Extreme weather monitoring method and system based on big data

Abstract

The invention relates to the technical field of weather monitoring, and discloses an extreme weather monitoring method and system based on big data, and the system comprises a data collection module which is responsible for collecting weather data from a historical database and recognizing the features of extreme weather events, thereby constructing an extreme weather sample library. The cloud layer analysis module is responsible for receiving and analyzing key feature information in cloud picture data provided by a satellite. And the classification module is used for carrying out regional division on the cloud picture data by utilizing urban information and predicting the weather condition of each region according to the association between the cloud picture feature of each region and the extreme weather sample. And the central control module carries out extreme evaluation on weather conditions of each region according to the data provided by the environment information acquisition module. And finally, the alarm module determines the weather extreme grade of each region according to the evaluation result of the central control module, and sends corresponding alarm information in time. According to the invention, through cooperative work of the modules, real-time monitoring, evaluation and early warning of extreme weather are effectively realized.

Description

Technical Field

[0001] The present invention relates to the field of weather monitoring technology, and in particular to a method and system for extreme weather monitoring based on big data. Background Art

[0002] In today's society, weather monitoring and early warning are of great significance to people's daily life, production activities and disaster prevention and control.

[0003] However, traditional weather monitoring methods are often limited by the number and coverage of their observation facilities, and it is difficult to meet people's demand for refined and comprehensive weather information. Although traditional observation facilities such as meteorological stations and weather radars can provide weather data to a certain extent, their layout is often relatively sparse, especially in remote areas or on the ocean. In addition, the operating costs of these facilities are relatively high, which is a considerable burden for areas with limited resources. At the same time, in addition to limited coverage and high operating costs, traditional weather warning systems also have some other problems. They mainly provide general weather information, and there are certain limitations in their monitoring and warning capabilities for extreme weather phenomena. This is mainly due to the incomplete cognition and understanding of complex weather systems by traditional methods, as well as the lack of observation data and accuracy limitations. Therefore, when extreme weather events occur suddenly, traditional warning systems often find it difficult to issue accurate warnings in advance, posing a threat to people's lives and property.

[0004] Given the limitations of current weather monitoring technology, including narrow monitoring range, high operating costs, and a lack of extreme weather data and low timeliness, we urgently need to develop a new extreme weather monitoring technology to comprehensively improve the accuracy and efficiency of weather monitoring and meet society's needs for extreme weather warning and response. Summary of the invention

[0005] In view of this, the present invention proposes an extreme weather monitoring method and system based on big data, aiming to solve the problems in current technology of narrow weather monitoring range, high operating cost of monitoring facilities, and lack of extreme weather data and poor timeliness.

[0006] The present invention proposes an extreme weather monitoring system based on big data, comprising:

[0007] A data acquisition module is electrically connected to the database, and is used to collect historical weather information in the database, extract characteristics of each extreme weather type in the historical weather information, and establish each extreme weather sample;

[0008] A cloud layer analysis module, used to receive satellite cloud images and extract characteristic information of the satellite cloud images;

[0009] A classification module, electrically connected to the data acquisition module and the cloud layer analysis module, respectively, and configured to divide the satellite cloud image into regions based on city information, and determine the weather conditions of each region according to the relationship between the characteristic information of the cloud image of each region and the types in each extreme weather sample;

[0010] An environmental information acquisition module is electrically connected to the environmental monitoring station of each of the areas, and is used to acquire environmental information of each of the areas, wherein the environmental information includes: temperature, humidity, wind speed, and air turbidity;

[0011] A central control module, electrically connected to the classification module and the environmental information acquisition module, respectively, and configured to perform an extreme score on the weather conditions of each of the areas according to the environmental information of each of the areas;

[0012] an alarm module, electrically connected to the central control module, and configured to determine the extreme weather level of each of the regions according to the extreme score, and send alarm information according to the extreme weather level;

[0013] Wherein, when the extreme weather level in the area is low, the alarm module is used to send the weather conditions in the area and the extreme weather level to the Meteorological Observation Bureau;

[0014] When the extreme weather level in the area is medium or high, the alarm module is used to send the weather conditions in the area and the extreme weather level to each smart terminal in the area.

[0015] Furthermore, the data collection module is used to collect historical weather information in the database, and extract the characteristics of each extreme weather type in the historical weather information, and establish each extreme weather sample, including:

[0016] The data acquisition module is used to obtain the cloud height, cloud thickness and cloud movement direction of each extreme weather type in the historical weather information. The data acquisition module is also used to grayscale the cloud image of each extreme weather type and obtain the grayscale of the grayscaled cloud image;

[0017] The data acquisition module is also used to divide each extreme weather type into a number of extreme weather samples Q based on a matrix method according to the weather type, where Q=(Q1, Q2, ...Qi);

[0018] The data acquisition module is also used to obtain the cloud height, cloud thickness, cloud movement direction and cloud image grayscale change ratio in each extreme weather sample Q.

[0019] Furthermore, the classification module is used to determine the weather conditions of each area according to the relationship between the characteristic information of the cloud map of each area and the types in each extreme weather sample, including:

[0020] The classification module is also used to obtain the real-time thickness of the cloud layer, the real-time height of the cloud layer and the real-time moving speed of the cloud layer from the characteristic information of the satellite cloud image of the area;

[0021] The classification module is also used to grayscale the satellite cloud image and obtain the real-time grayscale of the satellite cloud image;

[0022] The classification module is also used to determine the weather type of the area according to the relationship between the real-time cloud thickness, real-time cloud height, real-time cloud movement speed and real-time grayscale of the satellite cloud image and the cloud height, cloud thickness and cloud movement direction of each extreme weather sample Q and the cloud image grayscale, wherein:

[0023] If the real-time cloud thickness, real-time cloud height, real-time cloud movement speed and real-time grayscale of the satellite cloud image are consistent with the cloud height, cloud thickness and cloud movement direction and cloud image grayscale of the extreme weather sample Q, the classification module determines that the weather type of the area is the weather type of the extreme weather sample Q;

[0024] If any of the real-time cloud thickness, real-time cloud height, real-time cloud movement speed and real-time grayscale of the satellite cloud image is inconsistent with the cloud height, cloud thickness, cloud movement direction and cloud image grayscale of the extreme weather sample Q, the classification module obtains the change ratio of the real-time cloud thickness, real-time cloud height, real-time cloud movement speed and real-time grayscale of the satellite cloud image within the preset time period of the area, and determines the weather type of the area according to the change ratio of the real-time cloud thickness, real-time cloud height, real-time cloud movement speed and real-time grayscale of the satellite cloud image within the preset time period.

[0025] Furthermore, when the classification module obtains the change ratio of the real-time thickness of the cloud layer, the real-time height of the cloud layer, the real-time moving speed of the cloud layer, and the real-time grayscale of the satellite cloud image within the preset period of time in the area, and determines the weather type of the area according to the change ratio of the real-time thickness of the cloud layer, the real-time height of the cloud layer, the real-time moving speed of the cloud layer, and the real-time grayscale of the satellite cloud image within the preset period of time, it includes:

[0026] The classification module also determines the weather type of the area according to the relationship between the change ratio of the real-time cloud thickness, real-time cloud height, real-time cloud movement speed and real-time grayscale of the satellite cloud image within the preset time period and the change ratio of the cloud height, cloud thickness, cloud movement direction and cloud image grayscale in each extreme weather sample Q, wherein:

[0027] If the change ratio of the real-time cloud thickness, real-time cloud height, real-time cloud movement speed and real-time grayscale of the satellite cloud image within the preset time period is consistent with the change ratio of the cloud height, cloud thickness, cloud movement direction and cloud image grayscale in the extreme weather sample Q, the classification module determines that the weather type of the area is the weather type of the extreme weather sample Q;

[0028] If the change ratio of the real-time cloud thickness, real-time cloud height, real-time cloud movement speed and real-time grayscale of the satellite cloud image within the preset time period is inconsistent with the change ratio of the cloud height, cloud thickness, cloud movement direction and cloud image grayscale in each of the extreme weather samples Q, the classification module establishes a new extreme weather sample based on the real-time cloud thickness, real-time cloud height, real-time cloud movement speed and real-time grayscale of the satellite cloud image within the preset time period of the area and the change ratio of the real-time cloud thickness, real-time cloud height, real-time cloud movement speed and real-time grayscale of the satellite cloud image within the preset time period of the area.

[0029] Furthermore, the central control module is used to perform extreme scoring on the weather conditions of each of the areas according to the environmental information of each of the areas, including:

[0030] The central control module is also used to obtain the temperature difference L and humidity difference K of the area;

[0031] The central control module is further used to obtain the extreme score of the area according to the temperature difference L and the humidity difference K based on a formula, and the formula is as follows:

[0032] A=(L*z1)+(K*z2);

[0033] Wherein, A is the extreme score of the area, z1 and z2 are weight coefficients, and the sum of z1 and z2 is 1.

[0034] Furthermore, when the central control module is also used to obtain the temperature difference L and humidity difference K of the area, it includes:

[0035] The central control module is also used to obtain the real-time temperature l and real-time humidity k of the area, and the central control module is also used to determine the temperature difference L and humidity difference K of the area according to the relationship between the real-time temperature l and real-time humidity k and the preset temperature threshold interval and humidity threshold interval, wherein:

[0036] When the real-time temperature l is within the preset temperature threshold interval, and the real-time humidity k is within the preset humidity threshold interval, the central control module determines that the temperature difference L of the area is 0, and the humidity difference K of the area is 0;

[0037] When the real-time temperature l is lower than the preset temperature threshold interval, and the real-time humidity k is lower than the preset humidity threshold interval, the central control module determines the temperature difference L of the area = l 0-l, and the humidity difference K of the area = k0-k, where l 0 is the starting temperature of the preset temperature threshold interval, and k0 is the starting humidity of the preset temperature threshold interval;

[0038] When the real-time temperature l is higher than the preset temperature threshold interval and the real-time humidity k is higher than the preset humidity threshold interval, the central control module determines that the temperature difference L of the area is L=ll 1 and the humidity difference K of the area is K-k1, wherein l 1 is the end temperature of the preset temperature threshold interval and k1 is the end humidity of the preset humidity threshold interval.

[0039] Further, when the central control module determines the extreme score A of the area, it includes:

[0040] The central control module is also used to obtain the real-time wind speed J of the area, and the central control module is also used to compare the real-time wind speed J with the preset wind speed, and select a corresponding adjustment coefficient according to the comparison result to adjust the extreme score A of the area;

[0041] The central control module is further used to preset a first preset wind speed J1 and a second preset wind speed J2, and the central control module is further used to preset a first preset adjustment coefficient N1, a second preset adjustment coefficient N2 and a third preset adjustment coefficient N3, and J1<J2, N1<N2<N3<1;

[0042] When J<J1, the central control module selects the first preset adjustment coefficient N1 to adjust the extreme score A of the area;

[0043] When J1≤J<J2, the central control module selects the second preset adjustment coefficient N2 to adjust the extreme score A of the area;

[0044] When J≥J2, the central control module selects the third preset adjustment coefficient N3 to adjust the extreme score A of the area;

[0045] When the central control module selects the i-th preset adjustment coefficient Ni to adjust the extreme score A of the area, i=1, 2, 3, and determines that the extreme score of the area after adjustment is A1, and sets A1=A*Ni.

[0046] Further, when the central control module selects the i-th preset adjustment coefficient Ni to adjust the extreme score A of the region, and determines that the extreme score of the region after adjustment is A1, it includes:

[0047] The central control module is also used to obtain the real-time air turbidity H of the area, and the central control module is also used to compare the real-time air turbidity H with the preset air turbidity, and select a corresponding correction coefficient according to the comparison result to correct the adjusted extreme score A1 of the area;

[0048] The central control module is further used to preset a first preset air turbidity H1 and a second preset air turbidity H2, and the central control module is further used to preset a first preset correction coefficient M1, a second preset correction coefficient M2 and a third preset correction coefficient M3, and H1<H2, 0.5<M1<M2<M3<1;

[0049] When H

[0050] When H1≤H<H2, the central control module selects the second preset correction coefficient M2 to correct the extreme score A1 of the area;

[0051] When H≥H2, the central control module selects the third preset correction coefficient M3 to correct the extreme score A1 of the area after adjustment;

[0052] When the central control module selects the extreme score A1 of the area after correction and adjustment by the i-th preset correction coefficient Mi, i=1, 2, 3, and determines that the extreme score of the area after correction is A2, and sets A2=A1*M i.

[0053] Furthermore, when the alarm module is used to determine the weather extreme level of each area according to the extreme score, it includes:

[0054] The alarm module is also used to obtain the extreme score A2 of the area, and determine the weather extreme level of the area according to the relationship between the extreme score A2 of the area and the preset extreme score;

[0055] Wherein, the alarm module is further used to preset a first preset extreme score C1 and a second preset extreme score C2, and C1<C2;

[0056] When A2≤C1, the alarm module determines that the extreme weather level in the area is low;

[0057] When C1<A2≤C2, the alarm module determines that the extreme weather level in the area is medium;

[0058] When A2>C2, the alarm module determines that the extreme weather level in the area is high;

[0059] Moreover, low level < intermediate level < advanced level.​

[0060] Compared with the prior art, the beneficial effect of the present invention is that: through the data acquisition module, the system can make full use of the historical weather information in the database, extract various extreme weather features from it, and then establish various extreme weather samples. This step provides sufficient training data for the system, so that it has the ability to identify and predict different extreme weather phenomena. Secondly, the cloud layer analysis module obtains satellite cloud image data in real time, and the system can timely discover and respond to changes, effectively improving the real-time and accuracy of monitoring. The classification module, as a key part, can divide the satellite cloud image into regions according to city information, and establish a model according to the characteristics in the historical weather information, so as to accurately determine the weather conditions in each region. This regionalized monitoring method enables the system to more accurately formulate early warnings and response measures. At the same time, the environmental information acquisition module is responsible for obtaining environmental information of each region, such as temperature, humidity, wind speed, etc., which is crucial for evaluating weather conditions. By comprehensively considering environmental information, the system can more comprehensively evaluate weather conditions, thereby improving the accuracy and reliability of monitoring. At the same time, as the core part of the system, the central control module gives extreme scores to weather conditions based on environmental information in each area. This scoring system can more objectively judge the severity of weather conditions and provide an important reference for subsequent early warning and decision-making. Finally, the alarm module sends corresponding alarm information based on the extreme weather level. When the weather conditions are more serious, it sends information to the smart terminal in a timely manner to remind the public to take necessary precautions, thereby effectively reducing the impact of extreme weather events on society.

[0061] On the other hand, the present application also provides an extreme weather monitoring method based on big data, including:

[0062] Collect historical weather information, extract characteristics of each extreme weather type in the historical weather information, and establish samples of each extreme weather type;

[0063] Receiving a satellite cloud image and extracting characteristic information of the satellite cloud image;

[0064] Dividing the satellite cloud image into regions based on city information, and determining the weather conditions of each region according to the relationship between the characteristic information of the cloud image of each region and the types in each extreme weather sample;

[0065] Acquiring environmental information of each of the areas, the environmental information including: temperature, humidity, wind speed, and air turbidity;

[0066] Assessing the extreme weather conditions of each of the areas based on the environmental information of each of the areas;

[0067] The weather extreme level of each of the areas is determined according to the extreme score, and warning information is sent according to the weather extreme level.

[0068] It can be understood that the extreme weather monitoring method and system based on big data of the present invention have the same beneficial effects and will not be elaborated on. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0070] Figure 1 A structural block diagram of an extreme weather monitoring system based on big data provided by an embodiment of the present invention;

[0071] Figure 2 A flowchart of an extreme weather monitoring method based on big data provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0072] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features described in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0073] like Figure 1As shown, in some embodiments of the present application, this embodiment provides an extreme weather monitoring system based on big data, including: a data acquisition module, a cloud analysis module, a classification module, an environmental information acquisition module, a central control module and an alarm module. The data acquisition module is electrically connected to the database, and the data acquisition module is used to collect historical weather information in the database, and extract the characteristics of each extreme weather type in the historical weather information, and establish each extreme weather sample; the cloud analysis module is used to receive satellite cloud images, and extract characteristic information of satellite cloud images; the classification module is electrically connected to the data acquisition module and the cloud analysis module respectively, and the classification module is used to divide the satellite cloud images into regions based on city information, and determine the weather conditions of each region according to the relationship between the characteristic information of the cloud images of each region and the types in each extreme weather sample; the environmental information acquisition module is electrically connected to the environmental monitoring station of each region, and the environmental information acquisition module is used to obtain environmental information of each region, and the environmental information Including: temperature, humidity, wind speed and air turbidity; the central control module is electrically connected to the classification module and the environmental information acquisition module respectively, and the central control module is used to make extreme scores for the weather conditions in each area according to the environmental information of each area; the alarm module is electrically connected to the central control module, and the alarm module is used to determine the extreme weather level of each area according to the extreme score, and send alarm information according to the extreme weather level, wherein: when the extreme weather level of the area is low, the alarm module is used to send the weather conditions and extreme weather level of the area to the Meteorological Observation Bureau; when the extreme weather level of the area is medium or high, the alarm module is used to send the weather conditions and extreme weather level of the area to each smart terminal in the area.

[0074] It can be seen that, first, the data acquisition module obtains historical weather information through connection with the database, extracts various extreme weather features, establishes various extreme weather samples, and provides rich training data for the system. The cloud layer analysis module receives satellite cloud images and extracts feature information to achieve real-time monitoring of weather conditions. The classification module divides the satellite cloud images by region and establishes a model based on the features in the historical weather information to accurately determine the weather conditions in each region. The environmental information acquisition module obtains environmental information of each region, such as temperature, humidity, wind speed, etc., which provides an important basis for subsequent weather condition scoring. The central control module scores the weather conditions according to the environmental information of each region, which provides a basis for subsequent early warning. Finally, the alarm module sends corresponding alarm information according to the extreme level of weather, ensuring the real-time and accuracy of weather monitoring.

[0075] It is understandable that through the collaborative operation of the data acquisition module and the cloud analysis module, it is possible to make full use of historical weather information and real-time satellite cloud images to achieve accurate monitoring and prediction of extreme weather conditions. Secondly, the classification module combines historical weather data and real-time satellite images to achieve accurate classification of weather conditions in different regions, improving the regionality and accuracy of monitoring. The environmental data obtained by the environmental information acquisition module provides the system with more comprehensive background information, which helps to more accurately assess weather conditions. The central control module scores the weather based on environmental information, providing an important reference for subsequent early warning decisions. Finally, the alarm module sends early warning information to relevant departments and smart terminals in a timely manner based on the scoring results, which helps the public take timely response measures and minimize the losses and impacts that may be caused by extreme weather events.

[0076] In some embodiments of the present application, the data acquisition module is used to collect historical weather information in the database, and extract the characteristics of each extreme weather type in the historical weather information. When establishing each extreme weather sample, it includes: the data acquisition module is used to obtain the cloud height, cloud thickness and cloud movement direction of each extreme weather type in the historical weather information, and the data acquisition module is also used to grayscale the cloud map of each extreme weather type and obtain the grayscale of the grayscale cloud map. The data acquisition module is also used to divide each extreme weather type into a number of extreme weather samples Q based on the matrix method according to the weather type, Q = (Q1, Q2, ...Qi). The data acquisition module is also used to obtain the cloud height, cloud thickness, cloud movement direction and cloud map grayscale change ratio in each extreme weather sample Q.

[0077] In some embodiments of the present application, when the classification module is used to determine the weather conditions of each region based on the relationship between the characteristic information of the cloud map of each region and the types in each extreme weather sample, it includes: the classification module is also used to obtain the real-time thickness of the cloud layer, the real-time height of the cloud layer, and the real-time moving speed of the cloud layer in the characteristic information of the satellite cloud map of the region. The classification module is also used to grayscale the satellite cloud map and obtain the real-time grayscale of the satellite cloud map. The classification module is also used to determine the weather type of the region based on the relationship between the real-time thickness of the cloud layer, the real-time height of the cloud layer, the real-time moving speed of the cloud layer, and the real-time grayscale of the satellite cloud map and the cloud height, cloud thickness and cloud movement direction of each extreme weather sample Q and the grayscale of the cloud map, wherein: if the real-time thickness of the cloud layer, the real-time height of the cloud layer, the real-time moving speed of the cloud layer, and the real-time grayscale of the satellite cloud map are consistent with the cloud height, cloud thickness and cloud movement direction of the extreme weather sample Q and the grayscale of the cloud map, the classification module determines that the weather type of the region is the weather type of the extreme weather sample Q. If any of the real-time thickness of the clouds, the real-time height of the clouds, the real-time moving speed of the clouds and the real-time grayscale of the satellite cloud image are inconsistent with the cloud height, cloud thickness, cloud movement direction and cloud image grayscale of the extreme weather sample Q, the classification module obtains the change ratio of the real-time thickness of the clouds, the real-time height of the clouds, the real-time moving speed of the clouds and the real-time grayscale of the satellite cloud image within the preset period of time in the area, and determines the weather type of the area based on the change ratio of the real-time thickness of the clouds, the real-time height of the clouds, the real-time moving speed of the clouds and the real-time grayscale of the satellite cloud image within the preset period of time.

[0078] It can be seen that, first, the data acquisition module obtains the cloud height, cloud thickness and cloud movement direction of various extreme weather types in the historical weather information, and grayscales the cloud images of each extreme weather type to obtain the grayscale of the grayscale cloud image. Subsequently, the data acquisition module divides various extreme weather types into several extreme weather samples according to the weather type. The classification module undertakes further tasks. It obtains the real-time grayscale of the satellite cloud image based on the characteristic information of the satellite cloud image of each region, including the real-time thickness of the cloud layer, the real-time height of the cloud layer and the real-time moving speed of the cloud layer, and compares it with the historical sample data. If the real-time data is consistent with the historical sample data, the classification module determines that the weather type of the region is the type of the historical sample. If there is an inconsistency, the classification module makes an inferential judgment based on the change ratio of the real-time data to determine the weather type of the region. In this process, by comparing the relationship between the real-time data and the historical sample data, the system realizes the accurate judgment of the regional weather type, thereby improving the accuracy and practicality of weather monitoring.

[0079] It is understandable that through the grayscale processing of the data acquisition module and the establishment of historical weather samples, the system can accurately obtain historical extreme weather information and establish a sample library, providing a sufficient data basis for subsequent extreme weather monitoring. Secondly, the classification module can quickly and accurately determine the weather type of each region through the analysis and comparison of real-time satellite cloud images, thereby improving the accuracy and real-time nature of monitoring. This comprehensive analysis method based on historical data and real-time data helps to timely discover and respond to extreme weather events, minimize the possible losses and impacts, and protect the lives and property of the public.

[0080] In some embodiments of the present application, when the classification module obtains the change ratio of the real-time cloud thickness, the real-time cloud height, the real-time cloud movement speed and the real-time grayscale of the satellite cloud image within a preset time period in the area, and determines the weather type of the area according to the change ratio of the real-time cloud thickness, the real-time cloud height, the real-time cloud movement speed and the real-time grayscale of the satellite cloud image within the preset time period, it includes: the classification module also determines the weather type of the area according to the relationship between the change ratio of the real-time cloud thickness, the real-time cloud height, the real-time cloud movement speed and the real-time grayscale of the satellite cloud image within the preset time period and the change ratio of the cloud height, cloud thickness, cloud movement direction and cloud image grayscale in each extreme weather sample Q, wherein: if the change ratio of the real-time cloud thickness, the real-time cloud height, the real-time cloud movement speed and the real-time grayscale of the satellite cloud image within the preset time period is consistent with the change ratio of the cloud height, cloud thickness, cloud movement direction and cloud image grayscale in the extreme weather sample Q, the classification module determines that the weather type of the area is the weather type of the extreme weather sample Q. If the change ratio of the real-time cloud thickness, real-time cloud height, real-time cloud movement speed and real-time grayscale of the satellite cloud image within the preset time period is inconsistent with the change ratio of the cloud height, cloud thickness, cloud movement direction and cloud image grayscale in each extreme weather sample Q, the classification module will establish a new extreme weather sample based on the real-time cloud thickness, real-time cloud height, real-time cloud movement speed and real-time grayscale of the satellite cloud image within the preset time period of the region and the change ratio of the real-time cloud thickness, real-time cloud height, real-time cloud movement speed and real-time grayscale of the satellite cloud image within the preset time period of the region.

[0081] It can be seen that the classification module compares the real-time parameters within the preset time period with the corresponding parameters of each extreme weather sample. If the two are consistent, the weather type of the area is determined to be the type of the extreme weather sample. This matching can be achieved by comparing the changing trends of real-time data and historical sample data to ensure consistency with historical data. If the real-time parameters within the preset time period are inconsistent with the parameters of each extreme weather sample, the classification module will establish a new extreme weather sample based on the change ratio of the real-time parameters and the parameters within the preset time period of the region. This method fully considers the relationship between real-time parameters and historical samples, and realizes accurate judgment of regional weather types through comparison and analysis. At the same time, by establishing new extreme weather samples, the sample library is continuously enriched and improved, and the adaptability and accuracy of the system are improved. The application of this technical principle can effectively improve the accuracy and reliability of the extreme weather monitoring system, and provide more reliable technical support for responding to extreme weather events.

[0082] Specifically, assume that the classification module receives real-time parameter data within a preset period: the real-time thickness of the cloud layer is 2000 meters, the real-time height of the cloud layer is 5000 meters, the real-time moving speed of the cloud layer is 20 kilometers per hour, and the real-time grayscale change ratio of the satellite cloud image is 0.8. Multiple extreme weather samples have been established in the system, and one of the samples Q contains the following parameters: the average cloud height is 5500 meters, the average cloud thickness is 1800 meters, the cloud movement direction is northeast, the average grayscale of the satellite cloud image is 0.75, and the change ratio is 0.85. First, the classification module compares the real-time parameters within the preset period with the sample Q. In this example, the real-time data deviates slightly from the cloud height and thickness of the sample Q, but the real-time grayscale change ratio of the satellite cloud image is quite close to the change ratio in the sample Q. Therefore, it can be preliminarily inferred that the relationship between the real-time data and the sample Q is not completely consistent. Next, the classification module will establish a new extreme weather sample based on the change ratio of the real-time parameters and the parameter conditions within the preset period. For example, if the system does not yet contain samples similar to real-time parameters, the classification module may treat this set of parameter values ​​as a new extreme weather sample and mark it as sample Q2. This sample can help the system better understand and identify similar weather conditions and further improve the sample library. Through such example analysis, it can be clearly demonstrated how the classification module determines the weather type of the region based on the relationship between real-time data and historical sample data, and establishes new extreme weather samples when necessary, thereby improving the system's ability to accurately monitor extreme weather events.

[0083] In some embodiments of the present application, when the central control module is used to perform extreme scoring on the weather conditions of each area according to the environmental information of each area, the central control module is also used to obtain the temperature difference L and humidity difference K of the area. The central control module is also used to obtain the extreme score of the area according to the temperature difference L and the humidity difference K, and based on the formula, the formula is as follows:

[0084] A=(L*z1)+(K*z2).

[0085] Among them, A is the extreme score of the area, z1 and z2 are weight coefficients, and the sum of z1 and z2 is 1.

[0086] In some embodiments of the present application, when the central control module is further used to obtain the temperature difference L and humidity difference K of the region, it includes: the central control module is also used to obtain the real-time temperature l and real-time humidity k of the region, and the central control module is also used to determine the temperature difference L and humidity difference K of the region according to the relationship between the real-time temperature l and the real-time humidity k and the preset temperature threshold interval and humidity threshold interval, wherein: when the real-time temperature l is within the preset temperature threshold interval and the real-time humidity k is within the preset humidity threshold interval, the central control module determines that the temperature difference L of the region is 0 and the humidity difference K of the region is 0. When the real-time temperature l is lower than the preset temperature threshold interval and the real-time humidity k is lower than the preset humidity threshold interval, the central control module determines that the temperature difference L of the region is l 0-l and the humidity difference K of the region is k0-k, wherein l 0 is the starting temperature of the preset temperature threshold interval and k0 is the starting humidity of the preset temperature threshold interval. When the real-time temperature l is higher than the preset temperature threshold interval and the real-time humidity k is higher than the preset humidity threshold interval, the central control module determines the temperature difference L=ll 1 in the area and the humidity difference K=k-k1 in the area, where l 1 is the end temperature of the preset temperature threshold interval and k1 is the end humidity of the preset humidity threshold interval.

[0087] It can be seen that the central control module obtains the real-time temperature and humidity of the area, and compares them with the preset temperature threshold and humidity threshold to determine the temperature difference L and humidity difference K. According to the relationship between the preset temperature threshold interval and the humidity threshold interval, when the real-time temperature and humidity are within the corresponding threshold interval, the temperature difference and humidity difference are both 0; when the real-time temperature or humidity is lower than the preset threshold interval, the temperature difference and humidity difference are respectively the difference between the starting value of the preset threshold interval and the real-time value; when the real-time temperature or humidity is higher than the preset threshold interval, the temperature difference and humidity difference are respectively the difference between the real-time value and the end value of the preset threshold interval. Then, the central control module calculates the extreme score of the area according to the temperature difference L and the humidity difference K, combined with the preset weight coefficients z1 and z2, through the formula A=(Lz1)+(Kz2). Among them, the weight coefficients z1 and z2 represent the relative importance of the temperature difference and humidity difference to the extreme score, and their sum is 1. Through this method, the system can comprehensively consider the impact of temperature and humidity on the extreme degree of weather according to the temperature and humidity conditions in each area, provide quantitative assessments of weather conditions in different areas, and thus more accurately identify and evaluate extreme weather events.

[0088] Specifically, assume that the central control module receives the real-time temperature of a certain area as 30 degrees Celsius and the humidity as 80%. According to the temperature and humidity threshold intervals preset by the system, it is assumed that the preset temperature threshold interval is 25 degrees Celsius to 35 degrees Celsius, and the humidity threshold interval is 70% to 90%. First, the central control module compares the real-time temperature and humidity with the preset temperature and humidity thresholds. In this example, the real-time temperature is within the preset temperature threshold interval, and the real-time humidity is also within the preset humidity threshold interval. Therefore, according to the preset, the temperature difference and the humidity difference are both 0. Then, the central control module calculates the extreme score of the area according to the temperature difference and the humidity difference, as well as the preset weight coefficients z1 and z2, by formula A=(Lz1)+(Kz2). Assume that the weight coefficients z1 and z2 are 0.6 and 0.4 respectively. Substituting the actual values ​​into the formula, the extreme score A=(00.6)+(00.4)=0 is obtained. This means that in this case, the weather conditions in the area are rated as not extreme. Because the real-time temperature and humidity are within the preset normal range and do not exceed the threshold, the extreme score is 0. Through this example, we can see how the central control module calculates the extreme score based on the real-time environmental information and comprehensively considers the impact of temperature and humidity on weather conditions through weight coefficients, thus providing a quantitative method to evaluate the weather conditions in the area.

[0089] In some embodiments of the present application, when the central control module determines the extreme score A of the region, it includes: the central control module is also used to obtain the real-time wind speed J of the region, the central control module is also used to compare the real-time wind speed J with the preset wind speed, and select the corresponding adjustment coefficient to adjust the extreme score A of the region according to the comparison result. Wherein: the central control module is also used to pre-set the first preset wind speed J1 and the second preset wind speed J2, and the central control module is also used to pre-set the first preset adjustment coefficient N1, the second preset adjustment coefficient N2 and the third preset adjustment coefficient N3, and J1<J2, N1<N2<N3<1. When J<J1, the central control module selects the first preset adjustment coefficient N1 to adjust the extreme score A of the region. When J1≤J<J2, the central control module selects the second preset adjustment coefficient N2 to adjust the extreme score A of the region. When J≥J2, the central control module selects the third preset adjustment coefficient N3 to adjust the extreme score A of the region. When the central control module selects the extreme score A of the adjustment area of ​​the i-th preset adjustment coefficient Ni, i=1, 2, 3, and determines that the extreme score of the adjusted area is A1, and sets A1=A*N i.

[0090] In some embodiments of the present application, when the central control module selects the extreme score A of the adjusted area of ​​the i-th preset adjustment coefficient Ni and determines that the extreme score of the adjusted area is A1, it includes: the central control module is also used to obtain the real-time air turbidity H of the area, the central control module is also used to compare the real-time air turbidity H with the preset air turbidity, and select the corresponding correction coefficient to correct the extreme score A1 of the adjusted area according to the comparison result: wherein the central control module is also used to pre-set the first preset air turbidity H1 and the second preset air turbidity H2, the central control module is also used to pre-set the first preset correction coefficient M1, the second preset correction coefficient M2 and the third preset correction coefficient M3, and H1<H2, 0.5<M1<M2<M3<1. When H

[0091] It can be seen that the central control module obtains the real-time wind speed J and real-time air turbidity H of the area, and compares them with the pre-set wind speed threshold and air turbidity threshold. According to the comparison results, the central control module selects the corresponding adjustment coefficient or correction coefficient to adjust or correct the extreme score of the area.

[0092] ​Specifically, the central control module pre-sets two wind speed thresholds J1 and J2, and three adjustment coefficients N1, N2 and N3; it also pre-sets two air turbidity thresholds H1 and H2, and three correction coefficients M1, M2 and M3. When the real-time wind speed or air turbidity is within the corresponding threshold range, the central control module selects the corresponding adjustment coefficient or correction coefficient to adjust or correct the extreme score. According to the pre-set rules, when the real-time wind speed is less than J1, select N1 for adjustment; when the real-time wind speed is between J1 and J2, select N2 for adjustment; when the real-time wind speed is greater than or equal to J2, select N3 for adjustment. The same rules apply to the case of air turbidity.

[0093] It is understandable that by selecting the adjustment coefficient and the correction coefficient, the central control module can dynamically adjust the extreme score according to the real-time environmental information, so that it can more accurately reflect the actual weather conditions in the area. This technical principle can improve the accuracy of the system's recognition and assessment of extreme weather, help to take corresponding response measures in a timely manner, and protect the safety of people's lives and property.

[0094] In some embodiments of the present application, when the alarm module is used to determine the extreme weather level of each area according to the extreme score, it includes: the alarm module is also used to obtain the extreme score A2 of the area, and determine the extreme weather level of the area according to the relationship between the extreme score A2 of the area and the preset extreme score. Wherein: the alarm module is also used to pre-set a first preset extreme score C1 and a second preset extreme score C2, and C1<C2. When A2≤C1, the alarm module determines that the extreme weather level of the area is low. When C1<A2≤C2, the alarm module determines that the extreme weather level of the area is medium. When A2>C2, the alarm module determines that the extreme weather level of the area is high. And, low level<medium level<high level.

[0095] It can be seen that the alarm module obtains the extreme score A2 of the area and compares it with two preset extreme score thresholds C1 and C2. According to the comparison result, the alarm module determines the weather extreme level of the area.

[0096] Specifically, the alarm module pre-sets two extreme score thresholds C1 and C2, and C1 is less than C2. According to the pre-set rules, when the extreme score A2 of the area is less than or equal to C1, the weather extreme level of the area is determined to be low; when A2 is greater than C1 and less than or equal to C2, the weather extreme level of the area is determined to be medium; when A2 is greater than C2, the weather extreme level of the area is determined to be high. And according to the preset extreme level relationship, the low level is less than the medium level and less than the high level.

[0097] It is understandable that by setting different extreme score thresholds, the alarm module can quickly determine the extreme weather level of the area based on the real-time extreme score, and thus issue corresponding warning information to relevant departments and the public in a timely manner. This technical principle can effectively improve the accuracy and timeliness of extreme weather warnings, help people take precautions and respond, and reduce possible losses and harm.

[0098] In the above embodiment, through the data acquisition module, the system can make full use of the historical weather information in the database, extract various extreme weather features from it, and then establish various extreme weather samples. This step provides the system with sufficient training data, so that it has the ability to identify and predict different extreme weather phenomena. Secondly, the cloud layer analysis module obtains satellite cloud image data in real time, and the system can promptly discover and respond to changes, effectively improving the real-time and accuracy of monitoring. The classification module, as a key part, can divide the satellite cloud image into regions according to city information, and establish a model based on the characteristics in the historical weather information, so that the weather conditions in each region can be accurately determined. This regionalized monitoring method enables the system to more accurately formulate early warnings and response measures. At the same time, the environmental information acquisition module is responsible for obtaining environmental information of each region, such as temperature, humidity, wind speed, etc., which is crucial for assessing weather conditions. By comprehensively considering environmental information, the system can more comprehensively assess weather conditions, thereby improving the accuracy and reliability of monitoring. At the same time, the central control module, as the core part of the system, performs extreme scoring on weather conditions based on environmental information in each region. This scoring system can more objectively judge the severity of weather conditions, providing an important reference for subsequent early warnings and decision-making. Finally, the alarm module sends corresponding alarm information according to the extreme weather level. When the weather conditions are serious, it sends information to the smart terminal in a timely manner to remind the public to take necessary preventive measures, thereby effectively reducing the impact of extreme weather events on society.

[0099] like Figure 2 As shown, in another preferred embodiment based on the above embodiment, this embodiment provides an extreme weather monitoring method based on big data, including:

[0100] Step S100: Collect historical weather information, extract characteristics of each extreme weather type in the historical weather information, and establish each extreme weather sample.

[0101] Step S200: receiving a satellite cloud image and extracting characteristic information of the satellite cloud image.

[0102] Step S300: Divide the satellite cloud map into regions based on city information, and determine the weather conditions in each region based on the relationship between the characteristic information of the cloud map in each region and the types in each extreme weather sample.

[0103] Step S400: Acquire environmental information of each area, the environmental information including temperature, humidity, wind speed and air turbidity, and perform extreme scoring on the weather conditions of each area based on the environmental information of each area.

[0104] Step S500: determine the weather extreme level of each area according to the extreme score, and send warning information according to the weather extreme level.

[0105] It can be understood that the extreme weather monitoring method and system based on big data of the present invention have the same beneficial effects and will not be elaborated on.

[0106] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0107] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0108] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0109] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0110] Finally, it should be noted that 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 above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. An extreme weather monitoring system based on big data, characterized in that: include: A data acquisition module is electrically connected to the database, and is used to collect historical weather information in the database, extract characteristics of each extreme weather type in the historical weather information, and establish each extreme weather sample; A cloud layer analysis module, used to receive satellite cloud images and extract characteristic information of the satellite cloud images; A classification module, electrically connected to the data acquisition module and the cloud layer analysis module, respectively, and configured to divide the satellite cloud image into regions based on city information, and determine the weather conditions of each region according to the relationship between the characteristic information of the cloud image of each region and the types in each extreme weather sample; An environmental information acquisition module is electrically connected to the environmental monitoring station of each of the areas, and is used to acquire environmental information of each of the areas, wherein the environmental information includes: temperature, humidity, wind speed, and air turbidity; A central control module, electrically connected to the classification module and the environmental information acquisition module, respectively, and configured to perform an extreme score on the weather conditions of each of the areas according to the environmental information of each of the areas; an alarm module, electrically connected to the central control module, and configured to determine the extreme weather level of each of the regions according to the extreme score, and send alarm information according to the extreme weather level; Wherein, when the extreme weather level in the area is low, the alarm module is used to send the weather conditions in the area and the extreme weather level to the Meteorological Observation Bureau; When the extreme weather level in the area is medium or high, the alarm module is used to send the weather conditions in the area and the extreme weather level to each smart terminal in the area.

2. The extreme weather monitoring system based on big data according to claim 1, characterized in that: The data collection module is used to collect historical weather information in the database, and extract the characteristics of each extreme weather type in the historical weather information, and establish each extreme weather sample, including: The data acquisition module is used to obtain the cloud height, cloud thickness and cloud movement direction of each extreme weather type in the historical weather information. The data acquisition module is also used to grayscale the cloud image of each extreme weather type and obtain the grayscale of the grayscaled cloud image; The data acquisition module is also used to divide each extreme weather type into a number of extreme weather samples Q based on a matrix method according to the weather type, where Q=(Q1, Q2, ...Qi); The data acquisition module is also used to obtain the cloud height, cloud thickness, cloud movement direction and cloud image grayscale change ratio in each extreme weather sample Q.

3. The extreme weather monitoring system based on big data as claimed in claim 2, characterized in that: The classification module is used to determine the weather conditions of each area according to the relationship between the characteristic information of the cloud map of each area and the types in each extreme weather sample, including: The classification module is also used to obtain the real-time thickness of the cloud layer, the real-time height of the cloud layer and the real-time moving speed of the cloud layer from the characteristic information of the satellite cloud image of the area; The classification module is also used to grayscale the satellite cloud image and obtain the real-time grayscale of the satellite cloud image; The classification module is also used to determine the weather type of the area according to the relationship between the real-time cloud thickness, real-time cloud height, real-time cloud movement speed and real-time grayscale of the satellite cloud image and the cloud height, cloud thickness and cloud movement direction of each extreme weather sample Q and the cloud image grayscale, wherein: If the real-time cloud thickness, real-time cloud height, real-time cloud movement speed and real-time grayscale of the satellite cloud image are consistent with the cloud height, cloud thickness and cloud movement direction and cloud image grayscale of the extreme weather sample Q, the classification module determines that the weather type of the area is the weather type of the extreme weather sample Q; If any of the real-time cloud thickness, real-time cloud height, real-time cloud movement speed and real-time grayscale of the satellite cloud image is inconsistent with the cloud height, cloud thickness, cloud movement direction and cloud image grayscale of the extreme weather sample Q, the classification module obtains the change ratio of the real-time cloud thickness, real-time cloud height, real-time cloud movement speed and real-time grayscale of the satellite cloud image within the preset time period of the area, and determines the weather type of the area according to the change ratio of the real-time cloud thickness, real-time cloud height, real-time cloud movement speed and real-time grayscale of the satellite cloud image within the preset time period.

4. The extreme weather monitoring system based on big data as claimed in claim 3, characterized in that: The classification module obtains the change ratio of the real-time thickness of the cloud layer, the real-time height of the cloud layer, the real-time moving speed of the cloud layer, and the real-time grayscale of the satellite cloud image within the preset time period of the region, and determines the weather type of the region according to the change ratio of the real-time thickness of the cloud layer, the real-time height of the cloud layer, the real-time moving speed of the cloud layer, and the real-time grayscale of the satellite cloud image within the preset time period, including: The classification module also determines the weather type of the area according to the relationship between the change ratio of the real-time cloud thickness, real-time cloud height, real-time cloud movement speed and real-time grayscale of the satellite cloud image within the preset time period and the change ratio of the cloud height, cloud thickness, cloud movement direction and cloud image grayscale in each extreme weather sample Q, wherein: If the change ratio of the real-time cloud thickness, real-time cloud height, real-time cloud movement speed and real-time grayscale of the satellite cloud image within the preset time period is consistent with the change ratio of the cloud height, cloud thickness, cloud movement direction and cloud image grayscale in the extreme weather sample Q, the classification module determines that the weather type of the area is the weather type of the extreme weather sample Q; If the change ratio of the real-time cloud thickness, real-time cloud height, real-time cloud movement speed and real-time grayscale of the satellite cloud image within the preset time period is inconsistent with the change ratio of the cloud height, cloud thickness, cloud movement direction and cloud image grayscale in each of the extreme weather samples Q, the classification module establishes a new extreme weather sample based on the real-time cloud thickness, real-time cloud height, real-time cloud movement speed and real-time grayscale of the satellite cloud image within the preset time period of the area and the change ratio of the real-time cloud thickness, real-time cloud height, real-time cloud movement speed and real-time grayscale of the satellite cloud image within the preset time period of the area.

5. The extreme weather monitoring system based on big data as claimed in claim 4, characterized in that: The central control module is used to perform extreme scoring on the weather conditions of each of the areas according to the environmental information of each of the areas, including: The central control module is also used to obtain the temperature difference L and humidity difference K of the area; The central control module is further used to obtain the extreme score of the area according to the temperature difference L and the humidity difference K based on a formula, and the formula is as follows: A=(L*z1)+(K*z2); Wherein, A is the extreme score of the area, z1 and z2 are weight coefficients, and the sum of z1 and z2 is 1.

6. The extreme weather monitoring system based on big data according to claim 5, characterized in that: When the central control module is further used to obtain the temperature difference L and humidity difference K of the area, it includes: The central control module is also used to obtain the real-time temperature l and real-time humidity k of the area, and the central control module is also used to determine the temperature difference L and humidity difference K of the area according to the relationship between the real-time temperature l and real-time humidity k and the preset temperature threshold interval and humidity threshold interval, wherein: When the real-time temperature l is within the preset temperature threshold interval, and the real-time humidity k is within the preset humidity threshold interval, the central control module determines that the temperature difference L of the area is 0, and the humidity difference K of the area is 0; When the real-time temperature l is lower than the preset temperature threshold interval, and the real-time humidity k is lower than the preset humidity threshold interval, the central control module determines the temperature difference L of the area = l 0-l, and the humidity difference K of the area = k0-k, where l 0 is the starting temperature of the preset temperature threshold interval, and k0 is the starting humidity of the preset temperature threshold interval; When the real-time temperature l is higher than the preset temperature threshold interval and the real-time humidity k is higher than the preset humidity threshold interval, the central control module determines that the temperature difference L of the area is L=ll 1 and the humidity difference K of the area is K-k1, wherein l 1 is the end temperature of the preset temperature threshold interval and k1 is the end humidity of the preset humidity threshold interval.

7. The extreme weather monitoring system based on big data according to claim 5, characterized in that: When the central control module determines the extreme score A of the area, it includes: The central control module is also used to obtain the real-time wind speed J of the area, and the central control module is also used to compare the real-time wind speed J with the preset wind speed, and select a corresponding adjustment coefficient according to the comparison result to adjust the extreme score A of the area; The central control module is further used to preset a first preset wind speed J1 and a second preset wind speed J2, and the central control module is further used to preset a first preset adjustment coefficient N1, a second preset adjustment coefficient N2 and a third preset adjustment coefficient N3, and J1<J2, N1<N2<N3<1; When J<J1, the central control module selects the first preset adjustment coefficient N1 to adjust the extreme score A of the area; When J1≤J<J2, the central control module selects the second preset adjustment coefficient N2 to adjust the extreme score A of the area; When J≥J2, the central control module selects the third preset adjustment coefficient N3 to adjust the extreme score A of the area; When the central control module selects the i-th preset adjustment coefficient Ni to adjust the extreme score A of the area, i=1, 2, 3, and determines that the extreme score of the area after adjustment is A1, and sets A1=A*Ni.

8. The extreme weather monitoring system based on big data according to claim 7, characterized in that: When the central control module selects the i-th preset adjustment coefficient Ni to adjust the extreme score A of the area, and determines that the extreme score of the area after adjustment is A1, it includes: The central control module is also used to obtain the real-time air turbidity H of the area, and the central control module is also used to compare the real-time air turbidity H with the preset air turbidity, and select a corresponding correction coefficient according to the comparison result to correct the adjusted extreme score A1 of the area; The central control module is further used to preset a first preset air turbidity H1 and a second preset air turbidity H2, and the central control module is further used to preset a first preset correction coefficient M1, a second preset correction coefficient M2 and a third preset correction coefficient M3, and H1<H2, 0.5<M1<M2<M3<1; When H<H1, the central control module selects the first preset correction coefficient M1 to correct the extreme score A1 of the area; When H1≤H<H2, the central control module selects the second preset correction coefficient M2 to correct the extreme score A1 of the area; When H≥H2, the central control module selects the third preset correction coefficient M3 to correct the extreme score A1 of the area after adjustment; When the central control module selects the extreme score A1 of the area after correction and adjustment by the i-th preset correction coefficient Mi, i=1, 2, 3, and determines that the extreme score of the area after correction is A2, and sets A2=A1*Mi.

9. The extreme weather monitoring system based on big data according to claim 8, characterized in that: When the alarm module is used to determine the weather extreme level of each area according to the extreme score, it includes: The alarm module is also used to obtain the extreme score A2 of the area, and determine the weather extreme level of the area according to the relationship between the extreme score A2 of the area and the preset extreme score; Wherein, the alarm module is further used to preset a first preset extreme score C1 and a second preset extreme score C2, and C1<C2; When A2≤C1, the alarm module determines that the extreme weather level in the area is low; When C1<A2≤C2, the alarm module determines that the extreme weather level in the area is medium; When A2>C2, the alarm module determines that the extreme weather level in the area is high; Moreover, low level < intermediate level < advanced level.

10. A method for monitoring extreme weather based on big data, applicable to an extreme weather monitoring system based on big data as claimed in any one of claims 1 to 9, characterized in that: include: Collect historical weather information, extract characteristics of each extreme weather type in the historical weather information, and establish samples of each extreme weather type; Receiving a satellite cloud image and extracting characteristic information of the satellite cloud image; Dividing the satellite cloud image into regions based on city information, and determining the weather conditions of each region according to the relationship between the characteristic information of the cloud image of each region and the types in each extreme weather sample; Acquiring environmental information of each of the areas, the environmental information including: temperature, humidity, wind speed, and air turbidity; Assessing the extreme weather conditions of each of the areas based on the environmental information of each of the areas; The weather extreme level of each of the areas is determined according to the extreme score, and warning information is sent according to the weather extreme level.

Images