A water regime safety monitoring method based on digital twin

Abstract

The present invention relates to the technical field of environmental monitoring. The present invention relates to a water regime safety monitoring method based on digital twin. The method includes: collecting historical water regime data, and drawing a precipitation curve and a water level curve according to the historical water regime data; determining associated segments; calculating the lag period of the associated segments, and performing weighted summation on all lag periods belonging to positive numbers to obtain a target lag period; obtaining precipitation data at a set time and before the target lag period of the set time, and inputting the precipitation data into a trained ARIMA model to predict the water level at the set time. Based on the complex lag relationship between precipitation and water level changes, the present invention predicts water level changes according to historical precipitation data and the target lag period, improving the accuracy of water level prediction.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental monitoring. More specifically, the present invention relates to a water regime safety monitoring method based on digital twin. Background Art

[0002] Floods are relatively common and destructive natural disasters. Based on conditions such as precipitation intensity and basin topography, floodwaters can rise sharply in a short period of time, causing serious property damage and casualties. Water level monitoring can timely detect the trend of abnormal water level rise by collecting water level data in real time, thereby providing support for flood prevention early warning, drainage measures, and evacuation decision-making. Therefore, water level monitoring plays a crucial role in water regime safety management.

[0003] The prior art usually monitors the water levels at locations such as rivers, lakes, and reservoirs in real time, and issues alarms when the water level exceeds the safety warning value, and takes measures such as flood discharge and evacuation of people. The Chinese patent application document with the publication number CN116524515A discloses a real-time water level monitoring method based on computer vision, which includes: taking an image of the area with a water level gauge in the monitored water area; performing HSV transformation on the taken image of the area with a water level gauge in the monitored water area to initially obtain the image of the water level gauge area; performing image tilt correction on the initially obtained image of the water level gauge area; performing image segmentation on the tilted corrected picture to extract the image containing only the water level gauge area; performing character segmentation on the extracted image containing only the water level gauge area to obtain a character image; and determining the height of the water level according to the character image.

[0004] Since precipitation is an important factor affecting water level changes, the prior art also predicts the water level through a neural network model based on the precipitation amount. However, there is a certain time difference between the arrival of precipitation and the water level change. The increase in precipitation amount does not immediately cause the water level to rise. In some cases, even after the precipitation has ended, the water levels in some areas of the basin may still be affected for a long time. This means that the impact of precipitation on the water level does not appear immediately, but as time goes by, the water gradually accumulates, and only then will the water level show a significant change. Therefore, when using the ARIMA model to monitor and predict the water level, if the real-time precipitation amount is directly used as input data, the prediction of the ARIMA model may be inaccurate due to the lag of the precipitation affecting the water level change. Summary of the Invention

[0005] To solve the above technical problem that directly using the real-time precipitation amount as input data may lead to inaccurate prediction of the ARIMA model, the present invention provides a water regime safety monitoring method based on digital twin.

[0006] A water regime safety monitoring method based on digital twin includes: collecting historical water regime data, and drawing a precipitation curve and a water level curve according to the historical water regime data; using the data point before an inflection point between two adjacent peaks in the precipitation curve or the water level curve as a segmentation point to divide the corresponding curve into multiple segments; when the absolute value of the difference between the time of the peak in any segment of the water level curve and the time of the peak in a certain segment of the precipitation curve is less than a threshold value, determining that the corresponding segments of the precipitation curve and the water level curve are mutually related segments; for all related segments of the segments, determining the related segment with the largest peak among them as the associated segment of the segment; calculating the lag period of the associated segment G m , and performing weighted summation on all lag periods that are positive numbers to obtain the target lag period; where , F m is the time of the peak in the precipitation curve, E m is the time of the inflection point closest to the peak in the precipitation curve, f m is the time of the peak in the water level curve, e m is the time of the inflection point closest to the peak in the water level curve, and E m < F m 、 e m < f m ; obtaining the precipitation data of the target lag period before the set time and the set time, and inputting it into the trained ARIMA model to predict the water level at the set time.

