Dynamic analysis method for watershed water ecological space

Abstract

The invention discloses a watershed water ecological space dynamic analysis method, and belongs to the technical field of water conservancy project ecological analysis. The method comprises the following steps: acquiring multi-source geographic space data; performing multi-scale symbolization processing on the multi-source geographic space data to generate a multi-level symbol set, and generating a symbol sequence corresponding to the spatial-temporal characteristics of the watershed water ecological space according to the symbol set; a space-time state transition network is constructed based on symbolic dynamics, the space-time state transition network takes a geographic space area as a node and an ecological interaction relation as an edge, and the space-time state transition network is optimized by analyzing a state transition rule and information entropy of a symbol sequence; utilizing a network analysis method to extract dynamic interaction characteristics of the watershed water ecological space from the space-time state transition network, wherein the dynamic interaction characteristics comprise a periodic mode, an abnormal state or a cross-regional cooperation trend; and generating a dynamic monitoring result of the watershed water ecological space based on the dynamic interaction characteristics. According to the invention, accurate monitoring of the dynamic change of the watershed water ecological space is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of ecological analysis of water conservancy projects, and in particular to a method for dynamic analysis of water ecological space in a river basin. BACKGROUND

[0002] Water conservancy and hydropower engineering construction has an adverse impact on the water ecological environment of a river basin, and dynamic analysis of water ecological space is an important research direction for environmental protection and engineering management. Water ecological space in a river basin refers to a geographical space that covers water bodies, riparian zones, wetlands and associated biological communities, and its dynamic changes are driven by hydrological processes and human activities (such as water conservancy projects). Traditional ecological analysis methods usually rely on a single data source (such as remote sensing images or ground sensor data), which makes it difficult to fully capture the spatio-temporal dynamic characteristics of water ecological space in a river basin. In recent years, the fusion analysis of multi-source geographical space data has provided new possibilities for the analysis of water ecological space in a river basin, but existing technologies still have deficiencies in handling the multi-scale characteristics of multi-source data, constructing dynamic interaction networks and extracting complex ecological characteristics. For example, traditional methods lack adaptability in data symbolization processing, making it difficult to dynamically adjust the analysis strategy according to the types and environmental characteristics of water ecological space; at the same time, existing methods lack comprehensive analysis capabilities for periodic patterns, abnormal states and cross-regional collaborative trends in the optimization of spatio-temporal state transition networks and the extraction of dynamic interaction characteristics.

[0003] Therefore, there is an urgent need for an analysis method that can effectively fuse multi-source spatial data, dynamically construct spatio-temporal interaction networks and extract dynamic characteristics of water ecological space. SUMMARY

[0004] The present application provides a method for dynamic analysis of water ecological space in a river basin, which realizes accurate analysis of the dynamic changes of water ecological space, including a monitoring method and a monitoring system.

[0005] The present application provides the following solutions: In a first aspect of the present application, a monitoring method for analyzing the dynamic characteristics of a river basin water ecological space is provided. The method comprises: obtaining multi-source geographic spatial data, including hydrological monitoring data, water conservancy project scheduling logs, remote sensing image data, ground sensor data, and geographic information system data; performing multi-scale symbolization processing on the multi-source geographic spatial data to generate a multi-level symbol set, and generating a symbol sequence corresponding to the spatio-temporal characteristics of the river basin water ecological space according to the symbol set; constructing a spatio-temporal state transition network based on symbol dynamics, wherein the spatio-temporal state transition network takes geographic space regions as nodes and ecological interaction relationships as edges, and the spatio-temporal transition network is optimized by analyzing the state transition rules and information entropy of the symbol sequence; extracting dynamic interaction characteristics of the river basin water ecological space from the spatio-temporal state transition network using network analysis methods, wherein the dynamic interaction characteristics include periodic patterns, abnormal states, or cross-regional collaborative trends; and generating a dynamic monitoring result of the river basin water ecological space based on the dynamic interaction characteristics.

[0006] According to an implementable manner in the embodiments of the present application, preferably, the multi-scale symbolization processing adopts an adaptive partitioning strategy, and dynamically adjusts the partitioning threshold and the number of symbols of the symbol set according to the spatio-temporal resolution, spatial type, and / or environmental characteristics of the multi-source geographic spatial data.

[0007] According to an implementable manner in the embodiments of the present application, preferably, the optimization of the spatio-temporal transition network by analyzing the state transition rules and information entropy of the symbol sequence comprises: calculating a state transition probability matrix according to the symbol sequence, wherein the state transition probability matrix records the transition probability of each geographic space region from one symbol state to another symbol state; calculating a multi-scale entropy analysis index according to the multi-scale characteristics of the multi-level symbol set; and adjusting the node state and edge weight of the spatio-temporal state transition network according to the state transition probability matrix and the multi-scale entropy analysis index.

[0008] According to an implementable manner in the embodiments of the present application, further preferably, the method further comprises: adjusting the dynamic state of the nodes in the spatio-temporal state transition network according to the state transition probability matrix, and merging geographic space regions with similar dynamic behaviors into a single node based on the similarity of the state transition probability.

[0009] According to an implementable manner in the embodiments of the present application, preferably, the dynamic interaction features of the basin water ecological space are extracted from the spatio-temporal state transition network by using a network analysis method, and the dynamic interaction features include periodic patterns, abnormal states, or cross-regional collaborative trends, including: analyzing the spatial distribution characteristics of the multi-source geographic space data, extracting the topological features of spatial proximity and ecological interaction relationship; calculating the spatial correlation weight between nodes in the spatio-temporal state transition network according to the spatial proximity and topological features; combining the spatial correlation weight and the ecological interaction relationship, dynamically adjusting the edge weight and network structure of the spatio-temporal state transition network; using a network analysis method, based on the optimized spatio-temporal state transition network, extracting the dynamic interaction features of the basin water ecological space, including periodic patterns, abnormal states, or cross-regional collaborative trends.

[0010] According to an implementable manner in the embodiments of the present application, further preferably, the dynamic interaction features of the basin water ecological space are extracted from the spatio-temporal state transition network by using a network analysis method, and the dynamic interaction features include periodic patterns, abnormal states, or cross-regional collaborative trends, including: based on the optimized spatio-temporal state transition network, applying a community detection algorithm to identify groups of geographic space regions with similar dynamic interaction features, and dividing the functional zones of the basin water ecological space; based on the spatio-temporal state transition network, calculating the node centrality index to identify geographic space regions that have a key influence on the dynamic interaction of the basin water ecological space; combining the functional zones and key regions, extracting the dynamic interaction features of the basin water ecological space.

[0011] According to an implementable manner in the embodiments of the present application, preferably, the dynamic monitoring results of the basin water ecological space based on the dynamic interaction features include: generating an interactive visual analysis result according to the dynamic interaction features, wherein the interactive visual analysis result includes a spatial distribution map of the periodic patterns, abnormal states, or cross-regional collaborative trends of the basin water ecological space; applying a cross-regional collaborative prediction model to predict the dynamic evolution trend of the basin water ecological space according to the spatio-temporal state transition network and the dynamic interaction features, wherein the cross-regional collaborative prediction model combines the ecological interaction relationship and state transition rule between nodes in the network to generate a cross-regional ecological state prediction; generating a dynamic monitoring report of the basin water ecological space according to the interactive visual analysis result and the cross-regional collaborative prediction result, wherein the dynamic monitoring report includes an ecological state prediction, an abnormal event detection, or a cross-regional trend analysis.

