Hydrological data prediction method based on data analysis

Abstract

The present invention relates to the field of disaster prediction, and specifically to a hydrological data prediction method based on data analysis. The method first obtains the daily precipitation, soil moisture content, and soil infiltration rate of the area to be tested within a preset historical time period, obtains the daily precipitation intensity based on the daily precipitation and the precipitation of each day in the preset time domain, obtains the daily soil severity based on the daily soil moisture content, soil infiltration rate, and precipitation intensity, and analyzes the similarity of precipitation intensity and soil severity between normal days and disaster days. Similar normal days are screened out from all normal days. Based on the precipitation, soil moisture content, and soil infiltration rate of each similar normal day and disaster day, a disaster prediction model is constructed, and debris flow disasters are predicted for the current day. The present invention can improve the accuracy of debris flow disaster prediction.

Description

Technical Field

[0001] The present invention relates to the field of disaster prediction, and in particular to a hydrological data prediction method based on data analysis. Background Art

[0002] A debris flow is a special torrent of water caused by precipitation in valleys or hillsides, carrying a large amount of solid materials such as mud, sand, stones and boulders. It is characterized by suddenness, fast flow rate, large flow rate, large material capacity and strong destructive power. The occurrence of debris flows is usually accompanied by huge casualties and property losses. Therefore, accurate prediction of the occurrence of debris flow disasters can help relevant personnel take preventive and remedial measures in a timely manner.

[0003] In related technologies, hydrogeological data related to debris flow disasters, such as precipitation, soil moisture content, soil porosity, etc., are usually analyzed to predict debris flow disasters. However, due to the large differences in hydrogeological data in the same area at different times, the possibility of debris flow disasters occurring at different times is different, which makes it impossible to accurately predict the occurrence of debris flow disasters through existing methods. Summary of the Invention

[0004] In order to solve the technical problem that existing methods cannot accurately predict the occurrence of debris flow disasters, the purpose of the present invention is to provide a hydrological data prediction method based on data analysis. The technical solution adopted is as follows:

[0005] The present invention proposes a hydrological data prediction method based on data analysis, the method comprising:

[0006] Obtain daily precipitation, soil moisture content, and soil infiltration rate for the area to be measured within a preset historical time period. The days corresponding to debris flows occurring within the preset historical time period are considered disaster days, and the other historical days except for disaster days are considered normal days.

[0007] Obtaining daily precipitation intensity based on the daily precipitation and the precipitation of each day in a preset time domain; obtaining daily soil severity based on the daily soil moisture content, the soil infiltration rate, and the precipitation intensity;

[0008] Taking any normal day as a target normal day, obtaining the similarity of precipitation characteristics of each disaster day with respect to the target normal day based on the difference in precipitation intensity between each disaster day and the target normal day; obtaining the similarity of soil characteristics of each disaster day with respect to the target normal day based on the difference in soil severity between each disaster day and the target normal day; clustering all disaster days based on the difference in precipitation characteristic similarity and soil characteristic similarity between each disaster day with respect to the target normal day, obtaining multiple clusters of target normal days; obtaining the disaster probability of the target normal day based on the precipitation characteristic similarity and soil characteristic similarity of each disaster day in each cluster with respect to the target normal day and the number of disaster days in each cluster; and screening out similar normal days from all normal days based on the disaster probability;

[0009] Based on the precipitation, soil moisture content and soil infiltration rate of similar normal days and disaster days, a disaster prediction model is constructed, and the debris flow disaster of the current day is predicted.

[0010] Furthermore, obtaining the daily precipitation intensity includes:

[0011] Take any day as the target day, take the precipitation on the target day as the numerator, take the sum of the precipitation on all days in the preset time domain of the target day as the denominator, and take the ratio as the precipitation ratio of the target day;

[0012] The number of days with precipitation greater than 0 in the preset time domain of the target day is used as the numerator, all days in the preset time domain of the target day is used as the denominator, and the ratio is used as the proportion of precipitation days in the target day;

[0013] Taking the average of the precipitation of all days in the preset time domain of the target day as the overall precipitation of the preset time domain of the target day, normalizing the difference between the precipitation of the target day and the overall precipitation to obtain a relative difference value of precipitation on the target day;

[0014] The precipitation ratio of the target day, the ratio of the number of precipitation days and the relative difference value of precipitation are integrated and normalized to obtain the precipitation intensity of the target day.

[0015] Furthermore, obtaining the soil severity every day includes:

[0016] The soil moisture content, the soil infiltration rate and the precipitation intensity of the target day are integrated and normalized to obtain the soil severity of the target day.

[0017] Furthermore, obtaining the similarity of precipitation characteristics of each disaster day with respect to a target normal day includes:

[0018] The absolute value of the difference in precipitation intensity between each disaster day and the target normal day is subjected to negative correlation normalization processing to obtain the precipitation feature similarity of each disaster day with respect to the target normal day.

[0019] Furthermore, obtaining the soil characteristic similarity of each disaster day with respect to the target normal day includes:

[0020] The absolute value of the difference in soil severity between each disaster day and the target normal day is normalized by negative correlation to obtain the soil characteristic similarity of each disaster day with respect to the target normal day.

[0021] Furthermore, obtaining a plurality of clusters of target normal days includes:

[0022] Based on the precipitation feature similarity and the soil feature similarity of each disaster day with respect to the target normal day, calculating the Euclidean distance between any two disaster days as a distance metric between any two disaster days;

[0023] Using the K-means clustering algorithm and based on the distance metric between any two disaster days, all disaster days are clustered to obtain multiple clusters of target normal days.

[0024] Furthermore, obtaining the disaster probability of a target normal day includes:

[0025] Selecting a reference cluster of target normal days from among all the clusters of target normal days, wherein the number of disaster days in the reference cluster is the largest;

[0026] The average of the precipitation feature similarities of all disaster days in the reference cluster of the target normal day with respect to the target normal day is used as the first overall similarity of the target normal day. The average of the soil feature similarities of all disaster days in the reference cluster of the target normal day with respect to the target normal day is used as the second overall similarity of the target normal day. The first overall similarity of the target normal day, the second overall similarity, and the number of disaster days in the reference cluster of the target normal day are integrated to obtain the disaster environment similarity of the target normal day.

[0027] Obtaining a disaster risk coefficient for the target normal day according to a difference between the precipitation intensity on the target normal day and the overall level of the precipitation intensities on all normal days, and a difference between the soil severity on the target normal day and the overall level of the soil severity on all normal days;

[0028] The disaster environment similarity and the disaster risk coefficient of the target normal day are integrated and normalized to obtain the disaster possibility of the target normal day.

[0029] Furthermore, obtaining the disaster risk coefficient of the target normal day includes:

[0030] The precipitation intensity of the target normal day is used as the numerator, the average of the precipitation intensities of all normal days is used as the denominator, and the ratio is used as the first risk coefficient of the target normal day;

[0031] The soil severity of the target normal day is used as the numerator, the average of the soil severity of all normal days is used as the denominator, and the ratio is used as the second risk coefficient of the target normal day;

[0032] The first risk coefficient and the second risk coefficient of a target normal day are integrated to obtain a disaster risk coefficient of the target normal day.

[0033] Furthermore, based on the disaster possibility, screening similar normal days from all normal days includes:

[0034] Normal days with disaster probability greater than the preset probability threshold are regarded as similar normal days.

[0035] Furthermore, the prediction of debris flow disasters on the current day includes:

[0036] Standardizing the precipitation, soil moisture content, and soil infiltration rate of each similar normal day and each disaster day to obtain the standard precipitation, standard soil moisture content, and standard soil infiltration rate of each similar normal day and each disaster day;

[0037] Any similar normal day or any disaster day is used as the day to be measured, and the vector consisting of the standard precipitation, the standard soil moisture content, and the standard soil infiltration rate of the day to be measured is used as the feature vector of the day to be measured. If the day to be measured is a similar normal day, the class label of the feature vector of the day to be measured is set to a value of 0; if the day to be measured is a disaster day, the class label of the feature vector of the day to be measured is set to a value of 1, and the set consisting of the feature vectors with the class labels of all similar normal days and all disaster days is used as the training set;

[0038] Inputting the data in the training set into a support vector machine for training, and using the trained support vector machine as a disaster prediction model;

[0039] The current day's precipitation, soil moisture content, and soil infiltration rate are input into the disaster prediction model, which then outputs the debris flow disaster prediction result for the current day.

[0040] The present invention has the following beneficial effects:

[0041] The present invention takes into account that the existing methods cannot accurately predict the occurrence of debris flow disasters. Therefore, the daily precipitation, soil moisture content and soil infiltration rate of the test area in a preset historical time period are first obtained, and the days corresponding to the occurrence of debris flow are regarded as disaster days, and the days corresponding to no debris flow are regarded as normal days. Taking into account that different precipitation amounts and precipitation conditions in local time periods have different degrees of difficulty in triggering debris flow disasters, the obtained precipitation intensity can be used to reflect the possibility of the daily precipitation state to trigger debris flow disasters. At the same time, considering that the state characteristics of the soil are also a key factor in triggering debris flow disasters, the obtained soil severity can be used to reflect the possibility of the daily soil state in the test area to trigger debris flow disasters, providing a data basis for the subsequent analysis of the similarity of environmental characteristics between normal days and disaster days. Due to the interference of external factors, some normal days are close to the conditions for debris flow but no debris flow occurs. These normal days with similar soil and precipitation conditions to disaster days also need to be taken seriously. Therefore, the precipitation feature similarity is firstly reflected by the obtained precipitation feature similarity, and the soil feature similarity is used to reflect the similarity of soil conditions between the target normal day and each disaster day. Then, the disaster days with close precipitation feature similarity and soil feature similarity are divided into the same cluster. The possibility of debris flow disaster on the target normal day is further reflected by the disaster possibility, and similar normal days with close debris flow conditions are screened out. Using various data of each similar normal day and disaster day, an effective disaster prediction model is constructed, and the debris flow disaster of the current day is accurately predicted. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 A flow chart of a hydrological data prediction method based on data analysis provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0044] To further illustrate the technical means and effectiveness of the present invention in achieving its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementation, structure, features, and effectiveness of a hydrological data prediction method based on data analysis proposed by the present invention. In the following description, references to different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0045] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0046] The following describes in detail a specific scheme of a hydrological data prediction method based on data analysis provided by the present invention with reference to the accompanying drawings.

[0047] See also Figure 1 , which shows a flow chart of a hydrological data prediction method based on data analysis provided by one embodiment of the present invention, the method comprising:

[0048] Step S1: Obtain the daily precipitation, soil moisture content, and soil infiltration rate of the area to be tested within a preset historical time period, and define the days corresponding to the occurrence of debris flow within the preset historical time period as disaster days, and define the other historical days except the disaster days as normal days.

[0049] For areas where debris flows frequently occur, relevant surveyors usually measure the hydrogeological data related to debris flow disasters in the area, such as precipitation, soil moisture content, and soil infiltration rate, and then record and save these data in the hydrogeological database for subsequent data analysis.

[0050] Therefore, the embodiment of the present invention first extracts the daily precipitation, soil moisture content and soil infiltration rate within a preset historical time period from the hydrogeological database of the area to be measured, wherein the preset historical time period is set to 1 year, and the specific value of the preset historical time period can also be set by the implementer according to the specific real-time scenario, which is not limited here.

[0051] It should be noted that multiple debris flow disasters usually occur within a preset historical time period. Therefore, the embodiment of the present invention regards the days corresponding to the occurrence of debris flow within the preset historical time period as disaster days, and regards other historical days except disaster days as normal days. That is to say, debris flow disasters do not occur on normal days. Subsequently, by analyzing the similarity of environmental characteristics between normal days and disaster days, and combining various hydrological data of normal days and disaster days, accurate prediction of debris flow disasters can be made.

[0052] Step S2: Obtain daily precipitation intensity based on daily precipitation and precipitation on each day in a preset time domain; obtain daily soil severity based on daily soil moisture content, soil infiltration rate, and precipitation intensity.

[0053] Different precipitation amounts have different probabilities of causing debris flow disasters. Before each debris flow disaster occurs, the more precipitation there is and the longer it lasts, the more likely it is to cause a debris flow. Or, the more precipitation there is in a short period of time, the more likely it is to cause a debris flow. Therefore, the embodiment of the present invention analyzes the daily precipitation and the precipitation amount of each day in the preset time domain of each day. The obtained precipitation intensity reflects the possibility of the daily precipitation state causing a debris flow disaster. The greater the precipitation intensity on a certain day, the more likely the precipitation characteristics of that day are to cause a debris flow disaster, providing a data basis for subsequent analysis of the similarity of environmental characteristics between normal days and disaster days. Among them, the length of the preset time domain of a certain day is set to 7, that is, the preset time domain of the day includes the six days closest to the day and the day.

[0054] Preferably, in one embodiment of the present invention, the method for obtaining daily precipitation intensity specifically includes:

[0055] Take any day as the target day, the precipitation on the target day as the numerator, the sum of the precipitation on all days in the preset time domain of the target day as the denominator, and the ratio as the precipitation ratio of the target day. The larger the precipitation ratio, the greater the precipitation on the target day relative to the precipitation on other days in the preset time domain, and thus the more likely the precipitation on the target day is to cause a mudslide disaster.

[0056] The number of days with precipitation greater than 0 in the preset time domain of the target day is used as the numerator, all days in the preset time domain of the target day is used as the denominator, and the ratio is used as the proportion of precipitation days on the target day. Among them, if the precipitation on a certain day is greater than 0, it means that it is rainy day. The larger the proportion of precipitation days, the more frequent the precipitation in the preset time domain of the target day, and the more likely it is to cause mudslide disasters.

[0057] The average of the precipitation of all days in the preset time domain of the target day is taken as the overall precipitation of the preset time domain of the target day, and the difference between the precipitation of the target day and the overall precipitation is normalized, and the calculation result is limited to The relative difference value of precipitation on the target day is obtained. The larger the relative difference value of precipitation, the greater the precipitation on the target day is relative to the overall precipitation in the preset time domain, which further indicates that it is more likely to cause a debris flow disaster.

[0058] After the target day’s precipitation percentage, precipitation days percentage and precipitation relative difference values ​​are integrated and normalized, the calculation results are limited to range, thereby obtaining the precipitation intensity of the target day.

[0059] In an embodiment of the present invention, the integration of the three can be achieved by calculating the sum or product of the precipitation ratio of the target day, the ratio of precipitation days and the relative difference value of precipitation, which is not limited here.

[0060] In one embodiment of the present invention, the normalization processing can be specifically, for example, maximum and minimum value normalization processing, and the normalization in subsequent steps can all adopt maximum and minimum value normalization processing. In other embodiments of the present invention, other normalization methods can be selected according to the specific range of numerical values, which will not be repeated here.

[0061] As an example, in one embodiment of the present invention, the expression for the precipitation intensity on the target day may be specifically, for example, as follows:

[0062]

[0063] in, represents the precipitation intensity on the target day; represents the precipitation amount on the target day; The sum of the precipitation amounts of all days in the preset time domain representing the target day; Indicates the percentage of precipitation on the target day. Since the embodiment of the present invention predicts the area where debris flow occurs frequently, the precipitation in such area is relatively frequent. ; Indicates the number of days with precipitation greater than 0 in the preset time domain of the target day; Indicates all days in the preset time domain of the target day, that is, the length of the preset time domain. In one embodiment of the present invention, ; Indicates the overall precipitation in the preset time domain on the target day; Represents the activation function, which is used for normalization processing; Represents the normalization function.

[0064] The same method described above can be used to obtain daily precipitation intensity. During precipitation, large amounts of precipitation can quickly saturate the soil. Excessive water content leads to soil saturation, reducing the soil's water resistance, accelerating soil fluidity and erosion, and increasing the risk of debris flow disasters. The soil infiltration rate determines the penetration rate and distribution uniformity of precipitation water in the soil, affecting the rate of change in soil water content and soil saturation. When the soil reaches saturation, runoff begins to form on the surface. As rainfall continues to increase, debris flow disasters are more likely to occur. Therefore, the embodiment of the present invention analyzes daily soil water content and soil infiltration rate. At the same time, the greater the precipitation intensity on a certain day, the more likely the precipitation on that day will make the soil state more likely to cause debris flow disasters. Therefore, the soil severity obtained in combination with the daily precipitation intensity can reflect the possibility of the soil state in the test area triggering debris flow disasters on that day. The greater the soil severity on a certain day, the more likely the soil state on that day is to trigger debris flow disasters. This provides a data basis for subsequent analysis of the similarity of environmental characteristics between normal days and disaster days.

[0065] Preferably, in one embodiment of the present invention, the method for obtaining the daily soil severity specifically includes:

[0066] The soil moisture content, soil infiltration rate and precipitation intensity of the target day are integrated and normalized, and the calculation results are limited to range, thereby obtaining the soil severity on the target day.

[0067] In the embodiment of the present invention, the integration of soil moisture content, soil infiltration rate and precipitation intensity on the target day can be achieved by calculating the sum or product of the three, which is not limited here.

[0068] As an example, in one embodiment of the present invention, the expression for the soil severity on the target day may be specifically, for example, as follows:

[0069]

[0070] in, Indicates the severity of the soil on the target day; represents the soil moisture content on the target day; represents the soil infiltration rate on the target day; represents the precipitation intensity on the target day; Represents the normalization function.

[0071] The same method as above can be used to obtain the daily soil severity. At this point, the daily precipitation intensity and soil severity are obtained.

[0072] Step S3: Take any normal day as the target normal day, and obtain the precipitation feature similarity of each disaster day with respect to the target normal day based on the difference in precipitation intensity between each disaster day and the target normal day; obtain the soil feature similarity of each disaster day with respect to the target normal day based on the difference in soil severity between each disaster day and the target normal day; cluster all disaster days based on the difference in precipitation feature similarity and soil feature similarity between each disaster day with respect to the target normal day, and obtain multiple clusters of target normal days; obtain the disaster possibility of the target normal day based on the precipitation feature similarity and soil feature similarity of each disaster day in each cluster with respect to the target normal day and the number of disaster days in each cluster; and screen out similar normal days from all normal days based on the disaster possibility.

[0073] Since the occurrence of debris flow disasters is affected by many factors, under the interference of other external factors that are not considered, some normal days are close to the conditions for debris flow occurrence but do not experience debris flow, but are on the verge of debris flow disasters, and there is a great possibility of debris flow disasters. These normal days with similar soil and precipitation conditions to those on disaster days also need to be taken seriously. Therefore, the embodiment of the present invention first analyzes any normal day, takes any normal day as the target normal day, and obtains the precipitation feature similarity of each disaster day with respect to the target normal day based on the difference in precipitation intensity between each disaster day and the target normal day. The precipitation feature similarity reflects the similarity of precipitation features between the target normal day and each disaster day, providing a data basis for subsequent cluster analysis.

[0074] Preferably, in one embodiment of the present invention, the method for obtaining the similarity of precipitation characteristics of each disaster day with respect to the target normal day specifically includes:

[0075] The smaller the difference in precipitation intensity between the disaster day and the target normal day, the more similar the precipitation characteristics of the disaster day and the target normal day are. Therefore, the absolute value of the difference in precipitation intensity between each disaster day and the target normal day can be normalized by negative correlation to obtain the similarity of precipitation characteristics of each disaster day with respect to the target normal day.

[0076] In one embodiment of the present invention, the natural constant A negative exponential function with base Function form to achieve negative correlation normalization, where Represents the normalization function.

[0077] As an example, in one embodiment of the present invention, the expression for the similarity of precipitation characteristics of each disaster day with respect to the target normal day can be specifically, for example, as follows:

[0078]

[0079] in, Indicates the Similarity of precipitation characteristics of a disaster day to the target normal day; Indicates the Precipitation intensity on each disaster day; Indicates the precipitation intensity on a target normal day; Expressed as a natural constant An exponential function with base .

[0080] Similarly, it is also necessary to analyze the differences in soil severity between each disaster day and the target normal day. The obtained soil characteristic similarity can reflect the similarity of soil conditions between the target normal day and each disaster day, providing a data basis for subsequent cluster analysis.

[0081] Preferably, in one embodiment of the present invention, the method for obtaining the soil characteristic similarity of each disaster day with respect to the target normal day specifically includes:

[0082] The smaller the difference in soil severity between the disaster day and the target normal day, the more similar the soil conditions on the disaster day and the target normal day are. Therefore, the absolute value of the difference in soil severity between each disaster day and the target normal day can be normalized by negative correlation to obtain the similarity of soil characteristics of each disaster day with respect to the target normal day.

[0083] As an example, in one embodiment of the present invention, the expression for the similarity of soil characteristics of each disaster day with respect to the target normal day can be specifically, for example, as follows:

[0084]

[0085] in, Indicates the Similarity of soil characteristics of a disaster day to a target normal day; Indicates the The degree of soil degradation on each disaster day; Indicates the severity of the soil on a target normal day; Expressed as a natural constant An exponential function with base .

[0086] The precipitation feature similarity and soil feature similarity obtained above reflect the similarity of precipitation and soil features between each disaster day and the target day. Therefore, all disaster days can be further clustered according to the difference in precipitation feature similarity and soil feature similarity between each disaster day with respect to the target normal day, so that disaster days with close precipitation feature similarity and soil feature similarity can be divided into the same cluster. Subsequently, based on the difference in precipitation feature similarity and soil feature similarity of each disaster day in the cluster, the possibility of debris flow disaster on the target normal day can be accurately calculated and analyzed.

[0087] Preferably, in one embodiment of the present invention, the method for obtaining multiple clusters of target normal days specifically includes:

[0088] First, based on the similarity of precipitation characteristics and soil characteristics of each disaster day with respect to the target normal day, the Euclidean distance between any two disaster days is calculated as the distance measure between any two disaster days.

[0089] As an example, in one embodiment of the present invention, the distance measurement expression between any two disaster days can be specifically expressed as follows:

[0090]

[0091] in, Indicates the Disaster day and Distance measurement between disaster days; Indicates the Similarity of precipitation characteristics on disaster days; Indicates the Similarity of precipitation characteristics on disaster days; Indicates the Similarity of soil characteristics on disaster days; Indicates the The similarity of soil characteristics on disaster days.

[0092] Then, the K-means clustering algorithm is used, and based on the distance metric between any two disaster days, all disaster days are clustered to obtain multiple clusters of target normal days. In other embodiments of the present invention, other clustering algorithms such as DBSCAN clustering algorithms can also be used for clustering processing, which is not limited here.

[0093] After obtaining multiple clusters of target normal days, the degree of similarity between the precipitation status and soil status of each disaster day and the target normal day in the same cluster is relatively close, and the degree of similarity of different clusters is different. Clusters containing more disaster days can more accurately reflect the relationship between target normal days and disaster days. Therefore, the disaster probability of the target normal day can be obtained based on the similarity of precipitation characteristics and soil characteristics of each disaster day in each cluster with respect to the target normal day and the number of disaster days in each cluster. Subsequently, normal days with similar precipitation and soil environments to disaster days can be screened out based on the disaster probability, thereby improving the accuracy of the subsequent disaster prediction model.

[0094] Preferably, in one embodiment of the present invention, the method for obtaining the disaster probability on a target normal day specifically includes:

[0095] First, among all the clusters of target normal days, a reference cluster of target normal days is selected. Among them, the number of disaster days in the reference cluster is the largest. Since the number of disaster days in the reference cluster is the largest, it is the most representative, which improves the accuracy of the subsequent environmental similarity analysis between target normal days and disaster days.

[0096] The average value of the similarity of precipitation characteristics of all disaster days in the reference cluster of the target normal day with respect to the target normal day is taken as the first overall similarity of the target normal day. The larger the first overall similarity, the more similar the precipitation characteristics between the target normal day and each disaster day are. The average value of the similarity of soil characteristics of all disaster days in the reference cluster of the target normal day with respect to the target normal day is taken as the second overall similarity of the target normal day. The larger the second overall similarity, the more similar the soil characteristics between the target normal day and each disaster day are. The first overall similarity, the second overall similarity and the number of disaster days in the reference cluster of the target normal day are combined to obtain the disaster environment similarity of the target normal day. The larger the disaster environment similarity, the more similar the precipitation and soil characteristics of the target normal day are to the disaster day, which further indicates that the target normal day is more likely to have a debris flow disaster.

[0097] In an embodiment of the present invention, the sum or product value of the first overall similarity of the target normal day, the second overall similarity and the number of disaster days in the reference cluster of the target normal day can be used as the disaster environment similarity of the target normal day to achieve a combination of the three, which is not limited here.

[0098] As an example, in one embodiment of the present invention, the expression of the disaster environment similarity of the target normal day can be specifically, for example, as follows:

[0099]

[0100] in, Indicates the similarity of the disaster environment on a target normal day; represents the first overall similarity of the target normal day; represents the second overall similarity of the target normal day; Represents the number of disaster days in the reference cluster of target normal days.

[0101] Then, the greater the precipitation intensity and soil harshness of the target normal day are relative to the precipitation intensity and soil harshness of other normal days, the more likely a mudslide disaster is to occur on the target normal day. Therefore, the disaster risk coefficient of the target normal day can be obtained based on the difference between the precipitation intensity of the target normal day and the overall level of precipitation intensity of all normal days, as well as the difference between the soil harshness of the target normal day and the overall level of soil harshness of all normal days. The larger the disaster risk coefficient, the more likely a mudslide disaster is to occur on the target normal day.

[0102] Preferably, in one embodiment of the present invention, the method for obtaining the disaster risk coefficient of a target normal day specifically includes:

[0103] The precipitation intensity of the target normal day is taken as the numerator, the average precipitation intensity of all normal days is taken as the denominator, and the ratio is taken as the first risk coefficient of the target normal day. The larger the first risk coefficient, the greater the precipitation intensity of the target normal day is relative to the precipitation intensity of all normal days, which means that the target normal day is more likely to have a debris flow disaster risk.

[0104] The soil severity of the target normal day is taken as the numerator, the average value of the soil severity of all normal days is taken as the denominator, and the ratio is taken as the second risk coefficient of the target normal day. The larger the second risk coefficient, the greater the soil severity of the target normal day is relative to the soil severity of all normal days, which further indicates that the target normal day is more likely to have the risk of mudslide disasters.

[0105] Therefore, the first risk coefficient and the second risk coefficient of the target normal day can be integrated to obtain the disaster risk coefficient of the target normal day.

[0106] In an embodiment of the present invention, the sum or product of the first risk coefficient and the second risk coefficient of the target normal day may be used as the disaster risk coefficient of the target normal day to achieve a combination of the two, which is not limited here.

[0107] As an example, in one embodiment of the present invention, the expression of the disaster risk coefficient of a target normal day may be specifically, for example, as follows:

[0108]

[0109] in, represents the disaster risk coefficient of the target normal day; Indicates the precipitation intensity on a target normal day; It represents the average of precipitation intensity of all normal days; Indicates the first risk factor of the target normal day; Indicates the severity of the soil on a target normal day; It represents the average value of soil severity on all normal days; Indicates the second risk factor for a target normal day.

[0110] Then, the disaster environment similarity and disaster risk coefficient of the target normal day are integrated and normalized, and the calculation results are limited to range, thereby obtaining the disaster probability of the target normal day.

[0111] In an embodiment of the present invention, the combination of the disaster environment similarity and the disaster risk coefficient on a target normal day can be achieved by calculating the sum or product of the two, which is not limited here.

[0112] As an example, in one embodiment of the present invention, the expression for the disaster probability on a target normal day may be specifically, for example, as follows:

[0113]

[0114] in, Indicates the probability of disaster on a target normal day; Indicates the similarity of the disaster environment on a target normal day; represents the disaster risk coefficient of the target normal day; Represents the normalization function.

[0115] The same method as above can be used to obtain the disaster probability of each normal day. The greater the disaster probability, the more likely it is that a debris flow disaster will occur on a normal day, and the closer it is to the edge of the debris flow disaster risk. Therefore, based on the disaster probability, normal days with precipitation and soil environment similar to those on disaster days and extremely prone to debris flow disasters can be screened out from all normal days, namely similar normal days. Subsequently, based on various hydrogeological data of similar normal days and disaster days, a more accurate disaster prediction model can be constructed to improve the accuracy of debris flow disaster prediction.

[0116] Preferably, in one embodiment of the present invention, normal days with disaster possibilities greater than a preset possibility threshold are regarded as similar normal days, wherein the preset possibility threshold is set to 0.8. The specific value of the preset possibility threshold can also be set by the implementer according to the specific implementation scenario and is not limited here.

[0117] At this point, similar normal days have been screened out.

[0118] Step S4: Based on the precipitation, soil moisture content and soil infiltration rate of similar normal days and disaster days, a disaster prediction model is constructed, and the debris flow disaster of the current day is predicted.

[0119] Since debris flow disasters are very likely to occur on similar normal days, the hydrogeological data of similar normal days should also receive more attention to ensure the accuracy of debris flow disaster prediction. Therefore, based on the precipitation, soil moisture content and soil infiltration rate of similar normal days and disaster days, a disaster prediction model is constructed, and the debris flow disaster of the current day is predicted.

[0120] Preferably, in one embodiment of the present invention, the method for predicting debris flow disasters on the current day specifically includes:

[0121] First, in order to train the model at the same scale and improve the final model accuracy, it is necessary to standardize the precipitation, soil moisture content, and soil infiltration rate of each similar normal day and each disaster day, eliminate the influence of dimension, and obtain the standard precipitation, standard soil moisture content, and standard soil infiltration rate of each similar normal day and each disaster day. Among them, data standardization is a technical means well known to those skilled in the art and will not be elaborated here.

[0122] Then, any similar normal day or any disaster day is taken as the day to be tested, and the vector composed of the standard precipitation, standard soil moisture content and standard soil infiltration rate of the day to be tested is taken as the feature vector of the day to be tested. If the day to be tested is a similar normal day, the class label of the feature vector of the day to be tested is set to the value 0. If the day to be tested is a disaster day, the class label of the feature vector of the day to be tested is set to the value 1. The same method as above can be used to obtain the feature vectors and corresponding class labels of each similar normal day and each disaster day, and then the set composed of the feature vectors with class labels of all similar normal days and all disaster days can be used as the training set.

[0123] Finally, the data in the training set is input into the support vector machine for training, and the trained support vector machine is used as a disaster prediction model. Then, the current day's precipitation, soil moisture content and soil infiltration rate are input into the disaster prediction model, and the disaster prediction model outputs the debris flow disaster prediction result for the current day. Among them, the support vector machine is a technical means well known to technicians in this field and will not be elaborated here.

[0124] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0125] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A hydrological data prediction method based on data analysis, characterized in that: The method comprises: Obtain daily precipitation, soil moisture content, and soil infiltration rate for the area to be tested within a preset historical time period. The days corresponding to debris flows occurring within the preset historical time period are considered disaster days, and the remaining historical days are considered normal days. Obtaining daily precipitation intensity based on the daily precipitation and the precipitation of each day in a preset time domain; obtaining daily soil severity based on the daily soil moisture content, the soil infiltration rate, and the precipitation intensity; Taking any normal day as a target normal day, obtaining the similarity of precipitation characteristics of each disaster day with respect to the target normal day based on the difference in precipitation intensity between each disaster day and the target normal day; obtaining the similarity of soil characteristics of each disaster day with respect to the target normal day based on the difference in soil severity between each disaster day and the target normal day; clustering all disaster days based on the difference in precipitation characteristic similarity and soil characteristic similarity between each disaster day with respect to the target normal day, obtaining multiple clusters of target normal days; obtaining the disaster probability of the target normal day based on the precipitation characteristic similarity and soil characteristic similarity of each disaster day in each cluster with respect to the target normal day and the number of disaster days in each cluster; screening out similar normal days from all normal days based on the disaster probability; wherein, normal days with a disaster probability greater than a preset probability threshold are regarded as similar normal days; Based on the precipitation, soil moisture content, and soil infiltration rate of similar normal days and disaster days, a disaster prediction model is constructed, and a debris flow disaster of the current day is predicted; The disaster probability of obtaining a target normal day includes: Selecting a reference cluster of target normal days from among all the clusters of target normal days, wherein the number of disaster days in the reference cluster is the largest; The average of the precipitation feature similarities of all disaster days in the reference cluster of the target normal day with respect to the target normal day is used as the first overall similarity of the target normal day. The average of the soil feature similarities of all disaster days in the reference cluster of the target normal day with respect to the target normal day is used as the second overall similarity of the target normal day. The first overall similarity of the target normal day, the second overall similarity, and the number of disaster days in the reference cluster of the target normal day are integrated to obtain the disaster environment similarity of the target normal day. Obtaining a disaster risk coefficient for the target normal day according to a difference between the precipitation intensity on the target normal day and the overall level of the precipitation intensities on all normal days, and a difference between the soil severity on the target normal day and the overall level of the soil severity on all normal days; The disaster environment similarity and the disaster risk coefficient of the target normal day are integrated and normalized to obtain the disaster possibility of the target normal day.

2. The hydrological data prediction method based on data analysis according to claim 1, characterized in that: The method of obtaining the daily precipitation intensity includes: Take any day as the target day, take the precipitation on the target day as the numerator, take the sum of the precipitation on all days in the preset time domain of the target day as the denominator, and take the ratio as the precipitation ratio of the target day; The number of days with precipitation greater than 0 in the preset time domain of the target day is used as the numerator, all days in the preset time domain of the target day is used as the denominator, and the ratio is used as the proportion of precipitation days in the target day; Taking the average of the precipitation of all days in the preset time domain of the target day as the overall precipitation of the preset time domain of the target day, normalizing the difference between the precipitation of the target day and the overall precipitation to obtain a relative difference value of precipitation on the target day; The precipitation ratio of the target day, the ratio of the number of precipitation days and the relative difference value of precipitation are integrated and normalized to obtain the precipitation intensity of the target day.

3. The hydrological data prediction method based on data analysis according to claim 2, characterized in that: The soil severity obtained each day includes: The soil moisture content, the soil infiltration rate and the precipitation intensity of the target day are integrated and normalized to obtain the soil severity of the target day.

4. The hydrological data prediction method based on data analysis according to claim 1, characterized in that: Obtaining the similarity of precipitation characteristics of each disaster day with respect to a target normal day includes: The absolute value of the difference in precipitation intensity between each disaster day and the target normal day is subjected to negative correlation normalization processing to obtain the precipitation feature similarity of each disaster day with respect to the target normal day.

5. The hydrological data prediction method based on data analysis according to claim 1, characterized in that: Obtaining the soil characteristic similarity of each disaster day to the target normal day includes: The absolute value of the difference in soil severity between each disaster day and the target normal day is normalized by negative correlation to obtain the soil characteristic similarity of each disaster day with respect to the target normal day.

6. The hydrological data prediction method based on data analysis according to claim 1, characterized in that: The method of obtaining a plurality of clusters of target normal days includes: Based on the precipitation feature similarity and the soil feature similarity of each disaster day with respect to the target normal day, calculating the Euclidean distance between any two disaster days as a distance metric between any two disaster days; Using the K-means clustering algorithm and based on the distance metric between any two disaster days, all disaster days are clustered to obtain multiple clusters of target normal days.

7. The hydrological data prediction method based on data analysis according to claim 6, characterized in that: Obtaining the disaster risk coefficient of the target normal day includes: The precipitation intensity of the target normal day is used as the numerator, the average of the precipitation intensities of all normal days is used as the denominator, and the ratio is used as the first risk coefficient of the target normal day; The soil severity of the target normal day is used as the numerator, the average of the soil severity of all normal days is used as the denominator, and the ratio is used as the second risk coefficient of the target normal day; The first risk coefficient and the second risk coefficient of a target normal day are integrated to obtain a disaster risk coefficient of the target normal day.

8. The hydrological data prediction method based on data analysis according to claim 1, characterized in that: The prediction of the debris flow disaster on the current day includes: Standardizing the precipitation, soil moisture content, and soil infiltration rate of each similar normal day and each disaster day to obtain the standard precipitation, standard soil moisture content, and standard soil infiltration rate of each similar normal day and each disaster day; Any similar normal day or any disaster day is used as the day to be measured, and the vector consisting of the standard precipitation, the standard soil moisture content, and the standard soil infiltration rate of the day to be measured is used as the feature vector of the day to be measured. If the day to be measured is a similar normal day, the class label of the feature vector of the day to be measured is set to a value of 0; if the day to be measured is a disaster day, the class label of the feature vector of the day to be measured is set to a value of 1, and the set consisting of the feature vectors with the class labels of all similar normal days and all disaster days is used as the training set; Inputting the data in the training set into a support vector machine for training, and using the trained support vector machine as a disaster prediction model; The current day's precipitation, soil moisture content, and soil infiltration rate are input into the disaster prediction model, which then outputs the debris flow disaster prediction result for the current day.

Images