CN106295833B - Pacific ocean Pleurotus giganteus resource replenishment quantity prediction method and application thereof - Google Patents
Pacific ocean Pleurotus giganteus resource replenishment quantity prediction method and application thereof Download PDFInfo
- Publication number
- CN106295833B CN106295833B CN201510253869.1A CN201510253869A CN106295833B CN 106295833 B CN106295833 B CN 106295833B CN 201510253869 A CN201510253869 A CN 201510253869A CN 106295833 B CN106295833 B CN 106295833B
- Authority
- CN
- China
- Prior art keywords
- cpue
- pacific
- fishing
- sea
- chl
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Farming Of Fish And Shellfish (AREA)
Abstract
The invention relates to a Pacific ocean Pleurotus fasciatus resource replenishment quantity prediction method and application, wherein SST data in a sea area with the ranges of 125-140E and 25-40N in 1997-2009 are counted; calculating the concentration data of chl a in the sea area with the ranges of 125-140E and 25-40N in 1997-2009; counting CPUE of autumn-grown populations of Pacific Flex in 1998-2010; counting the sea area with the sea surface temperature of 15-20 ℃ in the sea area with the ranges of 125-140 DEG E and 25-40 DEG N in 10-12 months, and calculating PS(ii) a The time sequence of CPUE, SST and chl a concentration data and P are obtained by statistical analysisSThe point at which the time series of values is most correlated; performing multiple linear regression analysis; predicting a BP neural network model; and obtaining a predicted value of the CPUE of the Pacific ocean Pleurotus Pacificus, and calculating the prediction precision of the CPUE.
Description
Technical Field
The invention relates to a fishing situation forecasting method, in particular to a Pacific plectropods autumn school resource replenishment quantity forecasting method with spawning site ranges of 125-140 degrees E and 25-40 degrees N.
Background
Todarodes pacificus, also known as Japanese squid, eastern squid and the like, are one of oceanic economic squid, and are mainly distributed in 21-50 degrees N sea areas of northwest pacific, namely Japanese sea, Japanese pacific coasts, yellow sea and east sea in China. Pacific ocean velveteen mainly has three seasonal spawning groups, namely a summer group, an autumn group and a winter group. At present, the main fishing groups are autumn groups and winter groups. The current major fishing areas of the autumnal population are high in the harvest yields in the japanese sea, japan and korea. Its main spawning area is east China sea and the paradise strait, and its spawning period is 10-12 months. The bait is required to lay eggs in the north and the south of Japan in spring and summer every year.
The fishing situation forecast is a key link of fishery production, and the forecast of the Pacific ocean Pleurotus fasciatus resource supplement quantity is beneficial to the forecast of the Pacific ocean Pleurotus fasciatus yield, the central fishing ground position and the fishing season. The survival rate of the juvenile Pacific ocean velvety fish is closely related to external marine environmental factors besides the intrinsic physiological factors. The actions of the young fish are directly or indirectly influenced by a plurality of external factors, including hydrology (sea current, water temperature, tide, salinity, water color, water quality, runoff and the like), meteorology (wind, air pressure, air temperature, precipitation and the like), geography (terrain, geology, landform and the like), and organisms (plankton, benthonic, enemy and the like).
From the 20 th century and the 50 th century, various offshore marine aquatic product research institutes successively carried out possible fishing amount prediction, on-site prediction or flood season prediction work on fish species such as acete chinensis, small yellow croaker, prawn, hairtail, cod, large yellow croaker, mackerel and the like. The method is developed further in the 60 s, so that not only are the predicted varieties increased, but also the predicted contents are gradually enriched, and the method plays a certain role in promoting the development of fishery production. In the 70 s, mathematical models are used to estimate the change of fish resource quantity, which creates good conditions for realizing the modernization of fishery in China.
The development of fishing situation forecasting work in the past mainly depends on-site sampling investigation, the input manpower and material resources are large, the process is complex, the influence of weather is large, only samples in local areas can be collected, and the distribution characteristics of global marine environment factors cannot be visually seen. For example, the forecasting of the fishing situation of the salangid in the Hongze lake is completed in one day by carrying out full-moustache trawling 2-3 times before the fishing news every year. And (4) the trawl boat is driven at a medium speed, the trawl is not spotted for 30 minutes, and the quantity, the mantissa, the species composition and the growth condition of the fish obtained by the trawl are measured. And (4) measuring and reporting the fishing condition of the whitebait according to the quantity, density and growth condition of the whitebait and the feeding habit conversion condition of the big whitebait.
