Drought and flood sudden change prediction method and system fusing artificial intelligence and physical mechanism, and storage medium

Abstract

The invention discloses a drought and flood sudden change prediction method and system fusing artificial intelligence and a physical mechanism, and a storage medium. The method comprises the steps of collecting multi-source data in a selected drought and flood sudden change research area; key factors influencing land water reserves in each grid point in the research area are optimized; constructing and calibrating a time convolutional network deep learning model; using the long-series key factor set to drive the deep learning model, and reconstructing a long-series land water reserve inversion data set; extracting the drought and flood sudden change events and atmospheric circulation characteristics in the drought and flood sudden change events, and constructing an atmospheric circulation-drought and flood sudden change intensity pairing series; deducing a nonlinear scale relation between drought and flood sharp turning intensity and atmospheric circulation characteristics; and predicting the drought and flood sudden turning intensity and risk of each grid point in the future period. The method provides a new perspective for drought and flood sudden change prediction, has important scientific significance for disaster prevention and reduction, and provides a theoretical and technical basis for evaluating the environment and disaster effect of earth system evolution.

Description

Technical Field

[0001] The present application relates to the technical field of climate prediction, and in particular to a method, system and storage medium for predicting sudden transitions from drought to flood that integrate artificial intelligence and physical mechanisms. Background Art

[0002] Global climate change has changed the energy balance and water cycle of the land-atmosphere system. Extreme climate disasters such as heat waves, droughts, and floods have occurred frequently, posing huge challenges to the sustainable development of the social and economic system and the ecological environment. my country is one of the regions most severely affected by floods and droughts. The rate of climate warming is much higher than the global average. By the end of this century, the temperature may rise by 4°C, seriously threatening my country's flood control safety, water supply security, food security, energy security, and ecological and environmental security. A deep understanding of the socioeconomic impact of drought and flood disasters under the climate change scenario is of great significance for future drought and flood risk prediction, disaster prevention and mitigation, and adaptation management.

[0003] Continuous high temperature and drought, soil dehydration and looseness or caking and hardening, large atmospheric energy accumulation, slight disturbances are prone to severe convective weather and concentrated short-term heavy rainfall, and are prone to sudden flash floods and induce extreme disasters with multiple disaster-causing factors superimposed. In recent years, when there is no precipitation or less precipitation in the early stage and drought has occurred, it is easy to be followed by high-intensity precipitation in a short period of time and form floods. This phenomenon is called drought-flood transition. Due to the rapid transition of natural states, short time and high rainfall intensity, it is easy to cause flash floods, sudden rise of river water, river water intrusion and other phenomena. Drought-flood transition poses a great challenge to flood and drought disaster prevention, and early prevention is needed. However, it is still unclear how to monitor and predict future drought-flood transition disasters.

[0004] In March 2002, the Gravity Recovery and Climate Experiment (GRACE) satellite was successfully launched, providing a continuous and high-precision direct observation method for obtaining global large-scale migration of Earth's surface materials. The gravity field model based on the GRACE satellite signal solution can extract the change information of the Earth's lunar gravity field at a spatial scale of 300km×300km, deduct the influence of factors such as crustal material movement, atmospheric movement, ocean currents and tides, and can effectively reflect the gravity changes caused by ice and snow, surface water, soil water, groundwater and human factors, and comprehensively monitor the terrestrial water storage anomaly (TWSA) signal. In May 2018, after the GRACE gravity satellite stopped working for a year, the GRACE-FO (GRACE Follow-On) gravity satellite was successfully launched, continuing the scientific observation mission of the GRACE satellite. The GRACE / GRACE-FO gravity satellite effectively solved the problems of shallow ground observation range, uneven spatial distribution, and difficulty in data acquisition, and showed great potential in tracking regional and global water and drought events.

[0005] Although GRACE / GRACE-FO satellites have begun to be used for drought and flood disaster monitoring and assessment, the satellite observation time is short, making it difficult to achieve drought and flood disaster risk assessment over a longer time span. At present, related research on predicting future drought conditions based on abnormal land water storage has just started abroad, and there are few reports in China. At the same time, these papers usually only focus on changes in a single disaster type such as drought or waterlogging, and rarely consider the evolution of drought-flood sudden transition events, and fail to make full use of artificial intelligence technology to carry out drought-flood sudden transition prediction. Summary of the invention

[0006] In view of this, the present application provides a method, system and storage medium for predicting sudden transition from drought to flood that integrates artificial intelligence and physical mechanisms, which can effectively and accurately combine artificial intelligence and atmospheric thermal dynamic mechanisms to predict sudden transition from drought to flood disasters under climate change.

[0007] In a first aspect, the present invention provides a method for predicting drought-flood transition by integrating artificial intelligence and physical mechanisms, comprising the following steps:

[0008] Step 1: Select a drought-flood transition research area and collect multi-source data in the research area, including: meteorological and hydrological data, terrestrial water storage data inverted by GRACE gravity satellite, atmospheric circulation data, large-scale climate index and CMIP6 global climate model output data;

[0009] Step 2: Calculate saturated vapor pressure deficit and specific humidity; use multi-scale spatial feature extraction method, XGBoost model and spatial attention mechanism to select the key factors affecting terrestrial water storage in each grid point in the study area;

[0010] Step 3: Based on the preferred key factors and the terrestrial water storage data inverted by the GRACE gravity satellite, a time convolutional network deep learning model is constructed and calibrated for simulating terrestrial water storage; a long series of key factor sets are used to drive the deep learning model to reconstruct a long series of terrestrial water storage inversion data sets;

[0011] Step 4: Based on the long series of terrestrial water storage inversion data sets reconstructed in step 3, the drought-flood transition events are extracted in combination with the run theory; the atmospheric circulation data and large-scale climate indices are processed using the empirical orthogonal function analysis method to extract the atmospheric circulation characteristics in the drought-flood transition events, and to construct the atmospheric circulation-drought-flood transition intensity pairing series;

[0012] Step 5: Based on the bin scaling function, the atmospheric circulation characteristics and drought-flood abrupt transition intensity pairs of all grid points in the study area are divided into M bins with the same sample size, and the nonlinear scaling relationship between drought-flood abrupt transition intensity and atmospheric circulation characteristics is derived;

[0013] Step 6: Based on the CMIP6 global climate model output data and the nonlinear scaling relationship obtained in step 5, predict the intensity and risk of drought-flood transition at each grid point in the future; use the emergence constraint technology to reduce the uncertainty of the prediction, and provide a probabilistic drought-flood transition risk prediction through the quantitative regression method.

[0014] Furthermore, the meteorological and hydrological data in step 1 include: 2m air temperature, dew point temperature, near-ground air pressure, precipitation, soil moisture, water vapor flux divergence, cloud cover, shortwave radiation and leaf area index, 500hPa potential height field, 200hPa horizontal wind field in the ERA5 reanalysis data set; impervious area of ​​each grid point on a monthly scale.

[0015] Furthermore, the step 2 comprises:

[0016] The Clausius-Clapeyron thermodynamic equation was used to calculate the saturated vapor pressure deficit based on the 2m air temperature and dew point temperature in the ERA5 reanalysis dataset, and the surface pressure and dew point temperature were used to calculate the specific humidity.

[0017] 2m air temperature, specific humidity, saturated vapor pressure deficit, precipitation, soil moisture, water vapor flux divergence, cloud cover, shortwave radiation, leaf area index, and impervious area were selected as driving factors;

[0018] The average value of each driving factor in multiple sliding windows is calculated, and the driving factors of multiple months are selected as the initial input variables of the XGBoost model. The spatial attention mechanism is introduced to allow the XGBoost model to automatically learn the importance weights of different positions and rank the importance of each input variable to the simulation variable.

[0019] Set a threshold and select variables within the ranking threshold range as key factors.

[0020] Furthermore, the step 3 comprises:

[0021] Build and calibrate a temporal convolutional network deep learning model to simulate terrestrial water storage;

[0022] Based on the key factors selected in step 2, the time convolutional network deep learning model established in step 3 is driven by a long series of data sets to reconstruct a long series of terrestrial water storage inversion data sets.

[0023] Furthermore, the step 4 comprises:

[0024] Based on the terrestrial water storage data in the long series terrestrial water storage inversion dataset reconstructed in step 3, calculate the drought intensity based on terrestrial water storage anomaly;

[0025] Set up a standardized drought-flood transition event intensity measurement index;

[0026] Combined with the travel theory, drought thresholds and flood thresholds are set respectively. Based on the drought intensity of abnormal land water storage, whether it is a dry month or a flood month is determined. The drought-flood transition event judgment standard is set to extract drought-flood transition events and calculate the drought-flood transition event intensity measurement index.

[0027] The atmospheric circulation field data corresponding to the drought-flood transition event were extracted to construct data matrices, the characteristic roots of the covariance matrix were calculated and sorted, and the atmospheric circulation field data with variance contribution rate and cumulative variance contribution rate greater than the set threshold were selected as the main atmospheric circulation characteristics of the drought-flood transition event;

[0028] It is paired with the drought-flood sudden transition event intensity measurement index of all previous drought-flood sudden transition events at each grid point in the prediction area to form an atmospheric circulation-drought-flood sudden transition intensity pairing series.

[0029] Furthermore, the step 5 comprises:

[0030] The atmospheric circulation characteristics and drought-flood abrupt change intensity paired series of all grid points in the study area are used as inputs of the box element scaling method;

[0031] Respectively characterize the atmospheric circulation characteristics of the box element and the average intensity of drought-flood sudden change events; get the average value of atmospheric circulation characteristics of group M - average intensity of drought-flood sudden change;

[0032] Based on the average value of atmospheric circulation characteristics-the average intensity of drought-flood abrupt transition, the nonlinear scaling relationship between the intensity of drought-flood abrupt transition and atmospheric circulation characteristics is deduced.

[0033] Furthermore, the step 6 comprises:

[0034] At each grid point in the study area, for each global climate model under each global shared economy path, calculate the intensity of drought-flood abrupt transition in the future period, and extract the atmospheric circulation characteristic data in the future period;

[0035] Using the nonlinear scaling relationship obtained in step 5, a preliminary forecast of the intensity of drought-flood transition in the future period is made;

[0036] For each grid point in the study area, the trend of the principal component comprehensive score in the historical period is calculated for each global climate model;

[0037] The data of all grid points in the study area under multiple global climate models are integrated to obtain the paired combination of the change trend of the principal component comprehensive score in the historical period and the intensity of the sudden change from drought to flood in the future period;

[0038] An emergence constraint model was constructed. Based on the reanalysis data in the ERA5 reanalysis dataset and the large-scale climate index provided by NOAA, the trend of the PCS principal component comprehensive score of each grid point was deduced, and the trend term was substituted into the emergence constraint model.

[0039] The predicted results of the intensity of drought-flood transition in the future at all grid points in the study area under multiple global climate models are collected and probability distribution fitting is performed to calculate the probability of occurrence of drought-flood transition events of different intensity levels.

[0040] In a second aspect, the present invention provides a drought-flood rapid transition prediction system integrating artificial intelligence and physical mechanisms, comprising:

[0041] Data acquisition module: It is used to select the drought-flood rapid transition research area and collect multi-source data in the research area, including: meteorological and hydrological data, terrestrial water storage data inverted by GRACE gravity satellite, atmospheric circulation data, large-scale climate index and CMIP6 global climate model output data;

[0042] Key factor optimization module: It is used to calculate saturated vapor pressure deficit and specific humidity. It uses multi-scale spatial feature extraction methods, XGBoost model and spatial attention mechanism to optimize the key factors affecting terrestrial water storage in each grid point in the study area.

[0043] Dataset reconstruction module: It is used to construct and calibrate a time convolutional network deep learning model for simulating terrestrial water storage based on the preferred key factors and the terrestrial water storage data inverted by the GRACE gravity satellite; drive the deep learning model with a long series of key factor sets to reconstruct a long series of terrestrial water storage inversion data sets;

[0044] Pairing module: It is used to extract drought-flood transition events based on the reconstructed long series of terrestrial water storage inversion data sets combined with the run theory; it uses the empirical orthogonal function analysis method to process atmospheric circulation data and large-scale climate indices, extract the atmospheric circulation characteristics in drought-flood transition events, and construct an atmospheric circulation-drought-flood transition intensity pairing series;

[0045] Scaling relationship derivation module: It is used to divide the atmospheric circulation characteristics-drought-flood abrupt transition intensity pairs of all grid points in the study area into M bins with the same sample capacity based on the bin scaling function, and deduce the nonlinear scaling relationship between the drought-flood abrupt transition intensity and the atmospheric circulation characteristics;

[0046] The risk prediction module is used to predict the intensity and risk of drought-flood transition at each grid point in the future based on the CMIP6 global climate model output data and the nonlinear scaling relationship obtained in step 5; it uses the emergence constraint technology to reduce the uncertainty of the prediction, and provides a probabilistic drought-flood transition risk prediction through the quantitative regression method.

[0047] In a third aspect, the present invention provides a computer-readable medium, wherein the computer-readable medium is a server workstation;

[0048] The server workstation stores a computer program executed by an electronic device. When the computer program runs on the electronic device, the electronic device executes the steps of the drought-flood rapid transition prediction method integrating artificial intelligence and physical mechanisms as described in any one of claims 1 to 7.

[0049] Compared with the prior art, the present invention has the following beneficial effects: the present application provides a drought-flood transition prediction method, system and storage medium integrating artificial intelligence and physical mechanisms. The method collects multi-source data, optimizes key factors through the XGBoost model and spatial attention mechanism, and constructs a temporal convolutional network model in combination with GRACE satellite data to achieve long-series terrestrial water storage data reconstruction; further applies run theory and EOF analysis to extract drought-flood transition events and atmospheric circulation characteristics; deduces nonlinear scaling relationships through box element scaling functions, and finally predicts future drought-flood transition risks based on CMIP6 data and integrated learning models. The method innovatively combines multi-source data and advanced algorithms to provide a new perspective for drought-flood transition prediction, has important scientific significance for disaster prevention and mitigation, and provides a theoretical and technical basis for evaluating the environmental and disaster effects of the evolution of the earth system. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 A specific flow chart of the estimation method is provided for the embodiment of the present application;

[0052] Figure 2 Schematic diagram of the spatial sliding window method. DETAILED DESCRIPTION

[0053] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present application, so the present application is not limited by the specific embodiments disclosed below.

[0054] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or modules is not necessarily limited to those steps or modules clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices. The naming or numbering of steps in this application does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The process steps that have been named or numbered can change the execution order according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved. The division of units in this application is a logical division. There may be other division methods in actual application. For example, multiple units may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed may be through some interfaces, and the indirect coupling or communication connection between units may be electrical or other similar forms, which are not limited in this application. Moreover, the units or sub-units described as separate components may or may not be physically separated, may or may not be physical units, or may be distributed in multiple circuit units, and some or all of the units may be selected according to actual needs to achieve the purpose of the present application.

[0055] Example 1

[0056] This embodiment provides a method for predicting sudden transitions from drought to flood that integrates artificial intelligence and physical mechanisms. The method collects multi-source data, optimizes key factors through the XGBoost model and spatial attention mechanism, and builds a temporal convolutional network model in combination with GRACE satellite data to achieve reconstruction of long series of terrestrial water storage data; further applies run theory and EOF analysis to extract drought-flood sudden transition events and atmospheric circulation characteristics; derives nonlinear scaling relationships through box element scaling functions, and finally predicts future drought-flood sudden transition risks based on CMIP6 data and the XGBoost model. This method innovatively combines multi-source data and advanced algorithms to provide a new perspective for predicting sudden transitions from drought to flood, has important scientific significance for disaster prevention and mitigation, and provides a theoretical and technical basis for evaluating the environmental and disaster effects of the evolution of the Earth system. For details of the specific process, see Figure 1 .

[0057] The technical solution of the present application is further described in detail below through embodiments and in conjunction with the accompanying drawings:

[0058] Based on the above embodiment, step 1 includes:

[0059] Firstly, a set of meteorological, hydrological, vegetation and land use data since 1950 is collected, including the monthly meteorological, hydrological and atmospheric circulation data of the fifth generation atmospheric reanalysis data set (ERA5) of the European Centre for Medium-Range Weather Forecasts, including 2m air temperature, dew point temperature, air pressure, precipitation, soil moisture, water vapor flux divergence, cloud cover, shortwave radiation and leaf area index (LAI), 500hPa potential height field and 200hPa horizontal wind field; the land use data set adopts the land use data set published by international and domestic scholars, and the present invention extracts the impervious surface area (ISA) of each grid point on a monthly scale through Google Earth Engine technology.

[0060] Satellite gravity data is used to invert terrestrial water storage. Internationally, the main institutions responsible for data interpretation include the Potsdam Geoscience Center in Germany, the Jet Propulsion Laboratory (JPL) of the California Institute of Technology, the Center for Space Research at University of Texas, Austin (CSR) and the Goddard Space Flight Center (GSFC) of NASA, and the like, which publish global gravity field output data on a monthly scale. The present invention simultaneously uses the latest sixth-generation (RL06) products released by JPL, CSR and GSFC. These three data sources have different spatial resolutions, and all provide mascon monthly-scale equivalent water heights (minus the average field from 2004 to 2009) based on the concentrated mass block gravity field solution, and finally output a long sequence of TWSA data sets. In order to consider the possible uncertainties caused by different data products, the three GRACE / GRACE-FO gravity satellite datasets were interpolated to a 0.25°×0.25° spatial grid, and the average of each product was taken in each time step, finally obtaining a monthly dataset of terrestrial water storage from 2002 to the present.

[0061] We further obtained a large-scale climate index data set from 1950 to the present, including the monthly time series of the Pacific Decadal Oscillation (PDO) Index, the Arctic Oscillation (AO) Index, the North Atlantic Oscillation (NAO) Index, and three ENSO (El Nino Southern Oscillation) indices provided by the Physical Sciences Laboratory (PSL) and Climate Prediction Center (CPC) of the National Oceanic and Atmospheric Administration (NOAA), including the NINO 1+2 region sea surface temperature anomaly index, the NINO 3 region sea surface temperature anomaly index, and the NINO 3.4 region sea surface temperature anomaly index.

[0062] To predict future climate scenarios, the five global climate models (GFDL-ESM4, IPSL-CM6A-LR, MPI-ESM1-2-HR, MRI-ESM2-0, UKESM1-0-LL) released recently in the sixth phase of the International Coupled Model Inter-comparison Project (CMIP6) were used. Compared with the earlier version (CMIP5), CMIP6 uses the matrix framework of Shared Socioeconomic Pathway (SSP) and Representative Concentration Pathway (RCP). This implementation uses the model output data of the highest greenhouse gas emission scenario SSP5-8.5. The output variables of the five global climate models include daily temperature data, and 1985-2014 (30 years in total) was selected as the historical period; to predict the meteorological characteristics under the future climate change scenario, the last 30-year window of this century (2071-2100) was set as the future period.

[0063] Based on the above embodiment, step 2 includes:

[0064] The Clausius-Clapeyron thermodynamic equation can quantitatively describe the saturated water vapor pressure e sat Nonlinear relationship with temperature T:

[0065]

[0066] Among them, T0 and e s0 L is the first integral constant and the second integral constant, which are 273.16K and 611Pa respectively; vis the latent heat of vaporization constant, taken as 2.5×10 6 J kg -1 ; R v is the water vapor gas constant, take 461 J kg -1 K -1 .

[0067] The dew point temperature represents the temperature when the air is cooled to water vapor saturation under the condition of constant water vapor content and air pressure. Substituting it into the Clausius-Clapeyron equation can measure the actual water vapor pressure. 2m ) and dew point temperature (T dew ) are substituted into formula (1) to deduce the near-saturation vapor pressure deficit

[0068] VPD=e sat (T 2m )-e sat (T 2m )

[0069] Specific humidity q is the ratio of water vapor mass to the total mass of the air mass, which is derived using ERA5 ground pressure p and dew point temperature. The formula is as follows:

[0070]

[0071] Further, if Figure 2 As shown in the figure, a multi-scale spatial feature extraction method is used. For each grid point, 3×3, 5×5 and 7×7 are set as the spatial sliding window thresholds, and the sliding is carried out in sequence according to these intervals. This multi-scale method can capture information at different spatial scales and improve the robustness of the machine learning model and its sensitivity to local and regional scale changes.

[0072] The XGBoost algorithm is used to construct a relationship model between each driving factor in the above multi-scale spatial range and the GRACE gravity satellite land water storage. The driving factors include air temperature, specific humidity, saturated water vapor pressure deficit, precipitation, soil moisture, water vapor flux divergence, cloud coverage, shortwave radiation, leaf area index, and impervious area (a total of 10 driving factors). For each driving factor, the average value in 3×3, 5×5 and 7×7 sliding windows is calculated to form 30 spatial features (10 factors × 3 sliding window averages). The input data of the XGBoost model are all GRACE inversion data period (April 2002 to present), and the time lag effect of each driving factor on land water storage is considered. For each month, the driving factors of this month and the previous two months are selected as model inputs. For this embodiment, there are 30×3=90 variables as initial model inputs. At the same time, the spatial attention mechanism is introduced to allow the model to automatically learn the importance weights of different positions. The spatial attention mechanism can be expressed as:

[0073] A=softmax(f(X))Y=A☉X (3)

[0074] Where: X is the input spatial feature, which is a four-dimensional tensor [B, T, HW, C], where B is the batch size, T is the time step (the current month plus the previous 2 months, a total of 3 months), HW is the number of spatial grid points in the study area, C is 30 features (10 driving factors × 3 sliding window sizes), and a total of 90 variables (10 × 3 × 3); f is the attention scoring function, which is used to calculate the importance score of each spatial position and is implemented using a single-layer neural network, that is, f(X) = W*X+b, where W is the weight matrix and b is the bias vector; A is the attention weight matrix, which is obtained by normalizing the output of the attention scoring function by the softmax function; Y is the spatial feature output after weighting by the spatial attention mechanism, which has the same shape as X. Each feature in Y is assigned a different weight, highlighting the factors and spatial positions that are more important for the prediction of terrestrial water storage, and ⊙ represents matrix multiplication.

[0075] The XGBoost model can rank the importance of each input variable to the simulation variable, and combine the weight of the spatial attention mechanism to select the important factors affecting terrestrial water storage. In this embodiment, 20% is set as the threshold, that is, after ranking 90 variables, the top 18 variables are selected as key factors.

[0076] Based on the above embodiment, step 3 includes:

[0077] Based on the preferred key factors, a temporal convolutional network (TCN) deep learning model was constructed using the key factors and GRACE gravity satellite data since April 2002. The structure of the TCN model includes multiple dilated convolutional layers, residual connections and skip connections, which can effectively capture long-term temporal dependencies.

[0078] The constructed temporal convolutional network deep learning model is used to simulate the terrestrial water storage since April 2002, which is expressed as:

[0079] TWS(t)=F[QM(t),QM(t-1),QM(t-2),QM(t-3)] (4)

[0080] Among them, TWS(t) represents the terrestrial water storage simulated by the TCN model at time t, QM(t) represents the input variable at time t, QM(t-1) represents the input variable at time t-1, QM(t-2) represents the input variable at time t-2, and QM(t-3) represents the input variable at time t-3; F represents the TCN model.

[0081] Based on the key factors selected in step 2, the long series of data sets since 1940 are used to drive the temporal convolutional network deep learning model established in step 3 to reconstruct the long series of terrestrial water storage data sets since 1940.

[0082] Based on the above embodiment, step 4 includes:

[0083] 4.1 Based on the long series of terrestrial water storage data since 1940 reconstructed in step 3, the long series of drought intensity is calculated as follows:

[0084]

[0085] Where DWI(j) represents the drought intensity based on terrestrial water storage anomaly in the jth month, TWSA j represents the reconstructed terrestrial water storage data for the jth month, and σ m are the mean and standard deviation of TWSA in month m, m = 1, 2…, 12, determined according to the calendar month in which month j falls.

[0086] Furthermore, a standardized drought-wetness arupt alternation intensity index (SDWAI) is proposed, as follows:

[0087] SDWAI=[(|DWI i |+|DWI i+1 |)*W*D*S*I] α (6)

[0088] Where: DWI i and DWI i+1 are the drought intensity based on the abnormal land water storage for two consecutive months; W is the weight term, the purpose is to appropriately increase the asymmetry of drought-flood transition, and W is defined as: W = [max(|DWI i |,|DWI i+1 |) / min(|DWI i |,|DWI i+1 |)] β ,β is the weight adjustment parameter, which is set to 0.5; D is the persistence factor, which is defined as: D = 1 + ln (1 + N), where N is the number of consecutive drought or flood months before; S is the seasonal factor, which is defined as: S = 1 + 0.5 * sin (2π * m / 12), where m is the month when the event occurs (1-12); I is the intensity change rate, which is defined as: I = |DWI i+1 -DWI i | / max(|DWI i|,|DWI i+1 |); α is the nonlinear adjustment parameter, which is set to 1.5.

[0089] Combined with the run theory, based on the long series DWI, -0.8 and 0.8 are called drought threshold and flood threshold respectively to judge whether it is a dry month or a flood month; drought-flood abrupt transition event is defined as the transition between dry month and flood month occurs within two consecutive months, which is specifically divided into:

[0090] Drought to Flood (D to W) Event, DWI i <-0.8,DWI i+1 >0.8

[0091] Flood-to-drought (W to D) event, DWI i >0.8,DWI i+1 <-0.8

[0092] The above method is used to extract drought-flood transition events for each grid point in the study area since 1940. Furthermore, for each identified drought-flood transition event, its SDWAI value is calculated. The larger the SDWAI value, the more intense the drought-flood transition event. The classification standard of drought-flood transition events based on the SDWAI definition is shown in Table 1.

[0093] Table 1

[0094]

[0095]

[0096] 4.2 Apply the EOF (Empirical Orthogonal Function) analysis method to process atmospheric circulation data and large-scale climate indices, extract the atmospheric circulation characteristics in drought-flood transition events, and construct a pairing series of atmospheric circulation-drought-flood transition intensity. The specific steps are as follows:

[0097] For each month when drought-flood abrupt transition events occurred at each grid point since 1940, the corresponding atmospheric circulation field data were extracted, including the 500hPa geopotential height field, the 200hPa horizontal wind field, the Pacific Decadal Oscillation (PDO) index, the Arctic Oscillation (AO) index, the North Atlantic Oscillation (NAO) index, and the three El Nino Southern Oscillation (ENSO) indices from 1940 to the present. For each atmospheric circulation field data and climate index, a data matrix X (n×m) was constructed, where n is the number of spatial grid points (for climate index, n=1), and m is the number of time samples. Then the covariance matrix was calculated to obtain the square matrix C n×n , as follows:

[0098]

[0099] Then calculate the square matrix C n×nThe characteristic roots (λ1, ..., λ n ) and the eigenvector V n×n , both satisfy

[0100] C n×n ×V n×n =V n×n ×∧ n×n (8)

[0101] Where ∧ is an n×n dimensional diagonal matrix, that is

[0102]

[0103] Arrange the characteristic roots λ from large to small, that is, λ1>λ2>…>λ m ≥0, the eigenvector corresponding to each non-zero eigenvalue is an EOF mode. Projecting EOF onto the data matrix X, we can obtain the time coefficients (principal components) corresponding to all spatial eigenvectors, that is,

[0104]

[0105] Furthermore, the variance contribution rate and cumulative variance contribution rate of each mode are calculated. The first p main EOF modes are selected so that their cumulative variance contribution rate reaches 80%, and the selected p EOF modes are regarded as the main atmospheric circulation characteristics of the drought-flood abrupt transition event. The calculation formulas of variance contribution rate and cumulative variance contribution rate are as follows:

[0106]

[0107]

[0108] The SDWAI index of each grid point in the forecast area is paired with the p principal component scores of the corresponding time to form an atmospheric circulation-drought-flood transition intensity pairing series. The pairing form is as follows:

[0109] {time, event type, SDWAI, EOF_PC1, EOF_PC2, ..., EOF_PC p}

[0110] Where: EOF_PC1, EOF_PC2, ..., EOF_PC p They represent the scores of the first p EOF principal components at the corresponding time, EOF_PC1>EOF_PC2>…>EOF_PC p .

[0111] Based on the above embodiment, step 5 includes:

[0112] Binning scaling is a function that can better characterize the nonlinear relationship between variables and has been widely used in recent years to analyze the climate response characteristics of extreme hydrological events. In this step, the atmospheric circulation characteristics and drought-flood abrupt transition intensity pairing series of all grid points in the study area are used as the input of the binning scaling method.

[0113] Specifically, the principal component scores (EOF_PC1, EOF_PC2, ..., EOF_PCp) of the main EOF modes obtained in step 4 are used, and the principal component synthetic score (PCS) is used as the sorting criterion:

[0114] PCS=w1*EOF_PC1+w2*EOF_PC2+...+Wp*EOF_PCp(13)

[0115] Where: wi is the weight of the i-th principal component, and its corresponding variance contribution rate is used.

[0116] For each grid point in the study area, we pair the calculated PCS value with the previously calculated SDWAI value to form a series of PCS-SDWAI pairs. Each pair contains the following information:

[0117] {time, event type, PCS, SDWAI}

[0118] Combine the PCS-SDWAI pairings of all grid points and sort them by PCS value from small to large. Divide these pairs into 12 bins of equal sample size; calculate the median PCS of each PCS in each bin median and the median SDWAI median , respectively characterizing the atmospheric circulation characteristics of the box element and the average intensity of drought-flood sudden transition events, and obtaining 12 sets of atmospheric circulation characteristics-drought-flood sudden transition intensity series.

[0119] Further, using these 12 groups (PCS median ,SDWAI median ) data points, the following formula is used to measure and predict the response function of the drought-flood abrupt change intensity to the change of atmospheric circulation characteristics in the study area:

[0120] SDWAI2=SDWAI1*(1+α SDWAI *δPCS) β (14)

[0121] Where: SDWAI1 and SDWAI2 are the SDWAI of adjacent bins. median ; α SDWAIis the scaling factor (Scalingrate), which indicates the response strength; δPCS is the PCS between adjacent bins median ; β is a power exponent, which is used to capture nonlinear relationships. Specifically, β>1 indicates an upward convex (convex function) relationship, and O<β<1 indicates a downward concave (concave function) relationship.

[0122] The local weighted sliding regression smoothing method is used to fit equation (14). Previous studies have found that the climate response types of extreme hydrological events can be divided into monotonic rising type, monotonic falling type and Hook structure (the inflection point is defined as the critical point, PCS critical ). The present invention first identifies the climate response type and PCS critical , and then derive the scaling coefficient α by the least squares method SDWAI and power index β. In this process, only PCS is used <PCS critical The data are fitted in bins of the data to ensure the stability and reliability of the obtained nonlinear scaling relationship.

[0123] Based on the above embodiment, step 6 includes:

[0124] 6.1 At each grid point in the study area, for each global climate model under each global shared economy path, the drought-flood transition intensity SDWAII in the future period (2070-2100) is calculated by equation (6), and the atmospheric circulation characteristic data in the future period is extracted, the EOF mode corresponding to the future period is calculated, and the principal component comprehensive score (PCS) in the future period is calculated by equation (13). Using the nonlinear scaling relationship obtained in step 5, the drought-flood transition intensity in the future period is preliminarily predicted as follows:

[0125] SDWAI fut =SDWAI his *(1+α*δPCS fut ) β (15)

[0126] Where SDWAI fut It represents the average intensity of drought-flood transition in the future period under a global climate model at this grid point. his The average value of drought-flood transition intensity in the historical period obtained based on the reconstructed DWI index at this grid point, δPCS fut is the PCS change value of the future period relative to the historical period, α and β are the scaling coefficient and power exponent obtained in step 5.

[0127] For each grid point in the study area, the trend of PCS in the historical period under each global climate model (denoted as PCS trend). Furthermore, the data of all grid points in the study area under the five global climate models were integrated to obtain the trend of PCS in the historical period and SDWAI in the future period. fut The emergence constraint model constructed by the pairing combination is as follows:

[0128] SDWA Ifut =a*PCS trend +b (16)

[0129] Where: a and b represent the parameters of the emergence constraint model;

[0130] The least squares method is used to solve the parameters a and b of the emergence constraint model.

[0131] Furthermore, based on the reanalysis data of the ERA5 dataset and the large-scale climate index provided by NOAA, the changing trend of the PCS of each grid point during 1985-2014 was deduced, and the trend term was substituted into the constructed emergence constraint model, as follows:

[0132] SDWAI fut-corr =a*OBS trend +b (17)

[0133] Where: SDWAI fut-corr The OBS represents the forecast results of the intensity of drought-flood transition in the future after correction. trend Represents the observed PCS trend in this grid point calculated based on ERA5 reanalysis data and large-scale climate indices provided by NOAA.

[0134] Finally, the prediction results of drought-flood abrupt transition intensity of all grid points in the study area in the future under five global climate models were used to calculate the SDWAI fut-corr , set, perform probability distribution fitting, and calculate the probability of drought-flood sudden change events of different intensity levels, as follows:

[0135] P(SDWAI fut-corr >threshold)=1-CDF(threshold)

[0136] Wherein: CDF is the cumulative distribution function, threshold is the predetermined intensity threshold (multiple thresholds can be set to correspond to different levels, see Table 1 for details).

[0137] Example 2

[0138] This embodiment provides a drought-flood rapid transition prediction system integrating artificial intelligence and physical mechanisms, including:

[0139] Data acquisition module: It is used to select the drought-flood rapid transition research area and collect multi-source data in the research area, including: meteorological and hydrological data, terrestrial water storage data inverted by GRACE gravity satellite, atmospheric circulation data, large-scale climate index and CMIP6 global climate model output data;

[0140] Key factor optimization module: It is used to calculate saturated vapor pressure deficit and specific humidity. It uses multi-scale spatial feature extraction methods, XGBoost model and spatial attention mechanism to optimize the key factors affecting terrestrial water storage in each grid point in the study area.

[0141] Dataset reconstruction module: It is used to construct and calibrate a time convolutional network deep learning model for simulating terrestrial water storage based on the preferred key factors and the terrestrial water storage data inverted by the GRACE gravity satellite; drive the deep learning model with a long series of key factor sets to reconstruct a long series of terrestrial water storage inversion data sets;

[0142] Pairing module: It is used to extract drought-flood transition events based on the reconstructed long series of terrestrial water storage inversion data sets combined with the run theory; it uses the empirical orthogonal function analysis method to process atmospheric circulation data and large-scale climate indices, extract the atmospheric circulation characteristics in drought-flood transition events, and construct an atmospheric circulation-drought-flood transition intensity pairing series;

[0143] Scaling relationship derivation module: It is used to divide the atmospheric circulation characteristics-drought-flood abrupt transition intensity pairs of all grid points in the study area into M bins with the same sample capacity based on the bin scaling function, and deduce the nonlinear scaling relationship between the drought-flood abrupt transition intensity and the atmospheric circulation characteristics;

[0144] The risk prediction module is used to predict the intensity and risk of drought-flood transition at each grid point in the future based on the CMIP6 global climate model output data and the nonlinear scaling relationship obtained in step 5; it uses the emergence constraint technology to reduce the uncertainty of the prediction, and provides a probabilistic drought-flood transition risk prediction through the quantitative regression method.

[0145] Example 3

[0146] This embodiment provides a computer-readable medium.

[0147] The computer readable medium is a server workstation;

[0148] The server workstation stores a computer program executed by an electronic device. When the computer program runs on the electronic device, the electronic device executes the steps of the drought-flood rapid transition prediction method based on artificial intelligence and satellite remote sensing in an embodiment of the present invention.

[0149] The above is only a preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed in the present application should be covered within the protection scope of the present application.

[0150] It should be understood that parts not elaborated in detail in this specification belong to the prior art.

[0151] It should be understood that the above description of the preferred embodiment is relatively detailed and cannot be regarded as limiting the scope of patent protection of the present invention. Under the enlightenment of the present invention, ordinary technicians in this field can also make substitutions or modifications without departing from the scope of protection of the claims of the present invention, which all fall within the scope of protection of the present invention. The scope of protection requested for the present invention shall be based on the attached claims.

Claims

1. A method for predicting drought-flood transitions by integrating artificial intelligence and physical mechanisms, characterized in that: The following steps are involved: Step 1: Select a drought-flood transition research area and collect multi-source data in the research area, including: meteorological and hydrological data, terrestrial water storage data inverted by GRACE gravity satellite, atmospheric circulation data, large-scale climate index and CMIP6 global climate model output data; Step 2: Calculate saturated vapor pressure deficit and specific humidity; use multi-scale spatial feature extraction method, XGBoost model and spatial attention mechanism to select the key factors affecting terrestrial water storage in each grid point in the study area; Step 3: Based on the preferred key factors and the terrestrial water storage data inverted by the GRACE gravity satellite, a time convolutional network deep learning model is constructed and calibrated for simulating terrestrial water storage; a long series of key factor sets are used to drive the deep learning model to reconstruct a long series of terrestrial water storage inversion data sets; Step 4: Based on the long series of terrestrial water storage inversion data sets reconstructed in step 3, the drought-flood transition events are extracted in combination with the run theory; the atmospheric circulation data and large-scale climate indices are processed using the empirical orthogonal function analysis method to extract the atmospheric circulation characteristics in the drought-flood transition events, and to construct the atmospheric circulation-drought-flood transition intensity pairing series; Step 5: Based on the bin scaling function, the atmospheric circulation characteristics and drought-flood abrupt transition intensity pairs of all grid points in the study area are divided into M bins with the same sample size, and the nonlinear scaling relationship between drought-flood abrupt transition intensity and atmospheric circulation characteristics is derived; Step 6: Based on the CMIP6 global climate model output data and the nonlinear scaling relationship obtained in step 5, predict the intensity and risk of drought-flood transition at each grid point in the future; use the emergence constraint technology to reduce the uncertainty of the prediction, and provide a probabilistic drought-flood transition risk prediction through the quantitative regression method.

2. The method for predicting drought-flood transition by integrating artificial intelligence and physical mechanism according to claim 1, characterized in that: The meteorological and hydrological data in step 1 include: 2m air temperature, dew point temperature, near-ground air pressure, precipitation, soil moisture, water vapor flux divergence, cloud cover, shortwave radiation and leaf area index, 500hPa potential height field, 200hPa horizontal wind field in the ERA5 reanalysis data set; impervious area of ​​each grid point on a monthly scale.

3. The method for predicting drought-flood transition by integrating artificial intelligence and physical mechanism according to claim 2, characterized in that: The step 2 comprises: The Clausius-Clapeyron thermodynamic equation was used to calculate the saturated vapor pressure deficit based on the 2m air temperature and dew point temperature in the ERA5 reanalysis dataset, and the surface pressure and dew point temperature were used to calculate the specific humidity. 2m air temperature, specific humidity, saturated vapor pressure deficit, precipitation, soil moisture, water vapor flux divergence, cloud cover, shortwave radiation, leaf area index, and impervious area were selected as driving factors; The average value of each driving factor in multiple sliding windows is calculated, and the driving factors of multiple months are selected as the initial input variables of the XGBoost model. The spatial attention mechanism is introduced to allow the XGBoost model to automatically learn the importance weights of different positions and rank the importance of each input variable to the simulation variable. Set a threshold and select variables within the ranking threshold range as key factors.

4. The method for predicting drought-flood transition by integrating artificial intelligence and physical mechanism according to claim 1, characterized in that: The step 3 comprises: Build and calibrate a temporal convolutional network deep learning model to simulate terrestrial water storage; Based on the key factors selected in step 2, the time convolutional network deep learning model established in step 3 is driven by a long series of data sets to reconstruct a long series of terrestrial water storage inversion data sets.

5. The method for predicting drought-flood transition by integrating artificial intelligence and physical mechanism according to claim 1, characterized in that: The step 4 comprises: Based on the terrestrial water storage data in the long series terrestrial water storage inversion dataset reconstructed in step 3, calculate the drought intensity based on terrestrial water storage anomaly; Set up a standardized drought-flood transition event intensity measurement index; Combined with the travel theory, drought thresholds and flood thresholds are set respectively. Based on the drought intensity of abnormal land water storage, whether it is a dry month or a flood month is determined. The drought-flood transition event judgment standard is set to extract drought-flood transition events and calculate the drought-flood transition event intensity measurement index. The atmospheric circulation field data corresponding to the drought-flood transition event were extracted to construct data matrices, the characteristic roots of the covariance matrix were calculated and sorted, and the atmospheric circulation field data with variance contribution rate and cumulative variance contribution rate greater than the set threshold were selected as the main atmospheric circulation characteristics of the drought-flood transition event; It is paired with the drought-flood sudden transition event intensity measurement index of all previous drought-flood sudden transition events at each grid point in the prediction area to form an atmospheric circulation-drought-flood sudden transition intensity pairing series.

6. The method for predicting drought-flood transition by integrating artificial intelligence and physical mechanism according to claim 5, characterized in that: The step 5 comprises: The atmospheric circulation characteristics and drought-flood abrupt change intensity paired series of all grid points in the study area are used as inputs of the box element scaling method; Respectively characterize the atmospheric circulation characteristics of the box element and the average intensity of drought-flood sudden change events; get the average value of atmospheric circulation characteristics of group M - average intensity of drought-flood sudden change; Based on the average value of atmospheric circulation characteristics-the average intensity of drought-flood abrupt transition, the nonlinear scaling relationship between the intensity of drought-flood abrupt transition and atmospheric circulation characteristics is deduced.

7. The method for predicting drought-flood transition by integrating artificial intelligence and physical mechanism according to claim 5, characterized in that: The step 6 comprises: At each grid point in the study area, for each global climate model under each global shared economy path, calculate the intensity of drought-flood abrupt transition in the future period, and extract the atmospheric circulation characteristic data in the future period; Using the nonlinear scaling relationship obtained in step 5, a preliminary forecast of the intensity of drought-flood transition in the future period is made; For each grid point in the study area, the trend of the principal component comprehensive score in the historical period is calculated for each global climate model; The data of all grid points in the study area under multiple global climate models are integrated to obtain the paired combination of the change trend of the principal component comprehensive score in the historical period and the intensity of the sudden change from drought to flood in the future period; An emergence constraint model was constructed. Based on the reanalysis data in the ERA5 reanalysis dataset and the large-scale climate index provided by NOAA, the trend of the PCS principal component comprehensive score of each grid point was deduced, and the trend term was substituted into the emergence constraint model. The predicted results of the intensity of drought-flood transition in the future at all grid points in the study area under multiple global climate models are collected and probability distribution fitting is performed to calculate the probability of occurrence of drought-flood transition events of different intensity levels.

8. A drought-flood rapid transition prediction system integrating artificial intelligence and physical mechanisms, characterized in that: include: Data acquisition module: It is used to select drought-flood rapid transition research areas and collect multi-source data in the research area, including: meteorological and hydrological data, terrestrial water storage data inverted by GRACE gravity satellite, atmospheric circulation data, large-scale climate index and CMIP6 global climate model output data; Key factor optimization module: It is used to calculate saturated vapor pressure deficit and specific humidity. It uses multi-scale spatial feature extraction methods, XGBoost model and spatial attention mechanism to optimize the key factors affecting terrestrial water storage in each grid point in the study area. Dataset reconstruction module: It is used to construct and calibrate a time convolutional network deep learning model for simulating terrestrial water storage based on the preferred key factors and the terrestrial water storage data inverted by the GRACE gravity satellite; drive the deep learning model with a long series of key factor sets to reconstruct a long series of terrestrial water storage inversion data sets; Pairing module: It is used to extract drought-flood transition events based on the reconstructed long series of terrestrial water storage inversion data sets combined with the run theory; it uses the empirical orthogonal function analysis method to process atmospheric circulation data and large-scale climate indices, extract the atmospheric circulation characteristics in drought-flood transition events, and construct an atmospheric circulation-drought-flood transition intensity pairing series; Scaling relationship derivation module: It is used to divide the atmospheric circulation characteristics-drought-flood abrupt transition intensity pairs of all grid points in the study area into M bins with the same sample capacity based on the bin scaling function, and deduce the nonlinear scaling relationship between the drought-flood abrupt transition intensity and the atmospheric circulation characteristics; The risk prediction module is used to predict the intensity and risk of drought-flood transition at each grid point in the future based on the CMIP6 global climate model output data and the nonlinear scaling relationship obtained in step 5. It uses the emergence constraint technology to reduce the uncertainty of the prediction and provides a probabilistic drought-flood transition risk prediction through the quantitative regression method. The drought-flood transition prediction system integrating artificial intelligence and physical mechanisms is used to execute the steps in the drought-flood transition prediction method integrating artificial intelligence and physical mechanisms described in any one of claims 1-7.

9. A computer-readable medium, characterized in that The computer readable medium is a server workstation; The server workstation stores a computer program executed by an electronic device. When the computer program runs on the electronic device, the electronic device executes the steps of the drought-flood rapid transition prediction method integrating artificial intelligence and physical mechanisms as described in any one of claims 1 to 7.

Images