Method and device for dynamic evaluation and prediction of water and flood disasters

Abstract

The present application relates to the technical field of disaster prediction, and relates to a dynamic evaluation and prediction method and device for water and flood disasters. The method comprises the following steps: obtaining historical crop loss amounts of each region in a target area; calculating a historical crop economic loss index according to the historical crop loss amounts; calculating a fluctuation coefficient of the historical agricultural economic loss index of each region according to the historical crop economic loss index; dividing the grades of water and flood disasters according to the fluctuation coefficient of the historical agricultural economic loss index; and using a Logistic regression model to regress and predict the economic loss index of each region according to the historical crop economic loss index and the divided grades of water and flood disasters, so as to dynamically evaluate the water and flood disaster loss in the target area. Through the technical scheme, the dynamic evaluation of the water and flood disaster loss in the target area is realized.

Description

Technical Field

[0001] This invention relates to the field of disaster prediction technology, and in particular to a dynamic assessment and prediction method and apparatus for marine drought disasters. Background Technology

[0002] With the increasing severity of global warming, extreme disasters caused by climate change have become one of the most serious challenges facing humanity in the 21st century. Overexploitation of natural resources has severely damaged the Earth's ecological environment. China is one of the countries most frequently affected by natural disasters globally, with annual losses reaching hundreds of billions of yuan. Among these, droughts and floods cause particularly severe economic losses. Records show that since the beginning of the 21st century, droughts have become longer-lasting, more widespread, and have resulted in increasingly severe losses. Drought-affected areas account for over 40% of all natural disaster-affected areas annually in my country, agricultural losses from drought account for over 60% of total natural disaster losses, and the number of people affected by drought exceeds 50%. Droughts and floods have become significant factors impacting my country's grain production and are also major threats to the rapid development of agriculture. Therefore, a reasonable, scientific, and quantitative assessment of the affected population in drought-prone areas is crucial for drought relief and disaster reduction, and is of paramount importance to drought relief and disaster reduction projects.

[0003] There is a wealth of research both domestically and internationally on economic losses, disaster carrying capacity, disaster severity, and affected populations in drought-stricken areas. This research is of great significance for risk assessment, drought relief and disaster reduction, and drought and flood control in drought-stricken regions. Most scholars' studies on affected populations, disaster carrying capacity, disaster severity, and economic losses in drought-stricken areas tend to assess the entire drought-stricken region. However, these factors are not uniform across drought-stricken areas but rather regional. Therefore, a reasonable grid division of drought-stricken areas is necessary to obtain scientifically sound and reasonable indices for affected populations, disaster carrying capacity, disaster severity, and economic losses. Summary of the Invention

[0004] To overcome the problems existing in related technologies, the present invention provides a method and apparatus for dynamic assessment and prediction of flood and drought disasters, thereby realizing dynamic assessment of flood and drought disaster losses in target areas.

[0005] According to a first aspect of the present invention, a method for dynamic assessment and prediction of floods and droughts is provided, the method comprising:

[0006] Obtain historical crop loss data for each region within the target area;

[0007] Calculate the historical crop economic loss index based on the historical crop loss amount;

[0008] Based on the historical crop economic loss index, calculate the fluctuation coefficient of the historical agricultural economic loss index for each region.

[0009] The severity of floods and droughts is determined based on the fluctuation coefficient of the historical agricultural economic loss index.

[0010] Based on the historical crop economic loss index and the classification of flood and drought disaster levels, a Logistic regression model is used to predict the economic loss index of each region in order to dynamically assess the flood and drought disaster losses in the target area.

[0011] In one embodiment, preferably, the historical crop economic loss index is calculated using the following first calculation formula:

[0012]

[0013] Where I represents the agricultural economic loss index caused by floods or droughts, indicating the proportion of total agricultural output lost due to floods or droughts; S represents the total sown area of ​​crops in the current year, with the unit set at 0.1 million hm². 2 S i This indicates the area of ​​crops damaged by floods or droughts, with the unit set at 0.1 million hectares. 2 SI represents the total area of ​​crops damaged by floods or droughts in that year, with the unit set at 0.1 million hectares. 2 .

[0014] In one embodiment, preferably, the volatility coefficient of the historical agricultural economic loss index is calculated using the following second calculation formula:

[0015]

[0016] Where, λ it λ represents the fluctuation coefficient of flood and drought disasters in the i-th region in year t. The fluctuation coefficient is used to assess the degree of loss caused by floods and droughts. it The larger the value of λ, the greater the disaster losses in the region, and vice versa. it The smaller the value, the less damage the region suffers; I t denoted as the agricultural economic loss index caused by floods and droughts in year t; I represents the average agricultural economic loss index caused by floods and droughts in the target area since 1949.

[0017] In one embodiment, preferably, the classification of flood and drought disaster levels based on the fluctuation coefficient of the historical agricultural economic loss index includes:

[0018] When the fluctuation coefficient is less than the first threshold, the corresponding flood and drought disaster level is determined to be mild.

[0019] When the fluctuation coefficient is greater than or equal to the first threshold and less than or equal to the second threshold, the corresponding level of flood and drought disaster is determined to be medium, wherein the second threshold is greater than the first threshold;

[0020] When the fluctuation coefficient is greater than or equal to the first threshold and less than or equal to the second threshold, the corresponding level of flood and drought disaster is determined to be medium.

[0021] When the fluctuation coefficient is greater than the second threshold, the corresponding flood and drought disaster level is determined to be severe.

[0022] In one embodiment, preferably, based on the historical crop economic loss index and the classified levels of flood and drought disasters, a logistic regression model is used to predict the economic loss index of each region, so as to dynamically assess the flood and drought disaster losses within the target area, including:

[0023] The following third formula is used to calculate the flood and drought disaster losses in the target area:

[0024]

[0025] Where P represents the probability of floods and droughts occurring; α represents the intercept; β represents the regression coefficient; and X represents the historical crop economic loss index. When the output result P is 0, it means that the probability of floods and droughts occurring is 0; when the output result P is 1, it means that the probability of floods and droughts occurring is 100%.

[0026] In one embodiment, preferably, the method further includes:

[0027] The historical crop economic loss index of each region within the target area is classified and predicted according to the different levels of flood and drought disasters using a Logistic regression model, and the number of first datasets predicted for each level of flood and drought disaster is counted.

[0028] Count the number of second datasets corresponding to the actual flood and drought disaster levels;

[0029] The number of data points in the first dataset is compared with the number of data points in the second dataset to determine the prediction accuracy of the Logistic regression model;

[0030] When the prediction accuracy is less than the preset accuracy, the intercept and regression coefficients are adjusted, and the Logistic regression model is redefined.

[0031] According to a second aspect of the present invention, a dynamic assessment and prediction device for floods and droughts is provided, the device comprising:

[0032] The acquisition module is used to obtain the historical crop loss amount in various regions within the target area;

[0033] The first calculation module is used to calculate the historical crop economic loss index based on the historical crop loss amount.

[0034] The second calculation module is used to calculate the fluctuation coefficient of the historical agricultural economic loss index for each region based on the historical crop economic loss index.

[0035] The classification module is used to classify the levels of floods and droughts based on the fluctuation coefficient of the historical agricultural economic loss index.

[0036] The prediction module is used to perform regression prediction of the economic loss index of each region based on the historical crop economic loss index and the classification of flood and drought disaster levels, so as to dynamically assess the flood and drought disaster losses in the target area.

[0037] According to a third aspect of the present invention, a dynamic assessment and prediction device for floods and droughts is provided, the device comprising:

[0038] processor;

[0039] Memory used to store processor-executable instructions;

[0040] The processor is configured as follows:

[0041] Obtain historical crop loss data for each region within the target area;

[0042] Calculate the historical crop economic loss index based on the historical crop loss amount;

[0043] Based on the historical crop economic loss index, calculate the fluctuation coefficient of the historical agricultural economic loss index for each region.

[0044] The severity of floods and droughts is determined based on the fluctuation coefficient of the historical agricultural economic loss index.

[0045] Based on the historical crop economic loss index and the classification of flood and drought disaster levels, a Logistic regression model is used to predict the economic loss index of each region in order to dynamically assess the flood and drought disaster losses in the target area.

[0046] According to a fourth aspect of the present invention, a computer-readable storage medium is provided having computer instructions stored thereon, which, when executed by a processor, implement the steps of the method as described in any one of the embodiments of the second aspect.

[0047] Compared with the prior art, the beneficial effects of the present invention are:

[0048] To rationally, scientifically, and quantitatively estimate the damage caused by floods and droughts, this invention proposes a dynamic assessment and prediction method for flood and drought damage based on a Logistic regression model. This method first collects data on crop losses in various cities, counties, and townships within the target area since 1949. Then, it calculates the economic loss index of crops in each city, county, and township. A fluctuation coefficient is used to obtain the fluctuation coefficient of flood and drought disasters in each region in each year. Different levels of agricultural economic indices are then classified according to the range of the fluctuation coefficient. Finally, a Logistic regression model is used to complete the agricultural economic loss index of each region in each year, thereby completing the dynamic assessment of flood and drought disaster losses in the target area and further improving the accuracy of the agricultural economic loss index for different levels of flood and drought disasters.

[0049] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0050] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0051] Figure 1 This is a flowchart illustrating a dynamic assessment and prediction method for flood and drought disasters according to an exemplary embodiment.

[0052] Figure 2 This is a flowchart illustrating another dynamic assessment and prediction method for floods and droughts, according to an exemplary embodiment.

[0053] Figure 3 This is a block diagram illustrating a dynamic assessment and prediction device for floods and droughts according to an exemplary embodiment.

[0054] Figure 4 This is a block diagram illustrating another dynamic assessment and prediction device for floods and droughts, according to an exemplary embodiment. Detailed Implementation

[0055] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0056] Figure 1 This is a flowchart illustrating a dynamic assessment and prediction method for flood and drought disasters according to an exemplary embodiment.

[0057] like Figure 1 As shown, according to a first aspect of the present invention, a dynamic assessment and prediction method for floods and droughts is provided, the method comprising:

[0058] Step S101: Obtain the historical crop loss of each region within the target area; for example, if the target area is Henan Province, the crop loss of all cities, counties, and townships in Henan Province since 1949 can be collected through yearbooks, documents, the Internet, and other channels.

[0059] Step S102: Calculate the historical crop economic loss index based on the historical crop loss amount;

[0060] The most basic and conventional method for calculating agricultural economic losses is based on crop yield losses caused by natural disasters such as floods and droughts. This study uses data on the affected crop area to construct an agricultural economic loss model. Based on the affected area of ​​floods and droughts in Henan Province, this study constructs an agricultural economic water and drought disaster loss index. The process of establishing the agricultural economic loss index is shown in Equation 1:

[0061]

[0062] Where I represents the agricultural economic loss index caused by floods or droughts, indicating the proportion of total agricultural output lost due to floods or droughts; S represents the total sown area of ​​crops in the current year, with the unit set at 0.1 million hm². 2 S i The area of ​​crops damaged by floods or droughts is defined as 0.1 million hectares. 2 S I This represents the total area of ​​crops damaged by floods or droughts in the current year, with the unit set at 0.1 million hectares. 2 .

[0063] Step S103: Based on the historical crop economic loss index, calculate the fluctuation coefficient of the historical agricultural economic loss index for each region. The fluctuation coefficient is based on the principle of standardization after removing the mean from the sample's deviation from the overall statistical standard. It mainly measures the degree of deviation of the flood and drought disaster value of each year from the overall average flood and drought disaster value, thus eliminating the shortcomings of absolute value comparison. The calculation process of the fluctuation coefficient is shown in Equation 2:

[0064]

[0065] Where, λ it λ refers to the fluctuation coefficient of flood and drought disasters in the i-th region in year t. The fluctuation coefficient is used to assess the degree of loss caused by floods and droughts. it The larger the value of λ, the greater the disaster losses in the region, and vice versa. it The smaller the value, the less damage the region suffers; I tLet represent the agricultural economic loss index caused by floods and droughts in year t; This represents the average index of agricultural economic losses caused by floods and droughts in Henan Province since 1949.

[0066] Step S104: Classify the level of flood and drought disasters according to the fluctuation coefficient of the historical agricultural economic loss index;

[0067] In one embodiment, preferably, the classification of flood and drought disaster levels based on the fluctuation coefficient of the historical agricultural economic loss index includes:

[0068] When the fluctuation coefficient is less than the first threshold, the corresponding flood and drought disaster level is determined to be mild.

[0069] When the fluctuation coefficient is greater than or equal to the first threshold and less than or equal to the second threshold, the corresponding level of flood and drought disaster is determined to be medium, wherein the second threshold is greater than the first threshold;

[0070] When the fluctuation coefficient is greater than or equal to the first threshold and less than or equal to the second threshold, the corresponding level of flood and drought disaster is determined to be medium.

[0071] When the fluctuation coefficient is greater than the second threshold, the corresponding flood and drought disaster level is determined to be severe.

[0072] For example, λ it <1 indicates mild drought, 1<λ it <3 indicates moderate drought, λ it A score of >3 indicates severe drought, and the drought severity level is determined based on the fluctuation coefficients of various cities, counties, and townships in Henan Province over the years.

[0073] Step S105: Based on the historical crop economic loss index and the classification of flood and drought disaster levels, a Logistic regression model is used to predict the economic loss index of each region in order to dynamically assess the flood and drought disaster losses in the target area.

[0074] A logistic regression model was established to predict and assess flood and drought disasters. This study used a logistic regression model to predict the agricultural economic loss index for various cities, counties, and townships in Henan Province. The logistic regression model describes the relationship between a binary dependent variable and independent variables, where 0 represents the absence of flood and drought disasters and 1 represents their occurrence. The logistic regression function is shown in Equation 3:

[0075]

[0076] Where P is the probability of floods and droughts occurring; α is the intercept; β is the regression coefficient; and X is the historical crop economic loss index. When the output P is 0, it indicates that the probability of a flood or drought occurring is 0; when the output P is 1, it indicates that the probability of a flood or drought occurring is 100%. The above formula can be transformed into:

[0077]

[0078] Among them, the impact factor Xi (i=1,2,3...n) is the independent variable, representing the historical crop economic loss index. As a dependent variable.

[0079] Figure 2 This is a flowchart illustrating another dynamic assessment and prediction method for floods and droughts, according to an exemplary embodiment.

[0080] like Figure 2 As shown, in one embodiment, preferably, the method further includes:

[0081] Step S201: Classify and predict the historical crop economic loss index of each region in the target area according to the different levels of flood and drought disasters using the Logistic regression model, and count the number of first datasets predicted for each level of flood and drought disaster.

[0082] Step S202: Count the number of second datasets corresponding to the actual flood and drought disaster levels;

[0083] Step S203: Compare the number of the first dataset with the number of the second dataset to determine the prediction accuracy of the Logistic regression model;

[0084] Step S204: When the prediction accuracy is less than the preset accuracy, adjust the intercept and regression coefficients, and redetermine the Logistic regression model.

[0085] For example, based on the range of values ​​for the aforementioned fluctuation coefficient, the level of flood and drought disasters is determined. The agricultural economic loss index obtained from all cities, counties, and townships in Henan Province since 1949 is classified and predicted according to different flood and drought disaster levels using a Logistic regression model. The number of datasets corresponding to the actual drought level is counted and compared with the number of datasets predicted by the Logistic regression model. If the accuracy reaches 85%, the model is considered feasible; otherwise, if the accuracy does not reach 85%, the model is considered not feasible, and the intercept and regression coefficient are changed to redetermine the model.

[0086] Figure 3 This is a block diagram illustrating a dynamic assessment and prediction device for floods and droughts according to an exemplary embodiment.

[0087] like Figure 3 As shown, according to a second aspect of the present invention, a dynamic assessment and prediction device for floods and droughts is provided, the device comprising:

[0088] Module 31 is used to obtain the historical crop loss amount in each region within the target area;

[0089] The first calculation module 32 is used to calculate the historical crop economic loss index based on the historical crop loss amount.

[0090] The second calculation module 33 is used to calculate the fluctuation coefficient of the historical agricultural economic loss index for each region based on the historical crop economic loss index.

[0091] The classification module 34 is used to classify the levels of flood and drought disasters based on the fluctuation coefficient of the historical agricultural economic loss index.

[0092] The prediction module 35 is used to perform regression prediction of the economic loss index of each region based on the historical crop economic loss index and the classification of flood and drought disaster levels, using a Logistic regression model, so as to dynamically assess the flood and drought disaster losses in the target area.

[0093] In one embodiment, preferably, the historical crop economic loss index is calculated using the following first calculation formula:

[0094]

[0095] Where I represents the agricultural economic loss index caused by floods or droughts, indicating the proportion of total agricultural output lost due to floods or droughts; S represents the total sown area of ​​crops in the current year, with the unit set at 0.1 million hm². 2 S i This indicates the area of ​​crops damaged by floods or droughts, with the unit set at 0.1 million hectares. 2 SI represents the total area of ​​crops damaged by floods or droughts in that year, with the unit set at 0.1 million hectares. 2 .

[0096] In one embodiment, preferably, the volatility coefficient of the historical agricultural economic loss index is calculated using the following second calculation formula:

[0097]

[0098] Where, λ it λ represents the fluctuation coefficient of flood and drought disasters in the i-th region in year t. The fluctuation coefficient is used to assess the degree of loss caused by floods and droughts. it The larger the value of λ, the greater the disaster losses in the region, and vice versa. itThe smaller the value, the less damage the region suffers; I t This represents the index of agricultural economic losses caused by floods and droughts in year t. This represents the average index of agricultural economic losses caused by floods and droughts in the target area since 1949.

[0099] In one embodiment, preferably, the partitioning module is specifically used for:

[0100] When the fluctuation coefficient is less than the first threshold, the corresponding flood and drought disaster level is determined to be mild.

[0101] When the fluctuation coefficient is greater than or equal to the first threshold and less than or equal to the second threshold, the corresponding level of flood and drought disaster is determined to be medium, wherein the second threshold is greater than the first threshold;

[0102] When the fluctuation coefficient is greater than or equal to the first threshold and less than or equal to the second threshold, the corresponding level of flood and drought disaster is determined to be medium.

[0103] When the fluctuation coefficient is greater than the second threshold, the corresponding flood and drought disaster level is determined to be severe.

[0104] In one embodiment, preferably, the prediction module is used for:

[0105] The following third formula is used to calculate the flood and drought disaster losses in the target area:

[0106]

[0107] Where P represents the probability of floods and droughts occurring; α represents the intercept; β represents the regression coefficient; and X represents the historical crop economic loss index. When the output result P is 0, it means that the probability of floods and droughts occurring is 0; when the output result P is 1, it means that the probability of floods and droughts occurring is 100%.

[0108] Figure 4 This is a block diagram illustrating another dynamic assessment and prediction device for floods and droughts, according to an exemplary embodiment.

[0109] like Figure 4 As shown, in one embodiment, preferably, the device further includes:

[0110] The first statistical module 41 is used to classify and predict the historical crop economic loss index of each region in the target area according to the different levels of flood and drought disasters using a Logistic regression model, and to count the number of first datasets predicted for each level of flood and drought disaster.

[0111] The second statistics module 42 is used to count the number of second datasets corresponding to the actual flood and drought disaster levels;

[0112] The comparison module 43 is used to compare the number of the first dataset with the number of the second dataset to determine the prediction accuracy of the Logistic regression model;

[0113] The adjustment module 44 is used to adjust the intercept and regression coefficients and redetermine the Logistic regression model when the prediction accuracy is less than the preset accuracy.

[0114] According to a third aspect of the present invention, a dynamic assessment and prediction device for floods and droughts is provided, the device comprising:

[0115] processor;

[0116] Memory used to store processor-executable instructions;

[0117] The processor is configured as follows:

[0118] Obtain historical crop loss data for each region within the target area;

[0119] Calculate the historical crop economic loss index based on the historical crop loss amount;

[0120] Based on the historical crop economic loss index, calculate the fluctuation coefficient of the historical agricultural economic loss index for each region.

[0121] The severity of floods and droughts is determined based on the fluctuation coefficient of the historical agricultural economic loss index.

[0122] Based on the historical crop economic loss index and the classification of flood and drought disaster levels, a Logistic regression model is used to predict the economic loss index of each region in order to dynamically assess the flood and drought disaster losses in the target area.

[0123] According to a fourth aspect of the present invention, a computer-readable storage medium is provided having computer instructions stored thereon, which, when executed by a processor, implement the steps of the method as described in any one of the embodiments of the second aspect.

[0124] Furthermore, it can be understood that in this invention, "multiple" refers to two or more, and other quantifiers are similar. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship. The singular forms "a," "the," and "the" are also intended to include the plural forms unless the context clearly indicates otherwise.

[0125] It is further understood that the terms "first," "second," etc., are used to describe various types of information, but this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another, and do not indicate a specific order or degree of importance. In fact, the expressions "first," "second," etc., are completely interchangeable. For example, without departing from the scope of this invention, first information can also be referred to as second information, and similarly, second information can also be referred to as first information.

[0126] It is further understood that although the operations are described in a specific order in the accompanying drawings in the embodiments of the present invention, this should not be construed as requiring these operations to be performed in the specific order or serial order shown, or requiring all the operations shown to obtain the desired result. In certain environments, multitasking and parallel processing may be advantageous.

[0127] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0128] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A dynamic assessment and prediction method for floods and droughts, characterized in that, The method includes: Obtain historical crop loss data for each region within the target area; Calculate the historical crop economic loss index based on the historical crop loss amount; Based on the historical crop economic loss index, calculate the fluctuation coefficient of the historical agricultural economic loss index for each region. The severity of floods and droughts is determined based on the fluctuation coefficient of the historical agricultural economic loss index. Based on the historical crop economic loss index and the classification of flood and drought disaster levels, a Logistic regression model is used to predict the economic loss index of each region in order to dynamically assess the flood and drought disaster losses in the target area. The historical crop economic loss index is calculated using the following first calculation formula: Where I represents the agricultural economic loss index caused by floods or droughts, indicating the proportion of total agricultural output lost due to floods or droughts; S represents the total sown area of ​​crops in the current year, with the unit set at 0.1 million hm². 2 S i This indicates the area of ​​crops damaged by floods or droughts, with the unit set at 0.1 million hectares. 2 SI represents the total area of ​​crops damaged by floods or droughts in that year, with the unit set at 0.1 million hectares. 2 ; The volatility coefficient of the historical agricultural economic loss index is calculated using the following second calculation formula: in, I represents the fluctuation coefficient of flood and drought disasters in the i-th region in year t, and is used to assess the degree of loss caused by floods and droughts; t This represents the index of agricultural economic losses caused by floods and droughts in year t. This represents the average index of agricultural economic losses caused by floods and droughts in the target area since 1949. The severity of floods and droughts is classified according to the fluctuation coefficient of the historical agricultural economic loss index, including: When the fluctuation coefficient is less than the first threshold, the corresponding flood and drought disaster level is determined to be mild. When the fluctuation coefficient is greater than or equal to the first threshold and less than or equal to the second threshold, the corresponding level of flood and drought disaster is determined to be medium, wherein the second threshold is greater than the first threshold; When the fluctuation coefficient is greater than or equal to the first threshold and less than or equal to the second threshold, the corresponding level of flood and drought disaster is determined to be medium. When the fluctuation coefficient is greater than the second threshold, the corresponding flood and drought disaster level is determined to be severe. Based on the historical crop economic loss index and the classification of flood and drought disaster levels, a logistic regression model is used to predict the economic loss index of each region, in order to dynamically assess the flood and drought disaster losses within the target area, including: The following third formula is used to calculate the flood and drought disaster losses in the target area: （3） Where P represents the probability of floods and droughts occurring; α represents the intercept; β represents the regression coefficient; and X represents the historical crop economic loss index. When the output result P is 0, it means that the probability of floods and droughts occurring is 0; when the output result P is 1, it means that the probability of floods and droughts occurring is 100%.

2. The method according to claim 1, characterized in that, The method further includes: The historical crop economic loss index of each region within the target area is classified and predicted according to the different levels of flood and drought disasters using a Logistic regression model, and the number of first datasets predicted for each level of flood and drought disaster is counted. Count the number of second datasets corresponding to the actual flood and drought disaster levels; The number of data points in the first dataset is compared with the number of data points in the second dataset to determine the prediction accuracy of the Logistic regression model; When the prediction accuracy is less than the preset accuracy, the intercept and regression coefficients are adjusted, and the Logistic regression model is redefined.

3. A computer-readable storage medium storing computer instructions thereon, characterized in that, When executed by the processor, this instruction implements the steps of the method described in any one of claims 1-2.

Images