Port ecological construction assessment method and system

Abstract

The invention relates to the technical field of port ecological construction, and particularly discloses a port ecological construction evaluation method and system, and the method comprises the following steps: collecting dynamic ecological environment data in port construction operation through a multi-source sensor array; performing space-time coupling analysis on the data, calculating a dynamic attenuation rate # imgabs0 # of each dimension environment index by adopting a self-adaptive sliding time window algorithm, adjusting an ecological response time constant theta in combination with hydrodynamic conditions of a sea area around a port, performing synchronous integral calculation on a historical cumulative effect # imgabs1 #, and generating an environment health degree evolution curved surface; constructing a comprehensive evaluation model; and predicting an environmental risk value based on the hybrid prediction model. According to the invention, an intelligent, automatic, safe, reliable, green and low-carbon evaluation solution is provided for ecological construction of the port, and the ecological protection and sustainable development level of the port is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of port ecological construction, and specifically provides an evaluation method and system for port ecological construction. Background Art

[0002] With the rapid development of the global port economy, port ecological construction has become a key link in achieving sustainable development. In the process of traditional port construction and operation, problems such as fragmented ecological environment monitoring data, insufficient adaptability of dynamic assessment models, weak multi-objective decision-making support capabilities, and lack of data security evidence preservation mechanisms are faced. The specific manifestations are as follows: 1. At the level of data collection and processing: Existing systems rely on single sensors or local monitoring networks, making it difficult to comprehensively obtain multi-dimensional dynamic ecological environment data such as water quality, air, soil, and biodiversity. Moreover, there is a lack of efficient multi-modal data fusion and reliable evidence preservation technologies, resulting in limited data integrity and reliability. 2. At the level of assessment models: Traditional assessment methods mostly use static weight allocation and fixed time windows, which cannot respond in real time to the spatio-temporal heterogeneity of the port environment (such as tidal changes and hydrodynamic condition differences), have insufficient quantification accuracy for ecological cumulative effects and dynamic attenuation processes, and are difficult to accurately generate the evolution trend of environmental health. 3. At the level of decision-making support: There is a lack of intelligent optimization algorithms that integrate multiple objectives such as carbon footprint and ecological connectivity, and the prediction model does not fully combine port operation characteristics (such as ship scheduling and resource utilization efficiency), resulting in poor pertinence and economy of the assessment report and construction plan. In addition, traditional systems do not introduce technologies such as digital twins and augmented reality, making it difficult for decision-makers to intuitively perceive ecological impacts and lacking an interactive decision-making experience. 4. At the level of data security: Sensor data is vulnerable to tampering or attacks during transmission and storage. Traditional encryption technologies cannot meet the collaborative verification needs of multiple port participants (management departments, ecological environment protection agencies, enterprises), and there is a lack of a balance mechanism for data sharing and privacy protection. In summary, the existing port ecological construction assessment technologies have significant shortcomings in aspects such as reliable data collection, dynamic modeling, multi-objective optimization, and intelligent decision-making, and a systematic solution that integrates advanced information technologies and ecological assessment theories is needed. Summary of the Invention

[0003] Aiming at the deficiencies of the existing technology, the present invention provides an evaluation method and system for port ecological construction, which solves the problems in the above background art.

[0004] To achieve the above objectives, the present invention is realized through the following technical solutions: An evaluation method for port ecological construction includes the following steps: S1. Multi-source data collection and reliable evidence preservation: Collect dynamic ecological environment data during port construction and operation through a multi-source sensor array. The data includes water quality parameter groups, air pollutant concentrations, soil heavy metal contents, noise spectra, biodiversity indices, and resource utilization efficiency indicators; construct a multi-modal feature fusion matrix and perform trustworthy digital preservation on the original data; S2. Spatiotemporal dynamic analysis and environmental health assessment: Perform spatiotemporal coupling analysis on the data, and use an adaptive sliding time window algorithm to calculate the dynamic decay rate of environmental indicators in each dimension , adjust the ecological response time constant θ in combination with the hydrodynamic conditions of the sea area around the port, and synchronously integrate to calculate the historical cumulative effect , generate an environmental health evolution surface; S3. Construction of a comprehensive evaluation model: Construct a comprehensive evaluation model, quantify the habitat fragmentation index and the ecological connectivity index ECON, use a dynamic weight allocation algorithm to fuse subjective and objective evaluation factors, introduce an adaptive learning mechanism to optimize the weight convergence process, and output the ecological comprehensive index ECI; S4. Environmental risk prediction and decision support: Predict the environmental risk value based on a hybrid prediction model, generate a Pareto front solution set through a multi-objective optimization algorithm, generate a hierarchical evaluation report and a construction plan set in combination with the port ecological construction goal, and feedback the prediction result to the digital twin engine for dynamic calibration.

[0005] Preferably, the trustworthy digital preservation of the original data in S1 includes: Use blockchain technology to perform hash encryption on sensor data and timestamp it on the chain to construct an immutable data source proof chain; The blockchain digital preservation system adopts a consortium chain architecture. The nodes include port management departments, ecological environment protection agencies, and monitoring equipment manufacturers, and verify the data integrity through a consensus mechanism; Introduce a quantum random number generator to generate data encryption keys, and use quantum key distribution technology to ensure the security of key transmission and prevent data from being illegally cracked.

[0006] Preferably, the dynamic decay rate in S2 is calculated by the following formula: ; Among them, is the dynamic time window period (4h ≤ τ(t) ≤ 24h), is the adaptive decay coefficient, is the monitoring value at the th moment, is the safety lower limit threshold of the dynamically corrected environmental indicator, is the safety upper limit threshold of the dynamically corrected environmental indicators, and the threshold is automatically calibrated through the deviation between Monte Carlo simulation and real-time data. is the exponential decay factor. represents the current time and the historical time the time interval between them; Combine the environmental variables of sea surface temperature and salinity obtained from satellite remote sensing data to construct a multivariate regression model and dynamically adjust the adaptive decay coefficient to improve the accuracy of calculating the decay rate of environmental indicators; Introduce a reinforcement learning algorithm to optimize the adjustment strategy of the dynamic time window period according to the historical evolution trend of environmental indicators and real-time monitoring data of.

[0007] Preferably, the dynamic weight allocation algorithm in S3 embeds an attention mechanism, and the key index weights are calculated as follows: ; Among them, is the attention weight of the key index, and are feature extraction functions, and the weight matrix is dynamically optimized by minimizing the evaluation error; At the same time, introduce knowledge graph technology to construct a knowledge graph in the port ecological field to assist in adjusting weight allocation; and optimize the feature extraction functions and in combination with the federated learning framework to improve the generalization ability of the model.

[0008] Preferably, the hybrid prediction model in S4 is an improved STL-LSTM model, including the following features: Use the Hampel filter to eliminate outliers in the time series data, and extract the periodic features of the environmental data through seasonal decomposition; Construct a spatio-temporal attention LSTM network, and weight the port operation intensity index and tidal cycle parameters when updating the hidden layer state; Introduce a carbon footprint correction term, and the formula is: where is the carbon balance index; Integrate the generative adversarial network, generate potential change scenarios of environmental risks through the generator, and the discriminator compares the prediction results with the generated scenarios to optimize the prediction accuracy of the STL-LSTM model; Use edge computing nodes to preprocess and make preliminary predictions on the real-time data at the port site, and transmit the key feature data to the cloud for in-depth analysis to reduce data transmission latency and cloud computing pressure.

[0009] A port ecological construction evaluation system includes: an intelligent perception layer, a digital twin engine, a decision optimization layer, and an augmented reality terminal; the intelligent perception layer deploys a multi-spectral water quality sensor array, a MEMS gas sensor network, and an underwater acoustic Doppler profiler to form a heterogeneous data acquisition matrix, and integrates a blockchain evidence storage module to realize the trustworthy uploading of data to the chain; the digital twin engine integrates a spatio-temporal coupling analysis model and a hybrid prediction model, supports the simulation of the port environment freedom, and includes a dynamic grid optimization unit and an ecological stress analysis unit; the decision optimization layer runs a dynamic weight allocation algorithm and a multi-objective optimization algorithm to generate a three-dimensional decision cloud map of the Pareto solution set, and embeds a carbon footprint tracking module to quantify the carbon emissions and carbon sinks in the whole life cycle of the port; the augmented reality terminal presents the pollutant migration path through light field display technology, and realizes the interactive adjustment of the solution in combination with a tactile feedback and a neural feedback device.

[0010] Preferably, the blockchain evidence storage module includes: a data preprocessing unit and a smart contract unit; the data preprocessing unit denoises, normalizes, and checks the quality of the sensor data; the smart contract unit automatically verifies the data integrity, triggers an on-chain warning when the deviation between the monitored value and the historical average exceeds 20%, and marks the data abnormal status bit; at the same time, the zero-knowledge proof technology is introduced to verify the authenticity and integrity of the data to a third party without disclosing the content of the original data, and the blockchain data is divided into multiple shards and stored on different nodes by using the sharding storage technology to improve the data storage and retrieval efficiency.

[0011] Preferably, the dynamic grid optimization unit of the digital twin engine uses non-uniform rational B-splines, and the NURBS surface model reconstructs the port terrain. The grid resolution is dynamically adjusted according to the ship draft and tide height, and the minimum resolution reaches 0.5 m × 0.5 m; Combined with the point cloud processing technology, the port point cloud data obtained by drones and underwater robots is used to update the NURBS surface model in real time to improve the accuracy of the digital twin model; The ecological stress analysis unit introduces a physical engine to simulate the influence of the physical environment of port water flow and wind on ships and facilities, and realizes a more realistic simulation of port operation scenarios.

[0012] Preferably, the neural feedback evaluation module of the augmented reality terminal includes: an electroencephalogram signal acquisition device and a cortical activation map analysis unit; the electroencephalogram signal acquisition device obtains the characteristics of the decision maker's alpha wave and beta wave in real time; the cortical activation map analysis unit identifies the cognitive matching degree of the solution through a convolutional neural network and outputs optimization suggestions to the decision optimization layer; at the same time, the emotion computing technology is introduced to analyze the emotion characteristics of the decision maker's facial expressions and speech intonations, and combined with the electroencephalogram signals to evaluate the emotion preferences of the decision maker for different construction plans. Using the virtual scene generated by the digital twin engine and combining with virtual reality technology, the decision maker can immerse himself in experiencing the port ecological environment changes under different construction plans, enhancing the intuitiveness and accuracy of the decision.

[0013] Preferably, the carbon footprint tracking module is used to calculate the port operation carbon balance index, and the specific calculation formula is as follows: ; Where: represents the ecological carbon sink, and this value is calculated based on the wetland area and the vegetation carbon sequestration efficiency; represents the carbon emissions during the operation stage, and this value is estimated based on the energy consumption and the carbon emission factor; represents the embodied carbon emissions during the construction stage, and all three of these are incorporated into the constraint conditions of the multi-objective optimization model; At the same time, the life cycle assessment method is introduced to conduct a carbon footprint analysis on the entire life cycle of the port from construction, operation, maintenance to abandonment, to more comprehensively evaluate the carbon emissions of the port; combined with the carbon trading market data, a carbon cost assessment model is established to link the carbon balance index with the economic cost, providing an economic feasibility analysis for the port ecological construction plan.

[0014] The present invention provides a port ecological construction evaluation method and system, which have the following beneficial effects: I. Improvement in data collection and reliable evidence storage capabilities: 1. By deploying arrays of multi-spectral water quality sensors, MEMS gas sensors, etc., a dynamic data collection matrix covering dimensions such as the environment, resources, and organisms is constructed. Combining multi-modal feature fusion technology, comprehensive perception and real-time monitoring of port ecological elements are realized; 2. Using the consortium blockchain architecture and quantum key distribution technology, hash encryption, timestamp on-chain, and dynamic key management are performed on the sensor data to ensure that the data cannot be tampered with and the transmission is secure, providing a reliable data source for multi-party collaborative verification and solving the problem of the reliability of data evidence storage in traditional systems.

[0015] II. Breakthrough in dynamic assessment and prediction accuracy: 1. Based on the adaptive sliding time window and reinforcement learning algorithm, the time window period and the decay coefficient are dynamically adjusted. Combining the hydrodynamic conditions of the sea area around the port to quantify the ecological response process, accurately calculating the historical cumulative effect of environmental indicators, and generating a high-resolution environmental health evolution surface to improve the spatio-temporal dynamic assessment ability; 2. Embedding the attention mechanism and knowledge graph technology, dynamically fusing subjective and objective evaluation factors, realizing the adaptive optimization of the weights of key indicators such as habitat fragmentation and ecological connectivity; through the improved STL-LSTM hybrid prediction model, introducing a carbon footprint correction term and a generative adversarial network, significantly improving the environmental risk prediction accuracy and providing a scientific quantitative basis for port ecological construction.

[0016] III. Decision Support and Interactive Experience Innovation: 1. Utilize the NURBS surface model and point cloud processing technology to construct a high-precision digital twin engine, dynamically simulate physical environments such as port terrain, water flow, and wind force, and generate a three-dimensional decision cloud map in combination with the Pareto front solution set to support decision-makers in intuitively evaluating the ecological impacts of different scenarios; 2. Through electroencephalogram signal acquisition, emotion computing technology, and virtual reality scenarios, achieve an immersive interaction between decision-makers and the evaluation system, capture cognitive preferences and emotional feedback in real-time, assist in generating personalized construction plans, and improve decision-making efficiency and scientificity.

[0017] IV. Full-cycle Low-carbon Assessment and Economic Analysis: 1. Construct a carbon balance index model that includes carbon emissions and ecological carbon sinks during the construction and operation phases, combine the life cycle assessment method and carbon trading market data, link ecological assessment with economic costs, provide quantitative support for the low-carbon transformation of ports, and contribute to the realization of the dual-carbon goals; 2. Preprocess real-time data through edge nodes and transmit key features to the cloud to reduce data transmission latency and computing pressure, and improve the system response speed and resource utilization efficiency.

[0018] V. Technology Integration and System Scalability: Construct an intelligent evaluation framework that can be dynamically optimized, support the flexible expansion of the port ecological construction index system and model generalization, adapt to the geographical environments and development needs of different ports, and has broad application prospects and technological foresight.

[0019] In summary, through the full-chain technological innovation of data collection, analysis and modeling, intelligent decision-making, and interactive optimization, the present invention provides an intelligent, automated, safe, reliable, green, and low-carbon evaluation solution for port ecological construction, significantly improving the port ecological protection and sustainable development level. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a schematic flow chart of a port ecological construction evaluation method of the present invention; Figure 2 is a schematic block diagram of a port ecological construction evaluation system principle of the present invention; Figure 3 is a schematic block diagram of a digital twin engine principle; Figure 4 is a schematic block diagram of a blockchain evidence storage module principle; Figure 5 is a schematic block diagram of an augmented reality terminal principle. DETAILED DESCRIPTION OF THE INVENTION

[0021] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0022] As Figure 1 shown, the present invention provides a technical solution: an evaluation method for port ecological construction, including the following steps: S1. Multi-source data collection and trustworthy archiving: Collect dynamic ecological environment data during port construction and operation through a multi-source sensor array. The data includes water quality parameter groups, air pollutant concentrations, soil heavy metal contents, noise spectra, biodiversity indices, and resource utilization efficiency indicators; construct a multi-modal feature fusion matrix and perform trustworthy archiving on the original data; S2. Spatiotemporal dynamic analysis and environmental health assessment: Perform spatiotemporal coupling analysis on the data, and use an adaptive sliding time window algorithm to calculate the dynamic decay rate of each dimension of environmental indicators , adjust the ecological response time constant θ in combination with the hydrodynamic conditions of the sea area around the port, synchronously integrate and calculate the historical cumulative effect , and generate an environmental health evolution surface; S3. Construction of a comprehensive evaluation model: Construct a comprehensive evaluation model, quantify the habitat fragmentation index and the ecological connectivity index ECON, use a dynamic weight allocation algorithm to fuse subjective and objective evaluation factors, introduce an adaptive learning mechanism to optimize the weight convergence process, and output the ecological comprehensive index ECI; S4. Environmental risk prediction and decision-making support: Predict the environmental risk value based on a hybrid prediction model, generate a Pareto front solution set through a multi-objective optimization algorithm, generate a hierarchical evaluation report and a construction plan set in combination with the port ecological construction goal, and feedback the prediction result to the digital twin engine for dynamic calibration.

[0023] More specifically, the trustworthy archiving of the original data in S1 includes: Use blockchain technology to perform hash encryption and timestamp on the sensor data, and construct an immutable data source proof chain; the blockchain archiving system adopts a consortium chain architecture, and the nodes include port management departments, ecological and environmental protection agencies, and monitoring equipment manufacturers, and verify the data integrity through a consensus mechanism; introduce a quantum random number generator to generate data encryption keys, and use quantum key distribution technology to ensure the security of key transmission and prevent data from being illegally cracked.

[0024] The sensor generates quantum keys through QRNG and encrypts the original data to ensure that the data has not been tampered with (hash value matching) and the key cannot be leaked (QKD transmission). The encrypted data is transmitted through a hybrid of quantum channel + classical channel. QKD technology ensures key security, and blockchain nodes verify data integrity through a consensus mechanism (hash value and timestamp matching). The data is stored in the alliance chain in the form of encrypted original text + hash chain + timestamp. Any modification requires consensus from more than half of the nodes, and will leave an indelible tampering record (such as adding a block marked as abnormal).

[0025] More specifically, the dynamic decay rate in S2 Calculated by the following formula: ; in, is the dynamic time window period (4h≤τ(t)≤24h), is the adaptive attenuation coefficient, For the Monitor the value at all times, is the lower safety threshold of the environmental indicator after dynamic correction, The threshold is the upper limit of the safety of the environmental index after dynamic correction. The threshold is automatically calibrated with the deviation of real-time data through Monte Carlo simulation. Combined with the environmental variables of sea temperature and salinity obtained from satellite remote sensing data, a multivariate regression model is constructed to dynamically adjust the adaptive attenuation coefficient. , improve the accuracy of environmental indicator attenuation rate calculation; introduce reinforcement learning algorithm to optimize the dynamic time window period according to the historical evolution trend of environmental indicators and real-time monitoring data adjustment strategies; is the exponential decay factor, Indicates the current time And historical moments the time interval between Determines the size of the number attenuation factor, The larger the value, the more historical moments Distance from current time The farther, the The smaller the value of Monitoring value For the current moment The influence of the decay rate of environmental indicators is also weaker, reflecting the time lag effect of environmental impact. For example, at a certain moment, a port discharges a certain amount of pollutants. Over time, these pollutants will diffuse and degrade in the environment. The longer it is from the time of discharge, the smaller its impact on the current environmental health.

[0026] in, is the normalized difference term, which maps the monitoring value at the moment to the interval [0, 1], reflecting the degree to which the index at this moment deviates from the safety lower limit (the larger the value, the farther it deviates from the safety threshold, and the greater the environmental pressure). is the safety lower limit threshold of the environmental index after dynamic correction, is the safety upper limit threshold of the environmental index after dynamic correction, which is automatically calibrated through Monte Carlo simulation and real-time data deviation. is the exponential decay factor, reflecting that the "time lag effect" of environmental impact is such that the monitoring values from more distant times have less impact on the current moment, decaying exponentially with time ( the larger it is, the faster the decay rate). For example, if the noise exceeds the standard at a certain moment, its impact on the current environmental health will gradually weaken over time (such as being diffused by seawater or diluted by air), and the exponential function can better approximate the actual physical diffusion process. is the dynamic time window average. Within a time window of length (dynamically adjustable from 4h to 24h), the averaged attenuated normalized values are calculated to reflect the comprehensive impact of recent environmental indicators; this avoids interference from outliers at a single moment and also adapts to the periodic changes in the port environment (such as tidal cycles and peak ship operation times) through a dynamic window. Through weighted averaging (higher weights for recent data and lower weights for distant data), the dynamic decay process of environmental indicators over time is captured, generating the basic data for the evolution surface of environmental health. Combining with port hydrodynamic conditions (such as tides and water flow velocities) to dynamically adjust the decay parameters solves the problem that traditional fixed window models cannot handle rapid environmental changes. More specifically, the dynamic weight allocation algorithm in S3 embeds an attention mechanism, and the key index weights are calculated as follows:

[0027] ; ; where is the attention weight of the key index, , are feature extraction functions that dynamically optimize the weight matrix by minimizing the evaluation error; at the same time, knowledge graph technology is introduced to construct a knowledge graph in the port ecological field to assist in adjusting weight allocation; and the feature extraction functions are optimized in combination with the federated learning framework , , improving the generalization ability of the model.

[0028] Feature extraction functions: and respectively perform feature extraction on the ecological comprehensive index (ECI) and the biodiversity comprehensive index (BCI). These two functions map the original index data to a new feature space, extracting feature information that has an important impact on weight allocation. For example may extract features related to energy consumption, pollutant emissions, etc. in while

[0029] Attention function: measures the feature importance of the th key indicator. It calculates and through certain calculations (such as dot product, concatenation, etc.) to obtain a score representing the importance of this indicator in the current evaluation.

[0030] Weight normalization: Use the softmax function to normalize the attention scores so that the sum of the weights of all key indicators is 1. In this way, each represents the relative importance of the th key indicator in the comprehensive evaluation.

[0031] The knowledge graph represents various entities (such as pollutants, biological species, port facilities, etc.) in the port ecological field and their relationships (such as pollution relationships, dependency relationships, etc.) in the form of a graph. For example, the knowledge graph can include the causal relationship between oil spills and the death of marine organisms, the association relationship between sewage treatment facilities and water quality improvement, etc. The process of constructing the knowledge graph includes steps such as data collection, entity recognition, relationship extraction, and knowledge fusion. Knowledge can be obtained from various data sources such as port monitoring data, scientific research literature, and industry standards, and then natural language processing and machine learning techniques can be used to extract entities and relationships. Finally, this knowledge is integrated into a unified graph. The knowledge graph can provide prior knowledge and domain constraints for weight assignment. For example, when evaluating the port ecological environment, if the knowledge graph shows that a certain pollutant has a serious impact on biodiversity, then when calculating the weights, the weights of the indicators related to this pollutant can be appropriately increased. In addition, the knowledge graph can also help discover potential relationships between indicators and avoid unreasonable weight assignment.

[0032] The federated learning framework optimizes the feature extraction function. Federated learning is a distributed machine learning technology that allows model training among multiple participants (such as different port management departments, scientific research institutions, etc.) without sharing the original data. In port ecological assessment, different ports may have different monitoring data and evaluation experiences. Through federated learning, these data resources can be fully utilized to improve the generalization ability of the model.

[0033] More specifically, the hybrid prediction model in S4 is an improved STL-LSTM model, with the following characteristics: The Hampel filter is used to eliminate outliers in time series data, and the seasonal decomposition is used to extract the periodic characteristics of environmental data; a spatio-temporal attention LSTM network is constructed, and the port operation intensity index and tidal cycle parameters are weighted when updating the hidden layer state; A carbon footprint correction term is introduced, and the formula is: , where is the carbon balance index; a generative adversarial network is fused. The generator generates potential change scenarios of environmental risks, and the discriminator compares the prediction results with the generated scenarios to optimize the prediction accuracy of the STL-LSTM model; edge computing nodes are used to preprocess and perform preliminary predictions on the real-time data at the port site, and the key feature data is transmitted to the cloud for in-depth analysis, reducing data transmission latency and cloud computing pressure. In the process of dynamically monitoring and evaluating the port ecological environment, data is collected sequentially in time order, forming a time series. As the identifier of time, it can specifically represent a certain specific moment. For example, if data is collected in hours, = 1 represents the 1st hour, = 2 represents the 2nd hour. Through this identifier, the environmental data and related calculation results at different moments can be clearly distinguished and corresponding, facilitating the tracking and analysis of the changing trend of the port ecological environment over time.

[0034] Among them, is the carbon balance index, reflecting the ratio of the port ecological carbon sink to the total-cycle carbon emissions, is the correction coefficient (determined by training with historical data, with an initial value set to 0.1, dynamically adjusting the influence weight of the carbon balance on the prediction result). When > 1 (carbon sink is greater than emissions), the correction term is positive, enhancing the ecological friendliness of the predicted value; otherwise, the predicted value is suppressed, quantifying the negative impact of carbon emissions on environmental risks; the carbon balance index directly associates the port carbon emissions with the ecological protection goal, and the correction term makes the prediction result explicitly reflect the carbon neutrality orientation, providing a quantitative basis for the low-carbon construction plan. Combining data preprocessing, spatio-temporal feature modeling, generative simulation, and distributed computing, a complete technical chain of data cleaning, feature enhancement, risk correction, and efficient deployment is constructed, significantly improving the robustness and practicality of the prediction model; the corrected environmental risk prediction value is more in line with the actual port ecology.

[0035] Such as Figures 2 - 5As shown in the figure, a port ecological construction evaluation system includes: an intelligent perception layer, a digital twin engine, a decision-making optimization layer, and an augmented reality terminal; the intelligent perception layer deploys a multi-spectral water quality sensor array, a MEMS gas sensor network, and an underwater acoustic Doppler profiler to form a heterogeneous data acquisition matrix, and integrates a blockchain evidence storage module to realize the trustworthy uploading of data to the chain; the digital twin engine integrates a spatio-temporal coupling analysis model and a hybrid prediction model to support the simulation of the port environment freedom, including a dynamic grid optimization unit and an ecological stress analysis unit; the decision-making optimization layer runs a dynamic weight allocation algorithm and a multi-objective optimization algorithm to generate a three-dimensional decision cloud map of the Pareto solution set, and embeds a carbon footprint tracking module to quantify the carbon emissions and carbon sinks in the whole port life cycle; the augmented reality terminal presents the pollutant migration path through light field display technology, and combines tactile feedback and neural feedback devices to realize interactive adjustment of the solution.

[0036] Intelligent perception layer: Deploy a multi-spectral water quality sensor array (monitoring pH value, dissolved oxygen, heavy metal ions), a MEMS gas sensor network (monitoring SO 2 , NOx, VOCs), and an underwater acoustic Doppler profiler (monitoring water flow velocity and direction), covering six major dimensions of ecological data such as water quality, air, and hydrodynamics, and constructing a multi-modal data acquisition network; the blockchain evidence storage module adopts a consortium chain architecture (nodes include port management, environmental protection agencies, and equipment manufacturers), and realizes the immutability of data through hash encryption and timestamp uploading to the chain; integrates quantum key distribution technology to ensure data transmission security, combines intelligent contracts to automatically verify data integrity, and solves the problems of traditional data fragmentation and untrustworthy evidence storage.

[0037] More specifically, as Figure 4 shown, the blockchain evidence storage module includes: a data preprocessing unit and an intelligent contract unit; the data preprocessing unit denoises, normalizes, and performs quality verification on sensor data; the intelligent contract unit automatically verifies data integrity, triggers an on-chain warning when the deviation between the monitored value and the historical average exceeds 20%, and marks the data abnormal status bit; at the same time, introduces zero-knowledge proof technology to verify the authenticity and integrity of data to a third party without disclosing the original data content, and uses sharding storage technology to divide blockchain data into multiple shards and store them on different nodes to improve data storage and retrieval efficiency.

[0038] Digital twin engine: The spatio-temporal coupling analysis model calculates the dynamic decay rate of environmental indicators based on the adaptive sliding time window algorithm, combines hydrodynamic conditions to quantify the ecological cumulative effect, and generates an environmental health evolution surface; the hybrid prediction model embeds a carbon footprint correction term and a generative adversarial network to improve the accuracy of environmental risk prediction.

[0039] More specifically, as Figure 3As shown in the figure, the dynamic grid optimization unit of the digital twin engine uses non-uniform rational B-splines (NURBS) to reconstruct the port terrain with an NURBS surface model. The grid resolution is dynamically adjusted according to the ship's draft and tidal height, with a minimum resolution of 0.5 m × 0.5 m. Combining point cloud processing technology, the port point cloud data obtained by drones and underwater robots is used to update the NURBS surface model in real time, improving the accuracy of the digital twin model. The ecological stress analysis unit introduces a physics engine to simulate the impact of the physical environment of port water flow and wind on ships and facilities, realizing a more realistic simulation of port operation scenarios.

[0040] Decision optimization layer: The core is the dynamic weight allocation algorithm, which embeds the attention mechanism and knowledge graph, dynamically fuses subjective and objective factors such as habitat fragmentation and ecological connectivity, and outputs the ecological comprehensive index (ECI). Through the multi-objective optimization algorithm, a Pareto front solution set is generated to balance ecological protection, economic cost, and low-carbon goals, and a three-dimensional decision cloud map (such as the three-dimensional relationship of ecological health, carbon emissions, and construction cost) is output.

[0041] More specifically, the carbon footprint tracking module is used to calculate the port operation carbon balance index, and the specific calculation formula is as follows: ; Where: represents the ecological carbon sink, and this value is calculated based on the wetland area and vegetation carbon sequestration efficiency; represents the carbon emissions during the operation stage, and this value is estimated based on energy consumption and carbon emission factors; represents the embodied carbon emissions during the construction stage, and all three are included in the constraint conditions of the multi-objective optimization model; At the same time, the life cycle assessment method is introduced to conduct a carbon footprint analysis on the entire life cycle of the port from construction, operation, maintenance to abandonment, more comprehensively evaluating the port's carbon emissions. Combining carbon trading market data, a carbon cost assessment model is established to link the carbon balance index with economic costs, providing an economic feasibility analysis for the port ecological construction plan.

[0042] More specifically, such as Figure 5As shown in the figure, the neurofeedback evaluation module of the augmented reality terminal includes: an electroencephalogram signal acquisition device and a cortical activation map analysis unit; the electroencephalogram signal acquisition device obtains the characteristics of the decision maker's alpha waves and beta waves in real time; the cortical activation map analysis unit identifies the cognitive matching degree of the solution through a convolutional neural network and outputs optimization suggestions to the decision optimization layer; at the same time, an emotion computing technology is introduced to analyze the emotion characteristics of the decision maker's facial expressions and speech intonations, and combined with the electroencephalogram signals to evaluate the decision maker's emotional preferences for different construction plans. Using the virtual scene generated by the digital twin engine and combining virtual reality technology, the decision maker can immerse himself in the port ecological environment changes under different construction plans, enhancing the intuitiveness and accuracy of the decision-making.

[0043] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for evaluating port ecological construction, characterized in that: The following steps are involved: S1. Multi-source data collection and trusted evidence storage: The dynamic ecological environment data in port construction and operation are collected through a multi-source sensor array, including water quality parameter groups, air pollutant concentrations, soil heavy metal content, noise spectrum, biodiversity index and resource utilization efficiency indicators; a multimodal feature fusion matrix is ​​constructed, and the original data is credibly stored; S2. Spatiotemporal dynamic analysis and environmental health assessment: The data is analyzed in time and space, and the dynamic attenuation rate of environmental indicators in each dimension is calculated using an adaptive sliding time window algorithm. , combined with the hydrodynamic conditions of the sea area around the port to adjust the ecological response time constant θ, and synchronously integrate and calculate the historical cumulative effect , generate the environmental health evolution surface; S3. Construction of comprehensive evaluation model: A comprehensive assessment model was constructed to quantify the habitat fragmentation index and the ecological connectivity index ECON. A dynamic weight allocation algorithm was used to integrate subjective and objective evaluation factors. An adaptive learning mechanism was introduced to optimize the weight convergence process and output the ecological comprehensive index ECI. S4. Environmental risk prediction and decision support: The environmental risk value is predicted based on the hybrid prediction model, and the Pareto frontier solution set is generated through a multi-objective optimization algorithm. Combined with the port ecological construction goals, a graded assessment report and a construction plan set are generated, and the prediction results are fed back to the digital twin engine for dynamic calibration.

2. A method for evaluating port ecological construction according to claim 1, characterized in that: The credible evidence of the original data described in S1 includes: Blockchain technology is used to hash and timestamp sensor data to build an unalterable data source proof chain. The blockchain evidence storage system adopts a consortium chain architecture, with nodes including port management departments, ecological and environmental protection agencies and monitoring equipment manufacturers, and verifies data integrity through a consensus mechanism; A quantum random number generator is introduced to generate data encryption keys, and quantum key distribution technology is used to ensure the security of key transmission and prevent data from being illegally cracked.

3. A method for evaluating port ecological construction according to claim 2, characterized in that: The dynamic decay rate described in S2 Calculated by the following formula: ； in, is the dynamic time window period (4h≤τ(t)≤24h), is the adaptive attenuation coefficient, For the Monitor the value at all times, is the lower safety threshold of the environmental indicator after dynamic correction, It is the upper limit threshold of the environmental index after dynamic correction. The threshold is automatically calibrated by Monte Carlo simulation and real-time data deviation. is the exponential decay factor, Indicates the current time and historical moments the time interval between Combined with the environmental variables of sea temperature and salinity obtained from satellite remote sensing data, a multivariate regression model is constructed to dynamically adjust the adaptive attenuation coefficient. , improve the accuracy of calculation of environmental indicator attenuation rate; Introducing reinforcement learning algorithms to optimize dynamic time window cycles based on historical evolution trends of environmental indicators and real-time monitoring data adjustment strategy.

4. A method for evaluating port ecological construction according to claim 3, characterized in that: The dynamic weight allocation algorithm described in S3 is embedded in the attention mechanism, and the weights of key indicators are calculated as follows: ； in, is the attention weight of the key indicator, , For the feature extraction function, the weight matrix is ​​dynamically optimized by minimizing the evaluation error; At the same time, the knowledge graph technology is introduced to build a knowledge graph in the port ecological field to assist in adjusting the weight distribution; and the federated learning framework is combined to optimize the feature extraction function , , improve the generalization ability of the model.

5. A method for evaluating port ecological construction according to claim 4, characterized in that: The hybrid prediction model described in S4 is an improved STL-LSTM model, including the following features: Hampel filter is used to eliminate outliers in time series data, and seasonal decomposition is used to extract the periodic characteristics of environmental data; Construct a spatiotemporal attention LSTM network and weight the port operation intensity index and tidal cycle parameters when updating the hidden layer state; Introducing the carbon footprint correction term, the formula is: ,in is the carbon balance index; Integrate the generative adversarial network, generate potential change scenarios of environmental risks through the generator, and the discriminator compares the prediction results with the generated scenarios to optimize the prediction accuracy of the STL-LSTM model; Edge computing nodes are used to pre-process and preliminarily predict real-time data at the port site, and key feature data is transmitted to the cloud for in-depth analysis, reducing data transmission delays and cloud computing pressure.

6. A port ecological construction evaluation system, which is applied to a port ecological construction evaluation method according to claim 5, characterized in that: include: The intelligent perception layer deploys a multi-spectral water quality sensor array, a MEMS gas sensor network, and an underwater acoustic Doppler profiler to form a heterogeneous data acquisition matrix, and integrates a blockchain evidence storage module to achieve reliable data on-chain. Digital twin engine, integrating time-space coupling analytical model and hybrid prediction model, supports port environment freedom simulation, including dynamic grid optimization unit and ecological stress analysis unit; The decision optimization layer runs the dynamic weight allocation algorithm and multi-objective optimization algorithm to generate a three-dimensional decision cloud diagram of the Pareto solution set, and embeds a carbon footprint tracking module to quantify the carbon emissions and carbon sinks of the port throughout its life cycle; The augmented reality terminal presents the migration path of pollutants through light field display technology, and combines tactile feedback and neural feedback devices to realize interactive adjustment of the solution.

7. A port ecological construction evaluation system according to claim 6, characterized in that: The blockchain evidence storage module includes: Data preprocessing unit, which performs denoising, normalization and quality verification on sensor data; Smart contract units automatically verify data integrity. When the monitored value deviates from the historical average by more than 20%, an on-chain warning is triggered and the data abnormal status is marked. At the same time, zero-knowledge proof technology is introduced to verify the authenticity and integrity of data to a third party without leaking the original data content. Sharded storage technology is used to divide blockchain data into multiple shards and store them on different nodes to improve data storage and retrieval efficiency.

8. A port ecological construction evaluation system according to claim 7, characterized in that: The dynamic grid optimization unit of the digital twin engine uses non-uniform rational B-splines and NURBS surface models to reconstruct the port terrain. The grid resolution is dynamically adjusted according to the ship's draft depth and tidal height, with a minimum resolution of 0.5 meters by 0.5 meters. Combined with point cloud processing technology, using the port point cloud data obtained by drones and underwater robots, the NURBS surface model is updated in real time to improve the accuracy of the digital twin model; The ecological stress analysis unit introduces a physical engine to simulate the impact of the physical environment of port water flow and wind on ships and facilities, achieving a more realistic simulation of port operation scenarios.

9. A port ecological construction evaluation system according to claim 8, characterized in that: The neural feedback evaluation module of the augmented reality terminal includes: EEG signal acquisition equipment to obtain the alpha and beta wave characteristics of decision makers in real time; The cortical activation map analysis unit uses a convolutional neural network to identify the cognitive matching degree of the solution and output optimization suggestions to the decision optimization layer; At the same time, emotional computing technology is introduced to analyze the emotional characteristics of decision makers' facial expressions and voice intonation, and EEG signals are combined to evaluate decision makers' emotional preferences for different construction plans. The virtual scenes generated by the digital twin engine are combined with virtual reality technology to allow decision makers to immersively experience the changes in the port ecological environment under different construction plans, thereby enhancing the intuitiveness and accuracy of decision-making.

10. A port ecological construction evaluation system according to claim 9, characterized in that: The carbon footprint tracking module is used to calculate the carbon balance index of port operations. The specific calculation formula is as follows: ； in: Represents ecological carbon sink, which is calculated based on wetland area and vegetation carbon sequestration efficiency; Represents carbon emissions during the operation phase, which is estimated based on energy consumption and carbon emission factors; represents the embodied carbon emissions during the construction phase, and all three are included in the constraints of the multi-objective optimization model; At the same time, the life cycle assessment method is introduced to conduct carbon footprint analysis on the entire life cycle of port construction, operation, maintenance to abandonment, so as to more comprehensively evaluate the carbon emissions of the port; combined with the carbon trading market data, a carbon cost assessment model is established to link the carbon balance index with the economic cost, so as to provide economic feasibility analysis for the port ecological construction plan.

Images