[0007] The beneficial effects of the present invention are as follows: After segmenting the precipitation curve and the water level curve, the present invention matches the precipitation curve segments and the water level segment curves with similar characteristics according to the peaks and specific inflection points of each segment, and calculates the time difference between each pair of matched segments (i.e., each pair of associated segments), so as to obtain the lag period of the influence of precipitation on the water level through each segment. Then, by performing weighted summation on the lag periods greater than 0 corresponding to each pair of matched segments, the lag period of the influence of precipitation on the water level as a whole, that is, the target lag period, is obtained. Based on this, the present invention can predict the water level according to the rainfall data at a certain time distance before the moment of the expected predicted water level to obtain a more accurate water level prediction result, where the certain time distance is the target lag period.

[0008] Preferably, the weighted sum of all positive lag periods is calculated to obtain the target lag period, which includes: taking the associated segments with positive lag periods as the target associated segments, calculating the weights of the lag periods for each pair of target associated segments, where the weight of the lag period for a pair of target associated segments is proportional to the DTW distance between the two segments; and performing a weighted sum of the lag periods for each pair of target associated segments: , where G is the target lag period, is the i lag period for the η i th pair of target associated segments, i is the weight of the lag period for the N th pair of target associated segments, and

[0009] is the total number of pairs of target associated segments. n Preferably, calculating the weight of the lag period for the n th pair of target associated segments includes: calculating the DTW distance between the two segments in each pair of target associated segments; and calculating the weight of the lag period for the th pair of target associated segments: , where n is the weight of the lag period for the H n th pair of target associated segments, n is the DTW distance between the associated segments in the n th pair of associated segments, and the exp() function is the exponential function with the natural constant e as the base,

[0010] Based on the present invention, after determining the weights corresponding to each pair of target associated segments according to the correlation between the two segments in each pair of target associated segments (i.e., the DTW distance between the two segments), a weighted sum of the lag periods for each pair of target associated segments is performed to obtain the target lag period. Moreover, the stronger the correlation between the two segments in a pair of target associated segments, that is, the smaller the DTW distance between the two segments, the greater the weight of the lag period for this pair of target associated segments. Based on this, the target lag period can better reflect the time lag effect of precipitation on water level.

[0011] Preferably, calculating the DTW distance between two segments in a pair of target-associated segments includes: obtaining the precipitation data at multiple moments included in the segment corresponding to the precipitation curve in a pair of target-associated segments, denoted as the first sequence; obtaining the water level data at multiple moments included in the segment corresponding to the water level curve in a pair of target-associated segments, denoted as the second sequence, where the data in the first sequence and the second sequence are arranged in time series; linearly scaling the sequence with fewer data points in the first sequence and the second sequence so that the first sequence and the second sequence have the same number of data points; after linearly scaling the first sequence or the second sequence, calculating the DTW distance between the first sequence and the second sequence to obtain the DTW distance between two segments in a pair of target-associated segments.

[0012] The present invention makes the number of data points in the two sequences the same through linear scaling, ensuring the alignment of the precipitation and water level curves in time.

[0013] Preferably, drawing the precipitation curve includes: after preprocessing the historical water regime data, obtaining the precipitation data in the historical water regime data, where preprocessing the historical water regime data includes denoising the historical water regime data, removing outliers, and filling in missing values; fitting the precipitation data into a first curve through a fitting algorithm; smoothing the first curve to obtain the precipitation curve.

[0014] The present invention smooths the first curve fitted according to the precipitation data to obtain the precipitation curve, and the smoothing process reduces noise and ensures the continuity of the precipitation curve.

[0015] Preferably, drawing the water level curve includes: after preprocessing the historical water regime data, obtaining the water level data in the historical water regime data, where preprocessing the historical water regime data includes denoising the water level data, removing outliers, and filling in missing values; fitting the water level data into a second curve through a fitting algorithm; smoothing the second curve to obtain the water level curve.

[0016] The present invention smooths the first curve fitted according to the water level data to obtain the water level curve, and the smoothing process reduces noise and ensures the continuity of the water level curve.

[0017] Preferably, constructing the ARIMA model includes: obtaining a training set, where the training set includes multiple training data, where the collection moments corresponding to the water level or precipitation in each training data are different, and the difference between the collection moment of the water level and the collection moment of the precipitation in the training data is equal to the lag period; obtaining an initial ARIMA model, where the parameters of the initial ARIMA model are all preset values; training the initial ARIMA model with the training set to obtain the ARIMA model.

[0018] Preferably, obtaining precipitation data at a set time and before the target lag period of the set time and inputting it into the trained ARIMA model to predict the water level at the set time includes: determining the set time; after inputting the precipitation data before the target lag period of the set time into the ARIMA model, determining the output of the ARIMA model as the result of predicting the water level at the set time.

[0019] The beneficial effects of the present invention are as follows:

[0020] By segmentally matching the precipitation and water level curves and combining the dynamic time warping distance, i.e., the DTW distance, to calculate the correlation of each pair of segments, the present invention can more accurately capture the lag effect of precipitation on the water level. Based on the complex lag relationship between precipitation and water level changes, the present invention predicts water level changes according to historical precipitation data and the target lag period, improving the accuracy of water level prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features, and advantages of the exemplary embodiments of the present invention will become readily understood. In the drawings, several embodiments of the present invention are shown by way of illustration and not limitation, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0022] Figure 1 is a schematic flowchart showing the steps of a digital twin-based water regime safety monitoring method according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] Hereinafter, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0024] The following will describe the specific embodiments of the present invention in detail with reference to the drawings.

[0025] Figure 1 is a schematic flowchart showing the steps of a digital twin-based water regime safety monitoring method according to an embodiment of the present invention.

[0026] As Figure 1 shown, a digital twin-based water regime safety monitoring method includes steps S1 to S5.

[0027] Step S1: Collect historical water regime data and draw precipitation curves and water level curves according to the historical water regime data.

[0028] Among them, the historical water regime data includes precipitation data and water level data. In one embodiment, in the time period from the first predetermined moment to the second predetermined moment, the discrete data collected by the rainfall sensor at a frequency f 0 is denoted as precipitation data; in the time period from the first predetermined moment to the second predetermined moment, the discrete data collected by the water level sensor at a frequency f 0 is denoted as water level data. In this embodiment, the rainfall sensor and the water level sensor are at the same location.

[0029] In one embodiment, drawing the precipitation curve includes: after preprocessing the historical water regime data, obtaining the precipitation data in the historical water regime data, where preprocessing the historical water regime data includes denoising the historical water regime data, removing outliers, and filling in missing values; fitting the precipitation data into a first curve through a fitting algorithm; and smoothing the first curve to obtain the precipitation curve. Drawing the water level curve includes: after preprocessing the historical water regime data, obtaining the water level data in the historical water regime data, where preprocessing the historical water regime data includes denoising the water level data, removing outliers, and filling in missing values; fitting the water level data into a second curve through a fitting algorithm; and smoothing the second curve to obtain the water level curve.

[0030] It should be noted that both the precipitation curve and the water level curve are time series curves. A time series curve represents a curve of data changing over time, and a time series curve visualizes the numerical relationship between time (usually the independent variable) and a variable (precipitation or water level in the present invention) at consecutive time points.

[0031] Furthermore, when fitting the water level data and the precipitation data, the same fitting algorithm is used. The fitting algorithm can be algorithms such as polynomial regression, spline curve (Spline Fitting) fitting, etc. Among them, polynomial regression is a method that extends linear regression. Polynomial regression captures the non-linear relationship of data (i.e., precipitation or water level) by raising the independent variable (i.e., precipitation or water level) to a high power. Spline curves are smooth curves generated through a given set of control points.

[0032] Step S2: Using the data point immediately preceding an inflection point between two adjacent peaks in the precipitation curve or the water level curve as the segmentation point, divide the corresponding curve into multiple segments.

[0033] Among them, the target curve is a precipitation curve or a water level curve. It should be noted that for a smooth curve, there is at least one inflection point between two peaks, and any one of the inflection points between the two peaks is the inflection point. When segmenting the precipitation curve (i.e., when the target curve is a precipitation curve), the target curve segmentation point is the point on the precipitation curve at the moment before the inflection point. When segmenting the water level curve (i.e., when the target curve is a water level curve), the target curve segmentation point is the point on the upper water level curve at the moment before the inflection point.

[0034] In another embodiment, the segmentation point is the data point at the moment before the inflection point that is closest to the larger peak between the two peaks (i.e., the previous data point).

[0035] Step S3: Determine the associated segments.

[0036] Among them, determining the associated segments includes: using the data point at the moment before an inflection point between two adjacent peaks in the precipitation curve or the water level curve as the segmentation point to divide the corresponding curve into multiple segments; when the absolute value of the difference between the moment of the peak in any segment of the water level curve and the moment of the peak in a certain segment of the precipitation curve is less than the threshold, determine that the corresponding segments of the precipitation curve and the water level curve are mutually associated segments; for all the associated segments of the segments, determine the associated segment with the largest peak among them as the associated segment of the segment. In one embodiment, the threshold is 5 days.

[0037] It should be noted that during the corresponding process, there may be multiple segments of the precipitation curve that are mutually associated segments with the same segment of the water level curve. Because the small precipitation intensity has little impact on the water level change, select the segment with the highest precipitation peak among them to correspond to a segment of the water level curve, and determine that the two are mutually associated segments; similarly, if there are multiple segments of the water level curve that are mutually associated segments with the same segment of the precipitation curve, then select the segment of the water level curve with the most obvious water level change, that is, the largest peak, to correspond to a segment of the precipitation curve, and determine that the two are mutually associated segments.

[0038] Step S4: Calculate the lag period of the associated segments G m , and perform a weighted sum of all the lag periods that are positive numbers to obtain the target lag period.

[0039] Among them, , F m is the moment of the peak in the precipitation curve, E m is the moment of the inflection point closest to the peak in the precipitation curve, f m is the moment of the peak in the water level curve, em is the moment of the inflection point closest to the peak in the water level curve, and E m < F m 、 e m < f m 。

[0040] In one embodiment, G m is the lag period of the m th pair of associated segments. It should be noted that the m th pair of associated segments includes two segments. One is obtained by segmenting the precipitation curve, so this segment belongs to the segment of the precipitation curve. The other is obtained by segmenting the water level curve, so this segment belongs to the segment of the water level curve. When segmenting a curve (the curve is the precipitation curve or the water level curve), the data point immediately preceding the inflection point (any one) between two adjacent peaks is the segmentation point. Therefore, any segment of the curve includes a peak and at least one inflection point. The present invention selects the inflection point with the shortest time distance from the peak and located before the peak in time sequence, and the average value of the time difference between the selected inflection points of the two segments that are mutually associated segments and the time difference between the peaks reflects the lag of the influence of precipitation data on water level data.

[0041] In one embodiment, all the lag periods that are positive are weighted and summed to obtain the target lag period: taking the associated segments with positive lag periods as the target associated segments, calculating the weights of the lag periods of each pair of target associated segments, where the weight of the lag period of a pair of target associated segments is proportional to the DTW (Dynamic Time Warping) distance between the two segments; weighting and summing the lag periods of each pair of target associated segments: , where G is the target lag period, is the lag period of the i th pair of target associated segments, η i is the weight of the lag period of the i th pair of target associated segments, N is the total number of pairs of target associated segments. In this embodiment, calculating the weight of the lag period of the n th pair of associated segments includes: calculating the DTW distance between the two segments in each pair of associated segments; calculating the weight of the lag period of the n th pair of associated segments: , where is the weight of the lag period of the n th pair of target associated segments, H nis the n For the DTW distance between associated segments, the exp() function is the exponential function with the natural constant e as the base, n is a positive integer.

[0042] It should be noted that for a pair of associated segments, the DTW distance between the two segments included therein reflects the correlation between the two segments, and at the same time reflects the correlation between the precipitation data and the water level data within the two segments. The larger the DTW distance between the two segments, the smaller the correlation between the two segments, the smaller the correlation between the precipitation data and the water level data within the two segments, and the smaller the weight corresponding to this pair of associated segments.

[0043] In another embodiment, the weights of the lag periods of each pair of target associated segments are the same, and are all , N is the total number of pairs of associated segments.

[0044] In another embodiment, the weights of the lag periods of each pair of target associated segments are all empirical values, and the sum of the weights of the lag periods of each pair of target associated segments is equal to 1.

[0045] In one embodiment, calculating the DTW distance between associated segments includes: obtaining the precipitation data at multiple moments included in the segment corresponding to the precipitation curve in the associated segment, denoted as the first sequence; obtaining the water level data at multiple moments included in the segment corresponding to the water level curve in the associated segment, denoted as the second sequence, where the data in the first sequence and the second sequence are arranged in time series; linearly scaling the sequence with fewer data among the first sequence and the second sequence so that the first sequence and the second sequence have the same number of data; after linearly scaling the first sequence or the second sequence, calculating the DTW distance between the first sequence and the second sequence to obtain the DTW distance between the associated segments.

[0046] It should be noted that when calculating the DTW distance between associated segments, the purpose of linearly scaling the sequence with fewer data is to make the two sequences have the same length on the time axis so as to enable effective comparison and distance calculation.

[0047] Step S5: Obtain the precipitation data at the set moment and the target lag period before the set moment, and input it into the trained ARIMA model to predict the water level at the set moment.

[0048] Among them, a training data of the ARIMA model includes t the water level at time 1 and t the precipitation at time 2, t 1 - t 2 = G。In one embodiment, constructing the ARIMA model includes: obtaining a training set, which is a time series data set and includes a plurality of training data, where the collection times corresponding to the water level or precipitation in each training data are different, and the difference between the collection time of the water level and the collection time of the precipitation in the training data is equal to the lag period; obtaining an initial ARIMA model, where the parameters of the initial ARIMA model are all preset values; and training the initial ARIMA model with the training set to obtain the ARIMA model. In this embodiment, predicting the water level at a predetermined time includes: obtaining precipitation data at a target time, where the difference between the target time and the predetermined time is equal to the target lag period; and after inputting the precipitation data at the target time into the ARIMA model, determining the output of the ARIMA model as the water level at the predetermined time.

[0049] In another embodiment, the training set includes a plurality of training subsets, and the training subset includes a first time series data set and a second time series data set. The first time series data set includes water level data collected at a predetermined frequency f in a first time period, and the second time series data set includes precipitation data collected at a predetermined frequency f in a second time period. The time lengths of the first time period and the second time period are equal and both are T, and the difference between the initial time of the first time period and the initial time of the second time period is equal to the target lag period. In this embodiment, the ARIMA model trained by the training set receives a time series of precipitation data and outputs a time series of water level data. The time series of precipitation data is historical data (i.e., precipitation data collected before the current time), and the output of the time series of water level data includes water level data at multiple times. Based on the time series of water level data, the water level data at the desired time (the desired time is after the current time) can be obtained. For example, input a time series of precipitation data into the ARIMA model in this embodiment. This time series of precipitation data includes precipitation data collected by a precipitation sensor at a frequency f from time T1 to time T2, and the precipitation data is arranged in chronological order, where T2 - T1 = T. At this time, the ARIMA model inputs a time series of water level data. This time series of water level data includes Q water level data (the water level data is predicted water level data) from time T3 to time T4, and the water level data is arranged in chronological order, where T4 - T3 = T, Q = T × f. At this time, the q-th data in this time series of water level data represents the water level data at time (T3 + q × f), where q is a positive integer and q ≤ Q. Based on this, the water level data at the desired time (i.e., the water level prediction data) can be obtained.

[0050] Further, the precipitation data at any time includes the precipitation at that time. For example, the precipitation value at time t a isA Alternatively, the water level data at any moment includes the average value of the water level within a certain period of time before (including that moment). For example, a the water level data A collected at time t satisfies: , where T represents a positive integer, A i represents the precipitation value at the i -th time point, represents A the sum of the precipitation at each time point from 1 to A T within a certain period of time, A 1 represents the precipitation value at the earliest time point, A from 1 to A T are the water level data at consecutive moments, A T represents the precipitation data at the current moment t a collected.

[0051] In the description of this specification, the meanings of "a plurality of" and "several" are at least two, such as two, three or more, etc., unless otherwise specifically defined.

[0052] Although this specification has shown and described multiple embodiments of the present invention, it is obvious to those skilled in the art that such embodiments are provided only by way of example. Those skilled in the art will think of many changes, alterations and alternative ways without departing from the spirit and idea of the present invention. It should be understood that various alternative solutions to the embodiments of the present invention described herein can be adopted in the practice of the present invention.

Claims

1. A water situation safety monitoring method based on digital twins, characterized in that: include: Collect historical water regime data and draw precipitation curves and water level curves based on the historical water regime data; Taking the previous data point of an inflection point between two adjacent peaks in a precipitation curve or a water level curve as a segmentation point, the corresponding curve is divided into multiple segments; when the absolute value of the difference between the moment of the peak in any segment of the water level curve and the moment of the peak in a segment of the precipitation curve is less than a threshold, the corresponding segments of the precipitation curve and the water level curve are determined to be mutually related segments; for all related segments of the segment, the related segment with the largest peak value is determined as the associated segment of the segment; Calculate the hysteresis period of the associated segment G m , all positive lag periods are weighted summed to obtain the target lag period; , F m is the peak moment in the precipitation curve, E m is the moment of the inflection point closest to the peak in the precipitation curve, f m is the peak moment of the water level curve, e m is the moment of the inflection point closest to the peak in the water level curve, and E m < F m , e m < f m ; The precipitation data at the set time and the target lag period before the set time are obtained, and input into the trained ARIMA model to predict the water level at the set time.

2. A water situation safety monitoring method based on digital twins according to claim 1, characterized in that: The weighted sum of all positive lags to obtain the target lag includes: The association segments whose hysteresis period is positive are taken as target association segments, and the weights of the hysteresis period of each pair of target association segments are calculated, wherein the weights of the hysteresis period of a pair of target association segments are inversely proportional to the DTW distance between the two segments; Weighted summation of the lag periods for each pair of target-associated segments: ,in G is the target lag period, For the i The hysteresis period for target-related segments, η i For the i The weight of the lag period for the target association segment, N The total number of pairs of segments associated with the target.

3. A water situation safety monitoring method based on digital twin according to claim 2, characterized in that: Calculate the n The weights for the lag period of the target association segment include: Calculate the DTW distance between two segments in each pair of target associated segments; Calculate the n Weights for the lag period of the target-related segment: ,in For the n The weight of the lag period for the target association segment, H n For the n For the DTW distance between associated segments, the exp() function is an exponential function with the natural constant e as the base. n Is a positive integer.

4. A water situation safety monitoring method based on digital twins according to claim 3, characterized in that: Calculating the DTW distance between two segments in a pair of target associated segments includes: Obtain precipitation data at multiple moments included in a segment corresponding to a precipitation curve in a pair of target associated segments, recorded as a first sequence; obtain water level data at multiple moments included in a segment corresponding to a water level curve in a pair of target associated segments, recorded as a second sequence, wherein the data in the first sequence and the second sequence are arranged in time sequence; Linearly scaling the sequence with less data in the first sequence and the second sequence so that the first sequence and the second sequence have the same number of data; After linear scaling is performed on the first sequence or the second sequence, the DTW distance between the first sequence and the second sequence is calculated to obtain the DTW distance between two segments in a pair of target associated segments.

5. The water situation safety monitoring method based on digital twin according to claim 1 is characterized in that: Drawing precipitation curves includes: After preprocessing the historical water regime data, the precipitation data in the historical water regime data is obtained, wherein the preprocessing of the historical water regime data includes denoising the historical water regime data, removing outliers, and filling in missing values; Fitting the precipitation data into a first curve through a fitting algorithm; The first curve is smoothed to obtain the precipitation curve.

6. A water situation safety monitoring method based on digital twins according to claim 1, characterized in that: Drawing a water level curve includes: After preprocessing the historical water regime data, water level data in the historical water regime data is obtained, wherein the preprocessing of the historical water regime data includes denoising the water level data, removing abnormal values, and filling in missing values; Fitting the water level data into a second curve through a fitting algorithm; The second curve is smoothed to obtain the water level curve.

7. The water situation safety monitoring method based on digital twin according to claim 1 is characterized in that: Building the ARIMA model includes: Obtaining a training set, the training set comprising a plurality of training data, wherein the collection time corresponding to the water level or precipitation in each training data is different, and the difference between the collection time of the water level and the collection time of the precipitation in the training data is equal to the target lag period; Obtain the ARIMA initial model, where the parameters of the ARIMA initial model are all preset values; The ARIMA initial model is trained using a training set to obtain the ARIMA model.

8. The water situation safety monitoring method based on digital twin according to claim 1 is characterized in that: Obtaining precipitation data at the set time and the target lag period before the set time, and inputting it into the trained ARIMA model to predict the water level at the set time includes: Determine the set time; After the precipitation data of the target lag period before the set time is input into the ARIMA model, the output of the ARIMA model is determined to be the result of predicting the water level at the set time.

Images