CN103886220A - Water data discretization method for setting weight based on BP network and Gini coefficient - Google Patents
Water data discretization method for setting weight based on BP network and Gini coefficient Download PDFInfo
- Publication number
- CN103886220A CN103886220A CN201410140946.8A CN201410140946A CN103886220A CN 103886220 A CN103886220 A CN 103886220A CN 201410140946 A CN201410140946 A CN 201410140946A CN 103886220 A CN103886220 A CN 103886220A
- Authority
- CN
- China
- Prior art keywords
- unit
- water
- data
- administrative
- administrative unit
- 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.)
- Granted
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a water data discretization method for setting a weight based on a BP network and a Gini coefficient. The water data discretization method comprises the steps that a basic computing unit is acquired; spatial element data sets of the basic computing unit and an administrative unit are acquired; a quota method is adopted to supplement domestic water and industrial water, and a correlation factor apportion method is adopted to supplement ecological environment water consumption; a Gini coefficient method is adopted to determine a weight coefficient in an ecological environment water consumption computational formula; a discretization predicating result on the basic computing unit is obtained through analog computation; the result is corrected; step-by-step summarizing is carried out according to the attributes of water resource zones of the basic computing unit to obtain corresponding water data. According to the water data discretization method for setting the weight based on the BP network and the Gini coefficient, the economic society and water data of each level of water resource zone in the whole country can be obtained, and integrated water resource management is facilitated.
Description
Technical field
The present invention relates to water conservancy scientific technology field, refer to especially and a kind ofly determine the water Method of Data Discretization of weight based on BP network and Gini coefficient.
Background technology
Economic society water data are mainly by administrative unit statistics, and its border does not overlap with border, water resource district, causes the acquisition of water resource district water data very difficult.Existing economic society water data also exist shares difficulty, statistical difficulty and the problem such as statistics is various.Utilize computer technology to obtain water resource district economic society water data, drop into very important for improving Water resources data basis to support water resource administrative region and basin unified management and to reduce manpower generaI investigation.
Water refers to for certain is economical or social object, uses the behavior of certain attribute of water resource, is by water resources development, and the mode of development of water resources and the general name of method are used and used to water main body.Economic society water refers to adopt water intaking, water delivery engineering measure, from river, water causes water area by lake, reservoir and water table, meet town and country and produce and the water yield of living needs, comprise four of domestic water, process water, agricultural water and Eco-environmental Water Consumptions.
Water resource district is according to natural, the society of water resource and economic attribution, according to exploitation, utilize, administer, configuration, save, protection requirement, basin water system is divided and is got.Water resources regionalization mainly comprises water resource one-level district, water resource secondary district and water resource tertiary area.According to national water resources regionalization standard, water resource one-level district mainly comprises 10 Large Watersheds that China is domestic, and each water resource one-level district is subdivided into water resource secondary district, and each secondary district is subdivided into water resource tertiary area again.Due to water resource district and border, administrative area not overlapping, cause administrative areas at the county level to be cut apart by multiple water resource tertiary areas.At present, very deficient by the water data of water resources regionalization statistics at different levels.
In sum, proposing a kind of economic society water data statistical approach reliably, is problems anxious to be resolved to obtain the distribution situation of water data in each water resource district.
Summary of the invention
In view of this, the object of the invention is to propose a kind ofly determine the water Method of Data Discretization of weight based on BP network and Gini coefficient, to obtain the distribution situation of water data in each water resource district, thereby obtain national water resources regionalization economic society at different levels and water data, contribute to IWRM.
Determine the water Method of Data Discretization of weight based on above-mentioned purpose is provided by the invention based on BP network and Gini coefficient, comprising:
Administrative areas at the county level and water resource tertiary area polar plot are superposeed nested, obtain the fundamental space unit of different water resource tertiary area parts under each administrative unit at county level, as basic calculating unit;
All kinds of land use datas and dem data are counted on each basic calculating unit and administrative unitary space, obtain basic calculating unit and administrative unitary space factor data collection;
According to administrative unit at different levels economic society water data, adopt quota method to supplement to administrative unit at county level domestic water, process water and agricultural water, adopt correlation factor methodology to supplement to Eco-environmental Water Demand;
The weight coefficient that adopts correlation factor methodology to supplement in the computing formula obtaining to Eco-environmental Water Demand adopts Gini coefficient method to determine;
Based on BP artificial nerve network model, utilize correlationship between data target, obtain discrete predicted value on basic calculating unit through analog computation, thus by administrative unit at county level economic society water data spread to basic calculating unit;
Share downwards and carry out modified result by affiliated administrative unit at county level total value using each basic calculating unit predicted value as weight;
By revised economic society and water data value, gather step by step and obtain corresponding water data by the water resources regionalization attribute of basic calculating unit.
In some embodiments, describedly administrative areas at the county level and water resource tertiary area polar plot are superposeed nested, obtain the fundamental space unit of different water resource tertiary area parts under each administrative unit at county level, comprise as the step of basic calculating unit:
Adopt Geographic Information System (GIS) software Arc GIS, administrative areas at the county level and water resource tertiary area polar plot are superposeed nested, obtain the fundamental space unit of the affiliated different water resource tertiary area parts in each administrative unit at county level, as basic calculating unit;
To be less than the basic calculating unit of place administrative areas at the county level area 10% to the basic calculating mesh merging of contiguous area maximum.
In some embodiments, described all kinds of land use datas and dem data are counted on each basic calculating unit and administrative unitary space, the step that obtains basic calculating unit and administrative unitary space factor data collection comprises:
Utilize the spatial data that obtains basic calculating element vectors figure and comprise all kinds of land use datas and dem data, based on Arc GIS range statistics (Zonal Statistics) module, all kinds of land use datas and dem data are counted on each basic calculating unit;
Utilize administrative area element vectors figure to add up and obtain administrative unit at different levels all kinds of soils utilization and dem data;
Obtain basic calculating unit and administrative unitary space factor data collection, for spatial spreading fractional analysis.
In some embodiments, described based on BP artificial nerve network model, utilize correlationship between data target, obtain discrete predicted value on basic calculating unit through analog computation, thereby administrative unit at county level economic society water data spread is comprised to the step on basic calculating unit:
According to artificial neural network theories, build economic society water data space discretize BP artificial neural network three-layer network topological structure; Data space discretize neural network comprises three layers of input layer, hidden layer and output layers;
Influence index data enter input layer as independent variable, and simultaneously influence index vector dimension has determined the number m of input layer, and output layer nodes n is the result of the dependent variable of simulation; The output function of hidden layer is Sigmoid transforming function transformation function, and input and output function is linear function;
In forward-propagating process, input message is successively processed through hidden layer from input layer, and the state of each node layer only affects the state of next node layer; If can not obtain the output of expecting at output layer, proceed to backpropagation, error signal is returned along original connecting path, by revising the weights of each node layer, make error minimum;
Any 2/3 data sample is carried out to training study, complicated nonlinear relationship between the relative independent variable of simulation dependent variable;
Using other 1/3 sample as verification msg, to verify training study effect;
Coefficient R 1 between calculation training learning phase and Qualify Phase analog result and actual measurement sample respectively
2and R2
2, in the time that both are all greater than constant alpha (0< α <1), think that training effect is qualified, gets α=0.7～0.8;
To verify qualified neural network prediction model, the independent variable achievement data relevant to dependent variable on input basic calculating unit, obtains discrete predicting the outcome on basic calculating unit through analog computation.
In some embodiments, describedly share the step of carrying out modified result using each basic calculating unit predicted value as weight downwards by affiliated administrative unit at county level total value and comprise:
Adopt computing formula
revise;
Wherein:
for Neural Network model predictive obtains economic society and the value of target water on basic calculating unit i;
for on administrative unit at county level under basic calculating unit i through revised data value;
for the data value of revised basic calculating unit i.
In some embodiments, described by revised economic society and water data value, gather step by step by the water resources regionalization attribute of basic calculating unit the step that obtains corresponding water data and comprise:
Adopt computing formula
Wherein:
for the data value of revised basic calculating unit i;
for the corresponding achievement data value of water resource tertiary area j under basic calculating unit i;
for the corresponding achievement data value of water resource secondary district k under water resource tertiary area j;
for the corresponding achievement data value of water resource one-level district l under water resource secondary district k.
In some embodiments, describedly adopt correlation factor methodology to carry out supplementary step to Eco-environmental Water Demand to comprise:
The influence factor of Eco-environmental Water Consumption demand comprises forest land, meadow, waters, Urban Land, GDP and nonagricultural population, and administrative unit at different levels Eco-environmental Water Demand computing formula is
Wherein: k
i(i=1,2,3,4,5,6) are weight coefficient;
for administrative unit i Eco-environmental Water Demand, unit of account is hundred million m
3;
for the administrative unit of upper level Eco-environmental Water Demand, unit of account is hundred million m
3;
for administrative unit i forest land area, unit of account is kha;
for the administrative unit of upper level forest land area, unit of account is kha;
for administrative unit i grassland area, unit of account is kha;
for the administrative unit of upper level grassland area, unit of account is kha;
for administrative unit i water surface area, unit of account is kha;
for the administrative unit of upper level water surface area, unit of account is kha;
for administrative unit i Urban Land area, unit of account is kha;
for the administrative unit of upper level Urban Land area, unit of account is kha; GDP
ifor administrative unit i gross national product (GNP), unit of account is ten thousand yuan; GDP
onfor the administrative unit of upper level gross national product (GNP), unit of account is ten thousand yuan;
for administrative unit i nonagricultural population's number, unit of account is ten thousand people;
for the administrative unit of upper level nonagricultural population's number, unit of account is ten thousand people.
In some embodiments, the described weight coefficient that adopts correlation factor methodology to supplement in the computing formula obtaining to Eco-environmental Water Demand adopts the definite step of Gini coefficient method to comprise:
Each index sample data is normalized, and computing formula is
In formula: Y
kiit is the value after i sample data normalization of k index; V
kibe i sample data of k index;
Evaluation index Gini coefficient value,
In the time that the average of index normalization sample is not 0, computing formula is:
In the time that the average of index normalization sample is 0,
Wherein: G
kit is the Gini coefficient value of k index; N is the data sum of index; μ
kit is the expectation value of k all normalization samples of index;
Calculate acquisition Gini coefficient weight based on calculating the Gini coefficient value obtaining, computing formula is
Wherein: g
kit is the Gini coefficient weight of k index; G
kbe the Gini coefficient value of k index, m is index number.Calculate gained g
kbe Eco-environmental Water Demand and supplement weight coefficient K
k(k=1,2,3,4,5,6).
In some embodiments, the described weight coefficient that adopts correlation factor methodology to supplement in the computing formula obtaining to Eco-environmental Water Demand adopts the definite step of Gini coefficient method also to comprise:
After supplementing, on the basis of data, shared downwards step by step and carried out data filling by the administrative unit of higher level total value using the administrative cell value of subordinate as weight, computing formula is
Wherein:
for the data total value after upper level data correction, national sum is not revised;
for the data value of revised administrative unit i;
for the raw value of administrative unit i; Revised data characteristics is: national total value equals each province's sum, and each province's total value equals Qi Xiage city sum, and each city total value equals its lower each district sum.
In some embodiments, describedly adopt the supplementary step of quota method to comprise to administrative unit at county level domestic water, process water and agricultural water:
To administrative unit at county level domestic consumption supplement:
Suppose that unit, upper level administrative area domestic water comprehensive quota is identical with the administrative unit of its next stage domestic water comprehensive quota, and meet computing formula
Wherein:
for administrative unit i works as annual domestic water consumption, unit of account is hundred million m
3; N
ifor administrative unit i water population then, unit of account is ten thousand people;
for the administrative unit of the higher level of administrative unit i domestic water comprehensive quota per capita then, unit of account is L/ people d;
work as annual domestic water consumption for the administrative unit of higher level of administrative unit i, unit of account is hundred million m
3; N
onfor the administrative unit of the higher level water population then of administrative unit i, unit of account is ten thousand people;
To administrative unit at county level industrial water consumption supplement:
Using industrial added value as water consumption quota major influence factors, suppose that unit, upper level administrative area water duty of industry equates with the administrative unit of its next stage process water comprehensive quota, and meet computing formula
Wherein:
for administrative unit i industrial water consumption then, unit of account is hundred million m
3;
for administrative unit i industrial added value then, unit of account is ten thousand yuan;
for the administrative unit of higher level ten thousand yuan of industrial added value water consumptions then of administrative unit i, unit of account is hundred million m
3/ ten thousand yuan;
for the administrative unit of the higher level process water total amount then of administrative unit i, unit of account is hundred million m
3;
for the administrative unit of the higher level industrial added value then of administrative unit i, unit of account is ten thousand yuan;
To administrative unit at county level Water Consumption in Agriculture supplement:
Under the certain condition of the administrative unit of higher level precipitation, evaporation and other irrigation technique levels, suppose that subordinate's administrative unit crop irrigation intensity is identical with the administrative unit of corresponding higher level, calculates subordinate's administrative unit Water Consumption in Agriculture by irrigated area, and meets computing formula
Wherein:
for administrative unit i Water Consumption in Agriculture, unit of account is hundred million m
3;
for administrative unit i agricultural irrigation area, unit of account is kha;
for the administrative unit of cells area of upper level agricultural irrigation water amount, unit of account is hundred million m
3/ kha;
for the administrative unit of higher level Water Consumption in Agriculture, unit of account is hundred million m
3;
for the administrative unit of higher level irrigated area, unit of account is kha.
As can be seen from above, provided by the inventionly determine the water Method of Data Discretization of weight based on BP network and Gini coefficient, by accurate division basic calculating unit and carry out corresponding data statistics, then carry out data pre-service, further carry out spatial discretization, finally adopt modified result and data to gather the method for Data Post, obtain national water resources regionalization economic society at different levels and water data, contributed to IWRM; And the method is applicable to administrative unit economic society data at different levels and the processing of water data space discretize, and its data result quality is high, thereby water resources regionalization water data manpower census operations amount and relevant input are reduced.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of determining an embodiment of the water Method of Data Discretization of weight based on BP network and Gini coefficient provided by the invention;
Fig. 2 is the schematic flow sheet of determining another embodiment of the water Method of Data Discretization of weight based on BP network and Gini coefficient provided by the invention;
Fig. 3 is the schematic diagram of basic calculating dividing elements in the water Method of Data Discretization embodiment that determines weight based on BP network and Gini coefficient provided by the invention;
Fig. 4 is data space discretization model neural network topology structure schematic diagram in the water Method of Data Discretization embodiment that determines weight based on BP network and Gini coefficient provided by the invention;
Fig. 5 is the spatial discretization model framework schematic diagram based on BP neural network in the water Method of Data Discretization embodiment that determines weight based on BP network and Gini coefficient provided by the invention.
Embodiment
For making the object, technical solutions and advantages of the present invention clearer, below in conjunction with specific embodiment, and with reference to accompanying drawing, the present invention is described in more detail.
It should be noted that, in the embodiment of the present invention, the statement of all uses " first " and " second " is all in order to distinguish two non-identical entities of same names or non-identical parameter, visible " first " " second " only convenience in order to explain, should not be construed as the restriction to the embodiment of the present invention, subsequent embodiment is explanation no longer one by one to this.
With reference to accompanying drawing 1, it is the schematic flow sheet of determining an embodiment of the water Method of Data Discretization of weight based on BP network and Gini coefficient provided by the invention.
Describedly determine the water Method of Data Discretization of weight based on BP network and Gini coefficient, comprising:
Step 101: administrative areas at the county level and water resource tertiary area polar plot are superposeed nested, obtain the fundamental space unit of different water resource tertiary area parts under each administrative unit at county level, as basic calculating unit;
Step 102: all kinds of land use datas and dem data are counted on each basic calculating unit and administrative unitary space, obtain basic calculating unit and administrative unitary space factor data collection;
Step 103: according to administrative unit at different levels economic society water data, adopt quota method to supplement to administrative unit at county level domestic water, process water and agricultural water, adopt correlation factor methodology to supplement to Eco-environmental Water Demand;
Step 104: the weight coefficient that adopts correlation factor methodology to supplement in the computing formula obtaining to Eco-environmental Water Demand adopts Gini coefficient method to determine;
Step 105: based on BP artificial nerve network model, utilize correlationship between data target, obtain discrete predicted value on basic calculating unit through analog computation, thereby by administrative unit at county level economic society water data spread to basic calculating unit;
Step 106: share downwards and carry out modified result by affiliated administrative unit at county level total value using each basic calculating unit predicted value as weight;
Step 107: by revised economic society and water data value, gather step by step and obtain corresponding water data by the water resources regionalization attribute of basic calculating unit.
With reference to accompanying drawing 2, it is the schematic flow sheet of determining another embodiment of the water Method of Data Discretization of weight based on BP network and Gini coefficient provided by the invention.
The described water Method of Data Discretization of determining weight based on BP network and Gini coefficient comprises:
Step 100: basic data is collected;
Step 200: computing unit is divided and data statistics;
Step 300: data pre-service;
Step 400: spatial discretization;
Step 500: Data Post.
Further, described step 200---computing unit is divided and data statistics, mainly refer to by the principle of water resource zoning administrative zoning unit is divided into the space cell with water resources regionalization attribute that resolution is higher, as the basic calculating unit of spatial discretization; Then Space Elements on basic calculating unit is carried out to statistical study.Particularly, also can comprise the steps:
Step 201: utilize " intersect " order to administrative areas at the county level and water resource tertiary area polar plot superpose nested (with reference to accompanying drawing 3) in Geographic Information System (GIS) software Arc GIS;
Step 202: obtain the fundamental space unit of the affiliated different water resource tertiary area parts in each administrative unit at county level, be basic calculating unit;
, also can further process to the basic calculating unit that is less than place administrative areas at the county level area 10% the basic calculating mesh merging by it to contiguous area maximum meanwhile.
Step 203: utilize and obtain basic calculating element vectors figure and spatial data (DEM and MODIS soil utilize), based on Arc GIS range statistics (Zonal Statistics) module, all kinds of land use datas and dem data are counted on each basic calculating unit;
Meanwhile, utilize administrative area element vectors figure to add up equally and obtain administrative unit at different levels all kinds of soils utilization and dem data;
Thereby obtain basic calculating unit and administrative unitary space factor data collection, for spatial spreading fractional analysis.
Preferably, described step 300---data pre-service: mainly refer to obtain under basic data prerequisite trying one's best, to the administrative unit economic society water shortage of data problem that may exist, adopt rational analytical algorithm to supplement; To the various problem of statistics, adopt from the downward level of a higher level allocation way and revise.The a set of complete and supporting at different levels administrative unit economic society water basic data collection of final acquisition.Particularly, also can comprise the steps:
Step 301: data filling: according to administrative unit at different levels economic society water data, adopt quota method to supplement to administrative unit at county level domestic water, process water and agricultural water, adopt correlation factor methodology to supplement to Eco-environmental Water Demand.Compensation process is as follows:
(1) domestic consumption is supplemented
The material impact factor of domestic consumption is population.The domestic consumption in a region and its total number of people are deposited positive correlation.And due to the disappearance of statistics itself, for this area then domestic water comprehensive quota cannot calculate.Therefore, suppose that unit, upper level administrative area domestic water comprehensive quota is identical with the administrative unit of its next stage domestic water comprehensive quota, meets following formula:
In formula:
for administrative unit i works as annual domestic water consumption, unit is hundred million m
3; N
ifor administrative unit i water population then, unit of account is ten thousand people;
for the administrative unit of the higher level of administrative unit i domestic water comprehensive quota per capita then, unit of account is L/ people d;
work as annual domestic water consumption for the administrative unit of higher level of administrative unit i, unit of account is hundred million m
3; N
onfor the administrative unit of the higher level water population then of administrative unit i, unit of account is ten thousand people.
(2) industrial water consumption supplements
Using industrial added value as water consumption quota major influence factors, suppose that unit, upper level administrative area water duty of industry equates with the administrative unit of its next stage process water comprehensive quota, meets following formula:
In formula:
for administrative unit i industrial water consumption then, unit of account is hundred million m
3;
for administrative unit i industrial added value then, unit of account is ten thousand yuan;
for the administrative unit of higher level ten thousand yuan of industrial added value water consumptions then of administrative unit i, unit of account is hundred million m
3/ ten thousand yuan;
for the administrative unit of the higher level process water total amount then of administrative unit i, unit of account is hundred million m
3;
for the administrative unit of the higher level industrial added value then of administrative unit i, unit of account is ten thousand yuan.
(3) Water Consumption in Agriculture supplements
Under the certain condition of the administrative unit of higher level precipitation, evaporation and other irrigation technique levels, suppose that subordinate's administrative unit crop irrigation intensity is identical with the administrative unit of corresponding higher level, can calculate subordinate's administrative unit Water Consumption in Agriculture by irrigated area:
In formula:
for administrative unit i Water Consumption in Agriculture, unit of account is hundred million m
3;
for administrative unit i agricultural irrigation area, kha;
for the administrative unit of cells area of upper level agricultural irrigation water amount, hundred million m
3/ kha;
for the administrative unit of higher level Water Consumption in Agriculture, unit of account is hundred million m
3;
for the administrative unit of higher level irrigated area, kha.
(4) Eco-environmental Water Demand supplements
Eco-environmental Water Demand, closely related with Economic Development Status.Along with the development of economic society, Eco-environmental Water Consumption increase in demand, its major influence factors comprises forest land, meadow, waters, Urban Land, GDP and nonagricultural population.Administrative unit at different levels Eco-environmental Water Demand is calculated as follows:
In formula: k
i(i=1,2,3,4,5,6) are weight coefficient;
for administrative unit i Eco-environmental Water Demand, unit of account is hundred million m
3;
for the administrative unit of upper level Eco-environmental Water Demand, unit of account is hundred million m
3;
for administrative unit i forest land area, unit of account is kha;
for the administrative unit of upper level forest land area, unit of account is kha;
for administrative unit i grassland area, unit of account is kha;
for the administrative unit of upper level grassland area, unit of account is kha;
for administrative unit i water surface area, unit of account is kha;
for the administrative unit of upper level water surface area, unit of account is kha;
for administrative unit i Urban Land area, unit of account is kha;
for the administrative unit of upper level Urban Land area, unit of account is kha; GDP
ifor administrative unit i gross national product (GNP), unit of account is ten thousand yuan; GDP
onfor the administrative unit of upper level gross national product (GNP), unit of account is ten thousand yuan;
for administrative unit i nonagricultural population's number, unit of account is ten thousand people;
for the administrative unit of upper level nonagricultural population's number, unit of account is ten thousand people.
Further, for the weight coefficient in formula (4), adopt Gini coefficient method to determine, specifically determine that method is as follows:
Gini coefficient (Gini Coefficient) is the index of a quantitative measurement income disparity degree, is an important analysis index for the inner income disparity situation of integrated survey resident.Adopt Gini coefficient enabling legislation herein, by calculating evaluation index Gini coefficient value size, to reflect the size of the data difference between this index different evaluation object.Concrete computation process is as follows:
First, each index sample data is normalized, computing formula is as follows:
In formula: Y
kiit is the value after i sample data normalization of k index; V
kibe i sample data of k index.
Evaluation index Gini coefficient value is calculated as follows shown in formula:
In formula (6) and (7): G
kit is the Gini coefficient value of k index; N is the data sum of index; μ
kit is the expectation value of k all normalization samples of index.In the time that the average of index normalization sample is not 0, the Gini coefficient value of index adopts formula (6) to calculate; And in the time that its average is 0, adopt formula (7) to calculate.
Can calculate acquisition Gini coefficient weight based on calculating the Gini coefficient value obtaining, formula is as follows:
Wherein: g
kit is the Gini coefficient weight of k index; G
kbe the Gini coefficient value of k index, m is index number.Calculate gained g
kbe Eco-environmental Water Demand and supplement weight coefficient K
k(k=1,2,3,4,5,6).
Step 302: data correction: consider the problem that administrative unit at different levels may exist Statistical Criteria to differ, on the basis of data, shared downwards step by step by the administrative unit of higher level total value using the administrative cell value of subordinate as weight after supplementing, be shown below:
In formula:
for the data total value after upper level data correction, national sum is not revised;
for the data value of revised administrative unit i;
for the raw value of administrative unit i.Revised data characteristics is: national total value equals each province's sum, and each province's total value equals Qi Xiage city sum, and each city total value equals its lower each district sum.
Further, described step 400---spatial discretization: mainly refer on the basis of data pre-service gained relevant rudimentary data, based on BP artificial nerve network model, utilize correlationship between data target, carry out simulation and forecast by administrative unit at county level economic society water data spread to the process on basic calculating unit.Particularly, the economic society water data space discretization method based on BP artificial nerve network model, also can further comprise the steps:
Step 401: according to artificial neural network theories, build economic society water data space discretize BP artificial neural network three-layer network topological structure (with reference to accompanying drawing 4).Data space discretize neural network comprises three layers of input layer, hidden layer and output layers.Influence index data enter input layer as independent variable, and influence index vector dimension has determined the number m of input layer simultaneously, output layer nodes n, the i.e. result of the dependent variable of simulation.The output function of hidden layer is Sigmoid transforming function transformation function, and input and output function is linear function.In forward-propagating process, input message is successively processed through hidden layer from input layer, and the state of each node layer only affects the state of next node layer.If can not obtain the output of expecting at output layer, proceed to backpropagation, error signal is returned along original connecting path, by revising the weights of each node layer, make error minimum.BP artificial neural network has extremely strong sunykatuib analysis and predictive ability, has guaranteed the quality of spatial discretization outcome data.
Step 402: based on BP artificial nerve network model, economic society water digital simulation prediction flow process as shown in Figure 5.In simulation process, any 2/3 data sample is carried out to training study, complicated nonlinear relationship between the relative independent variable of simulation dependent variable; Meanwhile, using other 1/3 sample as verification msg, to verify training study effect.Coefficient R 1 between calculation training learning phase and Qualify Phase analog result and actual measurement sample respectively
2and R2
2, in the time that being all greater than constant alpha (0< α <1), both think that training effect is qualified, generally get α=0.7～0.8.Finally, to verify qualified neural network prediction model, the independent variable achievement data relevant to dependent variable on input basic calculating unit, obtains discrete predicting the outcome on basic calculating unit through analog computation.
The numerical value that outputs to basic calculating unit because of the prediction of BP artificial nerve network model not matches with administrative cell data, further, described step 500---Data Post, specifically comprise: further revise predicted data result, and by the further tabulate statistics of water resources regionalization attribute of basic calculating unit, obtain each water resource district distribution situation.Specifically comprise the following steps:
Step 501: modified result: share correction using each basic calculating unit predicted value as weight downwards by affiliated administrative unit at county level total value, be shown below.
In formula:
for Neural Network model predictive obtains economic society and the value of target water on basic calculating unit i;
for on administrative unit at county level under basic calculating unit i through revised data value;
for the data value of revised basic calculating unit i.
Step 502: water resources regionalization water data at different levels gather: by revised economic society and water data value, gather step by step by the water resources regionalization attribute of basic calculating unit, calculation expression is as follows:
In formula:
for the data value of revised basic calculating unit i;
for the corresponding achievement data value of water resource tertiary area j under basic calculating unit i;
for the corresponding achievement data value of water resource secondary district k under water resource tertiary area j;
for the corresponding achievement data value of water resource one-level district l under water resource secondary district k.
Can how to apply for clearer method provided by the invention, describe below in conjunction with method Application Example:
In conjunction with reference to accompanying drawing 1 and accompanying drawing 2, described method for the main thought of economic society water spatial discretization is: first, utilize spatial data and GIS technology to carry out the division of space computing unit, the basic calculating unit of specified data discretize, and statistics obtains the basic calculating unit Space Elements data relevant with administrative zoning unit.Meanwhile, utilize economic society data, Space Elements data and the water data of administrative unit at different levels, carry out economic society water data filling and correction, form a set of complete administrative subregion basic data collection.Then, based on the basic data of administrative areas at the county level and basic calculating unit, and consider correlationship between data target, utilize BP artificial nerve network model successively by economic society data and water data to basic calculating unitary space discretize.Finally, with reference to each administrative areas at the county level data, obtain the further correcting process of predicted value by discrete, and gather water data result by water resources regionalization, obtain water resource one-level district, water resource secondary district and water resource tertiary area economic society water data discrete result.
The method can not only be by discrete water data space to water resources at different levels district, also can be by related economic society data discrete spread to unit, water resource district.Below various processes is described in detail:
Basic data is collected.According to the requirement of economic society water data assimilation and spatial discretization, need first collect fundamental analysis data, mainly comprise: spatial data and (province, city, county) at different levels administrative unit economic society data and water data, as shown in table 1.Wherein, spatial data and administrative unit at different levels economic society data should be perfect, and administrative unit at different levels water data may exist the various problem of shortage of data and statistics.
Table 1 basic data system
Computing unit is divided.According to flow process shown in Fig. 1 or Fig. 2, utilize and collect the at county level administrative unit and the water resource tertiary area polar plot that obtain, carry out Arc GIS polar plot nestable, obtain basic calculating cell distribution polar plot.
Spatial data statistics.Utilize gained basic calculating element vectors figure and DEM and the utilization of MODIS soil, obtain each administrative unit at county level and basic calculating cells D EM data (comprising height above sea level and the gradient) and six kinds of land use datas (in table 1) based on Arc GIS range statistics module statistics, make data for the simulation and forecast of BP artificial neural network and prepare.
Water data filling.As in the basic data of collecting, there is the problem of disappearance in administrative unit economic society water data, calculates respectively to supplement so improve administrative unit lives at different levels, industry and agricultural water data according to formula (1)～(3).According to formula (5)～(8), with each provincial administrative unit grouping, successively forest land, meadow, waters and the Urban Land area (being obtained by the 3rd step) to all administrative unit at county level under each province and GDP and nonagricultural population's data are normalized, and the ecological water amount in each provincial administrative unit of calculating is supplemented the Geordie weight coefficient needing.Finally according to formula (4), calculate and supplement and improve each administrative unit at county level Eco-environmental Water Demand.
Data correction.According to economic society water data correction algorithm (seeing formula (9)), the at different levels administrative unit basis data of supplementing after improving are further revised, obtain the economic society water data set of the superior and the subordinate's coupling.
The prediction of BP artificial Neural Network Simulation.After aforementioned data is ready to complete, carry out the prediction of economic society water digital simulation based on BP artificial nerve network model, with reference to accompanying drawing 5.For reduce the impact of regional disparity on simulated training and discrete prediction effect as far as possible, carrying out training simulation and discrete forecast analysis by water resource one-level differentiation group respectively---the training sample of input is mainly from the achievement data sample of related administrative unit at county level, single water resource one-level district.Consider the correlationship between ground Space Elements index, economic society index and target water three, set up water data space discretize neuron network simulation prediction index system, independent variable and dependent variable index are as shown in table 2.Build on this basis economic society water data space discretize flow process: first using the Space Elements index of administrative unit at county level (height above sea level, the gradient, soil utilization) as independent variable, economic society index (population, economy, agricultural production) is dependent variable, carry out neural metwork training, verify that on qualified rear input basic calculating unit, height above sea level, the gradient, land use data predict economic society data discrete on basic calculating unit; Again in the same way, using Space Elements index and economic society index as independent variable, economic society target water is dependent variable, by water data discrete to basic calculating unit.Finally, the simulation and forecast value of discrete acquisition basic calculating unit economic society data and economic society water data.
Table 2 water data space discretize neuron network simulation index system
| Independent variable index | Dependent variable index |
| Height above sea level, the gradient, soil utilize class | Population class, economic class, agricultural production class |
| Height above sea level, the gradient, soil utilize class, population class, economic class, agricultural production class | Domestic consumption, industrial water consumption, Water Consumption in Agriculture, Eco-environmental Water Demand |
Modified result.According to formula (10), the basic calculating unit economic society data that the discrete prediction of the 6th step is obtained and the further correcting process of economic society water data, obtain the data set matching with administrative unit at county level.
Water resources regionalization water data at different levels gather.According to formula (11), the basic calculating cell data result that the 7th step is obtained is divided step by step and is gathered, and obtains economic society and economic society water data on each water resources regionalization.
As can be seen from above, provided by the inventionly determine the water Method of Data Discretization of weight based on BP network and Gini coefficient, by accurate division basic calculating unit and carry out corresponding data statistics, then carry out data pre-service, further carry out spatial discretization, finally adopt modified result and data to gather the method for Data Post, obtain national water resources regionalization economic society at different levels and water data, contributed to IWRM; And the method is applicable to administrative unit economic society data at different levels and the processing of water data space discretize, and its data result quality is high, thereby water resources regionalization water data manpower census operations amount and relevant input are reduced.
Those of ordinary skill in the field are to be understood that: the foregoing is only specific embodiments of the invention; be not limited to the present invention; within the spirit and principles in the present invention all, any modification of making, be equal to replacement, improvement etc., within all should being included in protection scope of the present invention.
Claims (10)
1. determine a water Method of Data Discretization for weight based on BP network and Gini coefficient, it is characterized in that, comprising:
Administrative areas at the county level and water resource tertiary area polar plot are superposeed nested, obtain the fundamental space unit of different water resource tertiary area parts under each administrative unit at county level, as basic calculating unit;
All kinds of land use datas and dem data are counted on each basic calculating unit and administrative unitary space, obtain basic calculating unit and administrative unitary space factor data collection;
According to administrative unit at different levels economic society water data, adopt quota method to supplement to administrative unit at county level domestic water, process water and agricultural water, adopt correlation factor methodology to supplement to Eco-environmental Water Demand;
The weight coefficient that adopts correlation factor methodology to supplement in the computing formula obtaining to Eco-environmental Water Demand adopts Gini coefficient method to determine;
Based on BP artificial nerve network model, utilize correlationship between data target, obtain discrete predicted value on basic calculating unit through analog computation, thus by administrative unit at county level economic society water data spread to basic calculating unit;
Share downwards and carry out modified result by affiliated administrative unit at county level total value using each basic calculating unit predicted value as weight;
By revised economic society and water data value, gather step by step and obtain corresponding water data by the water resources regionalization attribute of basic calculating unit.
2. method according to claim 1, it is characterized in that, describedly administrative areas at the county level and water resource tertiary area polar plot are superposeed nested, obtain the fundamental space unit of different water resource tertiary area parts under each administrative unit at county level, comprise as the step of basic calculating unit:
Adopt Geographic Information System (GIS) software Arc GIS, administrative areas at the county level and water resource tertiary area polar plot are superposeed nested, obtain the fundamental space unit of the affiliated different water resource tertiary area parts in each administrative unit at county level, as basic calculating unit;
To be less than the basic calculating unit of place administrative areas at the county level area 10% to the basic calculating mesh merging of contiguous area maximum.
3. method according to claim 1, is characterized in that, described all kinds of land use datas and dem data is counted on each basic calculating unit and administrative unitary space, and the step that obtains basic calculating unit and administrative unitary space factor data collection comprises:
Utilize the spatial data that obtains basic calculating element vectors figure and comprise all kinds of land use datas and dem data, based on Arc GIS range statistics (Zonal Statistics) module, all kinds of land use datas and dem data are counted on each basic calculating unit;
Utilize administrative area element vectors figure to add up and obtain administrative unit at different levels all kinds of soils utilization and dem data;
Obtain basic calculating unit and administrative unitary space factor data collection, for spatial spreading fractional analysis.
4. method according to claim 1, it is characterized in that, described based on BP artificial nerve network model, utilize correlationship between data target, obtain discrete predicted value on basic calculating unit through analog computation, thereby administrative unit at county level economic society water data spread comprised to the step on basic calculating unit:
According to artificial neural network theories, build economic society water data space discretize BP artificial neural network three-layer network topological structure; Data space discretize neural network comprises three layers of input layer, hidden layer and output layers;
Influence index data enter input layer as independent variable, and simultaneously influence index vector dimension has determined the number m of input layer, and output layer nodes n is the result of the dependent variable of simulation; The output function of hidden layer is Sigmoid transforming function transformation function, and input and output function is linear function;
In forward-propagating process, input message is successively processed through hidden layer from input layer, and the state of each node layer only affects the state of next node layer; If can not obtain the output of expecting at output layer, proceed to backpropagation, error signal is returned along original connecting path, by revising the weights of each node layer, make error minimum;
Any 2/3 data sample is carried out to training study, complicated nonlinear relationship between the relative independent variable of simulation dependent variable;
Using other 1/3 sample as verification msg, to verify training study effect;
Coefficient R 1 between calculation training learning phase and Qualify Phase analog result and actual measurement sample respectively
2and R2
2, in the time that both are all greater than constant alpha (0< α <1), think that training effect is qualified, gets α=0.7～0.8;
To verify qualified neural network prediction model, the independent variable achievement data relevant to dependent variable on input basic calculating unit, obtains discrete predicting the outcome on basic calculating unit through analog computation.
5. method according to claim 1, is characterized in that, describedly shares the step of carrying out modified result using each basic calculating unit predicted value as weight downwards by affiliated administrative unit at county level total value and comprises:
Adopt computing formula
revise;
Wherein:
for Neural Network model predictive obtains economic society and the value of target water on basic calculating unit i;
for on administrative unit at county level under basic calculating unit i through revised data value;
for the data value of revised basic calculating unit i.
6. method according to claim 1, is characterized in that, described by revised economic society and water data value, gathers step by step the step that obtains corresponding water data comprise by the water resources regionalization attribute of basic calculating unit:
Adopt computing formula
Wherein:
for the data value of revised basic calculating unit i;
for the corresponding achievement data value of water resource tertiary area j under basic calculating unit i;
for the corresponding achievement data value of water resource secondary district k under water resource tertiary area j;
for the corresponding achievement data value of water resource one-level district l under water resource secondary district k.
7. according to the method described in claim 1 to 6 any one, it is characterized in that, describedly adopt correlation factor methodology to carry out supplementary step to Eco-environmental Water Demand to comprise:
The influence factor of Eco-environmental Water Consumption demand comprises forest land, meadow, waters, Urban Land, GDP and nonagricultural population, and administrative unit at different levels Eco-environmental Water Demand computing formula is
Wherein: k
i(i=1,2,3,4,5,6) are weight coefficient;
for administrative unit i Eco-environmental Water Demand, unit of account is hundred million m
3;
for the administrative unit of upper level Eco-environmental Water Demand, unit of account is hundred million m
3;
for administrative unit i forest land area, unit of account is kha;
for the administrative unit of upper level forest land area, unit of account is kha;
for administrative unit i grassland area, unit of account is kha;
for the administrative unit of upper level grassland area, unit of account is kha;
for administrative unit i water surface area, unit of account is kha;
for the administrative unit of upper level water surface area, unit of account is kha;
for administrative unit i Urban Land area, unit of account is kha;
for the administrative unit of upper level Urban Land area, unit of account is kha; GDP
ifor administrative unit i gross national product (GNP), unit of account is ten thousand yuan; GDP
onfor the administrative unit of upper level gross national product (GNP), unit of account is ten thousand yuan;
for administrative unit i nonagricultural population's number, unit of account is ten thousand people;
for the administrative unit of upper level nonagricultural population's number, unit of account is ten thousand people.
8. method according to claim 7, is characterized in that, the described weight coefficient that adopts correlation factor methodology to supplement in the computing formula obtaining to Eco-environmental Water Demand adopts the definite step of Gini coefficient method to comprise:
Each index sample data is normalized, and computing formula is
In formula: Y
kiit is the value after i sample data normalization of k index; V
kibe i sample data of k index;
Evaluation index Gini coefficient value,
In the time that the average of index normalization sample is not 0, computing formula is:
In the time that the average of index normalization sample is 0,
Wherein: G
kit is the Gini coefficient value of k index; N is the data sum of index; μ
kit is the expectation value of k all normalization samples of index;
Calculate acquisition Gini coefficient weight based on calculating the Gini coefficient value obtaining, computing formula is
Wherein: g
kit is the Gini coefficient weight of k index; G
kbe the Gini coefficient value of k index, m is index number.Calculate gained g
kbe Eco-environmental Water Demand and supplement weight coefficient K
k(k=1,2,3,4,5,6).
9. method according to claim 8, is characterized in that, the described weight coefficient that adopts correlation factor methodology to supplement in the computing formula obtaining to Eco-environmental Water Demand adopts the definite step of Gini coefficient method also to comprise:
After supplementing, on the basis of data, shared downwards step by step and carried out data filling by the administrative unit of higher level total value using the administrative cell value of subordinate as weight, computing formula is
Wherein:
for the data total value after upper level data correction, national sum is not revised;
for the data value of revised administrative unit i;
for the raw value of administrative unit i; Revised data characteristics is: national total value equals each province's sum, and each province's total value equals Qi Xiage city sum, and each city total value equals its lower each district sum.
10. method according to claim 9, is characterized in that, describedly adopts the supplementary step of quota method to comprise to administrative unit at county level domestic water, process water and agricultural water:
To administrative unit at county level domestic consumption supplement:
Suppose that unit, upper level administrative area domestic water comprehensive quota is identical with the administrative unit of its next stage domestic water comprehensive quota, and meet computing formula
Wherein:
for administrative unit i works as annual domestic water consumption, unit of account is hundred million m
3; N
ifor administrative unit i water population then, unit of account is ten thousand people;
for the administrative unit of the higher level of administrative unit i domestic water comprehensive quota per capita then, unit of account is L/ people d;
work as annual domestic water consumption for the administrative unit of higher level of administrative unit i, unit of account is hundred million m
3; N is upper is the administrative unit of the higher level water population then of administrative unit i, and unit of account is ten thousand people;
To administrative unit at county level industrial water consumption supplement:
Using industrial added value as water consumption quota major influence factors, suppose that unit, upper level administrative area water duty of industry equates with the administrative unit of its next stage process water comprehensive quota, and meet computing formula
Wherein:
for administrative unit i industrial water consumption then, unit of account is hundred million m
3;
for administrative unit i industrial added value then, unit of account is ten thousand yuan;
for the administrative unit of higher level ten thousand yuan of industrial added value water consumptions then of administrative unit i, unit of account is hundred million m
3/ ten thousand yuan;
for the administrative unit of the higher level process water total amount then of administrative unit i, unit of account is hundred million m
3;
for the administrative unit of the higher level industrial added value then of administrative unit i, unit of account is ten thousand yuan;
To administrative unit at county level Water Consumption in Agriculture supplement:
Under the certain condition of the administrative unit of higher level precipitation, evaporation and other irrigation technique levels, suppose that subordinate's administrative unit crop irrigation intensity is identical with the administrative unit of corresponding higher level, calculates subordinate's administrative unit Water Consumption in Agriculture by irrigated area, and meets computing formula
Wherein:
for administrative unit i Water Consumption in Agriculture, unit of account is hundred million m
3;
for administrative unit i agricultural irrigation area, unit of account is kha;
for the administrative unit of cells area of upper level agricultural irrigation water amount, unit of account is hundred million m
3/ kha;
for the administrative unit of higher level Water Consumption in Agriculture, unit of account is hundred million m
3;
for the administrative unit of higher level irrigated area, unit of account is kha.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410140946.8A CN103886220B (en) | 2014-04-10 | 2014-04-10 | Water data discretization method for setting weight based on BP network and Gini coefficient |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410140946.8A CN103886220B (en) | 2014-04-10 | 2014-04-10 | Water data discretization method for setting weight based on BP network and Gini coefficient |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103886220A true CN103886220A (en) | 2014-06-25 |
| CN103886220B CN103886220B (en) | 2017-02-01 |
Family
ID=50955110
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410140946.8A Expired - Fee Related CN103886220B (en) | 2014-04-10 | 2014-04-10 | Water data discretization method for setting weight based on BP network and Gini coefficient |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103886220B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108764473A (en) * | 2018-05-23 | 2018-11-06 | 河北工程大学 | A kind of BP neural network water demands forecasting method based on correlation analysis |
| CN108897799A (en) * | 2018-06-13 | 2018-11-27 | 郑州大学 | A kind of water resource based on Web GIS and economic society matching relationship visualization system |
| CN109345067A (en) * | 2018-08-24 | 2019-02-15 | 山东省环境规划研究院 | A kind of social economy and the discretization method with water information data |
| CN112836449A (en) * | 2021-02-10 | 2021-05-25 | 北京师范大学 | Method for calibrating hydrological model |
| CN112966221A (en) * | 2021-03-04 | 2021-06-15 | 江西省水利科学院 | Method for converting total water consumption of assessment year in southern rich water region |
| CN115879745A (en) * | 2023-02-23 | 2023-03-31 | 珠海智信佰达科技有限公司 | Agricultural irrigation water analysis scheduling and service management method and platform |
| CN116307936A (en) * | 2023-05-17 | 2023-06-23 | 长江水利委员会长江科学院 | Method, system, electronic device and storage medium for decomposing total amount of water |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102750589B (en) * | 2012-06-30 | 2015-08-19 | 北京师范大学 | Water environment and hydro-ecological safety ensure management system |
| CN103366089A (en) * | 2013-07-11 | 2013-10-23 | 浪潮电子信息产业股份有限公司 | Evaluation method for water resource use efficiency in data center |
-
2014
- 2014-04-10 CN CN201410140946.8A patent/CN103886220B/en not_active Expired - Fee Related
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108764473A (en) * | 2018-05-23 | 2018-11-06 | 河北工程大学 | A kind of BP neural network water demands forecasting method based on correlation analysis |
| CN108897799A (en) * | 2018-06-13 | 2018-11-27 | 郑州大学 | A kind of water resource based on Web GIS and economic society matching relationship visualization system |
| CN109345067A (en) * | 2018-08-24 | 2019-02-15 | 山东省环境规划研究院 | A kind of social economy and the discretization method with water information data |
| CN112836449A (en) * | 2021-02-10 | 2021-05-25 | 北京师范大学 | Method for calibrating hydrological model |
| CN112836449B (en) * | 2021-02-10 | 2023-09-05 | 北京师范大学 | Method for calibrating hydrologic model |
| CN112966221A (en) * | 2021-03-04 | 2021-06-15 | 江西省水利科学院 | Method for converting total water consumption of assessment year in southern rich water region |
| CN115879745A (en) * | 2023-02-23 | 2023-03-31 | 珠海智信佰达科技有限公司 | Agricultural irrigation water analysis scheduling and service management method and platform |
| CN115879745B (en) * | 2023-02-23 | 2023-05-09 | 珠海智信佰达科技有限公司 | Agricultural irrigation water analysis scheduling and service management method and platform |
| CN116307936A (en) * | 2023-05-17 | 2023-06-23 | 长江水利委员会长江科学院 | Method, system, electronic device and storage medium for decomposing total amount of water |
| CN116307936B (en) * | 2023-05-17 | 2023-08-18 | 长江水利委员会长江科学院 | Method, system, electronic device and storage medium for decomposing total amount of water |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103886220B (en) | 2017-02-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103886220A (en) | Water data discretization method for setting weight based on BP network and Gini coefficient | |
| Li et al. | An uncertainty-based framework for agricultural water-land resources allocation and risk evaluation | |
| Luo et al. | Evaluating the coordinated development of social economy, water, and ecology in a heavily disturbed basin based on the distributed hydrology model and the harmony theory | |
| CN108536908B (en) | Method for evaluating watershed water environment safety based on non-point source nitrogen and phosphorus loss risk | |
| Liu et al. | Construction and application of a refined index for measuring the regional matching characteristics between water and land resources | |
| Liu et al. | Novel methods to assess environmental, economic, and social sustainability of main agricultural regions in China | |
| CN112765800A (en) | Design method of distributed water resource configuration model | |
| Jia et al. | An improved method for integrated water security assessment in the Yellow River basin, China | |
| Liu et al. | Optimal allocation of water quantity and waste load in the Northwest Pearl River Delta, China | |
| Sherafatpour et al. | Agricultural water allocation by integration of hydro-economic modeling with Bayesian networks and random forest approaches | |
| CN108520345A (en) | Evaluation for cultivated-land method and system based on GA-BP neural network models | |
| CN106599562B (en) | River ecological water demand computational methods based on probability weight FDC methods | |
| CN103218517A (en) | GIS (Geographic Information System)-based region-meshed spatial population density computing method | |
| CN103810648A (en) | Product industrial water footprint calculating method based on regional and seasonal water resource pressure indexes | |
| LaBeau et al. | Effects of future urban and biofuel crop expansions on the riverine export of phosphorus to the Laurentian Great Lakes | |
| CN111899126A (en) | Three red line control index dividing method based on water circulation simulation | |
| CN103886519A (en) | Economic water consumption data spatial discretization method based on RBF neural network | |
| Li et al. | System dynamic relationship between service water and food: Case study at Jinghe River Basin | |
| Wu et al. | Wetland area identification and waterbird protection management in consideration of lake topography and water level change | |
| Liu et al. | A quantitative analysis framework for water-food-energy nexus in an agricultural watershed using WEAP-MODFLOW | |
| Chen et al. | A quantitative assessment on ecological compensation based on water resources value accounting: A case study of water Source area of the middle route of south-to-north water transfer project in China | |
| CN102880753B (en) | Based on the land utilization space characteristic dimension conversion method of fractal dimension | |
| Li et al. | Multi-Scenario Simulation of Ecosystems Based on Adaptive Restoration to Promote Human–Nature Harmony: A Case Study of Loess Hills Micro-Watershed | |
| Wang et al. | Study of optimal and joint allocations of water and land resources for multiple objectives | |
| CN114117323A (en) | Water resource system optimal configuration method, device and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170201 Termination date: 20200410 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |