Blue-green algae bloom early warning method, device, storage medium and system

Abstract

The invention relates to a cyanobacterial bloom early warning method and device, a storage medium and a system.The cyanobacterial bloom early warning method comprises the steps that a plurality of monitoring nodes are arranged on a target water surface, monitoring data including optical image data and spectral data are collected through monitoring equipment of all the monitoring nodes, and image features of cyanobacterial bloom are extracted from the optical image data; according to the method, the spectral features of the cyanobacterial bloom are extracted from the spectral data, the image features and the spectral features are input into the pre-trained cyanobacterial bloom early warning model, the cyanobacterial bloom occurrence probability is obtained, and when the cyanobacterial bloom occurrence probability is larger than the target threshold value, early warning information can be sent to the terminal in time, so that the timeliness and accuracy of cyanobacterial bloom early warning are improved.

Description

Technical Field

[0001] The present invention relates to the field of water quality early warning, and in particular to a cyanobacteria bloom early warning method, device, storage medium and system. Background Art

[0002] A cyanobacterial bloom is a massive growth of blue-green algae that forms a foul-smelling blue-green foam on the water surface. It is a typical phenomenon of eutrophication and seriously affects water quality and ecological balance. In recent years, with climate change and intensified human activities, cyanobacterial blooms have become more frequent on large bodies of water, posing a serious threat to the ecological environment, agricultural production, and human health.

[0003] The traditional method for predicting cyanobacterial blooms is to collect water quality data from a certain area and use this data to predict the probability of cyanobacterial blooms on a large water surface. However, the above method has a limited monitoring range and poor prediction accuracy. Summary of the Invention

[0004] The embodiments of the present application provide a cyanobacteria bloom early warning method, device, storage medium and system, which can improve the accuracy of cyanobacteria bloom early warning.

[0005] In a first aspect, an embodiment of the present application provides a cyanobacteria bloom early warning method, the method being applied to a control center, the control center being communicatively connected to at least one monitoring device and at least one terminal, wherein a monitoring device is provided at a monitoring node on a target water surface, including:

[0006] Receiving monitoring data of the monitoring node collected by the at least one monitoring device; the monitoring data includes: optical image data and spectral data;

[0007] extracting image features of the cyanobacteria bloom from the optical image data, and extracting spectral features of the cyanobacteria bloom from the spectral data;

[0008] Inputting the image features and the spectral features into a pre-trained cyanobacteria bloom early warning model to obtain a probability of cyanobacteria bloom occurrence;

[0009] If the probability of occurrence of the cyanobacteria bloom is greater than a target threshold, an early warning message is sent to the at least one terminal.

[0010] In a second aspect, an embodiment of the present application provides a cyanobacteria bloom early warning device, which is applied to a control center. The control center is respectively connected to at least one monitoring device and at least one terminal. A monitoring device is set at a monitoring node on the target water surface. The device includes:

[0011] A monitoring data receiving module, configured to receive monitoring data of the monitoring node collected by the at least one monitoring device; the monitoring data includes: optical image data and spectral data;

[0012] a feature extraction module, configured to extract image features of the cyanobacteria bloom from the optical image data, and extract spectral features of the cyanobacteria bloom from the spectral data;

[0013] a cyanobacteria bloom warning module, configured to input the image features and the spectral features into a pre-trained cyanobacteria bloom warning model to obtain a probability of occurrence of cyanobacteria bloom;

[0014] The warning information sending module is used to send a warning message to the at least one terminal if the probability of the occurrence of the cyanobacteria bloom is greater than a target threshold.

[0015] In a third aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the cyanobacteria bloom early warning method as described in any one of the above.

[0016] In a fourth aspect, an embodiment of the present application provides a cyanobacteria bloom early warning system, comprising a control center, at least one monitoring device, and at least one terminal; the control center is communicatively connected to the at least one monitoring device and the at least one terminal, respectively, and one monitoring device is set at a monitoring node on the target water surface;

[0017] The control center is used to execute any one of the above-mentioned cyanobacteria bloom early warning methods.

[0018] In an embodiment of the present application, multiple monitoring nodes are set up on the target water surface, and monitoring data including optical image data and spectral data are collected by monitoring equipment at each monitoring node. Image features of cyanobacterial blooms are extracted from the optical image data, and spectral features of cyanobacterial blooms are extracted from the spectral data. The image features and the spectral features are input into a pre-trained cyanobacterial bloom early warning model to obtain the probability of cyanobacterial bloom occurrence. When the probability of cyanobacterial bloom occurrence is greater than the target threshold, an early warning message can be sent to the terminal in a timely manner, thereby improving the timeliness and accuracy of the cyanobacterial bloom early warning.

[0019] For better understanding and implementation, the present invention is described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a schematic diagram of an application scenario of a cyanobacteria bloom early warning method according to an embodiment of the present invention;

[0021] Figure 2 This is a flow chart of a cyanobacteria bloom early warning method according to one embodiment of the present invention;

[0022] Figure 3 This is a flow chart of a cyanobacteria bloom early warning method according to another embodiment of the present invention;

[0023] Figure 4 Flowchart of step S220 in one embodiment of the present invention;

[0024] Figure 5 Flowchart of step S140 in one embodiment of the present invention;

[0025] Figure 6 This is a flow chart of a cyanobacteria bloom early warning method according to another embodiment of the present invention;

[0026] Figure 7 This is a schematic structural diagram of a cyanobacteria bloom early warning device according to an embodiment of the present invention;

[0027] Figure 8 The figure is a schematic structural diagram of a cyanobacteria bloom early warning system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to make the objectives, technical solutions and advantages of the present application clearer, the embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

[0029] It should be clear that the embodiments described are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the embodiments of the present application.

[0030] The terms used in the embodiments of the present application are for the purpose of describing specific embodiments only and are not intended to limit the embodiments of the present application. The singular forms "a," "the," and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0031] When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims. In the description of the present application, it should be understood that the terms "first", "second", "third", etc. are only used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence, nor can they be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances.

[0032] In addition, in this application, unless otherwise specified, "several" refers to two or more. "And / or" describes a corresponding relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, or B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0033] See also Figure 1 , which is a schematic diagram of an application scenario of a cyanobacteria bloom early warning method provided by an embodiment of the present application. The method is applied to a control center 111, and the control center 111 is connected to at least one monitoring device 112 and at least one terminal 113 respectively. A monitoring device 112 is set at a monitoring node on the target water surface.

[0034] Monitoring nodes can be distributed across multiple different areas of the target water surface. The target water surface can be a user-defined area that needs to be monitored for the risk of cyanobacterial blooms. Monitoring nodes can be determined based on historical cyanobacterial blooms, or representative key areas determined by the water surface's geographic characteristics, water flow direction, and other factors.

[0035] In an embodiment of the present application, the monitoring nodes may include nodes that can cover different areas of the target water surface, such as nearshore, lake center, and water flow intersection points. By setting monitoring nodes in multiple different areas of the target water surface, it is ensured that comprehensive water surface information can be obtained and the accuracy of cyanobacteria bloom warning can be improved.

[0036] The control center 111 may include at least one high-performance server. The high-performance server may store data processing software, and the data processing software is used to process the monitoring data returned by each monitoring node.

[0037] The monitoring device 112 is used to detect the water surface of the monitoring node. The monitoring device 112 may include a multispectral camera, a hyperspectral camera, or other devices that can be used to collect optical image data and spectral data.

[0038] The terminal 113 is used to receive the warning information sent by the control center 111. The terminal 113 can be used by departments related to blue algae bloom control, such as environmental protection departments, water conservancy departments, fishery departments, staff or the public.

[0039] See also Figure 2 , the embodiment of the present application provides a cyanobacteria bloom early warning method, comprising:

[0040] S110: Receive monitoring data of the monitoring node collected by the at least one monitoring device; the monitoring data includes: optical image data and spectral data;

[0041] Optical image data can include visible light images and near-infrared images. Visible light images and near-infrared images can reflect the color, texture, and transparency of the water surface. By analyzing the color differences and texture changes in optical image data, the occurrence area and extent of cyanobacteria blooms can be preliminarily determined.

[0042] Spectral data, including spectral reflectance curves, can be analyzed to identify the characteristic absorption and reflectance peaks of cyanobacteria, accurately determining their species and concentration. Spectral data can also be used to infer parameters such as chlorophyll content and nutrient concentration in water bodies, providing more comprehensive information for early warning of cyanobacterial blooms.

[0043] S120: extracting image features of the cyanobacteria bloom from the optical image data, and extracting spectral features of the cyanobacteria bloom from the spectral data;

[0044] Image features can include color, texture, shape, and other features. Image features can be extracted using methods such as color histograms, gray-level co-occurrence matrices, and edge detection. By analyzing image features, the occurrence area and extent of cyanobacterial blooms can be preliminarily determined.

[0045] The color histogram describes the color distribution of an image by counting the number of pixels with different color values in the image.

[0046] The gray-level co-occurrence matrix is a matrix obtained by statistically analyzing the situation in which two pixels in an image that maintain a certain distance have a certain gray level.

[0047] Edge detection is used to identify areas of image brightness that vary significantly, thereby extracting important image features. Edge detection can include algorithms such as first-order differential operators, second-order differential operators, and Canny edge detection.

[0048] Spectral characteristics can include characteristic absorption peaks, reflection peaks, spectral slopes, etc. By analyzing spectral characteristics, the type and concentration of cyanobacteria can be accurately determined.

[0049] Optionally, the spectral features can be compared with features of a known cyanobacteria spectral library, and spectral features with high correlation with cyanobacteria can be used as spectral features input into the cyanobacteria bloom warning model, thereby further improving the accuracy of cyanobacteria warning.

[0050] S130: Inputting the image features and the spectral features into a pre-trained cyanobacteria bloom warning model to obtain a probability of cyanobacteria bloom occurrence;

[0051] The cyanobacteria bloom warning model can be built using decision trees, random forests, neural networks, or other machine learning algorithms with equivalent functionality. After constructing the cyanobacteria bloom warning model, it is pre-trained using pre-collected historical monitoring data and measured cyanobacteria bloom data to ensure that the pre-trained cyanobacteria bloom warning model achieves the target accuracy.

[0052] The target accuracy can be set according to actual application requirements.

[0053] S140: If the probability of occurrence of the cyanobacteria bloom is greater than a target threshold, sending a warning message to the at least one terminal;

[0054] The target threshold can be set specifically based on the impact of cyanobacterial blooms on the water environment and ecosystem in the area.

[0055] For example, when the cyanobacteria bloom has a greater impact on the local water environment and ecosystem, the target threshold can be set to a lower value, so that early warning information can be issued in advance, allowing personnel from relevant departments such as environmental protection, water conservancy, and fisheries to adopt physical methods such as salvaging cyanobacteria and shading, chemical methods such as the introduction of pesticides, and biological methods such as the introduction of filter-feeding fish to reduce the reproduction rate and number of cyanobacteria and improve the efficiency of cyanobacteria bloom control.

[0056] Early warning information is used to alert monitoring nodes of the risk of cyanobacteria bloom, so that relevant personnel can take corresponding preventive measures in time to stop the occurrence of cyanobacteria bloom at the monitoring nodes and improve the water quality of the monitoring nodes.

[0057] Optionally, the probability of occurrence of cyanobacteria bloom is less than or equal to the target threshold, indicating that there is no cyanobacteria bloom at the monitoring node or the cyanobacteria bloom is of low hazard. In this case, there is no need to send warning information to at least one terminal, thus saving resources.

[0058] In an embodiment of the present application, multiple monitoring nodes are set up on the target water surface, and monitoring data including optical image data and spectral data are collected by monitoring equipment at each monitoring node. Image features of cyanobacterial blooms are extracted from the optical image data, and spectral features of cyanobacterial blooms are extracted from the spectral data. The image features and the spectral features are input into a pre-trained cyanobacterial bloom early warning model to obtain the probability of cyanobacterial bloom occurrence. When the probability of cyanobacterial bloom occurrence is greater than the target threshold, an early warning message can be sent to the terminal in a timely manner, thereby improving the timeliness and accuracy of the cyanobacterial bloom early warning.

[0059] In step S110 , the monitoring device 112 may include a low-altitude aircraft equipped with a multispectral camera, a hyperspectral camera, and a laser radar; the low-altitude aircraft is connected to the control center via wireless communication technology.

[0060] Low-altitude aircraft can fly according to the flight path sent by the control center and collect monitoring data corresponding to the monitoring parameters sent by the control center. The monitoring parameters are used to determine the monitoring data that needs to be collected.

[0061] In one embodiment, the low-altitude aircraft is a drone or an unmanned airship.

[0062] The embodiment of the present application can use drones to collect monitoring data. Compared with traditional monitoring methods, using drones to monitor data and network has the advantages of low cost and high efficiency, which can effectively reduce the cost of cyanobacteria bloom warning.

[0063] The control center can adjust the flight path of low-altitude aircraft and the monitoring data to be collected as needed to adapt to monitoring needs in different situations.

[0064] Multispectral cameras, hyperspectral cameras and lidar can be used to obtain optical image data, spectral data and three-dimensional terrain data of the water surface at the monitoring node.

[0065] The monitoring equipment can communicate with the monitoring equipment of other monitoring nodes and the control center through common wireless communication technologies such as 5G.

[0066] Optionally, when the number of monitoring nodes on the target water surface is small and the distribution of the monitoring nodes is relatively concentrated, the monitoring equipment can adopt a star topology structure, determine one of the monitoring nodes as the central node, and perform data aggregation and forwarding with the central node as the core.

[0067] When the number of monitoring nodes on the target water surface is large and their distribution is relatively scattered, a mesh topology or a hybrid topology can be used to improve the reliability and fault tolerance of communication between nodes.

[0068] like Figure 3 As shown, in one embodiment, after receiving the monitoring data of the water surface of the monitoring node collected by the monitoring equipment, the method further includes:

[0069] S210: Converting the monitoring data into data in a target format;

[0070] The target format can be determined based on the format of data that can be processed by the data processing software of the control center. By converting the monitoring data into data in the target format that can be processed by the data processing software, the data processing software can denoise and calibrate the data in the target format, thereby improving data processing efficiency.

[0071] S220: De-noising and calibrating the data in the target format.

[0072] Specifically, the accuracy and consistency of the data can be ensured by calibrating the optical image data, and the optical image data and spectral data can be filtered to remove noise.

[0073] In the embodiment of the present application, by converting the monitoring data into data in a target format that can be processed by the data processing software, the data processing software can denoise and calibrate the data in the target format, thereby improving the data processing efficiency and the accuracy of the cyanobacteria bloom warning.

[0074] like Figure 4 As shown, in one embodiment, denoising and calibrating the data in the target format includes:

[0075] S221: performing filtering, radiation calibration, and geometric calibration on the optical image data;

[0076] Specifically, for optical image data, noise in the optical image data can be removed by filtering methods such as median filtering and mean filtering.

[0077] Median filtering replaces the value of a certain point in a digital image or digital sequence with the median of the values of all points in the neighborhood of that point, thereby eliminating isolated noise points and making the surrounding pixel values closer to the true value.

[0078] Mean filtering replaces the original value of a pixel with the average value of the pixel values in its neighborhood, thereby achieving the purpose of smoothing the image.

[0079] Radiometric calibration is used to adjust and correct radiometric data to eliminate interference from sensor characteristics and atmospheric influences. Specifically, atmospheric radiation transfer models can be used to remove atmospheric influences from remote sensing data.

[0080] During the acquisition process of remote sensing images, geometric distortion can occur due to various factors, such as sensor attitude changes, Earth curvature, terrain fluctuations, and platform motion. This can cause the pixel positions on the image to be inconsistent with the actual surface locations. Geometric calibration corrects the geometric distortion of remote sensing images so that the geometry of the remote sensing image is consistent with the geometry of the actual surface.

[0081] Specifically, correction models such as polynomial correction model, affine transformation model, and perspective transformation model can be used. By selecting control points with known geographic coordinates on the image, and establishing a correspondence between these control points and the corresponding image pixel coordinates, the parameters of the correction model are solved using methods such as the least squares method; then, according to the obtained correction model parameters, the entire image is geometrically transformed, and the position of each pixel is mapped to the correct geographic coordinate position; finally, the transformed image is resampled to generate a geometrically calibrated image.

[0082] S222: Filtering the spectral data.

[0083] Spectral data can be smoothed using a Savitzky-Golay filter. The Savitzky-Golay filter is a digital filter based on local polynomial regression and widely used in signal processing. It uses a linear least squares method to fit a low-order polynomial to the data points in a sliding window, reducing noise while preserving key signal features, such as peaks and valleys.

[0084] In the embodiment of the present application, the optical image data is filtered, the radiation calibration and the geometric calibration are performed, and the spectral data is filtered to ensure the accuracy of the monitoring data and improve the accuracy of the cyanobacteria bloom warning.

[0085] In step S140, at least one terminal may include a terminal used by departments related to blue algae bloom control, such as environmental protection departments, water conservancy departments, and fishery departments, staff, or the public. The terminal includes but is not limited to mobile phones, computers, servers, and other communication devices with communication functions.

[0086] like Figure 5 As shown, in one embodiment, sending warning information to the at least one terminal includes:

[0087] S141: Determining a warning level corresponding to the probability of occurrence of the cyanobacteria bloom based on preset warning level information;

[0088] The warning level information may include multiple cyanobacteria bloom probability ranges and multiple warning levels, and one cyanobacteria bloom probability range may correspond to one warning level.

[0089] In the embodiment of the present application, the warning levels may include a first warning level, a second warning level, and a third warning level. The first warning level is the highest warning level, indicating that a cyanobacterial bloom is imminent and poses a high degree of hazard. The second warning level indicates that a cyanobacterial bloom is likely to occur and poses a medium degree of hazard. The third warning level indicates that a cyanobacterial bloom is likely to occur and poses a low degree of hazard. The probability range of a cyanobacterial bloom corresponding to the first warning level is greater than the probability range of a cyanobacterial bloom corresponding to the second warning level, and the probability range of a cyanobacterial bloom corresponding to the second warning level is greater than the probability range of a cyanobacterial bloom corresponding to the third warning level.

[0090] The probability range of cyanobacterial blooms and the distribution of warning levels can be set according to the actual situation and degree of harm of cyanobacterial blooms in the area.

[0091] S142: Determine the terminal to which the warning information needs to be sent according to the warning level, and send the warning information to the terminal to which the warning information needs to be sent.

[0092] Different terminals can be used to send warning messages to different warning levels. Warning messages can be sent to the corresponding terminals via SMS, email, app message, or website message, allowing them to be promptly communicated to relevant departments and the public, buying valuable time for prevention and control measures for cyanobacteria blooms and reducing their harmful effects.

[0093] In an embodiment of the present application, the warning level corresponding to the probability of occurrence of cyanobacteria bloom is determined based on preset warning level information, and the terminal to which the warning information needs to be sent is determined according to different warning levels, so as to facilitate the provision of warnings to personnel in different departments, and then facilitate relevant personnel to take corresponding measures to intervene in the cyanobacteria bloom at the monitoring node and reduce the harmfulness of the cyanobacteria bloom.

[0094] like Figure 6 As shown, in one embodiment, before inputting the image features and the spectral features into the pre-trained cyanobacteria bloom warning model, the method further includes:

[0095] S310: constructing the cyanobacteria bloom early warning model based on a decision tree algorithm, obtaining historical monitoring data and measured cyanobacteria bloom data, and determining a training set based on the historical monitoring data and measured cyanobacteria bloom data;

[0096] S320: Pre-training the cyanobacteria bloom warning model based on a cross-validation method and the training set.

[0097] Cross-validation involves dividing a dataset into multiple subsets and then performing multiple training and testing cycles using different subset combinations to comprehensively evaluate model performance. Common cross-validation methods include K-fold cross-validation and leave-one-out cross-validation.

[0098] Taking K-fold cross-validation as an example, K-fold cross-validation involves randomly splitting the entire dataset into K equally sized subsets, called "folds." K iterations are then performed. In each iteration, one subset is selected as the validation set, and the remaining K-1 subsets are combined as the training set to train the model. In each iteration, the model is trained using the training set, and then the selected validation set is used to evaluate the model's performance, such as calculating accuracy and precision. The evaluation results from these K iterations are averaged to obtain a final estimate of the model's performance.

[0099] In the embodiment of the present application, the cyanobacteria bloom warning model is pre-trained by using a training set and a cross-validation method, so that the cyanobacteria bloom warning model can meet the target accuracy requirements and improve the accuracy of the cyanobacteria bloom warning model warning.

[0100] like Figure 7As shown, an embodiment of the present application further provides a cyanobacteria bloom early warning device, which is applied to a control center. The control center is respectively connected to at least one monitoring device and at least one terminal. A monitoring device is set at a monitoring node on the target water surface. The device includes:

[0101] The monitoring data receiving module 210 is configured to receive monitoring data of the monitoring node collected by the at least one monitoring device; the monitoring data includes: optical image data and spectral data;

[0102] a feature extraction module 220 for extracting image features of the cyanobacteria bloom from the optical image data and extracting spectral features of the cyanobacteria bloom from the spectral data;

[0103] a cyanobacteria bloom warning module 230 for inputting the image features and the spectral features into a pre-trained cyanobacteria bloom warning model to obtain a probability of occurrence of cyanobacteria bloom;

[0104] The warning information sending module 240 is configured to send a warning message to the at least one terminal if the probability of occurrence of the cyanobacteria bloom is greater than a target threshold.

[0105] In one embodiment, the warning information sending module 240 includes:

[0106] an early warning level determination unit, configured to determine an early warning level corresponding to the probability of occurrence of the cyanobacteria bloom based on preset early warning level information;

[0107] The warning information sending unit is used to determine the terminal to which the warning information needs to be sent according to the warning level, and send the warning information to the terminal to which the warning information needs to be sent.

[0108] In one embodiment, the apparatus further comprises:

[0109] a training set determination module, configured to construct the cyanobacteria bloom early warning model based on a decision tree algorithm, obtain historical monitoring data and measured cyanobacteria bloom data, and determine a training set based on the historical monitoring data and measured cyanobacteria bloom data;

[0110] A pre-training module is used to pre-train the cyanobacteria bloom early warning model based on a cross-validation method and the training set.

[0111] In one embodiment, the monitoring device includes a low-altitude aircraft equipped with a multispectral camera, a hyperspectral camera, and a lidar.

[0112] In one embodiment, the low-altitude aircraft is a drone or an unmanned airship.

[0113] In one embodiment, the apparatus further comprises:

[0114] A format conversion module, used to convert the monitoring data into data in a target format;

[0115] The data processing module is used to perform denoising and calibration on the data in the target format.

[0116] In one embodiment, the data processing module includes:

[0117] an optical image data processing unit, configured to perform filtering, radiation calibration, and geometric calibration on the optical image data;

[0118] The spectral data processing unit is used to filter the spectral data.

[0119] It should be noted that the cyanobacteria bloom early warning device provided in the above embodiment, when implementing the cyanobacteria bloom early warning method, is merely illustrated by the division of the aforementioned functional modules. In actual applications, the aforementioned functions can be assigned to different functional modules as needed, i.e., the internal structure of the device can be divided into different functional modules to perform all or part of the functions described above. Furthermore, the cyanobacteria bloom early warning device provided in the above embodiment and the cyanobacteria bloom early warning method provided in the above embodiment are based on the same concept. The implementation process is detailed in the method embodiments and will not be further described here.

[0120] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the cyanobacteria bloom early warning method as described in any one of the above are implemented.

