CN111667112B - Fishery resource abundance gray prediction model optimization method and application thereof - Google Patents
Fishery resource abundance gray prediction model optimization method and application thereof Download PDFInfo
- Publication number
- CN111667112B CN111667112B CN202010497152.2A CN202010497152A CN111667112B CN 111667112 B CN111667112 B CN 111667112B CN 202010497152 A CN202010497152 A CN 202010497152A CN 111667112 B CN111667112 B CN 111667112B
- Authority
- CN
- China
- Prior art keywords
- model
- month
- site
- months
- surface temperature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000005457 optimization Methods 0.000 title claims abstract description 28
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 238000010219 correlation analysis Methods 0.000 claims abstract description 4
- 229930002875 chlorophyll Natural products 0.000 claims description 72
- 235000019804 chlorophyll Nutrition 0.000 claims description 72
- ATNHDLDRLWWWCB-AENOIHSZSA-M chlorophyll a Chemical compound C1([C@@H](C(=O)OC)C(=O)C2=C3C)=C2N2C3=CC(C(CC)=C3C)=[N+]4C3=CC3=C(C=C)C(C)=C5N3[Mg-2]42[N+]2=C1[C@@H](CCC(=O)OC\C=C(/C)CCC[C@H](C)CCC[C@H](C)CCCC(C)C)[C@H](C)C2=C5 ATNHDLDRLWWWCB-AENOIHSZSA-M 0.000 claims description 72
- 230000009514 concussion Effects 0.000 claims description 34
- 241000251468 Actinopterygii Species 0.000 claims description 22
- 230000015654 memory Effects 0.000 claims description 6
- 238000013480 data collection Methods 0.000 claims description 4
- 230000010355 oscillation Effects 0.000 claims description 2
- 230000007547 defect Effects 0.000 abstract description 5
- 238000004519 manufacturing process Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 241000894007 species Species 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Husbandry (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Agronomy & Crop Science (AREA)
- Development Economics (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Farming Of Fish And Shellfish (AREA)
Abstract
The invention discloses a fishery resource abundance grey prediction model optimization method and application thereof, comprising the following steps: the CPUE sequence is preferably used as a standard sequence for establishing a gray prediction model of the resource abundance; aiming at a standard sequence, using a gray correlation analysis method, calculating gray correlation of influence factors of the resource abundance and selecting the influence factors with large gray correlation as factors of a gray prediction model of the resource abundance; establishing a resource abundance gray prediction model by using a discrete GM model and adopting selected factors, wherein the established resource abundance gray prediction model comprises a GM (0, N) model and a GM (1, N) model; and carrying out validity analysis on each prediction model, and selecting the model with the minimum relative error as the optimal prediction model. According to the prediction method, the CPUE sequence is optimized, so that the defect of poor prediction stability of the current gray system model is overcome; GM models with different orders are established, and an optimal prediction model is obtained from the GM models preferably, so that the prediction precision is improved.
Description
Technical Field
The invention belongs to the technical field of ocean fishing flood prediction, relates to a fishery resource abundance grey prediction model optimization method and application thereof, and in particular relates to a fishery resource abundance grey prediction model optimization method based on environmental factors and application thereof.
Background
The fishes at middle and upper layers are important economic species, and the change of the abundance of the resources is very closely related to factors such as climate, marine environment and the like. The resource abundance prediction is one of main prediction contents in the fish condition prediction, and the scientific prediction of the resource quantity and the evaluation of the resource abundance are beneficial to sustainable utilization and scientific management of fishery resources. The problem of too little sample size and too many environmental factors related to forecasting is generally encountered in building a fish-condition forecasting model, particularly in forecasting the abundance of resources among years, and the two problems are the difficulty in building a resource abundance forecasting model.
Gray system theory is a discipline of uncertain system theory, which has the advantage of allowing a smaller number of samples and obeying arbitrary distribution relative to other research methods (multiple linear regression, multiple nonlinear regression, and habitat index). At present, although the method is applied to the resource abundance prediction of some economic types, the method still has the problems of low prediction precision, poor stability and the like.
Therefore, the development of the resource abundance prediction method based on the gray system theory, which has high prediction precision and high stability, has very practical significance.
Disclosure of Invention
The invention aims to overcome the defects of low prediction precision and poor stability in the prior art and provides a resource abundance prediction method with high prediction precision and high stability based on a gray system theory.
In order to achieve the above purpose, the present invention provides the following technical solutions:
the fishery resource abundance grey prediction model optimization method is applied to electronic equipment and comprises the following steps:
(1) Aiming at CPUE sequences of fish C in sea area B in time period A, intercepting CPUE sequences in any time period, establishing a GM (1, 1) model corresponding to each intercepted CPUE sequence, establishing m GM (1, 1) models, respectively calculating relative errors of each GM (1, 1) model, and selecting a CPUE sequence corresponding to the GM (1, 1) model with the minimum relative error as a standard sequence for establishing a gray prediction model of resource abundance;
(2) Aiming at the standard sequence selected in the step (1), calculating and obtaining the gray correlation degree of the influence factors of the resource abundance by using a gray correlation analysis method;
(3) Selecting an influence factor with large gray correlation as a factor of a resource abundance gray prediction model;
(4) Utilizing a discrete GM model, adopting factors selected in the step (3) to establish a resource abundance gray prediction model, wherein the established resource abundance gray prediction model comprises a GM (0, N) model and a GM (1, N) model, and the GM (0, N) model and the GM (1, N) model are both linear dynamic models, wherein the GM (1, N) model is a first derivative calculation model, and compared with the GM (0, N) model, the calculation is more complicated, and meanwhile, the establishment of different-order GM prediction models can provide more models for later optimization, and then an optimal model is selected from the model to improve the prediction precision of the model;
(5) And (3) carrying out validity analysis on the prediction model obtained in the step (4), wherein the validity analysis comprises relative error analysis, the relative error is obtained by comparing a CPUE value calculated by using the prediction model with a real CPUE value, and a model with the minimum relative error is selected as an optimal prediction model.
According to the fishery resource abundance gray prediction model optimization method, before processing (before establishing a resource abundance gray prediction model), CPUE sequences are optimized, CPUE sequences in any time period are intercepted, GM (1, 1) models are established, CPUE sequences corresponding to the GM (1, 1) models with the minimum relative error are selected as standard sequences for subsequently establishing the resource abundance gray prediction model, the defect of poor prediction stability of the current gray system model is overcome to a certain extent, then when establishing the resource abundance gray prediction model, 0-order and 1-order GM prediction models containing different influence factors are established, and a model with the minimum relative error is optimized from a plurality of prediction models with different orders to serve as an optimal prediction model, so that the accuracy of the prediction model is greatly improved, and a basis is provided for more scientific and more effective fishery production. The method can be used for predicting middle-upper layer fishes in the ocean, has good applicability, can play a good guiding role in marine fishery production, can remarkably improve the fishing efficiency, reduces the fishing cost and has great application prospect, meanwhile, the obtained optimal prediction model is not invariable, and can be obtained again according to the latest data acquired in real time.
As a preferable technical scheme:
the optimization method of the gray prediction model of the abundance of the fishery resources is as described above, wherein the time period A is 1998-2016; the coordinate range of the sea area B is 35-45 degrees N, 140-179 degrees E; the fish C is North Pacific ocean soft fish. The protective scope of the invention is not limited to this, and the prediction method of the invention can be applied to the resource abundance prediction of the upper-layer fish in any time zone and any sea area by taking the fish in the time zone and the sea area as an example.
According to the optimization method of the fishery resource abundance gray prediction model, the standard sequence for establishing the resource abundance gray prediction model is a CPUE sequence of North Pacific soft fish with the coordinate range of 35-45 degrees N and 140-179 degrees E in 1998-2005. The standard sequence for establishing the gray prediction model of the resource abundance is selected based on the data, and a person skilled in the art can select an appropriate CPUE sequence as the standard sequence according to the actual data.
According to the optimization method of the gray prediction model of the fishery resource abundance, the relative errors of the GM (1, 1) models obtained in the step (1) are the same and are the minimum, and the corresponding CPUE sequence of the model with the minimum variance of the models is selected as the standard sequence for building the gray prediction model of the resource abundance.
The fishery resource abundance grey prediction model optimization method comprises the following steps of influencing factors of resource abundance including pacific annual concussion index (PDO), sea surface temperature of spawning sites (SGSST), sea surface temperature of fattening sites (FGST), chlorophyll concentration of spawning Sites (SGC) and chlorophyll concentration of fattening sites (FGC). The scope of the invention is not limited thereto, and the influencing factors of the abundance of the resources given herein correspond only to the Pacific ocean fish, and for other fish, the influencing factors of the abundance of the resources can be reasonably selected by those skilled in the art according to practical situations.
The optimization method of the gray prediction model for the abundance of the fishery resources comprises the following steps: and (3) taking the standard sequence selected in the step (1) as a parent sequence, taking corresponding influence factors as subsequences, and respectively calculating gray absolute association degrees of each subsequence and the parent sequence.
The resource abundance gray prediction model optimization method comprises the steps of respectively obtaining sea surface temperature (FGST) of a fattening field of 10 months, annual concussion index (PDO) of the pacific in 10 months, sea surface temperature (SGSST) of an spawning field of 2 months, chlorophyll concentration (SGC) of a spawning field of 3 months and chlorophyll concentration (FGC) of a fattening field of 8 months. The prediction models mentioned herein and hereinafter are merely examples of the operation logic of the prediction method of the present invention with some data, the protection scope of the present invention is not limited thereto, and a person skilled in the art may select appropriate data to predict the abundance of resources according to actual needs, where the factors of the selected abundance gray prediction models are not limited to these 5, and the number of the prediction models will also vary according to the number of factors of the selected abundance gray prediction models.
The optimization method of the gray prediction model of the fishery resource abundance, which is described above, is characterized in that the established gray prediction model of the resource abundance comprises the following models:
model I, GM (0, 6) models comprising five factors of sea surface temperature (fgst) for a 10 month fattening site, pacific annual concussion index (PDO) for 10 months, sea surface temperature (SGSST) for a 2 month spawning site, chlorophyll concentration (SGC) for a 3 month spawning site, and chlorophyll concentration (FGC) for an 8 month fattening site;
model II, including the GM (0, 5) model of four factors of sea surface temperature (fgst) for a 10 month fattening site, the pacific annual concussion index (PDO) for 10 months, chlorophyll concentration (SGC) for a 3 month spawning site, and chlorophyll concentration (FGC) for an 8 month fattening site;
model III, GM (0, 5) model comprising four factors of 10 months pacific annual concussion index (PDO), sea surface temperature of 2 months Spawning Ground (SGSST), chlorophyll concentration of 3 months Spawning Ground (SGC), and chlorophyll concentration of 8 months Fattening Ground (FGC);
model IV, including the GM (0, 5) model of four factors of sea surface temperature (fgst) for a 10 month fattening site, the pacific annual concussion index (PDO) for 10 months, sea surface temperature (SGSST) for a 2 month spawning site, and chlorophyll concentration (FGC) for an 8 month fattening site;
model V, GM (0, 5) model comprising four factors of sea surface temperature (fgst) for a 10 month fattening site, pacific annual concussion index (PDO) for 10 months, sea surface temperature (SGSST) for a 2 month spawning site, and chlorophyll concentration (SGC) for a 3 month spawning site;
model VI, GM (0, 5) model comprising four factors of sea surface temperature at 10 month fattening site (fgst), sea surface temperature at 2 month spawning site (SGSST), chlorophyll concentration at 3 month spawning Site (SGC), and chlorophyll concentration at 8 month fattening site (FGC);
model VII, comprising five factor GM (1, 6) models of sea surface temperature of 10 month fattening site (fgst), 10 month pacific annual concussion index (PDO), sea surface temperature of 2 month spawning site (SGSST), chlorophyll concentration of 3 month spawning Site (SGC), and chlorophyll concentration of 8 month fattening site (FGC);
model VIII, GM (1, 5) models comprising four factors of sea surface temperature (fgst) for a 10 month fattening site, pacific annual concussion index (PDO) for 10 months, chlorophyll concentration (SGC) for a 3 month spawning site, and chlorophyll concentration (FGC) for an 8 month fattening site;
model IX, GM (1, 5) models comprising four factors of 10 months pacific annual concussion index (PDO), sea surface temperature of 2 months Spawning Ground (SGSST), chlorophyll concentration of 3 months Spawning Ground (SGC), and chlorophyll concentration of 8 months Fattening Ground (FGC);
model X, GM (1, 5) models comprising four factors of sea surface temperature (fgst) for a 10 month fattening site, the pacific annual concussion index (PDO) for 10 months, sea surface temperature (SGSST) for a 2 month spawning site, and chlorophyll concentration (FGC) for an 8 month fattening site;
model XI, GM (1, 5) models comprising four factors of sea surface temperature (fgst) for a 10 month fattening site, pacific annual concussion index (PDO) for 10 months, sea surface temperature (SGSST) for a 2 month spawning site, and chlorophyll concentration (SGC) for a 3 month spawning site;
model XII, comprising GM (1, 5) models of four factors, sea surface temperature at 10 months of fattening site (fgst), sea surface temperature at 2 months of spawning site (SGSST), chlorophyll concentration at 3 months of spawning Site (SGC), and chlorophyll concentration at 8 months of fattening site (FGC).
According to the fishery resource abundance grey prediction model optimization method, model IV is the optimal prediction model. On the basis of conforming to the common knowledge in the field, the above preferred conditions can be arbitrarily combined to obtain the preferred examples of the invention.
The invention also provides an electronic device comprising one or more processors, one or more memories, one or more programs and a data collection device;
the data collection device is used for obtaining the CPUE sequence of the fish C in the sea area B in the time period A, the one or more programs are stored in the memory, and when the one or more programs are executed by the processor, the electronic equipment is caused to execute the fishery resource abundance grey prediction model optimization method.
The beneficial effects are that:
(1) According to the fishery resource abundance gray prediction model optimization method, before processing (before establishing a resource abundance gray prediction model), CPUE sequences are optimized firstly, CPUE sequences in any time period are intercepted, GM (1, 1) models are established, CPUE sequences corresponding to the GM (1, 1) models with the minimum relative error are selected as standard sequences for establishing the resource abundance gray prediction model subsequently, and the defect of poor prediction stability of the existing gray system model is overcome to a certain extent;
(2) According to the optimization method for the gray prediction model of the fishery resource abundance, when the gray prediction model of the resource abundance is built, GM prediction models of 0 order and 1 order containing different influence factors are built at the same time, and the model with the minimum relative error is optimized from a plurality of prediction models of different orders to serve as the optimal prediction model, so that the precision of the prediction model can be greatly improved, and a basis is provided for more scientific and more effective fishery production;
(3) The electronic equipment disclosed by the invention is simple in structure and low in cost, and can be used for rapidly predicting the abundance of marine fishery resources.
Drawings
FIG. 1 is a flow diagram of an optimization method of a gray prediction model of fishery resource abundance;
FIG. 2 is a graph of the relative error of multiple GM (1, 1) models in step (1);
FIG. 3 is a graph showing average relative error of the prediction models in step (6);
FIG. 4 is a fitting graph of predicted values of an optimal prediction model;
fig. 5 is a schematic structural diagram of an electronic device according to the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
A fishery resource abundance grey prediction model optimization method is shown in figure 1, and specifically comprises the following steps:
(1) For 1998-2016, CPUE (per year of fishing effort) sequences of North Pacific soft fishes in the coordinate ranges of 35-45 DEG N and 140-179 DEG E, wherein the CPUE is calculated according to the 1998-2016 years including date, longitude, latitude, daily yield (per ton) and fishing effort (per ship number), the coordinate ranges of 35-45 DEG N and 140-179 DEG E, the CPUE sequences of any time period are intercepted, a GM (1, 1) model is built corresponding to each intercepted CPUE sequence, m GM (1, 1) models are built, the relative error of each GM (1, 1) model is calculated respectively, selecting a CPUE sequence corresponding to a GM (1, 1) model with the smallest relative error as a standard sequence for establishing a resource abundance grey prediction model, if the relative errors of a plurality of GM (1, 1) models are the same and are the smallest, selecting the corresponding CPUE sequence of the model with the smallest variance of the models as the standard sequence for establishing the resource abundance grey prediction model, wherein the relative error diagram of the selected plurality of GM (1, 1) models is shown as figure 2, so that the CPUE sequence (the average relative error is the smallest and is 6.28%) of North Pacific soft fish with the coordinate range of 35-45 DEG N and 140-179 DEG E is finally selected as the standard sequence for establishing the resource abundance grey prediction model in 1998-2005;
(2) Aiming at the standard sequence selected in the step (1), calculating to obtain the gray correlation degree of the influence factors of the resource abundance by using a gray correlation analysis method, specifically, taking the standard sequence selected in the step (1) as a parent sequence, taking the corresponding influence factors as child sequences, and respectively calculating the gray absolute correlation degree of each child sequence and the parent sequence (the gray correlation coefficient of each obtained influence factor child sequence and the CPUE parent sequence is shown in a table 1), wherein the influence factors of the resource abundance comprise the Pacific annual oscillation index (PDO), the sea surface temperature of an spawning site (SGSST), the sea surface temperature of a fattening site (FGST), the chlorophyll concentration of the spawning Site (SGC) and the chlorophyll concentration of the fattening site (FGC);
TABLE 1 Gray correlation coefficient of each influence factor subsequence and CPUE parent sequence
(3) As can be seen from table 1, the influence factors with a large gray correlation degree are sea surface temperature (fgst) of a fattening site of 10 months, sea surface temperature (SGSST) of a pacific annual concussion index of 10 months, sea surface temperature (SGSST) of an spawning site of 2 months, chlorophyll concentration (SGC) of a spawning site of 3 months and chlorophyll concentration (FGC) of a fattening site of 8 months, so that the above influence factors are selected as factors of a resource abundance gray prediction model;
(4) Establishing a resource abundance gray prediction model by using a discrete GM model and adopting factors selected in the step (3), wherein the established resource abundance gray prediction model comprises a GM (0, N) model and a GM (1, N) model, and specifically comprises the following models:
model I, GM (0, 6) models comprising five factors of sea surface temperature (fgst) for a 10 month fattening site, pacific annual concussion index (PDO) for 10 months, sea surface temperature (SGSST) for a 2 month spawning site, chlorophyll concentration (SGC) for a 3 month spawning site, and chlorophyll concentration (FGC) for an 8 month fattening site;
model II, including the GM (0, 5) model of four factors of sea surface temperature (fgst) for a 10 month fattening site, the pacific annual concussion index (PDO) for 10 months, chlorophyll concentration (SGC) for a 3 month spawning site, and chlorophyll concentration (FGC) for an 8 month fattening site;
model III, GM (0, 5) model comprising four factors of 10 months pacific annual concussion index (PDO), sea surface temperature of 2 months Spawning Ground (SGSST), chlorophyll concentration of 3 months Spawning Ground (SGC), and chlorophyll concentration of 8 months Fattening Ground (FGC);
model IV, including the GM (0, 5) model of four factors of sea surface temperature (fgst) for a 10 month fattening site, the pacific annual concussion index (PDO) for 10 months, sea surface temperature (SGSST) for a 2 month spawning site, and chlorophyll concentration (FGC) for an 8 month fattening site;
model V, GM (0, 5) model comprising four factors of sea surface temperature (fgst) for a 10 month fattening site, pacific annual concussion index (PDO) for 10 months, sea surface temperature (SGSST) for a 2 month spawning site, and chlorophyll concentration (SGC) for a 3 month spawning site;
model VI, GM (0, 5) model comprising four factors of sea surface temperature at 10 month fattening site (fgst), sea surface temperature at 2 month spawning site (SGSST), chlorophyll concentration at 3 month spawning Site (SGC), and chlorophyll concentration at 8 month fattening site (FGC);
model VII, comprising five factor GM (1, 6) models of sea surface temperature of 10 month fattening site (fgst), 10 month pacific annual concussion index (PDO), sea surface temperature of 2 month spawning site (SGSST), chlorophyll concentration of 3 month spawning Site (SGC), and chlorophyll concentration of 8 month fattening site (FGC);
model VIII, GM (1, 5) models comprising four factors of sea surface temperature (fgst) for a 10 month fattening site, pacific annual concussion index (PDO) for 10 months, chlorophyll concentration (SGC) for a 3 month spawning site, and chlorophyll concentration (FGC) for an 8 month fattening site;
model IX, GM (1, 5) models comprising four factors of 10 months pacific annual concussion index (PDO), sea surface temperature of 2 months Spawning Ground (SGSST), chlorophyll concentration of 3 months Spawning Ground (SGC), and chlorophyll concentration of 8 months Fattening Ground (FGC);
model X, GM (1, 5) models comprising four factors of sea surface temperature (fgst) for a 10 month fattening site, the pacific annual concussion index (PDO) for 10 months, sea surface temperature (SGSST) for a 2 month spawning site, and chlorophyll concentration (FGC) for an 8 month fattening site;
model XI, GM (1, 5) models comprising four factors of sea surface temperature (fgst) for a 10 month fattening site, pacific annual concussion index (PDO) for 10 months, sea surface temperature (SGSST) for a 2 month spawning site, and chlorophyll concentration (SGC) for a 3 month spawning site;
model XII, GM (1, 5) model comprising four factors of sea surface temperature of 10 month fattening site (fgst), sea surface temperature of 2 month spawning site (SGSST), chlorophyll concentration of 3 month spawning Site (SGC), and chlorophyll concentration of 8 month fattening site (FGC);
(5) Carrying out validity analysis on each prediction model obtained in the step (4), and verifying by utilizing fishery production data in 2006, wherein verification results are shown in tables 2 and 3, average relative error comparison diagrams of each prediction model are shown in fig. 3, models 1-6 on the left side in fig. 3 are respectively in one-to-one correspondence with models I-VI in the step (4), and models 1-6 on the right side are respectively in one-to-one correspondence with models VII-XII in the step (4);
TABLE 2 relative error of North Pacific ocean Soft Fish resource abundance GM (0, N) predictive model
TABLE 3 relative error of the North Pacific ocean Soft Fish resource abundance GM (1, N) predictive model
The "errors" in tables 2 and 3 are relative error averages, and the "verification" is the error rate of the data of fishery production in 2006 and the actual data of fishery production in 2006, which are predicted using the model, and the units in the tables are;
as can be seen from fig. 2, GM (0, n) and GM (1, n) prediction models with added environmental factors are almost all more accurate than the fitting of GM (1, 1) models (except model XII) and the gray prediction models of 0 th order are all more accurate than the fitting of 1 st order.
As can be seen from tables 2 and 3, the average fitting error of the models in each GM (0, n) model is, in order from large to small: model I > model III > model II > model V > model IV > model VI; the model average fitting error of each GM (1, N) model is from small to large: model X > model VII > model VIII > model IX > model XI > model XII; from the verification results, model IV and model X were far higher than the other models with relative errors of 1.18% (lowest) and 1.20%, so model IV was chosen as the optimal predictive model for the abundance of north pacific soft fish resources.
The model IV is selected for prediction, the prediction fitting diagram is shown in fig. 4, the variation trend of CPUE is basically consistent, the variation range of the fitting value of the model prediction is small, and the value-a is-1.71 (table 4) in terms of the parameters of the prediction model and meets the condition (-a < 0.3) of the medium-long term prediction model.
TABLE 4 parameter values of factors for model IV
According to the prediction method, before processing (before establishing a resource abundance gray prediction model), CPUE sequences are optimized firstly, CPUE sequences in any time period are intercepted, GM (1, 1) models are established, CPUE sequences corresponding to the GM (1, 1) models with the minimum relative error are selected as standard sequences for subsequently establishing the resource abundance gray prediction model, and the defect of poor prediction stability of the current gray system model is overcome; when the gray prediction model of the resource abundance is built, GM prediction models of 0 order and 1 order containing different influencing factors are built at the same time, and a model with the smallest relative error is optimized from a plurality of prediction models of different orders to serve as an optimal prediction model, so that the precision of the prediction model can be greatly improved, a basis is provided for more scientific and more effective fishery production, and the method has a great application prospect.
Example 2
An electronic device, as shown in FIG. 5, includes one or more processors, one or more memories, one or more programs, and data gathering means;
the data collection device is used for obtaining the CPUE sequence of the sea area B fish C in the time period A (namely, the CPUE sequence of the North Pacific soft fish in the coordinate range of 35-45 DEG N and 140-179 DEG E in 1998-2016 in the embodiment 1), one or more programs are stored in the memory, and when the one or more programs are executed by the processor, the electronic equipment is caused to execute the fishery resource abundance gray prediction model optimization method as described in the embodiment 1.
While particular embodiments of the present invention have been described above, it will be understood by those skilled in the art that these are by way of example only and that various changes or modifications may be made to these embodiments without departing from the principles and spirit of the invention.
Claims (10)
1. The fishery resource abundance grey prediction model optimization method is applied to electronic equipment and is characterized by comprising the following steps of:
(1) Aiming at CPUE sequences of fish C in sea area B in time period A, intercepting CPUE sequences in any time period, establishing a GM (1, 1) model corresponding to each intercepted CPUE sequence, establishing m GM (1, 1) models, respectively calculating relative errors of each GM (1, 1) model, and selecting a CPUE sequence corresponding to the GM (1, 1) model with the minimum relative error as a standard sequence for establishing a gray prediction model of resource abundance;
(2) Aiming at the standard sequence selected in the step (1), calculating and obtaining the gray correlation degree of the influence factors of the resource abundance by using a gray correlation analysis method;
(3) Selecting an influence factor with large gray correlation as a factor of a resource abundance gray prediction model;
(4) Establishing a resource abundance gray prediction model by using the discrete GM model and adopting the factors selected in the step (3), wherein the established resource abundance gray prediction model comprises a GM (0, N) model and a GM (1, N) model;
(5) And (3) carrying out validity analysis on the prediction model obtained in the step (4), wherein the validity analysis comprises relative error analysis, the relative error is obtained by comparing a CPUE value calculated by using the prediction model with a real CPUE value, and a model with the minimum relative error is selected as an optimal prediction model.
2. The optimization method of the gray prediction model for the abundance of the fishery resources according to claim 1, wherein the time period A is 1998-2016; the coordinate range of the sea area B is 35-45 degrees N, 140-179 degrees E; the fish C is North Pacific ocean soft fish.
3. The optimization method of the gray prediction model for the abundance of the fishery resources according to claim 2, wherein the standard sequence for establishing the gray prediction model for the abundance of the resources is a CPUE sequence of North Pacific ocean soft fish with a coordinate range of 35-45 DEG N and 140-179 DEG E in 1998-2005.
4. The optimization method of gray prediction model for fishery resource abundance according to claim 3, wherein the relative errors of the GM (1, 1) models obtained in the step (1) are the same and are the minimum, and the corresponding CPUE sequences of the models with the smallest variance are selected as the standard sequences for building the gray prediction model for resource abundance.
5. The method for optimizing gray prediction model of fishery resource abundance according to claim 4, wherein the influencing factors of the resource abundance comprise pacific annual concussion index, sea surface temperature of spawning sites, sea surface temperature of fattening sites, chlorophyll concentration of spawning sites and chlorophyll concentration of fattening sites.
6. The optimization method of the gray prediction model for the abundance of fishery resources according to claim 5, wherein the step (2) is specifically: and (3) taking the standard sequence selected in the step (1) as a parent sequence, taking corresponding influence factors as subsequences, and respectively calculating gray absolute association degrees of each subsequence and the parent sequence.
7. The method for optimizing the gray prediction model of the abundance of the fishery resources according to claim 6, wherein factors of the gray prediction model of the abundance of the resources are sea surface temperature of a fattening field of 10 months, the annual oscillation index of the pacific for 10 months, sea surface temperature of an spawning field of 2 months, chlorophyll concentration of a spawning field of 3 months and chlorophyll concentration of a fattening field of 8 months respectively.
8. The method for optimizing the gray prediction model of the abundance of the fishery resources according to claim 7, wherein the established gray prediction model of the abundance of the resources comprises the following models:
model I, comprising a GM (0, 6) model of five factors of sea surface temperature at a 10 month fattening site, a 10 month pacific annual concussion index, a sea surface temperature at a 2 month spawning site, chlorophyll concentration at a 3 month spawning site, and chlorophyll concentration at an 8 month fattening site;
model II, comprising a GM (0, 5) model of four factors of sea surface temperature of a 10 month fattening site, pacific annual concussion index of 10 months, chlorophyll concentration of a 3 month spawning site, and chlorophyll concentration of an 8 month fattening site;
model III, GM (0, 5) model comprising four factors of the pacific annual concussion index of 10 months, the sea surface temperature of 2 months spawning ground, chlorophyll concentration of 3 months spawning ground, and chlorophyll concentration of 8 months fattening ground;
model IV, including a GM (0, 5) model of sea surface temperature of a 10 month fattening site, a 10 month pacific annual concussion index, sea surface temperature of a 2 month spawning site (and chlorophyll concentration of an 8 month fattening site by four factors);
model V, GM (0, 5) model comprising four factors of sea surface temperature at 10 month fattening site, pacific annual concussion index at 10 month, sea surface temperature at 2 month spawning site, and chlorophyll concentration at 3 month spawning site;
model VI, GM (0, 5) model comprising four factors of sea surface temperature at 10 month fattening site, sea surface temperature at 2 month spawning site, chlorophyll concentration at 3 month spawning site, and chlorophyll concentration at 8 month fattening site;
model VII, comprising a GM (1, 6) model of five factors of sea surface temperature at 10 month fattening sites, pacific annual concussion index at 10 months, sea surface temperature at 2 months spawning sites, chlorophyll concentration at 3 months spawning sites, and chlorophyll concentration at 8 month fattening sites;
model VIII, GM (1, 5) model comprising four factors of sea surface temperature at 10 month fattening site, pacific annual concussion index at 10 months, chlorophyll concentration at 3 months spawning site, and chlorophyll concentration at 8 months fattening site;
model IX, comprising a GM (1, 5) model of four factors of the pacific annual concussion index of 10 months, the sea surface temperature of 2 months spawning ground, the chlorophyll concentration of 3 months spawning ground, and the chlorophyll concentration of 8 months fattening ground;
model X, including four factors GM (1, 5) model for sea surface temperature of 10 month fattening site, 10 month pacific annual concussion index, sea surface temperature of 2 month spawning site, and chlorophyll concentration of 8 month fattening site;
model XI, including four factors GM (1, 5) model of sea surface temperature of fattening site of 10 months, annual concussion index of Pacific of 10 months, sea surface temperature of spawning site of 2 months and chlorophyll concentration of spawning site of 3 months;
model XII, comprising a GM (1, 5) model of four factors of sea surface temperature at 10 month fattening site, sea surface temperature at 2 month spawning site, chlorophyll concentration at 3 month spawning site, and chlorophyll concentration at 8 month fattening site.
9. The method for optimizing the gray prediction model of the abundance of fishery resources according to claim 8, wherein the model IV is an optimal prediction model.
10. An electronic device comprising one or more processors, one or more memories, one or more programs, and data gathering means;
the data collection device is configured to obtain a CPUE sequence of fish C in sea area B within a time period a, the one or more programs are stored in the memory, and when the one or more programs are executed by the processor, the electronic device is caused to perform a fishery resource abundance gray prediction model optimization method according to any one of claims 1-9.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010497152.2A CN111667112B (en) | 2020-06-04 | 2020-06-04 | Fishery resource abundance gray prediction model optimization method and application thereof |
| NL2027468A NL2027468B1 (en) | 2020-06-04 | 2021-02-01 | Method for optimizing a resource abundance grey prediction model in fishery and application thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010497152.2A CN111667112B (en) | 2020-06-04 | 2020-06-04 | Fishery resource abundance gray prediction model optimization method and application thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111667112A CN111667112A (en) | 2020-09-15 |
| CN111667112B true CN111667112B (en) | 2023-12-26 |
Family
ID=72385881
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010497152.2A Active CN111667112B (en) | 2020-06-04 | 2020-06-04 | Fishery resource abundance gray prediction model optimization method and application thereof |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111667112B (en) |
| NL (1) | NL2027468B1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7202709B2 (en) * | 2020-09-24 | 2023-01-12 | 上海海洋大学 | Prediction method of peak season for saltwater fish based on gray system theory and its application |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103050230A (en) * | 2012-12-13 | 2013-04-17 | 广东电网公司电力科学研究院 | Method for increasing breakdown voltage of transformer oil |
| CN104794550A (en) * | 2015-05-13 | 2015-07-22 | 山东科技大学 | WT-KPCA-SVR coupling model based gas emission quantity prediction method |
| CN104850916A (en) * | 2015-05-31 | 2015-08-19 | 上海电机学院 | Improved-gray-Markov-model-based power equipment fault prediction method |
| CN106203686A (en) * | 2016-06-30 | 2016-12-07 | 上海海洋大学 | The raw colony in northwest Pacific squid Winter-Spring based on gray system abundance Forecasting Methodology |
| CN109523071A (en) * | 2018-11-02 | 2019-03-26 | 上海海洋大学 | Saury resource abundance medium- and long-term forecasting method based on Pacific Ocean Oscillation Index |
-
2020
- 2020-06-04 CN CN202010497152.2A patent/CN111667112B/en active Active
-
2021
- 2021-02-01 NL NL2027468A patent/NL2027468B1/en active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103050230A (en) * | 2012-12-13 | 2013-04-17 | 广东电网公司电力科学研究院 | Method for increasing breakdown voltage of transformer oil |
| CN104794550A (en) * | 2015-05-13 | 2015-07-22 | 山东科技大学 | WT-KPCA-SVR coupling model based gas emission quantity prediction method |
| CN104850916A (en) * | 2015-05-31 | 2015-08-19 | 上海电机学院 | Improved-gray-Markov-model-based power equipment fault prediction method |
| CN106203686A (en) * | 2016-06-30 | 2016-12-07 | 上海海洋大学 | The raw colony in northwest Pacific squid Winter-Spring based on gray system abundance Forecasting Methodology |
| WO2018001338A1 (en) * | 2016-06-30 | 2018-01-04 | 上海海洋大学 | Grey system-based pelagic squid resource richness forecasting method |
| CN109523071A (en) * | 2018-11-02 | 2019-03-26 | 上海海洋大学 | Saury resource abundance medium- and long-term forecasting method based on Pacific Ocean Oscillation Index |
Non-Patent Citations (3)
| Title |
|---|
| Lan, KW 等.Effects of climate variability and climate change on the fishing conditions for grey mullet (Mugil cephalus L.) in the Taiwan Strait.2014,第126卷(第1-2期),全文. * |
| 基于灰色系统的太平洋褶柔鱼冬春生群资源丰度变化研究;解明阳;陈新军;汪金涛;;海洋渔业(第06期);全文 * |
| 王言丰.基于灰色系统西南大西洋阿根廷滑柔鱼 资源丰度预测模型的构建.海 洋 学 报.2019,第41卷(第4期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111667112A (en) | 2020-09-15 |
| NL2027468B1 (en) | 2021-07-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2018001338A1 (en) | Grey system-based pelagic squid resource richness forecasting method | |
| Hillier et al. | Greenhouse gas emissions from four bioenergy crops in England and Wales: integrating spatial estimates of yield and soil carbon balance in life cycle analyses | |
| Squires et al. | Technical change and the commons | |
| Hogue et al. | A multistep automatic calibration scheme for river forecasting models | |
| Leathwick et al. | Using multivariate adaptive regression splines to predict the distributions of New Zealand's freshwater diadromous fish | |
| Watters et al. | Decision‐making for ecosystem‐based management: evaluating options for a krill fishery with an ecosystem dynamics model | |
| Kristensen et al. | Estimating spatio-temporal dynamics of size-structured populations | |
| Cai et al. | Value of probabilistic weather forecasts: Assessment by real-time optimization of irrigation scheduling | |
| Thorson et al. | Spatial delay-difference models for estimating spatiotemporal variation in juvenile production and population abundance | |
| CN103218669A (en) | Intelligent live fish cultivation water quality comprehensive forecasting method | |
| CN110516856B (en) | Method for estimating ocean subsurface temperature based on convolutional neural network | |
| Dawson et al. | Long-term trends in reservoir water quality and quantity in two major river basins of the southern Great Plains | |
| Hill et al. | The use of CO 2 flux time series for parameter and carbon stock estimation in carbon cycle research | |
| Ariza et al. | Global decline of pelagic fauna in a warmer ocean | |
| Walsh et al. | Trade‐offs for data‐limited fisheries when using harvest strategies based on catch‐only models | |
| CN104217254A (en) | Construction method of quick forecasting operation system of fishery fishing condition | |
| Jackson et al. | A deterministic river temperature model to prioritize management of riparian woodlands to reduce summer maximum river temperatures | |
| Hordyk et al. | Misspecification in stock assessments: common uncertainties and asymmetric risks | |
| CN111667112B (en) | Fishery resource abundance gray prediction model optimization method and application thereof | |
| Jacobson et al. | Tools for estimating surplus production and F MSY in any stock assessment model | |
| CN114897264A (en) | Photovoltaic output interval prediction method under small sample scene based on transfer learning | |
| Liu et al. | Study of water quality response to water transfer patterns in the receiving basin and surrogate model | |
| Shen et al. | An artificial neural network-based data filling approach for smart operation of digital wastewater treatment plants | |
| Fu et al. | Simulation and forecasting of fishery weather based on statistical machine learning | |
| Fielder et al. | Large-scale fish movement affects metrics of management importance as indicated by quantitative stock assessment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |