Urban flood disaster monitoring and early warning system and method

Abstract

The invention relates to the technical field of flood disaster monitoring, in particular to an urban flood disaster monitoring and early warning system and method. The rainfall, the soil humidity, the temperature, the historical water level and the wind speed serve as input data of a linear regression model, prediction data are obtained accordingly, a time sequence data set is constructed through the prediction data, differential processing is executed, and the prediction result is obtained on the basis of the constructed time sequence data set. A flood hybrid prediction model jointly established by an SARIMA model and an ARIMAX model is introduced to predict the water level value in a city, so that the prediction precision and stability of the prediction model on the water level value are improved; and based on the predicted water level value, combining with a risk assessment model to comprehensively judge whether the city has a flood disaster risk, and when the flood disaster risk exists, determining an emergency plan of the city, and thus constructing a polynomial regression model to further predict the damage degree of the city at the future moment. And auxiliary decision support is provided for monitoring and disposal of urban flood disasters.

Description

Technical Field

[0001] The present invention relates to the technical field of flood disaster monitoring, and in particular to an urban flood disaster monitoring and early warning system and method. Background Art

[0002] Urban flood disasters refer to the serious losses caused by the rise of water levels in urban areas due to rainfall, poor drainage or other factors. Such disasters not only threaten the safety of people's lives and property, but also have a huge impact on urban infrastructure and ecological environment. With the intensification of global climate change and the acceleration of urbanization, the frequency and intensity of flood disasters are gradually increasing.

[0003] At present, the risk of urban flooding is usually predicted by combining parameters such as rainfall, wind speed, and humidity through a linear regression model. However, when analyzing the risk of urban flooding based on the parameters, the temporal characteristics of the parameter data, such as seasonal changes, are not considered, which results in the model being poor at processing temporal data, thereby affecting the accuracy of judgment. Moreover, the linear regression model only incorporates parameters such as rainfall, wind speed, and humidity into the model, and does not combine the inherent characteristics and external characteristics of the time series data to predict flood risks, further reducing the accuracy of predicting the degree of flood risk. Summary of the invention

[0004] In view of the above-mentioned shortcomings of the prior art, the present invention provides a system and method for monitoring and early warning of urban flood disasters, which can effectively solve the problem of inaccurate prediction of urban flood disaster conditions in the prior art.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: The present invention provides a system and method for monitoring and early warning of urban flood disasters, comprising: The data collection and construction module is used to obtain the city's rainfall, soil moisture, temperature, historical water level and wind speed, establish a linear regression model to predict water level data, and construct a time series data set. It also includes: The flood risk prediction and assessment module is based on the time series data set, introduces seasonal factors and the influence of rainfall, soil moisture, and wind speed, and combines the SARIMA model and the ARIMAX model to establish a flood hybrid prediction model to predict the water level value of the city, including: Based on the predicted water level value, the rainfall, soil moisture and sedimentation conditions of the city at the time of prediction are clearly defined to build a risk assessment model. Through the risk assessment model, it is determined whether the city is a flood disaster city and an early warning is implemented, including: If an early warning is issued, the generated emergency plan is obtained to clarify the completion degree of the emergency plan at the future moment, and the completion degree is combined with rainfall, soil moisture and siltation to establish a polynomial regression model to predict the extent of damage to the city caused by flood disasters.

[0006] Furthermore, after constructing the time series data set, a stationarity test is performed on the time series data set to determine whether to perform a difference operation, wherein the stationarity test may be performed through an ADF test or a KPSS test.

[0007] Furthermore, the algorithm expression of the SARIMA model is: In the formula, is the differential water level observation value at time t, that is, the change amplitude of the water level value, is the seasonal autoregressive polynomial, is an autoregressive polynomial, is the autoregressive order, is the seasonal difference operation, is the number of seasonal differences, is a non-seasonal difference operation, is the number of non-seasonal differences, is the seasonal moving average polynomial, The non-seasonal moving average part, is the order of the seasonal moving average term, is the error term.

[0008] Furthermore, the algorithm model expression of the ARIMAX model after differentiation is:

[0009] In the formula, are exogenous variables, including rainfall, soil moisture, and wind speed. is the coefficient of the exogenous variable, is the number of exogenous variables.

[0010] Furthermore, the algorithm expression of the flood hybrid prediction model is:

[0011] For differential operation, is the number of seasonal differences, is the number of non-seasonal differences.

[0012] Furthermore, the observed value after difference processing is obtained After that, the predicted value is restored. The algorithm expression is as follows: Where: is the water level value at the current moment, for The water level value at a certain moment.

[0013] Furthermore, the algorithm expression of the risk assessment model is:

[0014] In the formula, is the flood risk value, To predict the amount of rainfall at a given time, To predict the soil moisture at the time, To predict the sedimentation situation at the time, as well as are the corresponding weight coefficients respectively.

[0015] Furthermore, the method for determining the degree of completion of the emergency plan is as follows: Get the number of emergency response personnel in the current emergency plan ; Obtain the number of emergency equipment used in the emergency plan and determine the percentage of emergency equipment that can continue to perform normal work ; Get the number of emergency routes planned in the emergency plan , determine the distance between the emergency path and the area that needs to be dealt with in the emergency plan, obtain the total distance of multiple distances and record it as the emergency distance , Identify the fork features in the emergency path, obtain the number of fork features of all emergency paths and record it as the total fork and record it as ; in accordance with: In the formula, as well as are the corresponding weight coefficients, To calculate the number of items, is the constant correction factor; Get the completion coefficient , clarify the preset completion interval of the completion coefficient, and get the corresponding completion coefficient. .

[0016] Furthermore, the algorithm expression of the polynomial regression model is as follows:

[0017] In the formula, For the predicted extent of damage, are model parameters, For completion; Among them, ElasticNet is introduced to optimize the polynomial regression model by combining L1 regularization and L2 regularization, and its loss function is:

[0018] In the formula, is the true value, is the predicted value, For the The regression coefficient of the feature, is the sample size, is the feature vector, is the regularization parameter, which is used to control the strength of regularization. and are the strengths of L1 regularization and L2 regularization, respectively.

[0019] Different from the above, the present invention also provides a flood disaster monitoring and early warning method, which is implemented based on the urban flood disaster monitoring and early warning system.

[0020] Compared with the known prior art, the technical solution provided by the present invention has the following beneficial effects: By taking rainfall, soil moisture, temperature, historical water level and wind speed as input data of the linear regression model, the prediction data is obtained, and the prediction data is constructed into a time series data set, and differential processing is performed. Based on the constructed time series data set, the flood hybrid prediction model established by the SARIMA model and the ARIMAX model is introduced to predict the water level value in the city, thereby improving the prediction accuracy and stability of the prediction model for the water level value; Based on the predicted water level value and the risk assessment model, a comprehensive judgment is made on whether the city is at risk of flood disasters. If so, the city's emergency plan is clarified. A polynomial regression model is constructed to further predict the extent of damage to the city in the future, thus providing auxiliary decision-making support for the monitoring and disposal of urban flood disasters. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 It is a schematic diagram of the overall process of the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] The present invention will be further described below in conjunction with the embodiments.

[0025] Example 1 (see Figure 1 ): An urban flood disaster monitoring and early warning system, comprising at least: The data collection and construction module is used to obtain the impact data related to urban flood risk in different urban areas over a period of time. The impact data include: urban rainfall, soil moisture, temperature, historical water level and wind speed. The linear regression model is established by introducing the relationship between the impact data and the water level. The algorithm expression of the linear regression model is as follows:

[0026] In the formula, For the predicted water level data, is the intercept term, is the rainfall, is soil moisture, is the temperature, is the wind speed, The historical water level, as well as are the corresponding influence weights, is the error term; The above-mentioned period of time may be a monthly time, etc. (such as taking the current time as the time node and calculating forward 30 days to obtain the impact data under the historical monthly time), and clearly obtaining the average value of the impact data under the monthly time to establish a linear regression model and predict the current water level data.

[0027] Therefore, the predicted water level data is combined with the historical water level data to form a time series data set, wherein the time series data set is subjected to a stationarity test to determine the differential operation to ensure the stationarity of the data. The stationarity test can be performed through an ADF test or a KPSS test to determine whether a differential operation is required. If it is not stationary, a differential operation is required. The time series data set can be subjected to a first-order differential in advance to determine whether it is stationary. If it is stationary, stop, otherwise continue. The number of differential operations is determined to obtain a stationary time series data set. The differential operation is a well-known prior art, and therefore, it is not described in detail in this case.

[0028] The flood risk prediction and assessment module is used to construct a time series model through the time series data set after differencing. It should be noted that in this embodiment, the influence of seasonal factors and exogenous variables (precipitation, soil moisture, wind speed) on the time series model is taken into account. Therefore, seasonal factors, rainfall, soil moisture, wind speed (exogenous variables) are introduced into the time series model. The time series model includes the SARIMA model and the ARIMAX model. The SARIMA model can process seasonal time series data and can effectively identify and model seasonal patterns. The ARIMAX model can make the prediction more comprehensive by introducing exogenous variables such as rainfall, soil moisture, wind speed, etc. Through exogenous variables, ARIMAX can reveal the influence of different factors on the target variable (water level value) and enhance the explanatory power of the model.

[0029] Furthermore, the algorithm model expression for the SARIMA model after differentiation is:

[0030] The algorithm model expression for the ARIMAX model after differentiation is:

[0031] in, is the differential water level observation value at time t, that is, the change amplitude of the water level value, is the seasonal autoregressive polynomial, is an autoregressive polynomial, is the autoregressive order, is the seasonal difference operation, is the number of seasonal differences, is a non-seasonal differencing operation, is the number of non-seasonal differences, is the seasonal moving average polynomial, The non-seasonal moving average part, is the order of the seasonal moving average term, is the error term. are exogenous variables, including rainfall, soil moisture, and wind speed. is the coefficient of the exogenous variable, is the number of exogenous variables.

[0032] On the basis of the above time series model, in order to make the time series model provide more accurate prediction results for urban flood risk prediction in complex environment by considering seasonal changes and exogenous variables at the same time, that is, to relatively improve the model's understanding and prediction ability of complex dynamic systems, therefore, with the help of SARIMA model and ARIMAX model, a hybrid flood prediction model for urban flood disasters is obtained to achieve accurate prediction of urban flood disasters. The specific expression of the hybrid flood prediction model is as follows:

[0033] For differential operation, is the number of seasonal differences, is the number of non-seasonal differences. The observed value after difference processing is obtained Finally, in order to obtain the actual water level value, it is necessary to restore the predicted value. The algorithm expression involved is as follows:

[0034] Where: is the observed value (water level value) at the current moment, for The observed value at a moment.

[0035] It is worth noting that when it is necessary to predict the water level value in the city at a later time, the time to be predicted can be substituted to predict the water level value in the city at a later time (the predicted water level value can be expressed as According to the above-mentioned integrated flood hybrid prediction model, when predicting the predicted water level value at a future time, it is necessary to substitute the predicted rainfall at a future time. , soil moisture (See below) and wind speed, where the predicted wind speed can be predicted by establishing a linear regression model based on temperature, air pressure, humidity, rainfall, terrain characteristics and wind speed at the previous moment, which will not be repeated here).

[0036] Furthermore, the predicted water level value is obtained by predicting the water level value at a subsequent time. , and create a line risk assessment model to assess flood risk in the city. The specific steps are as follows: Water level values ​​based on forecasts , synchronously obtain the rainfall, soil moisture and siltation of drainage pipes at the predicted time; And build a risk assessment model based on this: In the formula, is the flood risk value, To predict the amount of rainfall at a given time, To predict the soil moisture at the time, To predict the sedimentation situation at the time, as well as are the corresponding weight coefficients respectively. Among them, The rainfall at the predicted time can be predicted by constructing a linear regression model. Specifically, weather parameters such as temperature, humidity, wind speed, and air pressure within a certain period of time are obtained. The correlation between rainfall and weather conditions is determined through Pearson correlation coefficient or heat map analysis to determine the key features that affect rainfall, usually including temperature, humidity, and wind speed. Thus, a linear regression model can be constructed to predict rainfall at future times. The same is true for soil moisture. By obtaining the temperature, wind speed, soil type, volumetric water content, saturated water content and rainfall in a certain period of time, the soil moisture at future moments can be predicted based on the linear regression model. For the sedimentation situation at the prediction time, the sedimentation data for a certain period of time in the past are obtained in advance, including rainfall, flow, flow rate, soil moisture, diameter of the drainage pipe and the height of the sediment (the sedimentation data are all average values), and the corresponding weight coefficients are assigned to build a linear regression model for prediction, and then the corresponding rainfall, soil moisture and sedimentation situation at the prediction time are obtained. Therefore, the flood risk value at the prediction time can be calculated according to the weighted method. Therefore, according to the flood risk value Determine the risk interval at the time of prediction, and then clarify the degree of flood disaster risk in different urban areas at the time of prediction. Generally speaking, the flood risk value The larger the value, the higher the risk level. When the flood risk value exceeds the preset safety interval, it is determined that there will be a flood disaster risk at the predicted time. Thus, an early warning signal is generated and output to the terminal device for execution of the early warning.

[0037] Furthermore, in this scheme, by clarifying whether there is a flood disaster risk in different urban areas at the predicted time, the urban areas with flood disaster risks are divided and recorded as flood disaster cities. At the same time, the predicted time when the flood disaster city triggers the flood disaster is obtained and recorded as the flood prediction time. Then, multiple different flood prediction times are obtained, and a disaster city data set is constructed through the flood disaster cities. The flood disaster cities in the disaster city data set are sorted from early to late according to the flood prediction time, and the time value between the corresponding flood prediction time and the current time is determined respectively, and recorded as the response time (multiple response times are obtained). The emergency response department corresponding to the flood disaster city is determined, and the emergency plan generated by each emergency response department for the flood disaster city is clarified (generally speaking, the emergency plan is preset in the database based on the response time and the predicted water level value, so as to be activated when encountering flood risks), and the completion coefficient of the emergency plan under the response time is determined. , where for the completion coefficient The judgment is based on the following steps: Get the number of emergency response personnel in the current emergency plan ; Obtain the number of emergency equipment used in the emergency plan and determine the percentage of emergency equipment that can continue to perform normal work , obtained based on the ratio between the emergency equipment that has not failed and the total emergency equipment; Get the number of emergency routes planned in the emergency plan Then determine the distance between the emergency path and the area that needs to be dealt with in the emergency plan, obtain the total distance of multiple distances and record it as the emergency distance , Clarify the fork features in the emergency path. When the emergency path application is affected, it is helpful for the emergency plan executors to change the original emergency path based on the fork, so as to facilitate the execution of the emergency plan. The number of fork features of all emergency paths is obtained and recorded as the total fork (determine the total number) and recorded as ; Based on this: In the formula, as well as are the corresponding weight coefficients, To calculate the number of items, is the constant correction factor; Get the completion coefficient , clarify the preset completion interval of the completion coefficient, and get the corresponding completion coefficient. , so as to obtain the execution completion degree of the emergency plan under the corresponding response time , and then, the completion Combined with the above-mentioned rainfall forecast , soil moisture , siltation A polynomial regression model is introduced to predict the extent of damage to cities caused by flood disasters in the future. The specific polynomial regression model is as follows:

[0038] In the formula, For the predicted extent of damage, are all model parameters.

[0039] The data analysis and optimization module is used to optimize the polynomial regression model using ElasticNet and combines L1 and L2 regularization. The polynomial regression model is optimized by L1 regularization and L2 regularization to effectively reduce the impact of unimportant features. The loss function of L1 regularization is:

[0040] The complexity of the model is limited by introducing the L2 regularization term, and its loss function is:

[0041] In the formula, is the real value (usually historical data, such as the actual observed value is the actual degree of damage to the city at a certain point in history), is the predicted value, For the The regression coefficient of the feature, is the sample size, is the eigenvector (4), is the regularization parameter, which is used to control the strength of regularization. Therefore, ElasticNet is introduced to optimize the polynomial regression model by combining the advantages of L1 regularization and L2 regularization to maintain the stability of the model. Its loss function is:

[0042] In the formula, and are the strengths of L1 regularization and L2 regularization, respectively. This reduces the risk of overfitting and improves the prediction stability of the above polynomial regression model.

[0043] Furthermore, based on the damage degree of the city predicted by the polynomial regression model obtained above, the damage degree of different flood-stricken cities in the future and through the implementation of emergency plans is clarified, so that the control center can make safety plans for the city in advance according to the degree of damage.

[0044] Different from the above, the present invention also provides a flood disaster monitoring and early warning method, which is implemented according to the urban flood disaster monitoring and early warning system, that is, refer to the above urban flood disaster monitoring and early warning system, and will not be repeated here.

[0045] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the protection scope of the technical solutions of the embodiments of the present invention.

Claims

1. An urban flood disaster monitoring and early warning system, comprising: The data collection and construction module is used to obtain the city's rainfall, soil moisture, temperature, historical water level and wind speed, establish a linear regression model to predict water level data, and construct a time series data set, which is characterized by also including: The flood risk prediction and assessment module, based on the time series data set, introduces seasonal factors and the influence of rainfall, soil moisture, and wind speed, and combines the SARIMA model and the ARIMAX model to establish a hybrid flood prediction model to predict the water level value of the city, including: Based on the predicted water level value, the rainfall, soil moisture and sedimentation conditions of the city at the time of prediction are clearly defined to build a risk assessment model. Through the risk assessment model, it is determined whether the city is a flood disaster city and an early warning is implemented, including: If an early warning is issued, the generated emergency plan is obtained to clarify the completion degree of the emergency plan at the future moment, and the completion degree is combined with rainfall, soil moisture and siltation to establish a polynomial regression model to predict the extent of damage to the city caused by flood disasters.

2. The urban flood disaster monitoring and early warning system according to claim 1 is characterized in that: After the time series data set is constructed, a stationarity test is performed on the time series data set to determine whether to perform a difference operation, wherein the stationarity test may be performed through an ADF test or a KPSS test.

3. The urban flood disaster monitoring and early warning system according to claim 1 is characterized in that: The algorithm expression of the SARIMA model is: In the formula, is the differential water level observation value at time t, that is, the change amplitude of the water level value, is the seasonal autoregressive polynomial, is an autoregressive polynomial, is the autoregressive order, is the seasonal difference operation, is the number of seasonal differences, is a non-seasonal differencing operation, is the number of non-seasonal differences, is the seasonal moving average polynomial, The non-seasonal moving average part, is the order of the seasonal moving average term, is the error term.

4. The urban flood disaster monitoring and early warning system according to claim 3 is characterized in that: The algorithm model expression of the ARIMAX model after differentiation is: In the formula, are exogenous variables, including rainfall, soil moisture, and wind speed. is the coefficient of the exogenous variable, is the number of exogenous variables.

5. The urban flood disaster monitoring and early warning system according to claim 4 is characterized in that: The algorithm expression of the flood hybrid prediction model is: In the formula, For differential operation, is the number of seasonal differences, is the number of non-seasonal differences.

6. The urban flood disaster monitoring and early warning system according to claim 5 is characterized in that: Get the observed value after difference processing After that, the predicted value is restored. The algorithm expression is as follows: Where: is the water level value at the current moment, for The water level value at a certain moment.

7. The urban flood disaster monitoring and early warning system according to claim 1 is characterized in that: The algorithm expression of the risk assessment model is: In the formula, is the flood risk value, To predict the amount of rainfall at a given time, To predict the soil moisture at the time, To predict the sedimentation situation at the time, as well as are the corresponding weight coefficients respectively.

8. The urban flood disaster monitoring and early warning system according to claim 7 is characterized in that: The method for determining the degree of completion of the emergency plan is as follows: Get the number of emergency response personnel in the current emergency plan ; Obtain the number of emergency equipment used in the emergency plan and determine the percentage of emergency equipment that can continue to perform normal work ; Get the number of emergency routes planned in the emergency plan , determine the distance between the emergency path and the area that needs to be dealt with in the emergency plan, obtain the total distance of multiple distances and record it as the emergency distance , Identify the fork features in the emergency path, obtain the number of fork features of all emergency paths and record it as the total fork and record it as ; in accordance with: In the formula, as well as are the corresponding weight coefficients, To calculate the number of items, is the constant correction factor; Get the completion coefficient , clarify the preset completion interval of the completion coefficient, and get the corresponding completion coefficient. .

9. The urban flood disaster monitoring and early warning system according to claim 7 is characterized in that: The algorithm expression of the polynomial regression model is as follows: In the formula, For the predicted extent of damage, are model parameters, For completion; Among them, ElasticNet is introduced to optimize the polynomial regression model by combining L1 regularization and L2 regularization, and its loss function is: In the formula, is the true value, is the predicted value, For the The regression coefficient of the feature, is the sample size, is the feature vector, is the regularization parameter, which is used to control the strength of regularization. and are the strengths of L1 regularization and L2 regularization, respectively.

10. A flood disaster monitoring and early warning method, characterized in that: The method is implemented according to the urban flood disaster monitoring and early warning system described in claim 1.

Images