[0121] The embodiments of the present application may take the form of a computer program product implemented on one or more storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing program code. Computer-readable storage media include permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs or other data. Examples of computer storage media include but are not limited to: phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0122] like Figure 8As shown, the embodiment of the present application further provides a cyanobacteria bloom early warning system 300, comprising a control center 311, at least one monitoring device 312, and at least one terminal 313; the control center 311 is respectively in communication with the at least one monitoring device 312 and the at least one terminal 313, and one monitoring device is set at a monitoring node on the target water surface;

[0123] The control center 311 is used to execute any of the above-mentioned cyanobacteria bloom early warning methods.

[0124] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0125] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A cyanobacteria bloom early warning method, characterized in that: The method is applied to a control center, wherein the control center is respectively connected to at least one monitoring device and at least one terminal, wherein one monitoring device is set at a monitoring node of a target water surface, and comprises: Receiving monitoring data of the monitoring node collected by the at least one monitoring device; the monitoring data includes: optical image data and spectral data; extracting image features of the cyanobacteria bloom from the optical image data, and extracting spectral features of the cyanobacteria bloom from the spectral data; Inputting the image features and the spectral features into a pre-trained cyanobacteria bloom early warning model to obtain a probability of cyanobacteria bloom occurrence; If the probability of occurrence of the cyanobacteria bloom is greater than a target threshold, an early warning message is sent to the at least one terminal.

2. The cyanobacteria bloom early warning method according to claim 1, characterized in that: Sending warning information to the at least one terminal includes: Determining a warning level corresponding to the probability of occurrence of the cyanobacteria bloom based on preset warning level information; The terminal to which the warning information needs to be sent is determined according to the warning level, and the warning information is sent to the terminal to which the warning information needs to be sent.

3. The cyanobacteria bloom early warning method according to claim 1, characterized in that: Before inputting the image features and the spectral features into the pre-trained cyanobacteria bloom warning model, the method further includes: Constructing the cyanobacteria bloom early warning model based on a decision tree algorithm, obtaining historical monitoring data and measured cyanobacteria bloom data, and determining a training set based on the historical monitoring data and measured cyanobacteria bloom data; The cyanobacteria bloom warning model is pre-trained based on a cross-validation method and the training set.

4. The cyanobacteria bloom early warning method according to claim 1, characterized in that: The monitoring equipment includes a low-altitude aircraft equipped with a multispectral camera, a hyperspectral camera and a laser radar.

5. The cyanobacteria bloom early warning method according to claim 4, characterized in that: The low-altitude aircraft is a drone or an unmanned airship.

6. The cyanobacteria bloom early warning method according to claim 1, characterized in that: After receiving the monitoring data of the water surface of the monitoring node collected by the at least one monitoring device, the method further includes: Converting the monitoring data into data in a target format; The data in the target format is denoised and calibrated.

7. The cyanobacteria bloom early warning method according to claim 6, characterized in that: Denoising and calibrating the data in the target format, including: performing filtering, radiometric calibration, and geometric calibration on the optical image data; The spectral data is filtered.

8. A cyanobacteria bloom early warning device, characterized in that: Applied to a control center, the control center is respectively connected to at least one monitoring device and at least one terminal, one monitoring device is set at a monitoring node of a target water surface, and the device includes: A monitoring data receiving module, configured to receive monitoring data of the monitoring node collected by the at least one monitoring device; the monitoring data includes: optical image data and spectral data; a feature extraction module, configured to extract image features of the cyanobacteria bloom from the optical image data, and extract spectral features of the cyanobacteria bloom from the spectral data; a cyanobacteria bloom warning module, configured to input the image features and the spectral features into a pre-trained cyanobacteria bloom warning model to obtain a probability of occurrence of cyanobacteria bloom; The warning information sending module is used to send a warning message to the at least one terminal if the probability of the occurrence of the cyanobacteria bloom is greater than a target threshold.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the cyanobacteria bloom early warning method according to any one of claims 1 to 7 are implemented.

10. A cyanobacteria bloom early warning system, characterized in that: It includes a control center, at least one monitoring device and at least one terminal; the control center is respectively connected to the at least one monitoring device and the at least one terminal in communication, and one monitoring device is set at a monitoring node on the target water surface; The control center is used to execute the cyanobacteria bloom early warning method according to any one of claims 1 to 7.

Images