Forest fire spreading prediction simulation system under complex mountainous terrain condition

Abstract

The invention relates to the technical field of forest fire prediction and simulation, in particular to a forest fire spreading prediction simulation system under complex mountain terrain conditions, which comprises a data acquisition module, a data preprocessing module, a terrain analysis generation module, a vegetation analysis module, a meteorological analysis module, a fire spreading simulation module and a result display module. According to the forest fire spreading prediction simulation system under the complex mountainous terrain condition, the influence of multiple factors such as the complex mountainous terrain, vegetation and weather on forest fire spreading is comprehensively considered, the prediction accuracy and reliability are improved, a user can visually know the forest fire spreading condition through visual result display, and the forest fire spreading prediction simulation system has the advantages of being convenient to use and high in practicability. According to the invention, scientific and reasonable fire prevention and extinguishing strategies can be formulated conveniently, latest data can be acquired and processed in time, powerful support is provided for monitoring and early warning of forest fire, scientific decision basis can be provided for forest management departments, fire departments and the like, and improvement of the prevention and control capability of forest fire is facilitated.

Description

Technical Field

[0001] The invention relates to the technical field of forest fire prediction and simulation, and in particular to a forest fire spread prediction simulation system under complex mountain terrain conditions. Background Art

[0002] Forest fire is a common natural disaster. It will cause considerable damage to the natural world, and even cause great harm to human life in some places. If it is not managed and controlled, and allowed to develop, the damage caused is immeasurable. How to obtain the current status information of the fire scene in a timely and effective manner after the fire occurs (fire range, fire intensity, advancement speed, fire type, wind speed and direction and other meteorological information). Most of the existing literature on the simulation of forest fire spread is based on the ignition point as the starting point. This simulation method considers more ideal factors and has a better effect on the simulation of small-scale short-term fires in the early stage of the fire. In actual situations, when the fire is discovered, it has been burning for a period of time. It has caused a certain range of damage. In this case, decision makers are more concerned about the prediction of the advancement trend of the fire in the future under the conditions of the existing fire boundary range.

[0003] The existing forest fire spread prediction methods and systems have the following main deficiencies:

[0004] The terrain factors are not adequately considered and cannot accurately reflect the impact of complex mountain terrain on the spread of forest fires;

[0005] Lack of detailed analysis of vegetation types and distribution leads to inaccurate assessment of fuel availability for forest fires;

[0006] The acquisition and analysis of meteorological data are not timely and accurate enough, which affects the accuracy of forest fire spread prediction;

[0007] Therefore, developing a system that can accurately predict and simulate the spread of forest fires in complex mountainous terrain conditions is of great significance for the prevention, monitoring and fighting of forest fires. Summary of the invention

[0008] The purpose of the present invention is to provide a forest fire spread prediction simulation system under complex mountain terrain conditions to solve the problems raised in the above background technology.

[0009] To achieve the above-mentioned object, the present invention provides the following technical solutions: a forest fire spread prediction simulation system under complex mountain terrain conditions, including a data acquisition module for collecting geographic information data, vegetation information data and real-time meteorological information data of complex mountain terrain;

[0010] A data preprocessing module, connected to the data acquisition module, is used to preprocess the collected data, remove noise and abnormal data, and convert the data into a format suitable for model input;

[0011] The terrain analysis generation module is used to construct a three-dimensional map of complex mountainous terrain based on geographic information data, and analyze the impact of terrain characteristics such as slope, slope direction, and altitude on the spread of forest fires;

[0012] The vegetation analysis module analyzes the combustion characteristics of different vegetation types, the fuel load, and the impact of vegetation distribution on the spread of forest fires based on vegetation information data;

[0013] The meteorological analysis module analyzes the impact of meteorological factors such as wind speed, wind direction, temperature, and humidity on the spread of forest fires based on real-time meteorological information data;

[0014] The fire spread simulation module is connected with the terrain analysis module, the vegetation analysis module and the meteorological analysis module, and uses an algorithm based on a combination of physical models and empirical models to simulate and predict the spread of forest fires in complex mountainous terrain conditions;

[0015] The result display module is used to display the simulated predicted forest fire spread results in a visual way, including the scope, speed, direction and other information of the fire spread.

[0016] Preferably, the data acquisition module includes a satellite remote sensing data acquisition submodule, a ground monitoring data acquisition submodule and a drone data acquisition submodule.

