Water bloom early warning method based on water body chlorophyll concentration and algae activity

Abstract

The invention relates to a water bloom early warning method based on water body chlorophyll a concentration and algae activity, which comprises the following steps: collecting and processing algae growth data of a target area water body to obtain the chlorophyll a concentration and algae photosynthetic activity index data of the target area water body; performing algal bloom risk grading according to the chlorophyll a concentration of the water body in the target area and the algae photosynthetic activity index data; analyzing each water bloom risk level weight based on a historical water bloom occurrence condition in a target time period corresponding to the target area; constructing a data set based on historical water quality data, historical meteorological data and each water bloom risk grade weight in a target time period corresponding to the target area; training an artificial neural network by using the data set to obtain a water bloom early warning data model; and performing target area water bloom early warning by using the water bloom early warning data model. According to the invention, the water bloom early warning accuracy can be improved, and the water bloom early warning in a real sense is realized.

Description

Technical Field

[0001] The invention relates to the technical field of water bloom early warning, and in particular to a water bloom early warning method based on chlorophyll a concentration and algae activity in water bodies. Background Art

[0002] Algal bloom refers to the phenomenon that in freshwater or seawater environments, due to excessive input of nutrients (such as nitrogen and phosphorus), algae and other phytoplankton grow and reproduce rapidly, eventually forming a large number of algae aggregations floating on the water surface. The large-scale reproduction of algae will consume the dissolved oxygen in the water, causing hypoxia in the water body, and harmful substances such as hydrogen sulfide will be produced during the death and decomposition of algae, further deteriorating the water quality. In addition, large-scale algal blooms in the basin will block sunlight, affect the photosynthesis of underwater plants, cause the death of aquatic plants, further change the transparency and temperature of the water body, and affect the living environment of other aquatic organisms. In addition, some algae (such as cyanobacteria) will produce toxins, such as microcystins and neurotoxins. Algal bloom toxins accumulate through the food chain, which may affect humans and other higher organisms and pose a threat to human health. The algal bloom problem not only affects fishery production, causing fish deaths or quality decline, but also increases the cost of drinking water treatment, and even directly affects the healthy and sustainable development of the local tourism industry. In recent years, my country's five major freshwater lakes have paid close attention to the problem of algal blooms. Therefore, in the face of the harm caused to aquatic ecosystems and human health by algal blooms, it is very important to detect and warn of algal blooms.

[0003] At present, early warning of algal blooms is one of the important means to prevent and control algal bloom pollution. It can detect the early signs of algal blooms in advance and take corresponding measures in advance to reduce the impact of algal blooms on water bodies and ecosystems. Common methods of early warning of algal blooms mainly use water quality monitoring data to analyze the external growth environment of algae, such as statistical analysis of nutrients (such as ammonia nitrogen, total phosphorus), chlorophyll a, pH value, water temperature and other indicators in water bodies, and identify the pattern of algal blooms and predict future trends based on machine learning models (such as support vector machines, random forests, neural networks, etc.), but lack integrated analysis of the internal core indicators of the growth status of algae themselves. Summary of the invention

[0004] Based on this, the first purpose of the present invention is to provide an algal bloom warning method based on the chlorophyll a concentration and algal activity of the water body, using chlorophyll a concentration and algae photosynthetic activity indicators to replace the algal biomass and algae growth status of the water body respectively, and presetting the training data weight coefficient based on the core indicators of algae growth, and combining water quality and meteorological historical data to train the algal bloom warning model, identify the probability of algal bloom occurrence and predict future trends.

[0005] To achieve the above object, the present invention adopts the following technical solutions:

[0006] The present invention provides a water bloom early warning method based on chlorophyll a concentration and algae activity in water bodies, which comprises the following steps:

[0007] S1. Collecting and processing algae growth data of the target area water body to obtain chlorophyll a concentration and algae photosynthetic activity index data of the target area water body;

[0008] S2. Classifying the risk level of algal bloom according to the chlorophyll a concentration of the water body in the target area and the photosynthetic activity index data of the algae;

[0009] S3. Analyze the weight of each algal bloom risk level based on the historical algal bloom occurrence in the target time period corresponding to the target area;

[0010] S4. Construct a data set based on historical water quality data, historical meteorological data and weights of each algal bloom risk level within the target time period corresponding to the target area;

[0011] S5. Using the data set to train an artificial neural network to obtain an algae bloom warning data model;

[0012] S6. Use the algal bloom warning data model to carry out early warning of algal bloom in the target area.

[0013] As a further improvement of the above solution of the present invention, the specific steps of step S1 are:

[0014] S11. using laser induced fluorescence spectroscopy to obtain the fluorescence spectrum and fluorescence kinetic curve of the water body in the target area;

[0015] S12. Obtaining the chlorophyll a concentration of the water body in the target area based on the fluorescence spectrum inversion of the water body in the target area;

[0016] S13. Obtaining the algae photosynthetic activity index data of the water body in the target area based on the fluorescence kinetic curve inversion of the water body in the target area.

[0017] As a further improvement of the above solution of the present invention, the inversion method of the chlorophyll a concentration of the water body in the target area includes:

[0018] S121. Prepare multiple chlorophyll a solutions with gradient concentrations;

[0019] S122. Obtaining the fluorescence spectrum of each of the chlorophyll a solutions using laser induced fluorescence spectroscopy;

[0020] S123. Linearly fitting the fluorescence intensity and concentration of the fluorescence spectra of each of the chlorophyll a solutions to establish a functional relationship between the fluorescence intensity and the chlorophyll a concentration;

[0021] S124. Based on the functional relationship and in combination with the fluorescence intensity of the fluorescence spectrum of the water body in the target area, the chlorophyll a concentration of the water body in the target area is obtained.

[0022] As a further improvement of the above solution of the present invention, the inversion method of the algae photosynthetic activity index data of the target area water body includes:

[0023] S131. Prepare multiple chlorophyll a solutions with gradient concentrations;

[0024] S132. Using a pulse modulated fluorescence instrument, the fluorescence kinetic curves of each chlorophyll a solution are obtained;

[0025] S133. Calculate the minimum fluorescence Fo and the maximum fluorescence Fm of the fluorescence kinetic curve of each chlorophyll a solution, and calculate the algae photosynthetic activity index data of each chlorophyll a solution according to the formula Fv / Fm=(Fm-Fo) / Fm;

[0026] S134. Acquire the algae photosynthetic activity index data of the water body in the target area according to the fluorescence kinetic curve of the water body in the target area and in combination with the algae photosynthetic activity index data of each of the chlorophyll a solutions.

[0027] As a further improvement of the above solution of the present invention, the specific steps of step S2 are:

[0028] Chlorophyll a concentration threshold and photosynthetic activity index data threshold are preset, and the bloom risk level is divided according to the following standards:

[0029] High risk level: The chlorophyll a concentration in the target area water body is greater than the chlorophyll a concentration threshold, and the algae photosynthetic activity index data is greater than or equal to the photosynthetic activity index data threshold;

[0030] Low risk level: The chlorophyll a concentration in the target area water body is ≤ the chlorophyll a concentration threshold, and the algae photosynthetic activity index data is ≥ the photosynthetic activity index data threshold;

[0031] Potential risks: The chlorophyll a concentration in the target area water body is greater than the chlorophyll a concentration threshold, or the algae photosynthetic activity index data is greater than or equal to the photosynthetic activity index data threshold.

[0032] As a further improvement of the above solution of the present invention, the preset chlorophyll a concentration threshold is set to 10 ug / L, and the photosynthetic activity index data threshold is set to 0.4.

[0033] As a further improvement of the above solution of the present invention, the specific steps of step S3 are:

[0034] S31. Obtain historical water quality data and historical meteorological data within the target time period corresponding to the target area;

[0035] S32. Analyze and calculate the probability of occurrence of water blooms corresponding to each water bloom risk level according to the historical occurrence of water blooms in the target area;

[0036] S33. Calculate the variance explanation rate corresponding to each algal bloom risk level using principal component analysis;

[0037] S34. The ratio of the variance explanation rate corresponding to each algal bloom risk level to the total variance explanation rate is used as the weight of the corresponding algal bloom risk level.

[0038] As a further improvement of the above scheme of the present invention, the specific steps of step S6 are: using the algal bloom warning data model in combination with core algae risk indicators, water quality indicators and meteorological indicators to conduct early warning of algal blooms in the target area water body, and output an algal bloom warning signal.

[0039] The second object of the present invention is to provide an electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein when the processor executes the computer program, the steps of the water bloom warning method based on chlorophyll a concentration and algae activity in the water body are implemented as described above.

[0040] The third object of the present invention is to provide a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, it implements the steps of the water bloom warning method based on chlorophyll a concentration and algae activity in the water body as described above.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] 1. The present invention first obtains the chlorophyll a concentration and algae photosynthetic activity index data of the target area water body, and replaces the algae biomass and algae growth status of the water body with the chlorophyll a concentration and algae photosynthetic activity index of the target area water body, respectively, and evaluates the risk level of water bloom in multiple dimensions according to the chlorophyll a concentration and algae photosynthetic activity index data of the target area water body, and presets the training data weight coefficient based on the algae growth core index judgment, and trains the water bloom early warning model in combination with historical water quality data and historical meteorological data to identify the probability of water bloom and predict future trends. The present invention fully integrates the internal cause index of algae growth status, and takes into account the conventional water quality meteorological index data set by presetting the weight. Compared with the previous water bloom early warning scheme, the present invention can improve the accuracy of water bloom early warning and realize the real early warning of water bloom.

[0043] 2. The water bloom early warning method based on chlorophyll a and algae activity in water bodies of the present invention integrates the core indicator parameters of the algae growth status, and presets the weights of the training data through multi-level judgment, thereby avoiding the interference of the algae's own growth status factors and improving the stability and accuracy of the water bloom prediction method.

[0044] 3. The water bloom early warning method based on chlorophyll a and algae activity in water bodies of the present invention can improve the quality of the later training data set and thus improve the prediction accuracy by preprocessing the monitoring data through primary and secondary classification and multi-level judgment. By presetting the weight information of the main factors, more feature information is provided to help the model capture more complex feature relationships.

[0045] 4. The water bloom early warning method for chlorophyll a and algae activity in water bodies of the present invention, combined with related equipment for online algae monitoring, can be flexibly applied to the field of water bloom monitoring and has a good practical prospect. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 The present invention provides a flowchart of a water bloom early warning method based on chlorophyll a concentration and algae activity in water bodies. DETAILED DESCRIPTION

[0047] For ease of understanding of the present invention, the present invention will be described more fully below in conjunction with specific embodiments. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thoroughly understood.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0049] Combination Figure 1 This embodiment proposes a water bloom early warning method based on chlorophyll a concentration and algae activity in water bodies, which includes the following six steps S1-S6.

[0050] S1. Collect and process algae growth data of the target area water body to obtain chlorophyll a concentration and algae photosynthetic activity index data of the target area water body.

[0051] In this embodiment, step S1 mainly includes the following three steps S11-S13.

[0052] S11. Collect water samples from the target area, and use laser induced fluorescence spectroscopy technology to obtain the fluorescence spectrum and fluorescence kinetic curve of the water in the target area.

[0053] S12. Obtain the chlorophyll a concentration of the water body in the target area based on the fluorescence spectrum inversion of the water body in the target area. In this embodiment, the inversion method of the chlorophyll a concentration of the water body in the target area mainly includes the following four steps S121-S124.

[0054] S121. Prepare multiple chlorophyll a solutions with gradient concentrations;

[0055] S122. Obtaining the fluorescence spectrum of each of the chlorophyll a solutions using laser induced fluorescence spectroscopy;

[0056] S123. Linearly fitting the fluorescence intensity and concentration of the fluorescence spectra of each of the chlorophyll a solutions to establish a functional relationship between the fluorescence intensity and the chlorophyll a concentration;

[0057] S124. Based on the functional relationship and in combination with the fluorescence intensity of the fluorescence spectrum of the water body in the target area, the chlorophyll a concentration of the water body in the target area is obtained.

[0058] S13. Obtaining the algae photosynthetic activity index data of the target area water body based on the fluorescence kinetic curve inversion of the target area water body. In this embodiment, the inversion method of the algae photosynthetic activity index data of the target area water body mainly includes the following four steps S131-S134.

[0059] S131. Prepare multiple chlorophyll a solutions with gradient concentrations;

[0060] S132. Using a pulse modulated fluorescence instrument, the fluorescence kinetic curves of each chlorophyll a solution are obtained;

[0061] S133. Calculate the minimum fluorescence Fo and the maximum fluorescence Fm of the fluorescence kinetic curve of each chlorophyll a solution, and calculate the algae photosynthetic activity index data of each chlorophyll a solution according to the formula Fv / Fm=(Fm-Fo) / Fm;

[0062] S134. Acquire the algae photosynthetic activity index data of the water body in the target area according to the fluorescence kinetic curve of the water body in the target area and in combination with the algae photosynthetic activity index data of each of the chlorophyll a solutions.

[0063] S2. Classifying the risk level of algal bloom according to the chlorophyll a concentration of the water body in the target area and the algae photosynthetic activity index data.

[0064] In this embodiment, the method for classifying the risk levels of algal blooms is as follows:

[0065] Chlorophyll a concentration threshold and photosynthetic activity index data threshold are preset, and the bloom risk level is divided according to the following standards:

[0066] High risk level: The chlorophyll a concentration in the target area water body is greater than the chlorophyll a concentration threshold, and the algae photosynthetic activity index data is greater than or equal to the photosynthetic activity index data threshold;

[0067] Low risk level: The chlorophyll a concentration in the target area water body is ≤ the chlorophyll a concentration threshold, and the algae photosynthetic activity index data is ≥ the photosynthetic activity index data threshold;

[0068] Potential risks: The chlorophyll a concentration in the target area water body is greater than the chlorophyll a concentration threshold, or the algae photosynthetic activity index data is greater than or equal to the photosynthetic activity index data threshold.

[0069] In this embodiment, the preset chlorophyll a concentration threshold is set to 10 ug / L, and the photosynthetic activity index data threshold is set to 0.4.

[0070] S3. Analyze the weights of each algal bloom risk level based on the historical algal bloom occurrences in the target time period corresponding to the target area.

[0071] In this embodiment, the water bloom risk level weight analysis method mainly includes the following four steps S31-S34:

[0072] S31. According to the water quality automatic monitoring cycle, obtain the historical water quality data and historical meteorological data within the target time period corresponding to the target area;

[0073] S32. Analyze and count the occurrence probabilities of water blooms corresponding to the above three water bloom risk levels according to the historical water bloom occurrence in the target area;

[0074] S33. Calculate the variance explanation rate corresponding to the above three algal bloom risk levels using principal component analysis;

[0075] S34. The ratio of the variance explanation rate corresponding to the above three algal bloom risk levels to the total variance explanation rate is used as the weight of the corresponding algal bloom risk level.

[0076] Principal component analysis (PCA) is a statistical analysis algorithm that can perform dimensionality reduction analysis for a large amount of data, and finally retain the main factors. The factor cumulative variance explanation rate is generally acceptable when it exceeds 60%, and then the minor factors are discarded to achieve the screening of the main influencing factors. Principal component analysis can be analyzed with the help of SPSS software, and dimensionality reduction processing is performed by entering statistical data to obtain variance explanation rate and total variance explanation rate. In the present embodiment, the total variance explanation rate is the sum of the variance explanation rates corresponding to the three types of algal bloom risk levels.

[0077] S4. Construct a data set based on the historical water quality data, historical meteorological data and weights of each algal bloom risk level within the target time period corresponding to the target area.

[0078] S5. Using the data set to train an artificial neural network to obtain an algal bloom warning data model.

[0079] S6. Use the algal bloom warning data model and combine the core algae risk indicators, water quality indicators and meteorological indicators to warn of algal blooms in the target area water body, and output an algal bloom warning signal.

[0080] This embodiment is based on the water body chlorophyll a and algae activity water bloom early warning method, integrates the core indicator parameters of the algae growth status, and presets the weight of the training data through multi-level judgment, avoiding the interference of the algae's own growth status factors, and improving the stability and accuracy of the water bloom prediction method.

[0081] Based on the above-mentioned water body chlorophyll a concentration and algae activity based water body water bloom early warning method, this embodiment further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. When the processor executes the computer program, the steps of the above-mentioned water body chlorophyll a concentration and algae activity based water body water bloom early warning method are implemented.

[0082] Based on the above-mentioned water body chlorophyll a concentration and algae activity based water body water bloom early warning method, this embodiment further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the above-mentioned water body chlorophyll a concentration and algae activity based water body water bloom early warning method are implemented.

[0083] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0084] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A water bloom early warning method based on chlorophyll a concentration and algae activity in water, characterized in that: It includes the following steps: S1. Collecting and processing algae growth data of the target area water body to obtain chlorophyll a concentration and algae photosynthetic activity index data of the target area water body; S2. Classifying the risk level of algal bloom according to the chlorophyll a concentration of the water body in the target area and the photosynthetic activity index data of the algae; S3. Analyze the weight of each algal bloom risk level based on the historical algal bloom occurrence in the target time period corresponding to the target area; S4. Construct a data set based on historical water quality data, historical meteorological data and weights of each algal bloom risk level within the target time period corresponding to the target area; S5. Using the data set to train an artificial neural network to obtain an algae bloom warning data model; S6. Use the algal bloom warning data model to carry out early warning of algal bloom in the target area.

2. The water bloom early warning method based on chlorophyll a concentration and algae activity in water according to claim 1, characterized in that: The specific steps of step S1 are: S11. using laser induced fluorescence spectroscopy to obtain the fluorescence spectrum and fluorescence kinetic curve of the water body in the target area; S12. Obtaining the chlorophyll a concentration of the water body in the target area based on the fluorescence spectrum inversion of the water body in the target area; S13. Obtaining the algae photosynthetic activity index data of the water body in the target area based on the fluorescence kinetic curve inversion of the water body in the target area.

3. The water bloom early warning method based on chlorophyll a concentration and algae activity in water according to claim 2, characterized in that: The inversion method of the chlorophyll a concentration of the water body in the target area includes: S121. Prepare multiple chlorophyll a solutions with gradient concentrations; S122. Obtaining the fluorescence spectrum of each of the chlorophyll a solutions using laser induced fluorescence spectroscopy; S123. Linearly fitting the fluorescence intensity and concentration of the fluorescence spectra of each of the chlorophyll a solutions to establish a functional relationship between the fluorescence intensity and the chlorophyll a concentration; S124. Based on the functional relationship and in combination with the fluorescence intensity of the fluorescence spectrum of the water body in the target area, the chlorophyll a concentration of the water body in the target area is obtained.

4. The water bloom early warning method based on chlorophyll a concentration and algae activity in water according to claim 2, characterized in that: The inversion method of the algae photosynthetic activity index data of the target area water body includes: S131. Prepare multiple chlorophyll a solutions with gradient concentrations; S132. Using a pulse modulated fluorescence instrument to obtain the fluorescence kinetic curve of each chlorophyll a solution; S133. Calculate the minimum fluorescence Fo and the maximum fluorescence Fm of the fluorescence kinetic curve of each chlorophyll a solution, and calculate the algae photosynthetic activity index data of each chlorophyll a solution according to the formula Fv / Fm=(Fm-Fo) / Fm; S134. Acquire the algae photosynthetic activity index data of the water body in the target area according to the fluorescence kinetic curve of the water body in the target area and in combination with the algae photosynthetic activity index data of each of the chlorophyll a solutions.

5. The water bloom early warning method based on chlorophyll a concentration and algae activity in water according to claim 1, characterized in that: The specific steps of step S2 are: Chlorophyll a concentration threshold and photosynthetic activity index data threshold are preset, and the bloom risk level is divided according to the following standards: High risk level: Chlorophyll a concentration in the target area water body is greater than the chlorophyll a concentration threshold, and the algae photosynthetic activity index data is greater than or equal to the photosynthetic activity index data threshold; Low risk level: The chlorophyll a concentration in the target area water body is ≤ the chlorophyll a concentration threshold, and the algae photosynthetic activity index data is ≥ the photosynthetic activity index data threshold; Potential risks: The chlorophyll a concentration in the target area water body is greater than the chlorophyll a concentration threshold, or the algae photosynthetic activity index data is greater than or equal to the photosynthetic activity index data threshold.

6. The water bloom early warning method based on chlorophyll a concentration and algae activity in water according to claim 5, characterized in that: The preset chlorophyll a concentration threshold is set to 10ug / L, and the photosynthetic activity index data threshold is set to 0.

4.

7. The water bloom early warning method based on chlorophyll a concentration and algae activity in water according to claim 1, characterized in that: The specific steps of step S3 are: S31. Obtain historical water quality data and historical meteorological data within the target time period corresponding to the target area; S32. Analyze and calculate the probability of occurrence of water blooms corresponding to each water bloom risk level according to the historical occurrence of water blooms in the target area; S33. Calculate the variance explanation rate corresponding to each algal bloom risk level using principal component analysis; S34. The ratio of the variance explanation rate corresponding to each algal bloom risk level to the total variance explanation rate is used as the weight of the corresponding algal bloom risk level.

8. The water bloom early warning method based on chlorophyll a concentration and algae activity in water according to claim 1, characterized in that: The specific steps of step S6 are: using the algal bloom warning data model and combining core algae risk indicators, water quality indicators and meteorological indicators to conduct early warning of algal blooms in the target area water body, and output an algal bloom warning signal.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: When the processor executes the computer program, the steps of the water bloom early warning method based on chlorophyll a concentration and algae activity in the water body are implemented as described in any one of claims 1 to 8.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the water bloom early warning method based on chlorophyll a concentration and algae activity in water bodies are implemented as described in any one of claims 1 to 8.

Images