Then, 3 space technologies of Remote Sensing (RS), Global Positioning System (GPS) and Geographic Information System (GIS) provide a solid platform for further development of marine fishery. The results of fishing scene forecast by using 3S technology at home and abroad are not enumerated. In foreign countries, the marine fishery application of satellite remote sensing is mainly applied to fishery developed countries such as the United states and Japan. Satellite remote sensing is used for obtaining information of marine water body environment and making fishing condition forecast in the early stage. With the progress of technical means, more and more environmental factors are obtained, the precision is higher and higher, a quantitative regression model is established for the activity rule and distribution of individual fish species, and the activity rule and the distribution of the individual fish species are successfully forecasted for many times; in the period of 'nine five', the national 863 plan combines a satellite remote sensing technology, a geographic information system and an artificial intelligence expert system to analyze and forecast fishing situation information and realize business operation. Generally, the research at home and abroad is mainly focused on a certain aspect in the 3S technology, and the research on the whole framework of comprehensively applying the 3S technology to the fishing situations in fishing farms is insufficient.
However, there is a disadvantage in obtaining information by using remote sensing technology in the ocean, and the information of fish schools in the fishing ground cannot be directly obtained by remote sensing when marine fishes live below the ocean surface. Only by researching and analyzing the environmental information of the water body of the fishery in the fishing scene and the ocean.
At present, methods such as a multivariate statistical method and a habitat index are mostly adopted for a forecasting method of a certain fishery category, but a forecasting result often has a certain deviation from an actual situation. Because the neural network has the advantages of self-organization, self-adaptation, self-learning, fault tolerance and the like, a plurality of scholars have long made application research on aspects of medicine, hydrological forecasting, earthquake forecasting and the like, and have been well applied to the aspect of processing multi-factor mass data, especially under the condition of data interruption, and many examples have been successful. These examples have shown that neural network methods are superior to other research methods.
Disclosure of Invention
The invention aims to solve the problems and overcome the problems in the existing fishing situation forecasting technology, and the invention aims to provide a method for predicting the resource supplement quantity of Pacific ocean Pleurotus fasciatus in the next year and an application thereof.
In order to achieve the purpose, the technical scheme of the invention is as follows:
a Pacific ocean velvetfish resource replenishment quantity prediction method is characterized by comprising the following steps:
(1) counting sea surface temperature data (SST) of sea areas of 125-140 degrees E and 25-40 degrees N in 10-12 months and each year in 1997-2009;
(2) counting chlorophyll a concentration data (chl a) of sea areas of 125-140E and 25-40N in 10-12 months and each year in 1997-2009;
(3) counting the unit fishing Nu-power catch amount (CPUE) of autumn-grown groups of Pacific ocean Pleurotus fasciatus in 1998-2010;
(4) counting the sea area with the sea surface temperature of 15-20 ℃ in the sea area of 125-140 DEG E and 25-40 DEG N in 10-12 months of each year in 1997-2009, and then calculating the ratio of the sea area (P) of the area occupying the range of 125-140 DEG E and 25-40 DEG NS)；
(5) Statistical analysis is carried out to obtain a time sequence of a unit fishing Nu force fishing harvest amount (CPUE), sea surface temperature data (SST), chlorophyll a concentration data (chl a) and PSThe point at which the time series of values is most correlated;
(6) respectively selecting sea surface temperature data (SST), chlorophyll a concentration data (chl a) and PSPerforming multiple linear regression analysis on points with high correlation between the time sequence of the values and the time sequence of unit fishing Nu force fishing yield (CPUE);
(7) respectively selecting sea surface temperature data (SST), chlorophyll a concentration data (chl a) and PSPredicting the point with high correlation between the time sequence of the values and the time sequence of the unit fishing Nu force fishing yield (CPUE) in the next year by using a BP neural network model;
the BP model takes the minimum fitting residual error as a standard for judging the optimal model. The fitting residual is a value obtained by comparing the CPUE predicted value and the measured value outputted by the output layer, and the function definition is as follows:
wherein E represents the fitting residual value, ykAs an actual measurement value of the CPUE,
for the prediction value of CPUE, N represents the number of CPUENumber, k, denotes CPUE ordinal number.
(8) Selecting sea surface temperature data (SST), chlorophyll a concentration data (chl a) and P of points with high correlation in 2010-2012SAnd obtaining a predicted value of the unit fishing yield strength and catch amount (CPUE) of Pacific ocean plena in 2011-2013, and calculating the prediction accuracy of the CPUE.
The forecasting accuracy is calculated by the following formula:
where P represents the prediction accuracy, ykAs an actual measurement value of the CPUE,
is a predicted value of the CPUE.
According to the prediction method for the resource replenishment quantity of the Pacific ocean juveniles, the 10-12 months are suitable time for the Pacific ocean juveniles to spawn.
