CN114757387A - Forest fire danger state monitoring and analyzing system and method based on artificial intelligence - Google Patents
Forest fire danger state monitoring and analyzing system and method based on artificial intelligence Download PDFInfo
- Publication number
- CN114757387A CN114757387A CN202210213924.4A CN202210213924A CN114757387A CN 114757387 A CN114757387 A CN 114757387A CN 202210213924 A CN202210213924 A CN 202210213924A CN 114757387 A CN114757387 A CN 114757387A
- Authority
- CN
- China
- Prior art keywords
- forest
- wind
- fire
- data
- atmospheric pressure
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 21
- 230000007480 spreading Effects 0.000 claims abstract description 39
- 239000000126 substance Substances 0.000 claims abstract description 39
- 238000004364 calculation method Methods 0.000 claims abstract description 30
- 238000004088 simulation Methods 0.000 claims abstract description 23
- 235000005121 Sorbus torminalis Nutrition 0.000 claims abstract description 11
- 244000152100 Sorbus torminalis Species 0.000 claims abstract description 11
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 9
- 230000008569 process Effects 0.000 claims abstract description 9
- 238000001514 detection method Methods 0.000 claims abstract description 6
- 241000196324 Embryophyta Species 0.000 claims description 41
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 24
- 230000008020 evaporation Effects 0.000 claims description 22
- 238000001704 evaporation Methods 0.000 claims description 22
- 238000002485 combustion reaction Methods 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000012876 topography Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 239000004519 grease Substances 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 235000015097 nutrients Nutrition 0.000 claims description 3
- 239000002245 particle Substances 0.000 claims description 3
- 239000000463 material Substances 0.000 abstract description 3
- 238000000714 time series forecasting Methods 0.000 abstract 1
- 230000001932 seasonal effect Effects 0.000 description 4
- 239000002689 soil Substances 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000704 physical effect Effects 0.000 description 2
- 238000005728 strengthening Methods 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L11/00—Measuring steady or quasi-steady pressure of a fluid or a fluent solid material by means not provided for in group G01L7/00 or G01L9/00
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P13/00—Indicating or recording presence, absence, or direction, of movement
- G01P13/02—Indicating direction only, e.g. by weather vane
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P5/00—Measuring speed of fluids, e.g. of air stream; Measuring speed of bodies relative to fluids, e.g. of ship, of aircraft
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Primary Health Care (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Aviation & Aerospace Engineering (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a forest fire danger state monitoring and analyzing system and method based on artificial intelligence, and belongs to the technical field of artificial intelligence. The method comprises the steps of constructing a forest wind prediction model, predicting the wind speed of forest wind and the wind direction of the forest wind through the forest wind prediction model, dividing a forest into chequers according to the detection range of forest fire monitoring equipment, calculating the content of combustion-supporting substances of the forest in each chequer according to the vegetation distribution of the forest, establishing a forest fire spreading speed calculation model, simulating different chequers as fire points, simulating the process of fire spreading, and finding out a key forest fire monitoring area; forecasting the wind power data of the forest through a time series forecasting algorithm, and ensuring the specific reference value of fire spreading simulation data; a forest fire spreading speed calculation model is established, simulation of forest fires is further achieved, emphasis of forest fire detection is found through the simulation of the forest fires, manpower and material resources are saved, and fire danger emphasis areas are effectively investigated.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a forest fire danger state monitoring and analyzing system and method based on artificial intelligence.
Background
The forest is the lung of the earth, the forest is an ecological system formed by a plant community, animals living in the forest and a non-biological environment in the space, the life cycle of the forest is long, the productivity of the forest is high, the use is multiple, the benefit is large, but the forest fire which is artificially controlled is lost seriously destroys the forest trees and the forest environment accumulated for many years, so that the forest ecological system is out of balance, the performance of the soil of the forest is destroyed, the landform is changed, and the destruction of the forest fire to the ecology is most direct and has the greatest disaster; a large number of plants are burnt, which causes water and soil loss, aggravation of land desertification and other adverse effects, and finally, even can not maintain ecological balance;
the spreading of forest fire has many essential factors, there is this close relation with weather, topography, forest combustible substance type, the conflagration takes place in the different areas of forest, it is also different that the time that the rescue team finds to arrive to develop the rescue after, that is to say in case the forest fire takes place, the degree of difficulty that the rescue team developed the rescue also is the difference, but current fire monitoring all is the full coverage formula, it is big to be limited to the forest area, the forest shelters from, hardly accomplish the coverage of full area, need a large amount of manpower and material resources, how under the environment of difference, it is the problem that we need to solve to find forest fire monitoring's focus.
Disclosure of Invention
The invention aims to provide a forest fire danger state monitoring and analyzing system and method based on artificial intelligence so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: the forest fire danger state monitoring and analyzing method based on artificial intelligence comprises the following specific steps:
the method comprises the following steps: collecting forest wind power data, wherein the forest wind power data comprises the wind direction of forest wind, the wind speed of the forest wind and the atmospheric pressure of a forest;
step two: normalizing the forest atmospheric pressure, and outputting a forest atmospheric pressure normalization value;
step three: constructing a forest wind prediction model based on LSTM, inputting the wind direction of forest wind, the wind speed of forest wind and the normalized value of forest atmospheric pressure, training the model, outputting the forest wind prediction model with the highest mAP value, and predicting the wind speed of forest wind and the wind direction of forest wind through the forest wind prediction model;
the forest fire is greatly influenced by the current wind speed and wind direction when the forest fire occurs, particularly in the initial stage of the fire, the influence of the wind speed and the wind direction is the largest, the fire borrows the wind force, and the wind mainly guides the spreading direction of the fire force;
china is located in the southeast of the Asian European continent, obvious seasonal changes of climate are formed due to different physical properties of the sea and the continent, the whole seasonal wind is regular in the whole year, the wind direction is fixed, and the local wind power can be changed in detail under the condition of large wind direction;
when a forest fire is researched, a more specific wind direction is needed, when the forest fire is not completely out of control, the wind direction leads the fire behavior, the possible wind direction is predicted through a time prediction algorithm, and the specific reference value of further fire spreading simulation data is guaranteed.
Step four: collecting forest data, wherein the forest data comprises a forest map, a forest gradient, forest vegetation distribution, forest rainfall data and forest evaporation capacity;
step five: dividing the forest into chequerboards according to the detection range of the forest fire monitoring equipment;
step six: calculating the content of combustion-supporting substances of the single checkerboard forest according to the vegetation distribution of the forest;
step seven: establishing a forest fire spreading speed calculation model;
step eight: simulating different checkerboards as fire points, simulating the process of fire spreading, and counting the number of checkerboards burnt before the rescue team arrives;
step nine: and setting a quantity threshold value of the burned checkerboards, and judging that the current ignition point is a key monitoring area when the quantity of the burned checkerboards exceeds the quantity threshold value of the burned checkerboards.
The wind direction of the forest can be changed continuously according to the change of time, a key monitoring area can be output continuously through a forest wind prediction algorithm, once a fire disaster happens in the key monitoring area, the fire disaster is an area which is difficult to rescue by a rescue team, the fire disaster is easy to further develop into a serious fire disaster, and the influence is serious.
And step two, normalizing the atmospheric pressure of the forest, further strengthening the characteristics of the atmospheric pressure of the forest, and effectively improving the accuracy of the prediction model of the forest wind. The specific calculation formula of the output forest atmospheric pressure normalization value is as follows: normalizing atmospheric pressure of a forest
Wherein AP represents a numerical value of the atmospheric pressure of the forest, μ represents a mean value of the atmospheric pressure of the forest,
atmospheric normalized values for the forest are indicated.
The third step of establishing the specific contents of the forest wind prediction model based on the LSTM comprises the following steps: the forest wind prediction model is provided with an attention mechanism on an LSTM network layer, and an output layer is connected with a full connection layer.
The sixth step of calculating the content of the combustion-supporting substances of the single checkerboard forest according to the vegetation distribution of the forest comprises the following specific steps:
on the basis of the water content of the plants, the rainfall and the evaporation capacity of the forest are calculated, and the water content of vegetation in a short time is effectively predicted; in case of fire outburst, the content of the vegetation combustion-supporting substances is accurately judged by effectively calculating the prediction of the water content of the vegetation in a short time;
step 1.1: collecting forest rainfall data and forest evaporation capacity, wherein the forest rainfall data comprises rainfall and rainfall interval time;
step 1.2: calculating the oil content OC of the trees in the checkerboard;
step 1.3: calculating the water content of the plants in the checkerboard, wherein the specific calculation formula is as follows:
wherein WC represents the water content of the plants in the checkerboard, RF represents the forest rainfall, EC represents the forest evaporation capacity, and WC represents the water content of the plants in the checkerboard;
step 1.4: and (3) calculating the content of the combustion-supporting substances in the checkerboards, wherein the specific calculation formula is as follows:
wherein CSS represents the content of combustion-supporting substances in the checkerboards, OC represents the content of grease of trees in the checkerboards, and TH represents the hardness of plants in the checkerboards.
Forest fires can not destroy everything, some plants select to adapt to forest fires, the plants reduce the oil content by improving the water content, when meeting forest fires, a large amount of heat is taken away by utilizing the evaporation of water in the body, the temperature is reduced, the vitality of the plants is preserved, the water content and the oil content of the plants are calculated, and the plants can effectively embody the effect of fire in the checkerboard to the fire by showing the content datamation of combustion-supporting substances in the checkerboard to the characteristics of combustion.
The plants in the forest depend on sunlight, soil, altitude, monsoon climate and the like, so the distribution of the plants in the forest is fixed, the life depending on the growth of the forest is relatively fixed, and the life depending on the growth of the plants is consistent with the characteristics of the plants through an enrichment phenomenon, so the distribution of combustion-supporting substances in the whole checkerboard of the plants can be represented, and the content of the combustion-supporting substances in the checkerboard is output by calculating the oil content and the water content of the plants in the forest.
The content of the combustion-supporting substances in the chequers is in direct proportion to the possibility of fire of the forest and the spreading speed of the forest fire, and the content of the combustion-supporting substances in the chequers is high.
The seventh step of establishing the forest fire spreading speed calculation model specifically comprises the following steps:
where R represents the rate of fire spread, R represents the initial source spread rate, slo represents the slope, θsRepresenting the angle of slope, thetawRepresenting wind direction, wv wind speed, ωSRepresenting the slope correction factor, a representing the forest fire spread coefficient, ρbThe particle size density of combustible distribution is shown, epsilon represents effective heat number, and Q represents ignition heat.
Wind and slopes can effectively promote the fire, and when the wind direction is opposite to the slope angle, the slope cannot promote the fire.
Step eight, simulating different checkerboards as ignition points, simulating the process of fire spreading, and counting the number of burned checkerboards and burned checkerboards before the rescue team arrives, wherein the specific steps comprise:
step 2.1: setting an initial fire point, and calculating the time of complete combustion of the checkerboard by a forest fire spreading speed calculation model;
step 2.2: collecting the current address and the traveling speed of a rescue team;
step 2.3: calculating the meeting time and place of the rescue team and the forest fire;
step 2.4: counting the number of the burned chessboards and the number of the burned chessboards before the rescue team arrives.
The judgment method for complete combustion of the checkerboard comprises the following steps: setting an area threshold and an edge threshold, wherein the area threshold and the edge threshold are more than or equal to 50%, the burned area of the checkerboards is more than the area threshold, and the burned edges of the checkerboards are more than the edge threshold.
Forest fire danger state monitoring and analyzing system based on artificial intelligence, fire danger monitoring and analyzing system includes: the system comprises a forest data acquisition module, a forest wind prediction module, a forest fire simulation model and a data display module;
the forest data acquisition module acquires forest data, stores the forest data in a structuralized mode and transmits the forest data to the forest wind prediction module and the forest fire simulation model;
the forest data acquisition module comprises a forest wind data acquisition module and a forest information acquisition module, acquires the wind direction of forest wind, the wind speed of forest wind and the atmospheric pressure of the forest, normalizes the atmospheric pressure of the forest and transmits the normalized atmospheric pressure to the forest wind prediction module;
the forest information acquisition module acquires a forest map, a forest gradient, forest vegetation distribution, forest rainfall data and forest evaporation capacity structure, stores the forest map, the forest gradient, the forest vegetation distribution, the forest rainfall data and the forest evaporation capacity structure and then transmits the forest map, the forest gradient, the forest vegetation distribution, the forest rainfall data and the forest evaporation capacity structure to the forest fire simulation module;
the forest wind prediction module builds a forest wind prediction model based on a time sequence prediction algorithm, a forest data acquisition module acquires forest wind data to set a training set, the model with the highest mAP value is output as a forest wind prediction model, and a forest wind direction prediction value of forest wind and a forest wind direction prediction value are output through the forest wind prediction model;
the forest fire simulation module simulates different places of a forest to generate forest fires for fire points, counts the burning area of the forest fires for the fire points in the different places before the rescue team arrives, outputs the burning area to the data display module,
the data display module is provided with an area burning threshold value, and when the burnt area exceeds the area burning threshold value, the data display module is displayed at the user terminal for a key monitoring area.
The important monitoring area is that once a fire disaster occurs, sufficient development time is provided before a rescue team arrives, the fire disaster can be easily developed into a major fire disaster, a user can easily find out the monitoring important through the display of the important monitoring area, and the fire disaster danger important area is further effectively checked.
The forest fire simulation module comprises a forest combustion-supporting substance content model and a forest fire spreading speed calculation model;
the forest combustion-supporting substance content model calculates the distribution of forest nutrient substances through plant distribution, and outputs the forest combustion-supporting substance content in the checkerboard to the forest fire spreading speed calculation model;
the forest fire spreading speed calculation model calculates the forest fire spreading speed based on the predicted wind direction value of forest wind, the predicted wind direction value of forest wind and the forest topography.
Compared with the prior art, the invention has the following beneficial effects: according to the method, the wind power data of the forest is predicted through a time series prediction algorithm, and the specific reference value of fire spread simulation data is ensured; according to the invention, the distribution of the combustion-supporting substances of the forest is calculated according to the vegetation distribution of the forest, a forest fire spreading speed calculation model is further established, the simulation of the forest fire is further realized, the key point of forest fire detection is found through the simulation of the forest fire, the manpower and material resources are saved, and the fire danger key area is effectively investigated.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic structural diagram of a forest fire danger state monitoring and analyzing system based on artificial intelligence;
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention provides a technical solution:
the first embodiment is as follows: a forest fire danger state monitoring and analyzing method based on artificial intelligence comprises the following specific steps:
the method comprises the following steps: collecting forest wind power data, wherein the forest wind power data comprises the wind direction of forest wind, the wind speed of the forest wind and the atmospheric pressure of a forest;
step two: normalizing the forest atmospheric pressure, and outputting a normalized value of the forest atmospheric pressure;
step three: constructing a forest wind prediction model based on LSTM, inputting the wind direction of forest wind, the wind speed of forest wind and the forest atmospheric pressure normalization value, training the model, outputting the forest wind prediction model with the highest mAP value, and predicting the wind speed of forest wind and the wind direction of forest wind through the forest wind prediction model;
the forest fire is greatly influenced by the current wind speed and wind direction when the forest fire occurs, particularly in the initial stage of the fire, the influence of the wind speed and the wind direction is the largest, the fire borrows the wind force, and the wind mainly guides the spreading direction of the fire force;
china is located in the southeast of the Asian European continent, obvious seasonal changes of climate are formed due to different physical properties of the sea and the continent, the whole seasonal wind is regular in the whole year, the wind direction is fixed, and the local wind power can be changed in detail under the condition of large wind direction;
when a forest fire is researched, a more specific wind direction is needed, when the forest fire is not completely out of control, the wind direction leads the fire behavior, the possible wind direction is predicted through a time prediction algorithm, and the specific reference value of further fire spreading simulation data is guaranteed.
Step four: collecting forest data, wherein the forest data comprises a forest map, a forest gradient, forest vegetation distribution, forest rainfall data and forest evaporation capacity;
step five: dividing a forest into chequers according to the detection range of the forest fire monitoring equipment;
step six: calculating the content of combustion-supporting substances of the single checkerboard forest according to the vegetation distribution of the forest;
step seven: establishing a forest fire spreading speed calculation model;
step eight: simulating different checkerboards as fire points, simulating the process of fire spreading, and counting the number of the checkerboards burned before the rescue team arrives;
step nine: and setting a quantity threshold value of the burned checkerboards, and judging that the current ignition point is a key monitoring area when the quantity of the burned checkerboards exceeds the quantity threshold value of the burned checkerboards.
The wind direction of the forest can be changed continuously according to the change of time, a key monitoring area can be output continuously through a forest wind prediction algorithm, once a fire disaster happens in the key monitoring area, the fire disaster is an area which is difficult to rescue by a rescue team, the fire disaster is easy to further develop into a serious fire disaster, and the influence is serious.
And step two, normalizing the atmospheric pressure of the forest, further strengthening the characteristics of the atmospheric pressure of the forest, and effectively improving the accuracy of the prediction model of the forest wind. The specific calculation formula of the output forest atmospheric pressure normalization value is as follows: normalizing atmospheric pressure of a forest
Wherein AP represents a numerical value of the atmospheric pressure of the forest, μ represents a mean value of the atmospheric pressure of the forest,
atmospheric normalized values for the forest are shown.
Step three, establishing specific contents of a forest wind prediction model based on LSTM, comprising the following steps: the forest wind forecasting model is provided with an attention mechanism on an LSTM network layer, and an output layer is connected with a full connection layer.
Sixthly, calculating the content of the combustion-supporting substances of the single checkerboard forest according to the vegetation distribution of the forest, and the specific steps comprise: on the basis of the water content of the plants, calculating the precipitation and evaporation capacity of the forest, and effectively predicting the water content of vegetation in a short time; in case of fire outburst, the content of the vegetation combustion-supporting substances is accurately judged by effectively calculating the prediction of the water content of the vegetation in a short time;
step 1.1: collecting forest rainfall data and forest evaporation capacity, wherein the forest rainfall data comprises rainfall and rainfall interval time;
step 1.2: calculating the oil content OC of the trees in the checkerboard;
step 1.3: and (3) calculating the water content of the plants in the checkerboard, wherein the specific calculation formula is as follows:
wherein WC represents the water content of the plants in the checkerboard, RF represents the forest rainfall, EC represents the forest evaporation capacity, and WC represents the water content of the plants in the checkerboard;
step 1.4: and (3) calculating the content of the combustion-supporting substances in the checkerboards, wherein the specific calculation formula is as follows:
wherein CSS represents the content of combustion-supporting substances in the checkerboards, OC represents the content of grease of trees in the checkerboards, and TH represents the hardness of plants in the checkerboards.
Forest fires can not destroy everything, some plants select to adapt to forest fires, the plants reduce the oil content by improving the water content, when meeting forest fires, a large amount of heat is taken away by utilizing the evaporation of water in the body, the temperature is reduced, the vitality of the plants is preserved, the water content and the oil content of the plants are calculated, and the plants can effectively embody the effect of fire in the checkerboard to the fire by showing the content datamation of combustion-supporting substances in the checkerboard to the characteristics of combustion.
The plants in the forest depend on sunlight, soil, altitude, monsoon climate and the like, so the distribution of the plants in the forest is fixed, the life depending on the growth of the forest is relatively fixed, and the life depending on the growth of the plants is consistent with the characteristics of the plants through an enrichment phenomenon, so the distribution of the combustion-supporting substances in the whole checkerboard of the plants in the checkerboard can be represented, and the content of the combustion-supporting substances in the checkerboard is output by calculating the oil content and the water content of the plants in the forest.
The content of the combustion-supporting substances in the chequers is in direct proportion to the possibility of fire of the forest and the spreading speed of the forest fire, and the content of the combustion-supporting substances in the chequers is high.
The seventh step of establishing the specific contents of the forest fire spreading speed calculation model comprises the following steps:
where R represents the rate of fire spread, R represents the initial source spread rate, slo represents the slope, θsRepresenting the angle of slope, thetawRepresenting wind direction, wv wind speed, ωSRepresents the slope correction factor, a represents the forest fire spread coefficient, ρbThe particle size density of combustible distribution is shown, epsilon represents effective heat number, and Q represents ignition heat.
Wind and slopes can effectively promote the fire, and when the wind direction is opposite to the slope angle, the slope cannot promote the fire.
Step eight, simulating different checkerboards as ignition points, simulating the process of fire spreading, and counting the number of burned checkerboards and burned checkerboards before the rescue team arrives, wherein the specific steps comprise:
step 2.1: setting an initial ignition point, and calculating the complete combustion time of the checkerboards by a forest fire spreading speed calculation model;
step 2.2: collecting the current address and the traveling speed of a rescue team;
step 2.3: calculating the meeting time and place of the rescue team and the forest fire;
step 2.4: counting the number of the burned chessboards and the number of the burned chessboards before the rescue team arrives.
The judgment method for complete combustion of the checkerboard comprises the following steps: setting an area threshold and an edge threshold, wherein the area threshold and the edge threshold are more than or equal to 50%, the burned area of the checkerboards is more than the area threshold, and the burned edges of the checkerboards are more than the edge threshold.
Forest fire danger state monitoring and analyzing system based on artificial intelligence, fire danger monitoring and analyzing system includes: the system comprises a forest data acquisition module, a forest wind prediction module, a forest fire simulation model and a data display module;
the forest data acquisition module acquires forest data, stores the forest data in a structuralized mode and transmits the forest data to the forest wind prediction module and the forest fire simulation model;
the forest data acquisition module comprises a forest wind data acquisition module and a forest information acquisition module, acquires the wind direction of forest wind, the wind speed of forest wind and the atmospheric pressure of the forest, normalizes the atmospheric pressure of the forest and transmits the normalized atmospheric pressure of the forest to the forest wind prediction module;
the forest information acquisition module acquires a forest map, a forest gradient, forest vegetation distribution, forest rainfall data and a forest evaporation capacity structure, stores the forest map, the forest gradient, the forest vegetation distribution, the forest rainfall data and the forest evaporation capacity structure and transmits the forest map, the forest rainfall data and the forest evaporation capacity structure to the forest fire simulation module;
the forest wind prediction module builds a forest wind prediction model based on a time sequence prediction algorithm, a forest data acquisition module acquires forest wind data to set a training set, the model with the highest mAP value is output as a forest wind prediction model, and a forest wind direction prediction value of forest wind and a wind direction prediction value of forest wind are output through the forest wind prediction model;
the forest fire simulation module simulates different places of a forest to generate forest fires for fire points, counts the combustion areas of the forest fires for the fire points before rescue teams arrive at the different places and outputs the forest fires to the data display module,
the data display module sets an area burning threshold value, and when the burnt area exceeds the area burning threshold value, the area is displayed at the user terminal as a key monitoring area.
The key monitoring area is that once a fire disaster occurs, the fire disaster has sufficient development time before the rescue team arrives, the fire disaster can be easily developed into a major fire disaster, and a user can easily find the key point of monitoring through the key monitoring area display, so that the key area of fire disaster danger can be further effectively investigated.
The forest fire simulation module comprises a forest combustion-supporting substance content model and a forest fire spreading speed calculation model;
calculating the distribution of forest nutrient substances by a forest combustion-supporting substance content model through plant distribution, and outputting the forest combustion-supporting substance content in the checkerboard to a forest fire spreading speed calculation model;
the forest fire spreading speed calculation model calculates the forest fire spreading speed based on the predicted value of the wind direction of the forest wind, the predicted value of the wind direction of the forest wind and the forest topography.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. The forest fire danger state monitoring and analyzing method based on artificial intelligence is characterized by comprising the following steps of: the fire danger state monitoring and analyzing method comprises the following specific steps:
the method comprises the following steps: collecting forest wind power data, wherein the forest wind power data comprises the wind direction of forest wind, the wind speed of the forest wind and the atmospheric pressure of a forest;
step two: normalizing the forest atmospheric pressure, and outputting a forest atmospheric pressure normalization value;
step three: constructing a forest wind prediction model based on LSTM, inputting the wind direction of forest wind, the wind speed of forest wind and the normalized value of forest atmospheric pressure, training the model, outputting the forest wind prediction model with the highest mAP value, and predicting the wind speed of forest wind and the wind direction of forest wind through the forest wind prediction model;
step four: collecting forest data, wherein the forest data comprises a forest map, a forest gradient, forest vegetation distribution, forest rainfall data and forest evaporation capacity;
step five: dividing the forest into chequerboards according to the detection range of the forest fire monitoring equipment;
step six: calculating the content of combustion-supporting substances of the single checkerboard forest according to the vegetation distribution of the forest;
step seven: establishing a forest fire spreading speed calculation model;
step eight: simulating different checkerboards as fire points, simulating the process of fire spreading, and counting the number of checkerboards burnt before the rescue team arrives;
step nine: and setting a quantity threshold value of the burned checkerboards, and judging that the current ignition point is a key monitoring area when the quantity of the burned checkerboards exceeds the quantity threshold value of the burned checkerboards.
2. The forest fire danger state monitoring and analyzing method based on artificial intelligence as claimed in claim 1, wherein: normalizing the forest atmospheric pressure in the second step, wherein a specific calculation formula of an output forest atmospheric pressure normalization value is as follows: normalizing atmospheric pressure of a forest
Wherein AP represents a numerical value of the atmospheric pressure of the forest, μ represents a mean value of the atmospheric pressure of the forest,
atmospheric normalized values for the forest are shown.
3. The forest fire danger state monitoring and analyzing method based on artificial intelligence of claim 1, wherein the method comprises the following steps: the third step of establishing the specific contents of the forest wind prediction model based on the LSTM comprises the following steps: the forest wind prediction model is provided with an attention mechanism on an LSTM network layer, and an output layer is connected with a full connection layer.
4. The forest fire danger state monitoring and analyzing method based on artificial intelligence as claimed in claim 1, wherein: the sixth step of calculating the content of the combustion-supporting substances of the single checkerboard forest according to the vegetation distribution of the forest comprises the following specific steps:
step 1.1: collecting forest rainfall data and forest evaporation capacity, wherein the forest rainfall data comprises rainfall and rainfall interval time;
step 1.2: calculating the oil content OC of the trees in the checkerboard;
step 1.3: calculating the water content of the plants in the checkerboard, wherein the specific calculation formula is as follows:
wherein WC represents the water content of the plants in the checkerboard, RF represents the forest rainfall, EC represents the forest evaporation capacity, and WC represents the water content of the plants in the checkerboard;
step 1.4: calculating the content of the combustion-supporting substances in the checkerboard, wherein the specific calculation formula is as follows:
wherein CSS represents the content of combustion-supporting substances in the checkerboards, OC represents the content of grease of trees in the checkerboards, and TH represents the hardness of plants in the checkerboards.
5. The forest fire danger state monitoring and analyzing method based on artificial intelligence as claimed in claim 1, wherein: the seventh step of establishing the specific contents of the forest fire spreading speed calculation model comprises the following steps:
where R represents the rate of fire spread, R represents the initial source spread rate, slo represents the slope, θsThe angle of the slope is shown as an angle,θwrepresenting wind direction, wv wind speed, ωSRepresenting the slope correction factor, a representing the forest fire spread coefficient, ρbThe particle size density of combustible distribution is shown, epsilon represents effective heat number, and Q represents ignition heat.
6. The forest fire danger state monitoring and analyzing method based on artificial intelligence as claimed in claim 1, wherein: simulating different chequers as ignition points, simulating the process of fire spreading, and counting the number of the burnt chequers and the number of the burnt chequers before the rescue team arrives, wherein the step eight comprises the following specific steps:
step 2.1: setting an initial fire point, and calculating the time of complete combustion of the checkerboard by a forest fire spreading speed calculation model;
step 2.2: collecting the current address and the traveling speed of a rescue team;
step 2.3: calculating the meeting time and place of the rescue team and the forest fire;
step 2.4: counting the number of the burned chessboards and the number of the burned chessboards before the rescue team arrives.
7. The forest fire danger state monitoring and analyzing method based on artificial intelligence as claimed in claim 6, wherein: the judgment method for complete combustion of the checkerboard comprises the following steps: setting an area threshold and an edge threshold, wherein the area threshold and the edge threshold are more than or equal to 50%, the burned area of the checkerboards is more than the area threshold, and the burned edges of the checkerboards are more than the edge threshold.
8. Forest fire danger state monitoring and analyzing system based on artificial intelligence, its characterized in that: the fire risk monitoring and analyzing system comprises: the system comprises a forest data acquisition module, a forest wind prediction module, a forest fire simulation model and a data display module;
the forest data acquisition module acquires forest data, stores the forest data in a structuralized mode and transmits the forest data to the forest wind prediction module and the forest fire simulation model;
the forest data acquisition module comprises a forest wind data acquisition module and a forest information acquisition module, acquires the wind direction of forest wind, the wind speed of forest wind and the atmospheric pressure of the forest, normalizes the atmospheric pressure of the forest and transmits the normalized atmospheric pressure to the forest wind prediction module;
the forest information acquisition module acquires a forest map, a forest gradient, forest vegetation distribution, forest rainfall data and forest evaporation capacity structure, stores the forest map, the forest gradient, the forest vegetation distribution, the forest rainfall data and the forest evaporation capacity structure and then transmits the forest map, the forest gradient, the forest vegetation distribution, the forest rainfall data and the forest evaporation capacity structure to the forest fire simulation module;
the forest wind prediction module builds a forest wind prediction model based on a time sequence prediction algorithm, a forest data acquisition module acquires forest wind data to set a training set, the model with the highest mAP value is output as a forest wind prediction model, and a forest wind direction prediction value of forest wind and a forest wind direction prediction value are output through the forest wind prediction model;
the forest fire simulation module simulates different places of a forest to generate forest fires for fire points, counts the burning area of the forest fires for the fire points in the different places before the rescue team arrives, outputs the burning area to the data display module,
the data display module is provided with an area burning threshold value, and when the burnt area exceeds the area burning threshold value, the data display module is displayed at the user terminal for a key monitoring area.
9. The forest fire danger state monitoring and analyzing system based on artificial intelligence of claim 8, wherein: the forest fire simulation module comprises a forest combustion-supporting substance content model and a forest fire spreading speed calculation model;
the forest combustion-supporting substance content model calculates the distribution of forest nutrient substances through plant distribution, and outputs the forest combustion-supporting substance content in the checkerboard to the forest fire spreading speed calculation model; the forest fire spreading speed calculation model is used for calculating the forest fire spreading speed based on the predicted wind direction value of forest wind, the predicted wind direction value of forest wind and forest topography.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210213924.4A CN114757387A (en) | 2022-03-07 | 2022-03-07 | Forest fire danger state monitoring and analyzing system and method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210213924.4A CN114757387A (en) | 2022-03-07 | 2022-03-07 | Forest fire danger state monitoring and analyzing system and method based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114757387A true CN114757387A (en) | 2022-07-15 |
Family
ID=82325292
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210213924.4A Pending CN114757387A (en) | 2022-03-07 | 2022-03-07 | Forest fire danger state monitoring and analyzing system and method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114757387A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115661245A (en) * | 2022-10-24 | 2023-01-31 | 东北林业大学 | Large-scale live wire instantaneous positioning method based on unmanned aerial vehicle |
| CN116415712A (en) * | 2023-02-14 | 2023-07-11 | 武汉大学 | Fire spread prediction method and system based on multiple data sources |
| CN116563719A (en) * | 2023-07-12 | 2023-08-08 | 四川三思德科技有限公司 | Fire identification prediction method, system and medium based on air volume data |
| CN116612440A (en) * | 2023-07-21 | 2023-08-18 | 山东金宇信息科技集团有限公司 | Building engineering safety monitoring method, equipment and medium based on machine vision |
| CN117173848A (en) * | 2023-09-07 | 2023-12-05 | 海南省林业科学研究院(海南省红树林研究院) | Forest fire detection method based on data analysis |
-
2022
- 2022-03-07 CN CN202210213924.4A patent/CN114757387A/en active Pending
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115661245A (en) * | 2022-10-24 | 2023-01-31 | 东北林业大学 | Large-scale live wire instantaneous positioning method based on unmanned aerial vehicle |
| CN115661245B (en) * | 2022-10-24 | 2023-04-18 | 东北林业大学 | Large-scale live wire instantaneous positioning method based on unmanned aerial vehicle |
| CN116415712A (en) * | 2023-02-14 | 2023-07-11 | 武汉大学 | Fire spread prediction method and system based on multiple data sources |
| CN116563719A (en) * | 2023-07-12 | 2023-08-08 | 四川三思德科技有限公司 | Fire identification prediction method, system and medium based on air volume data |
| CN116563719B (en) * | 2023-07-12 | 2023-10-20 | 四川三思德科技有限公司 | Fire identification prediction method, system and medium based on air volume data |
| CN116612440A (en) * | 2023-07-21 | 2023-08-18 | 山东金宇信息科技集团有限公司 | Building engineering safety monitoring method, equipment and medium based on machine vision |
| CN116612440B (en) * | 2023-07-21 | 2023-09-29 | 山东金宇信息科技集团有限公司 | Building engineering safety monitoring method, equipment and medium based on machine vision |
| CN117173848A (en) * | 2023-09-07 | 2023-12-05 | 海南省林业科学研究院(海南省红树林研究院) | Forest fire detection method based on data analysis |
| CN117173848B (en) * | 2023-09-07 | 2024-05-07 | 海南省林业科学研究院(海南省红树林研究院) | Forest fire detection method based on data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114757387A (en) | Forest fire danger state monitoring and analyzing system and method based on artificial intelligence | |
| Beringer et al. | Fire impacts on surface heat, moisture and carbon fluxes from a tropical savanna in northern Australia | |
| Pielke Sr et al. | Land use/land cover changes and climate: modeling analysis and observational evidence | |
| Rapaport | The Pacific islands: environment and society | |
| CN102542128B (en) | Forest fire danger accurate zoning model for southern collective forest areas | |
| Minale et al. | Hydrological dynamics and human impact on ecosystems of Lake Tana, northwestern Ethiopia | |
| Wei et al. | Quantifying the indirect effects of urbanization on urban vegetation carbon uptake in the megacity of Shanghai, China | |
| López-Blanco et al. | Multi-year data-model evaluation reveals the importance of nutrient availability over climate in arctic ecosystem C dynamics | |
| Granieri et al. | Carbon dioxide in the urban area of Naples: Contribution and effects of the volcanic source | |
| Mölders et al. | Influence of wildfire induced land-cover changes on clouds and precipitation in Interior Alaska—A case study | |
| Tariq et al. | Impact of aridity rise and arid lands expansion on carbon‐storing capacity, biodiversity loss, and ecosystem services | |
| Yue et al. | A patch connectivity index and its change in relation to new wetland at the Yellow River Delta | |
| Midgley et al. | Impacts, vulnerability and adaptation in key South African sectors | |
| CN114638736A (en) | Forest fire prevention data analysis system and method based on Internet of things | |
| Zhou et al. | Spatiotemporal dynamics of encroaching tall vegetation in timberline ecotone of the Polar Urals Region, Russia | |
| CN117910799A (en) | Forest fire disaster risk assessment method, system, equipment and medium | |
| Tanyukevich et al. | Fires in arid agroforestal landscapes and their damage assessment | |
| Dumayne | Late Holocene palaeoecology and human impact on the environment of northern Britain | |
| Islam et al. | Spatiotemporal mapping mangroves of Tengragiri wildlife sanctuary under Barguna district of Bangladesh using freely available satellite imagery | |
| Yin et al. | The simulation of surface fire spread based on Rothermel model in windthrow area of Changbai Mountain (Jilin, China) | |
| Daniels | Land surface impacts on precipitation in the Netherlands | |
| Li et al. | Validating the usefulness and calibration of a two-dimensional situation model of urgency-adaptability for cities responding to climate change—Taking Shenzhen as case study | |
| Mojiol | Ecological landuse planning and sustainable management of urban and sub-urban green areas in Kota Kinabalu, Malaysia | |
| Santos | The role of wind direction on the occurrence of large fire events in Portugal | |
| Ibol | Assessing the Change of Land Use and Land Cover in the Gambia |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |