Prediction Method and Device for the Recovery Prospect of Dry Lakes

Abstract

The present invention provides a method and device for predicting the recovery prospects of dried-up lakes. The method comprises: obtaining optical remote sensing image data of a target lake area during a period of time when the lake area has not dried up, and calculating the water area data of the target lake area during the period based on the optical remote sensing image data; obtaining gravity satellite data of the target lake area during a period of time, and calculating the terrestrial water storage data of the target lake area during the period based on the gravity satellite data; performing time series decomposition of the terrestrial water storage data to obtain terrestrial water storage decomposition data; determining a target regression model based on the water area data, the terrestrial water storage data, and the terrestrial water storage decomposition data; monitoring the real-time terrestrial water storage changes in the target lake area, and obtaining the inverted water area change trend of the target lake area through the target regression model based on the real-time terrestrial water storage changes. The present invention can achieve effective prediction of the recovery prospects of dried-up lakes.

Description

Technical Field

[0001] The present invention relates to the technical field of hydrological water resources applications, and particularly to a method and device for predicting the restoration prospect of a dried-up lake. Background Art

[0002] Lakes have functions such as supplying fresh water, regulating climate, storing carbon, and protecting biodiversity, and play a key role in the global hydrological cycle. Due to factors such as climate change, more and more lakes are facing problems such as shrinkage, drying up, and ecological degradation. Managers are trying to restore lakes by controlling water resource exploitation.

[0003] However, the restoration process of lakes is very slow. During the restoration process of lakes, since the groundwater level and water shortage of dried-up lakes cannot be determined, the restoration prospect of dried-up lakes cannot be predicted. Managers cannot determine whether the current quota of water resource exploitation is appropriate, and even less can they know how long it will take to restore the lake using the current quota of water resource exploitation. Therefore, during the restoration process of dried-up lakes, there is a technical problem that the restoration prospect of dried-up lakes cannot be predicted. Summary of the Invention

[0004] The present invention provides a method and device for predicting the restoration prospect of a dried-up lake, which can effectively predict the restoration prospect of a dried-up lake.

[0005] In a first aspect, the present invention provides a method for predicting the restoration prospect of a dried-up lake, including: obtaining optical remote sensing image data of a target lake area during a period when it was not dried up, and calculating water area data of the target lake area during this period based on the optical remote sensing image data; obtaining gravity satellite data of the target lake area during a period, and calculating terrestrial water storage data of the target lake area during this period based on the gravity satellite data; performing time series decomposition on the terrestrial water storage data to obtain terrestrial water storage decomposition data; constructing a linear regression model based on the water area data, terrestrial water storage data, and terrestrial water storage decomposition data, and obtaining a target regression model of the terrestrial water storage data with the highest goodness of fit through parameter calibration; monitoring the change in real-time terrestrial water storage of the target lake area, and obtaining the inversion water area change trend of the target lake area through the target regression model based on the change in real-time terrestrial water storage.

[0006] The present invention provides a method for predicting the restoration prospect of a dried-up lake. On the one hand, the water area data is calculated based on the optical remote sensing image data of the target lake area during a period when it was not dried up, and can reflect the true water area of the target lake area when it was not dried up. On the other hand, the terrestrial water storage data is calculated based on the gravity satellite data of the target lake area during a period, and can reflect the groundwater level situation of the target lake area. In this way, the linear regression model constructed by the present invention based on the water area data and the terrestrial water storage data can characterize the linear relationship between the true water area of the target lake area when it was not dried up and the groundwater level situation. Therefore, for the target lake area, the present invention can determine the inversion water area change trend based on the real-time change of the terrestrial water storage, so as to determine whether the target lake area is dried up and the water shortage situation after drying up, which is convenient for realizing the effective prediction of the restoration prospect of the dried-up lake.

[0007] In a possible implementation manner, calculating the water area data of the target lake area based on the optical remote sensing image data includes: for the optical remote sensing image at any moment in the optical remote sensing image data, extracting the green band data and the near-infrared band data in the optical remote sensing image at the any moment; and determining the green band reflectance of the green band data and the near-infrared band reflectance of the near-infrared band data; calculating the water area of the target lake area at the any moment based on the green band reflectance and the near-infrared band reflectance; and determining the water area data of the target lake area during the period based on the water areas of the target lake area at each moment.

[0008] In a possible implementation manner, calculating the water area of the target lake area at the any moment based on the green band reflectance and the near-infrared band reflectance includes: calculating the water area of the target lake area at the any moment based on the following formula;

[0009]

[0010] where A rea is the water area of the target lake area at the any moment, B green is the green band reflectance in the optical remote sensing image at the any moment, and B nir is the near-infrared band reflectance in the optical remote sensing image at the any moment.

[0011] In a possible implementation manner, performing time series decomposition on the terrestrial water storage data to obtain terrestrial water storage decomposition data includes: performing time series decomposition on the terrestrial water storage data to obtain terrestrial water storage decomposition data, and the terrestrial water storage decomposition data includes long-term trend data, interannual change data, seasonal dynamic change data, and residual data; the terrestrial water storage data and the terrestrial water storage decomposition data satisfy the following formula;

[0012] Traw = T trend + T inter-annual + T seasonal + T residuals ;

[0013] where T raw is the terrestrial water storage at the first moment, T trend is the long-term trend data at the first moment, T inter-annual is the interannual variability data at the first moment, T seasonal is the seasonal dynamics data at the first moment, T residuals is the residual data at the first moment, and the first moment is any moment in a period.

