Ecological system health monitoring system and method based on biological indicator species

Abstract

The invention relates to the technical field of ecological monitoring, in particular to an ecological system health monitoring system and method based on biological indicator species, and the method comprises the steps: screening out the biological indicator species from a species database according to a monitoring target; collecting biodiversity data, biomarker data and environmental data of the monitoring area based on the screened biological indicator species; integrating the collected data, executing ecological health assessment, habitat quality assessment and spatial-temporal change analysis, and predicting the change trend of the ecological system based on assessment and analysis results; and evaluating the service function of the ecological system based on the prediction result, establishing a quantitative correlation model between the key indexes of the biological indication species and the service function, making an ecological protection and restoration strategy according to the quantitative correlation model, and completing dynamic evaluation of the health condition of the ecological system. According to the method, the future health trend of the ecological system can be scientifically pre-judged, and key early warning is provided for potential ecological risks.

Description

Technical Field

[0001] This invention relates to the field of ecological monitoring technology, and more specifically, to an ecosystem health monitoring system and method based on bioindicator species. Background Technology

[0002] The health and stability of ecosystems are a crucial cornerstone of sustainable development for human society. They provide us with clean water and air, regulate climate, and maintain rich biodiversity. With the acceleration of global industrialization and urbanization, ecosystems are facing multiple pressures from environmental pollution, habitat destruction, and climate change, severely threatening their structure and function. Therefore, the scientific and accurate monitoring and assessment of ecosystem health has become a key task in environmental protection and natural resource management. Indicator species, as highly sensitive "ecological sentinels" to environmental changes, can directly and comprehensively reflect the health status of ecosystems. By monitoring the population dynamics, physiological states, and behavioral changes of these species, the cumulative impact of environmental pressures on ecosystems can be effectively assessed. How to systematically integrate multi-source data, including biological, environmental chemistry, and spatial geographic information, to construct a monitoring system that can comprehensively reflect, dynamically track, and scientifically predict ecosystem evolution trends is a crucial issue urgently needing to be addressed in the field of ecological protection, and it has profound significance for achieving preventive protection and adaptive management of ecosystems. Existing ecological monitoring technologies have many limitations, making it difficult to meet the needs of modern, refined management. On the one hand, traditional monitoring methods often rely on isolated physical or chemical indicators, such as detecting only the concentration of specific pollutants in water or air. While direct, this approach fails to comprehensively reflect the health of the ecosystem as a complex whole, easily overlooking the synergistic effects and long-term cumulative effects between different stressors. On the other hand, many monitoring methods are costly and time-consuming in data collection, resulting in low monitoring frequency and limited coverage, making it difficult to capture the dynamic changes of the ecosystem in time and space, thus missing the best opportunity for early warning. Furthermore, existing analytical models mostly focus on describing and assessing the current state, lacking forward-looking predictive capabilities and failing to anticipate potential risks to the ecosystem in the future. This often leads to management decisions lagging behind the occurrence of problems. Moreover, monitoring results are often presented as highly specialized academic data, creating a gap between them and specific ecological protection actions. This makes it difficult for managers to effectively transform monitoring data into scientific and precise restoration and protection strategies, resulting in a waste of management resources. Summary of the Invention

[0003] The purpose of this invention is to provide an ecosystem health monitoring system and method based on bioindicator species. It achieves a comprehensive assessment of the ecosystem by integrating multi-source data, provides key risk warnings using predictive models, and directly transforms monitoring results into precise and efficient guidance for ecological protection actions by constructing quantitative correlation models, thus realizing scientific and forward-looking management.

[0004] This invention is achieved through the following technical solution:

[0005] An ecosystem health monitoring system based on bioindicator species includes: an indicator species selection and classification module, a biodiversity monitoring module, an environmental data collection module, a data analysis model prediction module, a biomarker monitoring module, a habitat quality assessment module, a spatiotemporal change monitoring module, and an ecosystem service function monitoring module. The indicator species selection and classification module is used to screen and classify biological indicator species from the species database based on preset ecological sensitivity and habitat adaptability criteria. The biodiversity monitoring module is used to identify and calculate the biodiversity index, which reflects the diversity of the ecosystem, based on the screened biomarker species, and output the biodiversity index to the data analysis model prediction module; The environmental data collection module is used to acquire environmental factor data of the monitoring area through sensor networks and remote sensing data, and output the environmental factor data to the data analysis model prediction module. The biomarker monitoring module is used to detect biomolecular markers and gene expression in screened bioindicator species to reflect stress responses under ecological pressure, and outputs the detection results to the data analysis model prediction module. The habitat quality assessment module is used to analyze the degree of habitat fragmentation and restoration potential based on the selected bioindicator species and their distribution data, and outputs the analysis results to the data analysis model prediction module. The spatiotemporal change monitoring module is used to record and predict the distribution dynamics of selected bioindicator species in time and space, and output the recording and prediction results to the data analysis model prediction module. The data analysis model prediction module is used to integrate data from the biodiversity monitoring module, environmental data collection module, biomarker monitoring module, habitat quality assessment module, and spatiotemporal change monitoring module to assess the health status of the ecosystem and predict its changing trends. The ecosystem service function monitoring module is used to assess the ecosystem service functions based on the integrated data from the data analysis model prediction module, and to construct a quantitative correlation model between key indicators of biological indicator species and service functions, and to formulate ecological protection and restoration strategies based on the quantitative correlation model.

[0006] Optionally, the indicator species selection and classification module includes a species database and a classification unit; the species database stores data on the ecological habits, sensitive environmental factors, and geographical distribution range of species, and filters biological indicator species suitable for different ecosystems based on the data; the classification unit is configured to classify biological indicator species based on the ecological sensitivity and habitat adaptability of species, so as to output representative biological indicator species.

[0007] Optionally, the biodiversity monitoring module includes a species identification unit and a biodiversity index calculation unit; the species identification unit is configured to use machine learning and image recognition technology to identify biological indicator species through collected biological images or video data, and output the species identification results to the biodiversity index calculation unit; the biodiversity index calculation unit is configured to calculate the biodiversity index based on the identification results, and output the biodiversity index to the data analysis model prediction module.

[0008] Optionally, the environmental data collection module includes a sensor network unit and a remote sensing data acquisition unit; the sensor network unit is specifically deployed in the monitoring area, which collects environmental factor data such as temperature, humidity and / or pollutant concentration, and outputs the environmental factor data to the data analysis model prediction module; the remote sensing data acquisition unit acquires remote sensing image data of the monitoring area through satellites or drones, and outputs the remote sensing image data to the data analysis model prediction module.

[0009] Optionally, the biomarker monitoring module includes a biomolecular marker detection unit and a gene expression analysis unit; the biomolecular marker detection unit is configured to detect DNA fragments or metabolites in the sample of the biomarker species and output the detection results to the gene expression analysis unit; the gene expression analysis unit is configured to monitor gene expression levels based on the detection results to analyze the stress response state and output the analysis results to the data analysis model prediction module.

[0010] Optionally, the habitat quality assessment module includes a habitat fragmentation analysis unit and a habitat restoration potential assessment unit; the habitat fragmentation analysis unit is configured to analyze the number, density, connectivity, or area changes of habitat patches based on land use data, and output the analysis results to the restoration potential assessment unit; the habitat restoration potential assessment unit is configured to assess the restoration potential based on the analysis results and in combination with topographic, soil, and hydrological data, and output the assessment results to the data analysis model prediction module.

[0011] Optionally, the spatiotemporal change monitoring module includes a spatiotemporal data recording unit and a species distribution dynamic prediction unit; the spatiotemporal data recording unit is configured to record the distribution data of biological indicator species at different time points and spatial locations, and output the recorded data to the species distribution dynamic prediction unit; the species distribution dynamic prediction unit is configured to establish a dynamic model based on the recorded data and environmental variable data to predict future distribution, and output the prediction results to the data analysis model prediction module.

[0012] Optionally, the data analysis model prediction module includes an ecological health assessment unit and a data visualization unit; the ecological health assessment unit is configured to output ecological health assessment results and trend predictions through preset machine learning based on integrated data from the indicator species selection and classification module, biodiversity monitoring module, environmental data collection module, biomarker monitoring module, habitat quality assessment module, and spatiotemporal change monitoring module; the data visualization unit is configured to visualize the ecological health assessment results and trend predictions.

[0013] Optionally, the ecosystem service function monitoring module includes an ecosystem service assessment unit and a correlation model construction unit; the ecosystem service assessment unit is configured to quantitatively assess water purification or carbon absorption service functions based on integrated data from the data analysis model prediction module, and output the assessment results to the correlation model construction unit; the correlation model construction unit is configured to establish a quantitative correlation model between the key indicators of the biological indicator species and the assessment results through statistical analysis methods.

[0014] An ecosystem health monitoring method based on bioindicator species, comprising the following steps: Based on the monitoring objectives, bioindicator species are selected from the species database; Based on the selected biomarker species, biodiversity data, biomarker data, and environmental data of the monitoring area were collected. Integrate collected data, perform ecological health assessments, habitat quality assessments, and spatiotemporal change analyses, and predict ecosystem change trends based on the assessment and analysis results; Based on the prediction results, assess the ecosystem service functions, establish a quantitative correlation model between key indicators of biological indicator species and service functions, and formulate ecological protection and restoration strategies based on the quantitative correlation model to complete the dynamic assessment of ecosystem health status.

[0015] The technical solution of the present invention has at least the following advantages and beneficial effects: This invention establishes a multi-dimensional, three-dimensional monitoring framework that systematically integrates heterogeneous data from multiple sources, including biodiversity, biomarkers, habitat quality, and environmental factors. This enables a comprehensive and in-depth "health check" of the ecosystem, overcoming the limitations of traditional methods that rely on a single indicator for one-sided assessment. Furthermore, this invention incorporates modern technologies such as machine learning, remote sensing, and automated sensors, achieving real-time, efficient data acquisition and intelligent analysis of monitoring data. This significantly improves monitoring efficiency and accuracy, allowing for precise capture and dynamic tracking of the spatiotemporal evolution of the ecosystem. The core advantage of this invention lies in its powerful predictive capabilities. Through built-in data analysis and prediction models, it can scientifically predict future ecosystem health trends, providing crucial early warnings of potential ecological risks and enabling managers to shift from passive response to proactive prevention. Moreover, by uniquely establishing a quantitative correlation model between key indicators of biomarker species and ecosystem service functions, it successfully transforms complex ecological state data into intuitive and actionable decision-making data, directly serving the precise formulation of ecological protection and restoration strategies and achieving a seamless connection from data monitoring to scientific decision-making. Attached Figure Description

[0016] Figure 1 A schematic diagram illustrating the principle of the ecosystem health monitoring system based on bioindicator species provided by this invention; Figure 2 This is a schematic flowchart of the ecosystem health monitoring method based on bioindicator species provided by the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0018] Example 1 This invention provides an ecosystem health monitoring system based on bioindicator species. Physically, this system is a computing system deployed in the cloud or on a local server, communicating with front-end data acquisition devices and back-end management terminals via a network. At the software level, the system consists of multiple modular programs. These modules work collaboratively through pre-defined data interfaces to form a complete data processing and analysis chain, enabling comprehensive monitoring and assessment of ecosystem health.

[0019] like Figure 1As shown, the system includes: an indicator species selection and classification module, a biodiversity monitoring module, an environmental data collection module, a biomarker monitoring module, a habitat quality assessment module, a spatiotemporal change monitoring module, a data analysis model prediction module, and an ecosystem service function monitoring module.

[0020] Specifically, the indicator species selection and classification module is the foundation of the entire monitoring system. Its core function is to scientifically and efficiently screen and classify the biological indicator species that best represent the health status of the target ecosystem based on the monitoring objectives. This module includes a species database and a classification unit. The species database is technically constructed using the relational database management system MySQL or the non-relational database MongoDB. The database stores massive amounts of species information, and its data table structure includes species ID, species name, taxonomic information, ecological habits, sensitive environmental factors, geographical distribution data, and historical monitoring data. In this embodiment, the database pre-includes a large number of species that have been proven to have indicator roles, covering multiple groups such as plants, invertebrates, and amphibians. The classification unit is technically implemented by a series of Python scripts running on the server. When the user inputs the monitoring objective, the classification unit first screens candidate indicator species from the species database based on the ecosystem type and geographical location of the monitoring area; then, based on preset ecological sensitivity and habitat adaptability criteria, it uses a multi-criteria decision analysis method to score and rank the candidate species; finally, the unit outputs one or a group of representative biological indicator species with the highest scores to guide subsequent data collection.

[0021] Specifically, the biodiversity monitoring module is responsible for the field identification and diversity quantification of selected biomarker species, providing core biological data for ecological health assessment. This module includes a species identification unit and a biodiversity index calculation unit. The species identification unit is key to achieving automated monitoring; it employs convolutional neural network models from deep learning, such as ResNet, VGG, or YOLO. This model, trained on a dataset containing a large number of labeled biological images, achieves high-precision identification of target indicator species. Biological images or video data collected by infrared cameras, drones, or user-handheld devices deployed in the field are transmitted to this unit in real time via the network for processing, automatically identifying species in the images and recording their frequency and location information. The identification results are formatted and output to the biodiversity index calculation unit. Technically, the biodiversity index calculation unit is a data processing script implemented using Python and its scientific computing libraries Pandas and NumPy. After receiving the species identification results, it calculates various biodiversity indices according to standard ecological formulas, primarily including the Shannon index and the Simpson index. The calculated biodiversity index will serve as a key indicator for assessing ecosystem stability and complexity, and will be output to the data analysis model prediction module for further integrated analysis.

[0022] Specifically, the environmental data collection module is responsible for collecting physical and chemical environmental data of the monitoring area, providing environmental background information for comprehensive assessment. This module includes a sensor network unit and a remote sensing data acquisition unit. The sensor network unit consists of multiple wireless sensor nodes deployed in the monitoring area. These sensors can collect key environmental factor data in real time, including temperature, humidity, soil pH, light intensity, and pollutant concentrations in the air or water. Each sensor node attaches a timestamp and geographic coordinates to the collected data and periodically sends it to the system server via wireless communication protocols such as LoRa or NB-IoT. The remote sensing data acquisition unit is responsible for acquiring large-scale, macroscopic ecological and environmental information. It obtains remote sensing image data of the monitoring area by calling public or commercial satellite remote sensing data APIs such as Landsat, Sentinel, or MODIS, or by controlling drones equipped with multispectral cameras for aerial photography. This macroscopic data is crucial for assessing large-scale ecological patterns and is also output to the data analysis model prediction module.

[0023] Specifically, the biomarker monitoring module uses molecular biology techniques to reveal the physiological stress state of indicator species under environmental pressure at the microscopic level, providing earlier and more sensitive warning signals than macroscopic quantitative changes. This module includes a biomolecular marker detection unit and a gene expression analysis unit. The biomolecular marker detection unit processes biomarker species samples collected from the field. In a laboratory environment, technicians use molecular detection techniques such as polymerase chain reaction (PCR) or high-throughput sequencing to detect specific DNA fragments in the samples and analyze metabolite profiles using liquid chromatography-mass spectrometry (LC-MS). The detection results are digitized and output to the gene expression analysis unit. Upon receiving the detection results, the gene expression analysis unit analyzes mRNA expression levels using real-time quantitative PCR (qPCR) to monitor the gene expression levels of specific genes related to stress responses. By comparing the gene expression differences between samples from stressed and control areas, the stress response state of the species can be accurately determined. The analysis results are output to the data analysis model prediction module, serving as an important basis for assessing potential ecological pressure.

[0024] Specifically, the habitat quality assessment module focuses on evaluating the quality of habitats for indicator species and predicting their restoration potential. This module includes a habitat fragmentation analysis unit and a habitat restoration potential assessment unit. The habitat fragmentation analysis unit primarily uses land use data for spatial analysis. It utilizes professional Geographic Information System (GIS) software ArcGIS, or spatial analysis toolkits such as Python's GeoPandas library and Fragstats software, to analyze spatial pattern indices of habitats, including patch number, density, connectivity, and area change. These analytical results quantify the degree of habitat fragmentation. The analysis results are then output to the habitat restoration potential assessment unit. The habitat restoration potential assessment unit is a comprehensive assessment model that, based on the analysis results of the previous unit and combined with topographic, soil type, and hydrological data, comprehensively assesses the restoration potential of damaged habitats. The assessment results are output to the data analysis model prediction module, providing a scientific basis for the site selection and prioritization of ecological restoration projects.

[0025] Specifically, the spatiotemporal change monitoring module is responsible for recording and predicting the distribution dynamics of bioindicator species in both time and space to reveal long-term ecosystem trends. This module includes a spatiotemporal data recording unit and a species distribution dynamic prediction unit. The spatiotemporal data recording unit is a spatiotemporal database responsible for recording the distribution data of bioindicator species at different time points and spatial locations. Each record includes the species name, timestamp, and precise GPS geographic coordinates. The recorded data is output to the species distribution dynamic prediction unit. The species distribution dynamic prediction unit uses a niche model to predict the future distribution of species. It establishes a dynamic model based on recorded data and environmental variable data. The dynamic models used in this embodiment include the maximum entropy model (MaxEnt) and the generalized linear model (GLM). The model first learns the relationship between the current distribution of species and their habitat, and then combines the climate change scenario data predicted by the IPCC to predict the possible future distribution range of species. The prediction results are output to the data analysis model prediction module.

[0026] Specifically, the data analysis model prediction module is the central processing unit of the entire system, responsible for integrating data from all front-end modules to perform comprehensive evaluation and trend prediction. This module specifically includes an ecological health assessment unit and a data visualization unit. The core of the ecological health assessment unit is a pre-set machine learning model, such as random forest, support vector machine, or gradient boosting tree. This unit first integrates data from the biodiversity monitoring module, environmental data collection module, biomarker monitoring module, habitat quality assessment module, and spatiotemporal change monitoring module to form a high-dimensional feature vector. This feature vector is then input into a pre-trained model, outputting the current ecosystem's ecological health assessment results and trend predictions. The data visualization unit is responsible for presenting complex analysis results to users in an intuitive and easy-to-understand way. It utilizes Python's Matplotlib and Seaborn libraries, or front-end data visualization libraries such as D3.js and ECharts, to visualize ecological health assessment results and trend predictions, in formats including dynamic dashboards, multi-layered overlay GIS maps, and time-series trend charts.

[0027] Specifically, the ecosystem service function monitoring module directly links the health of the ecosystem to human well-being and provides quantitative evidence for formulating specific protection strategies. This module includes an ecosystem service assessment unit and a correlation model construction unit. The ecosystem service assessment unit, based on integrated data from the data analysis model prediction module, uses the professional InVEST ecosystem service assessment model to quantitatively assess service functions such as water purification or carbon absorption. The assessment results are output to the correlation model construction unit. The correlation model construction unit establishes a quantitative correlation model between key indicators of biomarker species and the assessment results of ecosystem service functions through statistical analysis methods. It collects key indicators of biomarker species as independent variables and the service function assessment results output by the ecosystem service assessment unit as dependent variables, and then uses multiple linear regression, ridge regression, and other nonlinear models to construct mathematical relationships. Ultimately, based on the quantitative correlation model, the system can formulate more scientific and precise ecological protection and restoration strategies.

[0028] Example 2 like Figure 2 As shown, this embodiment provides an ecosystem health monitoring method based on the system described in Embodiment 1. This method is a systematic workflow that ensures the scientific rigor and consistency of monitoring, assessment, and decision-making. The method includes the following steps: First, based on the monitoring objectives, operators input relevant information through the system interface. The system automatically filters out indicator species sensitive to the target issue from the species database, classifies and ranks these species based on ecological sensitivity and habitat adaptability, and finally determines the indicator species to be used for this monitoring task. Based on this, a detailed monitoring plan is designed, providing basic data for subsequent work.

[0029] Based on the biomarker species selected in the previous step, the system initiates a data acquisition task. The biodiversity monitoring module acquires images via field cameras to obtain biodiversity data; the biomarker monitoring module guides on-site personnel to collect samples and obtain biomarker data reflecting the stress state of the species; the environmental data collection module collects environmental data of the monitoring area in real time through sensor networks and remote sensing platforms. All collected data is timestamped and geotagged, and then output to subsequent steps for integration.

[0030] The system integrates all heterogeneous data collected in the previous step and performs preprocessing such as data cleaning and standardization. Subsequently, it performs an ecological health assessment, outputting the current health level of the ecosystem; a habitat quality assessment, evaluating the degree of habitat fragmentation and restoration potential; and a spatiotemporal change analysis, predicting the future distribution dynamics of indicator species. These assessment and analysis results are not only used to predict ecosystem change trends and generate visual reports, but also serve as input data to support subsequent service function assessments.

[0031] Based on the assessment and prediction results from the previous step, the system quantitatively evaluates key ecosystem service functions such as water purification and carbon absorption. Next, using historical and current data, the system establishes a quantitative correlation model between key indicators of biomarker species and their service functions. Finally, based on the established correlation model and the overall analysis results, the system can assist decision-makers in formulating specific ecological protection and restoration strategies.

[0032] Through the above steps, the method of the present invention ultimately completes the dynamic assessment of the health status of the ecosystem and realizes closed-loop management from scientific monitoring to precise decision-making.

[0033] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An ecosystem health monitoring system based on bioindicator species, characterized in that, include: The system includes modules for indicator species selection and classification, biodiversity monitoring, environmental data collection, data analysis and model prediction, biomarker monitoring, habitat quality assessment, spatiotemporal change monitoring, and ecosystem service function monitoring. The indicator species selection and classification module is used to screen and classify biological indicator species from the species database based on preset ecological sensitivity and habitat adaptability criteria. The biodiversity monitoring module is used to identify and calculate the biodiversity index, which reflects the diversity of the ecosystem, based on the screened biomarker species, and output the biodiversity index to the data analysis model prediction module; The environmental data collection module is used to acquire environmental factor data of the monitoring area through sensor networks and remote sensing data, and output the environmental factor data to the data analysis model prediction module. The biomarker monitoring module is used to detect biomolecular markers and gene expression in screened bioindicator species to reflect stress responses under ecological pressure, and outputs the detection results to the data analysis model prediction module. The habitat quality assessment module is used to analyze the degree of habitat fragmentation and restoration potential based on the selected bioindicator species and their distribution data, and outputs the analysis results to the data analysis model prediction module. The spatiotemporal change monitoring module is used to record and predict the distribution dynamics of selected bioindicator species in time and space, and output the recording and prediction results to the data analysis model prediction module. The data analysis model prediction module is used to integrate data from the biodiversity monitoring module, environmental data collection module, biomarker monitoring module, habitat quality assessment module, and spatiotemporal change monitoring module to assess the health status of the ecosystem and predict its changing trends. The ecosystem service function monitoring module is used to assess the ecosystem service functions based on the integrated data from the data analysis model prediction module, and to construct a quantitative correlation model between key indicators of biological indicator species and service functions, and to formulate ecological protection and restoration strategies based on the quantitative correlation model.

2. The ecosystem health monitoring system based on bioindicator species according to claim 1, characterized in that, The indicator species selection and classification module includes a species database and classification units; the species database stores data on the ecological habits, sensitive environmental factors, and geographical distribution range of species, and selects biological indicator species suitable for different ecosystems based on the data; The taxonomic unit is configured to classify bioindicator species based on their ecological sensitivity and habitat adaptability to output representative bioindicator species.

3. The ecosystem health monitoring system based on bioindicator species according to claim 2, characterized in that, The biodiversity monitoring module includes a species identification unit and a biodiversity index calculation unit. The species identification unit is configured to use machine learning and image recognition technology to identify biological indicator species through collected biological images or video data, and output the species identification results to the biodiversity index calculation unit. The biodiversity index calculation unit is configured to calculate the biodiversity index based on the identification results, and output the biodiversity index to the data analysis model prediction module.

4. The ecosystem health monitoring system based on bioindicator species according to claim 1, characterized in that, The environmental data collection module includes a sensor network unit and a remote sensing data acquisition unit. The sensor network unit is specifically deployed in the monitoring area, which collects environmental factor data such as temperature, humidity and / or pollutant concentration, and outputs the environmental factor data to the data analysis model prediction module. The remote sensing data acquisition unit acquires remote sensing image data of the monitoring area through satellites or drones, and outputs the remote sensing image data to the data analysis model prediction module.

5. The ecosystem health monitoring system based on bioindicator species according to claim 1, characterized in that, The biomarker monitoring module includes a biomolecular marker detection unit and a gene expression analysis unit. The biomolecular marker detection unit is configured to detect DNA fragments or metabolites in bioindicator species samples and output the detection results to the gene expression analysis unit. The gene expression analysis unit is configured to monitor gene expression levels based on the detection results to analyze stress response status and output the analysis results to the data analysis model prediction module.

6. The ecosystem health monitoring system based on bioindicator species according to claim 1, characterized in that, The habitat quality assessment module includes a habitat fragmentation analysis unit and a habitat restoration potential assessment unit. The habitat fragmentation analysis unit is configured to analyze the number, density, connectivity, or area changes of habitat patches based on land use data and output the analysis results to the restoration potential assessment unit. The habitat restoration potential assessment unit is configured to assess the restoration potential based on the analysis results and in combination with topographic, soil, and hydrological data, and output the assessment results to the data analysis model prediction module.

7. The ecosystem health monitoring system based on bioindicator species according to claim 1, characterized in that, The spatiotemporal change monitoring module includes a spatiotemporal data recording unit and a species distribution dynamic prediction unit. The spatiotemporal data recording unit is configured to record the distribution data of biological indicator species at different time points and spatial locations, and output the recorded data to the species distribution dynamic prediction unit. The species distribution dynamic prediction unit is configured to establish a dynamic model based on the recorded data and environmental variable data to predict future distribution, and output the prediction results to the data analysis model prediction module.

8. The ecosystem health monitoring system based on bioindicator species according to any one of claims 1-7, characterized in that, The data analysis model prediction module includes an ecological health assessment unit and a data visualization unit. The ecological health assessment unit is configured to integrate data from the indicator species selection and classification module, the biodiversity monitoring module, the environmental data collection module, the biomarker monitoring module, the habitat quality assessment module, and the spatiotemporal change monitoring module, and output ecological health assessment results and trend predictions through preset machine learning. The data visualization unit is configured to visualize the results of ecological health assessments and trend predictions.

9. The ecosystem health monitoring system based on bioindicator species according to claim 8, characterized in that, The ecosystem service function monitoring module includes an ecosystem service assessment unit and an association model construction unit; the ecosystem service assessment unit is configured to quantitatively assess water purification or carbon absorption service functions based on integrated data from the data analysis model prediction module, and output the assessment results to the association model construction unit. The association model building unit is configured to establish a quantitative association model between the key indicators of the biological indicator species and the evaluation results through statistical analysis methods.

10. An ecosystem health monitoring method based on bioindicator species, characterized in that, The steps of this method include: Based on the monitoring objectives, bioindicator species are selected from the species database; Based on the selected biomarker species, biodiversity data, biomarker data, and environmental data of the monitoring area were collected. Integrate collected data, perform ecological health assessments, habitat quality assessments, and spatiotemporal change analyses, and predict ecosystem change trends based on the assessment and analysis results; Based on the prediction results, assess the ecosystem service functions, establish a quantitative correlation model between key indicators of biological indicator species and service functions, and formulate ecological protection and restoration strategies based on the quantitative correlation model to complete the dynamic assessment of ecosystem health status.

Images