CN112986157A - Culture water environment early warning regulation and control method, device and system - Google Patents
Culture water environment early warning regulation and control method, device and system Download PDFInfo
- Publication number
- CN112986157A CN112986157A CN202110194304.6A CN202110194304A CN112986157A CN 112986157 A CN112986157 A CN 112986157A CN 202110194304 A CN202110194304 A CN 202110194304A CN 112986157 A CN112986157 A CN 112986157A
- Authority
- CN
- China
- Prior art keywords
- water environment
- early warning
- water quality
- aquaculture water
- hyperspectral image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/27—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands using photo-electric detection ; circuits for computing concentration
- G01N21/274—Calibration, base line adjustment, drift correction
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N2021/1793—Remote sensing
Abstract
The invention relates to the field of aquaculture water environment regulation, in particular to a method, a device and a system for early warning regulation of aquaculture water environment. The early warning regulation and control method for the aquaculture water environment comprises the following steps: acquiring a hyperspectral image of a specific aquaculture water environment area; selecting sampling points in the specific aquaculture water environment area according to the hyperspectral image, and measuring first water quality parameters on the sampling points; performing inversion on a second water quality parameter of the specific aquaculture water environment area by using the hyperspectral image and the first water quality parameter; and according to the inversion result, early warning is provided for a specific aquaculture water environment area with deteriorated water quality. The invention utilizes the unmanned aerial vehicle hyperspectral remote sensing technology to invert water quality parameters through hyperspectral images and combines a conventional method to sample the water quality parameters, opens up a new way for aquaculture water environment water quality monitoring and aquaculture water environment regulation and control, and is also beneficial to the protection of aquaculture water environment in freshwater fishery.
Description
The application claims priority of Chinese patent application with the name of 'a cultivation water environment early warning regulation and control method, device and system' filed by the Chinese patent office with the application number of 202011534129.2 on 23/12/2020, the entire contents of which are incorporated in the application by reference.
Technical Field
The invention relates to the field of aquaculture water environment regulation and control, in particular to a method, a device and a system for early warning regulation and control of aquaculture water environment
Background
The total yield of aquatic product cultivation in 2018 exceeds 5000 ten thousand tons, which accounts for more than 78% of the total yield of aquatic product cultivation in China. However, the freshwater aquaculture industry also currently faces a number of problems and challenges. For example, the cultivation form mainly comprises scattered household continuous sheet cultivation, and the problems of relatively extensive cultivation mode, excessive cultivation density and the like exist, so that on one hand, the water quality of the cultivation pond is deteriorated, and diseases of cultivation objects are frequently caused; on the other hand, a large amount of residual baits and excreta of aquatic animals are directly discharged into the natural water body without treatment, so that the eutrophication of the culture area and the surrounding water body is increased day by day, great pressure is caused to the ecological environment, and the residual baits and the excreta of the aquatic animals become important limiting factors for restricting the healthy and sustainable development of the freshwater aquaculture industry. Therefore, the method is very important for timely and accurately regulating and controlling the water environment of the pond, and more attracts attention of farmers.
In addition, the water environment is not well controlled, so that the accumulation of toxic and harmful substances such as nitrogen, phosphorus, algae, organic matters and the like is easily caused, the quality and the yield of the cultured objects are finally reduced, and further serious economic loss is caused. And for well regulating water quality, various parameters of the water environment, which mainly comprise indexes such as ammonia nitrogen, nitrate nitrogen, dominant algae, microbial quantity, suspended matters, total nitrogen, total phosphorus and the like, must be known first, and the regulation of the parameters is the key for obtaining greater economic benefit and environmental benefit. At present, a conventional water quality monitoring method is adopted for small-scale and distributed aquaculture water environment areas in China, namely, the specific aquaculture water environment areas are regularly and fixedly sampled and monitored for years and months, the method is limited by manpower, material resources, time and weather, and the collected data volume cannot be too much; but also has the defects of high cost, low speed and the like; and for the whole aquaculture water environment area, the measuring point data only have local and typical representative meanings, the water quality parameter distribution and change conditions of a large-range freshwater aquaculture water environment area are difficult to obtain, and the large-scale real-time monitoring requirements for the water quality of the aquaculture water environment area cannot be met. Therefore, an effective means for monitoring the dynamic change of the water quality of the aquaculture water environment area in real time and rapidly and adopting a corresponding regulation and control method is urgently needed.
Disclosure of Invention
In view of the defects of the prior art, the present application aims to provide a method, a device and a system for early warning regulation and control of aquaculture water environment, and aims to solve at least one problem existing in the prior art.
In a first aspect, the invention provides a culture water environment early warning regulation and control method, which comprises the following steps: acquiring a hyperspectral image of a specific aquaculture water environment area; selecting sampling points in the specific aquaculture water environment area according to the hyperspectral image, and measuring first water quality parameters on the sampling points; performing inversion on a second water quality parameter of the specific aquaculture water environment area by using the hyperspectral image and the first water quality parameter; and according to the inversion result, early warning is provided for a specific aquaculture water environment area with deteriorated water quality. The unmanned aerial vehicle hyperspectral remote sensing technology has the characteristics of wide monitoring range, high speed and low cost, and has the advantage of dynamically monitoring the water environment of the aquaculture pond for a long time; the invention utilizes the hyperspectral remote sensing technology of the unmanned aerial vehicle to acquire the hyperspectral image and further invert the water quality parameters, and combines the conventional method to sample the water quality parameters, thereby not only greatly improving the monitoring efficiency and reducing the monitoring cost, but also reflecting the characteristics of pollution sources, pollutant migration and the like which are difficult to reveal by the conventional method, opening up a new way for monitoring and controlling the water quality of the aquaculture water environment area, and being beneficial to protecting the aquaculture water environment area in freshwater fishery.
Optionally, the acquiring a hyperspectral image of a specific aquaculture water environment area comprises: providing aerial photographing equipment, wherein the aerial photographing equipment comprises an unmanned aerial vehicle and a spectrometer carried on the unmanned aerial vehicle; and after the unmanned aerial vehicle flies to the upper space of the specific aquaculture water environment area, controlling the spectrometer to acquire the hyperspectral image of the specific aquaculture water environment area. The invention can complete the acquisition of the hyperspectral image by adopting the existing unmanned aerial vehicle and the existing spectrometer on the market, and has the advantages of mature technology and easy realization.
Optionally, the aquaculture water environment early warning regulation and control method further comprises: and preprocessing the hyperspectral image which is acquired. According to the invention, the hyperspectral image is preprocessed, so that the accuracy of the subsequent inversion degree of the second water quality parameter is improved, and the timely and accurate early warning is further ensured.
Optionally, the preprocessing the hyperspectral image that has been acquired includes: performing lens correction on the hyperspectral image; performing black and white frame correction on the hyperspectral image; and performing atmospheric correction on the hyperspectral image. The influence of the internal distortion of the image of the spectrometer caused by built-in push-broom on splicing can be corrected by executing lens correction; the system error of the spectrometer can be reduced by performing black and white frame correction; the influence of factors such as atmosphere and water vapor on the hyperspectral image can be eliminated by executing atmosphere correction.
Optionally, the inverting a second water quality parameter of the specific aquaculture water environment area by using the hyperspectral image and the first water quality parameter comprises: extracting reflectivity values of all wave bands in the hyperspectral image corresponding to the sampling points; performing correlation statistics on a first water quality parameter corresponding to at least one of the wave bands according to the reflectivity values; and completing the inversion of the second water quality parameter by using one or more of a BP model, an RBF neural network model and an SVM model according to the result of the correlation statistics. The method adopts a machine learning technology, selects the optimal water quality parameter inversion model and provides a basis for the inversion of the second water quality parameter.
Optionally, the aquaculture water environment early warning regulation and control method further comprises: and studying and judging the change trend of the water quality in the specific aquaculture water environment area according to the first water quality parameter and the second water quality parameter. According to the invention, by studying and judging the change trend of the water quality in the specific aquaculture water environment area, the conditions that the water quality is possibly deteriorated and the like can be found in time, and a foundation is laid for subsequent timely disposal.
Optionally, the aquaculture water environment early warning regulation and control method further comprises: and regulating and controlling the water quality of the specific aquaculture water environment area according to the change trend. The invention can play a role in early warning regulation, namely can prompt farmers to regulate and control the water environment of culture ponds and the like with poor water quality in time, improve the culture water environment in time, effectively reduce culture risks and effectively avoid serious consequences such as blue-green algae outbreak and the like.
Optionally, the first water quality parameter comprises one or more of TN, ammonia nitrogen, nitrite nitrogen, TP, DP, chlorophyll a, dominant algae, suspended matter, clarity, PH, DO, and microbial count; the second water quality parameters comprise one or more of TN, ammonia nitrogen, nitrate nitrogen, nitrite nitrogen, TP, DP, chlorophyll, suspended matters and transparency. The invention can greatly improve the accuracy of data by collecting and inverting various parameters in the water quality and avoid the occurrence of misjudgment as much as possible.
In a second aspect, the invention provides a culture water environment early warning regulation and control device, which comprises: the system comprises a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are connected with each other, the memory is used for storing a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the steps of the aquaculture water environment early warning regulation and control method in the first aspect of the invention. The aquaculture water environment early warning regulation and control device disclosed by the invention inverts water quality parameters through hyperspectral images and samples the water quality parameters by combining a conventional method, so that the monitoring efficiency can be greatly improved, the monitoring cost is reduced, pollution sources and pollutant migration characteristics which are difficult to reveal by the conventional method can be reflected, a new way is developed for aquaculture water environment water quality monitoring and aquaculture water environment regulation and control, and meanwhile, the aquaculture water environment protection of freshwater fishery is facilitated.
In a second aspect, the invention provides a culture water environment early warning regulation and control system, which comprises: the early warning and regulation and control method comprises a breeding water environment early warning and regulation and control device and aerial shooting equipment, wherein the aerial shooting equipment is in communication connection with the breeding water environment early warning and regulation and control device, and the breeding water environment early warning and regulation and control device executes the steps of the breeding water environment early warning and control method in the first aspect of the invention. The early warning regulation and control system for the aquaculture water environment provided by the invention has the advantages of simple system composition, easiness in implementation and the like.
Drawings
FIG. 1 is a flow chart of a culture water environment early warning regulation method in an embodiment of the invention;
FIG. 2A is a hyperspectral image without lens correction according to an embodiment of the invention;
FIG. 2B is a hyperspectral image after lens correction according to an embodiment of the invention;
FIG. 2C is a DN value curve of a hyperspectral image without lens correction according to an embodiment of the invention;
FIG. 2D is a DN value curve of a hyperspectral image after lens correction according to an embodiment of the invention;
FIG. 3A is a DN value curve of a hyperspectral image without black and white frame correction according to an embodiment of the invention;
FIG. 3B is a DN value curve of a reference plate according to an embodiment of the invention;
FIG. 3C is a DN value curve of a dark background according to an embodiment of the invention;
FIG. 3D is a graph of relative reflectance values after black and white frame correction according to an embodiment of the present invention;
FIG. 4 is a spectrum of a plant of an embodiment of the present invention before and after atmospheric calibration;
FIG. 5A is a hyperspectral image before geometric refinement according to an embodiment of the invention;
FIG. 5B is a hyperspectral image after geometric refinement according to an embodiment of the invention;
fig. 6A is a result graph of stitching a plurality of hyperspectral images captured by a first set of unmanned aerial vehicles according to the embodiment of the invention;
fig. 6B is a result graph of stitching a plurality of hyperspectral images captured by a second unmanned aerial vehicle in the embodiment of the invention;
FIG. 7A is a first schematic diagram illustrating a distribution of 10 sampling points according to an embodiment of the present invention;
FIG. 7B is a schematic diagram of a distribution of 10 sampling points according to an embodiment of the present invention;
FIG. 7C is a plot of spectral reflectance of sampling points in Pond of Pond Hongkun, Lujiazhuang, freshwater shrimp, and weever in accordance with an embodiment of the present invention;
FIG. 8 is a correlation coefficient curve of the first water quality parameter and the reflectivity at each sampling point according to the embodiment of the present invention;
FIG. 9A is a graph showing the correlation coefficient distribution of total nitrogen to the ratio of each band in accordance with one embodiment of the present invention;
FIG. 9B is a graph showing the correlation coefficient distribution of the ratio of total phosphorus to each band in the example of the present invention;
FIG. 9C is a graph showing the correlation coefficient distribution of chlorophyll-a ratio to each wavelength band according to the example of the present invention;
FIG. 9D is a diagram showing a correlation coefficient distribution of potassium permanganate index and the ratio of each band in the embodiment of the present invention;
FIG. 10A is a one-dimensional linear regression equation between total nitrogen and ratio index for an embodiment of the present invention;
FIG. 10B is a one-dimensional linear regression equation between total phosphorus and ratio index for an embodiment of the present invention;
FIG. 10C is a one-dimensional linear regression equation between chlorophyll-a and the ratio index for the examples of the present invention;
FIG. 10D is a one-dimensional linear regression equation between potassium permanganate index and ratio index according to an embodiment of the present invention;
FIG. 11A is a schematic diagram of a first frame total nitrogen inversion according to an embodiment of the present invention;
FIG. 11B is a schematic diagram of a first frame total phosphorus inversion according to an embodiment of the present invention;
FIG. 11C is a schematic diagram of a first chlorophyll-a inversion scheme according to an embodiment of the present invention;
FIG. 11D is a schematic diagram of a first frame potassium permanganate index inversion according to an embodiment of the present invention;
FIG. 12A is a schematic diagram of a second frame total nitrogen inversion according to an embodiment of the present invention;
FIG. 12B is a schematic diagram of a second frame total phosphorus inversion according to an embodiment of the present invention;
FIG. 12C is a schematic diagram of a second frame chlorophyll-a inversion according to an embodiment of the present invention;
FIG. 12D is a schematic diagram of a second frame potassium permanganate index inversion according to an embodiment of the present invention;
fig. 13 is an inversion schematic diagram of sampling points of the rujiazhuang aeration tank and the rujiazhuang sedimentation tank in the embodiment of the present invention;
FIG. 14 is an inversion schematic diagram of sampling points of the Rujiazhuang ecological pond and the weever pond according to the embodiment of the invention;
fig. 15 is a schematic diagram of 1:1 of each inverted second water quality parameter and actually measured second water quality parameter of a sampling point according to an embodiment of the present invention.
Detailed Description
To facilitate an understanding of the present application, the present application will now be described more fully with reference to the accompanying drawings. Preferred embodiments of the present application are given in the accompanying drawings. This application may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.
Specific embodiments of the present invention will be described in detail below, and it should be noted that the embodiments described herein are only for illustration and are not intended to limit the present invention. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, it will be apparent to one of ordinary skill in the art that: it is not necessary to employ these specific details to practice the present invention. In other instances, well-known circuits, software, or methods have not been described in detail so as not to obscure the present invention.
Throughout the specification, reference to "one embodiment," "an embodiment," "one example," or "an example" means: the particular features, structures, or characteristics described in connection with the embodiment or example are included in at least one embodiment of the invention. Thus, the appearances of the phrases "in one embodiment," "in an embodiment," "one example" or "an example" in various places throughout this specification are not necessarily all referring to the same embodiment or example. Furthermore, the particular features, structures, or characteristics may be combined in any suitable combination and/or sub-combination in one or more embodiments or examples. Further, those of ordinary skill in the art will appreciate that the illustrations provided herein are for illustrative purposes and are not necessarily drawn to scale.
Referring to fig. 1, an embodiment shown in the invention discloses a cultivation water environment early warning regulation and control method, which comprises the following steps:
and S1, carrying out basic data investigation, and selecting a specific aquaculture water environment area according to the investigation result.
In an alternative embodiment, in order to improve the early warning efficiency, relatively concentrated and connected culture water environment areas can be selected as unmanned aerial vehicle aerial photography areas. Further, the basic data may be obtained by means of, but not limited to, site visits, network questionnaires, etc. to survey the basic data of the area, such as breeding breed, breeding density, feeding level, management method, etc., and in another embodiment or some embodiments, the basic data may be changed according to the actual situation, which is not necessarily listed here.
And S2, acquiring a hyperspectral image of the specific aquaculture water environment area.
In an alternative embodiment, when acquiring the hyperspectral image, an aerial photographing device may be provided first, where the aerial photographing device includes a drone and a spectrometer mounted on the drone. In an optional embodiment, the unmanned aerial vehicle can adopt a six-rotor unmanned aerial vehicle M600 Pro in large, the net weight of the unmanned aerial vehicle is about 4kg, the maximum load is about 10kg, a hyperspectral imaging spectrometer GaiaSky-mini-2 independently developed by the university of Sichuan, Liangleihe, science and technology, Inc. can be carried on a remote sensing platform of the unmanned aerial vehicle, the remote sensing platform of the unmanned aerial vehicle adopts the unmanned aerial vehicle to be suspended in the air, the hyperspectral imaging spectrometer adopts a built-in push-broom mode to acquire a ground image, and main parameters of the hyperspectral imaging spectrometer are shown in table 1.
TABLE 1 GaiaSky-mini-2 airborne imaging high-speed spectrometer system parameters
In an optional embodiment, after the unmanned aerial vehicle flies to the space above the specific aquaculture water environment area, the spectrometer is controlled to acquire the hyperspectral image of the specific aquaculture water environment area. The method comprises the steps of planning a route in advance when shooting a specific aquaculture water environment area is carried out, selecting a date with clear weather, few cloud layers and almost no wind, carrying out unmanned aerial vehicle aerial remote sensing control at fixed time and fixed point, and further obtaining a hyperspectral image of the specific aquaculture water environment area. It should be noted that the hyperspectral images may include a plurality of hyperspectral images acquired by a preset monitoring frequency; further, the monitoring frequency is 2 times per month or more, and the shooting period is 1 year. In another embodiment or some embodiments, the monitoring frequency can be determined according to the specific conditions of different aquaculture water environment areas, and is not particularly limited herein.
S3, preprocessing the hyperspectral image which is acquired.
In an alternative embodiment, the hyperspectral image may be subjected to image preprocessing in remote sensing ENVI4.5 software, and the image preprocessing main steps may include, but are not limited to, geometric correction, atmospheric correction, radiation correction and the like. In another optional embodiment, the pre-processing of the hyperspectral image can be further performed by using Spec View software independently developed by mitsui floribunda technologies ltd. Still further, the preprocessing may also include, but is not limited to, performing lens correction on the hyperspectral image; performing black and white frame correction on the hyperspectral image; and performing atmospheric correction on the hyperspectral image.
In an optional embodiment, the lens correction is performed on the raw data of the hyperspectral image because the imaging mode of the hyperspectral image is a push-broom type, the imaging lens and the spectrometer are separated, and the front end of the spectrometer is provided with a corresponding incident slit; the entrance slit has certain length, and when the slit was sheltered from by focusing lens, there was some parts image sheltered from, can't normally acquire high spectral image, and after the slit position exceeded the termination point, also can be sheltered from and then can't gather high spectral image equally. Therefore, when the parameter setting is not reasonable, or when a black uneven area occurs at the edge of the collected hyperspectral image, lens correction can be performed. Meanwhile, the lens is not a plane, so that when the hyperspectral image is collected, the slit is shot line by line relative to the mirror surface of the focusing lens, the plane can cause the distortion of the hyperspectral image, the distortion is not very obvious only when the hyperspectral image is observed, and the defects can be eliminated by utilizing the lens calibration mode. When the unmanned aerial vehicle carries out hyperspectral image acquisition, the influence on internal distortion and splicing of the hyperspectral image caused by built-in push-broom can be corrected only by checking a lens calibration parameter file provided by a manufacturer. Please refer to fig. 2A, fig. 2B, fig. 2C and fig. 2D; fig. 2A is a hyperspectral image without lens correction, fig. 2B is a hyperspectral image after lens correction, and fig. 2C is a DN value curve of a hyperspectral image without lens correction and fig. 2D is a DN value curve of a hyperspectral image after lens correction.
In an alternative embodiment, the purpose of performing black-and-white frame correction on the hyperspectral image is to convert DN value (digital quantization value) into reflectance value (reflectance) specifically including:
in the above formula, Rref is a reflectance value of the hyperspectral image after black and white frame correction, DNraw is a DN value of the original hyperspectral image, DNwhite is white frame data of the reference plate, DNdark is a system error DN value of the spectrometer, and Rwhite is a reflectance coefficient of the reference plate. For example, please refer to fig. 3A, fig. 3B, fig. 3C, and fig. 3D for hyperspectral images of corn kernels; wherein fig. 3A is a DN value curve of a hyperspectral image without black and white frame correction, fig. 3B is a DN value curve of a reference plate, fig. 3C is a DN value curve of a dark background, and fig. 3D is a relative reflectance value curve after black and white frame correction.
In an optional embodiment, the hyperspectral image data acquired by the spectrometer may be affected by factors such as atmosphere and moisture because the unmanned aerial vehicle is considered after flying to a certain height. In order to eliminate the influence of the factors, 2m × 2m gray cloth calibrated by a national measurement institute can be placed in a shooting area before the unmanned aerial vehicle takes off, and when the hyperspectral images are acquired, only the gray cloth needs to be covered in one hyperspectral image; furthermore, when the influence on factors such as atmosphere and water vapor is eliminated, the method specifically comprises the following steps:
in the above formula, Rfixed is the spectral reflectance of the hyperspectral image after eliminating factors such as atmosphere and water vapor, Rref is the spectral reflectance of the hyperspectral image after black and white frame correction, Rstandard is the spectral reflectance of gray cloth calibrated by the national measurement institute, and Rgrayref is the spectral reflectance of gray cloth in the hyperspectral image after black and white frame correction. Referring to fig. 4, the spectral curves of the plants before and after atmospheric calibration are shown in fig. 4.
In an optional embodiment, the pre-processing the hyperspectral image that has been acquired further comprises: and carrying out geometric fine correction on the unmanned aerial vehicle airborne spectrometer. The geometric fine correction of the airborne spectrograph of the unmanned aerial vehicle is mainly to solve the problem that a hyperspectral image is distorted due to slight vibration of a platform of the unmanned aerial vehicle in the process of acquiring the hyperspectral image by the unmanned aerial vehicle and the spectrograph, and the invention utilizes the registration airborne hyperspectral geometric fine correction software developed by Szechwan Shuangli Hesper science and technology Limited to eliminate the slight distortion of the hyperspectral image; in another embodiment or some embodiments, performing geometric fine correction on the hyperspectral image may also be performed by using software or a method thereof, which is not described herein again. Further, please refer to fig. 5A and 5B; fig. 5A is a hyperspectral image before geometric fine correction, and fig. 5B is a hyperspectral image after geometric fine correction.
In an optional embodiment, the pre-processing the hyperspectral image that has been acquired further comprises: and splicing the plurality of hyperspectral images. The splicing of the plurality of hyperspectral images is mainly to splice image data of the plurality of hyperspectral images subjected to geometric correction by using Agisoft Metashape Professional software. Referring to fig. 6A and 6B, fig. 6A shows a stitching result of a plurality of hyperspectral images captured after a spectrometer carried by a first unmanned aerial vehicle performs a shooting task; fig. 6B shows a stitching result of a plurality of hyperspectral images captured after the 2 nd unmanned aerial vehicle-carried spectrometer performs a shooting task.
S4, selecting sampling points in the specific aquaculture water environment area according to the hyperspectral image, and measuring a first water quality parameter on the sampling points.
In an alternative embodiment, the sampling points may be determined according to the result of the preliminary analysis of the hyperspectral images, and the specific aquaculture water environment area may be found by finding out an area with a large difference in image color, in one embodiment, the specific aquaculture water environment area includes an aquaculture pond, in one or some other embodiments, the specific aquaculture water environment area may further include any other fresh water area in which aquaculture is performed, and this is not necessarily listed here for brevity of the subject matter of the present invention. After the sampling point is determined, water quality sampling is carried out according to the coordinate position of the sampling point, sampling is carried out on each sewage treatment tank, and suspended matters, transparency, PH and DO can be detected on site; then, physicochemical indexes of water quality including but not limited to TN, ammonia nitrogen, nitrite nitrogen, TP, DP and chlorophyll a, dominant algae and microorganism amount are measured indoors. Referring to table 2, table 2 shows the first water quality parameter and the content distribution thereof at 10 sampling points; a water sample at 0.5m of the surface layer of each sampling point is taken for laboratory analysis, and the analysis parameters comprise total nitrogen (mg/L), total phosphorus (mg/L), chlorophyll a (ug/L) and potassium permanganate index (mg/L).
Water quality index parameter content distribution of 210 sampling points in table
And S5, inverting a second water quality parameter of the specific aquaculture water environment area by using the hyperspectral image and the first water quality parameter.
In an optional embodiment, according to the corrected hyperspectral image, correlation statistical analysis is performed on each wave band and each wave band combination and corresponding second water quality parameters by calculating reflectivity values of each wave band of each sampling point in SPSS18.0 software by using a Pearson method, an optimal inversion wave band and a wave band combination are determined, and second water quality parameters TN, ammonia nitrogen, nitrate nitrogen, nitrite nitrogen, TP, DP, chlorophyll, suspended matters and transparency in the aquaculture pond are inverted by using a multiple linear regression model, a BP model in an artificial neural network model, an RBF neural network model and an SVM model.
Referring to fig. 7A, 7B and 7C, fig. 7A and 7B respectively list the distribution of 10 sampling points of the ecological pond, aeration pond, sedimentation pond, freshwater shrimp pond and weever pond in the Yangkong village, Lujiazhuan village, and fig. 7C respectively shows the spectral reflectance curves of the hyperspectral images of the sampling points of the pond in the Yangkong village, Lujiazhuan freshwater shrimp and weever pond. As can be seen from the graph, the spectral reflectance of the ruffman sampling point is generally higher than the spectral reflectance of the other sampling points, while the spectral reflectance of the weever pond sampling point is generally lower than the spectral reflectance of the other sampling points.
And respectively carrying out correlation analysis on the first water quality parameters (such as total nitrogen, total phosphorus, chlorophyll a and potassium permanganate indexes) of the ecological pool, the aeration pool, the sedimentation pool, the freshwater shrimp pool and the weever pool of the Yangkong village and the Lujiazhu pond and the corresponding spectral reflectance values to obtain a correlation curve shown in a figure 8. As can be seen from fig. 8, the spectral reflectance of total nitrogen and chlorophyll a is consistent with the trend of the spectral reflectance of each wavelength band, but the spectral reflectance of total nitrogen is higher than that of chlorophyll a. The indexes of total phosphorus and potassium permanganate are in negative correlation with the spectral reflectivity of each wave band, and the correlation of total nitrogen and chlorophyll a with the spectral reflectivity of each wave band is in negative correlation, then in positive correlation and finally in negative correlation.
According to the prior art, the precision of monitoring water quality by using a single waveband is not as high as that of monitoring water quality by using a double waveband; compared with a dual-band monitoring model, a complex chemometrics analysis method such as a partial least square method, an artificial neural network, a support vector machine and the like is improved in monitoring precision, but the number of applied bands is large, the running time is long, and the method is not suitable for monitoring water quality parameters on line in real time in the practical application process. However, the dual-band combination factor can not only highlight the spectral characteristics of the water quality parameters, so that errors caused by the cross influence of other water quality parameters with non-characteristic bands and non-characteristic bands not coincident are averaged and randomized. Meanwhile, the division factor and the phase difference factor are effective operation methods for highlighting the spectral characteristic wave band of the water quality parameter. The invention constructs the ratio index according to the dual-waveband combination so as to find the optimal dual-waveband combination to construct the monitoring model to predict the second water quality parameter. And (3) carrying out correlation analysis on the ratio index and each first water quality parameter constructed by the reflectivity of all the wave bands with the wavelengths of 400-1000nm to obtain a correlation coefficient distribution diagram of the second water quality parameter and each wave band ratio. Please refer to fig. 9A, 9B, 9C and 9D; fig. 9A is a correlation coefficient distribution diagram of total nitrogen and each band ratio, fig. 9B is a correlation coefficient distribution diagram of total phosphorus and each band ratio, fig. 9C is a correlation coefficient distribution diagram of chlorophyll a and each band ratio, and fig. 9D is a correlation coefficient distribution diagram of potassium permanganate index and each band ratio.
And screening out the wave band combination with the highest correlation coefficient of each first water quality parameter and each ratio index through the correlation coefficient distribution of the first water quality parameters and the ratio indexes, and establishing a unitary linear regression equation between each first water quality parameter and each ratio index. Please refer to fig. 10A, fig. 10B, fig. 10C and fig. 10D; wherein, fig. 10A is a unary linear regression equation between total nitrogen and a ratio index, fig. 10B is a unary linear regression equation between total phosphorus and a ratio index, fig. 10C is a unary linear regression equation between chlorophyll a and a ratio index, and fig. 10D is a unary linear regression equation between a potassium permanganate index and a ratio index.
According to a unary linear equation fitted between the optimal two-band ratio index and each first water quality parameter in fig. 10A, fig. 10B, fig. 10C and fig. 10D, inverting the acquired first-frame and second-frame airborne hyperspectral splicing results and the single-view images of the weever pond, the rujiazhuang ecological pool, the aeration pool and the sedimentation pool to obtain content distribution maps of total nitrogen, total phosphorus, chlorophyll a and the potassium permanganate index of the first-frame, second-frame and single-view images, and visually displaying the spatial distribution rules of the water quality parameters of the total nitrogen, the total phosphorus, the chlorophyll a, the potassium permanganate index and the like of the yangkong, the rujiazhuang ecological pool, the aeration pool, the sedimentation pool, the freshwater shrimp pond and the weever pond according to the content distribution maps, as shown in fig. 11-14.
Because the water quality parameter samples of the test are relatively too few, the inversion result cannot be verified. Fig. 15 is a 1:1 diagram of the content and measured value of each water quality parameter of the constructed empirical model inverted sampling point, and it can be known from the diagram that the fitting coefficient of the measured value and the predicted value of total phosphorus and chlorophyll a is the highest and reaches more than 0.98, then the total nitrogen is present, the fitting coefficient of the measured value and the predicted value is 0.83, finally the potassium permanganate index is present, and the fitting coefficient of the measured value and the predicted value is 0.81.
And S6, providing early warning for a specific aquaculture water environment area with deteriorated water quality according to the inversion result.
In an optional embodiment, along with the increase of the shooting times and the water quality sampling, the robustness, the reliability and the precision of an inversion model are remarkably increased, each second water quality parameter is calculated according to the root mean square error and the relative error by combining the actually measured first water quality parameter and the actually measured model, the precision is monitored by remote sensing, the optimal inversion model is screened, then the hyperspectral inversion model of the second water quality parameter is applied to a hyperspectral image, the inversion result on each water quality surface of a culture pond in a shooting area is obtained, and early warning analysis is carried out on an area which exceeds the water quality parameter index of a culture water environment and has water quality deterioration.
And S7, studying and judging the change trend of the water quality in the specific aquaculture water environment area according to the first water quality parameter and the second water quality parameter.
In an optional embodiment, the result of the early warning analysis may be performed according to the result of the inversion of the second water quality parameter, so as to reasonably study and judge the water quality change trend, for example, in a specific aquaculture water environment area, the trend that one or more indexes in the second water quality parameter are about to break through a critical value may be judged, and the trend that the water quality in the area may be further deteriorated may be judged.
And S8, regulating and controlling the water quality of the specific aquaculture water environment area according to the change trend.
In an optional embodiment, different regulation and control measures can be adopted in a targeted manner to intervene in the specific aquaculture water environment region in time according to the water quality change trend, one or more times of unmanned aerial vehicle hyperspectral shooting can be carried out on the specific aquaculture water environment region again within one time after the water environment of the specific aquaculture water environment region is subjected to targeted regulation and control, and then the water environment regulation and control effect of the aquaculture water environment region is evaluated according to a second water quality parameter obtained by establishing a water quality model in an inversion mode.
The embodiment shown in the invention discloses a breeding water environment early warning regulation and control device, which comprises input equipment, a processor, a memory and output equipment, wherein the processor, the input equipment, the output equipment and the memory are connected with each other through a communication bus; further, the processor is configured to call the program instructions to execute the steps of executing the embodiment of the aquaculture water environment early warning regulation and control method. For specific description and beneficial effects of the early warning regulation and control method for aquaculture water environment, please refer to the above description and will not be repeated herein.
It will be appreciated that in embodiments of the invention, memory referred to may comprise both read-only memory and random-access memory, and provides instructions and data to the processor. The portion of memory may also include non-volatile random access memory. The memory may also store information regarding the type of device, for example.
The processor is used to run or execute the operating system, various software programs, and its own instruction set stored in internal memory, and to process data and instructions received from the touch input device or from other external input pathways to achieve various functions. The processor may include, but is not limited to, one or more of a central processing unit, a general purpose image processor, a microprocessor, a digital signal processor, a field programmable gate array, an application specific integrated circuit. In some embodiments, the processor and the memory controller may be implemented on a single chip. In some other embodiments, they may be implemented separately on separate chips from each other.
The input equipment can be a camera and the like, the camera is also called a computer camera, a computer eye, an electronic eye and the like, and is a video driving-in equipment and a touch input device such as a numeric keyboard or a mechanical keyboard and the like; the output device may include a display or the like.
Yet another embodiment of the present invention shows a computer-readable storage medium storing a computer program, the computer program comprising program instructions, which when executed by a processor, cause the processor to execute the relevant steps of the aquaculture water environment early warning regulation method.
The computer-readable storage medium may include, among other things, cache, high-speed random access memory, such as common double data rate synchronous dynamic random access memory, and may also include non-volatile memory, such as one or more read-only memories, magnetic disk storage devices, flash memory devices, or other non-volatile solid-state memory devices, such as compact disks, floppy disks, or data tapes.
The embodiment shown in the invention discloses a aquaculture water environment early warning and regulation system which comprises a aquaculture water environment early warning and regulation device and aerial shooting equipment, wherein the aerial shooting equipment is in communication connection with the aquaculture water environment early warning and regulation device, and the aquaculture water environment early warning and regulation device executes the steps related to the aquaculture water environment early warning and regulation method. The aerial photographing device comprises an unmanned aerial vehicle and a spectrometer carried on the unmanned aerial vehicle. In an optional embodiment, the unmanned aerial vehicle can adopt a six-rotor unmanned aerial vehicle M600 Pro in Xinjiang, the net weight of the unmanned aerial vehicle is about 4kg, the maximum load is about 10kg, a hyperspectral imaging spectrometer GaiaSky-mini-2 independently developed by Sichuan Lianghe Spectrum science and technology Limited can be carried on a remote sensing platform of the unmanned aerial vehicle, the remote sensing platform of the unmanned aerial vehicle adopts the unmanned aerial vehicle to be suspended in the air, and the hyperspectral imaging spectrometer adopts a built-in push-broom mode to acquire a ground image. Other expressions of the aerial photography equipment and the aquaculture water environment early warning regulation and control device can be specifically referred to the above, and the descriptions are not repeated here.
Claims (10)
1. A culture water environment early warning regulation and control method is characterized by comprising the following steps:
acquiring a hyperspectral image of a specific aquaculture water environment area;
selecting sampling points in the specific aquaculture water environment area according to the hyperspectral image, and measuring first water quality parameters on the sampling points;
performing inversion on a second water quality parameter of the specific aquaculture water environment area by using the hyperspectral image and the first water quality parameter;
and according to the inversion result, early warning is provided for a specific aquaculture water environment area with deteriorated water quality.
2. The aquaculture water environment early warning regulation and control method according to claim 1, wherein the acquiring of the hyperspectral image of the specific aquaculture water environment area comprises:
providing aerial photographing equipment, wherein the aerial photographing equipment comprises an unmanned aerial vehicle and a spectrometer carried on the unmanned aerial vehicle;
and after the unmanned aerial vehicle flies to the upper space of the specific aquaculture water environment area, controlling the spectrometer to acquire the hyperspectral image of the specific aquaculture water environment area.
3. The aquaculture water environment early warning regulation and control method according to claim 1, further comprising:
and preprocessing the hyperspectral image which is acquired.
4. The aquaculture water environment early warning regulation and control method according to claim 3, wherein the preprocessing the hyperspectral image which is obtained comprises:
performing lens correction on the hyperspectral image;
performing black and white frame correction on the hyperspectral image; and
performing atmospheric correction on the hyperspectral image.
5. The aquaculture water environment early warning regulation and control method according to claim 1, wherein the inverting the second water quality parameter of the specific aquaculture water environment area by using the hyperspectral image and the first water quality parameter comprises:
extracting reflectivity values of all wave bands in the hyperspectral image corresponding to the sampling points;
performing correlation statistics on a first water quality parameter corresponding to at least one of the wave bands according to the reflectivity values;
and completing the inversion of the second water quality parameter by using one or more of a BP model, an RBF neural network model and an SVM model according to the result of the correlation statistics.
6. The aquaculture water environment early warning regulation and control method according to claim 1, further comprising:
and studying and judging the change trend of the water quality in the specific aquaculture water environment area according to the first water quality parameter and the second water quality parameter.
7. The aquaculture water environment early warning regulation and control method according to claim 6, further comprising:
and regulating and controlling the water quality of the specific aquaculture water environment area according to the change trend.
8. The aquaculture water environment early warning regulation and control method according to claim 1, characterized in that:
the first water quality parameters comprise one or more of TN, ammonia nitrogen, nitrite nitrogen, TP, DP, chlorophyll a, dominant algae, suspended matters, transparency, PH, DO and microbial quantity;
the second water quality parameters comprise one or more of TN, ammonia nitrogen, nitrate nitrogen, nitrite nitrogen, TP, DP, chlorophyll, suspended matters and transparency.
9. The utility model provides a breed water environment early warning regulation and control device which characterized in that includes: the system comprises a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are connected with each other, the memory is used for storing a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the steps of the aquaculture water environment early warning regulation and control method according to any one of claims 1-8.
10. The utility model provides a breed water environment early warning regulation and control system which characterized in that includes: the aquaculture water environment early warning and regulating device comprises an aerial shooting device and the aquaculture water environment early warning and regulating device is in communication connection with the aerial shooting device, and the aquaculture water environment early warning and regulating device executes the steps of the aquaculture water environment early warning and regulating method according to any one of claims 1-8.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011534129 | 2020-12-23 | ||
| CN2020115341292 | 2020-12-23 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112986157A true CN112986157A (en) | 2021-06-18 |
Family
ID=76393907
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110194304.6A Pending CN112986157A (en) | 2020-12-23 | 2021-02-20 | Culture water environment early warning regulation and control method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112986157A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114417981A (en) * | 2021-12-28 | 2022-04-29 | 安徽新宇环保科技股份有限公司 | Intelligent river length patrol system |
| CN115211391A (en) * | 2022-09-21 | 2022-10-21 | 广东省农业科学院动物科学研究所 | Fish and shrimp polyculture method based on hyperspectral remote sensing technology |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108593569A (en) * | 2018-07-02 | 2018-09-28 | 中国地质环境监测院 | EO-1 hyperion water quality parameter quantitative inversion method based on spectrum morphological feature |
| CN108750110A (en) * | 2018-08-10 | 2018-11-06 | 辽宁省环境科学研究院 | A kind of unmanned plane Ecology remote sense monitoring system |
| CN110222475A (en) * | 2019-07-03 | 2019-09-10 | 中国水利水电科学研究院 | A method of based on unmanned plane multispectral remote sensing inverting winter wheat plant moisture content |
| CN110672805A (en) * | 2019-10-08 | 2020-01-10 | 核工业北京地质研究院 | Reservoir water quality parameter quantitative inversion method based on aviation hyperspectral data |
| CN110865040A (en) * | 2019-11-29 | 2020-03-06 | 深圳航天智慧城市系统技术研究院有限公司 | Sky-ground integrated hyperspectral water quality monitoring and analyzing method |
| CN110887792A (en) * | 2019-12-17 | 2020-03-17 | 深圳慧格科技服务咨询有限公司 | River water quality rapid monitoring system based on unmanned aerial vehicle hyperspectral image |
| CN111007021A (en) * | 2019-12-31 | 2020-04-14 | 北京理工大学重庆创新中心 | Hyperspectral water quality parameter inversion system and method based on one-dimensional convolution neural network |
-
2021
- 2021-02-20 CN CN202110194304.6A patent/CN112986157A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108593569A (en) * | 2018-07-02 | 2018-09-28 | 中国地质环境监测院 | EO-1 hyperion water quality parameter quantitative inversion method based on spectrum morphological feature |
| CN108750110A (en) * | 2018-08-10 | 2018-11-06 | 辽宁省环境科学研究院 | A kind of unmanned plane Ecology remote sense monitoring system |
| CN110222475A (en) * | 2019-07-03 | 2019-09-10 | 中国水利水电科学研究院 | A method of based on unmanned plane multispectral remote sensing inverting winter wheat plant moisture content |
| CN110672805A (en) * | 2019-10-08 | 2020-01-10 | 核工业北京地质研究院 | Reservoir water quality parameter quantitative inversion method based on aviation hyperspectral data |
| CN110865040A (en) * | 2019-11-29 | 2020-03-06 | 深圳航天智慧城市系统技术研究院有限公司 | Sky-ground integrated hyperspectral water quality monitoring and analyzing method |
| CN110887792A (en) * | 2019-12-17 | 2020-03-17 | 深圳慧格科技服务咨询有限公司 | River water quality rapid monitoring system based on unmanned aerial vehicle hyperspectral image |
| CN111007021A (en) * | 2019-12-31 | 2020-04-14 | 北京理工大学重庆创新中心 | Hyperspectral water quality parameter inversion system and method based on one-dimensional convolution neural network |
Non-Patent Citations (5)
| Title |
|---|
| 1 * |
| 2 * |
| 张宏鸣;刘雯;韩文霆;刘全中;宋荣杰;侯贵河;: "基于梯度提升树算法的夏玉米叶面积指数反演", 农业机械学报, no. 05, pages 251 - 258 * |
| 程俊毅;张显峰;孙敏;罗鹏;杨婉婷;: "基于空地协同采样的植被覆盖度随机森林估算方法", 北京大学学报(自然科学版), no. 01, pages 146 - 157 * |
| 黄宇 等: ""基于无人机高光谱成像技术的河湖水质参数反演"", vol. 51, no. 3, pages 205 - 212 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114417981A (en) * | 2021-12-28 | 2022-04-29 | 安徽新宇环保科技股份有限公司 | Intelligent river length patrol system |
| CN114417981B (en) * | 2021-12-28 | 2023-07-18 | 安徽新宇环保科技股份有限公司 | Intelligent river length inspection system |
| CN115211391A (en) * | 2022-09-21 | 2022-10-21 | 广东省农业科学院动物科学研究所 | Fish and shrimp polyculture method based on hyperspectral remote sensing technology |
| CN115211391B (en) * | 2022-09-21 | 2022-12-09 | 广东省农业科学院动物科学研究所 | Fish and shrimp polyculture method based on hyperspectral remote sensing technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lussem et al. | Estimating biomass in temperate grassland with high resolution canopy surface models from UAV-based RGB images and vegetation indices | |
| CN108985588B (en) | Crop yield per unit remote sensing estimation method, device and system | |
| Qiu et al. | Estimation of nitrogen nutrition index in rice from UAV RGB images coupled with machine learning algorithms | |
| Vaesen et al. | Ground-measured spectral signatures as indicators of ground cover and leaf area index: the case of paddy rice | |
| CN1302277C (en) | Field crops nutrition diagnostic method | |
| Kirk et al. | Estimation of leaf area index in cereal crops using red–green images | |
| AU2020101709A4 (en) | Crop yield prediction method and system based on low-altitude remote sensing information from unmanned aerial vehicle | |
| Sun et al. | Retrieval of rapeseed leaf area index using the PROSAIL model with canopy coverage derived from UAV images as a correction parameter | |
| Rasti et al. | A survey of high resolution image processing techniques for cereal crop growth monitoring | |
| CN112986157A (en) | Culture water environment early warning regulation and control method, device and system | |
| Zhou et al. | Qualification of soybean responses to flooding stress using UAV-based imagery and deep learning | |
| CN112345458A (en) | Wheat yield estimation method based on multispectral image of unmanned aerial vehicle | |
| CN116108318B (en) | Rape nitrogen fertilizer recommended dressing amount calculation method based on unmanned aerial vehicle multispectral image | |
| US20240037676A1 (en) | Upward facing light sensor for plant detection | |
| Facchi et al. | Comparing opticaland direct methods for leafarea index determination in a maize crop | |
| CN113063739A (en) | Rice canopy nitrogen content monitoring method based on airborne hyperspectral sensor | |
| Shi et al. | Using unmanned aerial vehicle-based multispectral image data to monitor the growth of intercropping crops in tea plantation | |
| CN104236486B (en) | A kind of cotton leaf area index quick nondestructive assay method | |
| Tavakoli et al. | Evaluation of different sensing approaches concerning to nondestructive estimation of leaf area index (LAI) for winter wheat | |
| Praeger et al. | Estimating the biomass density of macroalgae in land-based cultivation systems using spectral reflectance imagery | |
| Zhuo et al. | Spectral response and the retrieval of canopy chlorophyll content under interspecific competition in wetlands—case study of wetlands in the Yangtze River Estuary | |
| Guo et al. | Inversion of maize leaf area index from UAV hyperspectral and multispectral imagery | |
| CN106709922A (en) | Image based forage grass coverage and biomass automatic detection method | |
| Zheng et al. | Using high spatial and temporal resolution data blended from SPOT-5 and MODIS to map biomass of summer maize | |
| Guo et al. | High-throughput estimation of plant height and above-ground biomass of cotton using digital image analysis and Canopeo |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |