CN101763600A - Land use supply and demand prediction method based on model cluster - Google Patents
Land use supply and demand prediction method based on model cluster Download PDFInfo
- Publication number
- CN101763600A CN101763600A CN201010028960A CN201010028960A CN101763600A CN 101763600 A CN101763600 A CN 101763600A CN 201010028960 A CN201010028960 A CN 201010028960A CN 201010028960 A CN201010028960 A CN 201010028960A CN 101763600 A CN101763600 A CN 101763600A
- Authority
- CN
- China
- Prior art keywords
- model
- soil
- demand
- prediction
- supply
- 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 provides a land use supply and demand prediction method based on model cluster, aiming at the problem that the traditional land use supply and demand prediction only utilizes a single model to perform prediction of each evaluation index, thus hardly satisfying the demand of regional land use optimization decision on the comprehensive prediction of the land use system. The method of the invention comprehensively uses the applicability of different models for the prediction of different indexes, realizes the automatic selection of proper models according to the property and characteristic of index prediction, selects multiple models to predict the same index, comprehensively obtains the prediction result and realizes the integration of forecasting model so as to satisfy the prediction demand of the land use system. The method establishes proper model cluster for the prediction of signal index, realizes multi-model prediction of signal index and mutual verification and coordination of prediction result thereof; the local land use supply and demand are integrated to predict various indexes and model cluster, the method establishes prediction model library, realizes automatic selection of proper models and multi-index prediction flow process and increases the accuracy of prediction result and the prediction efficiency.
Description
Technical field
The present invention relates to a kind of regional soil and utilize the medium-and long-term forecasting method, refer to especially to be applied to utilize supply and demand prediction method in the soil based on model cluster of regional soil utilization, belong to the land use planning field.
Background technology
It is the basis of land use planning that the soil utilizes the supply and demand prediction, predictive content comprises: population, the grain per unit area yield that socio-economic development level and be is ploughed and the construction land demand forecast is carried out, multiple crop index, the grain consumption structure, construction land demand per capita, all construction land predictions of ground, its forecast model has based on the mathematical statistics regression analysis model, the intelligence computation model, model methods such as Expert System Model are as exponential smoothing, the simple regression analysis method, the multiple regression analysis method, the adaptive filtering method, expert prediction method, the Markov analysis method, neural network prediction, model methods such as grey system forecasting.Early stage soil utilizes forecasting research to be based upon on the decisive basis of demand, as the demand forecast of ploughing is by the demand of population to crops such as grains, construction land demand and economy development requirement determine the scale of land development and utilize mode, control arable land total amount.Along with the aggravation of minimizing of ploughing and people ground contradiction, according to the requirement of cultivated land protection and land resource sustainable utilization, development and use mode in arable land changes the soil gradually into supplies with restriction and guiding demand, guarantees quantity of cultivated land.Based on the general employing of this thought is Forecasting Methodologies such as linear regression model (LRM), exponential smoothing and fuzzy prediction method, the above two just carry out the processing of pure mathematics with regard to the seasonal effect in time series data, and do not consider that natural cause and social factor to the aftereffect of arable land total amount influence, therefore have certain limitation; The latter integrates the influence factor in numerous arable lands, by each factor the weighing factor of arable land total amount is carried out fuzzy prediction, the limitation of this method is that the factor that influences the arable land is constantly changing, the weight size also is changing, therefore the uncomfortable cooperation long-term forecasting of this method also can not show the variation tendency of the total amount of ploughing.Prediction simultaneously itself is higher to the raw data accuracy requirement, so this is selected for use correct, suitable forecast model to increase certain degree of difficulty.The Markov chain Forecasting Methodology has the better prediction effect to solving the prediction of without aftereffect.Gray system theory is in the conceptive disposal route that changes stochastic problems, make it can be used for the not clear or infull gray system of information of information, its main points are not to be the randomness in the system is regarded as a random signal but regard a grey number as, and random quantity is treated as the grey colo(u)r specification that changes on certain interval, the grey process is used as the stochastic process that between a tentering interval, a fixed time interval, changes.Grey system forecasting is applicable to the forecasting problem that the time is short, data information is few, fluctuation is little.Yet because the soil utilizes the complex nature of the problem, single forecast model method often is difficult to obtain the better prediction result, explore the multiple forecast model method advantage that how to fully utilize, carry out the soil and utilize the supply and demand prediction, obtaining more scientific and rational predicting the outcome is that current soil improves the technical need that the soil utilizes the optimum decision scientific level.
Summary of the invention
Utilize the supply and demand prediction only to utilize single model method to carry out the single index prediction at traditional soil, being difficult to satisfy regional soil utilizes optimum decision the soil to be utilized the demand of system synthesis prediction, the present invention proposes a kind of soil based on model cluster and utilizes supply and demand prediction method, fully utilize the applicability of different models to dissimilar index predictions, one side realizes the automatic selection of appropriate model according to prediction index character and characteristics, choosing multi-model simultaneously predicts same index, and comprehensively obtain and predict the outcome, realize the integrated of forecast model, utilize the system prediction demand to solve the soil.
Should utilize supply and demand prediction method may further comprise the steps based on the soil of model cluster:
(1) according to regional land type, application demand, set up regional soil and utilize supply and demand prediction index system, import achievement data by the index system of setting up, whether unusual according to the rationality judgment data, and the suppressing exception data;
(2) utilize the present status of land utilization analytical model bunch regional present status of land utilization to be analyzed according to achievement data, carry out regional potential of land resource evaluation according to analysis result again, As-Is analysis comprise regional present status of land utilization structure, utilize effect, space layout and existing problems;
(3) make up regional soil and utilize supply and demand predicting candidate model cluster storehouse, the model cluster storehouse comprises base values forecast model bunch, medium-term and long-term land used forecast model bunch, annual land used forecast model bunch at least;
(4) utilize from regional soil according to the regional present status of land utilization analysis result of step (2) and regional potential of land resource evaluation result and select base values forecast model bunch the supply and demand predicting candidate model cluster storehouse, and utilize selected base values forecast model bunch to carry out the base values integrated forecasting of regional soil, base values comprises population, GDP, multiple crop index, grain consumption structure and crop yield at least;
(5) utilize from regional soil the supply and demand predicting candidate model cluster storehouse according to the base values predicted data of step (4) and select medium-term and long-term land used forecast model bunch, annual land used forecast model bunch, utilize selected medium-term and long-term land used forecast model bunch, annual land used forecast model bunch respectively medium-term and long-term and regional soil year of soil, estimation range land used type, quantitative structure change and integrated forecasting result;
(6) the integrated forecasting result according to step (5) selects analysis of supply-demand balance model, and utilize selected analysis of supply-demand balance model to carry out the utilization of regional soil and supply with potentiality and demand equilibrium analysis, and according to analysis of supply-demand balance result to the utilization of regional soil predict the outcome adjust definite.
The described present status of land utilization analytical model of step (2) bunch comprises that at least land use structure analytical model, soil utilize landscape pattern analysis model and/or soil to utilize the Dynamic Variation Analysis model.
Described land use structure analytical model comprises ground class formation analytical model, region Structural Analysis Model, ecologic structure analytical model.
Described soil utilizes the landscape pattern analysis model to comprise shape index, patch density, degree of separation index, area ratio, diversity index, dominance index, diversity indices, centralization degree and/or composite type.
Described soil utilizes the free sequential analysis model of Dynamic Variation Analysis model, change-detection model and/or dynamic simulation model.
Described base values forecast model bunch, medium-term and long-term land used forecast model bunch, year, the land used forecast model bunch comprised the Song Jian Population Forecast Model at least, the Malthus demographic model, logistic gram model, ecological model, the time series analysis model, single factor regression model, multifactor regression model, Paul H. Douglas production function, the quota index model, the grey system forecasting model, Markov prediction, the Grey--Markov model, system dynamics model, neural network model, department's land used forecast model, difference-smoothing prediction model, fuzzy prediction model and/or based on the entropy forecast model.
Described analysis of supply-demand balance model cluster comprises goal programming, multiple objective programming, SD planning, GREY SITUATION DECISION, multi-criteria decision methods, dynamic programming model at least.
Described medium-term and long-term land used forecast model bunch comprises regression analysis model, Markov chain forecast model and/or grey system forecasting model at least.
Described annual land used forecast model bunch comprises trend extrapolation model and canonical correlation analysis model at least.
The advantage applies of this method exists:
(1) set up regional soil and utilized supply and demand prediction index system, provided the foundation for regional soil utilizes the supply and demand prediction;
(2) set up suitable model cluster for single index prediction, realized the multi-model prediction of single index and mutual checking and the coordination that predicts the outcome thereof;
(3) integrated regional soil utilizes supply and demand to predict each index prediction model cluster, has set up the forecast model storehouse, has realized choosing automatically and the operation of many index predictions procedure of appropriate model, has improved the precision and the prediction work efficient that predict the outcome.
Description of drawings
Fig. 1 is a process flow diagram of the present invention;
Fig. 2 is an As-Is analysis model cluster framework of the present invention;
Fig. 3 is a soil supply and demand forecast model bunch framework of the present invention;
Fig. 4 is an analysis of supply-demand balance model cluster framework of the present invention.
Embodiment
Should utilize supply and demand prediction method may further comprise the steps based on the soil of model cluster:
(1) according to regional land type, application demand, set up regional soil and utilize supply and demand prediction index system, import achievement data by the index system of setting up, whether unusual according to the rationality judgment data, and the suppressing exception data;
(2) utilize the present status of land utilization analytical model bunch regional present status of land utilization to be analyzed according to achievement data, the present status of land utilization analytical model bunch comprises that at least land use structure analytical model, soil utilize landscape pattern analysis model and/or soil to utilize the Dynamic Variation Analysis model, and the land use structure analytical model comprises ground class formation analytical model, region Structural Analysis Model, ecologic structure analytical model again; The soil utilizes the landscape pattern analysis model to comprise shape index, patch density, degree of separation index, area ratio, diversity index, dominance index, diversity indices, centralization degree and/or composite type; The soil utilizes the free sequential analysis model of Dynamic Variation Analysis model, change-detection model and/or dynamic simulation model.Carry out regional potential of land resource evaluation according to analysis result again, As-Is analysis comprise regional present status of land utilization structure, utilize effect, space layout and existing problems;
(3) make up regional soil and utilize supply and demand predicting candidate model cluster storehouse, the model cluster storehouse comprises base values forecast model bunch, medium-term and long-term land used forecast model bunch, annual land used forecast model bunch at least.Base values forecast model bunch, medium-term and long-term land used forecast model bunch, year, the land used forecast model bunch comprised the Song Jian Population Forecast Model at least, the Malthus demographic model, logistic gram model, ecological model, the time series analysis model, single factor regression model, multifactor regression model, Paul H. Douglas production function, the quota index model, the grey system forecasting model, Markov prediction, the Grey--Markov model, system dynamics model, neural network model, department's land used forecast model, difference-smoothing prediction model, fuzzy prediction model and/or based on the entropy forecast model, wherein medium-term and long-term land used forecast model bunch comprises regression analysis model at least, Markov chain forecast model and/or grey system forecasting model, annual land used forecast model bunch comprise trend extrapolation model and canonical correlation analysis model at least;
(4) utilize from regional soil according to the regional present status of land utilization analysis result of step (2) and regional potential of land resource evaluation result and select base values forecast model bunch the supply and demand predicting candidate model cluster storehouse, and utilize selected base values forecast model bunch to carry out the base values integrated forecasting of regional soil, base values comprises population, GDP, multiple crop index, grain consumption structure and crop yield at least;
(5) utilize from regional soil the supply and demand predicting candidate model cluster storehouse according to the base values predicted data of step (4) and select medium-term and long-term land used forecast model bunch, annual land used forecast model bunch, utilize selected medium-term and long-term land used forecast model bunch, annual land used forecast model bunch respectively medium-term and long-term and regional soil year of soil, estimation range land used type, quantitative structure change and integrated forecasting result;
(6) the integrated forecasting result according to step (5) selects analysis of supply-demand balance model, analysis of supply-demand balance model cluster comprises goal programming, multiple objective programming, SD planning, GREY SITUATION DECISION, multi-criteria decision methods and/or dynamic programming model at least, and utilize selected analysis of supply-demand balance model to carry out the utilization of regional soil and supply with potentiality and demand equilibrium analysis, and according to analysis of supply-demand balance result to the utilization of regional soil predict the outcome adjust definite.
Provide the example of three models below:
(a) regression analysis model
Regression forecasting is exactly the past and present value according to variable, finds out this quantitative relation, and infers following variable numerical value in the cards with this.Regression forecasting needs two groups or several groups of time serieses that mutual relationship is close simultaneously.Regression mathematical model commonly used has single factor to return and multinomial logistic regression, and single factor regression forecasting can be regarded as a kind of special case of multiple linear regression prediction, therefore can unify for drag:
y＝b
0+b
1x
1+b
2x
2+…+b
mx
m+υ
In the formula, the predicted value of y--forecasting object;
b
0, b
1... the bm--regression coefficient;
x
1, x
2... X
m--the independent variable observed reading:
υ-stochastic error.
Use matrix representation, regression equation is: Y=BX
In the formula,
(b) grey system forecasting model
Gray system is all regarded all stochastic variables as the grey variable, regards stochastic process as the grey process, thereby does not need a large amount of historical datas and only just can predict according to some data in " modern age ".This method for regularity not clearly, ordered series of numbers that influence factor is many predicts to have remarkable advantages.The grey system forecasting model is set up by the generation module that time series data adds up, the random quantity that may sneak in the elimination original series, from the time series of fluctuation up and down, seek certain implicit regularity, obtain randomness reduction and the regular new ordered series of numbers of having strengthened, excavate the internal characteristics of original series.This process of setting up from GM (1,1) forecast model as can be seen.If
X
(0)＝{x
(0)(1)，x
(0)(2)，…，x
(0)(n)}
Be one group of time series, these data may be disorderly and unsystematic irregular, but after generating through following adding up, and the randomness of the data that weakened and undulatory property have increased the albefaction degree of information and present certain rules.GM (1,1) model is the most frequently used a kind of gray model.
With X
(0)Obtain the generation module that adds up as one-accumulate:
X
(1)＝{x
(1)(1)，x
(1)(2)，…，x
(1)(n)}
Wherein
This formation sequence X
(1)Just present certain rules, its rule can obtain by finding the solution linear first-order differential equation:
Wherein a, u are that estimated parameter is treated in the unknown, and the note estimator is:
(c) Markov prediction
Markov chain prediction is based on Markovian process, description be the dynamic changing process of a random time sequence, this process only is in a state, t is with probability P constantly
IjBe in a
kState during moment t+1, is in a with another probability again
K+1State.Obtain probability under the various states according to this principle.
p
ij(n)＝p{x
n＝j|x
n-1＝I}
Usually, transition probability p
Ij(n) not only with I, j is relevant, and also relevant with n.Transition probability p by various possibility states in the system
IjThe matrix that constitutes is:
Step transition probability matrix for markov chain.Be characterized in: each p
IjBe non-bearing, i.e. p
Ij〉=0; And every row element sum is 1, promptly
Embodiment: choose-the year two thousand twenty in 2005 soil, certain city and utilize population, GDP, construction land and arable land supply and demand in the supply and demand prediction to predict that as an example concrete steps comprise:
(1) set up the prediction index system, import the achievement data line data analysis on its rationality of going forward side by side, prediction index comprises population forecast, the prediction of GDP development level, construction land, arable land prediction etc., predicts that wherein the population historical data is as shown in table 1:
1978～2005 years household register demographic data units in certain city of table 1: ten thousand people
(2) adopt soil utilization in 2005 to upgrade the enquiry data structure as background, to the present status of land utilization analysis, again according to analytical structure to the potential of land resource analysis, the main analysis of potentiality analysis does not utilize land development potentiality, consolidation, the potentiality of reclaiming, and this can obtain from relevant special topic planning.
(3) make up regional soil and utilize the predicting candidate model bank.According to estimation range reality, choose the model methods such as natural increase method, regretional analysis, gray system, time series analysis of base values prediction; And the soil utilizes the medium-and long-term forecasting model, comprises regression analysis model, Markov chain forecast model, grey system forecasting model, and annual land used forecast model bunch comprises trend extrapolation model and canonical correlation analysis model at least; Annual land used forecast model then mainly adopts the trend analysis Forecasting Methodology.
(4) utilize from regional soil according to the regional present status of land utilization analysis result of step (2) and regional potential of land resource evaluation result and select base values forecast model bunch the supply and demand predicting candidate model cluster storehouse, and utilize selected base values forecast model bunch to carry out the base values integrated forecasting of regional soil.Natural increase method, index method, regression analysis and four kinds of models of gray system have been adopted in population forecast, and it is as shown in table 2 to predict the outcome:
Certain city population size unit of predicting the outcome of table 2: ten thousand people
(5) utilize from regional soil the supply and demand predicting candidate model cluster storehouse according to the base values predicted data of step (4) and select medium-term and long-term land used forecast model bunch, annual land used forecast model bunch, utilize selected medium-term and long-term land used forecast model bunch, annual land used forecast model bunch respectively medium-term and long-term and regional soil year of soil, estimation range land used type, quantitative structure change.Adopt quota index per capita as the city-building land used, economics of population correlation analysis, gray system, Markov-chain model, natural increase method, regretional analysis and Markov-chain model are adopted in the prediction of ploughing, it is as shown in table 3 to predict the outcome, the prediction of ploughing adopts natural increase, regretional analysis, Markov-chain model to predict that the result is as shown in table 4.
Certain city's city-building of table 3 is with scale forecast unit as a result: hectare
Certain arable land, city scale forecast of table 4 is the list position as a result: hectare
Age natural increase method regretional analysis Markov chain
2006 270278.98 270082.94 270127.09
2007 268503.94 268111.85 268200.16
2008 266728.90 266140.76 266273.22
2009 264953.85 264169.67 264346.29
2010 263178.81 262198.58 262419.35
2011 261383.73 259492.89 259845.68
2012 259588.64 256787.2 257272.02
2013 257793.56 254081.5 254698.35
2014 255998.47 251375.81 252124.68
2015 254203.4 248670.1 249551
2016 253425.11 246959.11 247975.55
2017 252646.84 245248.1 246400.09
2018 251868.57 243537.08 244824.63
2019 251090.3 241826.07 243249.16
2020 250312.03 240115.06 241673.7
(6) the integrated forecasting result according to step (5) selects analysis of supply-demand balance model, obtaining the overall equilbrium result divides by high, normal, basic three kinds of situations, can get definite scheme that predicts the outcome of certain city's total population scale, city-building land scale and arable land scale, see Table 5 respectively, table 6, table 7.
Certain city total population scale forecast result of table 5 determines scheme (household register total population) unit: ten thousand people
Certain city's city-building land scale of table 6 predicts the outcome and determines scheme unit: hectare
Certain arable land, city scale forecast result of table 7 determines scheme unit: hectare
Claims (9)
1. the soil based on model cluster utilizes supply and demand prediction method, it is characterized in that this method comprises the steps:
(1) according to regional land type, application demand, set up regional soil and utilize supply and demand prediction index system, import achievement data by the index system of setting up, whether unusual according to the rationality judgment data, and the suppressing exception data;
(2) utilize the present status of land utilization analytical model bunch regional present status of land utilization to be analyzed according to achievement data, carry out regional potential of land resource evaluation according to analysis result again, As-Is analysis comprise regional present status of land utilization structure, utilize effect, space layout and existing problems;
(3) make up regional soil and utilize supply and demand predicting candidate model cluster storehouse, the model cluster storehouse comprises base values forecast model bunch, medium-term and long-term land used forecast model bunch, annual land used forecast model bunch at least;
(4) utilize from regional soil according to the regional present status of land utilization analysis result of step (2) and regional potential of land resource evaluation result and select base values forecast model bunch the supply and demand predicting candidate model cluster storehouse, and utilize selected base values forecast model bunch to carry out the base values integrated forecasting of regional soil, base values comprises population, GDP, multiple crop index, grain consumption structure and crop yield at least;
(5) utilize from regional soil the supply and demand predicting candidate model cluster storehouse according to the base values predicted data of step (4) and select medium-term and long-term land used forecast model bunch, annual land used forecast model bunch, utilize selected medium-term and long-term land used forecast model bunch, annual land used forecast model bunch respectively medium-term and long-term and regional soil year of soil, estimation range land used type, quantitative structure change and integrated forecasting result;
(6) the integrated forecasting result according to step (5) selects analysis of supply-demand balance model, and utilize selected analysis of supply-demand balance model to carry out the utilization of regional soil and supply with potentiality and demand equilibrium analysis, and according to analysis of supply-demand balance result to the utilization of regional soil predict the outcome adjust definite.
2. the soil based on model cluster according to claim 1 utilizes supply and demand prediction method, it is characterized in that: the described present status of land utilization analytical model of step (2) bunch comprises that at least land use structure analytical model, soil utilize landscape pattern analysis model and/or soil to utilize the Dynamic Variation Analysis model.
3. the soil based on model cluster according to claim 2 utilizes supply and demand prediction method, it is characterized in that: the land use structure analytical model comprises ground class formation analytical model, region Structural Analysis Model, ecologic structure analytical model.
4. the soil based on model cluster according to claim 2 utilizes supply and demand prediction method, it is characterized in that: the soil utilizes the landscape pattern analysis model to comprise shape index, patch density, degree of separation index, area ratio, diversity index, dominance index, diversity indices, centralization degree and/or composite type.
5. the soil based on model cluster according to claim 2 utilizes supply and demand prediction method, it is characterized in that: the soil utilizes the free sequential analysis model of Dynamic Variation Analysis model, change-detection model and/or dynamic simulation model.
6. the soil based on model cluster according to claim 1 utilizes supply and demand prediction method, it is characterized in that: base values forecast model bunch, medium-term and long-term land used forecast model bunch, year, the land used forecast model bunch comprised the Song Jian Population Forecast Model at least, the Malthus demographic model, logistic gram model, ecological model, the time series analysis model, single factor regression model, multifactor regression model, Paul H. Douglas production function, the quota index model, the grey system forecasting model, Markov prediction, the Grey--Markov model, system dynamics model, neural network model, department's land used forecast model, difference-smoothing prediction model, fuzzy prediction model and/or based on the entropy forecast model.
7. the soil based on model cluster according to claim 1 utilizes supply and demand prediction method, it is characterized in that: analysis of supply-demand balance model cluster comprises goal programming, multiple objective programming, SD planning, GREY SITUATION DECISION, multi-criteria decision methods and/or dynamic programming model at least.
8. the soil based on model cluster according to claim 1 utilizes supply and demand prediction method, it is characterized in that: medium-term and long-term land used forecast model bunch comprises regression analysis model, Markov chain forecast model and/or grey system forecasting model at least.
9. the soil based on model cluster according to claim 1 utilizes supply and demand prediction method, it is characterized in that: annual land used forecast model bunch comprises trend extrapolation model and canonical correlation analysis model at least.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010028960A CN101763600A (en) | 2010-01-12 | 2010-01-12 | Land use supply and demand prediction method based on model cluster |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010028960A CN101763600A (en) | 2010-01-12 | 2010-01-12 | Land use supply and demand prediction method based on model cluster |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101763600A true CN101763600A (en) | 2010-06-30 |
Family
ID=42494755
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201010028960A Pending CN101763600A (en) | 2010-01-12 | 2010-01-12 | Land use supply and demand prediction method based on model cluster |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101763600A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102609779A (en) * | 2012-02-22 | 2012-07-25 | 武汉大学 | Method for monitoring composite index of geographical national conditions |
| CN102622698A (en) * | 2012-02-17 | 2012-08-01 | 内蒙古东部电力有限公司 | Electricity market analyzing and predicting system and analyzing and predicting method thereof |
| CN103955764A (en) * | 2014-04-25 | 2014-07-30 | 杭州电子科技大学 | Mixing optimization method for medical image examination amount predicting |
| CN105512940A (en) * | 2014-09-26 | 2016-04-20 | 武汉光谷北斗地球空间信息产业股份有限公司 | Beidou based urban land optimization system |
| CN106901394A (en) * | 2017-04-27 | 2017-06-30 | 云南中烟工业有限责任公司 | A kind of method based on Markov process redried leaf tobacco stock's dynamic equilibrium |
| CN108346163A (en) * | 2018-02-09 | 2018-07-31 | 河南城建学院 | A kind of land use area reckoning method |
| CN108364060A (en) * | 2018-01-31 | 2018-08-03 | 天津市市政工程设计研究院 | A kind of classification design method of highway |
| CN109064036A (en) * | 2018-08-08 | 2018-12-21 | 武汉大学 | Ecosystems services supply and demand index variation detection method towards management domain |
| CN110059855A (en) * | 2019-03-12 | 2019-07-26 | 西安理工大学 | A kind of regional land use Optimal Configuration Method |
| CN110674975A (en) * | 2019-08-30 | 2020-01-10 | 华北水利水电大学 | Spatial layout method and device for reducing carbon emission in urban planning |
| CN110826062A (en) * | 2019-10-18 | 2020-02-21 | 北京天融信网络安全技术有限公司 | Malicious software detection method and device |
| US10949762B2 (en) | 2015-09-30 | 2021-03-16 | Tata Consultancy Services Limited | Methods and systems for optimizing hidden Markov Model based land change prediction |
| CN113988574A (en) * | 2021-10-22 | 2022-01-28 | 广州市城市规划勘测设计研究院 | Ecological protection red line marking method and device, terminal equipment and storage medium |
-
2010
- 2010-01-12 CN CN201010028960A patent/CN101763600A/en active Pending
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102622698A (en) * | 2012-02-17 | 2012-08-01 | 内蒙古东部电力有限公司 | Electricity market analyzing and predicting system and analyzing and predicting method thereof |
| CN102609779A (en) * | 2012-02-22 | 2012-07-25 | 武汉大学 | Method for monitoring composite index of geographical national conditions |
| CN102609779B (en) * | 2012-02-22 | 2016-03-16 | 武汉大学 | A kind of geographical national conditions aggregative index monitoring method |
| CN103955764A (en) * | 2014-04-25 | 2014-07-30 | 杭州电子科技大学 | Mixing optimization method for medical image examination amount predicting |
| CN103955764B (en) * | 2014-04-25 | 2017-01-18 | 杭州电子科技大学 | Mixing optimization method for medical image examination amount predicting |
| CN105512940A (en) * | 2014-09-26 | 2016-04-20 | 武汉光谷北斗地球空间信息产业股份有限公司 | Beidou based urban land optimization system |
| US10949762B2 (en) | 2015-09-30 | 2021-03-16 | Tata Consultancy Services Limited | Methods and systems for optimizing hidden Markov Model based land change prediction |
| CN106901394A (en) * | 2017-04-27 | 2017-06-30 | 云南中烟工业有限责任公司 | A kind of method based on Markov process redried leaf tobacco stock's dynamic equilibrium |
| CN108364060A (en) * | 2018-01-31 | 2018-08-03 | 天津市市政工程设计研究院 | A kind of classification design method of highway |
| CN108346163A (en) * | 2018-02-09 | 2018-07-31 | 河南城建学院 | A kind of land use area reckoning method |
| CN109064036A (en) * | 2018-08-08 | 2018-12-21 | 武汉大学 | Ecosystems services supply and demand index variation detection method towards management domain |
| CN109064036B (en) * | 2018-08-08 | 2021-07-06 | 武汉大学 | Ecosystem service supply and demand index change detection method facing management field |
| CN110059855A (en) * | 2019-03-12 | 2019-07-26 | 西安理工大学 | A kind of regional land use Optimal Configuration Method |
| CN110674975A (en) * | 2019-08-30 | 2020-01-10 | 华北水利水电大学 | Spatial layout method and device for reducing carbon emission in urban planning |
| CN110674975B (en) * | 2019-08-30 | 2023-04-07 | 华北水利水电大学 | Spatial layout method and device for reducing carbon emission in urban planning |
| CN110826062A (en) * | 2019-10-18 | 2020-02-21 | 北京天融信网络安全技术有限公司 | Malicious software detection method and device |
| CN110826062B (en) * | 2019-10-18 | 2022-02-01 | 北京天融信网络安全技术有限公司 | Malicious software detection method and device |
| CN113988574A (en) * | 2021-10-22 | 2022-01-28 | 广州市城市规划勘测设计研究院 | Ecological protection red line marking method and device, terminal equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101763600A (en) | Land use supply and demand prediction method based on model cluster | |
| CN113962364B (en) | Multi-factor power load prediction method based on deep learning | |
| Singh et al. | An efficient time series forecasting model based on fuzzy time series | |
| CN102034350B (en) | Short-time prediction method and system of traffic flow data | |
| Niu et al. | Power load forecasting using support vector machine and ant colony optimization | |
| Sun et al. | Prediction of stock index futures prices based on fuzzy sets and multivariate fuzzy time series | |
| Madani et al. | A Monte-Carlo game theoretic approach for multi-criteria decision making under uncertainty | |
| Froelich et al. | Fuzzy cognitive maps in the modeling of granular time series | |
| Lee et al. | Forecasting nonlinear time series of energy consumption using a hybrid dynamic model | |
| Bata et al. | Short-term water demand forecasting using hybrid supervised and unsupervised machine learning model | |
| CN107622329A (en) | The Methods of electric load forecasting of Memory Neural Networks in short-term is grown based on Multiple Time Scales | |
| Cerqueira et al. | Arbitrage of forecasting experts | |
| Yang et al. | SMAA-PO: project portfolio optimization problems based on stochastic multicriteria acceptability analysis | |
| Dariane et al. | Comparative analysis of evolving artificial neural network and reinforcement learning in stochastic optimization of multireservoir systems | |
| CN110989343A (en) | Multi-stage equipment combination planning method based on reinforcement learning | |
| Kachouei et al. | A common-weights approach for efficiency evaluation in fuzzy data envelopment analysis with undesirable outputs: application in banking industry | |
| Wang et al. | A power load forecasting model based on FA‐CSSA‐ELM | |
| Gomez-Omella et al. | Short-term forecasting methodology for energy demand in residential buildings and the impact of the COVID-19 pandemic on forecasts | |
| Işık et al. | Deep learning based electricity demand forecasting to minimize the cost of energy imbalance: A real case application with some fortune 500 companies in Türkiye | |
| Afshar et al. | Fuzzy multi-objective optimization of finance-based scheduling for construction projects with uncertainties in cost | |
| Shu et al. | Multi-step-ahead monthly streamflow forecasting using convolutional neural networks | |
| Syu et al. | Energy grid management system with anomaly detection and Q-learning decision modules | |
| Aghelpour et al. | Coupling ANFIS with ant colony optimization (ACO) algorithm for 1-, 2-, and 3-days ahead forecasting of daily streamflow, a case study in Poland | |
| Gorbatiuk et al. | Application of fuzzy time series forecasting approach for predicting an enterprise net income level | |
| CN109214610A (en) | A kind of saturation Methods of electric load forecasting based on shot and long term Memory Neural Networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20100630 |