Drought and flood sudden change prediction method fusing soil moisture content and rainfall coupling model

Abstract

The invention provides a drought and flood sudden change prediction method fusing a soil moisture content and rainfall coupling model, and relates to the technical field of drought and flood sudden change. Comprising the steps that layered soil moisture content, high-frequency rainfall and auxiliary data are collected and preprocessed, and a soil moisture content-rainfall coupling coordination initial value is constructed and corrected; traversing drought and flood windows by using the standardized soil moisture content-rainfall coupling coordination index sequence, and determining an optimal window; carrying out nonlinear correction, judging a sudden turning event according to a corrected threshold value, and outputting a drought and flood sudden turning prediction result; and calculating a drought and flood sudden change duration prediction value Tint and a soil moisture content rainfall mutation index SPIef according to a drought and flood sudden change prediction result, a soil texture coefficient and the like, constructing a risk matrix, outputting an early warning level and a response suggestion in combination with the vulnerability of the disaster-bearing body, and outputting early warning information. According to the method, the optimal window is determined and optimized, drought and flood sudden turning is predicted, the scientificity and accuracy of prediction are guaranteed, and the practical application value is enhanced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of drought-flood rapid transition, and in particular to a drought-flood rapid transition prediction method fusing a soil moisture content and precipitation coupling model. BACKGROUND

[0002] Drought-flood rapid transition event is an extreme combination of two water cycle extreme processes, i.e. drought and flood. The stability of hydrological system is increasingly reduced due to the combined effects of climate change and human activities, leading to the increasing frequency and range of drought-flood rapid transition events in recent years, which has caused serious harm to production, life and ecological environment in many regions.

[0003] Traditional drought-flood prediction methods have a single data source, mostly relying on a few data sources such as ground rain gauges, without integrating weather radar estimated precipitation and satellite precipitation products, which are difficult to fully capture the spatial and temporal distribution and suddenness of precipitation. Moreover, simple processing methods such as mean value filling are often used for data missing, without considering the spatial and temporal correlation of hydrological data and soil texture differences, resulting in uneven data quality and affecting the subsequent prediction accuracy. In terms of coupling relationship construction, linear models are mostly used to describe the correlation between soil moisture content and precipitation, which cannot adapt to the nonlinear dynamic changes of slow decline of soil moisture content in drought period and rapid rise of soil moisture content in flood period, resulting in a large deviation in the description of coupling coordination degree. In the determination of rapid transition events, fixed windows are mostly used, without the process of selecting the optimal window according to the data characteristics, which is easy to misjudge short-term data fluctuations as drought-flood rapid transition. At the same time, traditional methods do not combine with the vulnerability of disaster-bearing bodies to carry out risk classification, nor do they provide targeted disaster prevention response suggestions, but only output simple results of whether the rapid transition occurs, which cannot effectively support actual disaster prevention and mitigation decisions, and the overall practical value is limited. SUMMARY

[0004] The present application provides a drought-flood rapid transition prediction method fusing a soil moisture content and precipitation coupling model, which solves the defect that the prior art lacks the process of selecting the optimal window according to the data characteristics, which is easy to misjudge short-term data fluctuations as drought-flood rapid transition.

[0005] In one aspect, the present application provides a drought-flood rapid transition prediction method fusing a soil moisture content and precipitation coupling model, comprising: S1: constructing a three-dimensional hydrological map of the target region, labeling the soil texture distribution and the location of historical drought-flood rapid transition events, dividing the region into P sub-regions to be predicted and recording the center coordinates of each sub-region. Collecting layered soil moisture content, high-frequency precipitation and auxiliary data, and outputting the original drought-flood data set of the sub-region.

[0006] S2: preprocessing the original drought-flood data set of the sub-region to obtain a standardized data set.

[0007] S3: Calculate the soil moisture content-rainfall coupling coordination initial value according to the standardized data set, and correct it to obtain a standardized soil moisture content-rainfall coupling coordination index sequence.

[0008] S4: Use the standardized soil moisture content-rainfall coupling coordination index sequence to traverse the drought and flood window to determine the optimal window. Nonlinear correction is made in combination with the array rainfall, vegetation and soil texture, the threshold value after correction is determined to determine the sudden change event, and the drought and flood sudden change prediction result is output.

[0009] S5: According to the drought and flood sudden change prediction result and the soil texture coefficient, a drought and flood sudden change duration prediction value T is calculated int and the soil moisture content-rainfall mutation index SPI ef , a risk matrix is constructed, a warning level and a response suggestion are output in combination with a disaster-bearing body vulnerability, and warning information is output.

[0010] According to the drought and flood sudden change prediction method of the fusion soil moisture content and rainfall coupling model provided by the application, in step S2, the preprocessing includes: S21: An outlier is identified by using the isolated forest algorithm.

[0011] S22: Short missing data is filled by using the correlation interpolation method according to the soil texture difference, and long missing data is filled by using the LSTM-ATTention model.

[0012] S23: The data is converted to the [-1, 1] interval by the Z-score standardization formula.

[0013] According to the drought and flood sudden change prediction method of the fusion soil moisture content and rainfall coupling model provided by the application, in step S3, the specific steps for obtaining the standardized soil moisture content-rainfall coupling coordination index sequence are: S31: The coupling coordination initial value is calculated according to the standardized data set.

[0014] S32: In the initial value, the power function and the piecewise function are input, the least square method is used to quantify the soil moisture content-rainfall dynamic relationship, and the quantized initial value is obtained.

[0015] S33: The standardized soil moisture content-rainfall coupling coordination index sequence is obtained by using the Gamma distribution fitting and the inverse normal transformation quantization of the initial value.

[0016] According to the drought and flood sudden change prediction method of the fusion soil moisture content and rainfall coupling model provided by the application, in step S31, the specific steps for constructing the soil moisture content-rainfall coupling coordination index are: S311: The weight values of the soil moisture content index and the rainfall index are determined by the analytic hierarchy process.

[0017] S312: A function expression of the coupling coordination relationship between soil moisture content and rainfall is constructed.

[0018] S313: input the standardized data set into the function expression, and obtain the coupling coordination initial value.

[0019] According to the drought-flood abrupt change prediction method of the coupling model of soil moisture content and precipitation provided in the application, in step S33, the specific steps of using the Gamma distribution fitting and inverse normal conversion to quantify the initial value are as follows: S331: classify and arrange the quantified initial value, and distinguish the soil moisture content quantified initial value and the precipitation quantified initial value.

[0020] S332: use the probability density function of the Gamma distribution to perform Gamma distribution fitting on the soil moisture content quantified initial value and the precipitation quantified initial value, and obtain a Gamma distribution model.

[0021] S333: perform inverse normal conversion on the soil moisture content quantified initial value and the precipitation quantified initial value according to the Gamma distribution model, and obtain normalized soil moisture content data and normalized precipitation data.

[0022] S334: construct a soil moisture content-precipitation coupling coordination index calculation model, input the normalized soil moisture content data and the normalized precipitation data into the index calculation model, and obtain a coupling coordination index.

[0023] S335: perform standardization processing on the coupling coordination index to obtain a standardized soil moisture content-precipitation coupling coordination index sequence.

[0024] According to the drought-flood abrupt change prediction method of the coupling model of soil moisture content and precipitation provided in the application, in step S4, the specific steps of outputting the determination result are as follows: S41: according to the standardized soil moisture content-precipitation coupling coordination index CCIstd sequence, associate the sub-regions and the time nodes to form a sub-region CCIstd value three-dimensional data table.

[0025] S42: according to the three-dimensional data table, set a candidate set of drought-flood window length ranges, extract the window units corresponding to each N value and calculate the change index, determine the optimal window length, output the optimal window length and the CCIstd change characteristic parameters of each sub-region.

[0026] S43: collect the array precipitation, vegetation, and soil texture data of the optimal window period of each sub-region, associate the CCIstd values in the window to construct a nonlinear correction model, calculate the corrected index CCIstd corr , and output the corrected index sequence of each sub-region.

[0027] S44: according to the location of the historical drought-flood abrupt change event, determine the drought threshold T dry according to the corrected index sequence of each sub-region by using the percentile method.and the flood threshold T wet , output the modified threshold suitable for all sub-regions.

[0028] S45: Compare CCIstd in the optimal window of each sub-region corr The sequence trend and the modified threshold, combined with the optimal window change characteristic parameter, determine the abrupt change type, and output the drought and flood abrupt change prediction result.

[0029] According to the drought and flood abrupt change prediction method provided by the coupling model of soil moisture content and precipitation, in step S42, the specific steps of outputting the optimal window length and CCIstd change characteristic parameter of each sub-region are: S421: According to the three-dimensional data table, set the drought and flood window length range, determine the traversal range of each sub-region, and output the window length candidate set of each sub-region.

[0030] S422: For each N value in the window length candidate set, extract the CCIstd value of the corresponding sub-region at the continuous N time nodes from the three-dimensional data table as a window unit, calculate the range and linear fitting slope change index, and output the window unit change index data set.

[0031] S423: Determine the optimal window length according to the window unit change index data set, and output the optimal window length and the corresponding CCIstd change characteristic parameter of each sub-region.

[0032] According to the drought and flood abrupt change prediction method provided by the coupling model of soil moisture content and precipitation, in step S423, the specific steps of determining the optimal window length are: Based on the CCIstd sequence in the window, calculate the drought and flood conversion coupling strength CSI, and the calculation formula is represented as:

[0033] In the formula, is the range of CCIstd in the window, and the absolute value of the change slope of CCIstd in the window.

[0034] For different candidate window lengths, calculate the CSI under each window length, and then compare it with the historical drought and flood abrupt change event list to count the matching rate.

[0035] Select the window length with the highest matching rate and capable of distinguishing non-abrupt change events as the optimal window length.

[0036] According to the drought and flood abrupt change prediction method provided by the coupling model of soil moisture content and precipitation, in step S43, the specific steps of outputting the modified index sequence of each sub-region are: The cumulative frequency R1 of the array precipitation in the calculation window, the single maximum intensity R2, the average value V of the vegetation coverage index NDVI in the extraction window, and the proportion S of the soil clay content in the sub-region are associated with the CCIstd value in the optimal window of the sub-region to construct a nonlinear correction model. The optimal window length and the CCIstd variation characteristic parameter of each sub-region are substituted into the nonlinear correction model to obtain the corrected normalized coupling coordination index CCIstd in the optimal window of each sub-region. corr The CCIstd sequence of each sub-region is outputted. corr The CCIstd sequence of each sub-region is outputted.

[0037] According to the drought-flood sudden change prediction method of the coupling model of soil moisture content and precipitation provided by the application, in step S5, the specific steps of outputting the early warning information are: S51: According to the drought-flood sudden change prediction result and the soil texture coefficient of the sub-region, the historical average duration of the same type of sudden change is associated to form a drought-flood sudden change duration prediction value T according to the sub-region. int The SPI ef The basic data set is calculated.

[0038] S52: According to the basic data set, T int And SPI ef , the core index data set is outputted.

[0039] S53: A matrix is constructed with T int As the vertical axis and SPI ef As the horizontal axis, the data is mapped to a preliminary risk level, and the preliminary risk level data set is outputted.

[0040] S54: Collect the vulnerability data of the disaster-bearing body, and correct according to the preliminary risk level to output the corrected risk level data set.

[0041] S55: According to the corrected risk level, the warning level is determined, the type of sudden change is combined to make suggestions, and the information is integrated to output a structured drought-flood sudden change early warning information report.

[0042] The drought-flood sudden change prediction method of the coupling model of soil moisture content and precipitation provided by the application, by calculating the soil moisture content-precipitation coupling coordination initial value, traversing the drought-flood window, determining the optimal window and optimizing, the drought-flood sudden change is predicted, and the beneficial effects are: By constructing the three-dimensional hydrological map of the target area, not only the distribution of soil texture and the location of the historical drought-flood sudden change events are clearly marked, but also the region is reasonably divided into multiple sub-regions to be predicted and the coordinates are recorded, so that the subsequent analysis can focus on smaller and relatively consistent units, improve the accuracy of prediction, avoid errors caused by general analysis of large areas, and help to understand the characteristics of drought-flood sudden change in different sub-regions. The collection of layered soil moisture, high-frequency precipitation and other auxiliary data such as air temperature, humidity and wind speed comprehensively considers many factors related to drought-flood sudden change, and multiple sources of data complement and verify each other, which can more comprehensively reflect the actual water and heat conditions and trends in the region, and lay a solid foundation for accurate prediction.

[0043] The weights of soil moisture and precipitation indicators are determined by the analytic hierarchy process, and combined with the constructed coupling coordination function expression, the relative importance and interaction of the two in the process of drought-flood sudden change can be scientifically measured, so that the constructed soil moisture-precipitation coupling coordination index is more consistent with the actual physical process, and provides strong support for accurate judgment of drought-flood sudden change. By fusing power function and piecewise function to quantify the dynamic relationship between soil moisture and precipitation, and through a series of operations such as Gamma distribution fitting and inverse normal transformation, the index is finely processed and corrected, so that the standardized soil moisture-precipitation coupling coordination index obtained finally can more accurately reflect the complex coupling coordination between soil moisture and precipitation, and enhance the characterization ability of drought-flood sudden change phenomenon.

[0044] By traversing the drought and flood window, according to the set drought and flood state change core index and the calculation of drought and flood conversion coupling strength CSI, and compared with the historical drought and flood sudden change event to determine the matching rate, the optimal window is selected, which can accurately capture the period most likely to occur drought and flood sudden change in time scale, avoid misjudgment or missed judgment caused by improper window selection, and improve the timeliness and accuracy of drought and flood sudden change prediction. Combined with factors such as array precipitation, vegetation, soil texture, etc. Nonlinear correction, and using the percentile method to determine the drought threshold and flood threshold, fully considering the effect of various actual factors on the determination of drought and flood sudden change, the determination of threshold is more in line with the actual situation of the region, and then the type of drought and flood sudden change in each sub region is more accurately judged, and the reliability of the prediction result is improved. Based on the drought and flood sudden change prediction result, soil texture coefficient, etc. Calculate the drought and flood sudden change duration prediction value Tint and the soil moisture content precipitation mutation index SPIef, construct the risk matrix, and comprehensively evaluate the drought and flood sudden change risk level from the time duration and CCIstd mutation degree, so that the risk assessment result is more comprehensive and objective, and can more accurately reflect the difference in drought and flood sudden change risk faced by different sub regions. Considering the vulnerability of the disaster bearing body, the risk level is corrected, and then the warning level is determined according to the corrected risk level, and specific and targeted response suggestions are put forward according to the sudden change type, so that the warning information can not only reflect the situation of drought and flood sudden change itself, but also can be combined with the actual disaster bearing capacity of the region, and provide scientific for relevant departments to formulate accurate and effective disaster prevention and mitigation measures.

[0045] The present application improves the reliability of data basis, reduces data noise and deviation through multi-source data fusion, targeted abnormal value identification and missing value filling, standardization processing, provides high quality and high consistency basic data for drought and flood sudden change prediction, avoids the influence of data problems on prediction accuracy, improves the accuracy of sudden change prediction, quantifies the coupling relationship between soil moisture content and precipitation by combining dynamic function and probability distribution, and then selects the optimal window and nonlinear correction of multiple factors, accurately captures the nonlinear and sudden characteristics of drought and flood sudden change, effectively reduces the problems of misjudgment of short-term fluctuations and missed judgment of rapid sudden change. Realize spatial accurate prediction, divide the sub region matched with hydrological characteristics, customize the coupling modeling, window screening and other parameters for different sub regions, break through the limitation of traditional global general prediction, output sub regional prediction result, and adapt to the differentiated disaster prevention needs of different regions. BRIEF DESCRIPTION OF DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the present application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0047] Fig. 1is a flowchart of a drought-flood sudden change prediction method provided by an embodiment of the present application, which is a drought-flood sudden change prediction method based on a coupling model of soil moisture and precipitation; Fig. 2 is a flowchart of outputting a drought-flood sudden change prediction result. DETAILED DESCRIPTION

[0048] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described below in conjunction with the accompanying drawings in the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort belong to the scope of protection of the present application.

[0049] The drought-flood sudden change prediction method based on a coupling model of soil moisture and precipitation will be described below in conjunction with Figs. 1-2 the accompanying drawings in the present application.

[0050] As shown in the accompanying drawings, Figs. 1-2 the drought-flood sudden change prediction method based on a coupling model of soil moisture and precipitation provided by an embodiment of the present application comprises the following steps. S1: Construct a three-dimensional hydrological map of a target region, label soil texture distribution and historical drought-flood sudden change event positions, divide the region into P sub-regions to be predicted and record the center coordinates of each sub-region. Collect layered soil moisture, high-frequency precipitation and auxiliary data, and output the original drought-flood data set of the sub-region.

[0051] Determine the administrative and geographical boundaries of the target region, collect 1:50,000 DEM data, soil type distribution map, historical drought-flood sudden change event records in the past 30 years, and hydrological site distribution data, generate a basic data set, use DEM data to generate a three-dimensional terrain model of the target region by ArcGIS or Surfer, superimpose vector layers of hydrological elements such as watershed boundaries, river networks and reservoirs, set visualization parameters such as elevation and slope, generate a three-dimensional hydrological base map, and output a base map file containing spatial coordinates.

[0052] Vectorize the soil type distribution map and label it at the corresponding position according to the texture type, supplement the event occurrence time and impact range attributes, and output the labeled three-dimensional hydrological map.

[0053] Based on the consistency of soil texture and watershed unit of the three-dimensional hydrological map, divide the region into N sub-regions of equal area or equal hydrological unit by using GIS tools, calculate the longitude and latitude coordinates of the geometric center of each sub-region by using the tool, and output the sub-region division vector map and the comparison table.

[0054] Collect layered soil moisture, high-frequency precipitation, and auxiliary data synchronously. Summarize the data according to the sub-region number and arrange them into the original drought-flood data set of the sub-region.

[0055] Soil moisture data: The hierarchical Internet of Things sensor is used to capture the transition characteristics of slow decline in dry period and rapid rise in flood period.

[0056] Precipitation data: The ground rain gauge, weather radar estimated precipitation, and satellite precipitation products are integrated to generate 1 km x 1 km grid hourly precipitation intensity data through Kriging interpolation, which meets the needs of capturing the suddenness of short-period transition.

[0057] Coupling auxiliary data: including 2m air temperature, relative humidity, wind speed, soil texture, soil tightness, and crop root depth.

[0058] S2: Preprocess the original drought and flood data set of sub-regions to obtain a standardized data set.

[0059] S21: Use the Isolation Forest algorithm to identify outliers. Due to the spatio-temporal correlation of hydrological data, a dedicated preprocessing strategy is used to avoid the loss of key transition signals.

[0060] S22: Short missing data is filled according to soil texture differences using correlation interpolation method, and long missing data is filled using LSTM-ATTention model. Short time missing data is filled using precipitation-moisture correlation interpolation, such as calculating the moisture change rate according to the same period precipitation intensity and soil texture. Long time missing data is filled using LSTM time series model, inputting previous moisture, precipitation, and evapotranspiration data to generate filling values.

[0061] S23: Convert the data to the [-1, 1] interval through the Z-score standardization formula.

[0062] Min-Max standardization is used for all data to eliminate dimension differences, and the formula is:

[0063] In the formula, x is the original data, xmin and xmax are the historical extreme values of the data, and xnorm is the standardized data.

[0064] S3: According to the standardized data set, construct the soil moisture-precipitation coupling coordination index, and modify it to obtain the standardized soil moisture-precipitation coupling coordination index sequence.

[0065] S31: According to the standardized data set, construct the soil moisture-precipitation coupling coordination index.

[0066] S311: Determine the weight values of soil moisture index and precipitation index through AHP.

[0067] S312: Construct the function expression of the coupling coordination relationship between soil moisture and precipitation.

[0068] S313: input the standardized dataset into the function expression to obtain the initial value of the coupling coordination degree.

[0069] S32: fuse the power function and the segmented function to quantify the dynamic relationship between soil moisture and precipitation.

[0070] S33: use the Gamma distribution fitting and inverse normal transformation to obtain the standardized soil moisture-precipitation coupling coordination index.

[0071] S331: classify and arrange the quantified initial values to distinguish the quantified initial values directly related to soil moisture (denoted as X 初 ) and the quantified initial values directly related to precipitation (denoted as Y 初 ), and ensure that the two types of initial values correspond to the observation time or observation site one-to-one to form a paired dataset {(X 初i , Y 初 )} (i=1, 2, …, n, n is the sample number).

[0072] S332: based on the paired dataset {(X 初i , Y 初i )}, the soil moisture quantified initial value X 初i and the precipitation quantified initial value Y 初i are fitted with Gamma distribution respectively. The probability density function of Gamma distribution is expressed as:

[0073] In the formula, t≥0, α is the shape parameter, β is the scale parameter, and Γ(α) is the gamma function. The likelihood function is constructed for the soil moisture quantified initial value, which is expressed as:

[0074] After taking the logarithm, the maximum likelihood estimation method is used to determine the corresponding optimal parameters α X and β X , and the Gamma distribution model f X (t) of X 初i is obtained. Similarly, the optimal parameters α Y and β Y are calculated for the precipitation quantified initial value, and the Gamma distribution model f Y (t) of Y 初i is obtained, and the Gamma distribution fitting of the two types of quantified initial values is completed.

[0075] S333: according to the fitted Gamma distribution models f X (t) and f Y(t), respectively, the initial value of the soil moisture content and the initial value of the precipitation are inversely normally converted, and the Box-Cox transformation formula is adopted: When λ≠0, .

[0076] When λ=0, .

[0077] For Y 初i , combined with the characteristics of the Gamma distribution model f X (t), the optimal λ X that makes the converted data normally optimal is determined by trial and error method combined with Shapiro-Wilk normality test, and the normalized soil moisture content data is obtained. For Y 初i , the same reason is used to determine λ Y , and the normalized precipitation data is obtained, and the inverse normal conversion of the two types of quantitative initial values is realized.

[0078]

[0079] S335: The initial value of the coupling coordination index is standardized, and the influence of the dimension is eliminated by using the normalization method, and the standard of each sample is calculated, and finally the standardized soil moisture content-precipitation coupling coordination index is obtained.

[0080] S4: Use the standardized soil moisture content-precipitation coupling coordination index sequence to traverse the drought and flood window, and determine the optimal window. Combined with the nonlinear correction of the array precipitation, vegetation and soil texture, the sudden change event is determined according to the corrected threshold value, and the determination result is output. The window is selected as a continuous N time node, and the soil moisture content-precipitation coupling coordination index (CCIstd) in this time period is regarded as a whole, and the change trend of the drought and flood state in this time period is analyzed.

[0081] S41: Organize the standardized soil moisture content-precipitation coupling coordination index sequence (CCIstd sequence), and clearly define the time nodes corresponding to the sequence and the CCIstd value of each time node, and simultaneously associate the N sub-regions to be predicted divided in S1, to form a three-dimensional data table of sub-regions-time nodes-CCIstd values.

[0082] S42: According to the three-dimensional data table, set the candidate set of the length range of the drought and flood window, extract the window unit corresponding to each N value and calculate the change index, determine the optimal window length, and output the optimal window length of each sub-region and the CCIstd change characteristic parameter.

[0083] S421: Based on the above-mentioned three-dimensional data table, set the length range of the drought and flood window, the selectable value of N is 3-15 consecutive time nodes, which needs to be determined according to the data acquisition frequency and the typical time scale of the drought and flood rapid transition, and the window length does not exceed the total time node number of the CCIstd sequence, the window traversal range of each sub-region to be predicted is determined, and it is ensured that all possible continuous time periods in the sequence are covered in the traversal process, and the window length candidate set of each sub-region is output.

[0084] S422: For each N value in the window length candidate set of each sub-region, extract the CCIstd values of all consecutive N time nodes of the sub-region from the three-dimensional data table as a window unit, and calculate the drought and flood state change core index in each window unit. The drought and flood state change core index includes the range of CCIstd in the window, the difference between the maximum value and the minimum value, reflecting the drought and flood state change amplitude, the linear fitting slope reflecting the change trend direction of CCIstd, the positive slope is the development of the flood state, the negative slope is the development of the drought state, and the number of mutation points is detected by sliding t test whether CCIstd has a significant jump, reflecting whether there is a rapid state transition sign, and the window unit change index data set corresponding to different N values of each sub-region is output.

[0085] S423: Determine the optimal window length according to the window unit change index data set, and output the optimal window length of each sub-region and the corresponding CCIstd change characteristic parameter.

[0086] The specific steps for determining the optimal window are as follows: Based on the CCIstd sequence in the window, the drought and flood transition coupling strength CSI is calculated, and the calculation formula is represented as:

[0087] In the formula, is the range of CCIstd in the window, reflecting the amplitude of the drought and flood transition, the larger the difference, the greater the span from drought to flood / flood to drought, the absolute value of the change slope of CCIstd in the window, reflecting the speed of the drought and flood transition, the larger the slope, the faster the transition, the larger the slope, the faster the transition. The larger the final CSI value, the more significant the drought and flood rapid transition characteristics in the window.

[0088] For different candidate window lengths, calculate the CSI under each window length, and compare it with the historical drought and flood sudden change event list to count the matching rate. The matching rate is the proportion of the time when the peak value of the CSI in the window coincides with the occurrence time of the historical sudden change event.

[0089] Select the window length with the highest matching rate and capable of distinguishing non-sudden change events as the optimal window. In specific embodiments, if the window length is 3 days and the matching rate is 60%, it means that a large number of non-sudden change short-term fluctuations are included. If the window length is 7 days: the matching rate is 88%, which means that the CSI peak value is highly coincident with the historical sudden change event and can exclude short-term fluctuations. If the window length is 10 days: the matching rate is 75%, which means that part of the rapid sudden change events are diluted by the window, resulting in missed judgment. At this time, 7 days is the optimal window - it can accurately capture historical sudden change events and avoid misjudgment and missed judgment.

[0090] S43: Collect the data of the array precipitation, vegetation, and soil texture in the optimal window period of each sub-region, correlate the CCIstd value in the window to construct a non-linear correction model, calculate the corrected index, and output the CCIstd of each sub-region corr sequence.

[0091] Collect the auxiliary data of each sub-region in the time period corresponding to the optimal window - array precipitation data, calculate the cumulative frequency and single maximum intensity of the array precipitation in the window, denoted as R1, R2. Extract the average value of the vegetation coverage index NDVI in the window, denoted as vegetation data V, and obtain the proportion of soil clay content in the sub-region, denoted as soil texture data S. Correlate these data with the CCIstd value in the optimal window of the sub-region to construct a non-linear correction model, which can be expressed as:

[0092] In the formula, a, b, c, d, and e are correction coefficients fitted by historical drought and flood sudden change sample data. For example, the greater the array precipitation intensity, the higher the values of a and b, which can enhance the response of CCIstd to flood state. The higher the clay content, the higher the value of d, which can increase the sensitivity of CCIstd to changes in soil moisture.

[0093] Substitute the data to calculate the corrected normalized coupling coordination index CCIstd in the optimal window of each sub-region corr sequence, and output the CCIstd corr sequence of each sub-region.

[0094] S44: According to the location of the historical drought and flood sudden change event, use the above CCIstd corr value to determine the drought threshold T dry and the flood threshold T wet by the percentile method, and output the corrected threshold applicable to all sub-regions.

[0095] The corrected threshold was determined using the percentile method: CCIstd was statistically analyzed when historical drought-to-flood events occurred. corr The 90th percentile is used as the flood threshold T wet When historical flood-to-drought events occur, CCIstd corr The 10th percentile is used as the drought threshold T dry The output T applies to all sub-regions. dry and T wet .

[0096] S45: Compare the optimal CCIstd within each sub-region's window. corr The sequence trend and the corrected threshold are combined with the optimal window change characteristic parameters to determine the type of abrupt change, and the drought-flood abrupt change prediction results are output, including the sub-region number, time period and determination basis.

[0097] For each sub-region, compare the CCIstd values ​​within its optimal window. corr The trend of sequence change and the corrected threshold. If the sequence changes from below T... dry The range rose rapidly to above T wet If the absolute value of the slope is greater than or equal to the slope benchmark value in the optimal window change feature parameters, then it is predicted that the sub-region will experience a rapid shift from drought to flood within the time period corresponding to the optimal window. If the sequence starts above T... wet The range dropped rapidly to below T dry If the absolute value of the slope is greater than or equal to the baseline slope value, then a rapid shift from flood to drought is predicted. If the sequence remains at T... dry With T wet If the fluctuation or change range does not reach the benchmark value, then there is no risk of a sudden shift from drought to flood. The final output includes the drought-flood shift prediction results, which include the sub-region number, the optimal window period, the type of sudden shift, and the judgment criteria.

[0098] S5: Calculate the predicted duration T of the drought-flood transition based on the drought-flood transition prediction results and soil texture coefficient, etc. int Soil Moisture-Rainfall Abrupt Change Index (SPI) ef A risk matrix is ​​constructed, and early warning levels and response recommendations are output based on the vulnerability of disaster-bearing entities, thus providing early warning information.

[0099] S51: Risk level coefficients in the prediction results and judgment criteria for sudden shifts between drought and flood, and soil texture coefficients of each sub-region are extracted. The duration records of sudden shifts between drought and flood in the target area over the past 10 years are also linked. These data are aligned one by one according to the sub-region number to form the basic dataset for Tint and SPIef calculations. This dataset must ensure that there is no missing information for each sub-region.

[0100] S52: Calculate Tint (drought-flood abrupt transition duration prediction value) and SPIef (soil moisture precipitation mutation index) based on the basic data set, and the calculation formula of Tint is: Tint=history average duration of the same type of abrupt transition×soil texture coefficient.

[0101] The calculation formula of SPIef is:

[0102] In the formula, k is the absolute value of the linear fitting slope, is the difference between the maximum and minimum values of CCIstd in the window, and ω is the abrupt transition type weight.

[0103] In a specific embodiment, the ΔCCIstd of the optimal window of a sub-region is 0.7, |k|=0.2 / day, and the drought-flood transition is predicted, then SPIef=0.7×0.2×1.3=0.182. The Tint calculation results and SPIef calculation results of each sub-region are integrated according to the number, and the core index data set is output.

[0104] S53: Construct a matrix with T int as the vertical axis and SPI ef as the horizontal axis, map the data to the preliminary risk level, and output the preliminary risk level data set.

[0105] The vertical axis Tint is divided into three intervals according to the disaster duration impact threshold, short-term risk (Tint≤3 days, short duration, limited impact), medium-term risk (3 days

[0106] The horizontal axis SPIef is divided into three intervals according to the CCIstd mutation intensity threshold, low intensity (SPIef≤0.05, CCIstd slowly fluctuates, no obvious disaster risk in abrupt transition), medium intensity (0.05

[0107] S54: Collect the vulnerability data of disaster-affected bodies in each sub-region, which includes three types of core data: first, population density data, obtained through target regional statistical yearbook or remote sensing inversion, divided into high-density, medium-density and low-density areas according to the number of people per square kilometer. Second, main crop type data, obtained through agricultural department planting planning map, divided into flood-sensitive crops, drought-sensitive crops and moderately sensitive crops. Third, infrastructure data, obtained through agricultural department data, focusing on recording whether there are low-lying areas prone to flooding and irrigation facility coverage. Based on these data, the vulnerability level division standard is set: high vulnerability area needs to meet high population density + flood-sensitive / drought-sensitive crops + existence of low-lying area prone to flooding / irrigation coverage < 30%. Medium vulnerability area meets medium population density + moderately sensitive crops + no low-lying area prone to flooding / irrigation coverage 30%-80%. Low vulnerability area meets low population density + moderately sensitive crops + no low-lying area prone to flooding / irrigation coverage > 80%. At the same time, the risk level correction rule is formulated: high vulnerability area will increase the preliminary risk level output in the third step by 1 level. Low vulnerability area will reduce the preliminary risk level by 1 level. Medium vulnerability area keeps the preliminary risk level unchanged. Match the vulnerability level of each sub-region with the preliminary risk level, apply the correction rule, output the corrected risk level data set, and ensure that the risk level is more in line with the actual disaster-bearing capacity of the region.

[0108] S55: According to the corrected risk level, determine the warning level, combine the sudden change type to make suggestions, integrate information to output structured drought and flood sudden change warning information report. If it is drought to flood, the suggestions focus on preventing internal flooding, protecting drainage, dredging the drainage pipe network of the main and secondary roads in the jurisdiction, relocating residents in low-lying areas to temporary resettlement sites, suspending field irrigation and cleaning farmland drainage ditches. If it is flood to drought, focus on preventing drought and protecting water supply, start emergency water reserves, prioritize irrigation of wheat and other drought-sensitive crops during the critical growth period, and restrict high-water industrial water use. If there is no sudden change risk, it is recommended to maintain daily soil moisture monitoring and precipitation warning. Integrated into structured drought and flood sudden change warning information report.

[0109] In summary, the embodiment provides a drought and flood sudden change prediction method that integrates soil moisture and precipitation coupling model, calculates the initial value of soil moisture and precipitation coupling coordination, traverses the drought and flood window, determines the optimal window and optimizes it, and predicts the drought and flood sudden change, which has the beneficial effects of: The application improves data base reliability, reduces data noise and deviation through multi-source data fusion, targeted abnormal value identification and missing value filling, standardization processing, provides high-quality and high-consistency basic data for drought and flood sudden change prediction, avoids the influence of data problems on prediction accuracy, improves the accuracy of sudden change prediction, quantifies the coupling relationship between soil moisture and precipitation through the combination of dynamic function and probability distribution, and then screens the optimal window and corrects the non-linear factors, accurately captures the non-linear and sudden characteristics of drought and flood sudden change, effectively reduces the problems of misjudgment of short-term fluctuations and missed rapid sudden change. Realize spatial accurate prediction, divide the sub-regions matched with hydrological characteristics, customize the coupling modeling, window screening and other parameters for different sub-regions, break the limitations of traditional global general prediction, output sub-regional prediction results, and adapt to the differentiated disaster prevention needs of different regions.

[0110] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and necessary general hardware platforms, and of course, can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes a plurality of instructions for making a computer device (which can be a personal computer, server, or network device, etc.) execute the methods of each embodiment or some parts of the embodiment.

[0111] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application, and not to limit it. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some technical features. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for predicting rapid shifts between drought and flood by integrating a coupled model of soil moisture and precipitation, characterized in that, include: S1: Construct a three-dimensional hydrological map of the target area, mark the distribution of soil texture and the location of historical drought-flood transition events, divide the area into P sub-regions to be predicted and record the center coordinates of each sub-region; collect stratified soil moisture, high-frequency precipitation and auxiliary data, and output the original drought and flood datasets of the sub-regions. S2: Preprocess the original drought and flood dataset of the sub-region to obtain a standardized dataset; S3: Calculate and correct the initial value of soil moisture-precipitation coupling coordination based on the standardized dataset to obtain the standardized soil moisture-precipitation coupling coordination index sequence; S4: Using the standardized soil moisture-precipitation coupling coordination index sequence, the drought and flood windows are traversed to determine the optimal window; nonlinear corrections are made by combining intermittent precipitation, vegetation, and soil texture, and abrupt change events are determined according to the corrected threshold, and the drought and flood abrupt change prediction results are output. S5: Calculate the predicted duration T of the drought-flood transition based on the drought-flood transition prediction results and soil texture coefficient. int Soil Moisture-Rainfall Abrupt Change Index (SPI) ef A risk matrix is ​​constructed, and early warning levels and response recommendations are output based on the vulnerability of disaster-bearing entities, thus providing early warning information.

2. The method for predicting rapid shifts between drought and flood based on a coupled model of soil moisture and precipitation as described in claim 1, characterized in that, In step S2, the preprocessing includes: S21: Use the isolated forest algorithm to identify outliers; S22: Short missing data are filled using correlation interpolation based on soil texture differences, and long missing data are filled using the LSTM-ATTention model. S23: Transform the data to the [-1,1] interval using the Z-score normalization formula.

3. The method for predicting rapid shifts between drought and flood based on a coupled model of soil moisture and precipitation as described in claim 1, characterized in that, In step S3, the specific steps for obtaining the standardized soil moisture-precipitation coupling coordination index sequence are as follows: S31: Calculate the initial values ​​for coupling coordination based on the standardized dataset; S32: Input the power function and piecewise function in the initial value, and use the least squares method to quantify the dynamic relationship between soil moisture and precipitation to obtain the quantified initial value; S33: Standardize the soil moisture-precipitation coupled coordination index sequence by fitting the initial values ​​with Gamma distribution and inverse normal transformation.

4. The method for predicting rapid shifts between drought and flood based on a coupled model of soil moisture and precipitation as described in claim 3, is characterized in that... In step S31, the specific steps for constructing the soil moisture-precipitation coupling coordination index are as follows: S311: Determine the corresponding weight values ​​of soil moisture index and precipitation index using the analytic hierarchy process (AHP); S312: A functional expression for constructing the coupled and coordinated relationship between soil moisture and precipitation; S313: Input the standardized dataset into the function expression to obtain the initial values ​​for coupling coordination.

5. The method for predicting rapid shifts between drought and flood based on a coupled model of soil moisture and precipitation as described in claim 3, characterized in that, In step S33, the specific steps for fitting the initial value using the Gamma distribution and quantizing it using the inverse normal transformation are as follows: S331: Classify and organize the initial quantitative values, distinguishing between the initial quantitative values ​​related to soil moisture and the initial quantitative values ​​related to precipitation; S332: The probability density function of the Gamma distribution is used to fit the initial value of soil moisture quantification and the initial value of precipitation quantification with the Gamma distribution to obtain the Gamma distribution model; S333: Based on the Gamma distribution model, perform an inverse normal transformation on the initial values ​​of soil moisture quantification and precipitation quantification to obtain normalized soil moisture data and normalized precipitation data; S334: Construct a calculation model for the soil moisture-precipitation coupling coordination index. Input normalized soil moisture data and normalized precipitation data into the index calculation model to obtain the coupling coordination index. S335: The coupling coordination index is standardized to obtain a standardized soil moisture-precipitation coupling coordination index sequence.

6. The method for predicting rapid shifts between drought and flood based on a coupled model of soil moisture and precipitation as described in claim 1, characterized in that, In step S4, the specific steps for outputting the drought-flood shift prediction results are as follows: S41: Based on the standardized soil moisture-precipitation coupling coordination index CCIstd sequence, associate sub-regions with time nodes to form a three-dimensional data table of CCIstd values ​​for sub-regions; S42: Based on the three-dimensional data table, set a candidate set for the drought and flood window length N range, extract the window units corresponding to each N value and calculate the change index, determine the optimal window length, and output the optimal window length and CCIstd change characteristic parameters of each sub-region. S43: Collect data on intermittent precipitation, vegetation, and soil texture for the optimal window period in each sub-region, construct a nonlinear correction model by correlating the CCIstd values ​​within that window, and calculate the corrected exponent CCIstd. corr Output the corrected exponential sequence for each sub-region; S44: Based on the locations of historical drought-flood transition events, determine the drought threshold T using the percentile method based on the corrected exponential sequences of each sub-region. dry and flood threshold T wet The output is a corrected threshold applicable to all sub-regions; S45: Compare the optimal CCIstd within each sub-region's window. corr The sequence trend and the corrected threshold are combined with the optimal window change feature parameters to determine the type of abrupt change, and the prediction results of abrupt changes from drought to flood are output.

7. The method for predicting rapid shifts between drought and flood based on a coupled model of soil moisture and precipitation as described in claim 6, characterized in that, In step S42, the specific steps for outputting the optimal window length and CCIstd change characteristic parameters for each sub-region are as follows: S421: Based on the three-dimensional data table, set the drought and flood window length range, clarify the traversal range of each sub-region, and output the candidate set of window lengths for each sub-region; S422: For each N value in the candidate set of window length, extract the CCIstd values ​​of the corresponding sub-region for N consecutive time nodes from the three-dimensional data table as window units, calculate the range and linear fitting slope change index, and output the window unit change index dataset. S423: Determine the optimal window length based on the window unit change index dataset, and output the optimal window length of each sub-region and the corresponding CCIstd change feature parameters.

8. The method for predicting rapid shifts between drought and flood based on a coupled model of soil moisture and precipitation as described in claim 6, characterized in that, In step S423, the specific steps for determining the optimal window length are as follows: Based on the CCIstd sequence within the window, the drought-flood transition coupling strength (CSI) is calculated. For different candidate window lengths, calculate the CSI for each window length, and then compare it with the historical list of sudden drought-flood events to calculate the matching rate. The optimal window length is the one with the highest matching rate and the ability to distinguish non-abrupt events.

9. The method for predicting rapid shifts between drought and flood based on a coupled model of soil moisture and precipitation as described in claim 6, characterized in that, In step S43, the specific steps for outputting the corrected exponential sequence of each sub-region are as follows: Calculate the cumulative frequency R1 and the maximum intensity of a single shower within the window, extract the mean NDVI value V of the vegetation cover index within the window, obtain the proportion of soil clay content S in the sub-region, and correlate these data with the CCIstd value in the optimal window of the sub-region to construct a nonlinear correction model. Substituting the optimal window length and CCIstd variation characteristic parameters of each sub-region into the nonlinear correction model, the corrected standardized coupling coordination index CCIstd within the optimal window of each sub-region is calculated. corr The sequence outputs the CCIstd for each sub-region. corr sequence.

10. The method for predicting rapid shifts between drought and flood based on a coupled model of soil moisture and precipitation as described in claim 1, characterized in that, In step S5, the specific steps for outputting the warning information are as follows: S51: Based on the drought-flood transition prediction results and the soil texture coefficient of the sub-region, and by associating the average duration of similar historical transitions, a predicted value T for the duration of the drought-flood transition is generated by aligning the sub-regions. int Soil Moisture-Rainfall Abrupt Change Index (SPI) ef Compute the underlying dataset; S52: Calculate T based on the aforementioned basic dataset. int and SPI ef Output the core indicator dataset; S53: T int For the vertical axis, SPI ef Construct a matrix for the horizontal axis, map the data to determine the initial risk level, and output the initial risk level dataset; S54: Collect vulnerability data of disaster-bearing bodies, correct them according to the preliminary risk level correction, and output the corrected risk level dataset; S55: Determine the early warning level based on the revised risk level, and output a structured drought and flood emergency warning information report based on the type of emergency shift.

Images