Urban fire start number spatial distribution forecasting method based on deep learning algorithm

Abstract

The invention discloses an urban fire start number spatial distribution forecasting method based on a deep learning algorithm. The urban fire start number spatial distribution forecasting method comprises the steps of collecting original data; preprocessing the original data; determining an input variable and an output variable for the urban fire occurrence forecasting model, wherein the input variable comprises urban land type grid data, meteorological factor time sequence data of several past days and a daily fire occurrence grid map set of several past days; the output variable is an accumulated fire start grid map in several days in the future; the urban fire occurrence forecasting model comprises an encoder and a decoder, the encoder is used for processing a time sequence variable, and the decoder is used for processing an urban land use type space variable and a characteristic variable; and training and evaluating the urban fire start forecasting model. The method can process the time features and the space features together, is high in prediction precision, and effectively improves the accuracy of urban fire risk prediction.

Description

Technical Field

[0001] The present invention relates to the technical field of urban fire prediction, and in particular to a method for predicting the spatial distribution of urban fire numbers based on a deep learning algorithm. Background Art

[0002] With the acceleration of urbanization, urban fire risks are becoming more and more significant. In the face of this challenge, predicting the potential fire risks in urban areas in advance can provide support for urban fire management and fire emergency decision-making, such as providing a scientific basis for measures such as the pre-deployment of fire resources, thereby reducing the probability of fire and reducing the losses caused by fire. However, current research on urban fire risks is mostly focused on calculating the fire risk index of individual buildings, and less on building a regional-scale fire spatial distribution prediction model from the perspective of the entire city.

[0003] Compared with wildfires, urban fires are affected by more factors, showing more complex dynamic characteristics and lower predictability. There are two main types of factors affecting the distribution of urban fires: spatial factors and temporal factors. From a spatial perspective, the population distribution, building types, and functional zoning of a city may affect the risk of urban fires. For example, the land use classification of a city includes residential areas, commercial areas, industrial areas, green areas, etc., and the fire causes of different land use types are different. From a temporal perspective, fire events show cyclical changes with seasonal climate changes. From historical fire records, it can be seen that the probability of fires in summer when the climate is dry is greater than in other seasons. In addition, the probability of fires occurring during the day is often higher than at night. In short, there are many types of urban fires and their mechanisms are complex. How to use known fire influencing factors to infer the spatial distribution of urban fires in the future is a huge challenge. Although some data-driven methods have been applied to urban fire prediction tasks, most of them only consider temporal features or only spatial features, and only a few methods consider both temporal and spatial features. However, even these methods still have deficiencies in the joint modeling of spatial and temporal features, resulting in inaccurate performance in fire prediction.

[0004] Artificial intelligence technologies such as machine learning are expected to overcome the shortcomings of traditional methods in capturing complex disaster mechanisms, establish a mapping relationship between key fire influencing factors and the spatial distribution of fire occurrence, and provide technical support for improving the accuracy of urban fire predictions. Summary of the invention

[0005] The purpose of the present invention is to overcome the shortcomings of traditional technologies in predicting and accurately capturing the spatial distribution patterns of urban fires in the future, and to provide a method for predicting the spatial distribution of urban fires based on a deep learning algorithm.

[0006] The technical solution adopted by the present invention to overcome the technical problems is:

[0007] A method for predicting the spatial distribution of urban fire numbers based on a deep learning algorithm comprises the following steps:

[0008] S1. Collect original data: collect historical fire event data in the urban study area and urban land use type data and meteorological factor data corresponding to each historical fire event;

[0009] S2. Preprocessing the raw data collected in step S1: dividing the urban study area into grid units, and performing spatiotemporal aggregation processing on the historical fire event data in the urban study area; calculating the area ratio of each type of land use in each grid for urban land use types; averaging the meteorological factor data recorded by all meteorological stations in the urban study area for meteorological factors;

[0010] S3, based on the data pre-processed in step S2, determine the input variables and output variables for the urban fire number forecast model: the input variables include urban land type grid data, past Time series data of meteorological factors of the day and the past The three types of input variables are spatial type data, time type data and spatiotemporal type data; the output variable is the future Daily cumulative fire number grid map; , ,and and All are integers;

[0011] S4. Constructing a city fire number prediction model based on deep neural network: the city fire number prediction model includes an encoder and a decoder, wherein the encoder is used to process time series variables, and the decoder is used to process urban land type spatial variables and feature variables;

[0012] S5. Training and evaluation of the urban fire occurrence forecast model: Arrange the input variables and output variables of step S3 to obtain paired data sets, and divide the data sets into a training set, a validation set, and a test set in chronological order and at a preset ratio, wherein the training set and the validation set are used to determine the parameters of the urban fire occurrence forecast model, and the test set is used to evaluate the performance of the urban fire occurrence forecast model.

[0013] Furthermore, in step S1, the historical fire event data of the urban study area includes the address and time of occurrence of each fire; the urban land type data includes two categories: urban and rural land and urban construction land, among which urban and rural land is subdivided into construction land and non-construction land, and urban construction land is subdivided into residential land, public administration and public service land, commercial service facility land, industrial land, logistics and warehousing land, road and transportation facility land, public facility land, green space and square land according to function; the meteorological factor data includes the daily average temperature, daily average relative humidity and daily cumulative rainfall recorded by all meteorological observation stations in the urban study area.

[0014] Furthermore, in step S2, the urban study area is divided into grid cells, and spatiotemporal aggregation processing is performed on the historical fire event data of the urban study area, specifically including:

[0015] In terms of time, the data is divided into daily statistics to form a daily fire number data set;

[0016] In space, the grid cells are divided according to the preset spatial resolution, and the geographic coordinate points of the daily number of fires are counted into the grid cells to form a spatial grid map of the daily number of fires.

[0017] Furthermore, in step S2, for the meteorological factors, the meteorological factor data recorded by all meteorological stations in the urban study area are averaged, specifically including:

[0018] For different meteorological factors, the data recorded by all meteorological stations in the urban study area were averaged to obtain the time series data of daily average temperature, daily average relative humidity and daily accumulated rainfall in the urban study area.

[0019] Furthermore, in step S3, the urban land type raster data is as follows:

[0020] The urban land type raster maps are stacked into multi-channel image data in the spatial dimension. Suppose that the set of all urban land type raster layers is represented as follows:

[0021] (1)

[0022] In formula (1), Represents one of the urban land use type layers. , let the length and width of each raster layer be and , then the variable The dimension size ,Right now, As the input variable of the urban fire number prediction model.

[0023] Further, in step S3, the past The time series data of meteorological factors for the day are as follows:

[0024] The meteorological factors are stacked into multi-feature time series data in the time dimension. Let the time of the day be ,past The time series data of meteorological factors for the day are expressed as follows:

[0025] (2)

[0026] In formula (2), Indicates The time series of meteorological factors of the day, , the meteorological factor time series specifically includes three variables: daily average temperature, daily average relative humidity and daily cumulative rainfall. Then the variable The dimension size is ,Right now, As the input variable of the urban fire number prediction model.

[0027] Further, in step S3, the past The daily fire number grid map collection is as follows:

[0028] past The daily fire number raster map collection is represented as follows:

[0029] (3)

[0030] In formula (3), Indicates Raster map of the number of fires per day, ;

[0031] The empirical orthogonal function decomposition method is used to transform the spatiotemporal data Perform principal component decomposition and retain the previous principal components, so that the previous The cumulative variance explanation rate of the principal components is not less than the preset percentage, as follows:

[0032] (4)

[0033] In formula (4), Represents the number of grids in the daily fire count grid map, Represents the spatial component of the decomposed daily fire count raster map set, Represents the time component of the decomposed daily fire count raster map set, extract As the input variable of the urban fire number prediction model.

[0034] Further, in step S3, in the future The daily cumulative number of fires grid map is as follows:

[0035] By transferring the present day into the future Total days The daily fire count grid map collection is aggregated in time to form the future The daily cumulative number of fires grid map is:

[0036] (5)

[0037] In formula (5), Indicates The daily fire number grid map will be used to The daily cumulative fire number grid map is used as the output variable of the urban fire number prediction model.

[0038] Further, in step S4, the architecture of the encoder includes a long short-term memory network connected to a self-attention mechanism network, and the architecture of the decoder includes a fully connected network and several layers of convolutional neural networks;

[0039] The time series components that the encoder processes include the meteorological factor time variables and the time component of the number of fires per day in history , the specific operations include:

[0040] The meteorological factor time variable and the time component of the historical daily fire count raster map collection Splicing in the time dimension to obtain a composite time series [ E, M ] , composite time series [ E, M ] The dimension is , composite time series [ E, M ] As the input variable of the encoder, the encoder processes the composite time series [ E, M ] Encode, and then use the variable at the last moment of the self-attention mechanism network output as the feature variable , where r is the number of hidden units in the self-attention mechanism network;

[0041] Decoder for processing urban land use type spatial variables and feature variables , the specific operations include:

[0042] First, the feature variables After preprocessing, a fully connected network is used to Transformed into ; Secondly, use matrix transformation to Further transformed into variables ; Then, the variable and variables Concatenate on the channel dimension to obtain composite spatial variables [ Z ̃ , L] , composite spatial variable [ Z ̃ , L] The dimension is ; Input the composite spatial variable into the multi-layer convolutional neural network, and the output of the last layer of convolutional neural network is the future The predicted value of the daily cumulative number of fires grid map is set as .

[0043] Furthermore, in step S5, the training of the urban fire number forecasting model specifically includes:

[0044] Assume that the loss function of the urban fire number forecast model is the mean square error (MSE) of the district-level disaster loss, and the number of training samples is N, where A sample of the future The true and predicted values ​​of the daily cumulative fire number grid map are and , then the loss function is expressed as follows:

[0045] (6)

[0046] Set a number of training iterations, use the training set to back-propagate the mean square error (MSE) of the urban fire occurrence forecast model using the optimizer, and use the validation set to calculate the loss function of the urban fire occurrence forecast model after each round of training. When the number of training iterations of the urban fire occurrence forecast model is reached, stop training; otherwise, continue training the urban fire occurrence forecast model; select the urban fire occurrence forecast model with the best prediction result on the validation set within the iteration cycle as the final trained urban fire occurrence forecast model, and determine the parameters of the urban fire occurrence forecast model.

[0047] The beneficial effects of the present invention are:

[0048] The present invention can effectively capture the spatial distribution characteristics of the expected number of fires at a certain spatial resolution within a certain period of time in the future. The present invention fully considers the spatial and temporal distribution diagrams of urban land use types, meteorological factors and the number of daily fires in the past few days as the prediction variables of the urban fire number forecast model, covering the main factors affecting the occurrence of urban fires. In addition, the present invention proposes an urban fire number forecast model based on a deep neural network, including an encoder and a decoder, which can jointly process temporal characteristics and spatial characteristics, significantly improving the adaptability and prediction accuracy of the forecast model to different types of data, and effectively improving the accuracy of urban fire risk prediction. In addition, predicting the number of potential fires in a city in the future and their spatial distribution is of great significance to urban fire prevention and control and fire emergency management. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a flow chart of the method for predicting the spatial distribution of the number of urban fires based on a deep learning algorithm according to an embodiment of the present invention.

[0050] Figure 2 This is a schematic diagram of converting the original point data of historical fire events into a spatial grid map of the number of daily fires after preprocessing in an embodiment of the present invention.

[0051] Figure 3 Schematic diagram of the architecture of the urban fire number forecasting model described in an embodiment of the present invention.

[0052] Figure 4 This is the comparison result between the actual value and the predicted value of the spatial distribution of the cumulative number of fires in the next 30 days in the embodiment of the present invention. DETAILED DESCRIPTION

[0053] In order to facilitate those skilled in the art to better understand the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The following is only exemplary and does not limit the protection scope of the present invention.

[0054] The present invention discloses a method for predicting the spatial distribution of urban fire numbers based on a deep learning algorithm, comprising the following steps:

[0055] S1. Collect original data: collect historical fire event data in the urban study area and urban land use type data and meteorological factor data corresponding to each historical fire event;

[0056] S2. Preprocessing the raw data collected in step S1: dividing the urban study area into grid units, and performing spatiotemporal aggregation processing on the historical fire event data in the urban study area; calculating the area ratio of each type of land use in each grid for urban land use types; averaging the meteorological factor data recorded by all meteorological stations in the urban study area for meteorological factors;

[0057] S3, based on the data pre-processed in step S2, determine the input variables and output variables for the urban fire number forecast model: the input variables include urban land type grid data, past Time series data of meteorological factors of the day and the past The three types of input variables are spatial type data, time type data and spatiotemporal type data; the output variable is the future Daily cumulative fire number grid map; , ,and and All are integers;

[0058] S4. Constructing a city fire number prediction model based on deep neural network: the city fire number prediction model includes an encoder and a decoder, wherein the encoder is used to process time series variables, and the decoder is used to process urban land type spatial variables and feature variables;

[0059] S5. Training and evaluation of the urban fire occurrence forecast model: Arrange the input variables and output variables of step S3 to obtain paired data sets, and divide the data sets into a training set, a validation set, and a test set in chronological order and at a preset ratio, wherein the training set and the validation set are used to determine the parameters of the urban fire occurrence forecast model, and the test set is used to evaluate the performance of the urban fire occurrence forecast model.

[0060] In order to better understand the above technical solution, the exemplary embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. These are only exemplary embodiments of the present invention. However, it should be understood that the present invention can also be implemented in various forms and is not limited to the embodiments described herein. These embodiments are intended to enable those skilled in the art to understand the present invention more clearly and thoroughly.

[0061] The present embodiment describes a method for predicting the spatial distribution of urban fire numbers based on a deep learning algorithm. Figure 1 As shown, the following steps are included:

[0062] S1. Collect original data: Collect historical fire event data in the urban study area and urban land use type data and meteorological factor data corresponding to each historical fire event.

[0063] In this embodiment, historical fire event data that occurred in a certain urban study area in the past 10 years were collected, including the location and time of occurrence of each fire.

[0064] The land use type vector data of the urban study area were collected, including construction land, non-construction land, residential land, public administration and public service land, commercial service facility land, industrial land, logistics and warehousing land, road and transportation facility land, public facility land, green space and square land, a total of 10 land use types.

[0065] The daily meteorological observation dataset is obtained through official channels, such as the official National Oceanic and Atmospheric Administration, and the meteorological factors recorded by the meteorological stations in the urban study area are extracted, including the daily average temperature, daily average relative humidity and daily accumulated rainfall.

[0066] S2. Preprocess the original data collected in step S1: divide the urban study area into grid units, and perform spatiotemporal aggregation processing on the historical fire event data in the urban study area; for urban land types, calculate the area ratio of each type of land use in each grid; for meteorological factors, average the meteorological factor data recorded by all meteorological stations in the urban study area.

[0067] (1) The urban study area is divided into grid cells, and the historical fire event data of the urban study area are subjected to spatiotemporal aggregation processing, including:

[0068] If the occurrence address of the historical fire event data collected in step S1 is a geographic coordinate, it can be used directly; otherwise, a map tool is used to convert the attributes of the occurrence address of the historical fire event data into geographic coordinates.

[0069] In terms of time, the data is divided into daily statistics to form a daily fire number data set.

[0070] In space, the grid units are divided according to the preset spatial resolution, and the geographical coordinate points of the daily fire number are counted into the grid units to form a spatial grid map of the daily fire number. In this embodiment, the preset spatial resolution is preferably 2.5 kilometers, and the length of each grid layer is He Kuan Both are 20, that is, each grid layer has 20 grids in both length and width directions, forming a spatial grid map of the number of daily fires with an image size of 20×20, such as Figure 2 As shown, Figure 2 The left figure shows the raw point data of the number of fires per day. Figure 2 The right figure shows the spatial distribution data of the daily fire count on the grid.

[0071] (2) For urban land use types, calculate the area ratio of each land use type in each grid, including:

[0072] For urban land types, the geographic spatial analysis tool ArcGIS is used to calculate the area ratio of each urban land type in each grid.

[0073] (3) For meteorological factors, the meteorological factor data recorded by all meteorological stations in the urban study area are averaged, including:

[0074] For different meteorological factors, the data recorded by all meteorological stations in the urban study area are averaged to obtain the time series data of the daily average temperature, daily average relative humidity and daily cumulative rainfall in the urban study area. Since the number of meteorological stations collected in the urban study area in this embodiment is only one, this step is skipped, and only the meteorological factor data recorded by this one meteorological station in the urban study area need to be collected, that is, only the time series data of the daily average temperature, daily average relative humidity and daily cumulative rainfall of this meteorological station are collected.

[0075] S3, based on the data pre-processed in step S2, determine the input variables and output variables for the urban fire number forecast model: the input variables include urban land type grid data, past Time series data of meteorological factors of the day and the past The three types of input variables are spatial type data, time type data and spatiotemporal type data; the output variable is the future Daily cumulative fire number grid map; The value range is ; is a hyperparameter, and the optimal value can be found through sensitivity analysis. The minimum value of is 1 day, that is ,and and All are integers.

[0076] In this embodiment, it is preferred , .

[0077] (1) For urban land use types, the urban land use type raster data are as follows:

[0078] In this embodiment, there are 10 types of urban land use, so there are 10 layers of urban land use type raster maps. The 10 layers of urban land use type raster maps are stacked into 10-channel image data in the spatial dimension. Suppose that all urban land use type raster layer sets are expressed as follows:

[0079] (1)

[0080] In formula (1), Represents one of the urban land use type layers. , then the variable The dimension size is 10×20×20, that is, As the input variable of the urban fire number prediction model.

[0081] (2) The meteorological factor time series of the past 30 days, namely, daily average temperature, daily average relative humidity, and daily cumulative rainfall. These three variables are spliced ​​into three characteristic time series in the time dimension. The specific data are as follows:

[0082] Assume that the time of the day is , the time series data of meteorological factors in the past 30 days are expressed as follows:

[0083] (2)

[0084] In formula (2), Indicates The time series of meteorological factors of the day, , the meteorological factor time series specifically includes three variables: daily average temperature, daily average relative humidity and daily cumulative rainfall. Then the variable The dimension size is 3×30, that is, As the input variable of the urban fire number prediction model.

[0085] (3) The specific raster map set of the number of daily fires in the past 30 days is as follows:

[0086] The daily fire count raster map collection for the past 30 days is shown below:

[0087] (3)

[0088] In formula (3), Indicates Raster map of the number of fires per day, ;

[0089] The empirical orthogonal function decomposition method is used to transform the spatiotemporal data Perform principal component decomposition and retain the previous principal components, so that the previous The cumulative variance explanation rate of the principal components is not less than the preset percentage, which is generally at least 95%. The specific number of principal components to be retained depends on the data situation. In this embodiment, the cumulative variance explanation rate of the principal components retained is preferably 98.5%. Then, when k=100, the cumulative variance explanation rate of the first 100 principal components is 98.5%, as follows:

[0090] (4)

[0091] In formula (4), represents the number of grids in the daily fire count grid map, that is, m=400, Represents the spatial component of the decomposed daily fire count raster map set, Represents the time component of the decomposed daily fire count raster map set, extract As the input variable of the urban fire number forecast model, it is finally decomposed into the spatial components of the daily fire number grid map set The time component of the daily fire count raster map collection .Will As the input variable of the urban fire number prediction model.

[0092] (4) The grid map of the cumulative number of fires in the next 30 days is as follows:

[0093] By temporally aggregating the daily fire count grid graphs from the current day to the next 29 days, a total of 30 days, a cumulative fire count grid graph for the next 30 days is formed, namely:

[0094] (5)

[0095] In formula (5), Indicates The daily fire number grid map for the next 30 days is used as the output variable of the urban fire number forecast model.

[0096] S4. Construct a city fire number forecast model based on deep neural network: The city fire number forecast model includes an encoder and a decoder, the encoder is used to process time series variables, and the decoder is used to process urban land type spatial variables and feature variables.

[0097] In this embodiment, Figure 3 As shown in the figure, the architecture of the encoder includes a long short-term memory network connected to a self-attention mechanism network, and the architecture of the decoder includes a fully connected network and several layers of convolutional neural networks.

[0098] (1) The time series components processed by the encoder include the meteorological factor time variables and the time component of the number of fires per day in history , the specific operations include:

[0099] The meteorological factor time variable and the time component of the historical daily fire count raster map collection Splicing in the time dimension to obtain a composite time series [ E, M ] , composite time series [ E, M ] The dimension is 103×30, a composite time series [ E, M ] As the input variable of the encoder, the encoder processes the composite time series [ E, M ] Encode, and then use the variable at the last moment of the self-attention mechanism network output as the feature variable , where r is the number of hidden units of the self-attention mechanism network. In this embodiment, the hidden units of the first-layer long short-term memory network and the second-layer self-attention mechanism network are both 256. The tensor of size 103×30 is transformed into a tensor of size 256×30, and the variable at the last moment of the output of the attention mechanism network is taken as the output of the encoder, which is recorded as .

[0100] (2) Decoder is used to process urban land type spatial variables and feature variables , the specific operations include:

[0101] First, the feature variables After preprocessing, a fully connected network is used to Transformed into ; Secondly, use matrix transformation to Further transformed into variables ; Then, the variable and variables Concatenate on the channel dimension to obtain composite spatial variables [ Z ̃ , L] , composite spatial variable [ Z ̃ , L] The dimension is 11×20×20; the decoder of this embodiment adopts a two-layer convolutional neural network, and the composite spatial variable is input into the two-layer convolutional neural network. The first layer of the convolutional neural network has 64 convolution kernels with a size of 3×3, and the second layer of the convolutional neural network has 1 convolution kernel with a size of 2×2. The two-layer convolution operation converts the original tensor of size 11×20×20 into a tensor of size 1×20×20, and the generated predicted value of the grid map of the cumulative number of fires in the next 30 days is as the output of the decoder.

[0102] S5. Training and evaluation of the urban fire occurrence forecast model: Arrange the input variables and output variables of step S3 to obtain paired data sets, and divide the data sets into training set, validation set and test set in chronological order and at a preset ratio of 8:1:1, wherein the training set and validation set are used to determine the parameters of the urban fire occurrence forecast model, and the test set is used to evaluate the performance of the urban fire occurrence forecast model.

[0103] Specifically, the training of the urban fire number prediction model includes:

[0104] Assume that the loss function of the urban fire number forecast model is the mean square error (MSE) of the district-level disaster loss, and the number of training samples is N, where The true value and predicted value of the cumulative number of fires in the next 30 days for each sample are and , then the loss function is expressed as follows:

[0105] (6)

[0106] The Pytorch framework is used to train the urban fire occurrence prediction model, in which the Adam optimizer is used as the optimization algorithm, the learning rate is 0.0005, and the number of simulation training iterations is 1000 times. After each round of training, the validation set is used to calculate the loss function of the urban fire occurrence prediction model. When the number of training iterations of the urban fire occurrence prediction model is reached, the training is stopped; otherwise, the urban fire occurrence prediction model is continued to be trained; within the iteration cycle, the urban fire occurrence prediction model with the best prediction result on the validation set is selected as the final trained urban fire occurrence prediction model, and the parameters of the urban fire occurrence prediction model are determined.

[0107] Finally, the test set is used to evaluate the performance of the urban fire number prediction model. Take 6 samples in the test set as an example. Figure 4 As shown in the figure, the comparison results between the predicted value and the true value obtained by using the city fire number forecast model are shown. Figure 4 The darker the color, the more fires will occur in the next 30 days. Conversely, the lighter the color, the fewer fires will occur in the next 30 days. The results show that the method of the present invention can well capture the high-risk areas for fires in the next 30 days, which shows that the urban fire number forecasting model of the present invention has high prediction accuracy and good feasibility.

[0108] The above only describes the basic principles and preferred embodiments of the present invention. Those skilled in the art may make many changes and improvements based on the above description, and these changes and improvements should fall within the protection scope of the present invention.

Claims

1. A method for predicting the spatial distribution of urban fires based on a deep learning algorithm, characterized in that: The steps include: S1. Collect original data: collect historical fire event data in the urban study area and urban land use type data and meteorological factor data corresponding to each historical fire event; S2. Preprocessing the raw data collected in step S1: dividing the urban study area into grid units, and performing spatiotemporal aggregation processing on the historical fire event data in the urban study area; calculating the area ratio of each type of land use in each grid for urban land use types; averaging the meteorological factor data recorded by all meteorological stations in the urban study area for meteorological factors; S3, based on the data pre-processed in step S2, determine the input variables and output variables for the urban fire number forecast model: the input variables include urban land type grid data, past Time series data of meteorological factors of the day and the past The three types of input variables are spatial type data, time type data and spatiotemporal type data; the output variable is the future Daily cumulative fire number grid map; , ,and and All are integers; S4. Constructing a city fire number prediction model based on deep neural network: the city fire number prediction model includes an encoder and a decoder, wherein the encoder is used to process time series variables, and the decoder is used to process urban land type spatial variables and feature variables; S5. Training and evaluation of the urban fire occurrence forecast model: Arrange the input variables and output variables of step S3 to obtain paired data sets, and divide the data sets into a training set, a validation set, and a test set in chronological order and at a preset ratio, wherein the training set and the validation set are used to determine the parameters of the urban fire occurrence forecast model, and the test set is used to evaluate the performance of the urban fire occurrence forecast model.

2. The method for predicting the spatial distribution of urban fire occurrence based on a deep learning algorithm according to claim 1 is characterized in that: In step S1, the historical fire event data of the urban study area includes the address and time of occurrence of each fire; the urban land type data includes two categories: urban and rural land and urban construction land, among which urban and rural land is subdivided into construction land and non-construction land, and urban construction land is subdivided into residential land, public management and public service land, commercial service facility land, industrial land, logistics and warehousing land, road and transportation facility land, public facility land, green space and square land according to function; the meteorological factor data includes the daily average temperature, daily average relative humidity and daily cumulative rainfall recorded by all meteorological observation stations in the urban study area.

3. The method for predicting the spatial distribution of urban fire occurrence based on deep learning algorithm according to claim 1 is characterized in that: In step S2, the urban study area is divided into grid cells, and spatiotemporal aggregation processing is performed on the historical fire event data of the urban study area, specifically including: In terms of time, the data is divided into daily statistics to form a daily fire number data set; In space, the grid cells are divided according to the preset spatial resolution, and the geographic coordinate points of the daily number of fires are counted into the grid cells to form a spatial grid map of the daily number of fires.

4. The method for predicting the spatial distribution of urban fire occurrence based on a deep learning algorithm according to claim 1 is characterized in that: In step S2, for meteorological factors, the meteorological factor data recorded by all meteorological stations in the urban study area are averaged, specifically including: For different meteorological factors, the data recorded by all meteorological stations in the urban study area were averaged to obtain the time series data of daily average temperature, daily average relative humidity and daily accumulated rainfall in the urban study area.

5. The method for predicting the spatial distribution of urban fire occurrence based on deep learning algorithm according to claim 2 is characterized in that: In step S3, the urban land type raster data is as follows: The urban land type raster maps are stacked into multi-channel image data in the spatial dimension. Suppose that the set of all urban land type raster layers is represented as follows: （1） In formula (1), Represents one of the urban land use type layers. , let the length and width of each raster layer be and , then the variable The dimension size ,Right now, As the input variable of the urban fire number prediction model.

6. The method for predicting the spatial distribution of urban fire occurrence based on a deep learning algorithm according to claim 5 is characterized in that: In step S3, the past The time series data of meteorological factors for the day are as follows: The meteorological factors are stacked into multi-feature time series data in the time dimension. Let the time of the day be ,past The time series data of meteorological factors for the day are expressed as follows: （2） In formula (2), Indicates The time series of meteorological factors of the day, , the meteorological factor time series specifically includes three variables: daily average temperature, daily average relative humidity and daily cumulative rainfall. Then the variable The dimension size is ,Right now, As the input variable of the urban fire number prediction model.

7. The method for predicting the spatial distribution of urban fire occurrence based on deep learning algorithm according to claim 6 is characterized in that: In step S3, the past The daily fire number grid map collection is as follows: past The daily fire number raster map collection is represented as follows: （3） In formula (3), Indicates Raster map of the number of fires per day, ; The empirical orthogonal function decomposition method is used to transform the spatiotemporal data Perform principal component decomposition and retain the previous principal components, so that the previous The cumulative variance explanation rate of the principal components is not less than the preset percentage, as follows: （4） In formula (4), Represents the number of grids in the daily fire count grid map, Represents the spatial component of the decomposed daily fire count raster map set, Represents the time component of the decomposed daily fire count raster map set, extract As the input variable of the urban fire number prediction model.

8. The method for predicting the spatial distribution of urban fire occurrence based on deep learning algorithm according to claim 7 is characterized in that: In step S3, the future The daily cumulative number of fires grid map is as follows: By transferring the present day into the future Total days The daily fire count grid map collection is aggregated in time to form the future The daily cumulative number of fires grid map is: （5） In formula (5), Indicates The daily fire number grid map will be used to The daily cumulative fire number grid map is used as the output variable of the urban fire number prediction model.

9. The method for predicting the spatial distribution of urban fire occurrence based on a deep learning algorithm according to claim 7, characterized in that: In step S4, the architecture of the encoder includes a long short-term memory network connected to a self-attention mechanism network, and the architecture of the decoder includes a fully connected network and several layers of convolutional neural networks; The time series components that the encoder processes include the meteorological factor time variables and the time component of the number of historical daily fires , the specific operations include: The meteorological factor time variable and the time component of the historical daily fire count raster map collection Splicing in the time dimension to obtain a composite time series , composite time series The dimension is , composite time series As the input variable of the encoder, the encoder processes the composite time series Encode, and then use the variable at the last moment of the self-attention mechanism network output as the feature variable , where r is the number of hidden units in the self-attention mechanism network; Decoder for processing urban land use type spatial variables and feature variables , the specific operations include: First, the feature variables After preprocessing, a fully connected network is used to Transformed into ; Secondly, use matrix transformation to Further transformed into variables ; Then, the variable and variables Concatenate on the channel dimension to obtain composite spatial variables , composite spatial variable The dimension is ; Input the composite spatial variable into the multi-layer convolutional neural network, and the output of the last layer of convolutional neural network is the future The predicted value of the daily cumulative number of fires grid map is set as .

10. The method for predicting the spatial distribution of urban fire occurrence based on deep learning algorithm according to claim 1, characterized in that: In step S5, the training of the urban fire number forecasting model specifically includes: Assume that the loss function of the urban fire number forecast model is the mean square error (MSE) of the district-level disaster loss, and the number of training samples is N, where A sample of the future The true and predicted values ​​of the daily cumulative fire number grid map are and , then the loss function is expressed as follows: （6） Set a number of training iterations, use the training set to back-propagate the mean square error (MSE) of the urban fire occurrence forecast model using the optimizer, and use the validation set to calculate the loss function of the urban fire occurrence forecast model after each round of training. When the number of training iterations of the urban fire occurrence forecast model is reached, stop training; otherwise, continue training the urban fire occurrence forecast model; select the urban fire occurrence forecast model with the best prediction result on the validation set within the iteration cycle as the final trained urban fire occurrence forecast model, and determine the parameters of the urban fire occurrence forecast model.

Images