[0014] In a possible implementation, a linear regression model is constructed based on water area data, terrestrial water storage data, and terrestrial water storage decomposition data, and the target regression model with the highest goodness of fit for the terrestrial water storage data is obtained through parameter calibration, including: respectively constructing a first linear regression model between the water area data and the terrestrial water storage data, a second linear regression model between the water area data and the long-term trend data, a third linear regression model between the water area data and the interannual variability data, a fourth linear regression model between the water area data and the seasonal dynamics change data, and a fifth linear regression model between the water area data and the residual data according to the following formula;

[0015] A rea = a × T + b

[0016] where A rea is the water area data, T is the terrestrial water storage data, long-term trend data, interannual variability data, seasonal dynamics change data, or residual data, a is the slope parameter in the linear regression model, and b is the intercept parameter in the linear regression model;

[0017] Respectively determine the goodness of fit of the first linear regression model, the second linear regression model, the third linear regression model, the fourth linear regression model, and the fifth linear regression model; and determine the linear regression model with the highest goodness of fit as the target regression model.

[0018] In a possible implementation, obtaining the inversion water area change trend of the target lake area based on the real-time terrestrial water storage change through the target regression model includes: inputting the real-time terrestrial water storage into the target regression model to obtain the real-time inversion water area of the target lake area; calculating the average value of the inversion water area in the current period as the first average value; calculating the average value of the inversion water area in the previous period as the second average value; the current period and the previous period are adjacent periods; if the first average value is greater than the second average value, it is determined that the change trend of the inversion water area of the target lake area is gradually increasing; if the second average value is greater than the first average value, it is determined that the change trend of the inversion water area of the target lake area is gradually decreasing.

[0019] In a possible implementation, after obtaining the inversion water area change trend of the target lake area based on the real-time terrestrial water storage change through the target regression model, it further includes: if the value of the inversion water area is positive, it is determined that the target lake area is not dry; if the value of the inversion water area is negative and the inversion water area is gradually increasing, the water resource extraction amount per unit time in the target lake area remains unchanged; if the value of the inversion water area is negative and the inversion water area is gradually decreasing, the water resource extraction amount per unit time in the target lake area is reduced.

[0020] In a second aspect, an embodiment of the present invention provides a prediction device for the restoration prospect of a dry lake. The prediction device includes: a communication module and a processing module; the communication module is used to obtain optical remote sensing image data of the target lake area during a period when it is not dry; obtain gravity satellite data of the target lake area during a period; the processing module is used to calculate the water area data of the target lake area during this period based on the optical remote sensing image data; calculate the terrestrial water storage data of the target lake area during this period based on the gravity satellite data; perform time series decomposition on the terrestrial water storage data to obtain terrestrial water storage decomposition data; construct a linear regression model based on the water area data, terrestrial water storage data, and terrestrial water storage decomposition data, and obtain the target regression model of the terrestrial water storage data with the highest goodness of fit through parameter calibration; monitor the real-time change of the terrestrial water storage in the target lake area, and obtain the inversion water area change trend of the target lake area based on the real-time terrestrial water storage change through the target regression model.

[0021] In a third aspect, an embodiment of the present invention provides an electronic device, characterized in that the electronic device includes a memory and a processor. The memory stores a computer program, and the processor is used to call and run the computer program stored in the memory to execute the steps of the method described in the first aspect and any possible implementation manner in the first aspect.

[0022] Fourthly, an embodiment of the present invention provides a computer-readable storage medium storing a computer program, characterized in that when the computer program is executed by a processor, the steps of the method described in the first aspect and any possible implementation manner in the first aspect are implemented.

[0023] For the technical effects brought by any implementation manner in the second to fourth aspects above, reference can be made to the technical effects brought by the corresponding implementation manner in the first aspect, which will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0025] Figure 1 is a schematic flowchart of a method for predicting the restoration prospect of a dried-up lake provided by an embodiment of the present invention;

[0026] Figure 2 is a schematic flowchart of a method for predicting the restoration prospect of a dried-up lake provided by an embodiment of the present invention;

[0027] Figure 3 is a graph showing the change trend of the water area of a lake provided by an embodiment of the present invention;

[0028] Figure 4 is a graph showing the change trend of terrestrial water storage data and decomposed data provided by an embodiment of the present invention;

[0029] Figure 5 is a schematic diagram of a linear regression model provided by an embodiment of the present invention;

[0030] Figure 6 is a graph showing the change trend of the water area and the inverted water area of a lake provided by an embodiment of the present invention;

[0031] Figure 7 is a schematic structural diagram of a device for predicting the restoration prospect of a dried-up lake provided by an embodiment of the present invention;

[0032] Figure 8 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] In the following description, specific details such as specific system architectures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present invention. However, those skilled in the art should clearly understand that the present invention can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present invention.

