Lake water ecological restoration monitoring method based on big data

Abstract

This invention discloses a big data-based monitoring method for lake aquatic ecosystem restoration, relating to the field of submerged plant monitoring technology. The method includes the following steps: collecting original water quality data of the lake area to be restored before the use of submerged plants for restoration, and collecting initial water quality data after the start of restoration using submerged plants; performing correlation analysis to obtain relevant water quality physicochemical indicators; collecting water quality physicochemical data of relevant water quality physicochemical indicators of the lake area to be restored, and performing water quality physicochemical change analysis to obtain plant-related change data; monitoring and analyzing the submerged plants in the lake area to be restored based on the plant-related change data to obtain relevant change information of the submerged plants. This invention addresses the problem that existing submerged plant monitoring technologies, in the initial stage of lake aquatic ecosystem restoration using submerged plants, cannot accurately obtain the development status of submerged plants through water parameters without damaging the plants.

Description

Technical Field

[0001] This invention relates to the field of submerged plant monitoring technology, specifically a lake water ecological restoration monitoring method based on big data. Background Technology

[0002] Submerged plant monitoring technology refers to a comprehensive technical system that uses various technical means to observe, collect, and analyze data on the growth status, distribution range, community structure, biomass, and environmental adaptability of submerged plants in water areas. Its core objective is to accurately grasp the ecological characteristics of submerged plants and their interaction with the aquatic environment, so as to provide a scientific basis for the protection, restoration, and management of aquatic ecosystems.

[0003] In the initial stage of restoring lake ecosystems using submerged plants, the healthy development of these plants is the core foundation for the success of the entire restoration project. Submerged plants not only build an energy base through photosynthesis and efficiently absorb nutrients to purify water, but they also provide habitats for aquatic organisms, inhibit excessive algal growth, and reduce resuspension pollution from bottom sediments. More importantly, well-developed submerged plants in the early stages can promote the transformation of the lake's aquatic ecosystem and activate the ecosystem's self-repair mechanism. If the initial development of submerged plants is hindered, the restoration effect will be significantly reduced, and it may even lead the lake ecosystem into a vicious cycle. However, existing submerged plant monitoring technologies typically rely on on-site sampling or visual methods. Sampling in the field can damage submerged plants and affect their early development. For example, patent application CN117796224A discloses a rapid sampling device for submerged plants used in the ecological restoration assessment of shallow lakes. This method damages submerged plants during sampling, affecting their early development. In lakes where the aquatic ecosystem has been damaged, the water transparency is limited, making it difficult to collect clear images using visual methods. Therefore, existing submerged plant monitoring technologies cannot accurately obtain information about the development of submerged plants through water parameters without damaging them when monitoring them in the initial stage of lake aquatic ecosystem restoration. Summary of the Invention

[0004] This invention aims to at least partially solve one of the technical problems in the prior art. It involves collecting raw water quality data of the lake area to be restored before the use of submerged plants for restoration, and initial water quality data after the start of restoration using submerged plants. Based on the raw and initial water quality data, correlation analysis is performed to obtain relevant water quality physicochemical indicators. Water quality physicochemical data of relevant indicators in the lake area to be restored are collected, and water quality physicochemical changes are analyzed to obtain plant-related change data. Based on the plant-related change data, the submerged plants in the lake area to be restored are monitored and analyzed to obtain relevant change information of the submerged plants. This addresses the problem that existing submerged plant monitoring technologies, in the initial stage of lake ecological restoration using submerged plants, cannot accurately obtain the development status of submerged plants through water parameters without damaging the plants.

[0005] To achieve the above objectives, this application provides a big data-based monitoring method for lake aquatic ecosystem restoration, comprising the following steps:

[0006] Collect raw water quality data of the lake area to be restored before the use of submerged plants for restoration, and collect initial water quality data after the use of submerged plants for restoration begins;

[0007] Correlation analysis was performed on the raw water quality data and the initial water quality data to obtain relevant water quality physicochemical indicators.

[0008] Collect relevant water quality physicochemical data of the lake area to be restored, and conduct water quality physicochemical change analysis to obtain plant-related change data;

[0009] Based on data on plant-related changes, we monitored and analyzed the submerged plants in the lake area to be restored, and obtained relevant information on changes in the submerged plants.

[0010] Furthermore, collecting raw water quality data of the lake area to be restored before the use of submerged plants for restoration, and collecting initial water quality data after the start of restoration using submerged plants, includes the following sub-steps:

[0011] For the water body area in the lake that needs to be restored, it is denoted as the lake area to be restored; the average depth of the lake area to be restored is obtained and denoted as DE1; the maximum height of the submerged plants used to restore the lake area to be restored is obtained and denoted as DL1; k1 points are uniformly selected from [0, DE1-DL1] and denoted as the water depth collected by k1-k1 according to their size; where k1 is the number of points set.

[0012] Within a day, k2 sampling time points are set, denoted as sampling time points 1-k2; and k3 sampling locations are selected from the lake area to be restored; where k2 and k3 are the number of sampling locations set; water quality parameters related to submerged plants are obtained from the database, denoted as water quality parameters 1-n;

[0013] Before using submerged plants to restore the lake area, select k4 days and record them as the pre-restoration sampling days; and after starting the submerged plant restoration, select k4 days and record them as the post-restoration sampling days, where k4 is the set number of days.

[0014] Furthermore, collecting the original water quality data of the lake area to be restored before the use of submerged plants for restoration, and collecting the initial water quality data after the start of restoration using submerged plants, also includes the following sub-steps:

[0015] Take any pre-revision sampling date or post-revision sampling log as the first sampling date, and record any sampling time point on the first sampling date as the first time point;

[0016] At the first time point, the values ​​of each water quality parameter were collected from each sampling depth at each sampling location, and for each water quality parameter, the average value at the same sampling depth at different sampling locations was calculated; the average data of each water quality parameter at different sampling depths at the first sampling time point were obtained and recorded as the water quality sampling information at the first time point; the water quality sampling information at all sampling time points on the first sampling day was repeatedly obtained to obtain the water quality sampling data for the first sampling day;

[0017] Repeatedly acquire water quality sampling data for all pre-revision sampling days and record them as raw water quality data; and repeatedly acquire water quality sampling data for all post-revision sampling days and record them as initial water quality data.

[0018] Furthermore, based on the original water quality data and the initial water quality data, correlation analysis was performed to obtain relevant water quality physicochemical indicators, including the following sub-steps:

[0019] Any water quality parameter is denoted as the first water quality parameter; the first water quality parameters in the original water quality data that are located on different pre-revision sampling days, at the same sampling time point, and at the same sampling depth are sorted in chronological order and denoted as the original parameter sequence; any original water quality parameter sequence is denoted as the first parameter sequence; the average value from the k5th percentile to the k6th percentile of the first parameter sequence is calculated and denoted as the reference water quality data for the sampling time point and sampling depth corresponding to the first parameter sequence; where k5 and k6 are the set percentiles;

[0020] The first water quality parameter in the initial water quality data that is located on different post-sampling days, at the same sampling time point, and at the same sampling depth is sorted in chronological order and recorded as the initial parameter sequence.

[0021] And denote any initial parameter sequence as the second parameter sequence; calculate the average value from the k5th percentile to the k6th percentile of the second parameter sequence, and denote it as the initial water quality data of the sampling time point and the water depth collected for the second parameter sequence.

[0022] Furthermore, the correlation analysis based on the original water quality data and initial water quality data to obtain relevant water quality physicochemical indicators also includes the following sub-steps:

[0023] Repeatedly acquire reference water quality data and initial water quality data for the first water quality parameter at all sampling time points and at the sampling depth;

[0024] For the first water quality parameter, calculate the absolute value of the difference between the reference water quality data and the initial water quality data at all sampling time points and sampling depths, and record it as the absolute difference. Obtain the largest and second largest absolute differences, and record them as the maximum difference and the second largest difference, respectively. Mark the sampling time point and sampling depth corresponding to the maximum difference as the optimal sampling time and optimal sampling depth of the first water quality parameter, respectively. Obtain the specific data of the first water quality parameter at the optimal sampling time and optimal sampling depth for all sampling days before the revision, and calculate the average, which is recorded as the pre-revision reference average of the first water quality parameter.

[0025] Repeatedly obtain the maximum and second-largest differences of all water quality parameters, and obtain the corresponding optimal sampling time, optimal sampling depth, and pre-revision reference average.

[0026] Furthermore, the correlation analysis based on the original water quality data and initial water quality data to obtain relevant water quality physicochemical indicators also includes the following sub-steps:

[0027] Arrange all the largest and second largest differences in descending order, and denote them as the first difference sequence and the second difference sequence, respectively. Use density clustering algorithm to divide all the first difference sequences and the second difference sequences into k7 difference clusters, and denote them as the first difference cluster 1-k7 and the second difference cluster 1-k7, respectively, according to the corresponding differences in ascending order, where k7 is the set number.

[0028] For the first water quality parameter, the difference clusters to which the largest and second largest differences belong are respectively denoted as the first difference cluster n1 and the second difference cluster n2; n1+n2 is marked as the relevant score of the first water quality parameter;

[0029] Repeatedly obtain the relevant scores of all water quality parameters, and mark the k8 water quality parameters whose difference changes in the direction of the ecological function of submerged plants and whose relevant scores are the largest as relevant water quality physicochemical indicators, where k8 is the number set.

[0030] Furthermore, water quality physicochemical data of relevant water quality indicators in the lake area to be restored are collected, and water quality physicochemical changes are analyzed to obtain plant-related change data, including the following sub-steps:

[0031] For any relevant water quality physicochemical index, it is denoted as the first water quality index; the optimal sampling time and optimal sampling depth corresponding to the first water quality index are respectively denoted as the first sampling time and the first sampling depth.

[0032] At the first collection time each day, specific data of the first water quality index were collected from the first water depth at all collection locations, and the average value of the specific data collected from all collection locations was calculated and recorded as the representative value of the first water quality index. At the same time, the weather conditions and rainfall of each day were recorded and recorded as the water quality index data of the first water quality index.

[0033] Repeatedly obtain water quality index data for all relevant water quality physicochemical indicators to obtain water quality physicochemical data.

[0034] Furthermore, collecting relevant water quality physicochemical data for the lake area to be restored, and conducting water quality physicochemical change analysis to obtain plant-related change data also includes the following sub-steps:

[0035] Record any date with zero rainfall and good weather conditions as a useful day, and record any useful diary entry from the water quality physicochemical data as the first day.

[0036] Obtain the representative value of the first water quality indicator on the first day, denoted as the first representative value DA; obtain the representative value of the first water quality indicator for each useful day in the k9 days prior to the first day, denoted as the useful representative value; obtain the useful representative value that is closest to the first day in terms of time distance, denoted as DB; and calculate the average of all useful representative values, denoted as DP; where k9 is the set number of days.

[0037] The pre-revision reference average corresponding to the first water quality indicator is denoted as BP; the parameter change index of the first water quality indicator on the first day is calculated according to the first formula, where the first formula is as follows: Where BW represents the parameter change index, and u represents the correlation between the first water quality index and submerged plants. If the magnitude of the first water quality index is positively correlated with the amount of submerged plants, then u=1; otherwise, u=-1.

[0038] Repeatedly obtain the parameter changes of all relevant water quality physicochemical indicators on the first day.

[0039] Furthermore, collecting relevant water quality physicochemical data for the lake area to be restored, and conducting water quality physicochemical change analysis to obtain plant-related change data also includes the following sub-steps:

[0040] Select a point on the two-dimensional plane as the origin of the coordinate system, and draw k8 number axes in a counterclockwise direction starting from the origin of the coordinate system. The rotation angle between any two adjacent number axes is (360 / k8)°. Then, map the k8 number axes to k8 relevant water quality physicochemical indicators.

[0041] The number axis corresponding to the first water quality index is denoted as the first index number axis. The parameter change index of the first water quality index is uniformly plotted on the first index number axis by a unit length. The position of the parameter change index of the first water quality index on the first index number axis is obtained and denoted as the change index point.

[0042] Repeatedly obtain all relevant water quality physicochemical indicators on the corresponding number axis, connect all the indicator points in a counterclockwise direction, and record the enclosed area as the indicator area. Obtain the area size of the indicator area and record it as the relevant area indicator for the first day.

[0043] The relevant area indicators for each useful day were repeatedly obtained to obtain plant-related change data.

[0044] Furthermore, based on the data on changes in plant-related changes, the submerged plants in the lake area to be restored were monitored and analyzed. The relevant change information of submerged plants was obtained through the following sub-steps:

[0045] For the current date, obtain the relevant area indicators of the x1 most useful days in terms of time distance, and record them as reference area indicators; perform linear fitting on all reference area indicators to obtain the changing trend of the reference area indicators, which includes increasing, decreasing and basically unchanged; where x1 is the set number of days;

[0046] If the trend of the reference area index is increasing, the submerged plants in the lake area to be restored are considered to be developing well; if the trend of the reference area index is decreasing, the submerged plants in the lake area to be restored are considered to be developing poorly; if the trend of the reference area index is basically unchanged, the submerged plants in the lake area to be restored are considered to be developing moderately.

[0047] The beneficial effects of this invention are as follows: This invention collects the original water quality data of the lake area to be restored before the use of submerged plants for restoration, and also collects the initial water quality data after the start of restoration using submerged plants; based on the original water quality data and the initial water quality data, correlation analysis is performed to obtain relevant water quality physicochemical indicators; water quality physicochemical data of relevant water quality physicochemical indicators of the lake area to be restored are collected, and water quality physicochemical change analysis is performed to obtain plant-related change data; based on the plant-related change data, the submerged plants in the lake area to be restored are monitored and analyzed to obtain relevant change information of submerged plants; when monitoring submerged plants in the initial stage of restoring the lake's aquatic ecosystem using submerged plants, the development status of submerged plants can be accurately obtained through water parameters without damaging the submerged plants;

[0048] This invention analyzes the absolute difference between reference water quality data and initial water quality data to determine the optimal sampling time and depth for each water quality parameter. This avoids data bias caused by water stratification and dynamic fluctuations over time during subsequent data collection, accurately reflecting the true state of the water body and thus improving monitoring accuracy. By filtering relevant physicochemical indicators based on the maximum and second-largest differences in water quality parameters, the invention significantly reduces data dimensions, lowers monitoring costs, and improves the efficiency of monitoring and analysis. Furthermore, by calculating the parameter changes of relevant physicochemical indicators to obtain related area indicators, compared to traditional change ratios, this invention considers both the absolute intensity and relative fluctuations of water quality parameter changes, accurately characterizing these changes. Attached Figure Description

[0049] Figure 1 This is a flowchart of the steps of the method of the present invention;

[0050] Figure 2 This is a schematic diagram of the change index area of ​​the present invention;

[0051] Figure 3 This is a flowchart for judging the development of submerged plants according to the present invention;

[0052] Figure 4 This is a schematic diagram of the electronic device of the present invention. Detailed Implementation

[0053] 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. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0054] Example 1, please refer to Figure 1As shown, this application provides a big data-based monitoring method for lake aquatic ecosystem restoration, including the following steps:

[0055] Step S1 involves collecting raw water quality data of the lake area to be restored before the use of submerged plants for restoration, and initial water quality data after the start of restoration using submerged plants. Step S1 includes the following sub-steps:

[0056] Step S101: For the water body area in the lake to be restored, denoted as the lake area to be restored; obtain the average depth of the lake area to be restored, denoted as DE1; obtain the maximum height of the submerged plants used to restore the lake area to be restored, denoted as DL1; uniformly select k1 points from [0, DE1-DL1], and denot them as sampling depths 1-k1 according to their size; where k1 is the set number; ensure that the sampling points are not disturbed by the water surface environment or completely covered by submerged plants; ensure that the data can reflect the water quality characteristics of different layers in the water body, reflect the vertical water quality stratification, and help to understand the vertical change law of the aquatic ecosystem; k1 can be set according to the actual application scenario, in this embodiment k1=10;

[0057] Step S102: Set k2 sampling time points within one day, denoted as sampling time points 1-k2; and select k3 sampling locations from the lake area to be restored; where k2 and k3 are the set numbers; obtain water quality parameters related to submerged plants from the database, denoted as water quality parameters 1-n; in this embodiment, k2=4; these are 0, 6, 12, and 18 points respectively; k3 can be set according to the size of the lake area to be restored; multiple sampling locations ensure uniform spatial distribution, improve data representativeness, and avoid deviations caused by local errors; there are many types of water quality parameters, focusing on water quality parameters related to the growth of submerged plants, such as DO, TN, TP, and transparency, can improve the effectiveness and relevance of subsequent analysis;

[0058] Step S103: Select k4 days before using submerged plants to restore the lake area to be restored, and record them as the pre-restoration sampling days; and select k4 days after starting to use submerged plants to restore the lake area to be restored, and record them as the post-restoration sampling days, where k4 is the set number of days; in this embodiment, k4=7;

[0059] Step S104: Take any pre-revision sampling date or post-revision sampling date as the first sampling date, and record any sampling time point on the first sampling date as the first time point;

[0060] Step S105: At the first time point, collect the values ​​of each water quality parameter from each sampling depth at each sampling location, and for each water quality parameter, calculate the average value at the same sampling depth at different sampling locations; obtain the average data of each water quality parameter at different sampling depths at the first sampling time point, and record it as the water quality sampling information at the first time point; repeatedly obtain the water quality sampling information at all sampling time points on the first sampling day to obtain the water quality sampling data for the first sampling day; the calculation of the average value can smooth out outliers and improve data stability and comparability;

[0061] Step S106: Repeat the acquisition of water quality sampling data for all pre-revision sampling days and record it as the original water quality data; and repeat the acquisition of water quality sampling data for all post-revision sampling days and record it as the initial water quality data.

[0062] In the specific implementation process, the selected k4 days must ensure good weather conditions, without rainfall or other severe weather, because rainfall and other severe weather can cause sudden and drastic fluctuations in water quality parameters. For example, rainfall washes away the surface and carries suspended matter such as mud, sand, dead branches and leaves into the water body, causing a sharp drop in transparency; this will lead to data distortion, and the collected data cannot represent the state of the water body.

[0063] Step S2 involves performing correlation analysis based on the original water quality data and initial water quality data to obtain relevant water quality physicochemical indicators. Step S2 includes the following sub-steps:

[0064] Step S201: For any water quality parameter, it is denoted as the first water quality parameter; the first water quality parameters in the original water quality data that are located on different pre-revision sampling days, at the same sampling time point, and at the same sampling depth are sorted in chronological order and denoted as the original parameter sequence.

[0065] Step S202: Record any original water quality parameter sequence as the first parameter sequence; calculate the average value from the k5th percentile to the k6th percentile of the first parameter sequence, and record it as the reference water quality data for the sampling time point and the water depth collected corresponding to the first parameter sequence; where k5 and k6 are set percentiles; in this embodiment, k5=20, k6=80; the percentile average value can eliminate extreme value interference and improve the robustness of the reference data;

[0066] Step S203: Sort the first water quality parameters in the initial water quality data that are located on different post-sampling days, at the same sampling time point, and at the same sampling depth in chronological order, and record them as the initial parameter sequence.

[0067] Step S204, and denote any initial parameter sequence as the second parameter sequence; calculate the average value from the k5th percentile to the k6th percentile of the second parameter sequence, and denote it as the initial water quality data of the sampling time point and the water depth collected corresponding to the second parameter sequence;

[0068] Step S205: Repeatedly acquire reference water quality data and initial water quality data for the first water quality parameter at all sampling time points and at the sampling water depth;

[0069] Step S206: For the first water quality parameter, calculate the absolute value of the difference between all reference water quality data and initial water quality data located at the same sampling time point and sampling depth, and record it as the absolute difference. Obtain the largest and second largest absolute difference, and record them as the maximum difference and the second largest difference, respectively. The reference water quality data is the data before remediation, and the initial water quality data is the data at the beginning of the remediation. The difference between the two reflects the response intensity of the water quality parameter to the remediation by submerged plants, that is, the correlation between the water quality parameter and submerged plants. Obtaining the maximum and second largest differences is to avoid screening anomalies caused by single data anomalies, and helps to screen the key water quality parameters that are truly related to the remediation of submerged plants.

[0070] Step S207: Mark the sampling time point and sampling water depth corresponding to the maximum difference as the optimal sampling time and optimal sampling water depth of the first water quality parameter, respectively; determine the spatiotemporal point where the change of each water quality parameter is most obvious, provide a reference for subsequent sampling, and improve the accuracy of sampling; and obtain the specific data of the first water quality parameter with the optimal sampling time and optimal sampling water depth on all pre-revision sampling days, and calculate the average, which is recorded as the pre-revision reference average of the first water quality parameter.

[0071] Step S208: Repeatedly obtain the maximum and second largest differences of all water quality parameters, and obtain the corresponding optimal sampling time, optimal sampling water depth, and pre-revision reference average.

[0072] Step S209: Arrange all the largest and second largest differences in descending order, and denote them as the first difference sequence and the second difference sequence, respectively. Use density clustering algorithm to divide all the first difference sequences and the second difference sequences into k7 difference clusters, and denote them as the first difference cluster 1-k7 and the second difference cluster 1-k7, respectively, according to the corresponding differences in ascending order, where k7 is the set number; in this embodiment, k7 is 5, and k7 can be set according to the actual application scenario;

[0073] Step S210: For the first water quality parameter, the difference clusters to which the largest and second largest differences of the first water quality parameter belong are sequentially denoted as the first difference cluster n1 and the second difference cluster n2, respectively; n1+n2 is marked as the correlation score of the first water quality parameter; for example, the largest difference of the first water quality parameter belongs to the corresponding first difference cluster 5, and the second largest difference belongs to the corresponding first difference cluster 4; then the correlation score of the first water quality parameter is 5+4=9;

[0074] Step S211: Repeatedly obtain the relevant scores of all water quality parameters, and mark the k8 water quality parameters whose change direction of the difference conforms to the ecological role of submerged plants and whose relevant scores are the largest as relevant water quality physicochemical indicators, where k8 is the number set; in this embodiment, k8=3, and k8 can be set according to the actual application scenario, generally 2-5; the change direction conforms to the ecological role of submerged plants means that the change trend of water quality parameters is consistent with the expected role of submerged plants; for example, after the restoration is started using submerged plants, the concentration of total phosphorus and total nitrogen in the water should decrease, dissolved oxygen should increase, and turbidity should decrease, etc.

[0075] In practice, conventional water quality monitoring involves more than 20 parameters. If all of them are included in the analysis, it will lead to data redundancy, and the repetitive information will increase storage and computing costs, thus increasing the complexity of the analysis. However, by using mathematical statistics and cluster analysis from a large amount of water quality data, the key indicators that have been significantly changed due to the restoration of submerged plants can be identified. This not only eliminates the interference of "natural fluctuations" or "random changes", but also provides a data focus for subsequent plant monitoring and restoration effectiveness evaluation, thereby reducing data dimensions and focusing on core data.

[0076] Step S3 involves collecting relevant water quality physicochemical data for the lake area to be restored, analyzing changes in water quality physicochemical properties, and obtaining data on related plant changes. Step S3 includes the following sub-steps:

[0077] Step S301: For any relevant water quality physicochemical index, it is denoted as the first water quality index; the optimal collection time and optimal collection water depth corresponding to the first water quality index are denoted as the first collection time and the first collection water depth, respectively; the spatiotemporal window in which the parameter is most sensitive to the response of submerged plants is locked, reducing unnecessary multiple samplings and only acquiring data for key locations.

[0078] Step S302: Collect specific data of the first water quality index from the first water depth at all collection locations at the first collection time each day, and calculate the average value of the specific data collected from all collection locations, which is recorded as the representative value of the first water quality index. At the same time, record the weather conditions and rainfall of each day, which are recorded as the water quality index data of the first water quality index. Rainfall and other severe weather may distort the water quality data. Recording this information can help remove invalid data in subsequent analysis.

[0079] Step S303: Repeatedly acquire water quality index data of all relevant water quality physicochemical indicators to obtain water quality physicochemical data;

[0080] Step S304: Record any date with zero rainfall and good weather conditions as a useful day, and record any useful day in the water quality physicochemical data as the first day; exclude severe external disturbances such as rainfall to ensure that the monitored water quality changes mainly originate from the growth of submerged plants; ensure the comparability and accuracy of subsequent analyses;

[0081] Step S305: Obtain the representative value of the first water quality index on the first day, denoted as the first representative value DA; and obtain the representative value of the first water quality index for each useful day in the k9 days prior to the first day, denoted as the useful representative value; obtain the useful representative value that is closest to the first day in terms of time distance, denoted as DB; and calculate the average value of all useful representative values, denoted as DP; where k9 is the set number of days; in this embodiment, k9=7, if there is rainfall in the k9 days prior to the first day, the first day will be excluded, and the situation of the first day will be invalidally analyzed;

[0082] Step S306: Record the pre-revision reference average corresponding to the first water quality indicator as BP; calculate the parameter change index of the first water quality indicator on the first day according to the first formula, wherein the first formula is as follows: Where BW represents the parameter change index, u represents the correlation between the first water quality index and submerged plants. If the magnitude of the first water quality index is positively correlated with the amount of submerged plants, then u=1; otherwise, u=-1. This ensures that the signs are consistent when summarizing the changes of each index in the future. DA-DB1 can capture sudden changes in recent times, and DP reflects the cyclical change level of the first water quality index during the growth period of submerged plants. The comparison of different time scales can distinguish between instantaneous fluctuations and persistent effects, enhancing the robustness of the analysis.

[0083] Step S307: Repeatedly obtain the parameter change indicators of all relevant water quality physicochemical indicators on the first day;

[0084] For step S308, please refer to... Figure 3 As shown, select a point on the two-dimensional plane as the origin of the coordinate system, and draw k8 number axes in a counterclockwise direction starting from the origin of the coordinate system. The rotation angle between any two adjacent number axes is (360 / k8)°. Then, map the k8 number axes to k8 related water quality physicochemical indicators.

[0085] Step S309: The number axis corresponding to the first water quality index is denoted as the first index number axis. The parameter change index of the first water quality index is uniformly depicted on the first index number axis by a unit length. The position of the parameter change index of the first water quality index on the first index number axis is obtained and denoted as the change index point.

[0086] Step S310: Repeatedly obtain all relevant water quality physicochemical indicators on the corresponding number axis, and connect all the indicator points in a counterclockwise direction. The enclosed area is recorded as the indicator area. Obtain the area of ​​the indicator area and record it as the relevant area indicator for the first day. The area of ​​the indicator area in the same coordinate system will clearly present the values ​​of the multi-dimensional indicators. It can not only intuitively compare the relative strength and overall distribution of each indicator, but also quickly reflect the comprehensive performance of the ecological restoration of submerged plants, and thus reflect the development of submerged plants.

[0087] Step S311: Repeatedly acquire the relevant area indicators for each useful day to obtain plant-related change data;

[0088] In the specific implementation process, the parameter change index reflects the relative change of the first water quality index due to the action of submerged plants; while the area of ​​the change index region is a measure of the relative change of all relevant water quality physicochemical indicators. Its size comprehensively quantifies the "overall intensity" of the changes of each indicator. The larger the area, the more significant the overall effect of submerged plant ecological restoration, that is, the better the submerged plants are developing; the smaller the area, the weaker the overall effect of submerged plant ecological restoration, that is, the worse the submerged plants are developing.

[0089] Step S4 involves collecting relevant water quality physicochemical data for the lake area to be restored, analyzing changes in water quality physicochemical properties, and obtaining data on related plant changes. Step S4 includes the following sub-steps:

[0090] For step S401, please refer to... Figure 3 As shown, for the current date, the relevant area indicators of the x1 most useful days with the closest time distance are obtained according to the time distance, and are recorded as the reference area indicators; where x1 is the set number of days, and in this embodiment x1=5;

[0091] Step S402: Perform linear regression fitting on all reference area indicators to obtain the changing trend of the reference area indicators. The changing trend includes increasing, decreasing and basically unchanged; that is, perform linear regression fitting on the area indicators for this x1 day to obtain the trend slope and its direction.

[0092] Step S403: If the trend of the reference area index is increasing, that is, the effect of submerged plant ecological restoration is getting stronger; then mark the submerged plant development in the lake area to be restored as good. If the trend of the reference area index is decreasing, that is, the effect of submerged plant ecological restoration is getting weaker; then mark the submerged plant development in the lake area to be restored as declining. If the trend of the reference area index is basically unchanged, that is, the effect of submerged plant ecological restoration is basically unchanged; then mark the submerged plant development in the lake area to be restored as average.

[0093] In the specific implementation process, when the reference area index continues to increase, it means that the key water quality parameters are evolving in a direction that is conducive to the restoration of aquatic ecosystems. That is, the ecological restoration effect of submerged plants is becoming stronger and stronger. In essence, it is the result of the continuous strengthening of ecological functions driven by their healthy development and the positive feedback of the system, which indicates that the submerged plants are developing well.

[0094] Example 2, please refer to Figure 4 As shown, Figure 4 A schematic diagram of an electronic device is provided, which may include a processor, a communication interface, a memory, and a communication bus. The processor, communication interface, and memory communicate with each other via the communication bus. The memory stores computer-readable instructions, and the processor can call these instructions. When the processor executes a computer-readable instruction, it performs steps similar to those in a big data-based lake aquatic ecosystem restoration monitoring method to achieve the following functions: collecting raw water quality data of the lake area to be restored before the use of submerged plants for restoration, and collecting initial water quality data after the start of restoration using submerged plants; performing correlation analysis based on the raw and initial water quality data to obtain relevant water quality physicochemical indicators; collecting water quality physicochemical data of relevant indicators of the lake area to be restored, and performing water quality physicochemical change analysis to obtain plant-related change data; and monitoring and analyzing the submerged plants in the lake area to be restored based on the plant-related change data to obtain relevant change information of the submerged plants.

[0095] Furthermore, when the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0096] Example 3: This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it performs the steps of the above-mentioned big data-based lake water ecological restoration monitoring method to achieve the following functions: collecting original water quality data of the lake area to be restored before restoration using submerged plants, and collecting initial water quality data after restoration using submerged plants begins; performing correlation analysis based on the original water quality data and the initial water quality data to obtain relevant water quality physicochemical indicators; collecting water quality physicochemical data of relevant water quality physicochemical indicators of the lake area to be restored, and performing water quality physicochemical change analysis to obtain plant-related change data; monitoring and analyzing the submerged plants in the lake area to be restored based on the plant-related change data to obtain relevant change information of submerged plants.

[0097] Based on the above description of the embodiments, the embodiments of the present invention can be provided as methods, systems, or computer program products. Based on this understanding, the above technical solutions, in essence or in terms of their contribution to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or certain parts of the embodiments.

[0098] In the embodiments provided in this application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division, and there may be other division methods in actual implementation. Furthermore, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces. The indirect coupling or communication connection between systems, modules, and units may be electrical, mechanical, or other forms.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A lake water ecological restoration monitoring method based on big data, characterized in that, Includes the following steps: Collect raw water quality data of the lake area to be restored before the use of submerged plants for restoration, and collect initial water quality data after the use of submerged plants for restoration begins; Correlation analysis was performed on the raw water quality data and the initial water quality data to obtain relevant water quality physicochemical indicators. Collect relevant water quality physicochemical data of the lake area to be restored, and conduct water quality physicochemical change analysis to obtain plant-related change data; Based on data on plant-related changes, we monitored and analyzed the submerged plants in the lake area to be restored, and obtained information on the relevant changes of the submerged plants. Correlation analysis was performed on the raw and initial water quality data to obtain relevant water quality physicochemical indicators, including the following sub-steps: Any water quality parameter is denoted as the first water quality parameter; the first water quality parameters in the original water quality data that are located on different pre-revision sampling days, at the same sampling time point, and at the same sampling depth are sorted in chronological order and denoted as the original parameter sequence; any original water quality parameter sequence is denoted as the first parameter sequence; the average value from the k5th percentile to the k6th percentile of the first parameter sequence is calculated and denoted as the reference water quality data for the sampling time point and sampling depth corresponding to the first parameter sequence; where k5 and k6 are the set percentiles; The first water quality parameter in the initial water quality data that is located on different post-sampling days, at the same sampling time point, and at the same sampling depth is sorted in chronological order and recorded as the initial parameter sequence. And denote any initial parameter sequence as the second parameter sequence; calculate the average value from the k5th percentile to the k6th percentile of the second parameter sequence, and denote it as the initial water quality data of the sampling time point and the water depth collected for the second parameter sequence; Repeatedly acquire reference water quality data and initial water quality data for the first water quality parameter at all sampling time points and at the sampling depth; For the first water quality parameter, calculate the absolute value of the difference between the reference water quality data and the initial water quality data at all sampling time points and sampling depths, and record it as the absolute difference. Obtain the largest and second largest absolute differences, and record them as the maximum difference and the second largest difference, respectively. Mark the sampling time point and sampling depth corresponding to the maximum difference as the optimal sampling time and optimal sampling depth of the first water quality parameter, respectively. Obtain the specific data of the first water quality parameter at the optimal sampling time and optimal sampling depth for all sampling days before the revision, and calculate the average, which is recorded as the pre-revision reference average of the first water quality parameter. Repeatedly obtain the maximum and second largest differences of all water quality parameters, and obtain the corresponding optimal sampling time, optimal sampling water depth, and pre-revision reference average. Arrange all the largest and second largest differences in descending order, and denote them as the first difference sequence and the second difference sequence, respectively. Use density clustering algorithm to divide all the first difference sequences and the second difference sequences into k7 difference clusters, and denote them as the first difference cluster 1-k7 and the second difference cluster 1-k7, respectively, according to the corresponding differences in ascending order, where k7 is the set number. For the first water quality parameter, the difference clusters to which the largest and second largest differences belong are respectively denoted as the first difference cluster n1 and the second difference cluster n2; n1+n2 is marked as the relevant score of the first water quality parameter; Repeatedly obtain the relevant scores of all water quality parameters, and mark the k8 water quality parameters whose difference changes in the direction of the ecological function of submerged plants and whose relevant scores are the largest as relevant water quality physicochemical indicators, where k8 is the number set. Collect relevant water quality physicochemical data for the lake area to be restored, and analyze the changes in water quality physicochemical properties to obtain data on plant-related changes. This includes the following sub-steps: For any relevant water quality physicochemical index, it is denoted as the first water quality index; the optimal sampling time and optimal sampling depth corresponding to the first water quality index are respectively denoted as the first sampling time and the first sampling depth. At the first collection time each day, specific data of the first water quality index were collected from the first water depth at all collection locations, and the average value of the specific data collected from all collection locations was calculated and recorded as the representative value of the first water quality index. At the same time, the weather conditions and rainfall of each day were recorded and recorded as the water quality index data of the first water quality index. Repeatedly acquire water quality index data for all relevant water quality physicochemical indicators to obtain water quality physicochemical data; Record any date with zero rainfall and good weather conditions as a useful day, and record any useful diary entry from the water quality physicochemical data as the first day. Obtain the representative value of the first water quality indicator on the first day, denoted as the first representative value DA; obtain the representative value of the first water quality indicator for each useful day in the k9 days prior to the first day, denoted as the useful representative value; obtain the useful representative value that is closest to the first day in terms of time distance, denoted as DB; and calculate the average of all useful representative values, denoted as DP; where k9 is the set number of days. The pre-revision reference average corresponding to the first water quality indicator is denoted as BP; the parameter change index of the first water quality indicator on the first day is calculated according to the first formula, where the first formula is as follows: Where BW represents the parameter change index, and u represents the correlation between the first water quality index and submerged plants. If the magnitude of the first water quality index is positively correlated with the amount of submerged plants, then u=1; otherwise, u=-1. Repeatedly obtain the parameter changes of all relevant water quality physicochemical indicators on the first day.

2. The lake water ecological restoration monitoring method based on big data according to claim 1, characterized in that, Collecting raw water quality data of the lake area to be restored before the use of submerged plants for restoration, and collecting initial water quality data after the start of restoration using submerged plants, includes the following sub-steps: For the water body area in the lake that needs to be restored, it is denoted as the lake area to be restored; the average depth of the lake area to be restored is obtained and denoted as DE1; the maximum height of the submerged plants used to restore the lake area to be restored is obtained and denoted as DL1; k1 points are uniformly selected from [0, DE1-DL1] and denoted as the water depth collected by k1-k1 according to their size; where k1 is the number of points set. Within a day, k2 sampling time points are set, denoted as sampling time points 1-k2; and k3 sampling locations are selected from the lake area to be restored; where k2 and k3 are the number of sampling locations set; water quality parameters related to submerged plants are obtained from the database, denoted as water quality parameters 1-n; Before using submerged plants for restoration in lake areas, k4 days are selected and recorded as the pre-restoration sampling day; For the lake area to be restored, k4 days were selected after the start of restoration using submerged plants, and this was recorded as the post-restoration sampling day, where k4 is the set number of days.

3. The lake water ecological restoration monitoring method based on big data according to claim 2, characterized in that, Collecting raw water quality data of the lake area to be restored before the use of submerged plants for restoration, and collecting initial water quality data after the start of restoration using submerged plants, also includes the following sub-steps: Take any pre-revision sampling date or post-revision sampling log as the first sampling date, and record any sampling time point on the first sampling date as the first time point; The values ​​of each water quality parameter were collected from each sampling depth at each sampling location at the first time point, and for each water quality parameter, the average value of the same sampling depth at different sampling locations was calculated. The average data of each water quality parameter at different sampling depths at the first sampling time point are obtained and recorded as the water quality sampling information at the first time point; the water quality sampling information at all sampling time points on the first sampling day is repeatedly obtained to obtain the water quality sampling data for the first sampling day; Repeatedly acquire water quality sampling data for all pre-revision sampling days and record them as raw water quality data; and repeatedly acquire water quality sampling data for all post-revision sampling days and record them as initial water quality data.

4. The lake water ecological restoration monitoring method based on big data according to claim 3, characterized in that, Collecting relevant water quality physicochemical data for the lake area to be restored, and analyzing changes in water quality physicochemical properties to obtain data on plant-related changes, also includes the following sub-steps: Select a point on the two-dimensional plane as the origin of the coordinate system, and draw k8 number axes in a counterclockwise direction starting from the origin of the coordinate system. The rotation angle between any two adjacent number axes is (360 / k8)°. Then, map the k8 number axes to k8 relevant water quality physicochemical indicators. The number axis corresponding to the first water quality index is denoted as the first index number axis, and the parameter change index based on the first water quality index is uniformly depicted on the first index number axis by a unit length. And obtain the position of the parameter change index of the first water quality index on the first index number axis, and record it as the change index point; Repeatedly obtain all relevant water quality physicochemical indicators on the corresponding number axis, connect all the indicator points in a counterclockwise direction, and record the enclosed area as the indicator area. Obtain the area size of the indicator area and record it as the relevant area indicator for the first day. The relevant area indicators for each useful day were repeatedly obtained to obtain plant-related change data.

5. The lake water ecological restoration monitoring method based on big data according to claim 4, characterized in that, Based on data on changes in plant-related changes, monitoring and analysis of submerged plants in the lake area to be restored were conducted. The relevant changes in submerged plants were obtained through the following sub-steps: For the current date, obtain the relevant area indicators of the x1 most useful days in time distance according to the time distance, and record them as reference area indicators; perform linear fitting on all reference area indicators to obtain the changing trend of the reference area indicators, and the changing trend includes increasing, decreasing and basically unchanged; Where x1 is the set number of days; If the trend of the reference area index is increasing, the submerged plants in the lake area to be restored are considered to be developing well; if the trend of the reference area index is decreasing, the submerged plants in the lake area to be restored are considered to be developing poorly; if the trend of the reference area index is basically unchanged, the submerged plants in the lake area to be restored are considered to be developing moderately.

Images