A meteorological and hydrological analysis and management cloud platform

Abstract

This invention relates to the field of data analysis and management technology, specifically a meteorological and hydrological analysis and management cloud platform. Firstly, it stores and manages data through meteorological and hydrological information storage units within a meteorological and hydrological data storage module. Then, it visualizes the data through a data retrieval module. In particular, a passive query unit automatically acquires abnormal data and retrieves relevant data, providing data support for anomaly detection. An anomaly analysis module acquires abnormal meteorological and hydrological characteristics and calculates risk characteristic indicators based on forest vegetation density to determine whether anomalies exist. Finally, a management module performs risk classification and assigns detection tasks to anomaly areas. This invention provides a meteorological and hydrological analysis and management cloud platform that achieves efficient monitoring and management of forest vegetation cover.

Description

Technical Field

[0001] This invention relates to the field of data analysis and management technology, specifically to a meteorological and hydrological analysis and management cloud platform. Background Technology

[0002] With the increasing frequency of global climate change and extreme weather events, forest fires and floods have become serious threats to the ecological environment and socio-economic development. Forests, as vital natural ecosystems, play a crucial role in maintaining carbon balance, regulating climate, and protecting biodiversity. However, forest fires and floods not only cause enormous losses of forest resources but can also trigger secondary disasters, threatening the lives and property of residents in surrounding areas.

[0003] Traditional forest fire and flood monitoring relies primarily on manual patrols and fixed monitoring stations. However, due to the widespread distribution of forests and complex terrain, this method is inefficient, has limited coverage, and struggles to capture early signs of sudden disasters. Furthermore, meteorological and hydrological conditions are key factors initiating fires and floods. For example, high temperatures, low humidity, and strong winds can easily lead to the spread of fires, while continuous rainfall and rising river levels can trigger floods. Therefore, relying on a single data source is insufficient to fully understand the dynamic changes in the forest environment. How to utilize advanced technologies, combined with meteorological and hydrological information, to achieve anomaly monitoring and rapid response in forest vegetation, thereby detecting forest disasters, has become a crucial issue that urgently needs to be addressed.

[0004] To address this, a cloud platform for meteorological and hydrological analysis and management is proposed. Summary of the Invention

[0005] The purpose of this invention is to provide a meteorological and hydrological analysis and management cloud platform to improve the efficiency of monitoring and managing forest vegetation cover. Firstly, the meteorological and hydrological data storage module stores and manages the data through meteorological and hydrological information storage units. Then, the data retrieval module visualizes the data, particularly the passive query unit which automatically acquires abnormal data and retrieves relevant information, providing data support for anomaly detection. The anomaly analysis module acquires abnormal meteorological and hydrological characteristics and calculates risk characteristic indicators based on forest vegetation density to determine whether anomalies exist. Finally, the management module performs risk classification and detection task allocation for abnormal areas, achieving efficient monitoring and management of forest vegetation cover.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A meteorological and hydrological analysis and management cloud platform includes:

[0008] The meteorological and hydrological data storage module includes a meteorological information storage unit and a hydrological information storage unit; wherein the meteorological information storage unit includes a meteorological hot data storage unit and a meteorological cold data storage unit, and the hydrological information storage unit includes a hydrological hot data storage unit and a hydrological cold data storage unit, and the data is sorted according to the forest vegetation density and the collection time to establish data priority.

[0009] Furthermore, the meteorological information storage unit is used to store data from all monitoring stations and sort the data according to a data priority structure based on forest vegetation density and collection time. The formula for calculating the data priority is:

[0010]

[0011] Among them, P i j Let αi represent the priority of the i-th meteorological data point from the j-th monitoring station, and α1 represent the weighting coefficient of forest vegetation. This indicates the number of forest vegetation pixels at the i-th monitoring station. Let S represent the total number of pixels at the j-th monitoring station, S represent the area represented by one pixel, α represent the weighting coefficient of sampling time, e represent the natural base, k represent the time decay coefficient, and t represent the time decay coefficient. now t represents the current time. i This indicates the collection time of the i-th data item;

[0012] Determine the storage location based on data priority and threshold:

[0013]

[0014] Among them, P threshold P represents the threshold. i This indicates the data priority of the i-th data item.

[0015] Furthermore, regarding the optimization of storage resources for meteorological and hydrological data, the allocation ratio is dynamically adjusted based on the importance of the data:

[0016]

[0017] Where R represents the ratio of storage resources for hot data to cold data, S h S represents the storage resources currently used by the hot data unit. t Represents the total storage resources, P′ m This indicates the data priority of the m-th hot data record, where M represents the number of hot data records, and P″ n This indicates the data priority of the nth data record, and N represents the total number of data records.

[0018] The data retrieval module includes an active query unit and a passive query unit. The active query unit includes querying based on keywords and displaying data according to priority. The passive query unit includes acquiring first meteorological information and first hydrological information collected by the data monitoring station based on event triggering; retrieving second meteorological information based on the first meteorological information; retrieving second hydrological information based on the first hydrological information; interactively retrieving third hydrological information based on the first meteorological information; and interactively retrieving third meteorological information based on the first hydrological information. It also constructs an abnormal meteorological data vector based on the first, second, and third meteorological information, and an abnormal hydrological data vector based on the first, second, and third hydrological information.

[0019] Furthermore, the active query unit also includes: the active query unit is used to receive keywords, time range and geographical range actively input by the user and perform queries, and to sort and display the priority of the optimization results based on forest vegetation area and density; the active query unit also includes: keyword retrieval and multi-condition cross-filtering, the multi-condition cross-filtering including supporting composite queries based on keywords, time range, monitoring station location and forest vegetation coverage.

[0020] Furthermore, the passive query unit also includes:

[0021] The formula for retrieving second meteorological information based on first meteorological information is:

[0022]

[0023] in, This indicates the second meteorological information. Indicates the first meteorological information, F weather The function represents meteorological characteristics, corr() represents the correlation function, and θ1 represents the first meteorological correlation threshold.

[0024] The formula for retrieving third-level hydrological information based on first-level meteorological information interaction is as follows:

[0025]

[0026] in, Indicates third hydrological information, F hydro Here, f() represents the hydrological characteristics, θ2 represents the first interaction threshold, and f2 represents the interaction function.

[0027] The formula for retrieving second hydrological information based on first hydrological information is:

[0028]

[0029] in, This indicates the second hydrological information. θ3 represents the first hydrological information, and θ3 represents the second hydrological correlation threshold.

[0030] The formula for retrieving third-level meteorological information based on first-level hydrological information interaction is as follows:

[0031]

[0032] in, θ4 represents the third meteorological information, and θ4 represents the second interaction threshold.

[0033] An anomaly analysis module is used to acquire the abnormal meteorological data vector and the abnormal hydrological data vector, extract features based on the temporal differences of the data, obtain abnormal meteorological features and abnormal hydrological features, and obtain risk feature indicators by combining forest vegetation density, and determine whether there is an anomaly based on the risk feature indicators.

[0034] Furthermore, the specific steps for constructing anomalous meteorological and hydrological characteristics include:

[0035] Obtain abnormal meteorological data vectors and extract abnormal hot data and abnormal cold data to obtain abnormal meteorological hot data components and abnormal meteorological cold data components; obtain the abnormal meteorological hot data components collected within several time windows and use a sliding window to calculate the data change amount between adjacent time periods to obtain an abnormal meteorological hot data change matrix; use a trend analysis model to extract features from the abnormal meteorological hot data change matrix to obtain abnormal meteorological hot data features; obtain the abnormal meteorological hot data features and the abnormal meteorological cold data components to obtain abnormal meteorological features.

[0036] Anomalous hydrological data vectors are acquired, and anomalous hot and cold data are extracted to obtain anomalous hydrological hot data components and anomalous hydrological cold data components. The anomalous hydrological hot data components collected within several time windows are acquired, and the data change between adjacent time periods is calculated using a sliding window to obtain an anomalous hydrological hot data change matrix. Features are extracted from the anomalous hydrological hot data change matrix using a trend analysis model to obtain anomalous hydrological hot data features. The anomalous hydrological hot data features and the anomalous hydrological cold data components are then acquired to obtain anomalous hydrological features.

[0037] Furthermore, the formula for calculating the risk characteristic indicators is as follows:

[0038]

[0039] Where Dan represents the risk characteristic index, ω1 represents the weighting coefficient of the abnormal meteorological characteristic, H represents the length of the abnormal meteorological characteristic, and x h The h-th component representing the anomalous meteorological characteristics, μ x σ represents the mean of normal meteorological data. xω represents the standard deviation of normal meteorological data, ω² represents the weighting coefficient of anomalous hydrological features, G represents the length of anomalous hydrological features, and y represents the standard deviation of normal meteorological data. g μ represents the g-th component of the anomalous hydrological characteristics. y σ represents the mean of normal hydrological data. y ω3 represents the standard deviation of normal hydrological data, ω3 represents the weighting coefficient of forest vegetation density, and ΔF represents the standard deviation of normal hydrological data. density This indicates the change in forest vegetation density.

[0040] The management module is used to classify risks based on risk characteristic indicators, and to assign tasks and track their status.

[0041] Furthermore, the steps of classifying risk characteristics based on risk indicators and allocating tasks and tracking status also include: acquiring abnormal risk indicators and classifying abnormal risk levels according to priority, and allocating detection time, detection personnel and detection tools according to the abnormal risk level and historical detection data.

[0042] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0043] 1. Data priority is designed by combining the proportion of vegetation pixels in the area where the monitoring station is located and the collection time of meteorological and hydrological data, and the data is sorted so that monitoring data in areas with high forest vegetation density can be processed more easily, which meets the actual needs of forest anomaly monitoring; by comparing data priority and threshold, high-priority data is stored in hot data units and low-priority data is stored in cold data units, so as to achieve reasonable allocation of storage resources and improve storage efficiency.

[0044] 2. Through the correlation and interactive retrieval mechanisms, dynamic correlation and interactive retrieval between meteorological and hydrological data are realized, enabling the rapid retrieval of relevant data and improving retrieval efficiency and accuracy. The hot and cold data components of the abnormal data vector are decomposed, enabling fine-grained data processing and helping to more accurately capture potential anomalies. Through sliding windows and trend analysis models, change matrices and trend features are extracted from time series data, which can better reflect the dynamic changes of meteorological and hydrological data and construct comprehensive risk characteristic indicators, thereby improving risk assessment capabilities.

[0045] 3. By integrating forest vegetation density into all aspects of the storage, retrieval, analysis, and management of meteorological and hydrological data, the cloud platform can more accurately identify high-risk areas, rationally allocate resources, improve the efficiency of anomaly monitoring and disaster prevention, demonstrate the deep integration of data and forest ecological characteristics, reflect the intelligence and innovation of the cloud platform, realize real-time monitoring and management of forest vegetation, and improve early warning efficiency. Attached Figure Description

[0046] Figure 1A schematic diagram of the structure of a meteorological and hydrological analysis and management cloud platform provided in an embodiment of the present invention;

[0047] Figure 2 This is a schematic diagram of the structure of the meteorological and hydrological data storage module provided in an embodiment of the present invention;

[0048] Figure 3 The flowchart for constructing abnormal meteorological features and abnormal hydrological features is provided for embodiments of the present invention. Detailed Implementation

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0050] Example 1

[0051] A company introduced a meteorological and hydrological analysis and management cloud platform provided by this invention during the process of monitoring and managing forest vegetation, in order to improve management efficiency. The structure of the cloud platform is as follows: Figure 1 As shown, the specific implementation method is as follows:

[0052] First, a vegetation remote sensing monitoring module was introduced into the cloud platform to acquire and process forest remote sensing image data, and obtain the forest vegetation density of the data monitoring station based on the pixels of the remote sensing image.

[0053] The structure of the meteorological and hydrological data storage module is as follows: Figure 2 As shown, the system is used to store meteorological and hydrological information, including a meteorological information storage unit and a hydrological information storage unit. The meteorological information storage unit includes a meteorological hot data storage unit and a meteorological cold data storage unit. The hydrological information storage unit includes a hydrological hot data storage unit and a hydrological cold data storage unit. The data is sorted according to the forest vegetation density of the data monitoring station and the collection time. Table 1 shows some of the hydrological information stored in the hydrological information storage unit.

[0054] Table 1. Partial Hydrological Information

[0055] Monitoring station number Hydrological thermal data Hydrological cold data A001 Water level: 5.3m, flow velocity: 2.1m / s, ... Average water level: 4.8m, average annual flow velocity: 1.9m / s, ... A002 Water level: 3.8m, flow velocity: 1.5m / s, ... Average water level: 3.5m, average annual flow velocity: 1.4m / s, ... A003 Water level: 6.7m, flow velocity: 2.8m / s, ... Average water level: 6.2m, average annual flow velocity: 2.5m / s, ... A004 Water level: 4.1m, flow velocity: 1.8m / s, ... Average water level: 3.9m, average annual flow velocity: 1.6m / s, ... A005 Water level: 5.9m, flow velocity: 2.3m / s, ... Average water level: 5.5m, average annual flow velocity: 2.1m / s, ...

[0056] Furthermore, the meteorological information storage unit is specifically used to store data from all monitoring stations, and dynamically sorts all the data based on a data priority constructed using forest vegetation density and collection time, which facilitates subsequent data display and retrieval. The formula for calculating the data priority is:

[0057]

[0058] Among them, P i j α represents the data priority of the i-th meteorological data point from the j-th monitoring station, and α1 represents the weighting coefficient of forest vegetation. This represents the number of forest vegetation pixels at the j-th monitoring station. Let S represent the total number of pixels at the j-th monitoring station, S represent the area represented by one pixel, α2 represent the weighting coefficient of sampling time, e represent the natural base, k represent the time decay coefficient, and t represent the sampling time weighting coefficient. now t represents the current time. i This indicates the collection time of the i-th data item;

[0059] Furthermore, the storage location of meteorological data is determined based on data priority and thresholds:

[0060]

[0061] Among them, P threshold P represents the threshold. i This indicates the data priority of the i-th meteorological data point;

[0062] Furthermore, the hydrological information storage unit, similar to the meteorological information storage unit, uses a data priority approach for storage and display.

[0063] By prioritizing data based on forest vegetation density and data collection time at monitoring stations, meteorological and hydrological data can be prioritized, ensuring that critical data is stored and accessed preferentially. This maximizes storage resources while improving data management efficiency. Using priorities and thresholds to allocate storage locations allows high-priority data to be stored in fast-access areas and low-priority data in low-cost areas, significantly improving storage system performance and resource utilization. Furthermore, the division of data into hot and cold data areas supports subsequent anomaly feature extraction.

[0064] Furthermore, regarding the optimization of storage resources for meteorological and hydrological data, the allocation ratio is dynamically adjusted based on the importance of the data:

[0065]

[0066] Where R represents the ratio of storage resources for hot data to cold data, S h S represents the storage resources currently used by the hot data unit. t Represents the total storage resources, P′ m This indicates the data priority of the m-th hot data record, where M represents the number of hot data records, and P″ nThis indicates the data priority of the nth data record, and N represents the total number of data records.

[0067] By dynamically adjusting the storage resource ratio between hot and cold data based on data priority, storage resources can be rationally allocated, ensuring that critical data can be accessed quickly and enhancing the adaptability and flexibility of data storage.

[0068] The data retrieval module is used to query data according to user needs. It includes an active query unit and a passive query unit. The active query unit includes querying based on keywords and prioritizing the retrieval and display of data based on data priority. The passive query unit includes acquiring first meteorological information and first hydrological information collected by the data monitoring station based on event triggering; retrieving second meteorological information based on the first meteorological information; retrieving second hydrological information based on the first hydrological information; interactively retrieving third hydrological information based on the first meteorological information; interactively retrieving third meteorological information based on the first hydrological information; constructing an abnormal meteorological data vector based on the first meteorological information, the second meteorological information, and the third meteorological information; and constructing an abnormal hydrological data vector based on the first hydrological information, the second hydrological information, and the third hydrological information.

[0069] Furthermore, the active query unit also includes:

[0070] The active query unit supports users to actively input keywords, time ranges, and geographical ranges for queries, and sorts and displays data based on data priority. Its functions include keyword retrieval and multi-condition cross-filtering, which supports composite queries based on keywords, time ranges, monitoring station locations, and forest vegetation coverage.

[0071] The proactive query unit, combined with multi-condition cross-filtering and data priority sorting functions, significantly improves the accuracy and efficiency of data retrieval, while enhancing the system's intelligence and flexibility.

[0072] Furthermore, the acquisition of the first meteorological information and the first hydrological information collected by the data monitoring station based on the event trigger means that if certain data indicators of the monitoring station, such as temperature and air pressure, exceed the set threshold, the acquisition of the first meteorological information and the first hydrological information will be performed.

[0073] Furthermore, the passive query unit also includes:

[0074] The formula for retrieving second meteorological information based on first meteorological information is:

[0075]

[0076] in, This indicates the second meteorological information. Indicates the first meteorological information, F weather The function represents meteorological characteristics, corr() represents the correlation function, and θ1 represents the first meteorological correlation threshold.

[0077] Furthermore, the formula for calculating the correlation function is:

[0078]

[0079] Here, corr() represents the correlation function, X′ and Y′ represent two sets of data vectors, and x′ q Let y' represent the q-th component of the first data vector. q This represents the q-th component of the second set of data vectors, where Q represents the length of the data vector. and These represent the mean values ​​of the two sets of data vectors, respectively.

[0080] The formula for retrieving third-level hydrological information based on first-level meteorological information interaction is as follows:

[0081]

[0082] in, Indicates third hydrological information, F hydro Here, f() represents the hydrological characteristics, θ2 represents the first interaction threshold, and f2 represents the interaction function.

[0083] Furthermore, the formula for calculating the interaction effect function is:

[0084]

[0085] Where, ρ q Let represent the weighting coefficient of the q-th component, e represent the natural base, and κ represent the adjustment parameter used to control the decay rate of the interaction intensity.

[0086] The formula for retrieving second hydrological information based on first hydrological information is:

[0087]

[0088] in, This indicates the second hydrological information. θ3 represents the first hydrological information, and θ3 represents the second hydrological correlation threshold.

[0089] The formula for retrieving third-level meteorological information based on first-level hydrological information interaction is as follows:

[0090]

[0091] in, θ4 represents the third meteorological information, and θ4 represents the second interaction threshold.

[0092] Correlation retrieval, through the correlation function between data, can reveal the inherent correlations hidden behind the data and enhance the mining of data correlations. The introduction of interactive retrieval establishes a two-way influence relationship between meteorological and hydrological data, reveals the potential driving effect of meteorological changes on hydrological data, and analyzes the feedback effect of hydrological characteristics on meteorology. This two-way interactive data retrieval helps to construct joint characteristics of meteorology and hydrology, and provides data support for the analysis of complex environmental systems.

[0093] The anomaly analysis module acquires the abnormal meteorological data vector and the abnormal hydrological data vector, extracts features based on the temporal differences in the data to obtain abnormal meteorological features and abnormal hydrological features, and fuses these features with forest vegetation density to obtain risk feature indicators. Based on the risk feature indicators, it is determined whether there is an anomaly.

[0094] Furthermore, the specific steps for constructing anomalous meteorological and hydrological characteristics are as follows: Figure 3 Shown, including:

[0095] Obtain abnormal meteorological data vectors and extract abnormal hot data and abnormal cold data from them to obtain abnormal meteorological hot data components and abnormal meteorological cold data components; obtain abnormal meteorological hot data components collected in the most recent time windows and compare the data changes in adjacent time periods using a sliding window to obtain an abnormal meteorological hot data change matrix; extract features from the abnormal meteorological hot data change matrix using a trend analysis model to obtain abnormal meteorological hot data features; obtain the abnormal meteorological hot data features and the abnormal meteorological cold data components to obtain abnormal meteorological features;

[0096] Obtain abnormal hydrological data vectors and extract abnormal hot and cold data from them to obtain abnormal hydrological hot data components and abnormal hydrological cold data components; obtain abnormal hydrological hot data components collected in the most recent time windows and compare the data changes in adjacent time periods using a sliding window to obtain an abnormal hydrological hot data change matrix; extract features from the abnormal hydrological hot data change matrix using a trend analysis model to obtain abnormal hydrological hot data features; obtain the abnormal hydrological hot data features and the abnormal hydrological cold data components to obtain abnormal hydrological features.

[0097] Furthermore, the trend analysis model can be an existing model such as a recurrent neural network model, a convolutional neural network model, or a differential integrated moving average autoregressive model, for feature extraction.

[0098] First, separating hot and cold data helps to analyze data that changes significantly in the short term and anomalies that have small fluctuations in the long term but may be important. Then, comparing the changes in data in adjacent time periods through a sliding window can capture the dynamic evolution characteristics of anomaly data in a short period of time. Finally, features are extracted through a trend analysis model, which effectively compresses the data dimensions and retains key information. Finally, the features of the hot and cold data are fused to form more comprehensive features and enhance the comprehensiveness of the anomaly features.

[0099] Furthermore, the formula for calculating the risk characteristic indicators is as follows:

[0100]

[0101] Where Dan represents the risk characteristic index, ω1 represents the weighting coefficient of the abnormal meteorological characteristic, H represents the length of the abnormal meteorological characteristic, and x h The h-th component representing the anomalous meteorological characteristics, μ x σ represents the mean of normal meteorological data. x ω represents the standard deviation of normal meteorological data, ω² represents the weighting coefficient of anomalous hydrological features, G represents the length of anomalous hydrological features, and y represents the standard deviation of normal meteorological data. g μ represents the g-th component of the anomalous hydrological characteristics. y σ represents the mean of normal hydrological data. y ω3 represents the standard deviation of normal hydrological data, ω3 represents the weighting coefficient of forest vegetation density, and ΔF represents the standard deviation of normal hydrological data. density This indicates the change in forest vegetation density. Table 2 shows the risk characteristic indicators for some monitoring stations, all of which are normal.

[0102] Table 2. Risk Characteristic Indicators of Some Monitoring Stations

[0103] Monitoring station number Risk characteristic indicators A001 0.85 A002 0.72 A003 0.68 A004 0.76 A005 0.81

[0104] The risk characteristic indicators combine three key factors: abnormal meteorological characteristics, abnormal hydrological characteristics, and forest vegetation density. This helps to identify extreme weather events and abnormal hydrological changes, ensuring the multidimensionality and reliability of risk assessment results, improving the comprehensiveness, adaptability, and accuracy of risk identification, and providing strong support for disaster early warning, ecological protection, and emergency decision-making.

[0105] The management module is used to obtain the location of anomalies, define the priority of tasks based on risk characteristic indicators, and perform task allocation and status tracking.

[0106] Furthermore, the steps of classifying risk characteristics based on risk indicators and allocating tasks and tracking status also include: acquiring abnormal risk indicators and classifying abnormal risk levels according to priority, and allocating detection time, detection personnel and detection tools according to the abnormal risk level and historical detection data.

[0107] By acquiring abnormal risk indicators, prioritizing tasks based on forest density and risk level, and dynamically allocating exploration tasks in conjunction with historical data, the management module can significantly improve the scientific rigor, accuracy, and efficiency of exploration work.

[0108] The meteorological and hydrological analysis and management cloud platform provided by this invention first realizes the storage and retrieval of meteorological and hydrological data through a meteorological and hydrological data storage module, and sorts and allocates storage resources according to data priority based on forest vegetation density of monitoring stations and collection time. Then, the data retrieval module realizes automatic retrieval of abnormal data, and realizes comprehensive retrieval of abnormal data through correlation retrieval and interactive retrieval. Then, the abnormal data is analyzed, and risk characteristic indicators are constructed through abnormal meteorological characteristics, abnormal hydrological characteristics, and forest vegetation area, realizing the abnormal monitoring of forest vegetation and improving management efficiency.

[0109] Example 2

[0110] An engineering unit introduced a meteorological and hydrological analysis and management cloud platform provided by this invention when monitoring a certain forest. The specific implementation method is as follows:

[0111] The meteorological and hydrological data storage module includes a meteorological information storage unit and a hydrological information storage unit; wherein the meteorological information storage unit includes a meteorological thermal data storage unit and a meteorological cold data storage unit, and the hydrological information storage unit includes a hydrological thermal data storage unit and a hydrological cold data storage unit, and the data is sorted according to the data priority constructed based on forest vegetation density and collection time; Table 3 shows some meteorological information.

[0112] Table 3. Partial Meteorological Information

[0113] Monitoring station number Meteorological thermal data Meteorological cold data B001 Temperature: 24.3℃, Humidity: 65%, ... Precipitation: 0 mm, Air pressure: 1011 hPa, ... B002 Temperature: 25.4℃, Humidity: 54%, ... Precipitation: 0 mm, Air pressure: 1010 hPa, ... B003 Temperature: 24.8℃, Humidity: 59%, ... Precipitation: 0 mm, Air pressure: 1009 hPa, ... B004 Temperature: 24.5℃, Humidity: 62%, ... Precipitation: 0 mm, Air pressure: 1012 hPa, ... B005 Temperature: 24.1℃, Humidity: 64%, ... Precipitation: 0 mm, Air pressure: 1010 hPa, ...

[0114] Furthermore, the meteorological information storage unit is used to store data from all monitoring stations, and to sort the data by combining forest vegetation density and collection time to establish data priority. The formula for calculating the data priority is:

[0115]

[0116] Among them, P i j Let αi represent the priority of the i-th meteorological data point from the j-th monitoring station, and α1 represent the weighting coefficient of forest vegetation. This represents the number of forest vegetation pixels at the j-th monitoring station. Let S represent the total number of pixels at the j-th monitoring station, S represent the area represented by one pixel, α2 represent the weighting coefficient of sampling time, e represent the natural base, k represent the time decay coefficient, and t represent the sampling time weighting coefficient. now t represents the current time. i This indicates the collection time of the i-th data item;

[0117] Determine the storage location based on data priority and threshold:

[0118]

[0119] Among them, P threshokd P represents the threshold. i This indicates the data priority of the i-th data item.

[0120] Furthermore, regarding the optimization of storage resources for meteorological and hydrological data, the allocation ratio is dynamically adjusted based on the importance of the data:

[0121]

[0122] Where R represents the ratio of storage resources for hot data to cold data, S h S represents the storage resources currently used by the hot data unit. t Represents the total storage resources, P′ m This indicates the data priority of the m-th hot data record, where M represents the number of hot data records, and P″ n This indicates the data priority of the nth data record, and N represents the total number of data records.

[0123] The data retrieval module includes an active query unit and a passive query unit. The active query unit includes querying based on keywords and displaying data according to priority. The passive query unit includes acquiring first meteorological information and first hydrological information collected by the data monitoring station based on event triggering; retrieving second meteorological information based on the first meteorological information; retrieving second hydrological information based on the first hydrological information; interactively retrieving third hydrological information based on the first meteorological information; and interactively retrieving third meteorological information based on the first hydrological information. It also constructs an abnormal meteorological data vector based on the first, second, and third meteorological information, and an abnormal hydrological data vector based on the first, second, and third hydrological information.

[0124] Furthermore, the formula for retrieving second meteorological information based on the first meteorological information is as follows:

[0125]

[0126] in, This indicates the second meteorological information. Indicates the first meteorological information, F weatherThe function represents meteorological characteristics, corr() represents the correlation function, and θ1 represents the first meteorological correlation threshold.

[0127] Furthermore, the formula for retrieving third-level hydrological information based on the interaction of first-level meteorological information is as follows:

[0128]

[0129] in, Indicates third hydrological information, F hydro Here, f() represents the hydrological characteristics, θ2 represents the first interaction threshold, and f2 represents the interaction function.

[0130] Furthermore, the formula for retrieving second hydrological information based on the first hydrological information is as follows:

[0131]

[0132] in, This indicates the second hydrological information. θ3 represents the first hydrological information, and θ3 represents the second hydrological correlation threshold.

[0133] Furthermore, the formula for retrieving third-level meteorological information based on the interaction of first-level hydrological information is as follows:

[0134]

[0135] in, θ4 represents the third meteorological information, and θ4 represents the second interaction threshold.

[0136] An anomaly analysis module is used to acquire the abnormal meteorological data vector and the abnormal hydrological data vector, extract features based on the temporal differences of the data, obtain abnormal meteorological features and abnormal hydrological features, and obtain risk feature indicators by combining forest vegetation density, and determine whether there is an anomaly based on the risk feature indicators.

[0137] Furthermore, the formula for calculating the risk characteristic indicators is as follows:

[0138]

[0139] Where Dan represents the risk characteristic index, ω1 represents the weighting coefficient of the abnormal meteorological characteristic, H represents the length of the abnormal meteorological characteristic, and x h The h-th component representing the anomalous meteorological characteristics, μ x σ represents the mean of normal meteorological data. x ω represents the standard deviation of normal meteorological data, ω² represents the weighting coefficient of anomalous hydrological features, G represents the length of anomalous hydrological features, and y represents the standard deviation of normal meteorological data. g μ represents the g-th component of the anomalous hydrological characteristics. yσ represents the mean of normal hydrological data. y ω3 represents the standard deviation of normal hydrological data, ω3 represents the weighting coefficient of forest vegetation density, and ΔF represents the standard deviation of normal hydrological data. density This indicates the change in forest vegetation density.

[0140] The management module is used to classify risks based on risk characteristic indicators, and to assign tasks and track their status.

[0141] Furthermore, the formula for the hierarchical function is:

[0142]

[0143] Where L represents the risk level, and Dan1, Dan2 and Dan3 represent the first risk threshold, the second risk threshold and the third risk threshold, respectively.

[0144] Table 4. Risk Characteristic Indicators of Some Monitoring Stations

[0145] Monitoring station number Risk characteristic indicators B001 0.79 B002 0.81 B003 0.93 B004 0.78 B005 0.83

[0146] Table 4 shows the risk characteristic indicators of some monitoring stations. All of them are less than the threshold and there is no risk. Through the meteorological and hydrological analysis and management cloud platform provided by this invention, real-time monitoring of forest vegetation has been realized, management efficiency has been improved, and the early warning capability for natural disasters has been enhanced.

[0147] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A meteorological and hydrological analysis and management cloud platform, characterized in that, include: The meteorological and hydrological data storage module includes a meteorological information storage unit and a hydrological information storage unit; wherein the meteorological information storage unit includes a meteorological hot data storage unit and a meteorological cold data storage unit, and the hydrological information storage unit includes a hydrological hot data storage unit and a hydrological cold data storage unit, and the data is sorted according to the data priority constructed based on forest vegetation density and collection time; The meteorological information storage unit is used to store data from all monitoring stations and sort the data by combining forest vegetation density and collection time to establish data priority. The formula for calculating the data priority is: ； in, Indicates the first The first monitoring station Priority of meteorological data The weighting coefficients representing forest vegetation. Indicates the first The number of forest vegetation pixels at each monitoring station Indicates the first The total number of pixels at each monitoring station This represents the area represented by a single pixel. The weighting coefficient represents the sampling time. Represents the natural base. Indicates the time decay coefficient. Indicates the current time. Indicates the first The time of data collection; Determine the storage location based on data priority and threshold: ； in, Indicates the threshold. Indicates the first Data priority of each data item; The data retrieval module includes an active query unit and a passive query unit. The active query unit is used to query based on keywords and display data according to priority. The passive query unit includes acquiring first meteorological information and first hydrological information collected by the monitoring station based on event triggering; retrieving second meteorological information based on the first meteorological information, retrieving second hydrological information based on the first hydrological information, and interactively retrieving third hydrological information based on the first meteorological information; constructing an abnormal meteorological data vector based on the first, second, and third meteorological information, and constructing an abnormal hydrological data vector based on the first, second, and third hydrological information. The anomaly analysis module is used to acquire the abnormal meteorological data vector and the abnormal hydrological data vector, extract features based on the temporal differences of the data, obtain abnormal meteorological features and abnormal hydrological features, combine forest vegetation density to obtain risk feature indicators, and determine whether there is anomaly based on the risk feature indicators. The management module is used to classify risks based on risk characteristic indicators, and to assign tasks and track their status.

2. The meteorological and hydrological analysis and management cloud platform according to claim 1, characterized in that, Storage resources for meteorological and hydrological data are optimized, with allocation ratios dynamically adjusted based on data importance: ； in, This indicates the ratio of storage resources for hot data to cold data. Indicates the storage resources currently used by the hot data unit. Represents total storage resources. Indicates the first Data priority of hot data points Indicates the number of hot data records. Indicates the first Data priority of each data item This indicates the total number of data records.

3. The meteorological and hydrological analysis and management cloud platform according to claim 1, characterized in that, The active query unit also includes: The active query unit is used to receive keywords, time ranges, and geographical ranges actively input by users and perform queries, combining the priority sorting and display of forest vegetation area and density optimization results; the active query unit also includes the functions of keyword retrieval and multi-condition cross-filtering, the multi-condition cross-filtering including supporting composite queries based on keywords, time ranges, monitoring station locations, and forest vegetation coverage.

4. The meteorological and hydrological analysis and management cloud platform according to claim 1, characterized in that, The passive query unit also includes: The formula for retrieving second meteorological information based on first meteorological information is: ； in, This indicates the second meteorological information. This indicates the first meteorological information. Indicates meteorological characteristics, Represents the correlation function. This indicates the first meteorological correlation threshold; The formula for retrieving third-level hydrological information based on first-level meteorological information interaction is as follows: ； in, This indicates third-party hydrological information. Indicates hydrological characteristics, Represents the interaction effect function, Indicates the threshold of the first interaction effect; The formula for retrieving second hydrological information based on first hydrological information is: ； in, This indicates the second hydrological information. This indicates the first hydrological information. This indicates the second hydrological correlation threshold; The formula for retrieving third-level meteorological information based on first-level hydrological information interaction is as follows: ； in, This indicates third-party meteorological information. This indicates the threshold for the second interaction effect.

5. The meteorological and hydrological analysis and management cloud platform according to claim 1, characterized in that, The specific steps for constructing anomalous meteorological and hydrological characteristics include: Obtain abnormal meteorological data vectors and extract abnormal hot data and abnormal cold data to obtain abnormal meteorological hot data components and abnormal meteorological cold data components; obtain the abnormal meteorological hot data components collected within several time windows and use a sliding window to calculate the data change amount between adjacent time periods to obtain an abnormal meteorological hot data change matrix; use a trend analysis model to extract features from the abnormal meteorological hot data change matrix to obtain abnormal meteorological hot data features; obtain the abnormal meteorological hot data features and the abnormal meteorological cold data components to obtain abnormal meteorological features. Anomalous hydrological data vectors are acquired, and anomalous hot and cold data are extracted to obtain anomalous hydrological hot data components and anomalous hydrological cold data components. The anomalous hydrological hot data components collected within several time windows are acquired, and the data change between adjacent time periods is calculated using a sliding window to obtain an anomalous hydrological hot data change matrix. Features are extracted from the anomalous hydrological hot data change matrix using a trend analysis model to obtain anomalous hydrological hot data features. The anomalous hydrological hot data features and the anomalous hydrological cold data components are then acquired to obtain anomalous hydrological features.

6. The meteorological and hydrological analysis and management cloud platform according to claim 1, characterized in that, The formula for calculating the risk characteristic index is: ； in, This indicates the risk characteristic index. Weighting coefficients representing abnormal meteorological characteristics The length of the abnormal meteorological feature is indicated. The first characteristic representing abnormal meteorological features One portion, This represents the average of normal meteorological data. This represents the standard deviation of normal meteorological data. Weighting coefficients representing anomalous hydrological characteristics Indicates the length of the anomalous hydrological feature. The first characteristic representing abnormal hydrological features One portion, This represents the average value of normal hydrological data. This represents the standard deviation of normal hydrological data. Weighting coefficients representing forest vegetation density. This indicates the change in forest vegetation density.

7. The meteorological and hydrological analysis and management cloud platform according to claim 1, characterized in that, The steps of classifying risks based on risk characteristic indicators, and then assigning tasks and tracking their status, also include: Obtain abnormal risk indicators and classify abnormal risk levels according to priority. Allocate detection time, detection personnel and detection tools according to the abnormal risk level and historical detection data.

Images