CN102867217A - Projection pursuit-based risk evaluation method for meteorological disasters of facility agriculture - Google Patents
Projection pursuit-based risk evaluation method for meteorological disasters of facility agriculture Download PDFInfo
- Publication number
- CN102867217A CN102867217A CN2012103106899A CN201210310689A CN102867217A CN 102867217 A CN102867217 A CN 102867217A CN 2012103106899 A CN2012103106899 A CN 2012103106899A CN 201210310689 A CN201210310689 A CN 201210310689A CN 102867217 A CN102867217 A CN 102867217A
- Authority
- CN
- China
- Prior art keywords
- projection
- meteorological
- evaluation
- risk
- 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.)
- Pending
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a projection pursuit-based risk evaluation method for meteorological disasters of facility agriculture, belonging to the technical field of the evaluation of the meteorological disasters. The projection pursuit-based risk evaluation method comprises the following steps of: fitting and acquiring historical meteorological data by means of a neural network; counting the annual occurrence frequency of the meteorological disasters in various grade, calculating to acquire disaster comprehensive indexes of evaluation indexes, and establishing disaster comprehensive index grading standards of the evaluation indexes; constructing projection functions of the historical meteorological data, and acquiring the optimal projection vector by an accelerating genetic algorithm; and building a risk evaluation model according to projection values of the meteorological data on the optimal projection vector and the disaster comprehensive index grades of the evaluation indexes. The projection pursuit method is applied to the field of the risk evaluation of the meteorological disasters of the facility agriculture, the projection vectors are optimized by combining with the accelerating genetic algorithm, and the actual meteorological data are taken as input data of the evaluation model, the accuracy of risk evaluation results is high, and new thoughts and methods are provided for the research of the risk evaluation of the meteorological disasters.
Description
Technical field
The invention discloses the industrialized agriculture meteorological disaster risk evaluating method based on projection pursuit, belong to the technical field of meteorological disaster evaluation.
Background technology
Since the nineties in 20th century, China take Greenhouse in North as main industrialized agriculture take overtimely make, vegetables in improper season cultivate as main fast development, the industrialized agriculture area was from 10.8 ten thousand mu of more than 4,500 ten thousand mus of developing into 2010 in 1981, increased more than 440 times between 29 years, the simultaneously development of industrialized agriculture also proposes to have supplied the most basic solid guarantee for the supply of city vegetables in improper season.The ability that the northern China heliogreenhouse is withstood natural calamities, the economic benefit that unit facility area obtains is more far apart.Tracing it to its cause mainly is that China's facility level is lower, and the production of protected crop is higher for the degree of dependence of weather conditions, is subjected to the impact of diastrous weather larger.Therefore, necessary from the relation of multi-angle research facilities agricultural with meteorological condition, systematically China's industrialized agriculture risk is estimated.The meteorological disaster risk assessment is quantitative test and the assessment to the regular period risk area suffers the possibility of varying strength meteorological disaster and the consequence that may cause is carried out, the meteorological disaster risk management is by risk identification, risk estimation, risk assessment, and various risk management technology of optimal combination on this basis, the meteorological disaster risk is implemented effectively to control and to deal carefully with loss consequence due to the risk, to reaching the target that obtains maximum safety guarantee with minimum cost.Comprise construction Hazard Risk Assessment model, set up the meteorological disaster Risk Evaluating System, draw meteorological disaster risk thematic map etc.The disaster risk assessment is the key link in the management of hazard risk, is to carry out the movable scientific basis such as effective disaster prevention, disaster preparation, emergency management and rescue, and also be the important foundation of emergency capability construction and assessment.For the increasingly serious disaster situation that the whole world faces, the research of disaster risk assessment has important urgency and realistic meaning.Evaluation and Prediction research about the industrialized agriculture meteorological disaster is to be in the research starting stage, and Chinese scholars has been carried out some researchs.
The most area of external industrialized agriculture developed country is little, climate type is single, therefore in the risk assessment study, often side is in model investigations such as social risk, economic risk, environmental risk, potential risk and integrated risks, such as Piers the AWR model has been proposed, Carter has proposed the SRI model and HSE has proposed COMAH model etc., and uses these models and carried out venture analysis, but research lays particular emphasis on the economic field more.Existing scholar is used for drainage pipeline networks flooding risk evaluation method with projection pursuit model (PPE).The method does not solve the dimension global optimizing problem of projection vector, tries to achieve best projection direction a
*Has the not high problem of precision.
Genetic algorithm mainly comprises selection (selection), intersects (cros sover) and variation operation stepss such as (mutation).Step 1: generate at random N at the value constant interval of each decision variable and organize equally distributed stochastic variable; Step 2: the calculating target function value, arrange from big to small; Step 3: calculate the evaluation function (with eval (V) expression) based on order; Step 4: select to operate the new population of generation; Step 5: the new population that step 4 is produced carries out interlace operation; Step 6: the new population that step 5 is produced carries out mutation operation; Step 7: evolution iteration; Step 8: the variable change interval of the excellent individual that the iteration of evolving for the first time, for the second time produces is interval as the new initial change of variable, algorithm enters step 1, rerun SGA, form Accelerating running, until the Optimality Criteria functional value of optimum individual reaches predetermined acceleration times less than a certain setting value or algorithm operation, finish whole algorithm operation.At this moment, optimized individual in the current colony is appointed as the result of RAGA.Above-mentioned 8 steps consist of Accelerating Genetic Algorithm based on Real Coding (RAGA).
Also rare to the research of concrete a certain agricultural disaster venture analysis about utilizing based on the industrialized agriculture meteorological disaster risk evaluating method that accelerates the genetic algorithm projection pursuit at present.The meteorological disaster risk evaluating method that has had is research object mainly with field crop, seldom has take facility as the meteorological disaster risk evaluating method as research object.Conventional Hazard Assessment method mainly contains the methods such as expert consulting method, group decision-making method, risk assessment matrix, but these methods all have very strong subjective initiative; In existing greenhouse climate resource analysis and the zoning work, subregion index and method are take classic method and experience as main.As seen, in the existing meteorological disaster risk evaluating method, man's activity is stronger, lacks to a certain extent theoretical foundation.
Summary of the invention
Technical matters to be solved by this invention is the deficiency for the above-mentioned background technology, and the industrialized agriculture meteorological disaster risk evaluating method based on projection pursuit is provided.
The present invention adopts following technical scheme for achieving the above object:
Industrialized agriculture meteorological disaster risk evaluating method based on projection pursuit comprises the steps:
Step 1, data preparation: the historical weather data of collecting is carried out test of homogeneity, and carry out interpolation to lacking the survey data, form complete data acquisition, described complete data acquisition is carried out match;
Step 3 makes up PPE assessment model: make up projection function, calculate the projection value of each meteorological disaster grade evaluation index on projection vector, set up correlation model in the disaster aggregative index grade according to projection value and evaluation index;
Step 4, evaluation result is analyzed: with the weather data in zone to be evaluated input data as PPE assessment model, the Regional Assessment of Risk level data to be evaluated that generates according to PPE assessment model again, combining geographic information,, zoning color spot figure generated by the risk assessment grade.
In the described industrialized agriculture meteorological disaster risk evaluating method based on projection pursuit, step 1 adopts the BP neural network that described complete data acquisition match is drawn the indoor day lowest temperature.
In the step 3 of described industrialized agriculture meteorological disaster risk evaluating method based on projection pursuit: obtain the best projection vector according to accelerating genetic algorithm local optimum projection vector.
The present invention adopts technique scheme, has following beneficial effect:
1. projection Pursuit Method is applied to industrialized agriculture meteorological disaster risk assessment field, simultaneously in conjunction with accelerating the genetic algorithm optimization projection vector, with the input data of Practical Meteorological Requirements data as evaluation model of the present invention, precision is high as a result to obtain risk assessment, for the meteorological disaster Study on Risk Assessment provides new thinking and method
2. combine temperature, precipitation, sunshine, wind speed etc. to the larger factor of industrialized agriculture impact, made up the meteorological disaster risk evaluation model of industrialized agriculture, change the evaluation that in the past relied on monofactor, considered multiple Effects of Factors.
Description of drawings
Fig. 1 is the risk assessment schematic flow sheet.
Fig. 2 to Fig. 6 is the risk rating scheme in January to May among the embodiment.
Fig. 7 to Figure 10 is the risk rating scheme in September to Dec among the embodiment.
Figure 11 is for accelerating the procedure chart of genetic algorithm local optimum projection vector.
Embodiment
Be elaborated below in conjunction with the technical scheme of accompanying drawing to invention:
Meteorological disaster risk area with Greenhouse in North divides example into, based on the industrialized agriculture meteorological disaster risk evaluating method that accelerates the genetic algorithm projection pursuit as shown in Figure 1, specifically comprises the steps:
Step 1, at first collect this area's meteorological data, the weather data of utilizing 243 station 1980-2009 of 16 provinces, cities and autonomous regions of the northern area of China is collected at this place altogether, the weather data of collecting comprises: the weather data of the Basic Evaluation achievement datas such as temperature, sunshine, precipitation, wind speed, specific booth bearing capacity data.To the test of homogeneity that carries out of weather data, the weather data that lacks survey is carried out interpolation obtain complete data acquisition; Collect the hazard-affected ability to precipitation, strong wind etc. that common are representational greenhouse in the evaluation region, obtain the index of disasters at different levels; According to the correlationship of meteorological element in the greenhouse and extraneous meteorological condition, based on the analogy model of the indoor extremely low temperature of BP neural network, the mode input parameter is the highest temperature, the lowest temperature, radiation, the wind speed of proxima luce (prox. luc); Consult pertinent literature, low temperature, the widow's photograph of finding out common protected crop tomato, cucumber cause the calamity index; Utilize Matlab that the 1980-2009 data of making weather observations are carried out programmed process, adopt the complete data acquisition of BP neural network match to obtain day lowest temperature greenhouse in, lowest temperature is passed through 0.01 significance test day in the greenhouse that match obtains in.
The BP neural network selects the BP network of single hidden layer to carry out the simulation of the lowest temperature in the greenhouse in spring and winter.Wherein the input layer number is 4, and hidden layer neuron is 9, and output neuron is 1.Total solar radiation (Rout), the highest temperature (Tomax), the lowest temperature (Tomin) and wind speed (Wout) sample that the ground floor input is outdoor, the second layer is hidden layer, the 3rd layer of lowest temperature (Timin) data that output is outdoor, the hidden layer transport function adopts S type tan tansig, and the output layer transport function adopts S type logarithmic function logsig.The selected relevant parameter value of model is: initial learn speed η=0.1, inertia factor-alpha=0.9, maximum iteration time=10000 time, target error=0.0001.
RI=α×DF
1+β×DF
2+γ×DF
3+θ×DF
4 （1）
Wherein: α, β, γ, θ are coefficient, get respectively 0.2,0.3,0.3,0.2, DF
1, DF
2, DF
3, DF
4Be respectively each grade disaster generation frequency.
Clustering methodology is divided into four classes with aggregative index (RI), draw the index range of corresponding four grades, be I level: 0-0.25, II level: 0.26-0.5, III level: 0.51-0.75, IV level: 0.76-1.0 can determine the accordingly grade scale of each evaluation index disaster aggregative index, make up meteorological disaster grade evaluation achievement data storehouse, form assessment indicator system.
Step 3, structure is based on the PPE assessment model that accelerates genetic algorithm: according to the disaster aggregative index grade scale of evaluation index, utilize projection pursuit model to calculate the projection value of each meteorological disaster grade evaluation index, set up industrialized agriculture meteorological disaster risk evaluation model based on projection pursuit method according to projection value and disaster grade point;
Each grade disaster aggregative index of each meteorological disaster grade evaluation index as an evaluation unit, is made up index sample set { x
*(i, j) | i=1 ~ n, j=1 ~ p}, n are the disaster grade, and p is the number of evaluation index, and n, p are the natural number more than or equal to 1, x
*J evaluation index of (i, j) i grade of expression, implementation is as follows:
(1) normalized index sample set:
For x
*The disaster risk class of the larger expression of (i, j) value utilizes the following expression normalized when higher:
x(i，j)=(x
*(i，j)-x
min(j))/(x
max(j)-x
min(j)) （2）；
For x
*The disaster risk class of the less expression of (i, j) value utilizes the following expression normalized when lower:
x(i，j)=(x
max(j)-x
*(i，j))/(x
max(j)-x
min(j)) （3）；
Wherein, x
Max(j), x
Min(j) be respectively maximal value and the minimum value of j index, x (i, j) is the evaluation index after the normalization;
(2) structure projection target function:
Step a, the p dimension data x (i, j) | j=1,2 ..., p} comprehensively becomes with a={a (1), a (2) ..., a (p) } be a projection value z (i) of projecting direction:
I=1,2 ..., n;
Step b, according to z (i) | the one dimension scatter diagram of i=1～n} is classified, and during comprehensive projection desired value, require the distribution feature of projection value z (i) should be: partial projection point is intensive as far as possible, preferably be condensed into several some groups, and scatter as far as possible between the subpoint group on the whole.Therefore, the projection target function can be expressed as:
Q(a)＝Sz*Dz （4）
Wherein: Sz is the standard deviation of projection value z (i); Dz then is projection value z (i) local density, that is:
Wherein, E(z) be sequence z (i) | i=1,2 ..., the mean value of n}; Distance between r (i, j) expression sample, r (i, j)=| z (i)-z (j) |; U[R-r (i, j)] be unit-step function;
R is the windows radius of local density, it choose should make be included in the subpoint in the window mean number very little, avoid the running mean deviation too large, it is increased too high along with the increase of n, R can determine according to test, its span is rmax+0.5P≤R≤2P, R gets 0.1Sz in this research, the distance between r (i, j) expression sample, r (i, j)=| z (i)-z (j) |; U (t) is a unit-step function, and when t＜0, functional value is 0, and when t 〉=0, its functional value is 1, and the value of R is got 0.1Sz here;
(3) optimize the projection target function:
Utilization solves its higher-dimension global optimizing problem based on the acceleration genetic algorithm (RAGA) of real coding, tries to achieve best projection direction a
*, based on acceleration genetic algorithm (RAGA) the local optimum schematic diagram of real coding as shown in figure 11.
Maximization objective function: MaxQ (a)=Sz*Dz (7)
Constraint condition:
According to the best projection direction that draws, calculate projection value corresponding to each opinion rating: selected parent initial population scale is n=400, crossover probability p
c=0.8, the variation Probability p
m=0.8, the excellent individual number is chosen to be 16, α=0.05, and acceleration times is 8, draws the best projection direction and is respectively a
*=(0.859,0.469,0.137,0.1527) is with a
*Bringing into behind the phase formula is projection value z
*(j)=(0,0.69,1.1878,1.5177).
The grade of the disaster aggregative index of projection value and evaluation index is set up correlation model (being the industrialized agriculture meteorological disaster risk evaluation model based on projection pursuit):
Step 4, extrapolate risk class according to the evaluation model that step 3 is set up, generate each Regional Assessment of Risk level data, according to Geographic Information System (GIS), zone industrialized agriculture meteorological disaster risk assessment level data, and generated the risk rating scheme shown in Figure 10 extremely such as Fig. 2 with anti-distance weighting method of interpolation among the ArcGIS.Wherein Fig. 2 to Fig. 6 is the risk rating scheme in January to May, and Fig. 7 to Figure 10 is the risk rating scheme in September to Dec.
In sum, the present invention applies to industrialized agriculture meteorological disaster risk assessment field with projection Pursuit Method, simultaneously in conjunction with accelerating the genetic algorithm optimization projection vector, with the input data of Practical Meteorological Requirements data as evaluation model of the present invention, precision is high as a result to obtain risk assessment, for the meteorological disaster Study on Risk Assessment provides new thinking and method.Other method, the present invention combines temperature, precipitation, sunshine, wind speed etc. to the larger factor of industrialized agriculture impact, make up the meteorological disaster risk evaluation model of industrialized agriculture, changed the evaluation that in the past relied on monofactor, considered multiple Effects of Factors.Above-described embodiment only is an application example of the present invention, and the present invention is not limited only to the risk assessment of these four kinds of meteorological disasters of Greenhouse in North, and every embodiment that meets invention aim of the present invention is all within protection scope of the present invention.
Claims (3)
1. based on the industrialized agriculture meteorological disaster risk evaluating method of projection pursuit, it is characterized in that comprising the steps:
Step 1, data preparation: the historical weather data of collecting is carried out test of homogeneity, and carry out interpolation to lacking the survey data, form complete data acquisition, described complete data acquisition is carried out match;
Step 2, set up industrialized agriculture meteorological disaster grade scale: the data that match obtains in the treatment step 1, the frequency occurs in the year of adding up each grade meteorological disaster, calculates the aggregative index of every kind of meteorological disaster, utilizes clustering methodology to draw the disaster aggregative index grade scale of evaluation index;
Step 3 makes up PPE assessment model: make up projection function, calculate the projection value of each meteorological disaster grade evaluation index on projection vector, set up correlation model in the disaster aggregative index grade according to projection value and evaluation index;
Step 4, evaluation result is analyzed: with the weather data in zone to be evaluated input data as PPE assessment model, the Regional Assessment of Risk level data to be evaluated that generates according to PPE assessment model again, combining geographic information generates zoning color spot figure by the risk assessment grade.
2. the industrialized agriculture meteorological disaster risk evaluating method based on projection pursuit according to claim 1 is characterized in that described step 1 adopts the BP neural network that described complete data acquisition match is drawn the indoor day lowest temperature.
3. the industrialized agriculture meteorological disaster risk evaluating method based on projection pursuit according to claim 1 is characterized in that in the described step 3: obtain the best projection vector according to accelerating genetic algorithm local optimum projection vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012103106899A CN102867217A (en) | 2012-08-28 | 2012-08-28 | Projection pursuit-based risk evaluation method for meteorological disasters of facility agriculture |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012103106899A CN102867217A (en) | 2012-08-28 | 2012-08-28 | Projection pursuit-based risk evaluation method for meteorological disasters of facility agriculture |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102867217A true CN102867217A (en) | 2013-01-09 |
Family
ID=47446080
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012103106899A Pending CN102867217A (en) | 2012-08-28 | 2012-08-28 | Projection pursuit-based risk evaluation method for meteorological disasters of facility agriculture |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102867217A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104966130A (en) * | 2015-06-10 | 2015-10-07 | 中国西安卫星测控中心 | Data-driven spacecraft state prediction method |
| CN105303194A (en) * | 2015-10-12 | 2016-02-03 | 国家电网公司 | Power grid indicator system establishing method, device and computing apparatus |
| CN105303301A (en) * | 2015-10-14 | 2016-02-03 | 成都信息工程大学 | Pre-severe precipitation disaster risk prediction method |
| CN105469192A (en) * | 2015-11-17 | 2016-04-06 | 国家电网公司 | Power emergency rescue task allocation method |
| CN106845080A (en) * | 2016-12-23 | 2017-06-13 | 广西师范学院 | Scene Tourist meteorological disaster intelligent Forecasting based on difference amendment |
| CN108460691A (en) * | 2018-01-31 | 2018-08-28 | 杞人气象科技服务（北京）有限公司 | A kind of heliogreenhouse is even cloudy few according to Meteorological Index insurance method |
| CN109006278A (en) * | 2018-06-15 | 2018-12-18 | 云南省气候中心 | Analysis of Rice Chilling Injury risk evaluating method |
| CN109145454A (en) * | 2018-08-24 | 2019-01-04 | 中国科学院、水利部成都山地灾害与环境研究所 | The method that triple exponential models portray snow disaster in pastoral area restoring force space-time characterisation |
| CN109447347A (en) * | 2018-10-29 | 2019-03-08 | 水利部交通运输部国家能源局南京水利科学研究院 | A kind of water head site Optimizing Site Selection method evaded based on environmental risk |
| CN110059915A (en) * | 2019-03-01 | 2019-07-26 | 广东奥博信息产业股份有限公司 | A kind of winter wheat meteorological disaster integrated risk dynamic evaluation method and device |
| CN110766940A (en) * | 2019-09-24 | 2020-02-07 | 重庆交通大学 | Method for evaluating running condition of road signalized intersection |
| CN111429028A (en) * | 2020-04-16 | 2020-07-17 | 贵州电网有限责任公司 | Power transmission line icing disaster risk assessment method suitable for mountainous terrain |
| CN113177737A (en) * | 2021-05-26 | 2021-07-27 | 南京恩瑞特实业有限公司 | Urban rainstorm disaster risk assessment method and system based on GA (genetic algorithm) optimization BP (back propagation) neural network |
| CN114037283A (en) * | 2021-11-10 | 2022-02-11 | 内蒙古农业大学 | Fire dynamic risk assessment method for commercial complex |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| SU651254A1 (en) * | 1976-04-02 | 1979-03-05 | Институт Пустынь Ан Туркменской Сср | Anemorhumbograph |
-
2012
- 2012-08-28 CN CN2012103106899A patent/CN102867217A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| SU651254A1 (en) * | 1976-04-02 | 1979-03-05 | Институт Пустынь Ан Туркменской Сср | Anemorhumbograph |
Non-Patent Citations (2)
| Title |
|---|
| 张坤等: "基于改进投影寻踪法的农业气象灾情综合评价", 《中国农业气象》, vol. 30, no. 1, 31 March 2009 (2009-03-31), pages 114 - 116 * |
| 黄勇辉等: "基于加速遗传算法的投影寻踪聚类评价模型研究与应用", 《系统工程》, vol. 27, no. 11, 30 November 2009 (2009-11-30), pages 108 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104966130A (en) * | 2015-06-10 | 2015-10-07 | 中国西安卫星测控中心 | Data-driven spacecraft state prediction method |
| CN105303194A (en) * | 2015-10-12 | 2016-02-03 | 国家电网公司 | Power grid indicator system establishing method, device and computing apparatus |
| CN105303194B (en) * | 2015-10-12 | 2018-09-14 | 国家电网公司 | A kind of power grid index system method for building up, device and computing device |
| CN105303301A (en) * | 2015-10-14 | 2016-02-03 | 成都信息工程大学 | Pre-severe precipitation disaster risk prediction method |
| CN105469192A (en) * | 2015-11-17 | 2016-04-06 | 国家电网公司 | Power emergency rescue task allocation method |
| CN106845080B (en) * | 2016-12-23 | 2019-06-28 | 广西师范学院 | Based on the modified Scene Tourist meteorological disaster intelligent Forecasting of difference |
| CN106845080A (en) * | 2016-12-23 | 2017-06-13 | 广西师范学院 | Scene Tourist meteorological disaster intelligent Forecasting based on difference amendment |
| CN108460691A (en) * | 2018-01-31 | 2018-08-28 | 杞人气象科技服务（北京）有限公司 | A kind of heliogreenhouse is even cloudy few according to Meteorological Index insurance method |
| CN109006278A (en) * | 2018-06-15 | 2018-12-18 | 云南省气候中心 | Analysis of Rice Chilling Injury risk evaluating method |
| CN109145454A (en) * | 2018-08-24 | 2019-01-04 | 中国科学院、水利部成都山地灾害与环境研究所 | The method that triple exponential models portray snow disaster in pastoral area restoring force space-time characterisation |
| CN109145454B (en) * | 2018-08-24 | 2023-03-28 | 中国科学院、水利部成都山地灾害与环境研究所 | Method for depicting space-time characteristics of snow disaster resilience of pastoral area by triple exponential model |
| CN109447347A (en) * | 2018-10-29 | 2019-03-08 | 水利部交通运输部国家能源局南京水利科学研究院 | A kind of water head site Optimizing Site Selection method evaded based on environmental risk |
| CN110059915A (en) * | 2019-03-01 | 2019-07-26 | 广东奥博信息产业股份有限公司 | A kind of winter wheat meteorological disaster integrated risk dynamic evaluation method and device |
| CN110766940A (en) * | 2019-09-24 | 2020-02-07 | 重庆交通大学 | Method for evaluating running condition of road signalized intersection |
| CN111429028A (en) * | 2020-04-16 | 2020-07-17 | 贵州电网有限责任公司 | Power transmission line icing disaster risk assessment method suitable for mountainous terrain |
| CN113177737A (en) * | 2021-05-26 | 2021-07-27 | 南京恩瑞特实业有限公司 | Urban rainstorm disaster risk assessment method and system based on GA (genetic algorithm) optimization BP (back propagation) neural network |
| CN114037283A (en) * | 2021-11-10 | 2022-02-11 | 内蒙古农业大学 | Fire dynamic risk assessment method for commercial complex |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102867217A (en) | Projection pursuit-based risk evaluation method for meteorological disasters of facility agriculture | |
| Dong et al. | Hourly energy consumption prediction of an office building based on ensemble learning and energy consumption pattern classification | |
| CN110570651B (en) | Road network traffic situation prediction method and system based on deep learning | |
| CN105426970B (en) | A kind of meteorological intimidation estimating method based on discrete dynamic Bayesian network | |
| CN103033856B (en) | Rainfall frequency estimation method based on hydrometeorology consistency geographical analysis | |
| CN109214592A (en) | A kind of Air Quality Forecast method of the deep learning of multi-model fusion | |
| CN105184423B (en) | A kind of wind power plant cluster wind speed forecasting method | |
| CN110363327A (en) | Short based on ConvLSTM and 3D-CNN faces Prediction of Precipitation method | |
| CN108009674A (en) | Air PM2.5 concentration prediction methods based on CNN and LSTM fused neural networks | |
| Tabesh et al. | Fuzzy and neuro-fuzzy models for short-term water demand forecasting in Tehran | |
| CN106897826A (en) | A kind of street accidents risks appraisal procedure and system | |
| CN102722759A (en) | Method for predicting power supply reliability of power grid based on BP neural network | |
| CN112966871B (en) | Traffic jam prediction method and system based on convolution long-short-term memory neural network | |
| CN109492756B (en) | Multi-element wire galloping early warning method based on deep learning and related device | |
| CN107292534A (en) | The yardstick competition evaluation method and device of urban power distribution network long term dynamics investment | |
| CN105678397A (en) | Short-term photovoltaic power prediction method based on improved EMD algorithm and Elman algorithm | |
| CN112182951B (en) | Land utilization planning method considering multiple uncertainties | |
| CN109933901B (en) | MCR city expansion simulation method for optimizing service value of ecosystem | |
| CN105389742A (en) | Remote sensing identification method and system for water environment sensitive area and littoral zone construction method | |
| CN113537569B (en) | Short-term bus passenger flow prediction method and system based on weight stacking decision tree | |
| CN104318717A (en) | Rainstorm debris flow early warning method under shortage conditions of historical data | |
| CN105046453A (en) | Construction engineering project cluster establishment method introducing cloud model for evaluation and selection | |
| CN117332909B (en) | Multi-scale urban waterlogging road traffic exposure prediction method based on intelligent agent | |
| CN106845080A (en) | Scene Tourist meteorological disaster intelligent Forecasting based on difference amendment | |
| CN111144637A (en) | Regional power grid geological disaster forecasting model construction method based on machine learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130109 |