CN113792427B - Forest fire spread prediction simulation method under existing boundary conditions - Google Patents
Forest fire spread prediction simulation method under existing boundary conditions Download PDFInfo
- Publication number
- CN113792427B CN113792427B CN202111072420.7A CN202111072420A CN113792427B CN 113792427 B CN113792427 B CN 113792427B CN 202111072420 A CN202111072420 A CN 202111072420A CN 113792427 B CN113792427 B CN 113792427B
- Authority
- CN
- China
- Prior art keywords
- fire
- vector
- vertex
- spreading
- data
- 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.)
- Active
Links
- 238000004088 simulation Methods 0.000 title claims abstract description 35
- 238000000034 method Methods 0.000 title claims abstract description 26
- 239000013598 vector Substances 0.000 claims abstract description 73
- 238000011160 research Methods 0.000 claims abstract description 6
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000002485 combustion reaction Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000011835 investigation Methods 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000001629 suppression Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
- 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
- G06Q50/265—Personal security, identity or safety
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- Geometry (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Computer Security & Cryptography (AREA)
- Computer Hardware Design (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (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 relates to a forest fire spread prediction simulation method under the existing boundary condition. Comprising the following steps: inputting forest fire spreading area data (topographic data, combustibles and wind speeds) and establishing a data grid; extracting an actual fire boundary into a vector polygon, and then superposing the vector polygon in a research area; judging the position of a grid where the vertex of the fire boundary polygon falls; calculating the spreading speed of each vertex by a fire spreading simulation method according to a series of data of the grid, and determining the spreading direction; a fixed time step T is set to simulate the fire boundary at the next moment, and the future fire range can be obtained according to the method. According to the method, the fire boundary is extracted, and the spreading simulation is performed, so that a simulation result can be obtained more practically, accurately and efficiently.
Description
Technical Field
The invention relates to the field of forest fire spread simulation prediction, in particular to a method for forest fire spread prediction simulation under the existing boundary condition.
Background
Forest fires are a common natural hazard. And can cause little damage to the nature, even some places can cause great harm to the life of human beings. If it is not managed and controlled, the damage caused by its development is not estimated. How to timely and effectively acquire the current state information (weather information such as fire range, fire intensity, propulsion speed, fire type, wind speed and direction) of the fire after the fire occurs; how to restore the fire scene information in the virtual scene of the computer by adopting the existing visualization technology; how to use mathematical model to predict the spreading trend of fire under the real-time dynamic parameters, the comprehensive application of the technical means has great significance for disaster prevention and reduction after the occurrence of fire.
By turning over a large number of documents, it has been found that the simulation of forest fire spread in most of the prior documents is performed by taking the ignition point as the starting point, and the factor considered by the simulation method is ideal and the fire simulation effect for a small range and short period in the initial stage of fire is good. In practice, the fire is found to have been burned for some time. A range of damage has been inflicted, in which case decision-makers are more concerned with predicting the trend of a fire in the future over a period of time under existing fire boundary conditions. Based on the idea, a method for spreading simulation based on fire boundaries is proposed, so that the efficiency and accuracy in actual fire simulation can be improved.
Disclosure of Invention
The invention aims to provide a forest fire spread prediction simulation method under the existing boundary conditions, which can be well used for performing simulation prediction based on a certain fire range which is already burnt in practical situations. Therefore, the efficiency of the actual fire simulation can be improved, the actual fire boundary can be conveniently obtained in real time, and the model is improved, so that the accuracy is improved.
In order to achieve the above purpose, the technical scheme of the invention is as follows: a forest fire spread prediction simulation method under the existing boundary conditions comprises the following steps:
s1, inputting forest fire spreading area data and constructing a two-dimensional grid:
s2, setting the total combustion duration as T and the time step as T;
s3, extracting fire boundaries into vector polygons, and superposing the vector polygons on a research area;
s4, calculating the vertex position of each vector polygon;
s5, calculating the spreading speed and the spreading direction of each vertex;
s6, calculating a fire boundary at the next moment according to the time step;
and S7, repeating the steps S4-S6 to finish the simulation of fire spread.
In one embodiment of the present invention, in step S1, the investigation region is divided into a plurality of 60m×60m grids by using a regular grid form on a computer, and the combustible data, slope data, wind speed and direction data are input and stored into the grids.
In one embodiment of the present invention, in step S3, the method used to obtain the vector polygon of the fire boundary from the fire is: acquiring a thermal infrared image of a forest fire, then processing the thermal infrared image, and adding spatial and geographic position information to the fire boundary; extraction thereof using Canny edge monitoring, comprising: noise reduction of the image, image gradient calculation, non-maximum suppression and threshold screening; then further processing by using a refined algorithm; obtaining the outline of the fire boundary; extracting the contour lines as characteristic points, and connecting the characteristic points into polygons; it is transformed into a vector polygon which is superimposed on the investigation region.
In one embodiment of the present invention, in step S4, each vector polygon vertex is traversed in a computer, and a feature point is reserved when a plurality of feature points appear in the same grid; and calculating the mesh position of the vertex of each finally reserved vector polygon.
In one embodiment of the present invention, in step S5, each vector polygon vertex is traversed in a computer, and the speed of fire spread at each vertex is calculated by using a forest fire spread simulation formula according to the mesh data in which it is located; and calculating the fire spreading direction according to the gradient data, the wind direction data and the normal line data of the fire wire.
In one embodiment of the invention, the direction of fire propagation is the sum of the line normal and the slope of the adjacent edges of the vertices of each vector polygon and the wind direction vector.
In one embodiment of the present invention, in step S6, a new vector polygon for the next time step is calculated using the fire spread speed and direction of the vertices according to the set time step t.
In an embodiment of the present invention, when calculating a new vector polygon, the distance between adjacent vertices of the new fire polygon is traversed to form the new vector polygon, and the edge length of the new vector polygon is linearly interpolated to form a plurality of vertices when the distance is greater than a fixed distance, so as to ensure that the distance between the vertices is smaller than a given fixed distance.
In one embodiment of the present invention, in step S7, the result obtained in step S6 is used as a new vector polygon, and then the fire spread simulation of the next time step is performed until the simulated duration reaches the total duration.
In one embodiment of the invention, the sum of the vectors for each vertex is calculated as follows: the spreading direction of each vertex is determined by 3 vectors, namely gradient, wind direction and fire wire normal; then adding the two components by utilizing a parallelogram method; the calculation formula is as follows:wherein->For each vertex gradient vector ++>For each vertex wind vector, +.>For each vertex normal vector,/>Is a unit vector of x-axis,>is the unit vector of the y axis; i.e 1 ，j 1 ，k 1 The components of the respective vectors in the x-direction，i 2 ，j 2 ，k 2 Components of the respective vectors in the y direction; by calculating such vectors, new vectors of the respective vertexes are obtained, the direction of which is the direction in which the fire spot spreads.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides a forest fire spread prediction simulation method under the existing boundary condition, which more specifically and practically considers the simulation of forest fire spread. Instead of taking the ignition point as the starting point, the fire range is taken as a research object, and the simulation prediction is performed by combining the topographic data, the combustible data and the meteorological data. Thus, the spreading process is more accurately simulated, and the forest fire spreading precision is improved. Such simulated predictions are easier to combine with real-time and actual fires, thereby continually improving the model and thus accuracy.
Drawings
Fig. 1 is a flowchart of a method for predicting and simulating forest fire spread under the existing boundary conditions according to an embodiment of the present invention.
Fig. 2 is a regular grid diagram of an embodiment of the present invention.
FIG. 3 is a schematic diagram of a fire boundary superimposed on a regular grid of the present invention.
Fig. 4 is a calculation diagram of the fire spread direction of the present invention.
Fig. 5 is a schematic illustration of the propagation of a fire boundary of the present invention in one step.
Detailed Description
The technical scheme of the invention is specifically described below with reference to the accompanying drawings.
The embodiment of the invention provides a method for predicting and simulating forest fire spread under the existing boundary condition, which is shown by referring to fig. 1 and mainly comprises the following steps:
step S1, inputting forest fire spread area data (weather, combustibles and terrains) and constructing a two-dimensional grid on the basis of the forest fire spread area data:
inputting meteorological data (wind speed and wind direction data), combustible data and topographic data in a two-dimensional lattice form;
a regular grid is built in the computer, the side length of the grid is the space step length, the side length of the grid is equal, and the size of the regular grid represents the size of the space resolution, as shown in fig. 2. Numbering the constructed two-dimensional grid from left to right so as to facilitate the position determination of the vertexes of the subsequent vector polygons. The lattice data is stored in two-dimensional grids constructed such that they correspond one-to-one to each other, with each grid storing a unique set of input data for subsequent computation.
Step S2, setting the total combustion duration T, and setting the time step length as T:
the method comprises the steps that before fire simulation is conducted, the ending time is regulated, namely the total combustion time is T, when the simulated time reaches T, the combustion can be considered to be finished, and then the simulation can be ended;
the time step t is a fixed time step to be set by us, and also refers to a time interval from one fire boundary to the next fire boundary, in theory, the smaller the time t is set, the more accurate the simulated fire boundary is.
S3, extracting fire boundaries into vector polygons, and superposing the vector polygons on a research area;
the thermal infrared image may be acquired using an unmanned aerial vehicle and then processed with the positional information attached to it to form a thermal infrared image with spatial positional information.
The fire edge is then aligned for extraction, including but not limited to, using classical Canny edge monitoring, the main process being: noise reduction of the image, image gradient calculation, non-maximum suppression and threshold screening; processing the fire boundary by using a Pavldis refinement algorithm to obtain the outline of the fire boundary;
extracting the contour lines as feature points, connecting the feature points into polygons, and determining the geographic coordinates of each feature point; it is transformed into a vector polygon which is superimposed on the mesh of the investigation region according to its coordinates as shown in fig. 3.
Step S4, calculating the vertex position of each vector polygon:
traversing each polygon vertex in a computer, and reserving unique vertices when more than one vertex exists in the same grid so as to simulate the fire spread at the back; and determining the position of the grid where each vertex is positioned according to the coordinates of each vertex.
Step S5, calculating the spreading speed and the spreading direction of each vertex:
the method comprises the steps of utilizing the position of a grid where each vertex is positioned, utilizing data stored in the grid, and utilizing the existing fire spreading simulation speed calculation formulas, including but not limited to the calculation formulas of the Rothermel model, and calculating the fire spreading speed of each vertex by using the Wang Zhengfei calculation formulas;
determination of the direction of its propagation: mainly 3 kinds of vectors, including: wind direction data, gradient data and normal line of a fire wire;
the essence is that for 3 data, vectors are added, and the vectors are added two by utilizing a parallelogram rule; as shown in fig. 4. The main calculation formula is as follows:wherein->Each vertex gradient vector->Vector of wind per vertex>Each vertex normal vector>Is a unit vector of x-axis,>is the unit vector of the y-axis. i.e 1 ，j 1 ，k 1 The components of the respective vectors in the x-direction, i 2 ，j 2 ，k 2 Respectively are provided withIs the component of each vector in the y-direction; the new vector to each vertex can be calculated by the vector, and the direction is the spreading direction of the fire disaster point.
The new vector to each vertex can be calculated by the vector, and the direction is the spreading direction of the fire disaster point.
Step S6, calculating a fire boundary at the next moment:
according to the set time step t, sequentially calculating the vertex position of the next step by using the calculated fire spreading speed and direction of the vertex, so as to preliminarily obtain the fire boundary of the next step; as shown in fig. 5, the direction of the arrow in the figure is the spreading direction, and the size is the spreading distance under one step;
then, a fixed value is set to judge whether the side length is larger than the fixed value or not by traversing the distance between every two adjacent vertexes, if so, the side length is interpolated, and the interpolation method comprises but is not limited to linear interpolation and B-spline interpolation, so that a plurality of vertexes are formed, and the distance between every two vertexes is ensured to be smaller than the given fixed distance. This improves the accuracy of the simulation for the next step.
Step S7, repeating the steps to finish the simulation of fire spread:
and judging whether the simulation duration reaches the total duration, if not, repeating the steps S4, S5 and S6 to continuously output the fire boundary of each step length, and if so, judging that the combustion is finished, and ending the fire simulation.
The above is a preferred embodiment of the present invention, and all changes made according to the technical solution of the present invention belong to the protection scope of the present invention when the generated functional effects do not exceed the scope of the technical solution of the present invention.
Claims (3)
1. The method for predicting and simulating the forest fire spread under the existing boundary condition is characterized by comprising the following steps of:
s1, inputting forest fire spreading area data and constructing a two-dimensional grid:
s2, setting the total combustion duration as T and the time step as T;
s3, extracting fire boundaries into vector polygons, and superposing the vector polygons on a research area;
s4, calculating the vertex position of each vector polygon;
s5, calculating the spreading speed and the spreading direction of each vertex;
s6, calculating a fire boundary at the next moment according to the time step;
s7, repeating the steps S4-S6 to finish the simulation of fire spread;
in step S3, the method used to obtain the vector polygon of the fire boundary from the fire is: acquiring a thermal infrared image of a forest fire, then processing the thermal infrared image, and adding spatial and geographic position information to the fire boundary; extraction thereof using Canny edge monitoring, comprising: noise reduction of the image, image gradient calculation, non-maximum suppression and threshold screening; then further processing by using a refined algorithm; obtaining the outline of the fire boundary; extracting the contour lines as characteristic points, and connecting the characteristic points into polygons; converting the vector polygon into a vector polygon, and superposing the vector polygon on a research area; in step S4, traversing each vector polygon vertex in a computer, and reserving a feature point when a plurality of feature points appear in the same grid; calculating the grid position of the vertex of each finally reserved vector polygon; in step S5, traversing each vector polygon vertex in a computer, and calculating the fire spreading speed of each vertex by using a forest fire spreading simulation formula according to the grid data of each vector polygon vertex; calculating the direction of fire disaster spreading according to the gradient data, the wind direction data and the normal line data of the fire wire; the direction of fire spread is the sum of the fire line normal line and the gradient of the adjacent edge of each vector polygon vertex and the wind direction vector; in step S6, according to the set time step t, calculating a new vector polygon of the next time step by using the fire spreading speed and direction of the vertex; when calculating new vector polygon, traversing to form new distance between adjacent vertexes of fire polygon, linear interpolation is performed on side length to form multiple vertexes when distance is larger than fixed distance, thereby ensuring distance between vertexes is smaller than given valueIs a fixed distance from (a) to (b); the sum of the vectors for each vertex is calculated as follows: the spreading direction of each vertex is determined by 3 vectors, namely gradient, wind direction and fire wire normal; then adding the two components by utilizing a parallelogram method; the calculation formula is as follows:wherein->For each vertex gradient vector ++>For each vertex wind vector, +.>For each vertex normal vector,/>Is a unit vector of x-axis,>is the unit vector of the y axis; i.e 1， j 1 ，k 1 The components of the respective vectors in the x-direction, i 2 ，j 2 ，k 2 Components of the respective vectors in the y direction; by calculating such vectors, new vectors of the respective vertexes are obtained, the direction of which is the direction in which the fire spot spreads.
2. A method for forest fire spread prediction simulation according to claim 1, wherein in step S1, the investigation region is divided into a plurality of 60m x 60m grids by using a regular grid form on a computer, and the combustible data, slope data, wind speed and direction data are input and stored into the grids.
3. A method of forest fire spread prediction simulation according to claim 1, wherein in step S7, the result obtained in step S6 is used as a new vector polygon, and the fire spread simulation of the next time step is performed until the simulated duration reaches the total duration.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111072420.7A CN113792427B (en) | 2021-09-14 | 2021-09-14 | Forest fire spread prediction simulation method under existing boundary conditions |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111072420.7A CN113792427B (en) | 2021-09-14 | 2021-09-14 | Forest fire spread prediction simulation method under existing boundary conditions |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113792427A CN113792427A (en) | 2021-12-14 |
| CN113792427B true CN113792427B (en) | 2023-08-04 |
Family
ID=79183188
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111072420.7A Active CN113792427B (en) | 2021-09-14 | 2021-09-14 | Forest fire spread prediction simulation method under existing boundary conditions |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113792427B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114821320A (en) * | 2022-04-27 | 2022-07-29 | 福州大学 | Method for reversely deducing fire source position through forest fire track ground boundary |
| CN114818325B (en) * | 2022-04-27 | 2024-06-04 | 福州大学 | Method for determining position of forest fire ignition point by sampling method |
| CN114936502B (en) * | 2022-07-25 | 2022-10-04 | 四川开澜科技有限公司 | Forest fire spreading situation boundary analysis method, system, terminal and medium |
| CN116415712A (en) * | 2023-02-14 | 2023-07-11 | 武汉大学 | Fire spread prediction method and system based on multiple data sources |
| CN116824462B (en) * | 2023-08-30 | 2023-11-07 | 贵州省林业科学研究院 | Forest intelligent fireproof method based on video satellite |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014093063A (en) * | 2012-11-07 | 2014-05-19 | Pasco Corp | Prediction device of forest fire and prediction program of forest fire |
| CN106780732A (en) * | 2016-12-22 | 2017-05-31 | 山东神戎电子股份有限公司 | A kind of bottom class's forest fire appealing Dynamic Simulation Method based on three dimensional topographic data |
| CN106991681A (en) * | 2017-04-11 | 2017-07-28 | 福州大学 | A kind of fire boundary vector information extract real-time and method for visualizing and system |
| CN111932813A (en) * | 2020-08-14 | 2020-11-13 | 南京邮电大学 | Unmanned aerial vehicle forest fire reconnaissance system based on edge calculation and working method |
-
2021
- 2021-09-14 CN CN202111072420.7A patent/CN113792427B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014093063A (en) * | 2012-11-07 | 2014-05-19 | Pasco Corp | Prediction device of forest fire and prediction program of forest fire |
| CN106780732A (en) * | 2016-12-22 | 2017-05-31 | 山东神戎电子股份有限公司 | A kind of bottom class's forest fire appealing Dynamic Simulation Method based on three dimensional topographic data |
| CN106991681A (en) * | 2017-04-11 | 2017-07-28 | 福州大学 | A kind of fire boundary vector information extract real-time and method for visualizing and system |
| CN111932813A (en) * | 2020-08-14 | 2020-11-13 | 南京邮电大学 | Unmanned aerial vehicle forest fire reconnaissance system based on edge calculation and working method |
Non-Patent Citations (1)
| Title |
|---|
| 一种耦合元胞自动机的改进林火蔓延仿真算法;惠珊;芮小平;李尧;;武汉大学学报(信息科学版)(10);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113792427A (en) | 2021-12-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113792427B (en) | Forest fire spread prediction simulation method under existing boundary conditions | |
| CN107507275B (en) | Method and device for determining trip influence range of power transmission line based on big data | |
| CN112785526B (en) | Three-dimensional point cloud restoration method for graphic processing | |
| CN112581443A (en) | Light-weight identification method for surface damage of wind driven generator blade | |
| JP7153330B2 (en) | Sediment disaster prediction device, computer program, sediment disaster prediction method and map information | |
| CN111696196A (en) | Three-dimensional face model reconstruction method and device | |
| CN106204597A (en) | A kind of based on from the VS dividing method walking the Weakly supervised study of formula | |
| Dimitrios | Urban growth prediction modelling using fractals and theory of chaos | |
| CN115601520A (en) | Fire simulation method and device based on two-dimensional prediction and multi-scale grid | |
| CN115457001A (en) | Photovoltaic panel foreign matter detection method, system, device and medium based on VGG network | |
| CN116663960A (en) | Ecological network construction method based on accessibility and availability of habitat under climate change | |
| CN116958188A (en) | Smoke field multi-parameter prediction method based on physical information constraint neural network | |
| Ni et al. | Enhancing rooftop solar energy potential evaluation in high-density cities: A Deep Learning and GIS based approach | |
| CN108268977B (en) | Method and system for reducing influence of abnormal extra-high value of pollutants in soil remediation | |
| Mokhtar et al. | Pedestrian wind factor estimation in complex urban environments | |
| Scott et al. | Emerging concepts in wildfire risk assessment and management | |
| CN111260714B (en) | Flood disaster recovery assessment method, device and equipment and computer storage medium | |
| Albeaik et al. | Virtual cities: 3d urban modeling from low resolution lidar data | |
| CN109978978B (en) | SketchUp model lightweight processing method and system | |
| CN116129039A (en) | Three-dimensional point cloud generation method and device for power transmission line and storage medium | |
| CN114399728B (en) | Foggy scene crowd counting method | |
| Tempelis et al. | Erosion modelling on reconstructed rough surfaces of wind turbine blades | |
| Bianchini et al. | Improved prediction methods for wildfires using high performance computing: A comparison | |
| CN113139272A (en) | Forest fire spreading prediction method, device, equipment and storage medium | |
| CN113971348A (en) | Source end power short-term prediction method based on comprehensive energy system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |