography, the closer the distance between two geographical events, the greater the impact on each other. Therefore, the spatial lag effect usually decays with increasing distance. In order to capture this distance decay effect, an adaptive Gaussian random field is constructed based on the spatial distance between geographical events. Specific event lag distance and intensity: The spatial lag distance and the resulting impact intensity are not uniform among all geographical events. Different types of events will have different spatial impact ranges and have different degrees of impact on their surroundings. The spatial lag effect is also affected by the geographical environment in which the event occurs. When the spatial distance between two events is the same, different lag intensities will be generated according to the characteristics of the surrounding environment. An adaptive Gaussian field is constructed for different geographical environments. Its expression is:

[0075]

[0076] In the formula is the intensity of the spatial lag effect, reflecting the source event The degree of influence on surrounding events, each distance Corresponding spatial surface elements There are spatial heterogeneity differences. The intensity of the spatial lag effect Calculated from the spatial density distribution of event connection points, specifically, the intensity of the spatial lag effect It can be estimated by the following formula:

[0077]

[0078] like Figure 3 As shown, the standard deviation The fitting process includes:

[0079] Construct a likelihood function based on the filtered effective connection edge dataset;

[0080] Optimization via gradient descent or expectation maximization algorithms , so that it maximizes the probability distribution of the observed data.

[0081] The constructed Gaussian field is used to construct an adaptive Gaussian field model based on the filtered connection edge data, and the spatial lag effect intensity and influence range parameters are output, and a spatial causal network diagram and a lag effect distribution heat map are generated.

[0082] like Figure 4 As shown in FIG, the modeling process of the spatial lag effect of heavy rain events on landslide events includes:

[0083] Modeling heavy rain events and landslide events as spatial points;

[0084] The effective spatial lag edges of heavy rain events on landslide events are screened based on distance attenuation, long-range dependency retention and noise edge elimination rules.

[0085] According to the different geographical environments where the effective spatial lag edges are located, an adaptive Gaussian field AGF is constructed. According to the output spatial lag effect intensity and influence range parameters, a circular heat map is used to express the spatial lag effect of heavy rain events on landslide events.

[0086] The method for modeling the spatial lag relationship of geographic events provided in this embodiment uses a three-level filtering mechanism to screen valid spatial connection edges: 1) The time sequence rule deletes invalid edges whose results are earlier than the cause; 2) The geographical prior rule eliminates edges that violate geographical logic, such as geological disasters causing rainfall; 3) The spatial density distribution rule is combined with the normalized density calculation of the annular interval to retain edges that meet the distance attenuation and long-range dependence characteristics and eliminate noise. Subsequently, an adaptive Gaussian field model is constructed to quantify the spatial lag effect. Its intensity parameter is dynamically determined by the mean of the annular interval density, and the standard deviation is optimized through maximum likelihood estimation to characterize the scope of influence. The present invention significantly improves the accuracy of spatial causal inference through refined filtering and dynamic modeling.

[0087] The method of the present invention will be further described below by a specific embodiment, and the method mainly comprises the following steps:

[0088] Step 1: Model geographic entities. Model geographic events as spatial point features, which contain four pieces of information: longitude, latitude, occurrence time, and event type. Model them as spatial surface features, which contain spatial location and attribute information.

[0089] Step 2: Spatial connection edge filtering

[0090] Input geographic event dataset, including event type, location and time;

[0091] Delete according to time order rules edge;

[0092] Invalid causal edges are deleted according to the geographical prior rules in Table 1;

[0093] according to Divide the annular area and calculate the density of each interval , apply the rules in Table 2 to filter valid edges.

[0094] Step 3: AGF model construction

[0095] Calculate distances for retained edges and the ring interval index ;

[0096] According to the formula Calculate hysteresis strength parameters;

[0097] Based on MLE optimization , fitting Gaussian field function;

[0098] Output the quantification results of spatial hysteresis effect.

[0099] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware or a combination thereof.

[0100] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for modeling spatial hysteresis relationships of geographic events, characterized by: include: Step 1: Model the geographical events in the target area as spatial point features and the geographical factors as spatial surface features; Step 2: Screen the effective causal edges between different geographical events in the spatial point elements based on spatiotemporal rules; Step 3: Model an adaptive Gaussian field based on the effective causal correlation edges and spatial surface elements, and output the quantitative results of the spatial hysteresis effect; The step 3 specifically includes: Step 3.1, calculate the distance of each effective causal relationship edge and the ring interval index ; Step 3.2, calculate the hysteresis intensity parameter according to the distance and the index of the ring interval to which it belongs; Step 3.3, optimize the standard deviation based on MLE , and combined with the hysteresis intensity parameter and the spatial surface element to fit the Gaussian field function, the adaptive Gaussian field is modeled. The expression of the adaptive Gaussian field is: in, Indicates distance Spatial surface elements that are contained in space; Step 3.4, outputting the quantification result of spatial hysteresis effect through adaptive Gaussian field; The step of optimizing the standard deviation σ comprises: Construct a likelihood function based on the filtered effective connection edge dataset; Optimize σ by gradient descent or expectation maximization algorithm to maximize the probability distribution of the observed data.

2. The method according to claim 1, characterized in that The geographical events include longitude, latitude, occurrence time and event type; the geographical factors include natural factors and human factors; natural factors include topography, climate, soil type and vegetation distribution; human factors include social and economic activities and engineering construction.

3. The method according to claim 2, characterized in that The step 2 specifically includes: Step 2.1, connect the two geographic events in the spatial point features to form spatial connection edges; Step 2.2, set the time sequence rule as: take any geographical event as the central event, for the central event Adjacent events , if the adjacent event Time of occurrence Before the central event Time of occurrence ,Right now , then delete the central event Adjacent events Corresponding spatial connection edges ; Step 2.3, setting the geographic prior knowledge rule as follows: deleting the connection edges that do not conform to the geographic process logic according to the preset invalid causal type table. The invalid causal types include geological disaster events leading to rainfall events, surface deformation events leading to rainfall events, and earthquake events leading to rainfall events. Step 2.4, set the spatial density distribution rule as follows: divide the distance from the central event to the affected event into equal-width annular intervals, calculate the normalized spatial density of each interval, and filter the effective connecting edges based on the distance decay, long-range dependency retention and noise edge removal rules, where the distance decay rule is the normalized density of the neighboring annular intervals. If the normalized density of the distant interval is significantly higher than that of the distant neighbor interval, the corresponding connection edge is retained. The long-range dependency retention rule is that if the normalized density of the distant interval is Exceeding the preset threshold , then the corresponding connection edge is retained, and the noise edge removal rule is that if the density of the neighbor interval approaches zero and the density of the distant neighbor interval is significantly non-zero, then the corresponding connection edge is deleted; In step 2.5, the spatial connection edges are screened according to the time sequence rules, geographical prior knowledge rules, and spatial density distribution rules to obtain effective causal association edges.

4. The method according to claim 3, characterized in that The expression of the normalized spatial density is: in, The ring interval divided Number of geographical events affected within For the annular area The area, is the width of the divided ring, that is, the equal division step length of the ring.

5. The method according to claim 4, characterized in that The expression of the hysteresis strength parameter is in, Indicates the number of divided ring intervals.

Images