Evaluation and prediction system for water environment bearing capacity of lake basin in arid region

Abstract

The invention discloses an arid region lake basin water environment bearing capacity evaluation and prediction system, and relates to the technical field of lake drought early warning. A training data collection module is arranged to collect historical meteorological data, historical water level label data, historical meteorological characteristic data and historical drought duration label data; a training sample construction module is set to construct a plurality of lake water level training samples and a plurality of drought duration training samples, a model training module is set to train a water level sequence prediction model and a drought duration prediction model, and a bearing capacity prediction module is set to output future drought duration based on future meteorological characteristic data and the drought duration prediction model. Outputting a future lake water level sequence based on the future meteorological data, the future drought duration, the water level sequence prediction model and the real-time lake water level, and performing early warning on the lake bearing capacity based on the future lake water level sequence; and the prediction accuracy of lake water level change and drought occurrence is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of lake drought early warning, and in particular to a system for evaluating and predicting the water environment carrying capacity of lake basins in arid areas. Background Art

[0002] Assessment and early warning of lake water resource carrying capacity in arid regions are crucial for protecting the local ecological environment and rationally utilizing water resources. As an important water source in arid regions, changes in water quality and water level of lakes directly affect the ecological balance of the region and the water use of residents. However, the impact of climate change and human activities has caused significant changes in precipitation patterns in arid regions, resulting in dramatic fluctuations in lake water levels, exacerbating the risk of water shortage and ecological deterioration. Timely and accurate early warning of lake water level changes and drought events is crucial for taking countermeasures in advance and avoiding water resource crises and ecological disasters.

[0003] Existing drought early warning methods mostly rely on meteorological data analysis and manual experience, lacking sufficient modeling and accurate prediction of complex lake hydrological conditions. Single meteorological data analysis often fails to accurately reflect the dynamic changes of lake water levels, and manual empirical rules are difficult to quantify the weights of various influencing factors, resulting in high subjectivity and lag in early warning results. In addition, existing methods mostly focus on the prediction of a single lake water level or drought duration, lacking a comprehensive assessment of the overall water resources carrying capacity.

[0004] To this end, the present invention proposes a system for evaluating and predicting the water environment carrying capacity of lake basins in arid areas. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a water environment carrying capacity evaluation and prediction system for lake basins in arid areas, which improves the prediction accuracy of lake water level changes and drought occurrence.

[0006] In order to achieve the above purpose, a water environment carrying capacity evaluation and prediction system for lake basins in arid areas is proposed, which includes a training data collection module, a training sample construction module, a model training module and a carrying capacity prediction module; wherein each module is electrically connected;

[0007] The training data collection module is used to collect historical meteorological data, historical water level label data, historical meteorological characteristic data and historical drought duration label data, and send them to the training sample construction module;

[0008] The historical meteorological data and the historical water level tag data are collected in the following manner:

[0009] Extracting various daily meteorological parameters and lake water levels of lakes from historical meteorological records and historical water level records of lakes in arid regions, respectively, wherein various daily meteorological parameters constitute the historical meteorological data, and daily lake water levels constitute the historical water level label data;

[0010] The historical water level tag data is obtained by analyzing the daily water level of the lake from manual measurement data, automatic monitoring station data or remote sensing data;

[0011] The historical meteorological characteristic data and historical drought duration label data are collected in the following manner:

[0012] The starting time of each drought event is extracted from the historical drought records of lakes in the drought area, and the meteorological characteristics between the starting time of each drought event are intercepted from the historical precipitation records. The difference in the starting time of each drought event is used as the historical drought duration label; the meteorological characteristics of all drought events constitute the historical meteorological characteristic data; the historical drought duration labels of all drought events constitute the historical drought duration label data;

[0013] A training sample construction module constructs a number of lake water level training samples through historical meteorological data and historical water level label data, constructs a number of drought duration training samples through historical meteorological characteristic data and historical drought duration label data, and sends the lake water level training samples and drought duration training samples to the model training module;

[0014] The lake water level training sample is constructed as follows:

[0015] Set the output sequence duration T, input sequence duration L and sliding window step size S;

[0016] Label any historical date as t;

[0017] The number of each meteorological parameter is marked as x, and the parameter value of the xth meteorological parameter on the tth day is marked as x_t;

[0018] Construct a meteorological parameter sequence for the xth meteorological parameter: [x_(t-L+1), x_(t-L+2), ... x_t];

[0019] Mark the lake water level on day t as y_t; construct a water level label sequence: [y_(t+1), y_(t+2), ...y_(t+T)];

[0020] The meteorological parameter sequences of all meteorological parameters constitute a set of input sample sets;

[0021] A set of input sample sets and water level label sequences form a set of lake water level training samples;

[0022] Slide t back S days and reconstruct a new set of lake water level training samples;

[0023] The method of constructing a number of drought duration training samples using historical meteorological characteristic data and historical drought duration label data is as follows:

[0024] For each drought event, the historical drought duration label of the drought event is used as the duration sample label in advance;

[0025] Taking the start time of the drought event as the central time point, a drought event meteorological feature window is constructed as the input feature of the sample; the drought event meteorological feature window includes various meteorological features before and after the central time point; the length of the drought event meteorological feature window is preset, and the length of the drought event meteorological feature window is marked as W;

[0026] The drought event meteorological characteristic window and duration sample label of each drought event are constructed into a set of drought duration training samples;

[0027] The model training module uses the lake water level training samples to train the water level series prediction model, and uses the drought duration training samples to train the drought duration prediction model, and sends the water level series prediction model and the drought duration prediction model to the carrying capacity prediction module;

[0028] The training method of the water level series prediction model is:

[0029] The input sample set of each date is used as the input of the water level sequence prediction model, the water level sequence prediction model takes the predicted value of the lake water level sequence T days after the date as the output, takes the water level label sequence corresponding to the input sample set as the prediction target, takes the Euclidean distance between the predicted value of the lake water level sequence and the water level label sequence as the first prediction error, and takes minimizing the sum of the first prediction errors as the training target; the water level sequence prediction model is trained until the sum of the first prediction errors reaches convergence and the training is stopped; the water level sequence prediction model is a time series prediction model;

[0030] The training method of the drought duration prediction model is:

[0031] The meteorological characteristic window of each drought event is used as the input of the drought duration prediction model, the drought duration prediction model takes the predicted value of the drought duration of the drought event as the output, takes the duration sample label corresponding to the drought event as the prediction target, takes the square of the difference between the predicted value of the drought duration and the duration sample label as the second prediction error, and takes minimizing the average value of the second prediction errors of all drought events as the training target; the drought duration prediction model is trained until the sum of the second prediction errors reaches convergence and the training is stopped; the drought duration prediction model is a time series prediction model;

[0032] The carrying capacity prediction module is used to collect future meteorological data, future meteorological characteristic data and real-time lake water level, and output the future drought duration based on the future meteorological characteristic data and drought duration prediction model, and then output the future lake water level sequence based on the future meteorological data, future drought duration, water level sequence prediction model and real-time lake water level, and issue an early warning for the lake carrying capacity based on the future lake water level sequence;

[0033] The method of outputting the future drought duration based on the future meteorological characteristic data and the drought duration prediction model is as follows:

[0034] The duration of the future weather data to be collected is marked as F;

[0035] Mark the most recent date as t0, and the latest date for the predicted meteorological data and meteorological characteristic data is t0+F;

[0036] by The corresponding date is taken as the center date, and the dates before and after the center date are The meteorological characteristics of the day together form a set of time-length forecast input windows;

[0037] Input the duration prediction input window into the drought duration prediction model to obtain The predicted value of the drought duration corresponding to the corresponding date is used as the future drought duration;

[0038] The future drought duration is marked as K;

[0039] The method of outputting the future lake water level sequence based on future meteorological data, future drought duration, water level sequence prediction model and real-time lake water level and providing early warning of lake carrying capacity based on the future lake water level sequence is as follows:

[0040] The time period It is represented as a target time period, and the upper and lower time points of the target time period are marked as t_min and t_max respectively;

[0041] Divide the target time period into equal intervals according to the output sequence duration T. prediction durations, corresponding to forecast time period;

[0042] For each forecast period, the meteorological parameter sequences of various meteorological parameters L days before the forecast period are composed of a set of water level forecast input sequences, and all water level forecast input sequences are composed of an actual input set;

[0043] Input the actual input set into the water level series prediction model to obtain the predicted value sequence of the lake water level within the prediction time period;

[0044] The sequence of predicted values ​​of lake water level for all forecast time periods consists of a sequence of water level fluctuations of lake water level with the central point date as the period of drought event occurrence;

[0045] The lake water level is divided into several carrying capacity levels, each carrying capacity level corresponds to an upper limit and a lower limit of the water level, thereby forming a water level range for each carrying capacity level;

[0046] Count the proportion of days in each carrying capacity level from the water level fluctuation series;

[0047] Whether to implement bearing capacity warning is determined based on the proportion of days with each bearing capacity level.

[0048] A method for evaluating and predicting the water environment carrying capacity of lake basins in arid areas is proposed, which includes the following steps:

[0049] Collect historical meteorological data, historical water level label data, historical meteorological characteristic data, and historical drought duration label data;

[0050] Several lake water level training samples are constructed through historical meteorological data and historical water level label data, and several drought duration training samples are constructed through historical meteorological characteristic data and historical drought duration label data;

[0051] Use lake water level training samples to train the water level series prediction model, and use drought duration training samples to train the drought duration prediction model;

[0052] Collect future meteorological data, future meteorological characteristic data and real-time lake water level, and output the future drought duration based on the future meteorological characteristic data and the drought duration prediction model. Then output the future lake water level sequence based on the future meteorological data, future drought duration, the water level sequence prediction model and the real-time lake water level. Based on the future lake water level sequence, give early warning on the lake carrying capacity.

[0053] An electronic device comprises: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the above-mentioned arid area lake basin water environment carrying capacity assessment and prediction system by calling the computer program stored in the memory.

[0054] A computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned arid area lake basin water environment carrying capacity assessment and prediction system.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] The present invention sets a training data collection module for collecting historical meteorological data, historical water level label data, historical meteorological characteristic data and historical drought duration label data, sets a training sample construction module, constructs a number of lake water level training samples through historical meteorological data and historical water level label data, constructs a number of drought duration training samples through historical meteorological characteristic data and historical drought duration label data, sets a model training module, uses lake water level training samples to train a water level sequence prediction model, and uses drought duration training samples to train a drought duration prediction model, sets a carrying capacity prediction module, collects future meteorological data, future meteorological characteristic data and real-time lake water level, and outputs future drought duration based on future meteorological characteristic data and drought duration prediction model, and then outputs future lake water level sequence based on future meteorological data, future drought duration, water level sequence prediction model and real-time lake water level, and warns the lake carrying capacity based on future lake water level sequence. By constructing a lake water level sequence prediction model and a drought duration prediction model, and using historical meteorological data and hydrological data to train the two models, accurate prediction of lake water level fluctuation and drought duration in a future period of time can be achieved. On this basis, the system calculates the duration ratio of different water quality carrying capacity levels according to the predicted water level fluctuation sequence, so as to conduct a comprehensive assessment and early warning of the overall water environment carrying capacity in the future period, thereby improving the accuracy of predictions of lake water level changes and drought occurrence; combining water level fluctuation predictions and drought duration predictions, it realizes a quantitative assessment of the overall water environment carrying capacity, and the early warning results are more comprehensive and scientific; it avoids the subjectivity of artificial rules of thumb, improves the timeliness and foresight of early warnings, reduces dependence on professionals, and the early warning process is highly automated and intelligent. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 This is a module connection relationship diagram of the water environment carrying capacity evaluation and prediction system of arid lake basins in Example 1 of the present invention;

[0058] Figure 2 This is a flow chart of the method for evaluating and predicting the water environment carrying capacity of lake basins in arid areas in Example 2 of the present invention;

[0059] Figure 3 This is a schematic diagram of the structure of an electronic device in Embodiment 3 of the present invention;

[0060] Figure 4 This is a schematic diagram of the computer-readable storage medium structure in Example 4 of the present invention. DETAILED DESCRIPTION

[0061] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] Example 1

[0063] like Figure 1 As shown, the water environment carrying capacity evaluation and prediction system for lake basins in arid areas includes a training data collection module, a training sample construction module, a model training module and a carrying capacity prediction module; wherein each module is electrically connected;

[0064] The training data collection module is used to collect historical meteorological data, historical water level label data, historical meteorological characteristic data and historical drought duration label data, and send them to the training sample construction module;

[0065] Specifically, the historical meteorological data and the historical water level tag data are collected as follows:

[0066] Extracting various daily meteorological parameters and lake water levels of lakes from historical meteorological records and historical water level records of lakes in arid regions, respectively, wherein various daily meteorological parameters constitute the historical meteorological data, and daily lake water levels constitute the historical water level label data;

[0067] The meteorological parameters constituting the historical meteorological data include but are not limited to:

[0068] Precipitation data: Daily precipitation records are obtained through meteorological stations or satellite remote sensing products in the area where the lake is located.

[0069] Temperature data: comes from meteorological stations set up around the lake, collecting daily average temperature, daily maximum / minimum temperature, etc.

[0070] Evaporation data: calculated from meteorological station observation data or empirical formulas (such as potential evapotranspiration formula).

[0071] Other meteorological data: such as relative humidity, wind speed, sunshine hours and other possible influencing factors;

[0072] The historical water level tag data is obtained by analyzing the daily water level of the lake from manual measurement data, automatic monitoring station data or remote sensing data;

[0073] Specific:

[0074] The manual measurement data analysis method is as follows: on-site observers regularly measure the lake water level and record it.

[0075] The data analysis method of the automatic monitoring station is as follows: the water level monitoring equipment deployed in the lake area automatically collects and uploads the water level data.

[0076] The remote sensing data analysis method is: using satellite remote sensing images and other technologies to invert and estimate indicators such as lake area / volume.

[0077] Furthermore, the historical meteorological characteristic data and historical drought duration label data are collected in the following manner:

[0078] The starting time of each drought event is extracted from the historical drought records of lakes in the drought area, and the meteorological characteristics between the starting time of each drought event are intercepted from the historical precipitation records. The difference in the starting time of each drought event is used as the historical drought duration label; the meteorological characteristics of all drought events constitute the historical meteorological characteristic data; the historical drought duration labels of all drought events constitute the historical drought duration label data;

[0079] Specifically, the meteorological characteristics include but are not limited to:

[0080] Standardized Precipitation Index: A drought monitoring index calculated based on the precipitation time series. It is a conventional meteorological parameter in this field and will not be further described.

[0081] Total Precipitation: Calculates the total precipitation series from precipitation observations.

[0082] Other meteorological characteristics: temperature, relative humidity, etc. are obtained from meteorological stations or satellite remote sensing.

[0083] A training sample construction module constructs a number of lake water level training samples through historical meteorological data and historical water level label data, constructs a number of drought duration training samples through historical meteorological characteristic data and historical drought duration label data, and sends the lake water level training samples and drought duration training samples to the model training module;

[0084] Specifically, the lake water level training sample is constructed as follows:

[0085] Set the output sequence duration T, input sequence duration L and sliding window step size S;

[0086] Preferably, a typical example of the duration of T, L and S is as follows:

[0087] L = 9, including the weather conditions of the past 9 days;

[0088] T=3 means predicting the water level for the next 3 days;

[0089] S = 1 day, that is, one sample is constructed every day;

[0090] Label any historical date as t;

[0091] The number of each meteorological parameter is marked as x, and the parameter value of the xth meteorological parameter on the tth day is marked as x_t;

[0092] Construct a meteorological parameter sequence for the xth meteorological parameter: [x_(t-L+1), x_(t-L+2), ... x_t];

[0093] Mark the lake water level on day t as y_t; construct a water level label sequence: [y_(t+1), y_(t+2), ...y_(t+T)];

[0094] Preferably, in order to improve the prediction accuracy, the water level sequence of the lake water level in the past L days (i.e. [y_(t-L+1), y_(t-L+2), ...y_t]) can also be used as one of the meteorological parameter sequences;

[0095] The meteorological parameter sequences of all meteorological parameters constitute a set of input sample sets;

[0096] A set of input sample sets and water level label sequences form a set of lake water level training samples;

[0097] Slide t back S days and reconstruct a new set of lake water level training samples;

[0098] It can be understood that a number of lake water level training samples can be constructed through the above sliding window method, that is, the lake water level in the next L days can be predicted through the meteorological performance and lake water level performance in the past L days;

[0099] Furthermore, the method of constructing a number of drought duration training samples by using historical meteorological characteristic data and historical drought duration label data is as follows:

[0100] For each drought event, the historical drought duration label of the drought event is used as the duration sample label in advance;

[0101] Taking the start time of the drought event as the central time point, a drought event meteorological feature window is constructed as the input feature of the sample; the drought event meteorological feature window includes various meteorological features before and after the central time point; the length of the drought event meteorological feature window is preset, and the length of the drought event meteorological feature window is marked as W;

[0102] The drought event meteorological characteristic window and duration sample label of each drought event are constructed into a set of drought duration training samples;

[0103] The model training module uses the lake water level training samples to train the water level series prediction model, and uses the drought duration training samples to train the drought duration prediction model, and sends the water level series prediction model and the drought duration prediction model to the carrying capacity prediction module;

[0104] The training method of the water level series prediction model is:

[0105] The input sample set of each date is used as the input of the water level sequence prediction model, the water level sequence prediction model takes the predicted value of the lake water level sequence T days after the date as the output, takes the water level label sequence corresponding to the input sample set as the prediction target, takes the Euclidean distance between the predicted value of the lake water level sequence and the water level label sequence as the first prediction error, and takes minimizing the sum of the first prediction errors as the training goal; the water level sequence prediction model is trained until the sum of the first prediction errors reaches convergence, and the training is stopped; the water level sequence prediction model is a time series prediction model; the time series prediction model is any one of an RNN model or an LSTM model;

[0106] The training method of the drought duration prediction model is:

[0107] The meteorological characteristic window of each drought event is used as the input of the drought duration prediction model, the drought duration prediction model takes the predicted value of the drought duration of the drought event as the output, takes the duration sample label corresponding to the drought event as the prediction target, takes the square of the difference between the predicted value of the drought duration and the duration sample label as the second prediction error, and takes minimizing the average value of the second prediction errors of all drought events as the training target; the drought duration prediction model is trained until the sum of the second prediction errors reaches convergence and the training is stopped; the drought duration prediction model is a time series prediction model;

[0108] The carrying capacity prediction module is used to collect future meteorological data, future meteorological characteristic data and real-time lake water level, and output the future drought duration based on the future meteorological characteristic data and drought duration prediction model, and then output the future lake water level sequence based on the future meteorological data, future drought duration, water level sequence prediction model and real-time lake water level, and issue an early warning for the lake carrying capacity based on the future lake water level sequence;

[0109] It is understandable that there are a large number of related technical means and related applications (such as weather forecast) for future meteorological data and future meteorological characteristic data, such as rainfall, temperature and humidity. The present invention will not elaborate on how to obtain future daily meteorological data and meteorological characteristic data.

[0110] Furthermore, since the error of weather forecast increases with the increase of time distance, in order to control the accuracy of the forecast, it is considered to collect the forecasted weather data for a limited number of days in the future;

[0111] The method of outputting the future drought duration based on the future meteorological characteristic data and the drought duration prediction model is as follows:

[0112] The duration of the future weather data to be collected is marked as F;

[0113] Mark the most recent date as t0, and the latest date for the predicted meteorological data and meteorological characteristic data is t0+F;

[0114] by The corresponding date is taken as the center date, and the dates before and after the center date are The meteorological characteristics of the day together form a set of time-length forecast input windows;

[0115] Input the duration prediction input window into the drought duration prediction model to obtain The predicted value of the drought duration corresponding to the corresponding date is used as the future drought duration;

[0116] It is understandable that when the future drought duration is less than the preset drought duration threshold, it is considered that drought will not occur, that is, the risk of lake carrying capacity is small, and lake carrying capacity warning is not required;

[0117] Since the above-mentioned future drought duration can be calculated on a daily basis, that is, The duration of drought after the next day is actually a prediction of the duration of drought for each day in the future (on different dates), which means that the carrying capacity warning is implemented every day in the future;

[0118] The future drought duration is marked as K;

[0119] The method of outputting the future lake water level sequence based on future meteorological data, future drought duration, water level sequence prediction model and real-time lake water level and providing early warning of lake carrying capacity based on the future lake water level sequence is as follows:

[0120] Due to judgment Day is the central time point of the drought event, so the time period for analyzing the lake water level is The time period is expressed as the target time period. For the sake of simplicity, the upper and lower time points of the target time period are marked as t_min and t_max respectively; that is,

[0121] Divide the target time period into equal intervals according to the output sequence duration T. prediction durations, corresponding to forecast time period;

[0122] Specifically, the The time periods corresponding to the prediction time periods are t_min to t_min+T, t_min+T to t_min+2×T, .....t_max-T to t_max;

[0123] For each forecast period, the meteorological parameter sequences of various meteorological parameters L days before the forecast period are composed of a set of water level forecast input sequences, and all water level forecast input sequences are composed of an actual input set;

[0124] Input the actual input set into the water level series prediction model to obtain the predicted value sequence of the lake water level within the prediction time period;

[0125] The sequence of predicted values ​​of lake water level for all forecast time periods consists of a sequence of water level fluctuations of lake water level with the central point date as the period of drought event occurrence;

[0126] The lake water level is divided into several carrying capacity levels, each carrying capacity level corresponds to an upper limit and a lower limit of the water level, thereby forming a water level range for each carrying capacity level;

[0127] Preferably, the bearing capacity levels may include normal, warning, critical, extreme, etc., and the water level ranges of different bearing capacity levels may be: normal>=97m; warning>=95m and <97m; critical>=93m and <95m; extreme<93m;

[0128] Count the proportion of days in each carrying capacity level from the water level fluctuation series;

[0129] Determine whether to implement bearing capacity warning based on the proportion of days at each bearing capacity level;

[0130] Preferably, one method of judging whether to implement bearing capacity warning according to the proportion of days of each bearing capacity level is:

[0131] Set a critical probability upper limit. If the proportion of days with extreme (or critical and extreme) carrying capacity levels is greater than the critical probability upper limit, an early warning is initiated.

[0132] Another method of determining whether to implement bearing capacity warning according to the proportion of days of each bearing capacity level is:

[0133] Set a lower limit for the warning probability. If the proportion of days with normal (or normal and warning) carrying capacity is less than the lower limit, an early warning is initiated.

[0134] Therefore, the specific critical warning conditions are flexibly set according to actual needs, and various methods of judging whether to implement bearing capacity warning based on the proportion of days fall within the protection scope of the present invention.

[0135] Example 2

[0136] like Figure 2 As shown in the figure, the method for evaluating and predicting the water environment carrying capacity of lake basins in arid areas includes the following steps:

[0137] Collect historical meteorological data, historical water level label data, historical meteorological characteristic data, and historical drought duration label data;

[0138] Several lake water level training samples are constructed through historical meteorological data and historical water level label data, and several drought duration training samples are constructed through historical meteorological characteristic data and historical drought duration label data;

[0139] Use lake water level training samples to train the water level series prediction model, and use drought duration training samples to train the drought duration prediction model;

[0140] Collect future meteorological data, future meteorological characteristic data and real-time lake water level, and output the future drought duration based on the future meteorological characteristic data and the drought duration prediction model. Then output the future lake water level sequence based on the future meteorological data, future drought duration, the water level sequence prediction model and the real-time lake water level. Based on the future lake water level sequence, give early warning on the lake carrying capacity.

[0141] Example 3

[0142] See also Figure 3 As shown, according to another aspect of the present application, an electronic device 500 is also provided. The electronic device 500 may include one or more processors and one or more memories. The memories store computer readable codes, and when the computer readable codes are executed by one or more processors, the water environment carrying capacity evaluation and prediction method of arid lake basins can be executed.

[0143] The method or system according to the embodiment of the present application can also be used by Figure 3 The electronic device architecture shown in FIG. Figure 3 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a read-only memory (ROM) 503, a random access memory (RAM) 504, a communication port 505 connected to a network, an input / output component 506, a hard disk 507, etc. The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, may store the water environment carrying capacity evaluation and prediction method for arid lake basins provided in the present application. Furthermore, the electronic device 500 may also include a user interface 508. Of course, Figure 3 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 3 One or more components of an electronic device are shown.

[0144] Example 4

[0145] See also Figure 4As shown, a computer-readable storage medium 600 according to an embodiment of the present application is shown. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are executed by the processor, the method for evaluating and predicting the water environment carrying capacity of a lake basin in an arid area according to an embodiment of the present application described with reference to the above figures can be executed. The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0146] In addition, according to the embodiments of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, which stores machine-readable instructions, and the machine-readable instructions can be executed by a processor to execute instructions corresponding to the method steps provided by the present application;

[0147] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0148] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0149] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0150] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a method for evaluating and predicting the water environment carrying capacity of lake basins in arid areas. There may be other division methods in actual implementation. 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0151] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0152] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0153] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. The water environment carrying capacity assessment and prediction system for lake basins in arid areas is characterized by: It includes a training data collection module, a training sample construction module, a model training module and a bearing capacity prediction module; wherein each module is electrically connected; The training data collection module is used to collect historical meteorological data, historical water level label data, historical meteorological characteristic data and historical drought duration label data, and send them to the training sample construction module; A training sample construction module constructs a number of lake water level training samples through historical meteorological data and historical water level label data, constructs a number of drought duration training samples through historical meteorological characteristic data and historical drought duration label data, and sends the lake water level training samples and drought duration training samples to the model training module; The model training module uses the lake water level training samples to train the water level series prediction model, and uses the drought duration training samples to train the drought duration prediction model, and sends the water level series prediction model and the drought duration prediction model to the carrying capacity prediction module; The carrying capacity prediction module is used to collect future meteorological data, future meteorological characteristic data and real-time lake water level, and output the future drought duration based on the future meteorological characteristic data and the drought duration prediction model, and then output the future lake water level sequence based on the future meteorological data, future drought duration, the water level sequence prediction model and the real-time lake water level, and issue an early warning for the lake carrying capacity based on the future lake water level sequence.

2. The water environment carrying capacity evaluation and prediction system for lake basins in arid areas according to claim 1 is characterized in that: The historical meteorological data and the historical water level tag data are collected in the following manner: Extracting various daily meteorological parameters and lake water levels of lakes from historical meteorological records and historical water level records of lakes in arid regions, respectively, wherein various daily meteorological parameters constitute the historical meteorological data, and daily lake water levels constitute the historical water level label data; The historical water level tag data is obtained by analyzing the daily water level of the lake from manual measurement data, automatic monitoring station data or remote sensing data; The historical meteorological characteristic data and historical drought duration label data are collected in the following manner: The starting time of each drought event is extracted from the historical drought records of lakes in arid areas, and the meteorological characteristics between the starting time of each drought event are intercepted from the historical precipitation records. The difference in the starting time of each drought event is used as the historical drought duration label; the meteorological characteristics of all drought events constitute the historical meteorological characteristic data; the historical drought duration labels of all drought events constitute the historical drought duration label data.

3. The water environment carrying capacity evaluation and prediction system for lake basins in arid areas according to claim 2 is characterized in that: The lake water level training sample is constructed as follows: Set the output sequence duration T, input sequence duration L and sliding window step size S; Label any historical date as t; The number of each meteorological parameter is marked as x, and the parameter value of the xth meteorological parameter on the tth day is marked as x_t; Construct a meteorological parameter sequence for the xth meteorological parameter: [x_(t-L+1), x_(t-L+2), ... x_t]; Mark the lake water level on day t as y_t; construct a water level label sequence: [y_(t+1), y_(t+2), ...y_(t+T)]; The meteorological parameter sequences of all meteorological parameters constitute a set of input sample sets; A set of input sample sets and water level label sequences form a set of lake water level training samples; Slide t back S days and reconstruct a new set of lake water level training samples.

4. The system for evaluating and predicting the water environment carrying capacity of lake basins in arid areas according to claim 3 is characterized in that: The method of constructing a number of drought duration training samples using historical meteorological characteristic data and historical drought duration label data is as follows: For each drought event, the historical drought duration label of the drought event is used as the duration sample label in advance; Taking the start time of the drought event as the central time point, a drought event meteorological feature window is constructed as the input feature of the sample; the drought event meteorological feature window includes various meteorological features before and after the central time point; the length of the drought event meteorological feature window is preset, and the length of the drought event meteorological feature window is marked as W; The drought event meteorological characteristic window and duration sample label of each drought event are constructed into a set of drought duration training samples.

5. The system for evaluating and predicting the water environment carrying capacity of lake basins in arid areas according to claim 4 is characterized in that: The training method of the water level series prediction model and the drought duration prediction model is: The input sample set of each date is used as the input of the water level sequence prediction model, the water level sequence prediction model takes the predicted value of the lake water level sequence T days after the date as the output, takes the water level label sequence corresponding to the input sample set as the prediction target, takes the Euclidean distance between the predicted value of the lake water level sequence and the water level label sequence as the first prediction error, and takes minimizing the sum of the first prediction errors as the training target; the water level sequence prediction model is trained until the sum of the first prediction errors reaches convergence and the training is stopped; the water level sequence prediction model is a time series prediction model; The meteorological characteristic window of the drought event of each drought event is used as the input of the drought duration prediction model. The drought duration prediction model takes the predicted value of the drought duration of the drought event as the output, takes the duration sample label corresponding to the drought event as the prediction target, takes the square of the difference between the predicted value of the drought duration and the duration sample label as the second prediction error, and takes minimizing the average value of the second prediction errors of all drought events as the training target; the drought duration prediction model is trained until the sum of the second prediction errors reaches convergence, and the training is stopped; the drought duration prediction model is a time series prediction model.

6. The system for evaluating and predicting the water environment carrying capacity of lake basins in arid areas according to claim 5 is characterized in that: The method of outputting the future drought duration based on the future meteorological characteristic data and the drought duration prediction model is as follows: The duration of the future weather data to be collected is marked as F; Mark the most recent date as t0, and the latest date for the predicted meteorological data and meteorological characteristic data is t0+F; by The corresponding date is taken as the center date, and the dates before and after the center date are The meteorological characteristics of the day together form a set of time-length forecast input windows; Input the duration prediction input window into the drought duration prediction model to obtain The predicted value of the drought duration corresponding to the corresponding date is used as the future drought duration; The future drought duration is labeled K.

7. The system for evaluating and predicting the water environment carrying capacity of lake basins in arid areas according to claim 6 is characterized in that: The method of outputting the future lake water level sequence based on future meteorological data, future drought duration, water level sequence prediction model and real-time lake water level and providing early warning of lake carrying capacity based on the future lake water level sequence is as follows: The time period It is represented as a target time period, and the upper and lower time points of the target time period are marked as t_min and t_max respectively; Divide the target time period into equal intervals according to the output sequence duration T. prediction durations, corresponding to forecast time period; For each forecast period, the meteorological parameter sequences of various meteorological parameters L days before the forecast period are composed of a set of water level forecast input sequences, and all water level forecast input sequences are composed of an actual input set; Input the actual input set into the water level series prediction model to obtain the predicted value sequence of the lake water level within the prediction time period; The sequence of predicted values ​​of lake water level for all forecast time periods consists of a sequence of water level fluctuations of lake water level with the central point date as the period of drought event occurrence; The lake water level is divided into several carrying capacity levels, each carrying capacity level corresponds to an upper limit and a lower limit of the water level, thereby forming a water level range for each carrying capacity level; Count the proportion of days in each carrying capacity level from the water level fluctuation series; Whether to implement bearing capacity warning is determined based on the proportion of days with each bearing capacity level.

8. A method for evaluating and predicting the water environment carrying capacity of a lake basin in an arid area, which is implemented based on the system for evaluating and predicting the water environment carrying capacity of a lake basin in an arid area according to any one of claims 1 to 7, and is characterized by: The following steps are involved: Collect historical meteorological data, historical water level label data, historical meteorological characteristic data, and historical drought duration label data; Several lake water level training samples are constructed through historical meteorological data and historical water level label data, and several drought duration training samples are constructed through historical meteorological characteristic data and historical drought duration label data; Use lake water level training samples to train the water level series prediction model, and use drought duration training samples to train the drought duration prediction model; Collect future meteorological data, future meteorological characteristic data and real-time lake water level, and output the future drought duration based on the future meteorological characteristic data and the drought duration prediction model. Then output the future lake water level sequence based on the future meteorological data, future drought duration, the water level sequence prediction model and the real-time lake water level. Based on the future lake water level sequence, give early warning on the lake carrying capacity.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the arid area lake basin water environment carrying capacity assessment and prediction system as described in claim 8 by calling the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are run on a computer, the computer executes the water environment carrying capacity assessment and prediction system for arid lake basins as described in claim 8.

Images