A flood monitoring and early warning method and system based on multi-source remote sensing satellite data fusion

Abstract

The present invention proposes a flood monitoring and early warning method and system based on the fusion of multi-source remote sensing satellite data. The present invention collects various types of remote sensing satellite data of flood areas; pre-processes the collected remote sensing satellite data; integrates the pre-processed multiple remote sensing satellite data with features of different scales to obtain feature fusion; generalizes the feature fusion based on the revisited channel attention module from the same-layer scene to the cross-layer scene; utilizes the fused remote sensing images to identify floods and extract the boundaries and scope of the flood area; conducts flood warnings based on the identified flood areas and historical flood data, combined with meteorological and hydrological information, to obtain warning results; and conducts a comprehensive analysis of the causes, processes, and impacts of flood events. By integrating multi-source satellite data, the present invention aims to improve the accuracy of large-scale flood detection and enhance the ability to predict flood trends, thereby ensuring the accuracy and reliability of spatiotemporal flood warnings.

Description

Technical Field

[0001] The present invention belongs to the field of remote sensing geographic information technology, and in particular relates to a flood monitoring and early warning method and system based on multi-source remote sensing satellite data fusion. Background Art

[0002] With global climate change and accelerating urbanization, floods are becoming more frequent, posing a serious threat to people's lives and property. Therefore, timely and accurate access to flood disaster information, as well as flood warning and analysis, is crucial for mitigating flood losses. Traditional flood warning methods primarily rely on ground-based observation stations and meteorological data. However, these methods suffer from limited observation ranges and delayed data updates. In recent years, advances in remote sensing technology have provided new solutions for flood warning. Multi-source remote sensing satellites can provide large-scale, rapid, and accurate surface information, providing crucial data support for flood warning and analysis.

[0003] In recent years, with the rapid development of remote sensing technology, the application of multi-source remote sensing satellites for flood early warning and analysis has become increasingly widespread. Many scholars and research institutions at home and abroad are dedicated to researching the use of remote sensing data for flood early warning and analysis. Currently, a number of flood analysis methods and early warning systems based on remote sensing technology have been developed and have achieved certain results in practical applications. These systems primarily use remote sensing data to extract flood characteristics and combine them with ground observations and meteorological data to provide flood warning and analysis. However, how to effectively integrate multi-source remote sensing satellite data to improve the accuracy and efficiency of flood early warning and analysis remains a pressing challenge. Multi-source remote sensing satellite data has different spatial, temporal, and spectral resolutions. How to effectively integrate these data and extract flood characteristics is one of the key issues that needs to be addressed. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention proposes a flood monitoring and early warning method and system based on multi-source remote sensing satellite data fusion, constructs a revisit channel attention module, and aims to improve the accuracy and timeliness of flood warnings by integrating different types of remote sensing satellite data;

[0005] The technical solution of the method of the present invention is a flood monitoring and early warning method based on multi-source remote sensing satellite data fusion, and the specific steps are as follows:

[0006] Step 1: Collect various types of remote sensing satellite data of the flooded area;

[0007] Step 2: Perform radiometric calibration, geometric correction, and atmospheric correction preprocessing on the collected remote sensing satellite data to eliminate noise and interference in the data;

[0008] Step 3: The pre-processed remote sensing satellite data are integrated with features of different scales to achieve better performance through feature fusion; the feature fusion based on the revisit channel attention module is extended from the same-layer scenario to the cross-layer scenario;

[0009] Step 4: Utilize the fused remote sensing image to identify floods by using threshold segmentation, edge detection, and morphological processing to extract the boundaries and extent of the flood area;

[0010] Step 5: Based on the identified flood areas and historical flood data, combined with meteorological and hydrological information, flood warnings are issued to obtain warning results;

[0011] Step 6: Conduct a comprehensive analysis of flood causes, flood processes, and flood impacts.

[0012] Preferably, the remote sensing satellite data collection in step 1 needs to ensure the timeliness and accuracy of the data so as to obtain the latest surface information in a timely manner; at the same time, factors such as the coverage and resolution of different remote sensing satellite data need to be considered to ensure the comprehensiveness and reliability of the data.

[0013] Preferably, in step 2, data preprocessing can eliminate radiation errors in remote sensing images through radiometric calibration, thereby improving the radiation accuracy of images; geometric correction can eliminate geometric distortion in images, thereby making images more consistent with the true surface morphology; atmospheric correction can eliminate the influence of the atmosphere on remote sensing images, thereby improving the clarity and contrast of images; the distortion correction formula is:

[0014]

[0015] is the satellite's internal parameter, measuring the radial distance; and is the radial distortion coefficient.

[0016] Preferably, the data fusion in step 3 is to further improve the quality and resolution of the remote sensing image; a revisit channel attention module is constructed for data fusion;

[0017] The feature fusion based on the revisit channel attention module is extended from the same-layer scenario to the cross-layer scenario, including short skip connections and long skip connections, and even internal feature integration;

[0018] The revisit channel attention module includes a multi-scale channel fusion submodule, a local channel context aggregation submodule, and a global context fusion submodule; the input is a data feature map from different satellites, the size of Channels and feature maps; these inputs are used for subsequent feature extraction and attention weight calculation;

[0019] First, the multi-scale channel fusion submodule performs multi-scale feature fusion on the input multi-source satellite data; given a source satellite data , the size is Channel and feature map, channel attention weight The calculation formula is as follows:

[0020] ;

[0021] in represents the global feature context, and is global average pooling; represents the ReLU activation function, represents batch normalization; yes function; this is achieved by linking two fully connected layers, where is the dimensionality reduction layer, It is a dimensionality-increasing layer; it aggregates local and multi-source data context information;

[0022] The local channel context aggregation submodule aggregates local context through the convolution operation PWConv. The key idea is that by changing the spatial pooling size, channel attention can be achieved at multiple scales. The local context needs to be added to the global context in the attention module. Point-by-point convolution is selected as the local channel context aggregator, utilizing the point-by-point channel interaction at each spatial location. The local channel context L(X) is calculated as follows:

[0023]

[0024] Among them, PWConv is the convolution kernel Convolution; L(X) retains and highlights the details in low-level features;

[0025] Finally, the global context fusion submodule combines the local channel context and the global channel context to obtain the global feature representation of multi-source data. :

[0026]

[0027] in represents the generated attention weight; represents broadcast addition, represents element-wise multiplication; N represents multiple satellite data sources.

[0028] Preferably, flood identification in step 4 is a key step in flood warning and analysis. By adopting image processing techniques such as threshold segmentation, edge detection, and morphological processing, the boundaries and scope of the flood area can be effectively extracted. At the same time, other auxiliary information such as topographic, geomorphological, and meteorological data can be combined to more accurately and comprehensively identify and analyze the flood area. The flood identification index NDWI is calculated as follows:

[0029]

[0030] NIR represents the reflectance of the near-infrared band, and SWIR represents the reflectance of the short-wave infrared band. Deep learning is used to extract flood areas from optical remote sensing images. The input image is defined as , and its corresponding feature map is ; Its goal is to generate a binary mask ,in Represents pixels Is it a flood area? Use convolutional layers and pooling layers to extract high-level features of the image. The output feature map of the encoder is ;

[0031] Decoder Map it back to the original image size; use deconvolution layers and upsampling operations to restore the resolution; the output of the decoder is ;

[0032] Use a convolutional layer to generate a water segmentation probability map ,in Represents pixels The probability of belonging to water body; the probability map With a threshold Compare to get the final binary mask :

[0033]

[0034] The formula of the entire spinous process deep learning model for extracting flood area from optical remote sensing images can be expressed as:

[0035]

[0036] It is a threshold processing function.

[0037] Preferably, in step 5, flood warning needs to comprehensively consider multiple factors, including historical flood data, meteorological, hydrological and other information; by analyzing and modeling these factors, the probability of flood occurrence, peak flow, arrival time and other information can be predicted, providing an important reference for disaster prevention and response; flood warning model:

[0038]

[0039] It is a flood prediction model based on Transformer architecture; is the characteristic vector of historical flood data, including the frequency of past flood events, peak flow, flood duration, etc.; historical data can be obtained through statistical analysis; Q is the characteristic value of meteorological factors, including rainfall, rainfall intensity, rainfall distribution, etc.; meteorological data can be obtained from weather stations, satellites or other meteorological sensors; Hydrological factors, including the basin's topography, soil type, river network, and water storage capacity; hydrological data can be obtained through hydrological models and geographic information systems;

[0040] The warning results in step 5 include: probability of flood occurrence, flood peak flow, and flood arrival time information.

[0041] Preferably, the comprehensive analysis in step 6 is as follows:

[0042] Using geographic information system technology, flood data is overlaid and analyzed with geographical information such as topography, landforms, and population distribution to provide decision support for post-disaster rescue and reconstruction;

[0043] In step 6, flood warning requires analysis of flood causes, processes, and impacts, which can provide important experience and lessons for future disaster prevention and response. At the same time, it is also possible to use technologies such as geographic information systems (GIS) to overlay and analyze flood data with relevant geographic information, providing more scientific and effective decision-making support for post-disaster rescue and reconstruction.

[0044] The technical solution of the system of the present invention is a flood monitoring and early warning system integrating multi-source remote sensing satellite data, comprising:

[0045] Data acquisition module, used to collect various types of remote sensing satellite data in flood areas;

[0046] The preprocessing module is used to perform radiometric calibration, geometric correction, and atmospheric correction on the collected remote sensing satellite data to eliminate noise and interference in the data;

[0047] The feature fusion module is used to integrate features of different scales from pre-processed remote sensing satellite data to achieve better performance. The feature fusion module based on the revisited channel attention module is extended from the same-layer scenario to the cross-layer scenario.

[0048] The flood area identification module is used to identify floods using the fused remote sensing images through threshold segmentation, edge detection, and morphological processing to extract the boundaries and scope of the flood area;

[0049] The early warning module is used to provide flood warnings based on the identified flood areas and historical flood data, combined with meteorological and hydrological information, to obtain early warning results;

[0050] The comprehensive analysis module is used to conduct comprehensive analysis of flood causes, flood processes, and flood impacts.

[0051] This paper proposes a flood warning and analysis method based on the fusion of multi-source remote sensing satellite data using a revisited channel attention module. Compared with the traditional single remote sensing data source method, it has the following significant advantages and beneficial effects:

[0052] By integrating different types of remote sensing satellite data, the accuracy of large-scale flood detection can be improved, and the ability to predict flood trends can be strengthened, thereby ensuring the accuracy and reliability of flood spatiotemporal warnings. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 : A flow chart of a method according to an embodiment of the present invention.

[0054] Figure 2 : Flood prediction and warning map of an embodiment of the present invention. DETAILED DESCRIPTION

[0055] 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.

[0056] In specific implementation, the method proposed in the technical solution of the present invention can be automatically run by those skilled in the art using computer software technology. System devices that implement the method, such as computer-readable storage media that store the corresponding computer program of the technical solution of the present invention and computer equipment that runs the corresponding computer program, should also be within the scope of protection of the present invention.

[0057] The following is combined with Figure 1-2 The specific embodiment of the present invention is a flood monitoring and early warning method and system based on multi-source remote sensing satellite data fusion, which is as follows:

[0058] The specific implementation of the method of the present invention is a flood monitoring and early warning method based on multi-source remote sensing satellite data fusion, and the specific steps are as follows:

[0059] like Figure 1 FIG. 1 is a flow chart of a method according to an embodiment of the present invention.

[0060] Remote sensing data of flood-affected areas are collected through satellite remote sensing platforms.

[0061] Each step in the remote sensing data collection process for flood-affected areas is crucial. The first is satellite selection, which needs to be determined based on the specific needs of flood monitoring. For example, for large-scale flood monitoring, satellites with broad coverage and high resolution, such as MODIS or the Sentinel series, should be selected. Second, determining the type of remote sensing data required is crucial, including optical imagery and synthetic aperture radar (SAR) imagery. Optical imagery excels in clear weather conditions, while SAR imagery can penetrate clouds and is suitable for cloudy or rainy conditions.

[0062] Data acquisition is achieved through satellite remote sensing platforms such as the Earth Observing System Data and Information System (EOSDIS) or the European Space Agency's (ESA) Copernicus open access hub. After acquisition, the raw remote sensing data requires preprocessing, including radiometric, atmospheric, and geometric corrections, to improve data accuracy and usability.

[0063] Based on data processing, image processing and analysis techniques, such as water index calculation and classification algorithms, are applied to extract flood characteristics from the processed remote sensing data. Finally, this extracted flood characteristic information is integrated with other relevant data (such as topography, land use, and meteorological data) for comprehensive analysis to more accurately assess flood conditions. This series of steps constitutes the key process for collecting remote sensing data in flood-affected areas.

[0064] Step 1: Collect various types of remote sensing satellite data of the flooded area;

[0065] The remote sensing satellite data collection in step 1 needs to ensure the timeliness and accuracy of the data so as to obtain the latest surface information in a timely manner; at the same time, factors such as the coverage and resolution of different remote sensing satellite data need to be considered to ensure the comprehensiveness and reliability of the data.

[0066] Step 2: Perform radiometric calibration, geometric correction, and atmospheric correction preprocessing on the collected remote sensing satellite data to eliminate noise and interference in the data;

[0067] In step 2, data preprocessing can eliminate radiation errors in remote sensing images through radiometric calibration, thereby improving the radiation accuracy of images; geometric correction can eliminate geometric distortion in images, making them more consistent with the true surface morphology; atmospheric correction can eliminate the influence of the atmosphere on remote sensing images, thereby improving the clarity and contrast of images; the distortion correction formula is:

[0068]

[0069] =0.4 is the internal parameter of the satellite, measuring the radial distance; =0.6 and =0.3 is the radial distortion coefficient.

[0070] Step 3: The pre-processed remote sensing satellite data are integrated with features of different scales to achieve better performance through feature fusion; the feature fusion based on the revisit channel attention module is extended from the same-layer scenario to the cross-layer scenario;

[0071] The data fusion in step 3 is to further improve the quality and resolution of remote sensing images; a revisit channel attention module is constructed for data fusion;

[0072] The feature fusion based on the revisit channel attention module is extended from the same-layer scenario to the cross-layer scenario, including short skip connections and long skip connections, and even internal feature integration;

[0073] The revisit channel attention module includes a multi-scale channel fusion submodule, a local channel context aggregation submodule, and a global context fusion submodule; the input is a data feature map from different satellites, the size of Channels and feature maps; these inputs are used for subsequent feature extraction and attention weight calculation;

[0074] First, the multi-scale channel fusion submodule performs multi-scale feature fusion on the input multi-source satellite data; given a source satellite data , the size is Channel and feature map, channel attention weight The calculation formula is as follows:

[0075] ;

[0076] in represents the global feature context, and is global average pooling; represents the ReLU activation function, represents batch normalization; yes function; this is achieved by linking two fully connected layers, where is the dimensionality reduction layer, It is a dimensionality-increasing layer; it aggregates local and multi-source data context information;

[0077] The local channel context aggregation submodule aggregates local context through the convolution operation PWConv. The key idea is that by changing the spatial pooling size, channel attention can be achieved at multiple scales. The local context needs to be added to the global context in the attention module. Point-by-point convolution is selected as the local channel context aggregator, utilizing the point-by-point channel interaction at each spatial location. The local channel context L(X) is calculated as follows:

[0078]

[0079] Among them, PWConv is the convolution kernel Convolution; L(X) retains and highlights the details in low-level features;

[0080] Finally, the global context fusion submodule combines the local channel context and the global channel context to obtain the global feature representation of multi-source data. :

[0081]

[0082] in represents the generated attention weight; represents broadcast addition, represents element-wise multiplication; N represents multiple satellite data sources.

[0083] Step 4: Utilize the fused remote sensing image to identify floods by using threshold segmentation, edge detection, and morphological processing to extract the boundaries and extent of the flood area;

[0084] Flood identification in step 4 is a key step in flood warning and analysis. By using image processing techniques such as threshold segmentation, edge detection, and morphological processing, the boundaries and scope of the flood area can be effectively extracted. At the same time, other auxiliary information such as topographic, geomorphological, and meteorological data can be combined to more accurately and comprehensively identify and analyze the flood area. The flood identification index NDWI is calculated as follows:

[0085]

[0086] NIR represents the reflectance of the near-infrared band, and SWIR represents the reflectance of the short-wave infrared band. Deep learning is used to extract flood areas from optical remote sensing images. The input image is defined as , and its corresponding feature map is ; Its goal is to generate a binary mask ,in Represents pixels Is it a flood area? Use convolutional layers and pooling layers to extract high-level features of the image. The output feature map of the encoder is ;

[0087] Decoder Map it back to the original image size; use deconvolution layers and upsampling operations to restore the resolution; the output of the decoder is ;

[0088] Use a convolutional layer to generate a water segmentation probability map ,in Represents pixels The probability of belonging to water body; the probability map With a threshold = 0.7 to obtain the final binary mask :

[0089]

[0090] The formula of the entire spinous process deep learning model for extracting flood area from optical remote sensing images can be expressed as:

[0091]

[0092] It is a threshold processing function.

[0093] Step 5: Based on the identified flood areas and historical flood data, combined with meteorological and hydrological information, flood warnings are issued to obtain warning results;

[0094] In step 5, flood warning needs to comprehensively consider multiple factors, including historical flood data, meteorological, hydrological and other information. By analyzing and modeling these factors, the probability of flood occurrence, peak flow, arrival time and other information can be predicted, providing an important reference for disaster prevention and response. Flood warning model:

[0095]

[0096] It is a flood prediction model based on Transformer architecture; is the characteristic vector of historical flood data, including the frequency of past flood events, peak flow, flood duration, etc.; historical data can be obtained through statistical analysis; Q is the characteristic value of meteorological factors, including rainfall, rainfall intensity, rainfall distribution, etc.; meteorological data can be obtained from weather stations, satellites or other meteorological sensors; Hydrological factors, including the basin's topography, soil type, river network, and water storage capacity; hydrological data can be obtained through hydrological models and geographic information systems;

[0097] The warning results in step 5 include: probability of flood occurrence, flood peak flow, and flood arrival time information.

[0098] Step 6: Conduct a comprehensive analysis of flood causes, flood processes, and flood impacts.

[0099] The comprehensive analysis described in step 6 is as follows:

[0100] Using geographic information system technology, flood data is overlaid and analyzed with geographical information such as topography, landforms, and population distribution to provide decision support for post-disaster rescue and reconstruction;

[0101] In step 6, flood warning requires analysis of flood causes, processes, and impacts, which can provide important experience and lessons for future disaster prevention and response. At the same time, it is also possible to use technologies such as geographic information systems (GIS) to overlay and analyze flood data with relevant geographic information, providing more scientific and effective decision-making support for post-disaster rescue and reconstruction.

[0102] The early warning system receives and processes a variety of data in real time, including remote sensing imagery, meteorological information, and hydrological data, applying advanced algorithms and models to analyze and predict floods. Once the system detects that flood risk exceeds a preset threshold, it immediately generates a warning and notifies relevant departments and personnel via SMS, email, and app push notifications. The system also provides real-time monitoring and dynamic updates of flood coverage, helping decision-makers stay informed of the latest flood conditions and trends and formulate effective response measures.

[0103] like Figure 2 As shown, the system and method of the present invention extracted flood areas in the Canterbury flood zone in southeast England and inferred the flood warning area. Comparing the flood areas with those two weeks later, the prediction accuracy of the system of the present invention can reach over 80%.

[0104] The specific embodiment of the system of the present invention is a flood monitoring and early warning system integrating multi-source remote sensing satellite data, comprising:

[0105] Data acquisition module, used to collect various types of remote sensing satellite data in flood areas;

[0106] The preprocessing module is used to perform radiometric calibration, geometric correction, and atmospheric correction on the collected remote sensing satellite data to eliminate noise and interference in the data;

[0107] The feature fusion module is used to integrate features of different scales from pre-processed remote sensing satellite data to achieve better performance. The feature fusion module based on the revisited channel attention module is extended from the same-layer scenario to the cross-layer scenario.

[0108] The flood area identification module is used to identify floods using the fused remote sensing images through threshold segmentation, edge detection, and morphological processing to extract the boundaries and scope of the flood area;

[0109] The early warning module is used to provide flood warnings based on the identified flood areas and historical flood data, combined with meteorological and hydrological information, to obtain early warning results;

[0110] The comprehensive analysis module is used to conduct comprehensive analysis of flood causes, flood processes, and flood impacts.

[0111] It should be understood that parts not elaborated in detail in this specification belong to the prior art.

[0112] It should be understood that the above description of the preferred embodiment is relatively detailed and cannot be regarded as limiting the scope of protection of the patent of the present invention. Under the guidance of the present invention, ordinary technicians in this field can also make substitutions or modifications without departing from the scope of protection of the claims of the present invention, which all fall within the scope of protection of the present invention. The scope of protection requested by the present invention shall be based on the attached claims.

Claims

1. A flood monitoring and early warning method based on multi-source remote sensing satellite data fusion, characterized in that: The following steps are involved: Step 1: Collect various types of remote sensing satellite data of the flooded area; Step 2: Perform radiometric calibration, geometric correction, and atmospheric correction preprocessing on the collected remote sensing satellite data to eliminate noise and interference in the data; Step 3: The pre-processed remote sensing satellite data are integrated with features of different scales to achieve better performance through feature fusion; Multi-scale feature fusion is performed based on the data feature maps of different satellites to obtain the channel attention weights of different satellites, including: The revisit channel attention module includes a multi-scale channel fusion submodule, a local channel context aggregation submodule, and a global context fusion submodule; the input is a data feature map from different satellites, the size of Channels and feature maps; these inputs are used for subsequent feature extraction and attention weight calculation; First, the multi-scale channel fusion submodule performs multi-scale feature fusion on the input multi-source satellite data; given a source satellite data , the size is Channel and feature map, channel attention weight The calculation formula is as follows: ； in represents the global feature context, and is global average pooling; represents the ReLU activation function, represents batch normalization; yes function; this is achieved by linking two fully connected layers, where is the dimensionality reduction layer, It is a dimensionality-increasing layer; it aggregates local and multi-source data context information; Step 4: Utilize the fused remote sensing image to identify floods by using threshold segmentation, edge detection, and morphological processing to extract the boundaries and extent of the flood area; Step 5: Based on the identified flood areas and historical flood data, combined with meteorological and hydrological information, flood warnings are issued to obtain warning results; Step 6: Conduct a comprehensive analysis of flood causes, flood processes, and flood impacts.

2. The flood monitoring and early warning method based on multi-source remote sensing satellite data fusion according to claim 1 is characterized by: The remote sensing satellite data collection in step 1 needs to ensure the timeliness and accuracy of the data so as to obtain the latest surface information in a timely manner; at the same time, the coverage and resolution factors of different remote sensing satellite data need to be considered to ensure the comprehensiveness and reliability of the data.

3. The flood monitoring and early warning method based on multi-source remote sensing satellite data fusion according to claim 2 is characterized by: In step 2, data preprocessing eliminates radiation errors in remote sensing images through radiometric calibration to improve the radiometric accuracy of images; geometric correction eliminates geometric distortion in images to make them more consistent with the actual surface morphology; atmospheric correction eliminates the influence of the atmosphere on remote sensing images to improve the clarity and contrast of images; the distortion correction formula is: is the satellite's internal parameter, measuring the radial distance; and is the radial distortion coefficient.

4. The flood monitoring and early warning method based on multi-source remote sensing satellite data fusion according to claim 1 is characterized in that: The local channel context aggregation submodule aggregates local context through the convolution operation PWConv; channel attention is achieved at multiple scales by changing the spatial pooling size; local context needs to be added to the global context within the attention module; point-by-point convolution is selected as the local channel context aggregator, utilizing the point-by-point channel interaction at each spatial position; the local channel context L(X) is calculated as follows: Among them, PWConv is the convolution kernel Convolution; L(X) retains and highlights the details in low-level features; Finally, the global context fusion submodule combines the local channel context and the global channel context to obtain the global feature representation of multi-source data. : in represents the generated attention weight; represents broadcast addition, represents element-wise multiplication; N represents multiple satellite data sources.

5. The flood monitoring and early warning method based on multi-source remote sensing satellite data fusion according to claim 4 is characterized in that: Flood identification in step 4 is a key step in flood warning and analysis. By using threshold segmentation, edge detection, and morphological processing, the boundaries and scope of the flood area are extracted. At the same time, other auxiliary information, including topography, landform, and meteorological data, is combined to identify and analyze the flood area. The flood identification index NDWI is calculated as follows: NIR represents the reflectance of the near-infrared band, and SWIR represents the reflectance of the short-wave infrared band. Deep learning is used to extract flood areas from optical remote sensing images. The input image is defined as , and its corresponding feature map is ; Its goal is to generate a binary mask ,in Represents pixels Is it a flood area? Use convolutional layers and pooling layers to extract high-level features of the image. The output feature map of the encoder is ; Decoder Map it back to the original image size; use deconvolution layers and upsampling operations to restore the resolution; the output of the decoder is ; Use a convolutional layer to generate a water segmentation probability map ,in Represents pixels The probability of belonging to water body; the probability map With a threshold Compare to get the final binary mask : The formula for the entire spinous process deep learning model for extracting flood area from optical remote sensing images is: It is a threshold processing function.

6. The flood monitoring and early warning method based on multi-source remote sensing satellite data fusion according to claim 5 is characterized by: In step 5, flood warning needs to comprehensively consider multiple factors, including historical flood data, meteorological and hydrological information. By analyzing and modeling these factors, the probability of flood occurrence, peak flow, and arrival time information are predicted. Flood warning model: It is a flood prediction model based on Transformer architecture; is the characteristic vector of historical flood data, including the frequency, peak flow, and duration of past flood events; historical data are obtained through statistical analysis; Q is the characteristic value of meteorological factors, including rainfall, rainfall intensity, and rainfall distribution; meteorological data are obtained from weather stations, satellites, or other meteorological sensors; Hydrological factors, including the basin's topography, soil types, river network, and water storage capacity; Hydrological data are obtained through hydrological models and geographic information systems; The warning results in step 5 include: probability of flood occurrence, flood peak flow, and flood arrival time information.

7. The flood monitoring and early warning method based on multi-source remote sensing satellite data fusion according to claim 6 is characterized by: The comprehensive analysis described in step 6 is as follows: Using geographic information system technology, flood data is overlaid and analyzed with topography, landform, and population distribution information to provide decision support for post-disaster rescue and reconstruction.

8. The flood monitoring and early warning method based on multi-source remote sensing satellite data fusion according to claim 7 is characterized by: In step 6, flood warning requires analysis of flood causes, processes, and impacts; at the same time, using geographic information system technology, flood data is overlaid and analyzed with relevant geographic information.

9. A flood monitoring and early warning system based on multi-source remote sensing satellite data fusion, characterized in that: Used to execute the early warning method as claimed in claim 1.

Images