CN107590549A - A kind of Japanese squid winter life group's resource abundance Forecasting Methodology - Google Patents
A kind of Japanese squid winter life group's resource abundance Forecasting Methodology Download PDFInfo
- Publication number
- CN107590549A CN107590549A CN201610536379.7A CN201610536379A CN107590549A CN 107590549 A CN107590549 A CN 107590549A CN 201610536379 A CN201610536379 A CN 201610536379A CN 107590549 A CN107590549 A CN 107590549A
- Authority
- CN
- China
- Prior art keywords
- winter
- japanese squid
- group
- sst
- marine
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Farming Of Fish And Shellfish (AREA)
Abstract
The invention provides a kind of Japanese squid winter life group's resource abundance Forecasting Methodology, including：1st, Japanese squid winter life group's spawning field marine marine environment factor Hai Biaowen acquisition；2nd, the SST time sequential values of sample point and corresponding Japanese squid CPUE values in spawning month spawning ground are calculated and does correlation analysis, selects the higher marine site of correlation；3rd, 6 higher marine site S1-S6 of continuous three middle of the month coefficient correlations are selected；4th, S1-S6 SST is established into the multiple linear forecasting model with CPUE；5th, by the descending sequence of 6 SST and CPUE coefficient correlation；The increase input factor builds four kinds of BP neural network forecasting models successively；6th, compare multiple linear forecasting model and 4 kinds of BP neural network forecasting models, choose forecast model of the BP neural network forecasting model of 641 structures as life of Japanese squid winter group's resource abundance.
Description
Technical field
The present invention relates to a kind of fishery forescast method, and group's resource abundance prediction side is given birth to more particularly to a kind of Japanese squid winter
Method.
Background technology
Fishery forescast is the key link of fish production, and the forecast that group's resource abundance is given birth to the Japanese squid winter was beneficial to day
The forecast and grasp of this squid winter life group yield, cental fishing ground position and fishing season.Growth and distribution of the temperature factor to Japanese squid
Have a very big impact, and study catch (CPUE, the unit for thinking sea surface temperature and the capture of unit fishing boat：Thousand tails/day)
Recurrence then has pole conspicuousness, and therefore, the predictor for giving birth to group's resource abundance as the Japanese squid winter by the use of Hai Biaowen is feasible.
Fishery forescast is also the emphasis of fisheriesx hydrography research.Accurate fishery forescast can instruct enterprise's reasonable arrangement fishery life
Production, shorten the time for finding fishing ground, reduce cost, improve fishery harvesting yield.China starts main to coastal waters the 1950s
Tuna fisheries carry out fishery forescast work, have accumulated rich experience.Since the 1980s, the development of GIS-Geographic Information System
Powerful analysis tool is provided for fishery stock assessment and fishing ground prediction research.The popularization of seasat remote sensing technology more causes people
Sea situation information in energy quick obtaining is a wide range of, real-time accommodation monitoring and marine satellite mechanics of communication enable ocean fishing vessel effective
Ground receives the real-time prediction of fishery forescast mechanism.
And with the exhaustion of China coastal seas resource, also as one of important composition of China's fishery, it is produced deep-sea fishing
While continuous expand, production cost also constantly raises scale, and accordingly, deep-sea fishing enterprise is to fishery forescast accuracy
It is required that also more and more higher, this has also researched and proposed new challenge for fishery forescast technology and forecasting model.In recent years, with existing
For statistical theory, numerical computation method, data mining and the development of artificial intelligence scheduling theory and technology, make traditional statistical fluctuation
Model is shining to have issued new vitality, and all kinds of machine learning methods also provide new thinking for the exploitation of fishery forescast model.
Because various forecasting procedures and model emerge in an endless stream, the scope of application of explanation is also different, can actually make to us
Cause to puzzle with these methods.Therefore, it is relatively suitable from which kind of forecasting model and method, the precision of which kind of forecasting model compared with
Height, then us are needed to be contrasted and selected；Equally, correct forecasting model is selected to effectively improve the production effect of fishing boat
Rate, while provide reference frame to the annual planning of enterprise.
The content of the invention
The problem of technical problems to be solved by the invention are to overcome in the presence of fishery forescast in the prior art, there is provided
One kind utilizes ocean remote sensing data, and egg-laying season spawning ground scope different time Hai Biaowen is analyzed by Time series analysis method
(SST) corresponding catch per unit effort (CPUE) carries out correlation analysis, choose correlation highest 6 because
Son, the size for being given birth to group's resource abundance to the Japanese squid winter using different forecasting models is forecast, and compares its forecast precision, most
Method of the 6-4-1 structures of selection BP neural network forecasting model as the size for predicting Japanese squid winter life group's resource abundance eventually.
Its technical problem to be solved can be implemented by the following technical programs.
A kind of Japanese squid winter life group's resource abundance Forecasting Methodology, comprises the following steps：
(1) Japanese squid winter life group spawning field marine marine environment factor Hai Biaowen SST, are obtained by remote sensing satellite；
(2) the SST time sequences of 1 ° of * 1 ° of sample point of longitude and latitude in the range of Japanese squid winter life group's spawning month spawning ground, are calculated
Train value and corresponding Japanese squid CPUE values do correlation analysis, select the higher marine site of correlation；
(3) continuous three middle of the month coefficient correlations higher 6 marine sites S1, S2, S3, S4, S5 and S6, are selected；
(4), by the correlation of selection higher marine site S1, S2, S3, S4, S5 and S6 SST, the polynary line with CPUE is established
Property forecasting model, its equation are：
Y=0.931X1-0.286X2-0.647X3-0.151X4+0.728X5+0.345X6-26.567
In formula：Y is CPUE, and unit is thousand tails/day；X1, X2, X3, X4, X5, X6 are S1, S2, S3, S4, S5, S6 respectively
SST, unit are DEG C；Each coefficient unit before X1-X6 is thousand tails/( DEG C of day)；
(5) SST in 6 marine sites of selection, is pressed into its order descending with CPUE coefficient correlation, from big to small
Sequence is respectively S3, S4, S5, S1, S6, S2；The increase input factor builds four kinds of BP neural network forecasting models successively, is respectively
3-2-1、4-3-1、5-4-1、6-4-1；
(6), compare multiple linear forecasting model and 4 kinds of BP neural network forecasting models, choose the BP nerves of 6-4-1 structures
Forecast model of the network forecasting model as life of Japanese squid winter group's resource abundance.
As the further improvement of the technical program, the higher 6 marine sites difference of continuous three middle of the month coefficient correlations
For the S1 and S2 of first month, S3 and S4, the trimestral S5 and S6 of second month.
The further improvement of the technical program is also served as, the position of the spawning field marine is：28 ° of N -40 ° N, 125 °
E—140°E。
As the preferred embodiments of the present invention, the spawning month is January to March.The 1-3 months are to give birth to group's spawning the Japanese squid winter
The control environment predictor of field.
The preferred embodiments of the present invention equally are used as, S1 position is：30.5 ° of N, 136.5 ° of E；S2 position is：31.5°
N, 136.5 ° of E；S3 position is：30.5 ° of N, 137.5 ° of E；S4 position is 30.5 ° of N, 135.5 ° of E；S5 position is：37.5°
N, 129.5 ° of E；S6 position is：37.5 ° of N, 130.5 ° of E.
Further improvement also as the technical program, the sample point totally 180.
The beneficial effects of the invention are as follows：The neural network structure forecast model is averaged to life of Japanese squid winter group's resource abundance
Explanation Accuracy reaches 98%.The forecast result of life of the Japanese squid winter group's resource abundance obtained by Forecasting Methodology of the present invention provides in time
After user and relevant departments, it can refer to for fish production and the science arranged, can also be sent out in real time as a kind of product
Cloth.
Embodiment
In order that the technical means, the inventive features, the objects and the advantages of the present invention are easy to understand, below will
The present invention is expanded on further.
The Japanese squid speed of growth is very fast, life cycle about 1 year or shorter, and winter life group's distribution is most wide, and its spawning ground is located at
Nine divisions of China in remote antiquity southwest THE DONGHAI SEA CONTINENTAL SHELF outer rim, the middle part and the north in the East Sea are concentrated mainly on, the egg-laying season is 1-March；1-3 months are also
The control environment predictor in Japanese squid winter life group spawning ground.
Japanese squid winter life group's resource abundance Forecasting Methodology provided by the invention, is mainly included the following steps that：
(1) Japanese squid winter life group's spawning field marine (28 ° of N -40 ° N, 125 ° of E -140 ° E) sea, is obtained by remote sensing satellite
Foreign envirment factor Hai Biaowen (SST)；
(2) it is (common, to calculate 1 ° of * 1 ° of sample point of longitude and latitude in the range of Japanese squid winter life group's spawning month (1-March) spawning ground
180 sample points) SST time sequential values and corresponding Japanese squid CPUE values do correlation analysis, it is higher to select correlation
Marine site；
(3) the higher marine site of coefficient correlation, is selected：January S1 (30.5 ° of N, 136.5 ° of E) and S2 (31.5 ° of N,
136.5°E)；The S3 (30.5 ° of N, 137.5 ° of E) and S4 (30.5 ° of N, 135.5 ° of E) in 2 months；March S5 (37.5 ° of N,
129.5 ° of E) and S6 (37.5 ° of N, 130.5 ° of E)；
(4), by the SST in the higher marine site of the correlation of selection (S1, S2, S3, S4, S5, S6), the polynary line with CPUE is established
Property forecasting model, its equation are：
Y=0.931X1-0.286X2-0.647X3-0.151X4+0.728X5+0.345X6-26.567
In formula：Y is CPUE, thousand tails of unit/day；X1, X2, X3, X4, X5, X6 are S1, S2, S3, S4, S5, S6 respectively
SST, unit are DEG C；Each coefficient unit is thousand tails/( DEG C of day)；
(5) SST in 6 marine sites of selection, is pressed into its order descending with CPUE coefficient correlation, from big to small
Sequence is respectively S3, S4, S5, S1, S6, S2.The increase input factor builds four kinds of BP neural network forecasting models successively, is respectively
3-2-1、4-3-1、5-4-1、6-4-1；
(6), compare multiple linear forecasting model and 4 kinds of BP neural network forecasting models, choose the BP nerves of 6-4-1 structures
Forecast model of the network forecasting model as life of Japanese squid winter group's resource abundance.
The foregoing describe general principle, main feature and the advantage of the present invention.It should be understood by those skilled in the art that this
Invention is not restricted to the described embodiments, merely illustrating the principles of the invention described in above-described embodiment and specification, not
Various changes and modifications of the present invention are possible on the premise of disengaging spirit and scope of the invention, and these changes and improvements are both fallen within will
Ask in the scope of the invention of protection.The claimed scope of the invention is defined by appended claims and its equivalent.
Claims (6)
1. a kind of Japanese squid winter life group's resource abundance Forecasting Methodology, it is characterised in that comprise the following steps：
(1) Japanese squid winter life group spawning field marine marine environment factor Hai Biaowen SST, are obtained by remote sensing satellite；
(2) the SST time sequential values of 1 ° of * 1 ° of sample point of longitude and latitude in the range of Japanese squid winter life group's spawning month spawning ground, are calculated
Correlation analysis is done with corresponding Japanese squid CPUE values, selects the higher marine site of correlation；
(3) continuous three middle of the month coefficient correlations higher 6 marine sites S1, S2, S3, S4, S5 and S6, are selected；
(4), by the correlation of selection higher marine site S1, S2, S3, S4, S5 and S6 SST, establish pre- with CPUE multiple linear
Model is reported, its equation is：
Y=0.931X1-0.286X2-0.647X3-0.151X4+0.728X5+0.345X6-26.567
In formula：Y is CPUE；X1, X2, X3, X4, X5, X6 are S1, S2, S3, S4, S5, S6 SST respectively；
(5) SST in 6 marine sites of selection, is pressed into its order descending with CPUE coefficient correlation, sequence from big to small
Respectively S3, S4, S5, S1, S6, S2；The increase input factor builds four kinds of BP neural network forecasting models, respectively 3-2- successively
1、4-3-1、5-4-1、6-4-1；
(6), compare multiple linear forecasting model and 4 kinds of BP neural network forecasting models, choose the BP neural network of 6-4-1 structures
Forecast model of the forecasting model as life of Japanese squid winter group's resource abundance.
2. Japanese squid winter life group's resource abundance Forecasting Methodology according to claim 1, it is characterised in that described continuous three
6 higher marine sites of middle of the month coefficient correlation are respectively S3 and S4, the trimestral S5 of the S1 and S2 of first month, second month
And S6.
3. Japanese squid winter life group's resource abundance Forecasting Methodology according to claim 1 or 2, it is characterised in that the spawning
The position of field marine is：28 ° of N -40 ° N, 125 ° of E -140 ° E.
4. Japanese squid winter life group's resource abundance Forecasting Methodology according to claim 1 or 2, it is characterised in that the spawning
Month is January to March.
5. Japanese squid winter life group's resource abundance Forecasting Methodology according to claim 3, it is characterised in that S1 position is：
30.5 ° of N, 136.5 ° of E；S2 position is：31.5 ° of N, 136.5 ° of E；S3 position is：30.5 ° of N, 137.5 ° of E；S4 position is
30.5 ° of N, 135.5 ° of E；S5 position is：37.5 ° of N, 129.5 ° of E；S6 position is：37.5 ° of N, 130.5 ° of E.
6. Japanese squid winter life group's resource abundance Forecasting Methodology according to claim 1, it is characterised in that the sample point is total to
180.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610536379.7A CN107590549A (en) | 2016-07-08 | 2016-07-08 | A kind of Japanese squid winter life group's resource abundance Forecasting Methodology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610536379.7A CN107590549A (en) | 2016-07-08 | 2016-07-08 | A kind of Japanese squid winter life group's resource abundance Forecasting Methodology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107590549A true CN107590549A (en) | 2018-01-16 |
Family
ID=61045111
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610536379.7A Pending CN107590549A (en) | 2016-07-08 | 2016-07-08 | A kind of Japanese squid winter life group's resource abundance Forecasting Methodology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107590549A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108520311A (en) * | 2018-03-07 | 2018-09-11 | 中国地质大学（武汉） | In conjunction with the haze prediction model method for building up and system of SOFM nets and BP neural network |
| CN109460860A (en) * | 2018-10-18 | 2019-03-12 | 上海海洋大学 | Argentinian squid Resources Prediction method based on Antarctic Oscillations index |
| CN109472405A (en) * | 2018-11-02 | 2019-03-15 | 上海海洋大学 | Japanese Qiu Shengqun squid resource abundance prediction technique based on Pacific Ocean concussion index |
| CN109523070A (en) * | 2018-11-02 | 2019-03-26 | 上海海洋大学 | Raw group squid resource abundance prediction technique of Japanese winter based on Pacific Ocean concussion index |
| 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 |
| CN109543878A (en) * | 2018-10-18 | 2019-03-29 | 上海海洋大学 | North Pacific's squid Resources Prediction method based on Pacific Ocean Oscillation Index |
| CN110533245A (en) * | 2019-08-30 | 2019-12-03 | 上海海洋大学 | A kind of sliding squid fishing ground amount prediction technique of Argentina based on Hai Biaowen |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103004664A (en) * | 2012-12-21 | 2013-04-03 | 上海海洋大学 | Method for forecasting northwest Pacific Ocean squids resource stock recruitment and application method thereof |
| CN103049659A (en) * | 2012-12-21 | 2013-04-17 | 上海海洋大学 | Method for forecasting stock recruitment of Peruvian open-sea Dosidicus gigas and method for applying same |
| CN103053450A (en) * | 2012-12-24 | 2013-04-24 | 上海海洋大学 | Southwest Atlantic illex argentinus resource supplement quantity forecasting method |
-
2016
- 2016-07-08 CN CN201610536379.7A patent/CN107590549A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103004664A (en) * | 2012-12-21 | 2013-04-03 | 上海海洋大学 | Method for forecasting northwest Pacific Ocean squids resource stock recruitment and application method thereof |
| CN103049659A (en) * | 2012-12-21 | 2013-04-17 | 上海海洋大学 | Method for forecasting stock recruitment of Peruvian open-sea Dosidicus gigas and method for applying same |
| CN103053450A (en) * | 2012-12-24 | 2013-04-24 | 上海海洋大学 | Southwest Atlantic illex argentinus resource supplement quantity forecasting method |
Non-Patent Citations (2)
| Title |
|---|
| 汪金涛 等: "基于产卵场环境因子的阿根廷滑柔鱼资源补充量预报模型研究", 《海洋学报》 * |
| 胡飞飞 等: "太平洋褶柔鱼秋生群资源补充量预报模型研究", 《广东海洋大学学报》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108520311A (en) * | 2018-03-07 | 2018-09-11 | 中国地质大学（武汉） | In conjunction with the haze prediction model method for building up and system of SOFM nets and BP neural network |
| CN108520311B (en) * | 2018-03-07 | 2021-05-28 | 中国地质大学（武汉） | Haze prediction model establishing method and system combining SOFM (software on a programmable) network and BP (back propagation) neural network |
| CN109460860A (en) * | 2018-10-18 | 2019-03-12 | 上海海洋大学 | Argentinian squid Resources Prediction method based on Antarctic Oscillations index |
| CN109543878A (en) * | 2018-10-18 | 2019-03-29 | 上海海洋大学 | North Pacific's squid Resources Prediction method based on Pacific Ocean Oscillation Index |
| CN109472405A (en) * | 2018-11-02 | 2019-03-15 | 上海海洋大学 | Japanese Qiu Shengqun squid resource abundance prediction technique based on Pacific Ocean concussion index |
| CN109523070A (en) * | 2018-11-02 | 2019-03-26 | 上海海洋大学 | Raw group squid resource abundance prediction technique of Japanese winter based on Pacific Ocean concussion index |
| 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 |
| CN110533245A (en) * | 2019-08-30 | 2019-12-03 | 上海海洋大学 | A kind of sliding squid fishing ground amount prediction technique of Argentina based on Hai Biaowen |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107590549A (en) | A kind of Japanese squid winter life group's resource abundance Forecasting Methodology | |
| Fulton et al. | Sea temperature shapes seasonal fluctuations in seaweed biomass within the Ningaloo coral reef ecosystem | |
| Bednaršek et al. | The global distribution of pteropods and their contribution to carbonate and carbon biomass in the modern ocean | |
| Conti et al. | Fisheries yield and primary productivity in large marine ecosystems | |
| CN106295833B (en) | Pacific ocean Pleurotus giganteus resource replenishment quantity prediction method and application thereof | |
| CN106612495B (en) | A kind of indoor orientation method and system based on propagation loss study | |
| CN109767040A (en) | Saury cental fishing ground prediction technique based on habitat suitability index | |
| CN103049659B (en) | A kind of waters off Peru jumbo flying squid resource magnitude of recruitment Forecasting Methodology and application process thereof | |
| McDuie et al. | Trans-equatorial migration and non-breeding habitat of tropical shearwaters: implications for modelling pelagic Important Bird Areas | |
| Dissanayake et al. | Present status of the commercial sea cucumber fishery off the north-west and east coasts of Sri Lanka | |
| CN106251006A (en) | A kind of Argentina squid resource magnitude of recruitment Forecasting Methodology | |
| Wolfe et al. | Fish population fluctuation estimates based on fifteen years of reef volunteer diver data for the Monterey Peninsula, California | |
| Sherman et al. | 6 The US Northeast shelf large marine ecosystem: Zooplankton trends in fish biomass recovery | |
| Sherman | Biomass flips in large marine ecosystems | |
| Guy et al. | Understanding climate control of fisheries recruitment in the eastern Bering Sea: long-term measurements and process studies | |
| CN110751323A (en) | Fishing ground fishing situation prediction method based on dynamic modeling | |
| Neokye et al. | The role of oceanic environmental conditions on catch of Sardinella spp. in Ghana | |
| CN107330541A (en) | A kind of west and central Pacific ocean stripped tuna Predicting Center Fishery method | |
| CN105787967A (en) | Method for measuring and calculating construction area of marine ranching in island reef waters featuring complex landform | |
| Kuriakose et al. | Course Manual ICAR funded Summer School on Advanced Methods for Fish Stock Assessment and Fisheries Management | |
| CN109523070A (en) | Raw group squid resource abundance prediction technique of Japanese winter based on Pacific Ocean concussion index | |
| Wang et al. | Winter abundance and species composition of anchovy larvae associated with hydrological conditions in the coastal waters of Tanshui, Taiwan | |
| Terceiro | 10 Gulf of Maine-Georges Bank American plaice | |
| Gunawardane et al. | Capturing local knowledge of beach seine fishers in the north-western province of Sri Lanka | |
| Lehodey et al. | Operational real-time and forecast modelling of Atlantic albacore tuna |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180116 |
|
| RJ01 | Rejection of invention patent application after publication |