[0012] In a second aspect of the present application, a monitoring system for dynamic analysis of watershed water ecological space is provided, comprising: a data acquisition unit configured to acquire multi-source geospatial data, the multi-source geospatial data including hydrological monitoring data, water conservancy project scheduling logs, remote sensing image data, ground sensor data, and geographic information system data; a symbol set generation unit configured to perform multi-scale symbolization processing on the multi-source geospatial data to generate a multi-level symbol set, and generate a symbol sequence corresponding to the spatio-temporal characteristics of the watershed water ecological space according to the symbol set; a transition network construction unit configured to construct a spatio-temporal state transition network based on symbol dynamics, wherein the spatio-temporal state transition network takes geographical space regions as nodes and ecological interaction relationships as edges, and optimizes the spatio-temporal transition network by analyzing the state transition law and information entropy of the symbol sequence; an interaction feature extraction unit configured to extract dynamic interaction features of the watershed water ecological space from the spatio-temporal state transition network using network analysis methods, the dynamic interaction features including periodic patterns, abnormal states, or cross-regional collaborative trends; and a monitoring result generation unit configured to generate dynamic monitoring results of the watershed water ecological space based on the dynamic interaction features.

[0013] In a third aspect of the present application, a computer-readable storage medium is provided, which stores a computer program, the program being executed by a processor to implement the steps of the monitoring method of the watershed water ecological space dynamic analysis method of any one of the above-mentioned first aspect.

[0014] In a fourth aspect of the present application, an electronic device is provided, comprising: one or more processors; and a memory associated with the one or more processors, the memory being configured to store program instructions, the program instructions being executed by the one or more processors to perform the steps of the monitoring method of the watershed water ecological space dynamic analysis method of any one of the above-mentioned first aspect.

[0015] Compared with the prior art, the present application has the following advantages and beneficial effects: The present application realizes accurate monitoring of dynamic changes of watershed water ecological space by acquiring multi-source geospatial data, combining multi-scale symbolization processing and spatio-temporal state transition network construction. The method generates comprehensive monitoring results by dynamically generating symbol sequences and optimizing network structures, extracting dynamic interaction features such as periodic patterns, abnormal states, and cross-regional collaborative trends. The technical effect lies in effectively fusing multi-source data, adapting to different spatio-temporal resolutions and watershed water ecological space characteristics, improving the accuracy and flexibility of monitoring, and providing scientific basis and visualization support for ecological protection and resource management.

[0016] Of course, implementing any product of the present application does not necessarily require all the advantages described above to be achieved at the same time. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings described below only illustrate some of the embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative effort.

[0018] Figure 1 System architecture diagram applicable to the embodiments of the present application; Figure 2 Flowchart of the monitoring method for the dynamic analysis of the water ecological space of a river basin provided by the embodiments of the present application; Figure 3 Structural block diagram of the monitoring system for the dynamic analysis of the water ecological space of a river basin provided by the embodiments of the present application; Figure 4 Schematic block diagram of an electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art belong to the scope of protection of the present application.

[0020] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms "a", "an" and "the" used in the embodiments of the present application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0021] It should be understood that the term "and / or" used herein is only to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " in this paper generally represents that the front and rear associated objects are a "or" relationship.

[0022] Depending on the context, the word "if" as used herein can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if it is determined" or "if (a stated condition or event) is detected" can be interpreted as "when it is determined" or "in response to determining" or "when (a stated condition or event) is detected" or "in response to detecting (a stated condition or event)".

[0023] Several technologies exist that primarily employ single data sources for analysis or fuse multi-source geospatial data through simple data overlay. Common approaches include vegetation index monitoring based on remote sensing imagery, time-series analysis of ground sensors, or spatial distribution studies using GIS data. However, these methods lack adaptability when dealing with the multi-scale characteristics of multi-source data, making it difficult to dynamically adjust analysis strategies and resulting in insufficient capture of complex ecological interactions. Furthermore, existing technologies have limitations in constructing spatiotemporal dynamic networks and extracting periodic patterns, anomalous states, and cross-regional collaborative trends. The analysis results often lack comprehensiveness and predictive power, failing to meet the needs of spatial monitoring of watershed aquatic ecosystems in complex watersheds.

[0024] In view of this, this application provides a new approach. To facilitate understanding of this application, the system architecture on which this application is based will first be described. Figure 1 An exemplary system architecture that can be applied to embodiments of this application is shown, such as Figure 1 As shown, the system architecture may include: user equipment and a geospatial data fusion-based watershed water ecological spatial dynamic monitoring system located on the server side.

[0025] Users can input multi-source geospatial data through their user devices, which then send the data to a server-side monitoring system. The monitoring system can use the methods provided in this embodiment to obtain dynamic monitoring results. The server can then send the dynamic monitoring results to the user terminal.

[0026] User devices can include, but are not limited to, smart mobile terminals, smart home devices, wearable devices, and PCs (Personal Computers). Smart mobile devices can include mobile phones, tablets, laptops, PDAs (Personal Digital Assistants), and connected cars. Smart home devices can include smart TVs, smart refrigerators, and so on. Wearable devices can include smartwatches, smart glasses, virtual reality devices, augmented reality devices, and mixed reality devices.

[0027] A watershed water ecosystem spatial dynamic monitoring system based on geospatial data fusion can be configured as a standalone server, a server cluster, or a cloud server. A cloud server, also known as a cloud computing server or cloud host, is a hosting product within the cloud computing service system, designed to address the management difficulties and weak service scalability inherent in traditional physical hosts and Virtual Private Servers (VPS) services. Besides... Figure 1In addition to the illustrated architecture, the watershed water ecological space dynamic monitoring system based on geospatial data fusion can also be set up on a computer terminal with strong computing power.

[0028] It should be understood that Figure 1 The user equipment and the watershed water ecological space dynamic monitoring system based on geospatial data fusion in the figure are only illustrative. According to the implementation needs, there can be any number of user equipment and watershed water ecological space dynamic monitoring systems based on geospatial data fusion.

[0029] Figure 2 A flowchart of a monitoring method for watershed water ecological space dynamic analysis is provided for the embodiments of the present application. The method can be executed by Figure 1 The monitoring system for watershed water ecological space dynamic analysis in the illustrated system. As shown in Figure 2 The method can include the following steps: Step 201: Obtain multi-source geospatial data, including hydrological monitoring data, water conservancy project scheduling log, remote sensing image data, ground sensor data and geographic information system data.

[0030] Step 202: Perform multi-scale symbolization processing on the multi-source geospatial data, dynamically generate a multi-level symbol set according to the data spatio-temporal resolution and the watershed water ecological space environment characteristics, and generate a symbol sequence corresponding to the spatio-temporal characteristics of the watershed water ecological space according to the symbol set.

[0031] Step 203: Construct a spatio-temporal state transition network based on symbol dynamics, wherein the spatio-temporal state transition network takes a geographical space region as a node, an ecological interaction relationship as an edge, and optimizes the spatio-temporal transition network by analyzing the state transition law and information entropy of the symbol sequence.

[0032] Step 204: Extract the dynamic interaction characteristics of the watershed water ecological space from the spatio-temporal state transition network using network analysis methods, including periodic patterns, abnormal states or cross-regional collaborative trends.

[0033] Step 205: Based on the dynamic interaction characteristics, generate a dynamic monitoring result of the watershed water ecological space.

[0034] As can be seen from the above process, the application realizes accurate monitoring of dynamic changes of water ecological space in a basin by acquiring multi-source geospatial data, combining multi-scale symbolization processing and spatio-temporal state transition network construction. The method generates symbol sequences and optimizes network structures dynamically, extracts dynamic interaction features such as periodic patterns, abnormal states and cross-regional collaborative trends, and generates comprehensive monitoring results. The technical effect lies in effectively fusing multi-source data, adapting to different temporal and spatial resolutions and characteristics of water ecological space in a basin, improving the accuracy and flexibility of monitoring, and providing scientific basis and visualization support for ecological protection and resource management.

[0035] The steps in the above process and the effects that can be further produced will be described in detail below in conjunction with embodiments.

[0036] First, the above step 201, i.e., "acquiring multi-source geospatial data, the multi-source geospatial data including hydrological monitoring data, water conservancy engineering scheduling logs, remote sensing image data, ground sensor data and geographic information system data", will be described in detail in conjunction with embodiments.

[0037] The water ecological space in a basin refers to a geographical space that takes a basin (a region where rivers and their tributaries converge) as a geographical unit, covers water bodies, riparian zones, wetlands and associated biological communities, and its dynamic changes are driven by hydrological processes and human activities (such as water conservancy projects).

[0038] The application acquires data related to water ecological space in a basin with spatial and temporal attributes through various data collection methods to comprehensively capture the dynamic change characteristics of water ecological space in a basin. These data sources each have their own characteristics and complement each other to form a comprehensive data foundation for monitoring water ecological space in a basin.

[0039] Remote sensing image data is an image of the earth's surface obtained through a satellite or aerial platform, such as Landsat, Sentinel-2 satellite images, etc. The spatial resolution varies from meters to sub-meters. This type of data can cover a wide range of areas and provide spatial information on surface features such as vegetation coverage, land use, and water distribution. For example, the normalized vegetation index (NDVI) in remote sensing images can be used to monitor vegetation health and seasonal changes. The high spatial coverage of remote sensing image data makes it an important tool for analyzing the spatial distribution and change trend of water ecological space in a basin, but it may be limited in temporal resolution due to satellite revisit period and needs to be supplemented by other data sources.

[0040] Ground sensor data are collected by sensor devices deployed in the watershed hydro-ecological space, such as temperature, humidity, soil moisture, or water level sensors. These data have high temporal resolution and can record real-time changes in environmental parameters of the watershed hydro-ecological space. For example, water level sensors in wetlands can monitor water level fluctuations, and temperature sensors in riparian zones can reflect microclimate changes. The advantage of ground sensor data is its high precision and continuity, which can capture short-term dynamic changes in the watershed hydro-ecological space, but its spatial coverage is limited and it is difficult to reflect large-scale regional characteristics, so it needs to be combined with remote sensing data.

[0041] Geographic Information System (GIS) data includes topographic maps, land use type maps, water system distribution maps, and other spatial vector data, providing spatial structure and background information of the watershed hydro-ecological space. These data are based on spatial coordinates and describe static or semi-static features such as terrain slope, soil type, and administrative boundaries, providing a basis for spatial analysis of the watershed hydro-ecological space. For example, GIS data can be used to divide ecological function zones or analyze the impact of terrain on vegetation distribution. The advantage of GIS data is its high spatial accuracy and rich attribute information, but its dynamicity is weak and needs to be integrated with dynamic information from remote sensing and sensor data.

[0042] The following describes the step 202, i.e., "multi-scale symbolization processing of the multi-source geospatial data, dynamic generation of multi-level symbol sets according to data spatio-temporal resolution and watershed hydro-ecological space environmental characteristics, and generation of symbol sequences corresponding to spatio-temporal characteristics of the watershed hydro-ecological space" in detail in combination with embodiments.

[0043] The present application discretizes multi-source geospatial data, converting continuous numerical data into symbol sequences to simplify data complexity and highlight spatio-temporal dynamic characteristics of the watershed hydro-ecological space. Multi-scale symbolization processing dynamically generates multi-level symbol sets by considering data spatio-temporal resolution and watershed hydro-ecological space environmental characteristics, ensuring that the processing process can adapt to different data types and characteristics of the watershed hydro-ecological space, thereby providing a basis for subsequent spatio-temporal state transition network construction and dynamic feature extraction.

[0044] The multi-scale symbolization process first discretizes the data based on their spatio-temporal resolution and the environmental characteristics of the basin's water ecological space. For example, remote sensing image data may have a high spatial resolution but a low temporal resolution, while ground sensor data has a high temporal resolution but is limited to point measurements. To address these differences, the data are divided into different scale symbol sets, such as high, medium, and low scale symbol sets, according to their spatio-temporal characteristics. High scale symbol sets may be used to capture fine-grained local changes (such as hourly water level fluctuations), while low scale symbol sets are suitable for analyzing large-scale long-term trends (such as annual vegetation changes). This multi-scale division can preserve the key information of the data while reducing the complexity of analysis.

[0045] Dynamic generation of multi-level symbol sets is the core of the multi-scale symbolization process, involving dynamically adjusting the division threshold and symbol quantity of the symbol set according to the environmental characteristics of the basin's water ecological space (such as vegetation type, soil characteristics, or hydrological conditions). For example, in the ecological corridor space (i.e. the area from the first ridge line of the lake to the submerged line), remote sensing image data may be divided into 5 symbol states (such as "very low", "low", "medium", "high", "very high") to reflect the differences in vegetation coverage; while in the wetland space, water level data may be divided into 3 symbol states (such as "low water level", "normal water level", "high water level") to highlight hydrological changes. The generation process of the symbol set dynamically adjusts the division threshold according to the statistical distribution of the data and the ecological significance through an adaptive algorithm, ensuring that the symbol set can accurately represent the environmental characteristics and dynamic changes of the basin's water ecological space. Furthermore, the dynamic adjustment of the division threshold gives priority to hydrological period characteristics (such as the dry season), the intensity of water conservancy engineering disturbance, and water ecological sensitivity.

[0046] As an implementable way, the multi-scale symbolization process of the present application adopts an adaptive division strategy to dynamically adjust the division threshold and symbol quantity of the symbol set according to the spatio-temporal resolution, spatial type, and / or environmental characteristics of the multi-source geographic spatial data.

[0047] Specifically, the adaptive partitioning strategy first considers the spatiotemporal resolution differences of multi-source geospatial data. Remote sensing imagery data usually has high spatial resolution (e.g., 30-meter resolution of Landsat 8 or 10-meter resolution of Sentinel-2) but low temporal resolution (e.g., revisit period of several days to weeks); ground sensor data has high temporal resolution (e.g., hourly temperature or water level data) but limited spatial coverage. In response to these characteristics, the adaptive partitioning strategy dynamically adjusts the granularity of the symbol set according to the temporal and spatial resolution of the data. For example, for high-temporal-resolution sensor data, a finer partition threshold (e.g., dividing temperature into 10 symbol states) can be used to capture short-term fluctuations; for low-temporal-resolution remote sensing data, a coarser partition (e.g., dividing NDVI into 3 symbol states) can be used to highlight long-term trends. This dynamic adjustment ensures that the symbol set can balance the differences in spatiotemporal resolution.

[0048] The diversity of watershed water ecological space types is another key factor in the adaptive partitioning strategy. Different space types have different dynamic characteristics and environmental parameters. For example, the vegetation cover in the drawdown zone changes slowly, which is suitable for using a small number of symbols (e.g., 3-5 states) to represent the long-term change trend of NDVI; while the water level in the wetland space changes rapidly and frequently, which may require more symbol states (e.g., 6-8 states) to capture short-term fluctuations. The adaptive partitioning strategy dynamically adjusts the partition threshold and number of the symbol set by analyzing the dynamic characteristics of the space type. For example, in the coastal wetland monitoring, the water level can be divided into "low", "medium", "high", "extremely high" and other states according to the statistical distribution and ecological significance of the water level data, to ensure that the symbol set can accurately reflect the key characteristics of the watershed water ecological space.

[0049] Environmental characteristics (such as soil type, terrain slope, climate conditions) have an important influence on the dynamic changes of watershed water ecological space, so the adaptive partitioning strategy will combine these characteristics to further optimize the partition threshold of the symbol set. For example, in the seasonal river space in arid regions, soil moisture may have a characteristic of low-value concentration distribution, and the partitioning strategy will tend to set finer thresholds in the low-value interval to capture small changes; while in the lake reservoir space in humid regions, the NDVI value distribution is relatively uniform, and an equal-interval threshold partitioning may be used. By analyzing the statistical characteristics (such as mean, variance, distribution shape) of environmental characteristics, the adaptive algorithm can dynamically determine the optimal partition threshold to ensure that the symbol set can highlight the environmental driving factors of the watershed water ecological space.

[0050] The implementation of adaptive partitioning strategies often relies on statistical analysis and machine learning algorithms. The specific process includes: first, pre-processing multi-source geospatial data to extract temporal and spatial resolution information (such as time interval, spatial pixel size); then, combining spatial types and environmental characteristics (such as obtaining land use types and terrain information through GIS data), using clustering algorithms (such as K-means or adaptive density clustering) or information entropy analysis to determine the initial partition of the symbol set; then, dynamically adjusting the partition threshold and symbol number through iterative optimization algorithms (such as based on the maximum entropy principle or the minimum description length criterion); finally, verifying the effectiveness of the symbol set to ensure that it can accurately represent the temporal and spatial dynamic characteristics of the watershed water ecological space. For example, the partition effect can be evaluated by the information entropy of the symbol sequence or the stability of the state transition probability.

[0051] Based on the multi-level symbol set, the method further generates a symbol sequence corresponding to the temporal and spatial characteristics of the watershed water ecological space. The symbol sequence is a discrete symbol sequence converted from continuous geospatial data, recording the change trajectory of the state of the watershed water ecological space along the time or space axis. For example, the sequence of remote sensing image values of a certain area may be converted into the symbol sequence "medium-high-high-medium-low", reflecting the change rule of vegetation coverage over time; similarly, the symbol sequence in the spatial dimension can represent the ecological state distribution of different regions. The generation of symbol sequence preserves the temporal and spatial characteristics of the data, while reducing the influence of data noise through discretization, facilitating subsequent state transition analysis based on symbol dynamics.

[0052] The following embodiments will be described in detail below for step 203, i.e. "constructing a spatio-temporal state transition network based on symbol dynamics, wherein the spatio-temporal state transition network takes geographical space regions as nodes and ecological interaction relationships as edges, and optimizes the spatio-temporal transition network by analyzing the state transition rules and information entropy of the symbol sequence".

[0053] This step takes the symbol sequence converted from multi-source geospatial data as the basis to construct a network model with geographical space regions as nodes and ecological interaction relationships as edges, to represent the dynamic change rule of the watershed water ecological space. By analyzing the state transition rules and information entropy of the symbol sequence, the network structure is optimized to more accurately reflect the temporal and spatial dynamic characteristics of the watershed water ecological space, providing support for subsequent dynamic interaction feature extraction.

[0054] Symbolic dynamics is a method of discretizing continuous data into symbol sequences and analyzing their dynamic behaviors. In this application, based on the symbol sequences generated by the aforementioned multi-scale symbolization process, geographical spatial regions (such as grid cells of remote sensing images or ground sensor points) are taken as network nodes, and the states of nodes are represented by symbols in symbol sequences (such as "high vegetation coverage" or "low water level"). Ecological interaction relationships are defined as edges of the network, for example, the mutual influence of two adjacent regions due to vegetation migration or hydrological flow can be taken as the weight of the edge. The process of constructing the spatio-temporal state transition network includes: first, mapping the symbol sequence to the node state according to the time or space dimension; then, determining the connection relationship of the edge according to the ecological interaction relationship (such as spatial proximity or ecological process correlation); finally, generating an initial directed and weighted network, and the edge weight reflects the strength of the interaction relationship.

[0055] The analysis of state transition rules is a key step to optimize the spatio-temporal state transition network. By calculating the state transition probability matrix from the symbol sequence, the probability of each geographical spatial region from one symbol state (such as "high vegetation coverage") to another symbol state (such as "medium vegetation coverage") is recorded. These probabilities constitute the state transition probability matrix, which reflects the dynamic evolution rules of the watershed water ecological space in the time or space dimension. The construction of the matrix usually uses statistical methods, based on the frequency statistics or Markov chain model of the symbol sequence, to ensure the accurate capture of the regularity of state transition.

[0056] Information entropy is used to quantify the uncertainty and complexity of symbol sequences, and is an important tool for optimizing the spatio-temporal state transition network. By calculating the information entropy (such as Shannon entropy) of the symbol sequence, the randomness or orderliness of the dynamic change of the watershed water ecological space can be evaluated. For example, a higher information entropy may indicate that the state change of the watershed water ecological space is more random (such as disturbed areas), while a lower information entropy may reflect a periodic or stable change pattern (such as seasonal vegetation change).

[0057] As an implementable way, by analyzing the state transition rules and information entropy of the symbol sequence, the optimization of the spatio-temporal transition network includes: calculating the state transition probability matrix according to the symbol sequence, wherein the state transition probability matrix records the transition probability of each geographical spatial region from one symbol state to another symbol state; calculating the multi-scale entropy analysis index according to the multi-scale characteristics of the multi-level symbol set; adjusting the node state and edge weight of the spatio-temporal state transition network according to the state transition probability matrix and the multi-scale entropy analysis index.

[0058] Specifically, first, the time series data of the symbol sequence is extracted; then, the transition frequency of each state pair is calculated using a first-order Markov chain model or a sliding window statistical method; finally, the transition frequency is normalized to probability to generate a state transition probability matrix. For example, for the NDVI symbol sequence of a certain area "high-medium-low-high", P(high→medium)=0.4, P(medium→low)=0.3, etc. can be calculated, and the matrix records all possible state transition probabilities. This matrix provides a quantitative basis for dynamic changes for network optimization, reflecting the evolution law of the water ecological space of the basin in the time dimension.

[0059] The calculation of the multi-scale entropy analysis index is based on the multi-scale characteristics of the multi-level symbol set, aiming to quantify the complexity and uncertainty of the dynamic changes of the water ecological space of the basin. The multi-level symbol set contains symbol states of different granularities (such as high, medium, and low scale NDVI states), which reflect different dynamic characteristics of the water ecological space of the basin. The implementation method includes: first, calculate the information entropy (such as Shannon entropy) of the symbol sequence of each scale to evaluate the randomness of state changes at a single scale; then, combined with the multi-scale characteristics, use the multi-scale entropy method (such as sample entropy or approximate entropy) to analyze the complexity of cross-scale state changes. For example, high temporal resolution ground sensor data may show a higher entropy value, reflecting the complexity of short-term fluctuations; while low temporal resolution remote sensing data may show a lower entropy value, reflecting the stability of long-term trends. The multi-scale entropy analysis index can reveal the dynamic behavior of the water ecological space of the basin at different spatio-temporal scales, providing multi-dimensional information for network optimization.

[0060] Based on the state transition probability matrix and the multi-scale entropy analysis index, the node state and edge weight of the spatio-temporal state transition network are optimized. The specific implementation method includes: first, adjust the edge weight according to the state transition probability matrix, increase the edge weight of the high-probability transition path (such as P(high→medium)=0.8) to highlight the main dynamic interaction relationship; second, adjust the node state according to the multi-scale entropy analysis result, for example, merge the nodes with low entropy values (representing stable states of the region) into a single node to reduce network redundancy; finally, adjust the network topology through an iterative optimization algorithm (such as based on gradient descent or graph cut algorithm) to ensure that the node state and edge weight can balance the dynamic complexity and computational efficiency of the water ecological space of the basin. For example, in the river network space, the river section with high entropy value may represent an abnormal disturbance area affected by sudden floods, and its edge weight and node state will be adjusted preferentially to highlight the abnormal characteristics.

[0061] Preferably, the application also includes: adjusting the dynamic state of the node in the spatio-temporal state transition network according to the state transition probability matrix, and merging geographical space areas with similar dynamic behavior into a single node based on the similarity of the state transition probability.

[0062] First, the main transition path of each node in the state transition probability matrix is extracted, for example, if the probability of a node transitioning from the "high" state to the "medium" state is 0.8, the dynamic state of the node can be adjusted to be more inclined to the "medium" state to reflect its dominant dynamic behavior; combined with the symbol sequence in the time dimension, the current state of the node is updated, for example, by weighted average or maximum probability principle, the dynamic state of the node is set to the symbol state with the highest probability; verify whether the adjusted node state is consistent with the dynamic trend of the symbol sequence, and ensure that the adjustment result conforms to the actual change law of the watershed water ecological space. For example, in the riparian space, the NDVI state of the flood inundation area may be updated from "high" to "low" due to continuous inundation stress, to quantify the ecological degradation characteristics under hydrological disturbance.

[0063] Second, based on the state transition probability matrix, the state transition probability similarity between nodes is calculated, for example, the cosine similarity or KL divergence (Kullback-Leibler divergence) is used to compare the state transition probability distribution of two nodes; then, a similarity threshold is set, and nodes with a similarity higher than the threshold are identified as regions with similar dynamic behavior.

[0064] Finally, clustering algorithms (such as K-means or hierarchical clustering) or graph cut algorithms are used to merge these regions into a single node, and the state of the merged node can be determined by weighted average or dominant state selection; finally, the edge connection relationship of the network is updated, and the edge weight between the merged node and the adjacent node is recalculated. For example, in the wetland space, if the water level state transition probability distribution of two adjacent regions is highly similar (such as both mainly "high→medium"), they can be merged into one node to reduce the complexity of the network.

[0065] The above step 204, i.e. "extracting the dynamic interaction characteristics of the watershed water ecological space, including periodic patterns, abnormal states or cross-regional collaborative trends, from the spatio-temporal state transition network using network analysis methods", will be described in detail below in conjunction with the embodiments.

[0066] This step extracts key dynamic features of the watershed water ecological space from the spatiotemporal state transition network constructed based on symbolic dynamics through network analysis techniques. These features include periodic patterns (such as seasonal vegetation changes), abnormal states (such as mutations caused by floods or droughts), and cross-regional coordination trends (such as regional correlations of hydrological or species migration). Network analysis methods are a set of graph-based analysis techniques used to study network structures composed of nodes and edges and their dynamic characteristics. In the dynamic monitoring of watershed water ecological space, network analysis methods extract dynamic interaction features of watershed water ecological space, such as periodic patterns, abnormal states, and cross-regional coordination trends, by analyzing spatiotemporal state transition networks (with geographical space regions as nodes and ecological interaction relationships as edges). This process reveals the complex interaction relationships of watershed water ecological space by analyzing the topological structure and dynamic properties of the network, providing a scientific basis for dynamic monitoring.

[0067] The first step to achieve this step is to analyze the spatial distribution characteristics of multi-source geospatial data and extract the topological features of spatial proximity and ecological interaction. The specific methods include: first, using GIS data and remote sensing image data to calculate the spatial proximity of geographical space regions (such as based on Euclidean distance or topological adjacency relationship); then, combining ecological interaction relationships (such as hydrological flow, species migration, or vegetation cover correlation), to construct the topological structure of the network. For example, in wetland space, the connection relationship between nodes can be determined based on water system distribution to generate edges reflecting hydrological interaction. Topological feature extraction usually uses network analysis indicators such as node degree (reflecting the connection strength of the region) and clustering coefficient (reflecting the tightness of local interaction). These features provide a basis for subsequent spatial correlation analysis.

[0068] Based on spatial proximity and topological features, the spatial correlation weight between nodes in the spatiotemporal state transition network is calculated. The specific implementation methods include: first, based on spatial distribution characteristics, spatial autocorrelation analysis (such as Moran's I or Geary's C) is used to quantify the correlation between nodes, for example, areas with higher vegetation cover may exhibit positive spatial correlation; then, combining ecological interaction relationships (such as dynamic associations reflected by state transition probability matrices), assign correlation weights to each edge. For example, if the NDVI state transition probabilities of two regions are highly similar and spatially adjacent, the weight of their edge will increase. Weight calculation can be achieved through weighted linear combination or machine learning models (such as regression models) to ensure that edge weights can comprehensively reflect the strength of spatial and ecological interaction.

[0069] In combination with the spatial correlation weight and the ecological interaction relationship, the edge weight and structure of the spatio-temporal state transition network are dynamically adjusted. The specific method includes: first, updating the edge weight according to the spatial correlation weight, for example, increasing the edge weight of high correlation and reducing or deleting the edge weight of low correlation; second, adjusting the network topology by a network optimization algorithm (such as minimum spanning tree or community detection) to delete redundant edges or isolated nodes; finally, verifying whether the adjusted network can effectively represent the dynamic interaction of the water ecological space in the basin. For example, in the riverbank space, if some flood inundation areas show abnormal states, their related edge weights will be dynamically adjusted to highlight the abnormal characteristics. This dynamic adjustment ensures that the network structure can adapt to the real-time changes of the water ecological space in the basin.

[0070] The dynamic interaction characteristics of the water ecological space in the basin are extracted from the optimized spatio-temporal state transition network using network analysis methods. The specific implementation method includes: based on the optimized spatio-temporal state transition network, applying a community detection algorithm to identify groups of geographical space areas with similar dynamic interaction characteristics, and dividing the functional zones of the water ecological space in the basin; based on the spatio-temporal state transition network, calculating the node centrality index to identify geographical space areas that have a key influence on the dynamic interaction of the water ecological space in the basin; combining the functional zones and key areas, extracting the dynamic interaction characteristics of the water ecological space in the basin, including periodic patterns, abnormal states or cross-regional coordination trends.

[0071] Community detection is the first step to extract dynamic interaction characteristics, aiming to identify groups of geographical space areas with similar dynamic interaction characteristics and divide the functional zones of the water ecological space in the basin. The specific implementation method includes: based on the optimized spatio-temporal state transition network, using a community detection algorithm (such as Louvain algorithm or modularity optimization algorithm) to divide the network into several communities according to the edge weight (based on state transition probability or spatial correlation) and topology between nodes. Each community represents a group of geographical space areas with similar dynamic behavior, for example, in the wetland space, a community may correspond to a group of areas with similar water level change trends. The Louvain algorithm identifies communities by maximizing the modularity score (modularity), ensuring that the interaction intensity between nodes within a community is higher than that between communities. In implementation, community detection can be performed through Python's NetworkX or community library, outputting the community division result and mapping each community to geographical space to form a functional zoning map of the water ecological space in the basin, such as a high vegetation coverage area or a hydrological sensitive area.

[0072] The calculation of node centrality indicators is used to identify geographical regions that have a key influence on the dynamic interaction of the water ecological space of the basin. The specific method includes: based on the spatio-temporal state transition network, multiple centrality indicators are calculated, such as degree centrality (reflecting the number of connections of the node), betweenness centrality (reflecting the mediating role of the node in the network path) and eigenvector centrality (reflecting the connection strength of the node with high influence nodes). For example, in the ecological corridor space (i.e. the area from the first ridge line of the lake to the submergence line), nodes with high betweenness centrality may represent biodiversity hotspots or key channels for flood overflow. The calculation process can be realized through the NetworkX library, inputting the adjacency matrix of the network and outputting the centrality scores of each node. By setting a threshold or sorting, nodes with high centrality are screened out and identified as key regions. These regions usually have an important influence on the dynamic changes of the water ecological space of the basin (such as vegetation restoration or water level fluctuations), providing a basis for key areas for monitoring and management.

[0073] In combination with the functional division of community detection and the key regions identified by node centrality, the dynamic interaction features of the water ecological space of the basin are extracted, including periodic patterns, abnormal states and cross-regional coordination trends. The specific implementation method is as follows: periodic pattern extraction: analyze the time series of node states within each functional division, use Fourier transform or autoregressive model to identify periodic changes, such as seasonal cycles of vegetation NDVI. The periodic patterns of key regions can be analyzed first to highlight their influence on the overall dynamics of the water ecological space of the basin; abnormal state detection: based on the centrality indicators of key regions, combined with abnormal detection algorithms (such as Z-score), identify nodes that deviate from normal state, such as vegetation mutations caused by floods or droughts. Functional divisions can be used to limit the scope of abnormal detection, improving detection accuracy; cross-regional coordination trend analysis: by analyzing the edge weights between communities and the paths (such as the shortest path or weighted path) between key regions, cross-regional coordination trends are extracted, such as regional coordinated fluctuations of wetland water levels.

[0074] The following describes in detail the step 205, i.e. "generating dynamic monitoring results of the water ecological space of the basin based on the dynamic interaction features" in combination with embodiments.

[0075] This step uses the dynamic interaction features extracted from the spatio-temporal state transition network to generate dynamic monitoring results of the water ecological space of the basin. This process integrates multi-source geographic spatial data to generate comprehensive results reflecting the spatio-temporal changes of the water ecological space of the basin, which can include interactive visualization diagrams, dynamic evolution predictions and monitoring reports, providing scientific basis for ecological protection and resource management.

[0076] The application can generate an interactive visual analysis result according to the dynamic interaction feature, wherein the interactive visual analysis result includes a spatial distribution map of periodic patterns, abnormal states or cross-regional collaborative trends of the water ecological space of the basin; according to the spatio-temporal state transition network and the dynamic interaction feature, a cross-regional collaborative prediction model is applied to predict the dynamic evolution trend of the water ecological space of the basin, wherein the cross-regional collaborative prediction model combines the ecological interaction relationship and state transition rule between nodes in the network to generate an ecological state prediction across regions; and according to the interactive visual analysis result and the cross-regional collaborative prediction result, a dynamic monitoring report of the water ecological space of the basin is generated, including ecological state prediction, abnormal event detection or cross-regional trend analysis.

[0077] Specifically, generating an interactive visual analysis result is a core component of the dynamic monitoring result, which aims to present the dynamic interaction feature in the form of an intuitive spatial distribution map, showing the periodic patterns, abnormal states and cross-regional collaborative trends of the water ecological space of the basin. The specific implementation method includes: first, based on the dynamic interaction feature of the functional division and the key region, a spatial distribution map is generated, for example, using GIS tools to map the periodic patterns (such as seasonal changes in NDVI) to geographical space to generate a heat map or contour map; second, for abnormal states (such as flood or drought areas), highlight or color coding is used to mark abnormal areas; finally, cross-regional collaborative trends are displayed, and the interaction relationship between regions (such as hydrological flow direction) is represented by a network diagram or flow diagram. Interactive visualization can be realized by Python's Folium or Plotly library, supporting user zooming, click querying and other interactive functions, facilitating the analysis of the spatial dynamic characteristics of the water ecological space of the basin. For example, in the riparian space, an interactive NDVI periodic change map can be generated to highlight flood or drought abnormal areas.

[0078] The cross-regional collaborative prediction model is used to predict the dynamic evolution trend of the water ecological space of the basin, and the prediction result is generated by combining the ecological interaction relationship and state transition rule between nodes in the spatio-temporal state transition network. The specific implementation method includes: first, based on the state transition probability matrix and the network edge weight, a prediction model is constructed, such as a Markov chain model, a graph neural network or a long short-term memory network, to capture the dynamic interaction and time dependence between nodes; then, the historical symbol sequence and the dynamic interaction feature (such as periodic patterns and collaborative trends) are input to predict the ecological state in the future, for example, the future change trend of wetland water level or the recovery trajectory of vegetation or aquatic vascular plants; finally, the prediction accuracy of the model is verified, and cross-validation or historical data comparison is used to evaluate the performance of the model.

[0079] The interactive visualization analysis results and cross-region collaborative prediction results are integrated to generate a dynamic monitoring report of the river basin water ecological space, including ecological state prediction, abnormal event detection, and cross-region trend analysis. The specific implementation methods include: first, organizing the visualization results to generate the core content of the report, such as the spatial distribution map of periodic patterns, the highlight map of abnormal events, and the network map of collaborative trends; second, integrating the prediction results to generate the future trend description of the ecological state, for example, "it is predicted that the vegetation coverage in region A will recover to the medium level within the next 6 months"; and finally, adding analysis conclusions, such as the occurrence time, location, and impact range of abnormal events, and the ecological significance of cross-region collaborative trends. The report can be generated in PDF format by LaTeX or Python's ReportLab library, including charts, text, and quantitative indicators (such as abnormal event severity scores). For example, in flood monitoring, the report can include the distribution map of the flood-affected area, vegetation recovery prediction, and cross-region ecological impact analysis.

[0080] The above-mentioned method provided by the embodiments of the present application can be applied to various application scenarios. First, in the river network space, the method can be used to monitor the vegetation recovery dynamics after a flood, by fusing remote sensing images and ground sensor data, extracting the periodic patterns of flood abnormal states and seasonal vegetation changes, and predicting the recovery trend to provide a basis for river basin management. Second, in the wetland space, the method can analyze the cross-region collaborative trends of water level changes, divide functional zones in combination with GIS data, predict drought risks, and assist in water resource management and wetland protection. In addition, in wetland degradation monitoring, the method identifies degraded areas and evaluates their spatial distribution by extracting abnormal states and collaborative trends, providing scientific support for wetland ecological restoration. These scenarios use multi-source data fusion and network analysis to generate interactive visualization results and prediction reports, improving the accuracy and practicality of monitoring and providing comprehensive decision-making basis for ecological protection and resource management.

[0081] The above describes specific embodiments of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be executed in an order different than the order in the embodiments and still achieve the desired result. In addition, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous or possible.

[0082] According to another aspect, embodiments of a monitoring system for dynamic analysis of a river basin water ecological space are provided. Figure 3 A schematic block diagram of the monitoring system for dynamic analysis of the river basin water ecological space according to one embodiment is shown. As Figure 3 shown, the system 300 includes: The data acquisition unit 301 is configured to acquire multi-source geospatial data, including hydrological monitoring data, water conservancy dispatching logs, remote sensing image data, ground sensor data, and geographic information system data.

[0083] The symbol set generation unit 302 is configured to perform multi-scale symbolization processing on the multi-source geospatial data to generate a multi-level symbol set, and generate a symbol sequence corresponding to the spatio-temporal characteristics of the water ecological space of the watershed according to the symbol set.

[0084] The transition network construction unit 303 is configured to construct a spatio-temporal state transition network based on symbol dynamics, wherein the spatio-temporal state transition network takes geographical space regions as nodes and ecological interaction relationships as edges, and optimizes the spatio-temporal transition network by analyzing the state transition rules and information entropy of the symbol sequence.

[0085] The interaction feature extraction unit 304 is configured to extract dynamic interaction features of the water ecological space of the watershed from the spatio-temporal state transition network using network analysis methods, including periodic patterns, abnormal states, or cross-regional collaborative trends.

[0086] The monitoring result generation unit 305 is configured to generate dynamic monitoring results of the water ecological space of the watershed based on the dynamic interaction features.

[0087] As an implementable way, the symbol set generation unit 302 is configured to adopt an adaptive partitioning strategy for the multi-scale symbolization processing, dynamically adjusting the partitioning threshold and the number of symbols of the symbol set according to the spatio-temporal resolution, spatial type, and / or environmental characteristics of the multi-source geospatial data.

[0088] As an implementable way, when optimizing the spatio-temporal transition network by analyzing the state transition rules and information entropy of the symbol sequence, the transition network construction unit 303 can be configured to: calculate a state transition probability matrix according to the symbol sequence, wherein the state transition probability matrix records the transition probability of each geographical space region from one symbol state to another symbol state; calculate a multi-scale entropy analysis index according to the multi-scale characteristics of the multi-level symbol set; and adjust the node state and edge weight of the spatio-temporal state transition network according to the state transition probability matrix and the multi-scale entropy analysis index.

[0089] As an implementable way, the transition network construction unit 303 can be configured to adjust the dynamic state of the nodes in the spatio-temporal state transition network according to the state transition probability matrix, and merge geographical space regions with similar dynamic behaviors into a single node based on the similarity of the state transition probability.

[0090] As an implementable manner, the interaction feature extraction unit 304 can be configured to analyze the spatial distribution characteristics of the multi-source geographic space data, extract the topological features of spatial proximity and ecological interaction relationship, calculate the spatial correlation weight between nodes in the spatiotemporal state transition network according to the spatial proximity and topological features, dynamically adjust the edge weight and network structure of the spatiotemporal state transition network in combination with the spatial correlation weight and the ecological interaction relationship, and extract the dynamic interaction features of the river basin water ecological space, including periodic patterns, abnormal states or cross-regional collaborative trends, by using the network analysis method based on the optimized spatiotemporal state transition network.

[0091] As an implementable manner, the interaction feature extraction unit 304 can be configured to apply a community detection algorithm based on the optimized spatiotemporal state transition network to identify groups of geographic space regions with similar dynamic interaction features and divide the functional zones of the river basin water ecological space, calculate the node centrality index based on the spatiotemporal state transition network to identify geographic space regions that have a key influence on the dynamic interaction of the river basin water ecological space, and extract the dynamic interaction features of the river basin water ecological space, including periodic patterns, abnormal states or cross-regional collaborative trends, in combination with the functional zones and key regions, when extracting the dynamic interaction features of the river basin water ecological space by using the network analysis method based on the optimized spatiotemporal state transition network.

[0092] As an implementable manner, the monitoring result generation unit 305 can be configured to generate an interactive visual analysis result according to the dynamic interaction features, wherein the interactive visual analysis result includes a spatial distribution map of the periodic patterns, abnormal states or cross-regional collaborative trends of the river basin water ecological space, apply a cross-regional collaborative prediction model to predict the dynamic evolution trend of the river basin water ecological space according to the spatiotemporal state transition network and the dynamic interaction features, wherein the cross-regional collaborative prediction model combines the ecological interaction relationship and state transition rule between nodes in the network to generate an ecological state prediction across regions, and generate a dynamic monitoring report of the river basin water ecological space including the ecological state prediction, abnormal event detection or cross-regional trend analysis according to the interactive visual analysis result and the cross-regional collaborative prediction result, when generating the dynamic monitoring result of the river basin water ecological space based on the dynamic interaction features.

[0093] The various embodiments described in the specification are progressive in nature, and the same or similar parts among the various embodiments can be mutually referred to, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiments, since they are basically similar to the method embodiments, they are described more simply, and the relevant parts can be referred to the part of the method embodiments. The system embodiments described above are only illustrative, and the units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, i.e., they can be located in one place or distributed on multiple network units. Some or all of the modules can be selected to achieve the purpose of the embodiment according to actual needs. Those skilled in the art can understand and implement it without creative labor.

[0094] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation portal for user to choose authorization or refusal.

[0095] In addition, the embodiment of the present application also provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the steps of the method in any one of the preceding method embodiments.

[0096] An electronic device includes one or more processors and a memory associated with the one or more processors, the memory being configured to store program instructions that, when executed by the one or more processors, perform the steps of the method in any one of the preceding method embodiments.

[0097] The present application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the method in any one of the preceding method embodiments.

[0098] In which, Figure 4 An exemplary architecture of an electronic device is shown, which can specifically include a processor 410, a video display adapter 411, a disk drive 412, an input / output interface 413, a network interface 414, and a memory 420. The above processor 410, video display adapter 411, disk drive 412, input / output interface 413, network interface 414, and memory 420 can be connected by a communication bus 430.

[0099] The processor 410 can be implemented by a general-purpose CPU, a microprocessor, an application specific integrated circuit (ASIC), or one or more integrated circuits, and is configured to execute related programs to implement the technical solutions provided in the present application.

[0100] The memory 420 can be implemented by a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 420 can store an operating system 421 for controlling the operation of the electronic device 400, a basic input / output system (BIOS) 422 for controlling the low-level operation of the electronic device 400. In addition, a web browser 423, a data storage management system 424, and a monitoring system 425 for dynamic analysis of the water ecological space of a river basin, etc. can also be stored. The monitoring system 425 for dynamic analysis of the water ecological space of a river basin can be an application program for implementing the foregoing steps in the embodiments of the present application. In summary, when the technical solutions provided in the present application are implemented by software or firmware, the related program codes are stored in the memory 420 and are executed by the processor 410.

[0101] The input / output interface 413 is configured to connect input / output modules to realize information input and output. The input / output modules can be configured as components in the device (not shown in the figure) or can be externally connected to the device to provide corresponding functions. The input device can include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device can include a display, a speaker, a vibrator, an indicator light, etc.

[0102] The network interface 414 is configured to connect a communication module (not shown in the figure) to realize the communication interaction between the device and other devices. The communication module can realize communication through a wired manner (such as a USB, a network cable, etc.) or through a wireless manner (such as a mobile network, WIFI, Bluetooth, etc.).

[0103] The bus 430 includes a path for transmitting information between various components (such as the processor 410, the video display adapter 411, the disk drive 412, the input / output interface 413, the network interface 414, and the memory 420) of the device.

[0104] It should be noted that although the above device only shows the processor 410, the video display adapter 411, the disk drive 412, the input / output interface 413, the network interface 414, the memory 420, the bus 430 and the like, but in the process of implementation, the device can also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device can also contain only the components necessary to implement the present application, and does not have to contain all the components shown in the figure.

[0105] From the above description of the embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus the necessary general hardware platform. Based on such understanding, the technical solutions of the present application can be embodied in the form of a computer program product, which can be stored in a storage medium such as ROM / RAM, magnetic disk, optical disk, etc., and includes a number of instructions for making a computer device (which can be a personal computer, server, or network device, etc.) execute the methods described in various embodiments or some parts of the embodiments of the present application.

[0106] The above provides a detailed description of the technical solutions of the present application. The specific examples are applied to the principles and implementation of the present application. The above description of the embodiments is only to help understand the method and its core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation and application range will be changed. In conclusion, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A method for dynamic analysis of water ecological space of a river basin, comprising a monitoring method and a monitoring system for the monitoring method, characterized in that, The monitoring method comprises the following steps: acquiring multi-source geospatial data, the multi-source geospatial data comprising hydrological monitoring data, water conservancy project scheduling logs, remote sensing image data, ground sensor data, and geographic information system data; performing multi-scale symbolization processing on the multi-source geospatial data to generate a multi-level symbol set, and generating a symbol sequence corresponding to the spatiotemporal characteristics of the water ecological space of the basin according to the symbol set; constructing a spatiotemporal state transition network based on symbolic dynamics, the spatiotemporal state transition network taking geographical space regions as nodes and ecological interaction relationships as edges, and optimizing the spatiotemporal transition network by analyzing the state transition law and information entropy of the symbol sequence; extracting dynamic interaction characteristics of the water ecological space of the basin from the spatiotemporal state transition network using network analysis methods, the dynamic interaction characteristics comprising periodic patterns, abnormal states, or cross-regional collaborative trends; generating dynamic monitoring results of the water ecological space of the basin based on the dynamic interaction characteristics.

2. The method of claim 1, wherein: The multi-scale symbolization processing adopts an adaptive division strategy, dynamically adjusts the division threshold and the number of symbols of the symbol set according to the spatiotemporal resolution, spatial type, and / or environmental characteristics of the multi-source geospatial data.

3. The method of claim 1, wherein, The optimization of the spatiotemporal transition network by analyzing the state transition law and information entropy of the symbol sequence comprises: calculating a state transition probability matrix according to the symbol sequence, wherein the state transition probability matrix records the transition probability of each geographical space region from one symbol state to another symbol state; calculating a multi-scale entropy analysis index according to the multi-scale characteristics of the multi-level symbol set; adjusting the node state and edge weight of the spatiotemporal state transition network according to the state transition probability matrix and the multi-scale entropy analysis index.

4. The method of claim 3, wherein, The method further comprises: adjusting the dynamic state of the nodes in the spatiotemporal state transition network according to the state transition probability matrix, and merging geographical space regions with similar dynamic behaviors into a single node based on the similarity of the state transition probability.

5. The method of claim 1, wherein, The extraction of the dynamic interaction characteristics of the water ecological space of the basin from the spatiotemporal state transition network using network analysis methods, the dynamic interaction characteristics comprising periodic patterns, abnormal states, or cross-regional collaborative trends, comprises: analyzing the spatial distribution characteristics of the multi-source geospatial data to extract topological features of spatial proximity and ecological interaction relationships; calculating the spatial correlation weight between nodes in the spatiotemporal state transition network according to the spatial proximity and topological features; dynamically adjusting the edge weight and network structure of the spatiotemporal state transition network in combination with the spatial correlation weight and the ecological interaction relationship; extracting the dynamic interaction characteristics of the water ecological space of the basin based on the optimized spatiotemporal state transition network using network analysis methods, the dynamic interaction characteristics comprising periodic patterns, abnormal states, or cross-regional collaborative trends.

6. The method of claim 5, wherein, The extraction of the dynamic interaction characteristics of the water ecological space of the basin based on the optimized spatiotemporal state transition network using network analysis methods comprises: Based on the optimized spatio-temporal state transition network, a community detection algorithm is applied to identify groups of geographical space regions with similar dynamic interaction characteristics, and to divide the functional zones of the watershed water ecological space; Based on the spatio-temporal state transition network, a node centrality index is calculated to identify geographical space regions that have a key influence on the dynamic interaction of the watershed water ecological space; In combination with the functional zones and key regions, the dynamic interaction characteristics of the watershed water ecological space are extracted.

7. The method of claim 1, wherein, The generation of the dynamic monitoring results of the watershed water ecological space based on the dynamic interaction characteristics includes: According to the dynamic interaction characteristics, an interactive visual analysis result is generated, wherein the interactive visual analysis result includes a spatial distribution map of the periodic patterns, abnormal states, or cross-regional collaborative trends of the watershed water ecological space; According to the spatio-temporal state transition network and the dynamic interaction characteristics, a cross-regional collaborative prediction model is applied to predict the dynamic evolution trend of the watershed water ecological space, wherein the cross-regional collaborative prediction model combines the ecological interaction relationship and state transition law between nodes in the network to generate a cross-regional ecological state prediction; According to the interactive visual analysis result and the cross-regional collaborative prediction result, a dynamic monitoring report of the watershed water ecological space is generated, which includes ecological state prediction, abnormal event detection, or cross-regional trend analysis.

8. A monitoring system for use in the monitoring method of the dynamic analysis method of a river basin water ecological space according to any one of claims 1 to 7, characterized by, It includes: A data acquisition unit configured to acquire multi-source geographical space data, including hydrological monitoring data, water conservancy engineering scheduling logs, remote sensing image data, ground sensor data, and geographic information system data; A symbol set generation unit configured to perform multi-scale symbolization processing on the multi-source geographical space data to generate a multi-level symbol set, and generate a symbol sequence corresponding to the spatio-temporal characteristics of the watershed water ecological space based on the symbol set; A transition network construction unit configured to construct a spatio-temporal state transition network based on symbol dynamics, wherein the spatio-temporal state transition network takes geographical space regions as nodes and ecological interaction relationships as edges, and optimizes the spatio-temporal transition network by analyzing the state transition law and information entropy of the symbol sequence; An interaction feature extraction unit configured to extract the dynamic interaction characteristics of the watershed water ecological space from the spatio-temporal state transition network using network analysis methods, including periodic patterns, abnormal states, or cross-regional collaborative trends; A monitoring result generation unit configured to generate dynamic monitoring results of the watershed water ecological space based on the dynamic interaction characteristics.

9. An electronic device, comprising: It includes: One or more processors; And a memory associated with the one or more processors, the memory is used to store program instructions, the program instructions are read and executed by the one or more processors, and the steps of the monitoring method of the watershed water ecological space dynamic analysis method in any one of claims 1-7 are performed.

10. A computer readable storage medium having stored thereon a computer program, characterized in that: The computer program is executed by the processor to realize the steps of the monitoring method of the watershed water ecological space dynamic analysis method in any one of claims 1-7.

Images