[0017] Preferably, the terrain analysis generation module utilizes an unmanned aerial vehicle equipped with a high-resolution panoramic camera and a high-precision laser radar.

[0018] Preferably, the physical model in the fire spread simulation module includes a heat conduction model, a heat convection model and a heat radiation model, and the empirical model includes a statistical model based on historical fire data and a judgment model based on expert experience.

[0019] Preferably, the result display module uses virtual reality (VR) technology or three-dimensional animation technology to display the forest fire spread results to the user.

[0020] Preferably, the data preprocessing module uses EMD and ICA induced polarization methods in a computer to perform noise reduction on the collected data, and then performs format conversion and normalization processing so that it can be uniformly processed and analyzed by subsequent modules.

[0021] Preferably, the data collection module further comprises a ground monitoring data collection submodule which collects meteorological data and physiological status data of vegetation in real time through a sensor network arranged in the forest.

[0022] Preferably, during the transmission process, all data of the forest fire spread prediction simulation system uses a power inversion algorithm based on a minimum mean square error LMS algorithm to improve the quality of the transmission signal.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] This forest fire spread prediction simulation system under complex mountainous terrain conditions improves the accuracy and reliability of predictions by comprehensively considering the impact of complex mountainous terrain, vegetation, meteorology and other factors on the spread of forest fires. Through the visual display of results, users can intuitively understand the spread of forest fires and facilitate the formulation of scientific and reasonable fire prevention and extinguishing strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0026] Figure 1 It is an overall flow chart of the forest fire spread prediction simulation system of the present invention. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0028] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0029] See also Figure 1 , the present invention provides a technical solution:

[0030] A forest fire spread prediction simulation system under complex mountainous terrain conditions.

[0031] It includes a data acquisition module for collecting geographic information data, vegetation information data and real-time meteorological information data of complex mountainous terrain;

[0032] The satellite remote sensing data acquisition submodule uses satellite remote sensing technology to obtain information such as forest terrain and vegetation coverage over a large area. It has the advantages of wide coverage and fast data acquisition speed.

[0033] The ground monitoring data acquisition submodule collects meteorological data (such as temperature, humidity, wind speed, wind direction, etc.) and vegetation physiological status data (such as water content, etc.) in real time through a sensor network set up in the forest, with high data accuracy.

[0034] The drone data acquisition submodule uses the high-definition cameras and sensors carried by drones to conduct close-range monitoring and data collection of key areas, and can obtain detailed terrain and vegetation information, making up for the shortcomings of satellite remote sensing and ground monitoring.

[0035] A data preprocessing module, connected to the data acquisition module, is used to preprocess the collected data, remove noise and abnormal data, and convert the data into a format suitable for model input;

[0036] The terrain analysis generation module is used to construct a three-dimensional map of complex mountainous terrain based on geographic information data, and analyze the impact of terrain characteristics such as slope, slope direction, and altitude on the spread of forest fires;

[0037] The vegetation analysis module analyzes the combustion characteristics of different vegetation types, the fuel load, and the impact of vegetation distribution on the spread of forest fires based on vegetation information data;

[0038] The meteorological analysis module analyzes the impact of meteorological factors such as wind speed, wind direction, temperature, and humidity on the spread of forest fires based on real-time meteorological information data;

[0039] The fire spread simulation module is connected with the terrain analysis module, the vegetation analysis module and the meteorological analysis module, and uses an algorithm based on a combination of physical models and empirical models to simulate and predict the spread of forest fires in complex mountainous terrain conditions;

[0040] The physical models in the fire spread simulation module include a heat conduction model, a heat convection model and a heat radiation model, and the empirical models include a statistical model based on historical fire data and a judgment model based on expert experience.

[0041] The result display module is used to display the simulated predicted forest fire spread results in a visual manner, including information such as the scope, speed, and direction of the fire spread. The result display module uses virtual reality (VR) technology or three-dimensional animation technology to display the forest fire spread results to users.

[0042] Data preprocessing module:

[0043] Clean and denoise the various collected data to remove outliers and duplicate data and improve the quality of the data.

[0044] The data from different sources are formatted and normalized so that they can be uniformly processed and analyzed by subsequent modules.

[0045] The AE sensor converts the AE signal into an electrical signal and uses an A / D converter to send the result to a computer, where the EMD and ICA methods are used to reduce noise on the data.

[0046] The specific steps include:

[0047] Independent component analysis, which decomposes mixed signals into several independent components through optimization algorithms;

[0048] Independent component analysis is a multidimensional signal processing method that establishes an objective function according to the principle of statistical independence and decomposes a mixed signal into several independent components through an optimization algorithm.

[0049] Assuming the observed Dimensional signal ; is composed of n independent signals After linear aliasing of an unknown system, we get: ;

[0050] Rewritten into matrix form: ;

[0051] A is the unknown mixing coefficient The goal of ICA is to find a separation matrix W from the data matrix X, so that the output matrix Y=WX is the optimal estimate of the original signal matrix s. In practical applications, the tool operation data signal model is often affected by noise, which is extended to the following noise reduction model: ;

[0052] Where: u is the noise vector. Limited by the sensor array, most of the data signals obtained are tool operation data signals. Considering the addition of m types of noise, the tool operation data signal is expressed as: ;

[0053] in: and are the useful signal s and the noise The weight of the tool operation data is used to process such operation data signals. The virtual noise introduced is ;

[0054] The noise-added model can be rewritten as the standard ICA model without an explicit representation of the additive noise:

[0055]

[0056]

[0057] Then ICA can estimate the separation matrix by finding the inverse matrix of matrix A, so that is the optimal estimate of the source signal. Since the virtual noise u is artificially introduced, it can be obtained from the output signal The useful signal s is separated from the signal to achieve signal noise reduction.

[0058] Pseudo-noise channel construction: construct a virtual noise channel that is as similar to the noise as possible;

[0059] From the above formula, we can know that EMD can decompose complex signals into linear superposition of multiple intrinsic mode functions IMFs and residual terms with approximate single frequency components: ;

[0060] in: To observe the signal, is the intrinsic mode component arranged from high to low frequency, res is the remainder, and m is the number of IMFs set. Every time an IMF is separated by EMD, its time spectrum is calculated, where IMF is orthogonal in the frequency domain, and each IMF represents a component of different frequencies in the observed signal.

[0061] The excitation signal s of the transmitting device is preset artificially, so the approximate waveform, frequency and other prior information of the useful signal in the collected mixed signal are known, and the correlation coefficient between each IMF and the excitation signal s can be selected. As a judgment indicator:

[0062] ;

[0063] in: Represents the covariance of a and b. Select n intrinsic modal components, perform linear superposition, and construct virtual noise: ;

[0064] in: The correlation coefficient is less than the set threshold In practical applications, known information can be added to the independent component analysis process to improve the separation effect. A standard signal can be used to pre-observe a hybrid system, and then the system output can be analyzed to have a general understanding of the system noise, which can be used as a certain dimension observation in the virtual noise, which will also improve the effect of independent component separation.

[0065] A denoising method combining EMD and JCA is established. The virtual noise channel and the original observation signal are used as the ICA observation matrix to separate the useful signal and achieve the purpose of signal denoising.

[0066] Firstly, the observed signal is decomposed into multiple IMFs using the EMD method. Then, based on the prior information of the excitation signal of the induced polarization transmitter (the frequency and waveform are known), the mutual correlation coefficient between each IMF and the excitation signal is used as an indicator to separate the IMFs smaller than a certain threshold to construct a virtual noise channel. The virtual noise channel and the original observed signal are used together as the ICA observation matrix, thus expanding the one-dimensional observation signal to multi-dimensional observation. Finally, the ICA technology is applied to separate the useful signal to achieve the purpose of signal noise reduction.

[0067] Terrain Analysis Module:

[0068] Based on digital elevation model (DEM) data, a three-dimensional model of complex mountainous terrain is constructed to accurately reflect the terrain's undulation, slope, aspect and other characteristics.

[0069] Analyze the impact of terrain on the spread of forest fires. For example, fires spread faster in areas with larger slopes, and different slope directions will lead to differences in the direction of fire spread.

[0070] Vegetation Analysis Module:

[0071] Based on the vegetation information data, the combustion characteristics of different vegetation types are analyzed, including parameters such as the calorific value of combustibles, combustion speed, and combustion temperature.

[0072] Calculate the fuel load of vegetation in different areas and assess the fuel supply for forest fires.

[0073] Analyze the distribution of vegetation and determine the potential spread paths of fire and key prevention and control areas.

[0074] Meteorological analysis module:

[0075] Acquire meteorological data in real time, analyze and process the data, and predict meteorological trends in the future.

[0076] Study the impact of meteorological factors on the spread of forest fires, such as wind speed and direction will affect the spread speed and direction of the fire, temperature and humidity will affect the dryness and burning speed of combustibles, etc.

[0077] Fire spread simulation module:

[0078] By combining multi-source information such as terrain, vegetation and meteorology, and using an algorithm based on a combination of physical models and empirical models, the spread of forest fires in complex mountainous terrain conditions is simulated and predicted.

[0079] The physical model mainly includes heat conduction model, heat convection model and thermal radiation model, which are used to describe the heat transfer and diffusion process of fire; the empirical model is based on historical fire data and expert experience to summarize and generalize the spread laws of fire.

[0080] Suppose our goal is to predict the spread range A and spread speed v of a forest fire within a certain time t.

[0081] Definition: Terrain Factor: Slope , Slope , Altitude .

[0082] Vegetation factors: Vegetation type (Different types can be represented by numerical codes), vegetation density , moisture content of combustibles .

[0083] Meteorological factors: wind speed ,wind direction Temperature ,temperature .

[0084] Initial location of the fire source and strength .

[0085] Construct a fitness function:

[0086] Error calculation for predicted spread range:

[0087] Assume that the predicted spread range is , the actual observed spread is , we can calculate the range error using the mean squared error (MSE):

[0088] ;

[0089] in: is the sample size, and They are The predicted spread range and actual spread range of samples.

[0090] Error calculation for predicted spread speed:

[0091] Assume the predicted spreading speed is , the actual observed spreading speed is , the speed error can also be calculated using the mean square error:

[0092] ;

[0093] Construct a fitness function:

[0094] Taking into account the errors of range and speed, the fitness function F can be defined as:

[0095] ;

[0096] in, and are the weights of the spreading range error and spreading speed error in the fitness function, and .

[0097] Considering the weight of influencing factors, factor importance assessment:

[0098] The influence weight of each factor on the spread range and speed is determined by the analytic hierarchy process (AHP) and other methods. The weight of the impact on the spread speed is ,wind direction The weight of the impact on the spread direction (indirectly affecting the spread range) is wait.

[0099] Weight allocation method:

[0100] Taking the effect of wind speed on spreading speed as an example, we can establish the relationship between wind speed and spreading speed based on physical models or empirical formulas. For example, assuming that there is a linear relationship between spreading speed and wind speed:

[0101] ;

[0102] in, and is a model parameter. Then, when calculating the fitness function, the contribution of wind speed to the spread speed error can be expressed as:

[0103] ;

[0104] and, ,in is the contribution of other factors to the spread speed error. Similarly, the influence of other factors on the spread range and speed can be handled.

[0105] Data preprocessing and normalization:

[0106] Removing outliers: Statistical methods can be used, such as Principle, remove data points that obviously deviate from the normal range.

[0107] Data normalization:

[0108] Min-max normalization: For variables , its normalized value It can be calculated as:

[0109] ;

[0110] in: and The variables are The minimum and maximum values ​​of .

[0111] Use an independent set of forest fire data as a test set, substitute the prediction results into the fitness function to calculate the fitness value. Evaluate the performance of the model by comparing the fitness values ​​under different models or parameter settings.

[0112] Optimization algorithms such as genetic algorithms and particle swarm optimization algorithms can be used to adjust the parameters in the fitness function (such as weights , , model parameters , etc.) to minimize the value of the fitness function, thereby improving the accuracy of the prediction.

[0113] Results display module:

[0114] The simulated predicted forest fire spread results are displayed in a visual way, including two-dimensional plane graphics and three-dimensional models, so that users can intuitively understand the fire spread range, speed, direction and other information.

[0115] It provides a variety of visualization tools and interactive functions. Users can zoom, rotate, slice, and perform other operations on the displayed results as needed to analyze the spread of the fire in more depth.

[0116] During the transmission process of all data in the forest fire spread prediction simulation system, the power inversion algorithm based on the minimum mean square error LMS algorithm is used to improve the quality of the transmission signal.

[0117] The power inversion algorithm enhances the anti-interference capability of the transmission signal in the following ways:

[0118] Assume the number of antenna elements is N, and the power inversion array selection weight vector is The weight coefficient of the output power of the first array element is constant. The weight coefficients of the other N-1 array elements are adjustable. Set up four antenna array elements and analyze their antenna radiation patterns. At this time, the weight coefficients are: In the power inversion algorithm, the strongest signal component in the received signal should be suppressed to the greatest extent. Therefore, in the implementation of the adaptive filter, the received signal of a certain array element is selected as the desired signal. Usually, the received signal of the reference array element is selected as the desired signal. Without loss of generality, we can let .

[0119] The input signal is:

[0120]

[0121] The expected signal is:

[0122]

[0123] The output of the filter is:

[0124]

[0125] The array output is an error signal expressed as:

[0126]

[0127] Under the gradient algorithm, the weight coefficient update expression is:

[0128]

[0129] in It is the iteration step size of the gradient algorithm.

[0130] In actual situations, the antenna array is generally a four-element array, and four antenna array elements with a square array shape and an element spacing of λ / 2 (λ is the signal wavelength) are selected to form the antenna array.

[0131] The core of the LMS adaptive algorithm is to continuously adjust the weight coefficients. Before sending a resource allocation signal for the communication link, the processor will perform A / D analog-to-digital conversion on the electrical signal of the current environmental data, compare the current data with the local database, and set the weight coefficient that best suits the current environment based on the actual situation, so that the array output power of the interference signal is as small as possible, that is, when the interference signal power is small, the power of the output interference signal increases with the increase of the input interference signal; and when the interference signal power is higher than a certain limit value, the stronger the input interference signal, the smaller the output interference signal power. After the interference signal power is reduced, the quality of the transmission signal will improve, that is, the anti-interference ability of the transmission signal will be enhanced.

[0132] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0133] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A forest fire spread prediction simulation system under complex mountain terrain conditions, characterized in that: It includes a data acquisition module for collecting geographic information data, vegetation information data and real-time meteorological information data of complex mountainous terrain; A data preprocessing module, connected to the data acquisition module, is used to preprocess the collected data, remove noise and abnormal data, and convert the data into a format suitable for model input; The terrain analysis generation module is used to construct a three-dimensional map of complex mountainous terrain based on geographic information data, and analyze the impact of terrain characteristics such as slope, slope direction, and altitude on the spread of forest fires; The vegetation analysis module analyzes the combustion characteristics of different vegetation types, the fuel load, and the impact of vegetation distribution on the spread of forest fires based on vegetation information data; The meteorological analysis module analyzes the impact of meteorological factors such as wind speed, wind direction, temperature, and humidity on the spread of forest fires based on real-time meteorological information data; The fire spread simulation module is connected with the terrain analysis module, the vegetation analysis module and the meteorological analysis module, and uses an algorithm based on a combination of physical models and empirical models to simulate and predict the spread of forest fires in complex mountainous terrain conditions; The result display module is used to display the simulated predicted forest fire spread results in a visual way, including the scope, speed, direction and other information of the fire spread.

2. The forest fire spread prediction simulation system under complex mountainous terrain conditions according to claim 1 is characterized by: The data acquisition module includes a satellite remote sensing data acquisition submodule, a ground monitoring data acquisition submodule and an unmanned aerial vehicle data acquisition submodule.

3. The forest fire spread prediction simulation system under complex mountainous terrain conditions according to claim 1 is characterized by: The terrain analysis generation module utilizes an unmanned aerial vehicle equipped with a high-resolution panoramic camera and a high-precision laser radar.

4. The forest fire spread prediction simulation system under complex mountainous terrain conditions according to claim 1 is characterized by: The physical models in the fire spread simulation module include a heat conduction model, a heat convection model and a heat radiation model, and the empirical models include a statistical model based on historical fire data and a judgment model based on expert experience.

5. The forest fire spread prediction simulation system under complex mountainous terrain conditions according to claim 1 is characterized by: The result display module uses virtual reality (VR) technology or three-dimensional animation technology to display the forest fire spread results to users.

6. The forest fire spread prediction simulation system under complex mountainous terrain conditions according to claim 1 is characterized by: The data preprocessing module uses the electromagnetic method of EMD and ICA in the computer to perform noise reduction on the collected data, and then performs format conversion and normalization processing so that it can be uniformly processed and analyzed by subsequent modules.

7. The forest fire spread prediction simulation system under complex mountain terrain conditions according to claim 1 is characterized by: The data acquisition module also includes a ground monitoring data acquisition submodule which collects meteorological data and physiological status data of vegetation in real time through a sensor network arranged in the forest.

8. The forest fire spread prediction simulation system under complex mountainous terrain conditions according to claim 1 is characterized by: During the transmission process, all data of the forest fire spread prediction simulation system use a power inversion algorithm based on a minimum mean square error LMS algorithm to improve the quality of the transmission signal.

Images