[0034] In the description of the present invention, unless otherwise specified, " / " means "or". For example, A / B can represent A or B. The "and / or" herein is merely a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, "at least one" and "a plurality of" mean two or more. The terms such as "first" and "second" do not limit the quantity and execution order, and the terms such as "first" and "second" do not necessarily limit to be different.

[0035] In the embodiments of the present application, words such as "exemplary" or "for example" are used to represent examples, illustrations, or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly, using words such as "exemplary" or "for example" aims to present relevant concepts in a specific way for easy understanding.

[0036] In addition, the terms "including" and "having" mentioned in the description of the present application and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or modules is not limited to the listed steps or modules, but optionally further includes other unlisted steps or modules, or optionally further includes other steps or modules inherent to these processes, methods, products, or devices.

[0037] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will be described through specific embodiments in conjunction with the drawings of the present invention.

[0038] As described in the background art, during the restoration process of dried-up lakes, there are technical problems that the restoration prospects of dried-up lakes cannot be predicted.

[0039] To solve the above technical problems, as Figure 1 shown, the embodiments of the present invention provide a method for predicting the restoration prospects of dried-up lakes. The execution subject of the prediction method is a device for predicting the restoration prospects of dried-up lakes. The method includes steps S101 - S104.

[0040] S101. Obtain the optical remote sensing image data of the target lake area during a period when it was not dried up, and calculate the water area data of the target lake area during this period based on the optical remote sensing image data.

[0041] In some embodiments, the optical remote sensing image data may be the detection data of an optical remote sensing satellite. Exemplarily, the optical remote sensing image data may be the detection data of the Landsat satellite on land. For example, the optical remote sensing image data may be the detection data of a sensor in the Landsat satellite. Among them, the sensor may be a thematic mapper (TM) sensor, an enhanced thematic mapper plus (ETM+) sensor, and an operational land imager (OLI) sensor.

[0042] As a possible implementation, the prediction device may communicate with an optical remote sensing satellite to obtain the optical remote sensing image data of the target lake area during a period when it was not dried up.

[0043] In some embodiments, the water area of the target lake area is the area of the water surface of the target lake. The water area data of the target lake area during this period is the set of the water areas at each time point in the target lake area during this period.

[0044] As a possible implementation, the prediction device may calculate the water area at each time point in the target lake area during this period, and then determine the water area data of the target lake area during this period.

[0045] As a possible implementation, the prediction device may decompose the optical remote sensing image at any moment to obtain data of each band, and determine the water area at any moment based on the data of each band.

[0046] Exemplarily, the prediction device may determine the water area data of the target lake area during this period based on steps S1011 - S1013.

[0047] S1011. For the optical remote sensing image at any moment in the optical remote sensing image data, extract the green band data and the near-infrared band data in the optical remote sensing image at this moment; and determine the green band reflectance of the green band data and the near-infrared band reflectance of the near-infrared band data.

[0048] As a possible implementation, the prediction device may preprocess the optical remote sensing image, and obtain the green band reflectance and the near-infrared band reflectance based on the preprocessed optical remote sensing image. Among them, the preprocessing may be radiometric calibration and atmospheric correction, which is not limited thereto.

[0049] S1012. Calculate the water area of the target lake area at any moment based on the green band reflectance and the near-infrared band reflectance.

[0050] As a possible implementation, the prediction device can calculate the water area of the target lake area at any moment based on the following formula.

[0051]

[0052] Where A rea is the water area of the target lake area at any moment, and B green is the green band reflectance in the optical remote sensing image at any moment, and B nir is the near-infrared band reflectance in the optical remote sensing image at any moment.

[0053] S1013. Determine the water area data of the target lake area during this period based on the water areas of the target lake area at each moment.

[0054] As a possible implementation, the prediction device can sort the water areas at each moment in time series to determine the water area data of the target lake area during this period.

[0055] In this way, the prediction device can determine the water area of the target lake area based on the green band data and the near-infrared band data in the optical remote sensing image. Since the optical remote sensing image is the data when the target lake area is not dry, the determined water area of the target lake area can truly reflect the state when the target lake area is not dry, improving the authenticity and accuracy of the water area data of the target lake area during this period.

[0056] S102. Obtain the gravity satellite data of the target lake area during a period, and calculate the terrestrial water storage data of the target lake area based on the gravity satellite data.

[0057] In some embodiments, the gravity satellite data is the detection data of the gravity satellite. Exemplarily, the gravity satellite data of the target lake area can be the equivalent water thickness of each point in the target lake area.

[0058] As a possible way, the prediction device can communicate with the gravity satellite to obtain the gravity satellite data of the target lake area during a period.

[0059] As another possible implementation, the prediction device can communicate with the server storing the gravity satellite data to obtain the gravity satellite data of the target lake area during a period.

[0060] Exemplarily, the server storing the gravity satellite data can be the server of the Center for Space Research at the University of Texas at Austin, USA.

[0061] In some embodiments, the terrestrial water storage in the target lake area is used to characterize the groundwater level in the target lake area. Exemplarily, the terrestrial water storage in the target lake area can be 400 mm or 300 mm.

[0062] As a possible implementation, for the gravity satellite data at any moment within a period, the prediction device can calculate the average value of the equivalent water thickness in the gravity satellite data of the target lake area at that moment, and determine this average value as the terrestrial water storage data of the target lake area at that moment.

[0063] S103. Perform time series decomposition on the terrestrial water storage data to obtain the decomposed terrestrial water storage data.

[0064] In some embodiments, the decomposed terrestrial water storage data includes long-term trend data, interannual variation data, seasonal dynamic variation data, and residual data.

[0065] Exemplarily, the long-term trend data is used to characterize the long-term level of the terrestrial water storage. The prediction device can calculate the average value of the terrestrial water storage data of the target lake area within the sliding window over a fixed time period through a fixed-duration sliding window to obtain the long-term trend data.

[0066] In another example, the interannual variation data is used to characterize the annual average level of the terrestrial water storage. The prediction device can calculate the average value of the terrestrial water storage data of the target lake area within the sliding window over a period of one year through a sliding window with a duration of one year to obtain the interannual variation data. Alternatively, the prediction device can also calculate the difference data between the terrestrial water storage data of the target lake area within the sliding window over a period of one year and the long-term trend data through a sliding window with a duration of one year, and calculate the average value of this difference data within the sliding window to obtain the interannual variation data.

[0067] In another example, the seasonal dynamic variation data is used to characterize the seasonal average level of the terrestrial water storage. The prediction device can calculate the average value of the terrestrial water storage data of the target lake area within the sliding window over a period of one quarter through a sliding window with a duration of one quarter to obtain the seasonal dynamic variation data. Alternatively, the prediction device can also calculate the difference data between the terrestrial water storage data of the target lake area within the sliding window over a period of one quarter and the long-term trend data and interannual variation data through a sliding window with a duration of one quarter, and calculate the average value of this difference data within the sliding window to obtain the interannual variation data.

[0068] In another exemplary case, the residual data is used to characterize the error between the terrestrial water storage and the sum of the long-term trend data, the interannual variation data, and the seasonal dynamic variation data. The prediction device may determine the difference between the terrestrial water storage data and the sum of the long-term trend data, the interannual variation data, and the seasonal dynamic variation data as the residual data.

[0069] As a possible implementation, the terrestrial water storage data and the terrestrial water storage decomposition data satisfy the following formula;

[0070] T raw = T trend + T inter-annual + T seasonal + T residuals ;

[0071] where, T raw is the terrestrial water storage at the first moment, T trend is the long-term trend data at the first moment, T inter-annual is the interannual variation data at the first moment, T seasonal is the seasonal dynamic data at the first moment, T residuals is the residual data at the first moment, and the first moment is any moment in a period.

[0072] S104. Construct a linear regression model based on the water area data, the terrestrial water storage data, and the terrestrial water storage decomposition data, and obtain the target regression model of the terrestrial water storage data with the highest goodness of fit through parameter calibration.

[0073] In some embodiments, the linear regression model is used to determine the linear relationship between the water area data and the terrestrial water storage data or the terrestrial water storage decomposition data.

[0074] As a possible implementation, the prediction device may respectively construct a first linear regression model between the water area data and the terrestrial water storage data, a second linear regression model between the water area data and the long-term trend data, a third linear regression model between the water area data and the interannual variation data, a fourth linear regression model between the water area data and the seasonal dynamic variation data, and a fifth linear regression model between the water area data and the residual data based on the following formula.

[0075] A rea = a×T + b;

[0076] where, A rea is the water area data, T is the terrestrial water storage data, the long-term trend data, the interannual variation data, the seasonal dynamic variation data, or the residual data, a is the slope parameter in the linear regression model, and b is the intercept parameter in the linear regression model.

[0077] After that, the prediction device respectively determines the goodness of fit of the first linear regression model, the second linear regression model, the third linear regression model, the fourth linear regression model, and the fifth linear regression model; and determines the linear regression model with the highest goodness of fit as the target regression model.

[0078] S105. Monitor the real-time change of the terrestrial water storage in the target lake area, and obtain the trend of the inverted water area change in the target lake area through the target regression model based on the real-time change of the terrestrial water storage.

[0079] It should be noted that the terrestrial water storage can only characterize the groundwater level situation in the target lake area, but only based on the terrestrial water storage, it is impossible to determine whether the target lake area is dry and the water shortage situation after drying. Through the target regression model of the present invention, a linear relationship between the water area and the terrestrial water storage is established, and based on this linear relationship and the real-time terrestrial water storage, the inverted water area determined can reflect whether the target lake area is dry.

[0080] Exemplarily, when the inverted water area is positive, it indicates that there is water accumulation in the target lake area and it is in an undry state. When the inverted water area is zero or negative, it indicates that the target lake area is in a dry state. The smaller the inverted water area, the more serious the dryness degree of the target lake area.

[0081] It can be understood that the embodiment of the present invention can determine the critical point of the terrestrial water storage based on the target regression model, so as to determine whether the target lake area is in a dry state; and determine the dryness degree of the target lake area based on the magnitude of the value of the inverted water area.

[0082] As a possible implementation manner, the prediction device can determine the trend of the inverted water area change in the target lake area based on the magnitude relationship between the terrestrial water storage at the current moment and the terrestrial water storage at the previous moment.

[0083] As another possible implementation manner, the prediction device can determine the trend of the inverted water area change in the target lake area based on the magnitude relationship between the terrestrial water storage in the current time period and the terrestrial water storage in the previous time period.

[0084] Exemplarily, the prediction device can determine the trend of the inverted water area change in the target lake area based on steps S1051 - S1054.

[0085] S1051. Input the real-time terrestrial water storage into the target regression model to obtain the real-time inverted water area of the target lake area.

[0086] S1052. Calculate the average value of the inverted water area in the current time period as the first average value; calculate the average value of the inverted water area in the previous time period as the second average value; the current time period and the previous time period are adjacent time periods.

[0087] S1053. If the first average value is greater than the second average value, it is determined that the changing trend of the retrieved water area of the target lake area is gradually increasing.

[0088] S1054. If the second average value is greater than the first average value, it is determined that the changing trend of the retrieved water area of the target lake area is gradually decreasing.

[0089] The present invention provides a method for predicting the restoration prospect of a dried-up lake. On the one hand, the water area data is calculated based on the optical remote sensing image data of the target lake area during a period when it was not dried up, and can reflect the true water area of the target lake area when it was not dried up. On the other hand, the terrestrial water storage data is calculated based on the gravity satellite data of the target lake area during a period, and can reflect the groundwater level situation of the target lake area. In this way, the linear regression model constructed by the present invention based on the water area data and the terrestrial water storage data can characterize the linear relationship between the true water area of the target lake area when it was not dried up and the groundwater level situation. Thus, for the target lake area, the present invention can determine the changing trend of the retrieved water area based on the real-time change of the terrestrial water storage, so as to determine whether the target lake area is dried up and the water shortage situation after drying up, facilitating the effective prediction of the restoration prospect of the dried-up lake.

[0090] Optionally, as Figure 2 shown, after step S105, the method for predicting the restoration prospect of a dried-up lake provided by the present invention further includes: steps S201 - S203.

[0091] S201. If the value of the retrieved water area is positive, it is determined that the target lake area is not dried up, and the water resource extraction amount per unit time in the target lake area is increased, or the water resource extraction amount per unit time in the target lake area is kept unchanged.

[0092] S202. If the value of the retrieved water area is negative and the retrieved water area is gradually increasing, the water resource extraction amount per unit time in the target lake area is kept unchanged.

[0093] S203. If the value of the retrieved water area is negative and the retrieved water area is gradually decreasing, the water resource extraction amount per unit time in the target lake area is decreased.

[0094] In this way, the method for predicting the restoration prospect of a dried-up lake provided by the embodiments of the present invention can adjust the water-saving measures in the target lake area based on the changing trend of the retrieved water area of the target lake area, that is, adjust the water resource extraction amount per unit time in the target lake area. While effectively predicting the restoration prospect of the dried-up lake, more reasonable water-saving measures are formulated, making the restoration prospect of the dried-up lake clearer.

[0095] Exemplarily, taking Angulinuo Lake as an example, the prediction method for the restoration prospect of dried lakes provided by the embodiments of the present invention will be described below.

[0096] As Figure 3 shown, the embodiments of the present invention provide a graph of the change trend of the water area of a lake. Angulinuo Lake dried up in 2004. Between 2002 and 2004, the lake area showed a cosine curve shape, with a minimum area of 15 km 2 , and a maximum area of 37 km 2 .

[0097] As Figure 4 shown, the embodiments of the present invention provide a graph of the change trend of terrestrial water storage data and decomposed data. From the terrestrial water storage data in Figure 4 , it can be seen that between 2002 and 2004, the terrestrial water storage of Angulinuo Lake showed a cosine curve shape similar to that of the lake area. The minimum terrestrial water storage was 10 mm, and the maximum terrestrial water storage was 45 mm. Figure 4 The long-term trend data represents the long-term level of the terrestrial water storage of Angulinuo Lake. From the Figure 4 long-term trend data, it can be seen that between 2002 and 2004, the terrestrial water storage of Angulinuo Lake was basically flat, about 40 mm. After 2004, the terrestrial water storage of Angulinuo Lake decreased year by year. Figure 4 The interannual change data characterizes the annual average level of the terrestrial water storage of Angulinuo Lake. Figure 4 The seasonal dynamic change data in Figure 4 characterizes the seasonal average level of the terrestrial water storage of Angulinuo Lake.

[0098] As Figure 5 shown, the embodiments of the present invention provide a schematic diagram of a linear regression model. Figure 5 The a in 2 represents the linear regression between the water area data and the terrestrial water storage data in the target lake area. The expression after fitting the first linear regression model is: Area = 0.6282T + 8.9906, and the goodness of fit R

[0099] Figure 5 The b in 2 represents the linear regression between the water area data and the long-term trend data in the target lake area. The expression after fitting the second linear regression model is: Area = 2.0901T - 54.477, and the goodness of fit R

[0100] Figure 5In this, c represents the linear regression between the water area data and the inter-annual change data of the target lake area. The expression after fitting the third linear regression model is: Area = 0.6487T + 33.902, and the goodness of fit R 2 = 0.7609.

[0101] Figure 5 In this, d represents the linear regression between the water area data and the seasonal dynamic change data of the target lake area. The expression after fitting the fourth linear regression model is: Area = 0.1916T + 27.765, and the goodness of fit R 2 = 0.026.

[0102] Figure 5 In this, e represents the linear regression between the water area data and the residual data of the target lake area. The expression after fitting the fifth linear regression model is: Area = 0.4279T + 27.837, and the goodness of fit R 2 = 0.0372.

[0103] By comparing the expressions and goodness of fit of the first linear regression model, the second linear regression model, the third linear regression model, the fourth linear regression model, and the fifth linear regression model, it can be seen that the goodness of fit of the first linear regression model is the highest, which is 0.83. The slope parameter of the calibrated linear regression model is 0.6282, and the intercept parameter is 8.9906. The fitting effect of the first linear regression model is good, indicating that compared with the long-term trend data, the inter-annual change data, the seasonal dynamic change data, and the residual data, the terrestrial water storage data can most accurately express the change of the lake area.

[0104] As Figure 6 shown, the embodiment of the present invention provides a change trend diagram of the water area and the inverted water area of a lake. Figure 6 In this, ①②③④ respectively represent 4 short-term recovery events of Angulinuo Lake between 2008 and 2017. Figure 6 In this, ⑤⑥⑦⑧ respectively represent that the inverted water area data is adapted to the water area data of the lake, and accurately judge these four short-term recovery events, indicating that the recovery prospect of the dried-up lake can be accurately and effectively predicted by inverting the water area. In this way, the embodiment of the present invention can adjust the water-saving measures in the target lake area based on the change trend of the inverted water area of the target lake area, making the water-saving measures more reasonable and the recovery prospect of the dried-up lake clearer.

[0105] Exemplarily, in 2009, the inverted water area of Angulinuo Lake was close to zero, indicating that Angulinuo Lake was relatively easy to recover. Assuming that the water-saving amount was appropriately increased, that is, the water resource extraction amount of Angulinuo Lake per unit time was appropriately reduced, water accumulation might occur in Angulinuo Lake.

[0106] Another example is that from 2011 to 2014, the inverted water area of Angulinuo Lake decreased rapidly, indicating that the drying degree of the area where Angulinuo Lake is located has intensified. Therefore, more stringent water-saving measures need to be formulated to restore Angulinuo Lake.

[0107] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0108] The following is an apparatus embodiment of the present invention. For details not described in detail herein, reference may be made to the corresponding method embodiments above.

[0109] Figure 7 FIG. shows a schematic structural diagram of a prediction apparatus for the restoration prospect of a dried-up lake provided by an embodiment of the present invention. The prediction apparatus 700 includes: a communication module 701 and a processing module 702.

[0110] The communication module 701 is configured to obtain optical remote sensing image data of a target lake area during a period when it was not dried up; and obtain gravity satellite data of the target lake area during a period.

[0111] The processing module 702 is configured to calculate water area data of the target lake area during the period based on the optical remote sensing image data; calculate terrestrial water storage data of the target lake area during the period based on the gravity satellite data; perform time series decomposition on the terrestrial water storage data to obtain terrestrial water storage decomposition data; construct a linear regression model based on the water area data, terrestrial water storage data, and terrestrial water storage decomposition data, and obtain a target regression model of the terrestrial water storage data with the highest goodness of fit through parameter calibration; monitor the real-time change of the terrestrial water storage in the target lake area, and obtain the change trend of the inverted water area of the target lake area through the target regression model based on the real-time change of the terrestrial water storage.

[0112] In a possible implementation manner, the processing module 702 is specifically configured to, for the optical remote sensing image at any moment in the optical remote sensing image data, extract the green band data and the near-infrared band data in the optical remote sensing image at the any moment; and determine the green band reflectance of the green band data and the near-infrared band reflectance of the near-infrared band data; calculate the water area of the target lake area at the any moment based on the green band reflectance and the near-infrared band reflectance; and determine the water area data of the target lake area during the period based on the water areas of the target lake area at each moment.

[0113] In a possible implementation manner, the processing module 702 is specifically configured to calculate the water area of the target lake area at the any moment based on the following formula;

[0114]

[0115] Among them, A rea is the water area of the target lake area at any moment, and B green is the reflectance of the green band in the optical remote sensing image at any moment, and B nir is the reflectance of the near-infrared band in the optical remote sensing image at any moment.

[0116] In a possible implementation manner, the processing module 702 is specifically configured to perform time series decomposition on the terrestrial water storage data to obtain terrestrial water storage decomposition data, where the terrestrial water storage decomposition data includes long-term trend data, interannual variation data, seasonal dynamic variation data, and residual data; the terrestrial water storage data and the terrestrial water storage decomposition data satisfy the following formula;

[0117] T raw = T trend + T inter-annual + T seasonal + T residuals ;

[0118] Among them, T raw is the terrestrial water storage at the first moment, T trend is the long-term trend data at the first moment, T inter-annual is the interannual variation data at the first moment, T seasonal is the seasonal dynamic data at the first moment, T residuals is the residual data at the first moment, and the first moment is any moment in a period.

[0119] In a possible implementation manner, the processing module 702 is specifically configured to respectively construct a first linear regression model between the water area data and the terrestrial water storage data, a second linear regression model between the water area data and the long-term trend data, a third linear regression model between the water area data and the interannual variation data, a fourth linear regression model between the water area data and the seasonal dynamic variation data, and a fifth linear regression model between the water area data and the residual data based on the following formula;

[0120] A rea = a×T + b

[0121] Among them, A rea is the water area data, T is the terrestrial water storage data, long-term trend data, interannual variation data, seasonal dynamic variation data, or residual data, a is the slope parameter in the linear regression model, and b is the intercept parameter in the linear regression model;

[0122] Determine the goodness of fit of the first linear regression model, the second linear regression model, the third linear regression model, the fourth linear regression model, and the fifth linear regression model respectively; determine the linear regression model with the highest goodness of fit as the target regression model.

[0123] In a possible implementation manner, the processing module 702 is specifically configured to input the real-time terrestrial water storage into the target regression model to obtain the real-time inverted water area of the target lake area; calculate the average value of the inverted water area in the current period as the first average value; calculate the average value of the inverted water area in the previous period as the second average value; the current period and the previous period are adjacent periods; if the first average value is greater than the second average value, determine that the change trend of the inverted water area of the target lake area is gradually increasing; if the second average value is greater than the first average value, determine that the change trend of the inverted water area of the target lake area is gradually decreasing.

[0124] In a possible implementation manner, the processing module 702 is further configured to determine that the target lake area is not dry if the value of the inverted water area is positive; if the value of the inverted water area is negative and the inverted water area is gradually increasing, keep the water resource extraction amount per unit time in the target lake area unchanged; if the value of the inverted water area is negative and the inverted water area is gradually decreasing, reduce the water resource extraction amount per unit time in the target lake area.

[0125] Figure 8 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. As Figure 8 shown, the electronic device 800 of this embodiment includes: a processor 801, a memory 802, and a computer program 803 stored in the memory 802 and executable on the processor 801. When the processor 801 executes the computer program 803, it implements the steps in the above method embodiments, such as Figure 1 the steps 101 to 104 shown. Alternatively, when the processor 801 executes the computer program 803, it implements the functions of each module / unit in the above device embodiments. For example, Figure 7 the functions of the communication module 701 and the processing module 702 shown. Exemplarily, the computer program 803 can be divided into one or more modules / units, and the one or more modules / units are stored in the memory 802 and executed by the processor 801 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program 803 in the electronic device 800. For example, the computer program 803 can be divided into Figure 7The communication module 701 and the processing module 702 are shown. The so-called processor 801 may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0126] The memory 802 may be an internal storage unit of the electronic device 800, such as the hard disk or memory of the electronic device 800. The memory 802 may also be an external storage device of the electronic device 800, such as a plug-in hard disk equipped on the electronic device 800, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 802 may also include both the internal storage unit of the electronic device 800 and the external storage device. The memory 802 is used to store the computer program and other programs and data required by the terminal. The memory 802 may also be used to temporarily store data that has been output or is to be output.

[0127] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules as needed, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be described in detail here.

[0128] In the above embodiments, the descriptions of the various embodiments have their own emphases. For parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0129] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0130] In the embodiments provided by the present invention, it should be understood that the disclosed device / terminal and method can be implemented in other ways. For example, the device / terminal embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0131] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0132] In addition, the functional units in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0133] When the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice within the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0134] The above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for predicting the restoration prospect of a dried-up lake, characterized in that, comprising: Obtaining optical remote sensing image data of the target lake area during a period when it was not dried up, and calculating the water area data of the target lake area during this period based on the optical remote sensing image data; Obtaining gravity satellite data of the target lake area during the period, and calculating the terrestrial water storage data of the target lake area during this period based on the gravity satellite data; Performing time series decomposition on the terrestrial water storage data to obtain terrestrial water storage decomposition data; Constructing a linear regression model based on the water area data, the terrestrial water storage data, and the terrestrial water storage decomposition data, and obtaining a target regression model of the terrestrial water storage data with the highest goodness of fit through parameter calibration; Monitoring the real-time change of the terrestrial water storage in the target lake area, and obtaining the inversion water area change trend of the target lake area through the target regression model based on the real-time change of the terrestrial water storage; The constructing a linear regression model based on the water area data, the terrestrial water storage data, and the terrestrial water storage decomposition data, and obtaining a target regression model of the terrestrial water storage data with the highest goodness of fit through parameter calibration includes: respectively constructing a first linear regression model between the water area data and the terrestrial water storage data, a second linear regression model between the water area data and the long-term trend data, a third linear regression model between the water area data and the interannual change data, a fourth linear regression model between the water area data and the seasonal dynamic change data, and a fifth linear regression model between the water area data and the residual data; respectively determining the goodness of fit of the first linear regression model, the second linear regression model, the third linear regression model, the fourth linear regression model, and the fifth linear regression model; Determining the linear regression model with the highest goodness of fit as the target regression model.

2. The method according to claim 1, characterized in that, the calculating the water area data of the target lake area during this period based on the optical remote sensing image data includes: For the optical remote sensing image at any moment in the optical remote sensing image data, extracting the green band data and the near-infrared band data in the optical remote sensing image at this any moment; and determining the green band reflectance of the green band data and the near-infrared band reflectance of the near-infrared band data; Calculating the water area of the target lake area at this any moment based on the green band reflectance and the near-infrared band reflectance; Determining the water area data of the target lake area during this period based on the water areas of the target lake area at each moment.

3. The method according to claim 2, characterized in that, the calculating the water area of the target lake area at this any moment based on the green band reflectance and the near-infrared band reflectance includes: Calculating the water area of the target lake area at this any moment based on the following formula; ； wherein, is the water area of the target lake area at any given moment, is the reflectance of the green band in the optical remote sensing image at any given moment, is the reflectance of the near-infrared band in the optical remote sensing image at any given moment.

4. The method according to claim 1, characterized in that, the performing time series decomposition on the terrestrial water storage data to obtain terrestrial water storage decomposition data includes: Perform time series decomposition on the terrestrial water storage data to obtain decomposed terrestrial water storage data, where the decomposed terrestrial water storage data includes long-term trend data, interannual variation data, seasonal dynamic variation data, and residual data; the terrestrial water storage data and the decomposed terrestrial water storage data satisfy the following formula; ； Among them, is the terrestrial water storage at the first moment, is the long-term trend data at the first moment, is the interannual variability data at the first moment, is the seasonal dynamics data at the first moment, is the residual data at the first moment, and the first moment is any moment in the period.

5. The method according to claim 4, wherein, the steps of respectively constructing a first linear regression model between the water area data and the terrestrial water storage data, a second linear regression model between the water area data and the long-term trend data, a third linear regression model between the water area data and the interannual variation data, a fourth linear regression model between the water area data and the seasonal dynamic variation data, and a fifth linear regression model between the water area data and the residual data include: Construct a first linear regression model, a second linear regression model, a third linear regression model, a fourth linear regression model, and a fifth linear regression model based on the following formula; ； wherein, is the water area data, T is the terrestrial water storage data, the long-term trend data, the interannual variability data, the seasonal dynamic variability data, or the residual data, a is the slope parameter in the linear regression model, and b is the intercept parameter in the linear regression model.

6. The method according to claim 1, wherein, the step of obtaining the inversion water area change trend of the target lake area through the target regression model based on the real-time terrestrial water storage change includes: Input the real-time terrestrial water storage into the target regression model to obtain the real-time inversion water area of the target lake area; Calculate the average value of the inversion water area in the current period as the first average value; calculate the average value of the inversion water area in the previous period as the second average value; the current period and the previous period are adjacent periods; If the first average value is greater than the second average value, determine that the inversion water area change trend of the target lake area is gradually increasing; If the second average value is greater than the first average value, determine that the inversion water area change trend of the target lake area is gradually decreasing.

7. The method according to any one of claims 1 to 6, wherein, after obtaining the inversion water area change trend of the target lake area through the target regression model based on the real-time terrestrial water storage change, further includes: If the value of the inversion water area is positive, determine that the target lake area is not dry; If the value of the inversion water area is negative and the inversion water area is gradually increasing, keep the water resource extraction amount per unit time in the target lake area unchanged; If the value of the inversion water area is negative and the inversion water area is gradually decreasing, reduce the water resource extraction amount per unit time in the target lake area.

8. A prediction device for the restoration prospect of a dry lake, wherein, it includes: A communication module and a processing module; The communication module is used to obtain optical remote sensing image data of the target lake area during a period when it is not dry; Obtain gravity satellite data of the target lake area during the period; The processing module is used to calculate the water area data of the target lake area during the period based on the optical remote sensing image data; Calculate the terrestrial water storage data of the target lake area during this period based on the gravity satellite data; perform time series decomposition on the terrestrial water storage data to obtain the decomposed terrestrial water storage data; Construct a linear regression model based on the water area data, the terrestrial water storage data, and the decomposed terrestrial water storage data, and obtain the target regression model of the terrestrial water storage data with the highest goodness of fit through parameter calibration; monitor the real-time change of the terrestrial water storage in the target lake area, and obtain the inversion water area change trend of the target lake area through the target regression model based on the real-time change of the terrestrial water storage; The processing module is specifically configured to respectively construct a first linear regression model between the water area data and the terrestrial water storage data, a second linear regression model between the water area data and the long-term trend data, a third linear regression model between the water area data and the interannual change data, a fourth linear regression model between the water area data and the seasonal dynamic change data, and a fifth linear regression model between the water area data and the residual data; respectively determine the goodness of fit of the first linear regression model, the second linear regression model, the third linear regression model, the fourth linear regression model, and the fifth linear regression model; Determine the linear regression model with the highest goodness of fit as the target regression model.

9. An electronic device, characterized in that, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor is configured to call and run the computer program stored in the memory to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, the computer-readable storage medium stores a computer program, characterized in that, when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 above are implemented.

Images