Disaster-causing element extraction method and device, equipment and storage medium

Abstract

The invention discloses a disaster-causing element extraction method, device and equipment and a storage medium, and relates to the technical field of remote sensing disaster monitoring, and the method comprises the steps: collecting multi-source satellite remote sensing data; inputting the multi-source satellite remote sensing data into a pre-constructed satellite remote sensing inversion algorithm model to obtain at least one of a rainfall intensity distribution map, a flood inundation range map and a flood inundation water depth estimation map; and extracting disaster-causing elements based on at least one of the rainfall intensity distribution map, the flood inundation range map and the flood inundation water depth estimation map. According to the method, multi-source satellite remote sensing data can be comprehensively utilized, and efficient extraction of the disaster-causing elements is realized.

Description

Technical Field

[0001] This application relates to the field of remote sensing disaster monitoring technology, and in particular to a method, apparatus, equipment, and storage medium for extracting disaster-causing factors. Background Technology

[0002] The typhoon and rainstorm disaster chain is a complex natural disaster process involving multiple links such as typhoons, rainstorms, flash floods, and urban flooding. Its disaster-causing factors are numerous and change rapidly.

[0003] With the development of remote sensing technology, especially the widespread application of multi-source satellite remote sensing data such as meteorological satellites, high-resolution optical satellites, and radar satellites, new means have been provided for disaster monitoring. However, how to comprehensively utilize these multi-source satellite remote sensing data to efficiently extract key disaster-causing factors in the typhoon and rainstorm disaster chain remains a technical challenge that urgently needs to be solved.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of this application is to provide a method, apparatus, equipment and storage medium for extracting disaster-causing factors, aiming to solve the technical problem that it is currently impossible to comprehensively utilize multi-source satellite remote sensing data to achieve efficient extraction of key disaster-causing factors in the typhoon and rainstorm disaster chain.

[0006] To achieve the above objectives, this application proposes a method for extracting disaster-causing factors, the method comprising: Collect multi-source satellite remote sensing data; The multi-source satellite remote sensing data is input into a pre-constructed satellite remote sensing inversion algorithm model to obtain at least one of the following: rainfall intensity distribution map, flood inundation range map, and flood inundation depth estimation map. Disaster-causing factors are extracted based on at least one of the rainfall intensity distribution map, the flood inundation range map, and the flood inundation depth estimation map.

[0007] In one embodiment, the step of extracting disaster-causing factors based on at least one of the rainfall intensity distribution map, the flood inundation range map, and the flood inundation depth estimation map includes: Obtain at least one of the following: satellite cloud imagery, meteorological radar data, and ground station data; By using a pre-built disaster chain identification algorithm model, disasters are identified and / or tracked based on at least one of the satellite cloud images, the meteorological radar data, and the ground station data, and disaster prediction information is obtained. Obtain static geographic data; The extraction of disaster-causing factors based on at least one of the rainfall intensity distribution map, the flood inundation range map, and the flood inundation depth estimation map includes: The disaster-causing factors are extracted based on at least one of the rainfall intensity distribution map, the flood inundation range map, and the flood inundation depth estimation map, as well as the disaster prediction information and the static geographic data.

[0008] In one embodiment, the step of identifying and / or tracking disasters based on at least one of the satellite cloud image, the weather radar data, and the ground station data using a pre-built disaster chain identification algorithm model to obtain disaster prediction information includes: The warm and cold characteristics of the typhoon cloud system are observed based on the infrared images in the satellite cloud images. Based on the water vapor map in the satellite cloud image, obtain the water vapor distribution information of the typhoon-affected area; Obtain classification information of different cloud elements in the satellite cloud image; The step of identifying and / or tracking disasters based on at least one of the following—satellite cloud images, meteorological radar data, and ground station data—using a pre-built disaster chain identification algorithm model to obtain disaster prediction information includes: Using the pre-built disaster chain identification algorithm model, the typhoon is identified and / or tracked based on at least one of the following: the cold and warm characteristics of the typhoon cloud system, the water vapor distribution information of the typhoon-affected area, the classification information of different cloud elements, the meteorological radar data, and the ground station data. This allows for the acquisition of at least one of the typhoon's location, shape, and trajectory.

[0009] In one embodiment, the step of acquiring static geographic data includes: Human activity areas and / or facilities can be identified through remote sensing imagery. Spatial analysis of urban flooding is obtained through a geographic information system based on the human activity area and / or facilities, serving as the static geographic data.

[0010] In one embodiment, the step of extracting the disaster-causing factors based on at least one of the rainfall intensity distribution map, the flood inundation range map, the flood inundation depth estimation map, the disaster prediction information, and the static geographic data includes: By using satellite-based dual-frequency precipitation measurement radar and microwave imaging, the flood inundation area and water depth in the affected area during the evolution of the typhoon disaster chain, as well as the physical information of the disaster-bearing bodies, can be obtained. The disaster prediction information output by the disaster chain identification algorithm model is optimized by taking the disaster-causing factors, the flood inundation area and water depth of the affected area, and the physical information of the disaster-bearing body, to obtain optimized disaster prediction information.

[0011] In one embodiment, the step of collecting multi-source satellite remote sensing data includes, prior to: Collect multi-source satellite remote sensing training data; The multi-source satellite remote sensing training data is preprocessed; A primary inversion algorithm model was obtained by training preprocessed multi-source satellite remote sensing training data. The model parameters of the primary inversion algorithm model are optimized by comparing and analyzing the water extraction effects of at least two of the visible light, infrared light and microwave bands, and the satellite remote sensing inversion algorithm model is obtained.

[0012] In one embodiment, the disaster-causing factors include at least one of rainfall, water body changes, settlements, lifeline projects, flash floods, and river / reservoir overtopping and dam failure.

[0013] Furthermore, to achieve the above objectives, this application also proposes a disaster-causing factor extraction device, which includes: The data collection module is used to collect multi-source satellite remote sensing data; The data processing module is used to input the multi-source satellite remote sensing data into a pre-constructed satellite remote sensing inversion algorithm model to obtain at least one of the following: rainfall intensity distribution map, flood inundation range map, and flood inundation depth estimation map. The element extraction module is used to extract disaster-causing elements based on at least one of the rainfall intensity distribution map, the flood inundation range map, and the flood inundation depth estimation map.

[0014] In addition, to achieve the above objectives, this application also proposes a disaster-causing factor extraction device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the disaster-causing factor extraction method as described above.

[0015] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the disaster-causing element extraction method described above.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: This application collects multi-source satellite remote sensing data and inputs the multi-source satellite remote sensing data into a pre-constructed satellite remote sensing inversion algorithm model to obtain at least one of a rainfall intensity distribution map, a flood inundation range map, and a flood inundation depth estimation map. Thus, disaster-causing factors can be accurately and comprehensively extracted based on at least one of the rainfall intensity distribution map, the flood inundation range map, and the flood inundation depth estimation map. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating an embodiment of the disaster-causing factor extraction method of this application. Figure 2 This is a flowchart illustrating Embodiment 5 of the disaster-causing element extraction method of this application; Figure 3 This is a simplified flowchart illustrating the disaster-causing factor extraction method of this application; Figure 4 This is a schematic diagram of the module structure of the disaster-causing element extraction device according to an embodiment of this application; Figure 5 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the disaster-causing element extraction method in the embodiments of this application.

[0020] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0023] The main solution of this application embodiment is: collecting multi-source satellite remote sensing data; inputting the multi-source satellite remote sensing data into a pre-constructed satellite remote sensing inversion algorithm model to obtain at least one of a rainfall intensity distribution map, a flood inundation range map, and a flood inundation depth estimation map; and extracting disaster-causing factors based on at least one of the rainfall intensity distribution map, the flood inundation range map, and the flood inundation depth estimation map.

[0024] In this embodiment, for ease of description, the following description uses a remote sensing monitoring system as the execution subject.

[0025] With the development of remote sensing technology, especially the widespread application of multi-source satellite remote sensing data such as meteorological satellites, high-resolution optical satellites, and radar satellites, new means have been provided for disaster monitoring. However, how to comprehensively utilize these multi-source satellite remote sensing data to efficiently extract key disaster-causing factors in the typhoon and rainstorm disaster chain remains a technical challenge that urgently needs to be solved.

[0026] This application provides a solution that collects multi-source satellite remote sensing data and inputs the multi-source satellite remote sensing data into a pre-constructed satellite remote sensing inversion algorithm model to obtain at least one of a rainfall intensity distribution map, a flood inundation range map, and a flood inundation depth estimation map. This allows for the accurate and comprehensive extraction of disaster-causing factors based on at least one of the rainfall intensity distribution map, the flood inundation range map, and the flood inundation depth estimation map.

[0027] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone; or an electronic device or disaster factor extraction device capable of performing the above functions; or an electronic system or remote sensing monitoring system capable of performing the above functions. The following description uses a remote sensing monitoring system as an example to illustrate this embodiment and the subsequent embodiments.

[0028] Based on this, embodiments of this application provide a method for extracting disaster-causing factors, referring to... Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of the disaster-causing factor extraction method of this application.

[0029] In this embodiment, the disaster-causing factor extraction method includes steps S50~S60 and S130: Step S50: Collect multi-source satellite remote sensing data; Among them, multi-source satellites include different types of satellites, such as meteorological satellites, optical remote sensing satellites, and radar satellites.

[0030] Meteorological satellites are mainly used to acquire atmospheric data, including cloud images, temperature, humidity, wind fields, and other information; optical remote sensing satellites can acquire high-resolution optical images of the ground and clearly identify ground features, such as vegetation cover and land use types; radar satellites are not limited by weather and lighting conditions, can penetrate clouds to acquire ground information, and can monitor the dynamic changes of disasters such as floods and landslides.

[0031] Among them, multi-source satellite remote sensing data includes meteorological satellite data (such as TRMM, GPM, Suomi-NPP / VIIRS, AVHRR, MODIS, etc.), high-resolution optical image data (such as LandSat-8, Sentinel-2) and radar data (such as spaceborne Ku and Ka dual-frequency precipitation measurement radar).

[0032] Step S60: Input the multi-source satellite remote sensing data into the pre-constructed satellite remote sensing inversion algorithm model to obtain at least one of the following: rainfall intensity distribution map, flood inundation range map, and flood inundation depth estimation map; Among them, the satellite remote sensing inversion algorithm model is used to extract the required geographic and environmental information from satellite remote sensing data.

[0033] As one implementation method, after collecting multi-source satellite remote sensing data, the multi-source satellite remote sensing data can be preprocessed, including data correction, noise reduction and format conversion, to ensure the accuracy and usability of the data.

[0034] As one implementation method, training a satellite remote sensing inversion algorithm model may include: collecting multi-source satellite remote sensing training data, preprocessing the multi-source satellite remote sensing training data, training a primary inversion algorithm model based on the preprocessed multi-source satellite remote sensing training data, optimizing the model parameters of the primary inversion algorithm model by comparing and analyzing the water body extraction effects of at least two of the visible light, infrared light and microwave bands, and obtaining the satellite remote sensing inversion algorithm model.

[0035] Step S130: Extract disaster-causing factors based on at least one of the rainfall intensity distribution map, the flood inundation range map, and the flood inundation depth estimation map.

[0036] The disaster-causing factors include at least one of the following: rainfall, water body changes, settlements, lifeline projects, flash floods, and river / reservoir overtopping and dam failure.

[0037] Among them, the spatiotemporal distribution characteristics of rainfall can be analyzed from the rainfall intensity distribution map, and disaster-causing factors such as concentrated rainfall areas, rainfall duration, and maximum rainfall intensity can be extracted.

[0038] Among them, the flood inundation range map can determine the boundaries of the flood and the affected area, and extract disaster-causing factors such as the inundated area, the topographic features of the inundated area, and the land use type.

[0039] This study comprehensively analyzes disaster-causing factors such as rainfall intensity, flood inundation range, and water depth, considering their interactions and impacts. For example, high-intensity rainfall may cause river levels to rise rapidly, thereby expanding the flood inundation range and increasing the inundation depth, thus exacerbating the severity of the disaster. Through comprehensive analysis, the risk and severity of rainstorm flood disasters can be assessed more accurately.

[0040] By efficiently extracting disaster-causing factors, comprehensive disaster-causing factor information is provided for disaster risk assessment and emergency management.

[0041] This embodiment provides a method for extracting disaster-causing factors. By collecting multi-source satellite remote sensing data and inputting it into a pre-constructed satellite remote sensing inversion algorithm model, at least one of a rainfall intensity distribution map, a flood inundation range map, and a flood inundation depth estimation map can be obtained. This allows for the accurate and comprehensive extraction of disaster-causing factors based on at least one of these maps. Furthermore, this embodiment significantly improves the extraction accuracy of rainfall range, intensity, and flood inundation range by combining high-resolution optical imagery and data from multiple satellite payloads.

[0042] Based on Embodiment 1 of this application, in Embodiment 2 of this application, the content that is the same as or similar to that in Embodiment 1 can be referred to the above description, and will not be repeated hereafter. Based on this, before extracting the disaster-causing factors based on at least one of the rainfall intensity distribution map, the flood inundation range map, and the flood inundation depth estimation map in step S130, the disaster-causing factor extraction method further includes steps S70 and S110~S120: Step S70: Obtain at least one of the following: satellite cloud image, weather radar data, and ground station data; Among them, satellite cloud images are obtained by meteorological satellites receiving images of cloud distribution in the Earth's atmosphere. They can intuitively show the shape, range, and direction of movement of cloud systems, helping to determine the evolution of weather systems, such as identifying typhoons and rainstorm clouds.

[0043] Among them, meteorological radar data is obtained by using ground-based meteorological radar equipment to emit electromagnetic waves and receive reflected signals, thereby acquiring information such as the distribution, intensity, and velocity of precipitation particles.

[0044] The ground station data is collected from meteorological ground stations distributed in various locations, including basic meteorological elements such as temperature, air pressure, humidity, wind speed, and wind direction.

[0045] Step S110: Using a pre-built disaster chain identification algorithm model, identify and / or track disasters based on at least one of the satellite cloud image, the meteorological radar data, and the ground station data to obtain disaster prediction information; Among them, the disaster chain identification algorithm model is a comprehensive computational model used to identify the occurrence of disasters, track their dynamic evolution, and predict disaster development trends and related information.

[0046] The disaster chain identification algorithm model can integrate various types and sources of data, including satellite cloud images, meteorological radar data, and ground station data. Through data fusion, the model can fully utilize the advantages of different data sources, compensate for the shortcomings of a single data source, and improve the accuracy of disaster identification and prediction.

[0047] In addition, the disaster chain identification algorithm model can automatically identify ongoing or potential disasters and track their dynamic evolution. The model can update disaster status information in real time based on changes in input data, such as the center location and intensity changes of typhoons, and the range and intensity changes of heavy rainfall.

[0048] Furthermore, disaster chain identification algorithms can predict future disaster trends and issue early warnings based on analysis of the current disaster situation and reference to historical data. This helps relevant departments and personnel take preventative measures in advance, reducing losses caused by disasters.

[0049] Step S120: Obtain static geographic data.

[0050] Human activity areas and / or facilities can be identified through remote sensing imagery, and spatial analysis of urban flooding can be obtained based on the human activity areas and / or facilities through a geographic information system, serving as the static geographic data.

[0051] Step S130, which extracts disaster-causing factors based on at least one of the rainfall intensity distribution map, the flood inundation range map, and the flood inundation depth estimation map, further includes step S131: Step S131: Extract the disaster-causing factors based on at least one of the rainfall intensity distribution map, the flood inundation range map, the flood inundation depth estimation map, the disaster prediction information, and the static geographic data.

[0052] Among them, disaster inversion results such as rainfall intensity distribution map, flood inundation range map, and flood inundation depth estimation map, disaster prediction information, and static geographic data can be comprehensively analyzed and extracted to identify disaster-causing factors.

[0053] This application's embodiments are based on comprehensive analysis and extraction of disaster-causing factors using multiple data sources, avoiding the biases that may arise from single data or single methods, thus making the extraction of disaster-causing factors more scientific and reasonable. Furthermore, this application's embodiments utilize remote sensing technology to achieve real-time automatic identification and tracking of typhoon and rainstorm disaster chains, enabling timely understanding of the evolution of disaster chains and providing timely information support for disaster early warning.

[0054] Based on the above embodiments, in Embodiment 3 of this application, the same or similar content as the above embodiments can be referred to the above description, and will not be repeated hereafter. On this basis, before obtaining disaster prediction information by identifying and / or tracking disasters based on at least one of the satellite cloud image, the meteorological radar data, and the ground station data through a pre-constructed disaster chain identification algorithm model in step S110, the disaster-causing element extraction method further includes steps S80~S100: Step S80: Observe the warm and cold characteristics of the typhoon cloud system based on the infrared image in the satellite cloud image; This application utilizes meteorological satellites to detect and record information such as cloud images, temperature, and humidity of typhoons, and combines this with remote sensing technology to establish a real-time automatic disaster chain identification and tracking mechanism.

[0055] Infrared cloud imagery reveals the warming and cooling characteristics of typhoon cloud systems, reflecting their internal convection intensity and thermal structure. Cold cloud regions typically correspond to strong updrafts and convective activity, serving as key areas for typhoon energy release and development. Understanding these characteristics helps determine typhoon intensity changes and development trends, providing crucial information for typhoon monitoring and early warning.

[0056] Step S90: Obtain water vapor distribution information of the typhoon-affected area based on the water vapor map in the satellite cloud image; Among these methods, using moisture maps to obtain information on moisture distribution in typhoon-affected areas can help analyze the moisture sources and transport paths of typhoons, and predict the intensity and extent of precipitation. Furthermore, the distribution and changes in moisture also affect the thermal structure and dynamic characteristics of typhoons, significantly influencing their intensity and path.

[0057] Step S100: Obtain classification information of different cloud elements in the satellite cloud image; Among them, image processing and pattern recognition technologies are used to classify cloud elements into different categories, such as cumulus, stratus, and cirrus, based on their shape, texture, brightness, and other characteristics.

[0058] Among these, obtaining classification information of different cloud elements in satellite cloud images helps to gain a deeper understanding of the cloud system structure and evolution process of typhoons, providing more detailed information for typhoon monitoring and analysis.

[0059] Step S110, which involves identifying and / or tracking disasters based on at least one of the satellite cloud image, the meteorological radar data, and the ground station data using a pre-built disaster chain identification algorithm model to obtain disaster prediction information, further includes step S111: Step S111: Using the pre-built disaster chain identification algorithm model, the typhoon is identified and / or tracked based on at least one of the following: the cold and warm characteristics of the typhoon cloud system, the water vapor distribution information of the typhoon-affected area, the classification information of different cloud elements, the meteorological radar data, and the ground station data, thereby obtaining at least one of the typhoon's location, shape, and trajectory.

[0060] Among them, a pre-designed disaster chain identification algorithm model is used to automatically identify and track typhoons by comprehensively utilizing the cold and warm characteristics of typhoon cloud systems, water vapor distribution information, cloud element classification information, as well as meteorological radar data and ground station data obtained in the previous steps, and to determine key information such as the location, shape and trajectory of the typhoon.

[0061] This application comprehensively utilizes infrared images, water vapor maps, and cloud element classification information from satellite cloud images, combined with meteorological radar data and ground station data, to obtain typhoon-related information from multiple angles and levels. Infrared images can reflect the warm and cold characteristics of typhoon cloud systems and understand their internal convection intensity; water vapor maps can obtain information on water vapor distribution in the typhoon-affected area and analyze water vapor sources and transport; cloud element classification information can provide in-depth understanding of the typhoon's cloud system structure and evolution process. Meteorological radar data can monitor typhoon precipitation and wind field structure in real time, while ground station data can provide local meteorological conditions. The fusion of multiple data sources reduces the errors and limitations of single data sources, improving the accuracy and comprehensiveness of typhoon monitoring.

[0062] Based on the above embodiments, in Embodiment 4 of this application, the same or similar content as the above embodiments can be referred to the above description, and will not be repeated hereafter. On this basis, step S120, obtaining static geographic data, includes steps S121~S122: Step S121: Identify human activity areas and / or facilities through remote sensing imagery. By using image data acquired through remote sensing technology and employing specific image recognition algorithms and patterns, the scope of human activities and the location and distribution of related facilities can be identified and determined.

[0063] Step S122: Obtain spatial analysis of urban flooding based on the human activity area and / or facilities through a geographic information system, as the static geographic data.

[0064] By leveraging the powerful spatial analysis and data processing capabilities of Geographic Information System (GIS), and combining the information on human activity areas and facilities identified in step S121, spatial analysis of urban flooding is conducted, and the analysis results are used as static geographic data for subsequent disaster assessment and decision-making.

[0065] Among them, by analyzing the output data of multi-source remote sensing images, ground stations and radar signals, disaster-causing factors related to the occurrence of rainstorm and flood disasters are extracted, such as rainfall, water body changes, settlements and lifeline projects.

[0066] High-resolution remote sensing image data is used to identify urban buildings, roads, and other human activity areas and facilities affected by disaster-causing factors. Spatial analysis of urban flooding is conducted using geographic information systems (GIS) to extract disaster-causing factors such as flash floods, river embankment / reservoir overtopping and dam failure.

[0067] This application's embodiments comprehensively utilize remote sensing imagery and geographic information systems (GIS) to obtain more comprehensive and accurate information related to rainstorm and flood disasters. Remote sensing imagery can provide large-scale, high-resolution surface information, identifying the detailed distribution of human activity areas and facilities; GIS can perform spatial analysis and integration of this information, considering the impact of multiple factors on urban flooding. By combining the two, the flooding risk of different regions can be more accurately assessed, providing a more reliable basis for disaster prevention and emergency response.

[0068] Based on the above embodiments, in Embodiment 5 of this application, the content that is the same as or similar to the above embodiments can be referred to the above description, and will not be repeated hereafter. On this basis, refer to Figure 2 Step S131, after extracting the disaster-causing factors based on at least one of the rainfall intensity distribution map, the flood inundation range map, and the flood inundation depth estimation map, as well as the disaster prediction information and the static geographic data, includes steps S132-S133: Step S132: Using the dual-frequency precipitation measurement radar and microwave imaging of the satellite, obtain the flood inundation area and water depth of the affected area during the evolution of the typhoon disaster chain, as well as the physical information of the disaster-bearing bodies; Among them, by utilizing the spaceborne Ku and Ka dual-frequency precipitation measurement radar, combined with a passive microwave imager, the advantages of high radar observation resolution and wide satellite observation range are fully utilized to obtain precipitation structure information at different vertical altitudes, thereby realizing the detection of vertical precipitation.

[0069] Among them, the dual-frequency precipitation measurement radar can emit radar waves of different frequencies and use the differences in the characteristics of different frequency waves during propagation to obtain relevant information such as precipitation; the microwave imager generates images by receiving microwave signals reflected or emitted by the target area.

[0070] Furthermore, dual-frequency precipitation measurement radar can analyze the intensity and distribution of precipitation based on echo signals, and indirectly assist in obtaining flood-related information by combining the relationship between precipitation and floods; the images generated by the microwave imager can intuitively show the extent of flooding on the ground surface, and the flooded area can be accurately calculated through image analysis and processing. At the same time, utilizing the high-resolution characteristics of the equipment, disaster-bearing bodies can be identified and measured to obtain their physical information, such as the height and shape of buildings, and the size of infrastructure.

[0071] Step S133: Optimize the disaster prediction information output by the disaster chain identification algorithm model using the disaster-causing factors, the flood inundation area and water depth of the affected area, and the physical information of the disaster-bearing body to obtain optimized disaster prediction information.

[0072] Specifically, the dual-frequency precipitation measurement radar and microwave imager of the domestically produced Fengyun-3G satellite were used to acquire key physical information on the flooded area and water depth in the affected area during the evolution of the typhoon disaster chain, as well as disaster-bearing structures such as river embankments and reservoirs. The monitoring results were further optimized by using an adaptive real-time typhoon-rainstorm-flood disaster chain identification algorithm model, benchmarked against the characteristic parameters and band selection of the domestic satellite payload.

[0073] As one implementation method, the characteristic parameters and band selection of the precipitation measurement radar and microwave imager payload of the domestic Fengyun-3G satellite can be benchmarked to construct an adaptive real-time typhoon rainstorm and flood disaster chain identification algorithm model, and obtain the flood inundation area and water depth of the affected area during the evolution of the typhoon disaster chain, as well as the key physical information of disaster-bearing bodies such as river embankments and reservoirs.

[0074] This application utilizes a dual-frequency precipitation measurement radar and microwave imaging technology from a satellite to acquire high-resolution monitoring data. The dual-frequency precipitation measurement radar can accurately detect precipitation structure information at different vertical heights, and combined with the microwave imager's acquisition of flood inundation range and physical information of disaster-bearing bodies, multi-dimensional and high-precision monitoring of the typhoon disaster chain impact area is achieved. This comprehensive monitoring can more accurately reflect the actual situation of the disaster, providing a reliable data foundation for subsequent disaster analysis and prediction.

[0075] In addition, the embodiments of this application optimize the disaster chain identification algorithm model by inputting the actual monitored disaster-causing factors, flood inundation area and water depth, and physical information of the disaster-bearing body into the disaster chain identification model, which can promptly correct errors and uncertainties in the model prediction.

[0076] In addition, the embodiments of this application fully utilize the advantages of the precipitation measurement radar and microwave imager of the domestically produced Fengyun-3G satellite, thereby enhancing the application value of domestically produced satellites in natural disaster monitoring.

[0077] Based on the above embodiments, in Embodiment Six of this application, the same or similar content as the above embodiments can be referred to the above description, and will not be repeated hereafter. Based on this, step S50, collecting multi-source satellite remote sensing data, includes steps S10~S40 before: Step S10: Collect multi-source satellite remote sensing training data; Step S20: Preprocess the multi-source satellite remote sensing training data; Step S30: Train the primary inversion algorithm model based on the preprocessed multi-source satellite remote sensing training data; Step S40: Optimize the model parameters of the primary inversion algorithm model by comparing and analyzing the water extraction effects of at least two of the visible light, infrared light, and microwave bands to obtain the satellite remote sensing inversion algorithm model.

[0078] This application uses multi-source remote sensing data, including meteorological satellites (such as TRMM, GPM, Suomi-NPP / VIIRS, AVHRR, MODIS, etc.), radar, and high-resolution optical images (such as LandSat-8, Sentinel-2), combined with satellite cloud images, to identify the rainfall range and intensity during the formation and development of typhoons.

[0079] By utilizing high spatial resolution imagery and radar data, accurate extraction of flood inundation areas can be achieved. Drawing upon mature international flood identification and inversion algorithms, flood disaster monitoring models using polar-orbiting and geostationary meteorological satellites are established. The water body extraction effects in the visible, infrared, and microwave bands are compared and analyzed. A typhoon-rainstorm-flood disaster chain inversion algorithm model is constructed, thereby improving the accuracy of extracting rainfall range, intensity, and flood inundation area.

[0080] This application embodiment collects multi-source satellite remote sensing training data, preprocesses the multi-source satellite remote sensing training data, trains a primary inversion algorithm model based on the preprocessed multi-source satellite remote sensing training data, and optimizes the model parameters of the primary inversion algorithm model by comparing and analyzing the water body extraction effects of at least two of the visible light, infrared light and microwave bands, thus obtaining the satellite remote sensing inversion algorithm model, which can improve the extraction accuracy of rainfall range, intensity and flood inundation range.

[0081] For example, to help understand the implementation process of the disaster-causing factor extraction method obtained by combining this embodiment with the above embodiment one, please refer to... Figure 3 , Figure 3 A simplified flowchart of a method for extracting disaster-causing factors is provided. Specifically, the process includes the following steps: 1. Data collection and preprocessing: Collect multi-source satellite remote sensing data and preprocess the multi-source satellite remote sensing data. Input the preprocessed data into the satellite remote sensing inversion algorithm model to obtain at least one of the following: rainfall intensity distribution map, flood inundation range map, and flood inundation depth estimation map.

[0082] 2. Constructing a satellite remote sensing inversion algorithm model: Collect multi-source satellite remote sensing training data, preprocess the multi-source satellite remote sensing training data, train a primary inversion algorithm model based on the preprocessed multi-source satellite remote sensing training data, optimize the model parameters of the primary inversion algorithm model by comparing and analyzing the water body extraction effects of at least two of the visible light, infrared light and microwave bands, and obtain the satellite remote sensing inversion algorithm model.

[0083] 3. Real-time automatic identification and tracking of disaster chains: Based on at least one of the satellite cloud image, the meteorological radar data, and the ground station data, disaster prediction information is obtained by using a pre-built disaster chain identification algorithm model.

[0084] 4. Extraction of disaster-causing factors / elements: The disaster-causing elements are extracted based on at least one of the rainfall intensity distribution map, the flood inundation range map, the flood inundation depth estimation map, the disaster prediction information, and static geographic data.

[0085] 5. Application of domestic satellite remote sensing data: By using the dual-frequency precipitation measurement radar and microwave imaging of satellites, the flood inundation area and water depth of the affected area during the evolution of the typhoon disaster chain are obtained, as well as the physical information of the disaster-bearing bodies; the disaster-causing factors, the flood inundation area and water depth of the affected area, and the physical information of the disaster-bearing bodies are used to optimize the disaster prediction information output by the disaster chain identification algorithm model to obtain optimized disaster prediction information.

[0086] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the disaster-causing element extraction method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0087] This application also provides a disaster-causing factor extraction device, please refer to... Figure 4 The disaster-causing element extraction device includes: Data collection module 10 is used to collect multi-source satellite remote sensing data; Data processing module 20 is used to input the multi-source satellite remote sensing data into a pre-constructed satellite remote sensing inversion algorithm model to obtain at least one of the following: rainfall intensity distribution map, flood inundation range map, and flood inundation depth estimation map; The element extraction module 30 is used to extract disaster-causing elements based on at least one of the rainfall intensity distribution map, the flood inundation range map, and the flood inundation depth estimation map.

[0088] The disaster-causing element extraction device provided in this application, employing the disaster-causing element extraction method described in the above embodiments, can solve the technical problem of the current inability to comprehensively utilize multi-source satellite remote sensing data to efficiently extract key disaster-causing elements in the typhoon and rainstorm disaster chain. Compared with the prior art, the beneficial effects of the disaster-causing element extraction device provided in this application are the same as those of the disaster-causing element extraction method provided in the above embodiments, and other technical features in the disaster-causing element extraction device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0089] This application provides a disaster-causing element extraction device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the disaster-causing element extraction method in the above embodiment 1.

[0090] The following is for reference. Figure 5 The diagram illustrates a structural schematic of a disaster-causing element extraction device suitable for implementing embodiments of this application. The disaster-causing element extraction device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), vehicle terminals (e.g., vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The disaster-causing element extraction device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0091] like Figure 5As shown, the disaster-causing element extraction device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory 1002 or a program loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the disaster-causing element extraction device. The processing unit 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the disaster factor extraction device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows disaster factor extraction devices with various systems, it should be understood that it is not required to implement or possess all of the systems shown. More or fewer systems may be implemented alternatively.

[0092] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0093] The disaster-causing element extraction device provided in this application, employing the disaster-causing element extraction method described in the above embodiments, can solve the technical problem of the current inability to comprehensively utilize multi-source satellite remote sensing data to efficiently extract key disaster-causing elements in the typhoon and rainstorm disaster chain. Compared with the prior art, the beneficial effects of the disaster-causing element extraction device provided in this application are the same as those of the disaster-causing element extraction method provided in the above embodiments, and other technical features of this disaster-causing element extraction device are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0094] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0095] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0096] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the disaster-causing element extraction method in the above embodiments.

[0097] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0098] The aforementioned computer-readable storage medium may be included in the disaster factor extraction device; or it may exist independently and not be assembled into the disaster factor extraction device.

[0099] The aforementioned computer-readable storage medium carries one or more programs. When the aforementioned one or more programs are executed by the disaster-causing element extraction device, the disaster-causing element extraction device causes the following: to collect multi-source satellite remote sensing data; to input the multi-source satellite remote sensing data into a pre-constructed satellite remote sensing inversion algorithm model to obtain at least one of a rainfall intensity distribution map, a flood inundation range map, and a flood inundation depth estimation map; and to extract disaster-causing elements based on at least one of the rainfall intensity distribution map, the flood inundation range map, and the flood inundation depth estimation map.

[0100] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0101] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0102] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0103] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described disaster-causing element extraction method. This solves the technical problem of the current inability to comprehensively utilize multi-source satellite remote sensing data to efficiently extract key disaster-causing elements in typhoon and rainstorm disaster chains. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the disaster-causing element extraction method provided in the above embodiments, and will not be elaborated upon here.

[0104] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A hazard extracting method characterized by comprising: The method comprises: collecting multi-source satellite remote sensing data; inputting the multi-source satellite remote sensing data into a pre-constructed satellite remote sensing inversion algorithm model to obtain at least one of a rainfall intensity distribution map, a flood inundation range map, and a flood inundation water depth estimation map; extracting a disaster-causing element based on at least one of the rainfall intensity distribution map, the flood inundation range map, and the flood inundation water depth estimation map.

2. The method of claim 1, wherein, The step of extracting the disaster-causing element based on at least one of the rainfall intensity distribution map, the flood inundation range map, and the flood inundation water depth estimation map comprises: obtaining at least one of a satellite cloud image, meteorological radar data, and ground station data; identifying and / or tracking a disaster based on at least one of the satellite cloud image, the meteorological radar data, and the ground station data through a pre-constructed disaster chain identification algorithm model to obtain disaster prediction information; obtaining static geographic data; The step of extracting the disaster-causing element based on at least one of the rainfall intensity distribution map, the flood inundation range map, and the flood inundation water depth estimation map comprises: extracting the disaster-causing element based on at least one of the rainfall intensity distribution map, the flood inundation range map, and the flood inundation water depth estimation map and the disaster prediction information and the static geographic data.

3. The method of claim 2, wherein, The step of identifying and / or tracking a disaster based on at least one of the satellite cloud image, the meteorological radar data, and the ground station data through a pre-constructed disaster chain identification algorithm model to obtain disaster prediction information comprises: observing the cold and warm features of a typhoon cloud system based on an infrared image in the satellite cloud image; obtaining water vapor distribution information of a typhoon affected area based on a water vapor image in the satellite cloud image; obtaining classification information of different cloud elements in the satellite cloud image; The step of identifying and / or tracking a disaster based on at least one of the satellite cloud image, the meteorological radar data, and the ground station data through a pre-constructed disaster chain identification algorithm model to obtain disaster prediction information comprises: identifying and / or tracking a typhoon based on at least one of the cold and warm features of the typhoon cloud system, the water vapor distribution information of the typhoon affected area, the classification information of the different cloud elements, the meteorological radar data, and the ground station data through the pre-constructed disaster chain identification algorithm model to obtain at least one of a position, a shape, and a movement trajectory of the typhoon.

4. The method of claim 2, wherein, The step of obtaining static geographic data comprises: identifying a human activity area and / or a facility through remote sensing images; obtaining spatial analysis of urban waterlogging based on the human activity area and / or the facility through a geographic information system as the static geographic data.

5. The method of claim 2, wherein, The step of extracting the disaster-causing element based on at least one of the rainfall intensity distribution map, the flood inundation range map, and the flood inundation water depth estimation map and the disaster prediction information and the static geographic data comprises: obtaining flood inundation area and water depth in an affected area and physical information of a disaster-bearing body in a typhoon disaster chain evolution process through satellite dual-frequency precipitation measurement radar and microwave imaging; The disaster-causing element, the flood inundation area and water depth of the influence area, and the physical information of the disaster-bearing body are used to optimize the disaster prediction information output by the disaster chain identification algorithm model, to obtain optimized disaster prediction information.

6. The method of claim 1, wherein, The step of collecting multi-source satellite remote sensing data comprises: collecting multi-source satellite remote sensing training data; preprocessing the multi-source satellite remote sensing training data; training a primary inversion algorithm model based on the preprocessed multi-source satellite remote sensing training data; comparing and analyzing the water body extraction effects of at least two of the visible light, infrared light and microwave bands to optimize the model parameters of the primary inversion algorithm model, to obtain the satellite remote sensing inversion algorithm model.

7. The method of any one of claims 1 to 6, wherein, The disaster-causing element includes at least one of rainfall, water body change, residential area, lifeline engineering, mountain flood, and dam breach of river embankment / reservoir.

8. A hazard extracting apparatus characterized by comprising: The device comprises: a data collection module for collecting multi-source satellite remote sensing data; a data processing module for inputting the multi-source satellite remote sensing data into a pre-constructed satellite remote sensing inversion algorithm model to obtain at least one of a rainfall intensity distribution map, a flood inundation range map, and a flood inundation water depth estimation map; an element extraction module for extracting a disaster-causing element based on at least one of the rainfall intensity distribution map, the flood inundation range map, and the flood inundation water depth estimation map.

9. A hazard extracting apparatus characterized by comprising: The device comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the disaster-causing element extraction method according to any one of claims 1 to 7.

10. A storage medium, characterized by The storage medium is a computer-readable storage medium, and the storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the disaster-causing element extraction method according to any one of claims 1 to 7.

Images