Fishpond water temperature forecasting method based on intelligent grid forecasting data

Abstract

The invention discloses a fishpond water temperature forecasting method based on intelligent grid forecasting data, and the method comprises the steps: constructing a fishpond grid map, obtaining M candidate station coordinates located in the same coordinate system as the fishpond grid map, determining the actual air temperature of a target grid in the previous day and the forecast air temperature of the current day according to the M candidate station coordinates, and carrying out the forecasting of the fishpond water temperature. The method comprises the following steps: selecting K anchoring grids in a fishpond grid map, determining the actual water temperature of a target grid on the previous day according to the K anchoring grids, determining the predicted water temperature of the target grid on the current day according to the actual water temperature of the target grid on the previous day, the actual air temperature of the previous day and the predicted air temperature on the current day, and inputting the predicted water temperature of the target grid on the current day to a head tool, obtaining a water temperature forecasting grid distribution diagram of the fish pond; according to the method, the water temperature change in the fishpond can be comprehensively covered, errors caused by too large grids or neglecting of local differences in a traditional forecasting method are avoided, and more accurate water temperature forecasting is provided.

Description

Technical Field

[0001] The present invention relates to a water temperature forecasting method, in particular to a fish pond water temperature forecasting method based on intelligent grid forecast data. Background Art

[0002] Currently, many aquaculture farmers need to make actual forecasts of the water temperature for the day when conducting aquaculture. The patent document with patent publication number CN202411682670.6 discloses a freshwater fish pond water temperature prediction method, system, medium and equipment, which can construct freshwater fish pond water temperature prediction models under different weather types, such as low temperature and low illumination type, rapid cooling and pressure reduction type, and high temperature and stuffy type. However, in the above patent documents and the prior art, point-based measured data is usually used to predict water temperature. With the expansion and increase in complexity of water body areas, traditional methods are difficult to provide sufficient spatial resolution to accurately predict the water temperature distribution of the entire water body. Especially in irregularly shaped water body areas such as fish ponds, traditional air temperature data and water temperature models are difficult to accurately capture the temperature differences between regions, resulting in limited accuracy and practicality of water temperature prediction results.

[0003] Furthermore, existing water temperature prediction technologies rely on relatively crude air and water temperature data, often failing to effectively account for factors such as flow direction, topographic slope, and internal flow patterns. Consequently, existing technologies often struggle to provide accurate water temperature maps in complex environments, failing to fully reflect temperature variations between grid points, which in turn impacts aquaculture management. Summary of the Invention

[0004] In view of the deficiencies of the prior art, the present invention provides a fish pond water temperature forecasting method based on intelligent grid forecast data, which solves the technical problems raised in the background technology by introducing gridded water temperature forecasting.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: The method for predicting fish pond water temperature based on intelligent grid forecast data includes the following steps: S1, constructing a fish pond grid map; Wherein, the fish pond grid map includes a number of grid coordinates; S2. Obtain the coordinates of M candidate sites in the same coordinate system as the fish pond grid map; S3. Determine the previous day's actual temperature and the current day's forecast temperature of the target grid based on the coordinates of the M candidate stations; S4, select K anchor grids in the fish pond grid map; S5. Determine the actual water temperature of the target grid on the previous day based on the K anchor grids; S6. Determine the forecast water temperature for the target grid on the current day based on the actual water temperature of the target grid on the previous day, the actual air temperature of the target grid on the previous day, and the forecast air temperature for the current day; S7. Input the daily forecast water temperature of the target grid into the output tool to obtain a water temperature forecast grid distribution map of the fish pond.

[0006] In some specific embodiments, constructing a fish pond grid map includes: S1-1. Obtain the coordinates of the boundary points of the fish pond; S1-2. Determine the coordinates of the center of the fish pond based on the coordinates of the boundary points of the fish pond; S1-3, using the center coordinates of the fish pond as the drawing origin, and constructing an origin fish pond grid with a predefined grid side length; wherein the intersection of the diagonals of the origin fish pond grid coincides with the drawing origin; S1-4, repeatedly constructing fish pond grids in the four neighborhoods of the origin fish pond grid until the fish pond grid distribution at least covers the coordinates of all boundary points; S1-5. Define the fish pond grid distribution covering all boundary point coordinates as a fish pond grid map.

[0007] In some specific embodiments, repeatedly constructing fish pond grids on the four neighborhoods of the origin fish pond grid until the fish pond grid distribution at least covers all boundary point coordinates; including: S1-4-1. Obtain the coordinates of the center of the fish pond and the four equal sides of the origin fish pond grid; S1-4-2. For any equal side lengths, mark the coordinates of the midpoint of the side length; S1-4-3. Starting from the center coordinate of the fish pond, extend the neighborhood dotted line in the direction of the midpoint coordinate of the side length; S1-4-4. Calculate the extension length of the neighborhood dashed line; S1-4-5. If the extended length of the neighborhood dashed line is twice the distance from the center coordinate of the fish pond, stop extending the neighborhood dashed line and define the end of the neighborhood dashed line as the neighborhood grid coordinate; S1-4-6, constructing a neighborhood grid according to the neighborhood grid coordinates and the predefined grid side length; S1-4-7. Starting from the neighborhood grid coordinates, extend the neighborhood dotted line in the direction where the neighborhood grid is not constructed, and repeat S1-4-1-4 to S1-4-7 until all boundary point coordinates are covered by the neighborhood grid.

[0008] In some specific embodiments, obtaining M candidate site coordinates in the same coordinate system as the fish pond grid map includes: S2-1. Obtain the coordinates of N temperature measurement stations in the same coordinate system as the fish pond grid map; S2-2, calculating the N first coordinate distances between the coordinates of the N temperature measurement stations and the coordinates of the center of the fish pond; S2-3, selecting M second coordinate distances from the N first coordinate distances; S2-4. Obtain M candidate site coordinates corresponding to the second coordinate distance from the N temperature measurement site coordinates.

[0009] In some specific embodiments, selecting M second coordinate distances from N first coordinate distances includes: S2-3-1. Order the N first coordinate distances in ascending order to generate a first sequence; S2-3-2. Select the shortest first coordinate distance from the first sequence as the second coordinate distance, and add it to the second sequence; S2-3-3. Repeat S2-3-2 until there are M second coordinate distances in the second sequence.

[0010] In some specific embodiments, determining the previous day's actual temperature and the current day's forecast temperature of the target grid based on the coordinates of the M candidate sites includes: S3-1, obtaining the grid coordinates of each fish pond grid in the fish pond grid map; S3-2, calculating the Euclidean distance between the target grid and the coordinates of M candidate sites; S3-3, obtaining the previous day's actual temperature and the current day's forecast temperature of the coordinates of M candidate stations; S3-4, determining the previous day's actual temperature and the current day's forecast temperature of the target grid based on the previous day's actual temperature and the current day's forecast temperature of the M candidate site coordinates, and the Euclidean distance between the target grid and the M candidate site coordinates; The calculation formula for the actual temperature of the previous day of the target grid is: ; The calculation formula for the daily forecast temperature of the target grid is: ; in, Represents grid coordinates The previous day's actual temperature, Represents grid coordinates The forecast temperature for the day is represents the actual temperature of the previous day at the i-th candidate station, represents the daily forecast temperature of the i-th candidate station, Represents grid coordinates The Euclidean distance between the i-th candidate site, Represents the distance attenuation index, which means that the farther the candidate site is, the smaller its site weight is.

[0011] In some specific embodiments, selecting K anchor grids from the fish pond grid map includes: S4-1. Calculate the Euclidean distance between the target grid and all boundary point coordinates; S4-2, determining the average distance between the target grid and the coordinates of all boundary points based on the Euclidean distance between the target grid and the coordinates of all boundary points; S4-3. Calculate the standard deviation of the target grid based on the average distance and Euclidean distance between the target grid and all boundary point coordinates until a set of standard deviations of all grid coordinates is obtained; S4-4. Select the maximum standard deviation from the standard deviation set of all grid coordinates in turn, and match the corresponding grid based on the maximum standard deviation as the anchor grid; S4-5. Repeat 4-4 until L anchor grids are obtained.

[0012] In some specific embodiments, determining the previous day's actual water temperature of the target grid based on the K anchor grids includes: S5-1. Calculate the Euclidean distance between the target grid and K anchor grids; S5-2, obtaining the measured water temperature of K anchor grids on the previous day; S5-3, determining the actual water temperature of the target grid on the previous day based on the actual water temperatures of the K anchor grids on the previous day and the Euclidean distances between the target grid and the K anchor grids; The calculation formula for determining the actual water temperature of the target grid on the previous day is: ; in, Indicates the actual water temperature of the target grid the previous day. represents the water temperature measured on the previous day by the i-th anchor grid, represents the Euclidean distance between the target grid and the anchor grid, represents the water flow direction angle between the i-th anchor grid and the target; Indicates the water flow direction angle of the target grid, represents the bottom slope difference between the target grid and the i-th anchor grid, and k represents the influence coefficient of controlling the bottom slope difference The present invention provides a fish pond water temperature forecasting method based on intelligent grid forecast data, which has the following beneficial effects: The present invention significantly improves the spatial accuracy of water temperature forecasts by constructing a fish pond grid map and combining data from multiple candidate sites. Fish ponds are usually irregular in shape, and traditional methods use relatively simple grid processing, which makes it difficult to effectively capture changes in water temperature in different areas. Therefore, by dividing the fish pond into multiple grid cells, the water temperature of each grid cell can be forecast separately, ensuring that temperature changes in each area can be predicted. This allows the method to fully cover water temperature changes in the fish pond, avoiding errors caused by overly large grids or ignoring local differences in traditional forecasting methods, and providing more accurate water temperature forecasts.

[0013] Furthermore, by optimizing water temperature estimation by introducing factors such as flow direction angle and bottom slope difference into the target grid water temperature forecast process, the accuracy of actual water temperature prediction is further improved. The introduction of flow direction angle simulates the propagation and variation of water temperature within the water body, ensuring that the water temperature prediction more closely matches the flow characteristics of the actual water body. The introduction of bottom slope difference takes into account the impact of topography on water temperature changes, with areas with larger slope differences experiencing more dramatic water temperature changes. Especially in the case of irregularly shaped water bodies or complex flow environments, the water temperature prediction results can be dynamically adjusted to reflect the full picture of water temperature changes within the water body in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 Schematic diagram of the flow of the fish pond water temperature forecasting method based on intelligent grid forecast data of the present invention; Figure 2 This is a schematic diagram of the process of constructing the fish pond grid map of the present invention; Figure 3 Schematic diagram of the selection process of the anchor grid according to the present invention. DETAILED DESCRIPTION

[0015] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0016] Example 1: See Figure 1 The present invention provides a method for predicting fish pond water temperature based on intelligent grid forecast data, comprising the following steps: S1, constructing a fish pond grid map; Wherein, the fish pond grid map includes a number of grid coordinates; S2. Obtain the coordinates of M candidate sites in the same coordinate system as the fish pond grid map; S3. Determine the previous day's actual temperature and the current day's forecast temperature of the target grid based on the coordinates of the M candidate stations; It should be noted that the daily temperature forecast refers to the expected temperature value calculated based on an existing temperature prediction model. This expected temperature value takes into account current weather conditions, historical data, and other factors that affect temperature fluctuations. Therefore, the daily temperature forecast represents the expected temperature in the area where the fish pond is located during a specific period of time.

[0017] S4, select K anchor grids in the fish pond grid map; S5. Determine the actual water temperature of the target grid on the previous day based on the K anchor grids; S6. Determine the forecast water temperature for the target grid on the current day based on the actual water temperature of the target grid on the previous day, the actual air temperature of the target grid on the previous day, and the forecast air temperature for the current day; For example, in this embodiment, the calculation formula for determining the daily forecast water temperature of the target grid is: ; in, Indicates the water temperature forecast for the day. The forecast temperature for the day. Indicates the actual temperature of the previous day. Indicates the actual water temperature of the previous day; is a constant term used to represent the reference offset, , , are the influence weights of the forecast temperature for the day, the actual temperature for the previous day, and the actual water temperature for the previous day on the forecast water temperature for the day.

[0018] For example, the constant term It is fixed in the prediction model, but can fluctuate within a reasonable range. In this embodiment, the given constant term is 3.111. Usually, this value will fluctuate within the range of ±0.5, so the range of the constant term can be set as: [2.611, 3.611]. Specifically, the constant term This is an offset based on historical data, used to correct the baseline relationship between air and water temperatures. Its upper and lower floating range is set based on the fluctuation range of actual meteorological data.

[0019] Furthermore, the influence weight , , Respectively represent the relative importance of the forecast temperature of the day, the actual temperature of the previous day and the actual water temperature of the previous day in the calculation of the forecast water temperature of the day. , , .

[0020] The specific values of the impact weights are described below in this embodiment: The temperature forecast for the day has a small impact on the water temperature, with a coefficient of 0.214. This is because although the temperature has a certain impact on the water temperature, the change in water temperature is not only caused by the temperature change on the day, but also by the temperature and water temperature of the previous day. In addition, the thermal inertia of water is large, and the change in water temperature is not as rapid as that of air temperature. Therefore, It is set to 0.214, indicating that the forecast air temperature for the day has a small contribution to the water temperature.

[0021] The previous day's actual temperature has a significant impact on water temperature, with a coefficient of 0.523. Water temperature is a physical quantity with strong thermal inertia, and the previous day's temperature usually has a significant impact on the current water temperature. This is because the temperature of a water body takes time to change, and the previous day's temperature has a more significant cumulative effect on the water body's temperature. Especially in the absence of drastic weather changes, the previous day's temperature determines the basic level of water temperature. Therefore, It is set to 0.523, indicating that the previous day's actual air temperature has the strongest impact on the forecast water temperature for the day.

[0022] The influence of the actual water temperature of the previous day is the smallest, with a coefficient of 0.147. The influence of the water temperature of the previous day is continuous, but the influence is relatively weak, because the water temperature will adjust with the temperature and environmental changes of the day. The water temperature of the previous day provides a certain initial condition for the current water temperature, but because the water body has a certain amount of time to adapt to the temperature change, the water temperature is less dependent on the water temperature of the previous day. Therefore, is set to , indicating that the influence of the water temperature on the previous day on the predicted water temperature is relatively weak.

[0023] S7. Input the daily forecast water temperature of the target grid into the output tool to obtain a water temperature forecast grid distribution map of the fish pond.

[0024] Specifically, in this embodiment, the water temperature forecast grid distribution map refers to a grid distribution map generated using the daily forecast temperature for the target grid. Specifically, this grid distribution map represents the water temperature forecast for each grid in the entire fish pond. Each grid in the map represents a specific spatial unit, and the water temperature value for each grid is calculated using a model based on its surrounding environmental conditions (such as temperature, flow direction, slope, etc.).

[0025] This example constructs a fish pond grid map and combines data from multiple candidate sites to predict water temperature for each grid in the pond. This method leverages the spatial relationship between the target grid and multiple candidate sites, combined with multiple factors such as the previous day's actual air temperature, the current day's forecasted air temperature, and the previous day's actual water temperature, to calculate the current day's forecast water temperature for each grid. The resulting water temperature forecast grid distribution map visually displays the water temperature distribution across the pond, providing data support for fish pond aquaculture management.

[0026] Example 2: See Figures 2 to 3 The technical solution of this embodiment 2 is different from that of embodiment 1 in that the following exemplary steps are disclosed. For example, the step of constructing a fish pond grid map includes: S1-1. Obtain the coordinates of the boundary points of the fish pond; S1-2. Determine the coordinates of the center of the fish pond based on the coordinates of the boundary points of the fish pond; It should be noted that the shape of most fish ponds is an irregular plane shape, so the center coordinates of the fish pond can be calculated based on the coordinates of the boundary points. Specifically, if the boundary of the fish pond is an irregular polygon (such as an uneven shape), the centroid method can be used to calculate the center coordinates of the fish pond. The centroid refers to the weighted average position of all points in the polygon. The centroid method is suitable for irregularly shaped water areas because it can derive the geometric center of the fish pond by considering the distribution of all boundary points, rather than just a simple geometric center point. In actual operation, the coordinates of the boundary points of the fish pond may not be completely closed, and it is necessary to first compare the boundary point coordinates for a closing operation to ensure the accuracy of the calculation.

[0027] S1-3, using the center coordinates of the fish pond as the drawing origin, and constructing an origin fish pond grid with a predefined grid side length; wherein the intersection of the diagonals of the origin fish pond grid coincides with the drawing origin; S1-4, repeatedly constructing fish pond grids in the four neighborhoods of the origin fish pond grid until the fish pond grid distribution at least covers the coordinates of all boundary points; S1-5. Define the fish pond grid distribution covering all boundary point coordinates as a fish pond grid map.

[0028] Because fish ponds typically have irregular planar shapes, this embodiment uses the centroid method to determine the center coordinates of the fish pond. This method accurately calculates the geometric center of the fish pond based on the coordinates of its boundary points. By gridding the area around the fish pond's center coordinates with a predefined grid length and gradually expanding it to cover the entire pond area, a complete fish pond grid map is ultimately constructed. This gridding method allows each grid cell in the spatial distribution of the fish pond to function as an independent calculation unit, effectively capturing water temperature variations across different grid areas.

[0029] Exemplarily, the fish pond grid is repeatedly constructed on the four neighborhoods of the origin fish pond grid until the fish pond grid distribution at least covers all boundary point coordinates, including: S1-4-1. Obtain the coordinates of the center of the fish pond and the four equal sides of the origin fish pond grid; S1-4-2. For any equal side lengths, mark the coordinates of the midpoint of the side length; S1-4-3. Starting from the center coordinate of the fish pond, extend the neighborhood dotted line in the direction of the midpoint coordinate of the side length; S1-4-4. Calculate the extension length of the neighborhood dashed line; S1-4-5. If the extended length of the neighborhood dashed line is twice the distance from the center coordinate of the fish pond, stop extending the neighborhood dashed line and define the end of the neighborhood dashed line as the neighborhood grid coordinate; S1-4-6, constructing a neighborhood grid according to the neighborhood grid coordinates and the predefined grid side length; S1-4-7. Starting from the neighborhood grid coordinates, extend the neighborhood dotted line in the direction where the neighborhood grid is not constructed, and repeat S1-4-1-4 to S1-4-7 until all boundary point coordinates are covered by the neighborhood grid.

[0030] This embodiment ensures that the fish pond grid distribution can cover the entire fish pond boundary by gradually expanding the grid on the four neighborhoods of the origin fish pond grid. Specifically, the center coordinates of the fish pond and the four equal sides of the origin fish pond grid are first determined. By marking the midpoint coordinates of each side length, a neighborhood dotted line extending from the center of the fish pond to each side length is established, and the extension length is calculated. The dotted line stops when it extends to twice the distance from the center of the fish pond, and the end of the dotted line is defined as the neighborhood grid coordinate. Finally, the complete fish pond grid coverage is gradually expanded to ensure that all boundary points are included. By accurately covering all boundary points and by gradually expanding the grid, the problem of incomplete grid coverage due to irregular shapes is effectively avoided.

[0031] Exemplarily, obtaining M candidate site coordinates in the same coordinate system as the fish pond grid map includes: S2-1. Obtain the coordinates of N temperature measurement stations in the same coordinate system as the fish pond grid map; S2-2, calculating the N first coordinate distances between the coordinates of the N temperature measurement stations and the coordinates of the center of the fish pond; S2-3, selecting M second coordinate distances from the N first coordinate distances; S2-4. Obtain M candidate site coordinates corresponding to the second coordinate distance from the N temperature measurement site coordinates.

[0032] Specifically, the spatial relationship between the center of the fish pond and all stations is determined by calculating the first coordinate distance between each temperature measurement station and the center of the fish pond. Then, based on these calculated first coordinate distances, the M stations with the shortest distances to the center of the fish pond are selected. These M stations are considered to have the greatest impact on the changes in the water temperature of the fish pond. Selecting stations with close distances as candidate stations ensures the relevance of the selected data to the water temperature of the fish pond.

[0033] Exemplarily, selecting M second coordinate distances from N first coordinate distances includes: S2-3-1. Order the N first coordinate distances in ascending order to generate a first sequence; S2-3-2. Select the shortest first coordinate distance from the first sequence as the second coordinate distance, and add it to the second sequence; S2-3-3. Repeat S2-3-2 until there are M second coordinate distances in the second sequence.

[0034] In this example, a first sequence is generated by sorting N first coordinate distances in ascending order. The coordinates with the shortest distances from the first sequence are then selected as second coordinate distances and added to the second sequence until the second sequence contains the M shortest coordinate distances. This step ensures that the M candidate sites with the shortest distances to the pond center are selected to maximize correlation with water temperature changes.

[0035] Exemplarily, determining the previous day's actual temperature and the current day's forecast temperature of the target grid based on the coordinates of the M candidate sites includes: S3-1, obtaining the grid coordinates of each fish pond grid in the fish pond grid map; S3-2, calculating the Euclidean distance between the target grid and the coordinates of M candidate sites; S3-3, obtaining the previous day's actual temperature and the current day's forecast temperature of the coordinates of M candidate stations; S3-4, determining the previous day's actual temperature and the current day's forecast temperature of the target grid based on the previous day's actual temperature and the current day's forecast temperature of the M candidate site coordinates, and the Euclidean distance between the target grid and the M candidate site coordinates; The calculation formula for the actual temperature of the previous day of the target grid is: ; The calculation formula for the daily forecast temperature of the target grid is: ; in, Represents grid coordinates The previous day's actual temperature, Represents grid coordinates The forecast temperature for the day is represents the actual temperature of the previous day at the i-th candidate station, represents the daily forecast temperature of the i-th candidate station, Represents grid coordinates The Euclidean distance between the i-th candidate site, that is, , and is the coordinate of the first candidate site; Indicates the distance attenuation index. In this embodiment, 2 is selected, indicating that the farther the candidate site is, the smaller its site weight is.

[0036] That is to say, for each fish pond grid corresponding to a grid station, its actual temperature on the previous day and the forecast temperature on the current day are both determined by the Euclidean distance between it and the M candidate stations. The closer the candidate station is, the greater its influence on the temperature of the grid point is, thus ensuring that the temperature of each grid point is determined by weighted interpolation from multiple stations.

[0037] In this embodiment, the previous day's actual temperature and the current day's forecast temperature for the target grid are calculated using distance-weighted interpolation. Specifically, the coordinates of each fish pond grid are first obtained, and the Euclidean distance between that grid and the M candidate sites is calculated. Next, the previous day's actual temperature and the current day's forecast temperature for each candidate site are obtained. The data for each candidate site is weighted using the inverse of the Euclidean distance. This ensures that closer sites have a greater impact on the target grid's temperature, thereby improving the relevance of the temperature calculation.

[0038] Exemplarily, the selecting K anchor grids from the fish pond grid map includes: S4-1. Calculate the Euclidean distance between the target grid and all boundary point coordinates; S4-2, determining the average distance between the target grid and the coordinates of all boundary points based on the Euclidean distance between the target grid and the coordinates of all boundary points; S4-3. Calculate the standard deviation of the target grid based on the average distance and Euclidean distance between the target grid and all boundary point coordinates until a set of standard deviations of all grid coordinates is obtained; S4-4. Select the maximum standard deviation from the standard deviation set of all grid coordinates in turn, and match the corresponding grid based on the maximum standard deviation as the anchor grid; S4-5. Repeat 4-4 until L anchor grids are obtained.

[0039] In this embodiment, the introduction of standard deviation is used to evaluate the uniformity of spatial distribution between the target grid and the boundary point coordinates. Specifically, the Euclidean distance between the target grid and all boundary point coordinates is calculated, and the standard deviation of each grid is calculated based on these distances. The standard deviation reflects the degree of dispersion of the distance between the target grid and the boundary point coordinates. A grid with a larger standard deviation indicates that the difference in distance from the second boundary point is larger, which means that the grid is more evenly distributed in space, neither too close to the boundary nor too far away from the boundary. The selection of the maximum standard deviation makes the selected anchor grid have a more uniform spatial distribution, because it does not deviate too far from the boundary, nor is it too close to the boundary, so it can be defined as a grid representing the temperature change in the fish pond area. Through this step, the spatial distribution of the anchor grid is more balanced, avoiding the prediction error caused by the anchor grid being too concentrated or deviating from the boundary point.

[0040] Exemplarily, determining the previous day's actual water temperature of the target grid based on the K anchor grids includes: S5-1. Calculate the Euclidean distance between the target grid and K anchor grids; S5-2, obtaining the measured water temperature of K anchor grids on the previous day; It should be noted that the previous day's measured water temperature for the anchor grid refers to real-time water temperature data collected by water temperature sensors or temperature detection instruments within the fish pond. These devices are deployed at various locations in the fish pond to collect actual water temperature information. The previous day's water temperature data reflects the actual measured temperature conditions.

[0041] S5-3, determining the actual water temperature of the target grid on the previous day based on the actual water temperatures of the K anchor grids on the previous day and the Euclidean distances between the target grid and the K anchor grids; The calculation formula for determining the actual water temperature of the target grid on the previous day is: ; in, Indicates the actual water temperature of the target grid on the previous day (i.e. the actual water temperature of the target grid on the previous day). represents the water temperature measured on the previous day by the i-th anchor grid, represents the Euclidean distance between the target grid and the anchor grid, represents the water flow direction angle between the i-th anchor grid and the target; Indicates the water flow direction angle of the target grid, represents the bottom slope difference between the target grid and the i-th anchor grid, and k represents the influence coefficient of controlling the bottom slope difference; Specifically, this calculation incorporates the correlation between the angular difference in water flow direction between the target grid and the anchor grid. If the water flow directions are the same, the correlation is high; conversely, if the water flow directions differ significantly, the correlation is low. Furthermore, the correlation between the bottom slope difference is also incorporated. In other words, the greater the bottom slope difference between the target grid and the anchor grid, the more dramatic the water temperature change. In other words, the farther the anchor grid is, the less impact it has on the target grid's water temperature. The closer the anchor grid's water flow direction, the greater its impact on the target grid's water temperature. The greater the bottom slope difference, the greater the impact of the anchor grid on the target grid's water temperature.

[0042] In this embodiment, the previous day's actual water temperature of the target grid is calculated by inferring the previous day's measured water temperature of the anchor grid and related environmental factors. Although the previous day's actual water temperature of the anchor grid is collected in real time at multiple locations within the pond using water temperature sensors or temperature detection instruments, due to the typically large number of grids in a pond, it is impractical to measure the water temperature of each grid. This means that the number of target grids is typically much greater than the number of anchor grids. Therefore, the previous day's actual temperature of the anchor grid is used to infer the water temperature of other unmeasured areas.

[0043] In this embodiment, the Euclidean distance is used to measure the spatial proximity between the target grid and the anchor grid. The closer the distance is, the greater the impact of the grid on the water temperature of the target grid. Secondly, the water flow direction angle takes into account the impact of water flow on water temperature transmission. The closer the water flow direction is, the stronger the impact on the water temperature of the target grid. Finally, the bottom slope difference reflects the regulatory effect of the terrain on water temperature changes. The greater the slope difference in the area, the more drastic the water temperature change, and the weight increases accordingly. By introducing the above parameters, this embodiment can more accurately infer the actual water temperature of the target grid on the previous day based on the actual water temperature measured on the anchor grid on the previous day, thereby ensuring higher prediction accuracy and greater spatial consistency of the actual water temperature of the target grid on the previous day.

[0044] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiments of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired method (e.g., infrared, wireless, microwave, etc.).

[0045] The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., DVD ), or semiconductor media. The semiconductor media may be a solid-state drive.

[0046] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative, and for example, multiple units or components can be combined or integrated into another system, or some features can be omitted or not implemented. In addition, the coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of devices or units, and can be electrical, mechanical, or other forms.

[0047] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A method for predicting fish pond water temperature based on intelligent grid forecast data, characterized in that: include: S1, constructing a fish pond grid map; Wherein, the fish pond grid map includes a number of grid coordinates; S2. Obtain the coordinates of M candidate sites in the same coordinate system as the fish pond grid map; S3. Determine the previous day's actual temperature and the current day's forecast temperature of the target grid based on the coordinates of the M candidate stations; S4, select K anchor grids in the fish pond grid map; S5. Determine the actual water temperature of the target grid on the previous day based on the K anchor grids; S6. Determine the forecast water temperature for the target grid on the current day based on the actual water temperature of the target grid on the previous day, the actual air temperature of the target grid on the previous day, and the forecast air temperature for the current day; S7. Input the daily forecast water temperature of the target grid into the output tool to obtain a water temperature forecast grid distribution map of the fish pond.

2. The method for predicting fish pond water temperature based on intelligent grid forecast data according to claim 1, characterized in that: Construct a fish pond grid map, including: S1-1. Obtain the coordinates of the boundary points of the fish pond; S1-2. Determine the coordinates of the center of the fish pond based on the coordinates of the boundary points of the fish pond; S1-3, using the center coordinates of the fish pond as the drawing origin, and constructing an origin fish pond grid with a predefined grid side length; wherein the intersection of the diagonals of the origin fish pond grid coincides with the drawing origin; S1-4, repeatedly constructing fish pond grids in the four neighborhoods of the origin fish pond grid until the fish pond grid distribution at least covers the coordinates of all boundary points; S1-5. Define the fish pond grid distribution covering all boundary point coordinates as a fish pond grid map.

3. The method for predicting fish pond water temperature based on intelligent grid forecast data according to claim 2, characterized in that: Repeatedly construct the fish pond grid on the four neighborhoods of the origin fish pond grid until the fish pond grid distribution at least covers the coordinates of all boundary points; including: S1-4-1. Obtain the coordinates of the center of the fish pond and the four equal sides of the origin fish pond grid; S1-4-2. For any equal side lengths, mark the coordinates of the midpoint of the side length; S1-4-3. Starting from the center coordinate of the fish pond, extend the neighborhood dotted line in the direction of the midpoint coordinate of the side length; S1-4-4. Calculate the extension length of the neighborhood dashed line; S1-4-5. If the extended length of the neighborhood dashed line is twice the distance from the center coordinate of the fish pond, stop extending the neighborhood dashed line and define the end of the neighborhood dashed line as the neighborhood grid coordinate; S1-4-6, constructing a neighborhood grid according to the neighborhood grid coordinates and the predefined grid side length; S1-4-7. Starting from the neighborhood grid coordinates, extend the neighborhood dotted line in the direction where the neighborhood grid is not constructed, and repeat S1-4-1-4 to S1-4-7 until all boundary point coordinates are covered by the neighborhood grid.

4. The method for predicting fish pond water temperature based on intelligent grid forecast data according to claim 1, characterized in that: Get the coordinates of M candidate sites in the same coordinate system as the fish pond grid map, including: S2-1. Obtain the coordinates of N temperature measurement stations in the same coordinate system as the fish pond grid map; S2-2, calculating the N first coordinate distances between the coordinates of the N temperature measurement stations and the coordinates of the center of the fish pond; S2-3, selecting M second coordinate distances from the N first coordinate distances; S2-4. Obtain M candidate site coordinates corresponding to the second coordinate distance from the N temperature measurement site coordinates.

5. The method for predicting fish pond water temperature based on intelligent grid forecast data according to claim 1, characterized in that: Select M second coordinate distances from N first coordinate distances, including: S2-3-1. Order the N first coordinate distances in ascending order to generate a first sequence; S2-3-2. Select the shortest first coordinate distance from the first sequence as the second coordinate distance, and add it to the second sequence; S2-3-3. Repeat S2-3-2 until there are M second coordinate distances in the second sequence.

6. The method for predicting fish pond water temperature based on intelligent grid forecast data according to claim 1, characterized in that: Based on the coordinates of M candidate stations, determine the previous day's actual temperature and the current day's forecast temperature for the target grid, including: S3-1, obtaining the grid coordinates of each fish pond grid in the fish pond grid map; S3-2, calculating the Euclidean distance between the target grid and the coordinates of M candidate sites; S3-3, obtaining the previous day's actual temperature and the current day's forecast temperature of the coordinates of M candidate stations; S3-4, determining the previous day's actual temperature and the current day's forecast temperature of the target grid based on the previous day's actual temperature and the current day's forecast temperature of the M candidate site coordinates, and the Euclidean distance between the target grid and the M candidate site coordinates; The calculation formula for the actual temperature of the previous day of the target grid is: ； The calculation formula for the daily forecast temperature of the target grid is: ； in, Represents grid coordinates The previous day's actual temperature, Represents grid coordinates The forecast temperature for the day is represents the actual temperature of the previous day at the i-th candidate station, represents the daily forecast temperature of the i-th candidate station, Represents grid coordinates The Euclidean distance between the i-th candidate site, Represents the distance attenuation index, which means that the farther the candidate site is, the smaller its site weight is.

7. The method for predicting fish pond water temperature based on intelligent grid forecast data according to claim 1, characterized in that: Select K anchor grids from the fish pond grid map, including: S4-1. Calculate the Euclidean distance between the target grid and all boundary point coordinates; S4-2, determining the average distance between the target grid and the coordinates of all boundary points based on the Euclidean distance between the target grid and the coordinates of all boundary points; S4-3. Calculate the standard deviation of the target grid based on the average distance and Euclidean distance between the target grid and all boundary point coordinates until a set of standard deviations of all grid coordinates is obtained; S4-4. Select the maximum standard deviation from the standard deviation set of all grid coordinates in turn, and match the corresponding grid based on the maximum standard deviation as the anchor grid; S4-5. Repeat 4-4 until L anchor grids are obtained.

8. The method for predicting fish pond water temperature based on intelligent grid forecast data according to claim 1, characterized in that: Based on the K anchor grids, determine the actual water temperature of the target grid on the previous day, including: S5-1. Calculate the Euclidean distance between the target grid and K anchor grids; S5-2, obtaining the measured water temperature of K anchor grids on the previous day; S5-3, determining the actual water temperature of the target grid on the previous day based on the actual water temperatures of the K anchor grids on the previous day and the Euclidean distances between the target grid and the K anchor grids; The calculation formula for determining the actual water temperature of the target grid on the previous day is: ； in, Indicates the actual water temperature of the target grid the previous day. represents the water temperature measured on the previous day at the i-th anchor grid, represents the Euclidean distance between the target grid and the anchor grid, represents the water flow direction angle between the i-th anchor grid and the target; Indicates the water flow direction angle of the target grid, represents the bottom slope difference between the target grid and the i-th anchor grid, and k represents the influence coefficient of controlling the bottom slope difference.

Images