Digital twinborn body construction method and system of terrestrial ecosystem

Abstract

The invention relates to a digital twin construction method and system of a terrestrial ecosystem, and the method comprises the steps: obtaining animal and plant information and environment quality evaluation conditions according to biological and environmental data collected in an ecological protection area; processing animal and plant information, an environment quality evaluation condition, a biological feature vector generated based on biological data, an environment feature vector generated based on environment data and a comprehensive feature vector generated by fusing the two types of vectors based on the evaluation large model to obtain an ecological system service function evaluation result; generating a comprehensive characteristic matrix based on animal and plant information, environment quality evaluation conditions and ecological system service function evaluation results, and performing deep learning on the comprehensive characteristic matrix to construct a digital twinborn engine; and after a digital twinborn large model is constructed based on the digital twinborn engine and the model static substrate information, in response to real-time data input into the digital twinborn large model, rendering a linkage state of species, environment and ecosystem service functions on a visual interface.

Description

Technical Field

[0001] The present application relates to the field of ecological technology, and in particular to a method and system for constructing a digital twin of a terrestrial ecosystem. Background Art

[0002] With growing awareness of ecological conservation, ecosystem monitoring has become crucial for maintaining biodiversity and ecological balance. Real-time ecosystem monitoring can provide early warnings of environmental degradation, assess ecosystem services, and provide a basis for ecological restoration and sustainable management.

[0003] With the rapid development of digital technology, digital twin technology has gradually emerged and is being applied in various fields. A digital twin is a virtual digital model that corresponds to a physical entity by integrating multiple sources of information, including physical models, sensor data, and historical data. It can reflect the physical entity's status in real time. In the ecological field, although related technologies have been attempted to build digital twins of ecosystems for ecosystem monitoring, they still face many challenges.

[0004] 1. Data collection is single, mostly focusing only on the collection of environmental data, ignoring the importance of biological data, resulting in an incomplete assessment of ecosystem functions; 2. Due to the wide range of ecosystems and complex environments, there are problems such as difficulty in data collection and poor real-time performance; 3. At the data fusion level, data of different modalities often have different data structures and time resolutions. Simple data superposition cannot fully utilize the advantages of multi-source data, and it is difficult to obtain comprehensive data that accurately reflects the status of the ecosystem; 4. Data collaboration in fields such as ecology, geographic information, and computer science is difficult, making it difficult to form a sustainable digital twin ecosystem.

[0005] It can be seen that there are still many problems to be solved in the application of digital twin technology in the ecological field in existing technologies, and there is an urgent need for a feasible solution to build a digital twin of the ecosystem. Summary of the Invention

[0006] The present invention aims to provide a method and system for constructing a digital twin of a terrestrial ecosystem to address the deficiencies in the prior art. The technical problems to be solved by the present invention are achieved through the following technical solutions.

[0007] In a first aspect, an embodiment of the present application provides a method for constructing a digital twin of a terrestrial ecosystem, comprising: Obtaining information on flora and fauna within the ecological reserve and an assessment of environmental quality based on biological data and environmental data collected in the ecological reserve, wherein the biological data is used to generate biological feature vectors for flora and fauna identification, and the environmental data is used to generate environmental feature vectors for environmental quality assessment; Processing the plant and animal information, the environmental quality assessment, the biological feature vector, the environmental feature vector, and the comprehensive feature vector based on the large assessment model to obtain an ecosystem service function assessment result of the ecological protection zone, wherein the comprehensive feature vector is determined based on a fusion of the biological feature vector, the environmental feature vector, and dynamically adjusted biological weights and environmental weights; Generate a comprehensive feature matrix based on the plant and animal information, the environmental quality assessment, and the ecosystem service function assessment results, and perform deep learning on the comprehensive feature matrix to construct a digital twin engine; wherein the comprehensive feature matrix is ​​composed of fused feature vectors of multiple spatiotemporal units arranged in a spatiotemporal sequence, and the fused feature vector of a single spatiotemporal unit is formed by multimodal feature splicing of the plant and animal information, environmental quality assessment, and ecosystem service function assessment results corresponding to the current spatiotemporal unit; After constructing a digital twin large model based on the digital twin engine and the model's static base information, in response to real-time data input into the digital twin large model, the linkage status of species, environment, and ecosystem service functions is rendered on a visualization interface, and the visualization interface is a virtual reality VR interface or an augmented reality AR interface.

[0008] In a second aspect, an embodiment of the present application provides a system for constructing a digital twin of a terrestrial ecosystem, comprising: an acquisition module for acquiring information on flora and fauna within the ecological reserve and an assessment of environmental quality based on biological data and environmental data collected within the ecological reserve, wherein the biological data is used to generate biological feature vectors for flora and fauna identification, and the environmental data is used to generate environmental feature vectors for environmental quality assessment; a processing and acquisition module, configured to process the plant and animal information, the environmental quality assessment, the biological feature vector, the environmental feature vector, and the comprehensive feature vector based on the assessment model to obtain an assessment result of the ecosystem service function of the ecological protection zone, wherein the comprehensive feature vector is determined based on a fusion of the biological feature vector, the environmental feature vector, and dynamically adjusted biological weights and environmental weights; A generation and construction module is used to generate a comprehensive feature matrix based on the plant and animal information, the environmental quality assessment, and the ecosystem service function assessment results, and to perform deep learning on the comprehensive feature matrix to construct a digital twin engine; wherein the comprehensive feature matrix is ​​composed of fused feature vectors of multiple spatiotemporal units arranged in a spatiotemporal sequence, and the fused feature vector of a single spatiotemporal unit is formed by multimodal feature splicing of the plant and animal information, environmental quality assessment, and ecosystem service function assessment results corresponding to the current spatiotemporal unit; A rendering module is used to render the linkage status of species, environment and ecosystem service functions on a visual interface in response to real-time data input into the digital twin large model after constructing the digital twin large model based on the digital twin engine and the model static base information. The visual interface is a virtual reality (VR) interface or an augmented reality (AR) interface.

[0009] The technical solution provided in the embodiments of the present application, after analyzing biological data and environmental data to obtain information on flora and fauna and environmental quality assessments within the ecological protection zone, conducts a comprehensive analysis of biological feature vectors generated based on biological data, environmental feature vectors generated based on environmental data, comprehensive feature vectors generated by fusing the two types of vectors with dynamically adjusted biological weights and environmental weights, and flora and fauna information and environmental quality assessments within the ecological protection zone to obtain more comprehensive, accurate, and scientific ecosystem service function assessment results; generates a comprehensive feature matrix based on the flora and fauna information, environmental quality assessments, and ecosystem service function assessment results, which can improve the accuracy of coupling modeling between ecological variables; after obtaining the comprehensive feature matrix, performs deep learning on the comprehensive feature matrix to construct a digital twin engine, constructs a digital twin large model based on the digital twin engine and the static base information of the model, processes real-time data input into the digital twin large model, and renders the linkage status of species, environment, and ecosystem service functions in a VR interface or AR interface, which can achieve state synchronization between the physical ecosystem and the digital twin large model, ensuring the timeliness and accuracy of the large model, and visually displaying the content provided by the digital twin large model through VR technology or AR technology to provide an immersive user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic diagram of a method for constructing a digital twin of a terrestrial ecosystem provided in an embodiment of the present application; Figure 2 A simplified flowchart of the digital twin model processing real-time data provided by an embodiment of the present application is shown; Figure 3 The overall implementation flow chart of the digital twin construction in the embodiment of the present application is shown; Figure 4 Schematic diagram of the digital twin construction system for terrestrial ecosystems provided in an embodiment of the present application. DETAILED DESCRIPTION

[0011] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0012] The present application provides a method for constructing a digital twin of a terrestrial ecosystem. Figure 1As shown, the following steps are included: Step 101: Based on the biological data and environmental data collected in the ecological protection zone, obtain information on animals and plants and environmental quality assessment in the ecological protection zone. The biological data is used to generate biological feature vectors for animal and plant identification, and the environmental data is used to generate environmental feature vectors for environmental quality assessment.

[0013] After selecting an ecological protection zone, embodiments of the present application utilize data collection equipment (e.g., unmanned equipment equipped with various sensors) to collect biological and environmental data within the ecological protection zone during one or more specific time periods. After acquiring the biological and environmental data through data collection, a biological feature vector is generated based on the biological data, and an environmental feature vector is generated based on the environmental data. The generated biological feature vector is used to indicate the global biological characteristics of the ecological protection zone, and the generated environmental feature vector is used to indicate the global environmental characteristics of the ecological protection zone.

[0014] By identifying plants and animals within the ecological reserve based on biological feature vectors and assessing their environmental quality based on environmental feature vectors, we can obtain information on the flora and fauna within the ecological reserve and an assessment of their environmental quality. The obtained flora and fauna information represents the overall flora and fauna information for the ecological reserve, while the obtained environmental quality assessment represents the overall environmental quality assessment for the ecological reserve. By identifying plant and animal species within the ecological reserve, we can understand information such as the species, abundance, and distribution of plants and animals within the reserve. By conducting environmental quality assessments within the ecological reserve, we can promptly identify environmental problems within the reserve and provide a scientific basis for ecological protection and management.

[0015] Step 102: Process the plant and animal information, environmental quality assessment, biological feature vectors, environmental feature vectors, and comprehensive feature vectors based on the large assessment model to obtain the ecosystem service function assessment results of the ecological protection zone. The comprehensive feature vector is determined based on the fusion of the biological feature vector, the environmental feature vector, and the dynamically adjusted biological weight and environmental weight.

[0016] After obtaining the information of plants and animals in the ecological protection zone based on biological characteristic vectors and the environmental quality assessment situation in the ecological protection zone based on environmental characteristic vectors, the large assessment model is used to process the biological characteristic vectors, environmental characteristic vectors, comprehensive characteristic vectors, the information of plants and animals in the ecological protection zone and the environmental quality assessment situation to evaluate the ecosystem service function of the ecological protection zone and obtain the ecosystem service function assessment results.

[0017] The comprehensive feature vector is determined by integrating the biological and environmental feature vectors, along with dynamically adjusted biological and environmental weights. These weights can be dynamically adjusted based on the real-time contributions of biological and environmental factors. For example, the weights are adjusted based on their actual contributions to ecosystem health and function at the current point in time. The biological feature vector reflects information such as biodiversity and species richness, while the environmental feature vector encompasses multiple environmental factors. By integrating the biological and environmental feature vectors and combining them with the dynamically adjusted biological and environmental weights to generate a comprehensive feature vector, a more comprehensive assessment of the ecological status of ecological reserves can be achieved.

[0018] The biological and environmental feature vectors, respectively, contain biological and environmental information within the ecological reserve. These vectors provide foundational data from which more specific biological information (primarily regarding flora and fauna) and environmental quality assessments can be extracted. The flora and fauna information derived from analyzing the biological feature vectors represents higher-level information, such as species diversity and the distribution of key species. The environmental quality assessments derived from analyzing the environmental feature vectors also represent higher-level information, such as water quality compliance and soil contamination levels. While individual flora and fauna information and environmental quality assessments provide important information, they are preliminary results and may lose some details and potential connections within the original data. Analyzing the biological, environmental, and combined feature vectors, while also considering flora and fauna information and environmental quality assessments within the ecological reserve, can uncover more potential information and relationships.

[0019] By comprehensively analyzing biological characteristic vectors, environmental characteristic vectors, comprehensive characteristic vectors, information on plants and animals in ecological protection areas, and environmental quality assessments, we can reveal the complex interactions between organisms and the environment, and gain a more comprehensive understanding of the overall status of the ecosystem. This will enable us to evaluate the ecosystem service functions in a more comprehensive, accurate, and in-depth manner, and obtain the results of the ecosystem service function assessment.

[0020] Step 103: Generate a comprehensive feature matrix based on the plant and animal information, environmental quality assessment, and ecosystem service function assessment results, and perform deep learning on the comprehensive feature matrix to construct a digital twin engine; wherein the comprehensive feature matrix is ​​composed of fused feature vectors of multiple spatiotemporal units arranged in a spatiotemporal sequence, and the fused feature vector of a single spatiotemporal unit is formed by multimodal feature splicing of the plant and animal information, environmental quality assessment, and ecosystem service function assessment results corresponding to the current spatiotemporal unit.

[0021] After obtaining information on flora and fauna within the ecological reserve, environmental quality assessments, and ecosystem service function assessment results using a large-scale assessment model, the relevant data within each spatiotemporal unit of the ecological reserve is processed. A spatiotemporal unit refers to a specific area and time period within the ecological reserve, divided according to both spatial and temporal dimensions. For each spatiotemporal unit, the comprehensive feature vector is processed with the corresponding flora and fauna information, environmental quality assessments, and ecosystem service function assessment results to determine standard data. Multimodal features (including at least biological, environmental, and service function features) are extracted from the standard data, and feature vectors for each modality are generated based on these extracted features. Within the same temporal and spatial dimensions, the feature vectors for each modality are concatenated to generate a fused feature vector for the current spatiotemporal unit. For example, for each spatiotemporal unit (e.g., a 10m grid x 1h time slice), multimodal feature vectors are generated from the biological, environmental, and service function features extracted within the spatiotemporal unit. These vectors are then concatenated to form a fused feature vector. The fused feature vectors for multiple spatiotemporal units are then arranged in time sequence and spatial grid order to form a comprehensive feature matrix.

[0022] After obtaining the comprehensive feature matrix, a deep learning process is performed on it to construct a digital twin engine. The digital twin engine consists of a dynamic computing layer and a rule engine layer, each responsible for real-time computing and logical decision-making, respectively. Together, they constitute the core functionality of the digital twin engine. Hierarchically, the dynamic computing layer is typically at the bottom, responsible for basic computing, while the rule engine layer is at the top, responsible for logical judgment and decision support.

[0023] When building a digital twin engine based on a comprehensive feature matrix, the comprehensive feature matrix is ​​used as input, and deep learning is used to form a dynamic computing layer. With the dynamic computing layer as the core, the rule engine layer is integrated and encapsulated into the digital twin engine. The constructed digital twin engine has real-time data access, state calculation, rule judgment, and response triggering capabilities. It is the core driver module of the digital twin model, supporting the dynamic operation and intelligent decision-making of the large model.

[0024] Step 104: After constructing the digital twin large model based on the digital twin engine and the model static base information, in response to the real-time data input into the digital twin large model, the linkage status of species, environment and ecosystem service functions is rendered on the visualization interface, and the visualization interface is a virtual reality VR interface or an augmented reality AR interface.

[0025] The digital twin engine constructed based on deep learning of the comprehensive feature matrix serves as the core computing and decision-making module of the digital twin large model, responsible for multiple dynamic functions such as real-time data processing, state calculation, and rule response; the model's static base information provides the spatial structure and basic properties of the large model, including information such as terrain, vegetation type, and soil texture. This information provides a spatial reference framework for the digital twin engine, enabling its calculation results to be accurately located and displayed in geographic space.

[0026] The digital twin engine is responsible for calculation and response. The static base information of the model is the skeleton, which can provide spatial structure and basic properties. The digital twin engine is combined with the static base information of the model to construct a large digital twin model.

[0027] After constructing the digital twin model, real-time data is fed into it, which then processes the input. For example, real-time plant and animal information, environmental quality assessments, and ecosystem service function evaluations are fed into the digital twin engine through an IoT interface. The engine then dynamically updates the state of the digital twin model, keeping it synchronized with the real ecosystem.

[0028] After processing the input real-time data, the digital twin model outputs the linkage status of species, environment and ecosystem service functions, and visualizes the output content through VR (Virtual Reality) or AR (Augmented Reality) technology, allowing users to intuitively understand the status of the ecosystem through the VR interface or AR interface.

[0029] The latest data is continuously acquired through the Internet of Things and processed by the digital twin model, ensuring that the model always reflects the current state of the ecosystem and maintains its timeliness and accuracy; and the output content of the digital twin model is displayed using a visual interface. VR or AR technology can be used to convert abstract data into intuitive three-dimensional images or augmented reality images to ensure the user's visual experience.

[0030] The above implementation scheme of the embodiment of the present application, after analyzing biological data and environmental data to obtain animal and plant information and environmental quality assessment in the ecological protection zone, comprehensively analyzes the biological feature vectors generated based on biological data, the environmental feature vectors generated based on environmental data, the comprehensive feature vectors generated by the fusion of the two types of vectors combined with dynamically adjusted biological weights and environmental weights, and the animal and plant information and environmental quality assessment in the ecological protection zone to obtain more comprehensive, accurate and scientific ecosystem service function assessment results; generating a comprehensive feature matrix based on animal and plant information, environmental quality assessment and ecosystem service function assessment results can improve the accuracy of coupling modeling between ecological variables; after obtaining the comprehensive feature matrix, deep learning is performed on the comprehensive feature matrix to construct a digital twin engine, and a digital twin large model is constructed based on the digital twin engine and the static base information of the model. The real-time data input into the digital twin large model is processed, and the linkage status of species, environment and ecosystem service functions is rendered in a VR interface or AR interface, which can achieve state synchronization between the physical ecosystem and the digital twin large model, ensure the timeliness and accuracy of the large model, and visualize the content provided by the digital twin large model through VR technology or AR technology to provide an immersive user experience.

[0031] The following describes the method for obtaining information on flora and fauna within ecological protection zones, environmental quality assessments, and ecosystem service function assessments. The method involves: Generate biological feature vectors based on the collected biological data, and generate environmental feature vectors based on the collected environmental data, where the biological data at least includes image data, audio data and positioning data of animals and plants, and the environmental data at least includes meteorological data and physical environment data; perform species identification on the biological feature vectors based on the biological big model to obtain information on animals and plants in the ecological protection zone, and perform environmental analysis on the environmental feature vectors based on the environmental big model to obtain an environmental quality assessment within the ecological protection zone.

[0032] The biological data collected by the collection equipment includes at least image data, audio data, and location data of plants and animals. The environmental data collected includes at least meteorological data and physical environment data. For example, environmental data includes, but is not limited to, temperature, humidity, soil conditions, water quality, light intensity, air pressure, wind speed, and seasonal factors. By collecting environmental data, we can provide background information on the survival and activities of plants and animals within the ecological reserve, which, combined with the biological data, can more comprehensively describe the regional characteristics of the ecological reserve.

[0033] After generating a biological feature vector based on the collected biological data, the biological feature vector is used to identify species based on a pre-built biological macro model to obtain information about plants and animals. The biological macro model is a species identification model. Based on the biological macro model, inference analysis is performed on the biological feature vector to obtain information about plants and animals within the ecological protection zone output by the biological macro model. This allows for effective identification of species within the ecological protection zone and global information about plants and animals. After generating an environmental feature vector based on the collected environmental data, an environmental quality assessment is performed on the environmental feature vector based on the pre-built environmental macro model. The environmental macro model is an environmental assessment model. Based on the environmental feature vector, a global environmental quality assessment of the ecological protection zone output by the environmental macro model can be obtained. The environmental quality assessment output by the environmental macro model includes, for example, an environmental quality score, which is determined based on a comprehensive assessment of environmental factors such as water quality, soil, and meteorological conditions within the ecological protection zone.

[0034] Optionally, when processing the plant and animal information, environmental quality assessment, biological feature vectors, environmental feature vectors, and comprehensive feature vectors based on the large assessment model to obtain the ecosystem service function assessment results of the ecological protection zone, the following may be included: The comprehensive feature vector is determined by vector splicing based on the biological feature vector, environmental feature vector and dynamically adjusted biological weight and environmental weight; based on the optimized assessment model, the biological feature vector, environmental feature vector, comprehensive feature vector, animal and plant information and environmental quality assessment are comprehensively reasoned and analyzed to generate the ecosystem service function assessment results.

[0035] The comprehensive feature vector is determined based on the fusion of biological feature vectors, environmental feature vectors, and dynamically adjusted biological and environmental weights. By integrating biological and environmental feature vectors to form a comprehensive feature vector, a more comprehensive assessment of the health of an ecological conservation area can be achieved. Furthermore, the comprehensive feature vector is not only based on the biological and environmental feature vectors, but also takes into account the dynamically adjusted biological and environmental weights. The biological and environmental weights are dynamically adjusted based on the contribution of biological and environmental data to the assessment of ecosystem service functions. This dynamic adjustment mechanism allows for flexible weight adjustments based on the characteristics and conservation objectives of different ecological regions, thereby obtaining a targeted comprehensive feature vector. Compared to existing technologies that have difficulty integrating multi-source heterogeneous data (such as biological and environmental data) and have fixed weights that cannot be dynamically adjusted, the present embodiment integrates biological data (such as images, audio, and location data) with environmental data (such as meteorological, soil, and water quality) to generate biological and environmental feature vectors. The comprehensive feature vector is then generated based on the dynamically adjusted weights, addressing the data integration challenge. Furthermore, the dynamic weight adjustment mechanism allows for flexible weight adjustments based on the data's real-time contribution to the assessment of ecosystem service functions, thereby more accurately reflecting the overall health of the ecosystem.

[0036] For example, a specific example of generating a comprehensive feature vector with dynamic weight adjustment is given here: 1. Input data and initial feature vector Biological feature vector (dimension = 4): B = [0.2, 0.95, 0.15, 0.5] (indicating the number of Siberian tigers, confidence, number of red deer, and activity range); environmental feature vector (dimension = 4): E = [0.6, 0.65, 0.68, 0.67] (indicating temperature, humidity, soil pH, and snow depth).

[0037] 2. Dynamic weight adjustment rules Default weights (ecological balance scenario): biological weight = 0.5, environmental weight = 0.5; Dynamic adjustment conditions: If the number of key species (such as the Siberian tiger) is detected to have decreased by more than 10%, the biological weight = 0.7 and the environmental weight = 0.3; if the environmental parameters (such as soil pH) exceed the threshold (<6.5 or >7.5), the environmental weight = 0.8 and the biological weight = 0.2.

[0038] Example scenario: The current Siberian tiger population has decreased by 15% compared to last month (triggering the key species protection rule), and the weights are adjusted to: biological weight = 0.7, environmental weight = 0.3.

[0039] 3. Weighted fusion calculation Weighted biological feature vector: B_weighted = biological weight * B = 0.7 * [0.2, 0.95, 0.15, 0.5] = [0.14, 0.665, 0.105, 0.35]; weighted environmental feature vector: E_weighted = environmental weight * E = 0.3 * [0.6, 0.65, 0.68, 0.67] = [0.18, 0.195, 0.204, 0.201].

[0040] Comprehensive feature vector (after splicing): F = concat(B_weighted, E_weighted) = [0.14, 0.665, 0.105, 0.35, 0.18, 0.195, 0.204, 0.201].

[0041] The evaluation model is a large-scale model used to assess ecosystem service functions. It uses the model to intelligently and comprehensively analyze biological feature vectors, environmental feature vectors, comprehensive feature vectors, information on flora and fauna within ecological protection areas, and environmental quality assessments. This can reveal the complex interactions between organisms and the environment, and provide a more comprehensive understanding of the overall state of the ecosystem, thereby enabling a more comprehensive, accurate, and in-depth assessment of ecosystem service functions. The evaluation model can be optimized from multiple perspectives, including data quality, model architecture, training strategies, and evaluation metrics, to improve the accuracy and reliability of the model's assessment of ecosystem service functions. Pre-training or transfer learning can also be used to pre-train the model on large amounts of relevant data, improving its performance and generalization capabilities. For example, relevant data can be fed into the evaluation model in advance to allow the model to learn.

[0042] The ecosystem service functions evaluated in the embodiments of this application include, for example, biodiversity, water purification, climate regulation, soil fertility maintenance, etc. By comprehensively and in-depth evaluating the ecosystem service functions, more scientific decision-making support can be provided for ecological protection and resource management, thereby formulating effective protection strategies in a targeted manner.

[0043] For example, here is a specific example of how the ecosystem service function assessment results are generated: Based on the comprehensive analysis of biological and environmental data by the evaluation model, quantitative indicators of service function modalities are generated: (1) Carbon sink (t / ha): Input layer: Vegetation cover data: Broadleaf forest proportion (45%), coniferous forest proportion (30%); Meteorological data: Monthly average temperature (5.2°C), historical benchmark temperature (6.0°C); Processing flow: Calculation of vegetation carbon sequestration potential: The carbon sequestration coefficient of broadleaf forest is α=0.8, and that of coniferous forest is β=0.6; Basic carbon sink value = (0.45×α+ 0.3×β) = 0.54; Temperature adaptability correction: Use Sigmoid response function (the carbon sequestration efficiency is maximized when the optimum temperature is met (should be 1.0)):

[0044] Wherein, T represents the current ambient temperature (5.2°C in the embodiment) and T0 represents the optimum temperature of the species (or vegetation) (set to 6.0°C in the embodiment).

[0045] Ecological significance: When the ambient temperature is equal to T0, biological functions (such as carbon sequestration efficiency) reach the optimal state.

[0046] k: represents the sensitivity coefficient (k=0.5), which controls the steepness of the curve and reflects the sensitivity of the species to temperature deviation.

[0047] Temperature correction factor = ≈0.8.

[0048] Final carbon sink: Normalized value = basic carbon sink value × temperature correction factor = 0.54 × 0.8 ≈ 0.43.

[0049] (2) Water conservation capacity (%) Input layer: Hydrological data: monthly precipitation (120 mm); soil data: pH value (7.8), snow depth (15 cm); historical benchmark: average annual precipitation (100 mm); Processing flow: Calculation of basic conservation capacity: precipitation factor = min(current precipitation / historical benchmark, 1.2) = 1.2; Soil water retention amendment: pH deviation penalty: When pH When [6.5,7.5], the penalty coefficient γ=0.9; Snow compensation: δ=h*(snow thickness / reference thickness) Snow thickness: measured value (15cm); Baseline thickness: Take the historical average snow thickness of the region in winter (e.g. 22.5cm, which needs to be adjusted according to actual data); Compensation coefficient h: The value range is 0.1~0.3 (needs calibration), which represents the contribution intensity of unit snow thickness to water conservation. In this embodiment, the value is 0.3; δ=0.3×(15cm / 22.5cm) = 0.2; Soil correction factor = γ + δ = 1.1; Comprehensive calculation: Original value = precipitation factor × soil correction factor = 1.2 × 1.1 = 1.32; Normalized value = tanh(original value) ≈ 0.72.

[0050] (3) Biodiversity Index Input layer: Species data: Siberian tiger index (0.58), red deer index (0.15); Vegetation data: Broadleaf forest (45%), shrub (25%); Processing flow: Species diversity calculation: Key species weights: Siberian tiger w1=0.6, red deer w2=0.4; Animal diversity = w1 × Siberian tiger index + w2 × red deer index = 0.6 × 0.58 + 0.4 × 0.15 ≈ 0.41; Vegetation diversity calculation: Shannon index calculation: H'=-Σ(p i ×ln(p i )), where p i represents the relative proportion of the i-th species (or vegetation type) in the community (i.e., the ratio of the number of individuals or area covered by the species to the total). For example: if broadleaf forest accounts for 45% → p1 = 0.45; if coniferous forest accounts for 30% → p2 = 0.3; if shrubs account for 25% → p3 = 0.25.

[0051] ln(p i ): indicates the p i Take the natural logarithm (base e).

[0052] If p i = 0 (a species does not exist), then it is agreed that p i ×ln(p i ) = 0 (to avoid mathematical undefined).

[0053] Σ (cumulative): represents the p for all species (or vegetation types) i ×ln(p i ) values.

[0054] Vegetation composition ratio: broad-leaved forest 0.45, coniferous forest 0.3, shrub 0.25.

[0055] H'≈1.03, which is 0.68 after normalization.

[0056] Composite Index: The geometric mean was used: sqrt(animal diversity × vegetation diversity) = sqrt(0.41 × 0.68) ≈ 0.53; After logistic regression calibration, the output was 0.61; The service function feature vector is obtained: S = [0.65, 0.72, 0.61].

[0057] In the above-mentioned implementation plan for ecosystem service function evaluation based on multidimensional data, a comprehensive and dynamic evaluation of ecosystem service functions is achieved by integrating multidimensional data and dynamically adjusting weights, including species diversity, water purification, climate regulation, soil fertility maintenance and other aspects. Compared with the existing technology that usually focuses on the static evaluation of a single or a few service functions, this application achieves a comprehensive and dynamic evaluation of ecosystem service functions through multimodal data fusion and dynamic analysis, which can more realistically reflect the changing trends of the ecosystem.

[0058] The following describes the scheme for generating a comprehensive feature matrix. This includes the following steps based on plant and animal information, environmental quality assessments, and ecosystem service function assessments: Data preprocessing and temporal and spatial alignment of multi-source data within each spatiotemporal unit are performed to determine standard data. Multi-source data within a single spatiotemporal unit includes comprehensive feature vectors, as well as the corresponding animal and plant information, environmental quality assessment, and ecosystem service function assessment results of the current spatiotemporal unit. Extracting multimodal features from standard data and generating feature vectors of each modality based on the extracted features, wherein the multimodal features include at least biological features, environmental features, and service function features; In the same time and space dimensions, the feature vectors of each modality are concatenated to generate the fused feature vector of the current space-time unit; The fused feature vectors of multiple spatiotemporal units are arranged in time series and spatial grid order to form a comprehensive feature matrix.

[0059] The comprehensive feature matrix is ​​a structured data representation generated by preprocessing, spatiotemporal alignment, feature extraction and feature fusion of multi-source heterogeneous data. It is the core input for building a large digital twin model. The comprehensive feature matrix provides a unified and standardized data foundation for a series of subsequent operations.

[0060] When generating a comprehensive feature matrix based on plant and animal information, environmental quality assessment results, and ecosystem service function assessment results, the specific implementation process is as follows: 1. Data preprocessing and data format unification When generating a comprehensive feature matrix, the data provided includes plant and animal information (such as species name, location coordinates, confidence level, richness index, etc.), environmental quality assessments (such as water quality parameters, soil parameters, meteorological data, etc.), and ecosystem service function assessment results (such as biodiversity index, carbon sequestration, water conservation, pollination service intensity, pollutant purification rate, etc.). It also needs to be combined with a comprehensive feature vector derived from the fusion of global biological feature vectors and global environmental feature vectors. The provided data is preprocessed, such as denoising, outlier removal, missing value filling, data format unification (such as rasterization and time series alignment), and data processing based on dimensional normalization or standardization.

[0061] 2. Space-time alignment and gridding Align data temporally and spatially based on a unified spatiotemporal benchmark to determine standard data. For example, a unified spatial grid (e.g., 10m×10m) is used at the spatial level, and a unified temporal resolution (e.g., 1 hour, 5 hours, etc.) is determined at the temporal level. Alignment can be performed using methods such as spatial interpolation to map species observation point data to the grid, and temporal interpolation to align data with different sampling frequencies to a unified timestamp.

[0062] 3. Feature extraction and vectorization Multimodal feature extraction is performed in standard data, where the multimodal features include at least biometric features, environmental features, and service function features. Biometric features include image features, audio features, and positioning features. For image data, for example, image features are extracted using a convolutional neural network; for audio data, for example, voiceprint features are extracted using an audio recognition model; for positioning data, for example, positioning features are extracted using a graph neural network or a trajectory embedding model. Environmental data includes at least meteorological data and physical environment data. For environmental data, time series statistical features are extracted to obtain environmental features. Service function features are extracted for service function data. After extracting features to obtain feature vectors of fixed dimensions, all feature vectors are organized in space grid-time units. It is worth noting that in the same time and space dimensions, it is preferably considered to dynamically adjust the weights of each modality, and obtain the weighted feature vectors of each modality with the dynamically adjusted weights of each modality.

[0063] 4. Feature fusion and matrix generation During feature fusion, feature vectors from different modalities are concatenated within the same temporal and spatial dimensions. Feature importance can also be considered, with different weights assigned to feature vectors from different modalities. After feature fusion, each spatial grid-time unit corresponds to a fused feature vector. All fused feature vectors are arranged in time series and spatial grid order to form a comprehensive feature matrix, which serves as input for subsequent modeling.

[0064] 4.1 Assuming input data (single spatiotemporal unit) Spatiotemporal unit: Grid A of a certain ecological protection area, time: 2023-10-01 10:00.

[0065] The input data includes the following: Plant and animal information (biological characteristics): Species 1 (Siberian tiger): number = 2, confidence = 0.95, activity range = 5km²; Species 2 (red deer): number = 15, confidence = 0.90.

[0066] Environmental quality assessment (environmental characteristics): temperature = 18°C, humidity = 65%, soil pH = 6.8, snow depth = 20 cm.

[0067] Ecosystem service function assessment results (service function characteristics): carbon sequestration = 2.4 t / ha, water conservation capacity = 85%, biodiversity index = 0.78.

[0068] 4.2 Generating the fused feature vector of a single spatiotemporal unit (1) Data preprocessing Normalize the values ​​(scale to [0, 1]): Number of Siberian tigers: 2 → normalized to 0.2 (assuming the maximum number of tigers in the area = 10); temperature: 18°C ​​→ 0.6 (assuming the temperature range is [-10, 30]°C); carbon sink: 2.4 t / ha → 0.8 (assuming the maximum carbon sink = 3 t / ha).

[0069] (2) Multimodal feature extraction Biological feature vector (dimension = 4): [0.2, 0.95, 0.15, 0.5] (Note: 0.15 = normalized value of elk population, 0.5 = normalized value of activity range); Environmental feature vector (dimension = 4): [0.6, 0.65, 0.68, 0.67] (Note: 0.65 = normalized value of humidity, 0.68 = normalized value of soil pH, 0.67 = normalized value of snow depth); Service function modal feature vector (dimension = 3): [0.8, 0.85, 0.78] (Note: 0.85 = normalized value of water conservation capacity).

[0070] It should be noted that, in this embodiment, it is still preferred to consider dynamically adjusting the weights of each modality.

[0071] The weights of the three vectors must meet the normalization condition: biological weight + environmental weight + service weight = 1. The following is an example of dynamic weight calculation: basic weight (default scenario): biological weight = 0.4, environmental weight = 0.4, service weight = 0.2.

[0072] Example adjustment rule: If the species diversity index drops below a threshold (e.g., 10%), then: biological weight = 0.6, environmental weight = 0.3, service weight = 0.1.

[0073] If the water pH exceeds the safe range (6.5-7.5), then: environmental weight = 0.7, biological weight = 0.2, service weight = 0.1.

[0074] In the scenario prioritizing the protection of key species, the input data are: the number of Siberian tigers decreased by 15% month-on-month (triggering the protection rule); environmental parameters are normal (pH = 6.8, temperature = 18°C); carbon sequestration is stable, and the weights are adjusted: biological weight = 0.6, environmental weight = 0.3, and service weight = 0.1.

[0075] Weighted eigenvectors: Biometric feature vector B = [0.2, 0.95, 0.15, 0.5]→0.6*B = [0.12, 0.57, 0.09,0.3]; Environmental feature vector E = [0.6, 0.65, 0.68, 0.67]→0.3*E = [0.18, 0.195,0.204, 0.201]; Service function vector S = [0.8, 0.85, 0.78]→0.1*S = [0.08, 0.085, 0.078].

[0076] 4.3 Feature stitching Concatenate the vectors of the three modalities into a fused feature vector (dimension = 11): F = concat(0.6B, 0.3E, 0.1S) = [0.12, 0.57, 0.09, 0.3,0.18, 0.195, 0.204, 0.201, 0.08, 0.085, 0.078].

[0077] 4.4 Constructing a comprehensive feature matrix Repeat the above process to generate fused feature vectors of multiple spatiotemporal units and arrange them in spatiotemporal order:

[0078] The final generated comprehensive feature matrix is ​​in the form of: [0.12, 0.57, 0.09, 0.30, 0.18, 0.195, 0.204, 0.201, 0.08, 0.085,0.078], grid A 10:00; [0.18, 0.552, 0.108, 0.30, 0.186, 0.189, 0.210, 0.195, 0.079, 0.083,0.077], grid B 11:00; [0.00, 0.00, 0.00, 0.00, 0.165, 0.210, 0.195, 0.180, 0.07, 0.075,0.065], grid C 10:00.

[0079] During the above implementation process, consistency checks can be performed to ensure the spatial consistency of different data sources within the same grid; integrity checks can be performed to identify whether there are null values ​​or outliers; and logical checks can be performed to verify the ecological rationality between species distribution and environmental conditions (for example, wetland species should not appear in arid areas).

[0080] In the above implementation plan for generating a comprehensive feature matrix, a framework for the fusion of the three modal features of "species-environment-service function" is implemented, and the three types of data on species, environment, and service functions are aligned to a unified grid and time axis to eliminate scale differences and ensure the comparability of variables in the same dimension; animal and plant information supplements biological data, environmental data characterizes the background information of species, and service functions provide ecological output indicators. The three complement each other to increase the amount of information; through spatiotemporal alignment and deep learning, the quantification of the coupling relationship of ecological variables is achieved, and the matrixed data retains effective features, which improves the data signal-to-noise ratio.

[0081] In the embodiment of the present application, after generating the comprehensive feature matrix, a digital twin engine is constructed by performing deep learning on the comprehensive feature matrix. The process includes the following steps: Deep learning is performed on the comprehensive feature matrix to output a weight matrix, a response function, and a threshold rule. The weight matrix includes multiple coupling weights and is used to quantify the interaction between species and the environment and service functions. The response function is used to describe the response relationship between ecosystem variables. The threshold rule is used to define the critical state of the ecosystem. Based on the weight matrix, response function and threshold rules, a dynamic kernel is generated to calculate the ecosystem state, evaluate the trend of ecosystem state change and identify critical states; Encapsulate the dynamic kernel and rule engine to build a digital twin engine. The rule engine makes decision responses based on the output results of the dynamic kernel.

[0082] After generating a comprehensive feature matrix, a deep learning model (such as the neural network shown in the figure) conducts deep learning on the matrix, automatically extracting coupling weights between species and environment, species and service functions, environment and service functions, and species and environment and service functions. The model then outputs a weight matrix, response function, and threshold rules. Together, these three constitute the dynamic core, providing logical support for subsequent calculations. The dynamic core is then integrated with a rule engine, encapsulating it as a digital twin engine. The digital twin engine provides real-time data access, state calculation, trend analysis, rule judgment, and response triggering capabilities. It is the core driver module of the digital twin model, supporting its dynamic operation and intelligent decision-making.

[0083] Among them, the dynamic kernel is responsible for real-time calculation of the interactions and state changes between various elements of the ecosystem (species, environment, service functions), analysis of the changing trends of the ecosystem state, identification of critical situations, and output of the current system state, the analyzed changing trends, and identification of whether critical conditions have been reached; the rule engine performs logical judgments and response actions based on the output of the dynamic kernel to achieve intelligent feedback and decision support.

[0084] Specifically, the dynamic kernel is primarily used to calculate the current real-time state of the ecosystem, analyze trends in ecosystem state changes, and identify critical states. For example, when calculating the real-time state of the ecosystem, it assesses species status (such as species richness, diversity, and distribution), environmental status (such as water quality, soil, and meteorological parameters), and service function status (such as carbon sequestration capacity, water conservation capacity, and biodiversity maintenance capacity). When analyzing ecosystem state trends, it uses recent data, historical ecosystem data, and response functions to calculate the direction and magnitude of change in the current state relative to the previous moment. For example, it assesses whether species richness is increasing or decreasing, water quality is improving or deteriorating, and service capacity is increasing or decreasing. When identifying critical states, it identifies whether ecological thresholds have been reached (such as whether pH is less than 6.5 or whether species richness has decreased by more than 20%). The dynamic kernel can provide input to the rule engine, such as transmitting the current ecosystem state value, state change trends, and critical state identification results to the rule engine, which then processes the information accordingly.

[0085] It should be noted that the dynamic kernel mainly processes real-time data, but the historical data of the ecosystem serves as background information to enhance the accuracy and reliability of the analysis and to assist in a more comprehensive and accurate understanding of the changes in the ecosystem.

[0086] The rules engine is primarily responsible for performing the following tasks based on the current state, state change trends, and critical identification results output by the dynamic core: 1. Logical judgment and decision triggering; 2. Response action execution. During logical judgment and decision triggering, it determines whether pre-set business rules or response conditions are met. For example, a pH value below 6.5 triggers an acidification warning, a species richness decrease of more than 20% triggers an ecological degradation alert, and a carbon sink estimate decrease of more than 10% triggers a service adjustment recommendation. When executing a response action, the rules engine automatically executes matching actions based on the judgment results, such as issuing a warning and recommending intervention measures (such as planting water-purifying plants or limiting pollutant discharge). The rules engine also supports feedback of judgment results and response actions to a visual interface, allowing relevant personnel to review risks and intervention recommendations, providing auxiliary information for ecological protection and resource regulation decisions. It is important to note that the rules engine not only considers the current state but also integrates state change trends in its logical judgment, thereby enabling more intelligent and proactive ecological response and decision support.

[0087] Specifically, the dynamic core calculates the current state of the ecosystem, analyzes state change trends, and identifies critical areas, providing a basis for real-time monitoring and response. Based on the dynamic core's output of the current state, state change trends, and critical areas, the rule engine, combined with pre-set business rules, executes logical judgments and triggers corresponding response actions, enabling intelligent feedback and decision support for the ecosystem. As a key module for achieving intelligent feedback and decision support, the rule engine forms a closed-loop "judgment + response" mechanism with the dynamic core, building the digital twin engine as the core driver of the digital twin model.

[0088] Optionally, when performing deep learning on the comprehensive feature matrix and outputting the weight matrix, response function, and threshold rule, the following steps are included: The comprehensive feature matrix is ​​input into the deep learning model to learn the coupling relationship between species variables, environmental variables and service function variables. The output includes a weight matrix including the coupling weights between species and environment, the coupling weights between species and service functions, the coupling weights between environment and service functions, and the coupling weights of multi-factor synergy. Embed nonlinear activation layers in deep learning models to fit the functional relationships among species variables, environmental variables, and service function variables, and determine the response function. During the training process of the deep learning model, key ecological thresholds are learned based on the loss function constraints and threshold rules are generated.

[0089] The deep learning model inputs a comprehensive feature matrix, and deep learning is performed on the matrix to obtain coupling weights for species and environment, species and service functions, environment and service functions, and multi-factor synergy, forming a weight matrix. The multi-factor synergy coupling weight can be understood as the combined influence, or coupling weight, of species and environment on ecosystem services. It not only considers the impact of species on services or the impact of the environment on services in isolation, but also comprehensively considers the interactions between species and the environment, as well as their synergistic effects on services (such as carbon sequestration, water conservation, and biodiversity maintenance). For example, the species-environment-service synergy weight indicates how changes in species and service functions interact under specific environmental conditions, or how environmental changes affect service functions under specific species composition. For example, if increased precipitation (an environmental factor) and increased vegetation cover (a species factor) significantly improve water conservation capacity, the multi-factor synergy coupling weight indicates the strength of the positive impact of these two combined effects on water conservation. For example, under the combined effects of soil acidification (environmental factor) and the reduction of key species (species factor), the soil carbon sequestration capacity has significantly decreased, and the coupling weight of multi-factor synergy represents the intensity of the negative impact of the combined effects of the two on carbon sequestration.

[0090] Species, environment, and service functions all exist as variables in deep learning models. For example, species variables include species richness, diversity index, and the presence of key species; environmental variables include water pH, soil organic matter, temperature, and precipitation; and service function variables include carbon sequestration, water conservation capacity, and pollination service intensity. Learning the coupled relationships between species, environment, and service functions is essentially learning the coupled relationships between variables. Learning the coupled relationships between species, environment, and service functions is essentially modeling the interactions and response mechanisms between these variables through deep learning. By learning the correlations, causal relationships, or response patterns between these variables, deep learning models automatically extract coupling weights, response functions, and threshold rules.

[0091] A response function describes how one variable (such as environmental factors) responds to changes in another variable (such as species richness or service functions). It is used to describe the response relationship between ecosystem variables. It defines the mode and intensity of influence between variables and can be linear, nonlinear, or conditional. For example, a response function can represent the effect of improved water quality on species richness, or the effect of increased vegetation cover on carbon sequestration capacity.

[0092] Among them, the implementation process of deep learning of the comprehensive feature matrix, output weight matrix, response function and threshold rule is briefly described as follows: The comprehensive feature matrix is ​​input into the deep learning model, the coupling relationship between species, environment and service functions is learned through model training, and the coupling weight matrix between species, environment and service functions is output; a nonlinear activation layer is embedded in the deep learning model to learn the response relationship between variables and obtain the response function; loss function constraints are introduced during the model training process to automatically learn key ecological thresholds and obtain threshold rules.

[0093] Deep learning models such as graph neural networks (GNNs), spatiotemporal transformers, and convolutional neural networks (CNNs) are used to learn the coupling relationship between species, environment, and service functions from a comprehensive feature matrix; nonlinear activation layers are used to introduce nonlinear transformations, enabling the model to fit more complex functional relationships. Nonlinear activation layers are embedded in the model to enhance the model's ability to model the nonlinear response relationship between ecosystem variables, fit the complex functional relationship between species, environment, and service function variables in the ecosystem, and thus determine the response function; by introducing loss function constraints, threshold information can be learned, and then threshold rules can be obtained.

[0094] In the above implementation plan for building a digital twin engine, deep learning is performed on the comprehensive feature matrix to generate a dynamic kernel that calculates the state of the ecosystem, evaluates the trend of state changes, and identifies critical states. The dynamic kernel and the rule engine are integrated to build a digital twin engine, which can provide guarantees for the subsequent generation of large digital twin models.

[0095] The following describes the process of initializing a large digital twin model. When building a digital twin engine based on deep learning, the model's static foundational information, used to construct the 3D spatial skeleton and basic attributes, is loaded into the digital twin engine. The digital twin engine and the model's static foundational information are spatially aligned and logically bound, and various model parameters in the digital twin engine are configured to initialize the large digital twin model.

[0096] The model's static base information is used to construct the three-dimensional spatial skeleton and basic properties of the digital twin model. The model's static base information constructs the three-dimensional spatial skeleton and basic properties of the digital twin model by providing terrain structure and ecological properties. It is the spatial and property basis for the operation of the large model.

[0097] The three-dimensional spatial skeleton includes, for example, a terrain DEM (Digital Elevation Model), spatial gridding, and spatial positioning. The terrain DEM provides information such as elevation, slope, and aspect at each spatial point, thereby providing continuous elevation and terrain attributes. Spatial gridding divides the ecological region into regular grids (e.g., 10m x 10m), with each grid corresponding to a spatial unit, thereby discretizing the DEM into numbered grid cells. Spatial positioning spatially locates and overlays all dynamic data (species distribution, environmental parameters) based on this skeleton. In other words, grid IDs are used to accurately map real-time data such as species and environmental conditions to corresponding terrain units.

[0098] Basic attributes include, for example, a vegetation type raster and a soil texture map. The vegetation type raster provides rasterized vegetation attribute values, while the soil texture map provides rasterized soil attribute values. By unifying grid coordinates, vegetation, soil, and dynamic data are aligned on the same spatial basis to avoid misalignment. The vegetation type raster characterizes cover by annotating specific vegetation types (forest, grassland, wetland, etc.) within each spatial grid. These vegetation types directly influence species habitat suitability, carbon sequestration capacity, and other ecological processes, providing key ecological attribute inputs for the digital twin model. The soil texture map provides soil ecological parameters by specifying attributes such as soil type, organic matter content, and pH value for each grid cell. These parameters significantly influence plant growth rates, nutrient availability, pollutant adsorption, and water purification efficiency, and serve as fundamental inputs for the digital twin model's ecological simulations.

[0099] The process of initializing the digital twin large model based on the digital twin engine and the model's static base information mainly includes the following steps: 1. Loading the model's static base information into the digital twin engine to provide the large model with a three-dimensional spatial skeleton and basic attributes to ensure the large model's spatial accuracy and authenticity; 2. Through spatial alignment and data association, the model's static base information is integrated with the dynamic kernel and rule engine in the digital twin engine to establish a correspondence between space and attributes, enabling the digital twin engine to perform state calculations and response judgments based on the model's static base information; 3. According to the characteristics of the actual ecosystem (based on characteristics obtained from historical long-term statistics, such as multi-year average species richness, seasonal water quality fluctuation range, soil background value, etc.), configure the parameters in the digital twin engine, such as coupling weights, response functions, threshold rules, etc., and initialize the large model state to ensure that the large model can accurately reflect the initial situation of the ecosystem.

[0100] Among them, coupling weights are used to quantify the strength of interactions between species and their environments and service functions, and are key parameters for describing the relationships between variables in the macromodel. Response functions are used to describe the response relationships between variables and are functions that describe the patterns of change between variables in the macromodel. Threshold rules are used to define the critical state of the ecosystem, identifying whether warning or response conditions have been met and forming the basis for logical judgment and response triggering within the macromodel. Together, these parameters constitute the dynamic core of the digital twin macromodel, serving as key model parameters for describing the relationships, patterns of change, and critical states between ecosystem variables. They are the core components of the digital twin macromodel's ability to accurately reflect ecosystem status and behavior, and are the foundation for the macromodel's ability to perform real-time calculations, state updates, trend analysis, criticality identification, and response triggering.

[0101] After initializing the digital twin model, real-time data processing is performed based on the digital twin model to render the linkage status of species, environment, and ecosystem service functions on a visual interface. The process includes the following steps: The acquired real-time data is connected to the digital twin engine through a data interface, driving the digital twin engine to update the model status of the digital twin model. The real-time data includes real-time plant and animal information, real-time environmental quality assessment, and real-time ecosystem service function assessment results. Based on the updated digital twin model, real-time data and historical ecosystem data are processed to output ecosystem operation results. The ecosystem operation results indicate the linkage status of species, environment, and ecosystem service functions, and the ecosystem operation results include at least one of the current state of the ecosystem, the trend of ecosystem state change, the critical state of the ecosystem, and the decision response; The ecosystem operation results provided by the digital twin model are visualized through a VR interface or an AR interface.

[0102] The digital twin engine obtains real-time data (real-time plant and animal information, real-time environmental quality assessment, and real-time ecosystem service function assessment results) through data interfaces (such as the Internet of Things interface). The digital twin engine dynamically updates the status of the digital twin large model based on the real-time data obtained, keeping the large model synchronized with the real ecosystem.

[0103] After updating the digital twin model, real-time data and historical ecosystem data are processed based on the updated digital twin model. During this processing, the digital twin engine utilizes a dynamic core to perform state calculations based on real-time data, historical ecosystem data, and the model's static baseline information. This core evaluates the ecosystem's current state, state trends, and determines whether a critical state has been reached. Based on the dynamic core's output, the rules engine executes logical judgments and response actions, such as triggering early warnings, providing decision support for ecological protection and management.

[0104] Using a large digital twin model to process real-time and historical ecosystem data, the system can output ecosystem operational results that indicate the interconnected status of species, the environment, and ecosystem services. These results include at least one of the following: the current ecosystem state, ecosystem state trends, ecosystem criticality, and decision-making responses. The ecosystem operational results provided by the large digital twin model are displayed through a visual interface, allowing users to display the latest data using VR or AR interfaces.

[0105] It's important to note that historical ecosystem data reveals the long-term evolution and seasonal changes of ecosystem variables, helping the large-scale model understand the formation of the current state. Furthermore, by combining real-time and historical data, the large-scale model can capture both long-term trends and short-term fluctuations in ecosystem variables, thereby improving the accuracy of analysis. In other words, historical ecosystem data is a crucial input for digital twin large-scale model analysis, providing not only context and long-term trends but also enhancing analytical accuracy.

[0106] Figure 2 A simplified flowchart of the digital twin large model processing real-time data provided by an embodiment of the present application is shown.

[0107] The dynamic kernel receives real-time data (real-time plant and animal information, real-time environmental quality assessment, and real-time ecosystem service function assessment results) accessed through the Internet of Things, and combines historical ecosystem data, model static base information, coupling weights, response functions, and threshold rules to calculate the current state of the ecosystem, evaluate the trend of ecosystem state changes, identify whether the ecosystem state has reached critical conditions, and output results including the current state value of the ecosystem, state change trends, and critical identification situations.

[0108] The rules engine executes business logic judgments and response actions based on the output of the dynamic core. The rules engine receives the ecosystem's current state, state change trends, and critical identification output from the dynamic core. Based on the set response strategy, it determines whether the warning conditions are met, executes the response, and outputs decision recommendations.

[0109] The decision responses provided by the rule engine, as well as the current state value, state change trend, and critical identification situation of the ecosystem output by the dynamic kernel are rendered on the visual interface. The real-time data of the digital twin large model connected through the Internet of Things drives the digital twin engine to refresh the large model in real time, ensuring that the large model remains synchronized with the real ecosystem.

[0110] Among them, the ecosystem operation results provided by the digital twin large model cover multiple dimensions such as the current state of the ecosystem, state change trends, critical state identification, response actions, etc., comprehensively reflecting the operation status and response mechanism of the ecosystem.

[0111] The current state of an ecosystem includes species status, environmental quality, and ecosystem service function status. Species status includes, for example, real-time identification of species names, abundance, diversity indices, and spatial distribution heat maps within each grid cell. Environmental quality status includes, for example, real-time raster values ​​for water quality, soil quality, and weather conditions. Ecosystem service function status includes, for example, grid-based carbon sink flux, water conservation capacity, biodiversity maintenance index, and pollutant purification efficiency. The real-time environmental quality assessment is a comprehensive evaluation based on the raw data. The digital twin model then rasterizes these evaluation results and outputs continuous physical quantities (such as pH, dissolved oxygen, and organic matter) for each grid cell, representing the environmental status. The real-time ecosystem service function assessment results in a comprehensive score or ranking of the raw data. The digital twin model rasterizes these evaluation results and converts them into continuous physical quantities or fluxes for each grid cell, representing the service function.

[0112] The current state of an ecosystem can be visualized in a visualization interface, displaying species distribution maps, environmental quality maps, and service function status maps. Species distribution maps can be presented in various formats, including heat maps (using color depth to represent species density or richness), dot maps (using discrete dots to indicate the location of each individual observation or sampling point), and three-dimensional models (overlaying species data on a three-dimensional terrain or vegetation model to provide an immersive spatial perspective). These three types of maps can be presented individually or in combination to form a comprehensive visualization of species spatial distribution. Environmental quality maps, for example, plot parameters such as water quality (pH, dissolved oxygen), soil (organic matter, heavy metals), and meteorological (temperature, humidity) into spatial distribution maps by grid or region. For example, a pH distribution map or temperature heat map can quickly identify areas with acidic water quality or high temperatures. Service function status maps, for example, plot the spatial distribution of ecosystem output capacity (carbon sequestration, water conservation, biodiversity index, etc.), visually displaying areas with high carbon sequestration values, hot spots for water conservation, and cold and hot spots for biodiversity.

[0113] Trends include the changing trends (e.g., increases, decreases, fluctuations), rates of change, and magnitudes (e.g., daily changes in the water quality index) of various elements (species, environment, and services). Trends can be visualized using trend graphs, dynamic evolution graphs, and rate of change graphs. For example, trend graphs show the temporal changes in species richness, water quality index, and service indicators; dynamic evolution graphs use animations or timeline playback to visually illustrate how ecosystem status changes over time; and rate of change graphs use spatial distribution to display the rate of increase or decrease of various ecological elements per unit time.

[0114] Critical state identification includes identifying whether the ecological threshold has been reached. The warning map can show which areas have triggered the ecological threshold warning, the warning list can list all current warning information (such as low pH, decreased species richness), and the critical area can be highlighted through the critical mark.

[0115] For response actions and decision-making recommendations, the large model can automatically trigger response actions, recommend intervention measures (such as planting water-purifying plants, limiting pollution discharge, and ecological restoration plans), and can use scenario simulation to simulate the ecological restoration effects under different intervention measures.

[0116] The above implementation plan refreshes the big model based on real-time data to ensure that the big model remains synchronized with the real ecosystem; the operating results output by the digital twin big model cover multiple dimensions such as the current state of the ecosystem, state change trends, critical warnings, and response actions, comprehensively reflecting the operating status and response mechanism of the ecosystem; the visual interface displays all information in the operating results of the digital twin big model that requires users to intuitively understand, interact or make decision-making references, providing users with a good experience.

[0117] In an optional embodiment of the present application, the method further comprises: In response to receiving an interactive operation on the VR interface or the AR interface, updating the model state of the digital twin model, and obtaining an updated ecosystem operation result output by the digital twin model; Based on the updated ecosystem operation results, the visual content on the VR interface or AR interface is updated in real time.

[0118] Visualizing the operational results of the digital twin model through VR or AR technology allows users to intuitively understand the current state of the ecosystem, state change trends, critical situations, and response decisions. The visualization interface supports interactive operations. Based on user interactions on the visualization interface, the model state of the digital twin model can be updated. The digital twin model then outputs the latest ecosystem operational results, which in turn updates the visualization interface.

[0119] The visual interface can support user interaction in the following ways, for example: Parameter Adjustment: Allows users to adjust parameters such as environmental factors and species abundance, with the large model generating responses. Scenario Simulation: Provides different scenario options. Users can activate simulations and view simulated ecosystem changes under different scenarios. Layer Control: Users can choose to display or hide different data layers, such as species distribution and water quality. Warning Information Viewing: Displays warning details, allowing users to click to view specific risk areas and recommended measures. Timeline Operation: Users can drag the timeline to view historical changes and trends in ecosystem status.

[0120] The interactive methods supported above enable users to actively participate in model operations, explore different scenarios, and verify results, thereby better understanding the state of the ecosystem and assisting decision-making.

[0121] The visualization interface can be a VR or AR interface. The VR interface supports immersive operation. For example, users can wear a VR headset and enter a three-dimensional virtual ecosystem. They can interact with the virtual environment through controllers, gestures, eye tracking, and other methods to view the ecological status of different areas, observe species distribution, water quality changes, and so on. In parameter adjustment and scenario simulation scenarios, environmental parameters (such as precipitation and temperature) can be adjusted on the virtual interface, and different scenario simulations (such as pollution incidents and ecological restoration) can be initiated and the responses can be viewed in real time. In information query and feedback scenarios, clicking on a species or area can view detailed information (such as species name, abundance, and health status).

[0122] The AR interface supports augmented reality overlays. Using AR glasses or a camera, virtual ecological information can be superimposed on the real-world scene. This means that when users wear AR glasses or use their phone's camera, they can see real-time monitoring data superimposed on the real-world scene, such as water quality indicators displayed above a real river or species distribution maps overlaid on a forest. Users can view real-time monitoring data (such as water and air quality) in the real environment and click to view details, historical trends, and early warning information. In scenario-based simulations, the effects of different intervention measures (such as vegetation restoration and pollution control) can be simulated, and the differences between the current and simulated ecological states can be compared. Users can control these data using voice commands or gesture input.

[0123] In the embodiment of the present application, the operation of the large model relies on a real-time update mechanism (driven by IoT data) and a visual display (VR / AR interactive interface) to achieve real-time mapping and dynamic interaction of the ecosystem; the VR / AR interface supports users to interact with the digital twin large model intuitively and in real time through immersive interaction, parameter adjustment, scenario simulation, information query, etc., thereby improving the understanding, analysis and decision-making efficiency of the ecosystem.

[0124] Figure 3The overall implementation flow chart of the digital twin construction in the embodiment of the present application is shown.

[0125] Step 301: Generate biological feature vectors based on biological data collected in the ecological protection zone, generate environmental feature vectors based on environmental data collected in the ecological protection zone, perform species identification on the biological feature vectors based on the biological macro model to obtain information on plants and animals in the ecological protection zone, perform environmental analysis on the environmental feature vectors based on the environmental macro model, and obtain an environmental quality assessment of the ecological protection zone.

[0126] Step 302: Determine a comprehensive feature vector by combining the biological feature vector and the environmental feature vector with the dynamically adjusted biological weight and environmental weight.

[0127] Step 303: Based on the optimized evaluation model, a comprehensive reasoning analysis is performed on the biological feature vector, environmental feature vector, comprehensive feature vector, plant and animal information, and environmental quality evaluation to generate an ecosystem service function evaluation result.

[0128] Step 304: preprocess the multi-source data in each spatiotemporal unit, align the data in time and space, and determine the standard data. The multi-source data in a single spatiotemporal unit includes the animal and plant information, environmental quality assessment status, and ecosystem service function assessment results corresponding to the current spatiotemporal unit.

[0129] Step 305: Extract multimodal features from the standard data, generate feature vectors of each modality based on the extracted features, obtain weighted feature vectors of each modality with dynamically adjusted weights in the same time and space dimensions; concatenate the weighted feature vectors of each modality to generate a fused feature vector of the current spatiotemporal unit, arrange the fused feature vectors of multiple spatiotemporal units in time series and spatial grid order to form a comprehensive feature matrix. The multimodal features include at least biological features, environmental features, and service function features.

[0130] Step 306: Perform deep learning on the comprehensive feature matrix and output a weight matrix, a response function, and a threshold rule. Based on the weight matrix, the response function, and the threshold rule, a dynamic kernel is generated to calculate the state of the ecosystem, evaluate the trend of state changes, and identify critical states.

[0131] Step 307: Encapsulate the dynamic kernel and rule engine to build a digital twin engine.

[0132] Step 308: Load the model static base information used to construct the three-dimensional spatial skeleton and basic attributes into the digital twin engine, spatially align and logically bind the digital twin engine and the model static base information, configure various model parameters in the digital twin engine, and initialize the digital twin large model.

[0133] Step 309: In response to the real-time data input into the digital twin macro model, the model state of the digital twin macro model is updated, the real-time data and ecosystem historical data are processed based on the updated digital twin macro model, and the ecosystem operation results are output and displayed through a visual interface.

[0134] Step 310: In response to receiving an interactive operation on the visualization interface, obtain the latest ecosystem operation result and update the visualization content on the visualization interface.

[0135] The above implementation process of this application realizes the real-time twinning of the ecosystem status based on digital twin technology; the operation results output by the digital twin large model cover multiple dimensions, comprehensively reflecting the operation status and response mechanism of the ecosystem; the use of a visual interface for content display and support for real-time interaction provides users with a good experience.

[0136] In order to further introduce the solution provided by the embodiment of the present application, a specific example is provided below.

[0137] Collect biological and environmental data from ecological reserves. To collect biological data, the following procedures are performed: Multiple infrared cameras are deployed in hotspots of Siberian tiger activity. Images are captured at regular intervals (e.g., 15 minutes) and transmitted to edge computing nodes via wireless networks. GPS collars (with an accuracy of ±3 meters) are fitted to, for example, 10 Siberian tigers, with location data uploaded to Beidou satellites every 30 minutes. Acoustic sensors are deployed at, for example, 20 locations to record tiger roars. To collect environmental data, weather stations are installed to monitor snow depth, temperature, and humidity. Drone scans are performed monthly to generate a 3D point cloud of the forest.

[0138] After data collection, data preprocessing is performed, including temporal and spatial alignment. For temporal alignment, GPS collar data and meteorological data are converted to a unified format; time offsets between audio and image data are corrected using a dynamic time warping algorithm. For spatial alignment, point cloud data and GPS coordinates are projected and converted to UTM.

[0139] After data preprocessing, feature vectors are generated. When generating biological feature vectors, for example, 2048-dimensional feature vectors are extracted for image data, and for example, 128-dimensional embedding vectors are output for audio data. GPS location information is already implicitly included in the spatial alignment step and need not be re-encoded in the feature stage. When generating environmental feature vectors, values ​​such as snow depth and temperature are normalized and concatenated into a 6-dimensional vector. An attention mechanism is used to perform a weighted fusion of the biological and environmental feature vectors to generate a composite feature vector (dimensionality: 2048 + 128 + 6 = 2182). This process dynamically adjusts biological and environmental weights based on their real-time contributions to more accurately reflect the current state of the ecosystem.

[0140] After obtaining the biological, environmental, and comprehensive feature vectors, the biological feature vectors are processed using the large biological model to identify species. The environmental feature vectors are processed using the large environmental model to predict a seven-day snow depth sequence (e.g., [28, 26, 25, 24, 23, 22, 21] cm). Furthermore, the ecosystem service function is assessed using the large assessment model, which processes the biological, environmental, and comprehensive feature vectors, along with the identification results of the large biological model and the output of the large environmental model.

[0141] A comprehensive feature matrix is ​​constructed based on the identification results of the biological model, the output of the environmental model, and the ecosystem service function assessment results. For example, the matrix has an N × 2182 shape, where N is the time step (e.g., daily data for the past 30 days). Each row contains 2182 features (biological, environmental, and service function assessment features). Deep learning of the comprehensive feature matrix is ​​used to develop a dynamic kernel. This development process involves the following steps: weight matrix learning, response function fitting, and threshold rule generation.

[0142] During the weight matrix learning stage, a suitable model architecture is selected, position encoding is added to the comprehensive feature matrix, temporal information is retained, and a 2182×2182 weight matrix is ​​output through self-attention calculation to characterize the coupling strength between species, environment, and service functions. The non-zero elements in the weight matrix represent key relationships (e.g., the weight of Siberian tiger activity and snow accumulation is -0.6).

[0143] During the response function fitting stage, the key coupling relationships in the weight matrix (such as the weight of -0.6 between the activity of the Siberian tiger and snow cover) and historical time series data (the activity range of the Siberian tiger, snow thickness, and deer density) were used as input data to characterize the impact of changes in snow cover and deer populations on the activity range of the Siberian tiger, and to obtain the response function while taking into account both fitting accuracy and readability.

[0144] During the threshold rule generation stage, the normal range is set according to statistical laws using the historical change rate of Siberian tiger activity, snow thickness, and deer frequency; if the change rate is far below the average for five consecutive days and the snow is very thin, the habitat is marked as degraded, and the threshold is refreshed every month based on the latest data to adapt to seasonal fluctuations.

[0145] After developing the dynamic kernel, a digital twin engine was constructed based on the dynamic kernel and the rules engine. The rules engine then made decisions based on the dynamic kernel's output. For example, if 28 cm of snow fell for four consecutive days, reducing the Siberian tiger's range by 18%, the dynamic kernel determined that the -15% warning level had been exceeded, and the rules engine immediately triggered a "habitat crisis" alert.

[0146] When building a digital twin large model based on the digital twin engine and the static base information of the model, real-time data is connected to the digital twin engine based on the data interface, and the model status of the digital twin large model is updated. The digital twin large model processes the real-time data and the historical data of the ecosystem, and provides the ecosystem operation results for display on a visual interface (such as an AR interface).

[0147] The AR interface displays content such as individual Siberian tigers, snow cover heat maps, deer density particle clouds, key indicator cards, and event warning zones. Each Siberian tiger is represented by a 3D model that resembles its actual size. The 3D model is anchored to real-time GPS coordinates and moves in sync with the animal's movements. A trail line can be dragged behind the animal to display its movement path over the past few hours or days. A floating number can be displayed above the 3D model, indicating gender, age, and other identification information. In the snow cover heat map, thinner snow is bluer, while thicker snow is whiter. With each change in thickness, the color is immediately recalculated and updated, resulting in real-time changes in the perceived snow surface color. The deer density particle cloud appears as a "cloud" composed of countless small light points above the forest. Brighter and denser the light points, the more deer there are; sparser or dimmer the light points, the fewer deer there are. Users can control the appearance or disappearance of the particle cloud through voice commands or gestures. Key indicator cards display information such as habitat scores and warning thresholds, allowing managers to quickly understand relevant information. For event warning areas, when rules such as "habitat crisis" are determined to be triggered, the affected area will be immediately covered by a red translucent grid, and a prompt box will pop up to inform the ranger to patrol first and provide route guidance.

[0148] The present application also provides a digital twin construction system for a terrestrial ecosystem, such as Figure 4 Shown, including: Acquisition module 401 is used to acquire information on plants and animals within the ecological protection zone and an assessment of environmental quality based on biological data and environmental data collected within the ecological protection zone, wherein the biological data is used to generate biological feature vectors for plant and animal identification, and the environmental data is used to generate environmental feature vectors for environmental quality assessment; a processing and acquisition module 402 for processing the plant and animal information, the environmental quality assessment, the biological feature vector, the environmental feature vector, and the comprehensive feature vector based on the large assessment model to obtain an ecosystem service function assessment result of the ecological protection zone, wherein the comprehensive feature vector is determined based on a fusion of the biological feature vector, the environmental feature vector, and the dynamically adjusted biological weight and environmental weight; A generation and construction module 403 is used to generate a comprehensive feature matrix based on the plant and animal information, the environmental quality assessment, and the ecosystem service function assessment results, and to perform deep learning on the comprehensive feature matrix to construct a digital twin engine; wherein the comprehensive feature matrix is ​​composed of fused feature vectors of multiple spatiotemporal units arranged in a spatiotemporal sequence, and the fused feature vector of a single spatiotemporal unit is formed by multimodal feature splicing of the plant and animal information, environmental quality assessment, and ecosystem service function assessment results corresponding to the current spatiotemporal unit; The rendering module 404 is used to render the linkage status of species, environment and ecosystem service functions on a visual interface in response to real-time data input into the digital twin large model after constructing the digital twin large model based on the digital twin engine and the static base information of the model. The visual interface is a virtual reality VR interface or an augmented reality AR interface.

[0149] Optionally, the acquisition module includes: a generating submodule, configured to generate the biometric feature vector based on the collected biometric data and generate the environmental feature vector based on the collected environmental data, wherein the biometric data includes at least image data, audio data, and positioning data of plants and animals, and the environmental data includes at least meteorological data and physical environment data; The acquisition submodule is used to perform species identification on the biological feature vector based on the biological macro model to obtain information on animals and plants in the ecological protection zone, and to perform environmental analysis on the environmental feature vector based on the environmental macro model to obtain an environmental quality assessment in the ecological protection zone.

[0150] Optionally, the processing and acquisition module includes: a splicing determination submodule, configured to perform vector splicing based on the biological feature vector and the environmental feature vector in combination with the dynamically adjusted biological weight and environmental weight to determine the comprehensive feature vector; The analysis and generation submodule is used to perform comprehensive reasoning and analysis on the biological feature vector, the environmental feature vector, the comprehensive feature vector, the animal and plant information and the environmental quality assessment based on the optimized evaluation model to generate an ecosystem service function evaluation result.

[0151] Optionally, the generating construction module includes: A processing and determination submodule is used to perform data preprocessing and time and space alignment of the multi-source data in each spatiotemporal unit, and determine standard data. The multi-source data in a single spatiotemporal unit includes the comprehensive feature vector and the plant and animal information, environmental quality assessment, and ecosystem service function assessment results corresponding to the current spatiotemporal unit; An extraction and generation submodule, configured to extract multimodal features from the standard data and generate feature vectors of each modality based on the extracted features, wherein the multimodal features include at least biological features, environmental features, and service function features; The splicing acquisition submodule is used to obtain the weighted feature vectors of each modality with the weights of each modality dynamically adjusted in the same time and space dimensions, and to splice the weighted feature vectors of each modality to generate a fused feature vector of the current spatiotemporal unit; The construction submodule is used to arrange the fused feature vectors of multiple spatiotemporal units in a time series and a spatial grid order to form the comprehensive feature matrix.

[0152] Optionally, the generating construction module includes: a learning output submodule for performing deep learning on the comprehensive feature matrix and outputting a weight matrix, a response function, and a threshold rule, wherein the weight matrix includes multiple coupling weights and is used to quantify the interaction between species and the environment and service functions; the response function is used to describe the response relationship between ecosystem variables; and the threshold rule is used to define the critical state of the ecosystem; A generation submodule for generating a dynamic kernel for calculating the state of the ecosystem, evaluating the trend of state changes, and identifying critical states based on the weight matrix, the response function, and the threshold rule; The encapsulation construction submodule is used to encapsulate the dynamic kernel and the rule engine, and build the digital twin engine. The rule engine makes a decision response based on the output result of the dynamic kernel.

[0153] Optionally, the learning output submodule includes: A learning unit is used to input the comprehensive feature matrix into the deep learning model, learn the coupling relationship between species variables, environmental variables and service function variables, and output a weight matrix including the coupling weights between species and environment, the coupling weights between species and service functions, the coupling weights between environment and service functions, and the coupling weights of multi-factor collaboration; A fitting determination unit, configured to embed a nonlinear activation layer in the deep learning model, fit the functional relationship between species variables, environmental variables, and service function variables, and determine a response function; A learning generation unit is used to learn key ecological thresholds and generate threshold rules based on loss function constraints during the training process of the deep learning model.

[0154] Optionally, the system further comprises: A loading module for loading static base information of a model used to construct a three-dimensional spatial skeleton and basic attributes into the digital twin engine when the digital twin engine is constructed based on deep learning; A processing module is used to spatially align and logically bind the digital twin engine with the static base information of the model, configure various model parameters in the digital twin engine, and initialize the digital twin large model.

[0155] Optionally, the rendering module includes: An update submodule, configured to connect the acquired real-time data to the digital twin engine based on a data interface, and drive the digital twin engine to update the model state of the digital twin large model, wherein the real-time data includes real-time plant and animal information, real-time environmental quality assessment, and real-time ecosystem service function assessment results; a processing and output submodule, configured to process the real-time data and the historical ecosystem data based on the updated digital twin macromodel, and output an ecosystem operation result, wherein the ecosystem operation result indicates the linkage status of species, environment, and ecosystem service functions, and the ecosystem operation result includes at least one of the current state of the ecosystem, the trend of change in the ecosystem state, the critical state of the ecosystem, and the decision response; The display submodule is used to visualize the ecosystem operation results provided by the digital twin model through a VR interface or an AR interface.

[0156] Optionally, the system further comprises: An update acquisition module, configured to update the model state of the digital twin macro model in response to receiving an interactive operation on the VR interface or the AR interface, and obtain an updated ecosystem operation result output by the digital twin macro model; An updating module is used to update the visual content on the VR interface or the AR interface in real time based on the updated ecosystem operation results.

[0157] As for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0158] It should be noted that the above detailed description is exemplary and is intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which this application belongs.

[0159] It should be noted that the terms used herein are intended only to describe specific embodiments and are not intended to limit the exemplary embodiments described herein. As used herein, unless the context clearly indicates otherwise, the singular form is intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0160] In the above detailed description, reference is made to the accompanying drawings, which form a part hereof. In the drawings, similar symbols typically identify similar components, unless the context dictates otherwise. The illustrated embodiments described in the detailed description, drawings, and claims are not meant to be limiting. Other embodiments may be used, and other changes may be made, without departing from the spirit or scope of the subject matter presented herein.

[0161] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A method for constructing a digital twin of a terrestrial ecosystem, characterized in that: include: Obtaining information on flora and fauna within the ecological reserve and an assessment of environmental quality based on biological data and environmental data collected in the ecological reserve, wherein the biological data is used to generate biological feature vectors for flora and fauna identification, and the environmental data is used to generate environmental feature vectors for environmental quality assessment; Processing the plant and animal information, the environmental quality assessment, the biological feature vector, the environmental feature vector, and the comprehensive feature vector based on the large assessment model to obtain an ecosystem service function assessment result of the ecological protection zone, wherein the comprehensive feature vector is determined based on a fusion of the biological feature vector, the environmental feature vector, and dynamically adjusted biological weights and environmental weights; Generate a comprehensive feature matrix based on the plant and animal information, the environmental quality assessment, and the ecosystem service function assessment results, and perform deep learning on the comprehensive feature matrix to construct a digital twin engine; wherein the comprehensive feature matrix is ​​composed of fused feature vectors of multiple spatiotemporal units arranged in a spatiotemporal sequence, and the fused feature vector of a single spatiotemporal unit is formed by multimodal feature splicing of the plant and animal information, environmental quality assessment, and ecosystem service function assessment results corresponding to the current spatiotemporal unit; After constructing a digital twin large model based on the digital twin engine and the model's static base information, in response to real-time data input into the digital twin large model, the linkage status of species, environment, and ecosystem service functions is rendered on a visualization interface, and the visualization interface is a virtual reality VR interface or an augmented reality AR interface.

2. The method according to claim 1, characterized in that The biological and environmental data collected in the ecological protection zone are used to obtain information on flora and fauna and environmental quality assessments within the ecological protection zone, including: generating the biometric feature vector based on the collected biometric data and generating the environmental feature vector based on the collected environmental data, wherein the biometric data includes at least image data, audio data, and positioning data of plants and animals, and the environmental data includes at least meteorological data and physical environment data; The biological feature vectors are subjected to species identification based on the biological macro model to obtain information on plants and animals in the ecological protection zone; and the environmental feature vectors are subjected to environmental analysis based on the environmental macro model to obtain an environmental quality assessment in the ecological protection zone.

3. The method according to claim 1 or 2, characterized in that The process of processing the plant and animal information, the environmental quality assessment, the biological feature vector, the environmental feature vector, and the comprehensive feature vector based on the large assessment model to obtain the ecosystem service function assessment result of the ecological protection zone includes: Determine the comprehensive feature vector by performing vector splicing based on the biological feature vector, the environmental feature vector, and the dynamically adjusted biological weight and environmental weight; Based on the optimized evaluation model, a comprehensive reasoning analysis is performed on the biological feature vector, the environmental feature vector, the comprehensive feature vector, the animal and plant information and the environmental quality evaluation situation to generate an ecosystem service function evaluation result.

4. The method according to claim 1, wherein The generating of a comprehensive feature matrix based on the animal and plant information, the environmental quality assessment, and the ecosystem service function assessment results includes: Data preprocessing and spatial and temporal alignment of multi-source data within each spatiotemporal unit are performed to determine standard data. Multi-source data within a single spatiotemporal unit includes the corresponding animal and plant information, environmental quality assessment, and ecosystem service function assessment results of the current spatiotemporal unit. Extracting multimodal features from the standard data and generating feature vectors of each modality based on the extracted features, wherein the multimodal features include at least biological features, environmental features, and service function features; obtaining weighted feature vectors of each modality with dynamically adjusted weights of each modality in the same time and space dimensions; The weighted feature vectors of each modality are concatenated to generate the fused feature vector of the current spatiotemporal unit; The fused feature vectors of multiple spatiotemporal units are arranged in time series and spatial grid order to form the comprehensive feature matrix.

5. The method according to claim 1, wherein The deep learning of the comprehensive feature matrix to construct a digital twin engine includes: Deep learning is performed on the comprehensive feature matrix to output a weight matrix, a response function, and a threshold rule. The weight matrix includes multiple coupling weights and is used to quantify the interaction between species and the environment and service functions. The response function is used to describe the response relationship between ecosystem variables. The threshold rule is used to define the critical state of the ecosystem. Based on the weight matrix, the response function and the threshold rule, a dynamic kernel is generated for calculating the state of the ecosystem, evaluating the trend of changes in the state of the ecosystem and identifying the critical state; The dynamic kernel and rule engine are encapsulated to build the digital twin engine, and the rule engine makes a decision response based on the output result of the dynamic kernel.

6. The method according to claim 5, characterized in that The deep learning of the comprehensive feature matrix and the output of the weight matrix, the response function and the threshold rule include: Inputting the comprehensive feature matrix into the deep learning model, learning the coupling relationship between species variables, environmental variables and service function variables, and outputting a weight matrix including the coupling weights between species and environment, the coupling weights between species and service functions, the coupling weights between environment and service functions, and the coupling weights of multi-factor synergy; Embedding a nonlinear activation layer in the deep learning model to fit the functional relationship between species variables, environmental variables and service function variables to determine the response function; During the training process of the deep learning model, key ecological thresholds are learned based on loss function constraints and threshold rules are generated.

7. The method according to claim 5 or 6, characterized in that Also includes: In the case of building the digital twin engine based on deep learning, loading the model static base information used to build the three-dimensional space skeleton and basic attributes into the digital twin engine; The digital twin engine is spatially aligned and logically bound to the static base information of the model, and various model parameters in the digital twin engine are configured to initialize the digital twin large model.

8. The method according to claim 7, characterized in that The step of rendering the linkage status of species, environment, and ecosystem service functions on a visual interface in response to real-time data input into the digital twin macro model includes: Connecting the acquired real-time data to the digital twin engine based on a data interface to drive the digital twin engine to update the model state of the digital twin large model, wherein the real-time data includes real-time plant and animal information, real-time environmental quality assessment, and real-time ecosystem service function assessment results; Processing the real-time data and ecosystem historical data based on the updated digital twin model to output ecosystem operation results, where the ecosystem operation results indicate the linkage status of species, environment, and ecosystem service functions, and the ecosystem operation results include at least one of the current state of the ecosystem, the trend of ecosystem state changes, the critical state of the ecosystem, and the decision response; The ecosystem operation results provided by the digital twin large model are visualized through a VR interface or an AR interface.

9. The method according to claim 8, characterized in that The method further comprises: In response to receiving an interactive operation on the VR interface or the AR interface, updating a model state of the digital twin macro model, and obtaining an updated ecosystem operation result output by the digital twin macro model; Based on the updated ecosystem operation results, the visual content on the VR interface or the AR interface is updated in real time.

10. A digital twin construction system for a terrestrial ecosystem, characterized in that: include: an acquisition module for acquiring information on flora and fauna within the ecological reserve and an assessment of environmental quality based on biological data and environmental data collected within the ecological reserve, wherein the biological data is used to generate biological feature vectors for flora and fauna identification, and the environmental data is used to generate environmental feature vectors for environmental quality assessment; a processing and acquisition module, configured to process the plant and animal information, the environmental quality assessment, the biological feature vector, the environmental feature vector, and the comprehensive feature vector based on the assessment model to obtain an assessment result of the ecosystem service function of the ecological protection zone, wherein the comprehensive feature vector is determined based on a fusion of the biological feature vector, the environmental feature vector, and dynamically adjusted biological weights and environmental weights; A generation and construction module is used to generate a comprehensive feature matrix based on the plant and animal information, the environmental quality assessment, and the ecosystem service function assessment results, and to perform deep learning on the comprehensive feature matrix to construct a digital twin engine; wherein the comprehensive feature matrix is ​​composed of fused feature vectors of multiple spatiotemporal units arranged in a spatiotemporal sequence, and the fused feature vector of a single spatiotemporal unit is formed by multimodal feature splicing of the plant and animal information, environmental quality assessment, and ecosystem service function assessment results corresponding to the current spatiotemporal unit; A rendering module is used to render the linkage status of species, environment and ecosystem service functions on a visual interface in response to real-time data input into the digital twin large model after constructing the digital twin large model based on the digital twin engine and the model static base information. The visual interface is a virtual reality (VR) interface or an augmented reality (AR) interface.

Images