According to the prediction method for the resource supplement amount of the Pacific ocean Pleurotus giganteus, the temperature of 15-20 ℃ is the appropriate spawning temperature of the Pacific ocean Pleurotus giganteus.
The invention also provides application of the pacific plectropods resource replenishment quantity prediction method in a fishing situation forecasting technology.
The method for predicting the pacific ocean juveniles resource replenishment amount is preferably used for predicting the pacific ocean juveniles resource replenishment amount in the northwest.
The invention adopts an EBP (error back propagation) algorithm in a neural network, which is called BP model for short. The method belongs to a multilayer forward neural network, and a supervision algorithm of error back propagation is adopted, so that a large number of mode mapping relations can be learned and stored.
The invention has the beneficial technical effects that:
the invention provides a Pacific ocean Pleurotus giganteus resource replenishment quantity prediction method and application thereof. The BP neural network model can predict about 90% of the change of the Pacific ocean Pleurotus giganteus resource abundance.
By applying the prediction method for the pacific plectropods resource supplement amount, the prediction result of the pacific plectropods resource supplement amount is timely provided for users and relevant departments for scientific reference, and the pacific plectropods resource supplement amount can be published in real time as a product in future.
Description of the drawings:
FIG. 1: critical sea areas with significant correlation to resource replenishment.
FIG. 2: and a linear relation between the characteristic environmental factor and the plectropods resource supplement amount.
FIG. 3: and (5) simulation results of three models.
Detailed Description
The present invention is further described below, and it should be understood by those skilled in the art that the examples are only for illustration and are not to be construed as limiting the present invention in any way.
Pacific ocean Pacific Flex fish is an annual short life cycle species, usually there is no population left, only a supplementary population, and the amount of supplementation in the next year depends largely on the marine environmental conditions of the spawning ground. The egg survival rate is high under the suitable marine environment condition, the resource supplement amount of the pacific ocean plectropods in the next year is good, and the resource supplement amount is poor otherwise. The egg laying time of Pacific ocean Pacific Flex Nameko is usually 10-12 months, the suitable egg laying sea surface temperature is 15-20 deg.C, and the egg laying sea area is 125-140 deg.E, 25-40 deg.N. Fishery data of the invention is derived from the resource assessment report of autumn population of Pacific Pleurotus Pacific Flex 2013, and the time span is 1998-2012; the environmental data is derived from http:// oceanwatch. pifsc. noaa. gov, the time resolution is month, and the time span is 1997-2012; SST spatial resolution is 0.05 ° × 0.05 °, chl a concentration spatial resolution is 0.1 ° × 0.1 °; the latitude and longitude ranges from 25 degrees N to 40 degrees N and from 125 degrees E to 140 degrees E.
The spatial resolution of the environmental data is unified to 0.5 degrees multiplied by 0.5 degrees, the conversion of the environmental data of different spatial scales is completed through Arcgis software, for example, SST data of each spatial scale of 0.5 degrees multiplied by 0.5 degrees is obtained by calculating the average value of 25 original data.
A Pacific ocean velvetfish resource replenishment quantity prediction method comprises the following steps:
(1) counting sea surface temperature data (SST) of sea areas of 125-140 degrees E and 25-40 degrees N in 10-12 months and each year in 1997-2009;
(2) counting chlorophyll a concentration data (chl a) of sea areas of 125-140E and 25-40N in 10-12 months and each year in 1997-2009;
(3) counting the unit fishing Nu-power catch amount (CPUE) of autumn-grown groups of Pacific ocean Pleurotus fasciatus in 1998-2010;
(4) counting the sea area with the sea surface temperature of 15-20 ℃ in the sea area of 125-140 DEG E and 25-40 DEG N in 10-12 months of each year in 1997-2009, and then calculating the ratio of the sea area (P) of the area occupying the range of 125-140 DEG E and 25-40 DEG NS)；
(5) Statistical analysis is carried out to obtain a time sequence of a unit fishing Nu force fishing harvest amount (CPUE), sea surface temperature data (SST), chlorophyll a concentration data (chl a) and PSThe point at which the time series of values is most correlated;
in the spawning months (10-12 months), the correlation analysis of the time series of 0.5 ° × 0.5 ° SST per 10-12 months in the spawning field area (25 ° -40 ° N, 125 ° -140 ° E) with the time series of the next year CPUE revealed that: month 10, the maximum of SST correlation with next year CPUE occurs at 32 ° N, 136 ° E (Point1) (table 1, fig. 2 a); month 11, SST and next year CPUE correlation maximum occurs at 29.5 ° N, 127 ° E (Point2) (table 1, fig. 2 b); the maximum value of the correlation of SST with CPUE of the next year occurs at 29 ° N, 137.5 ° E (Point3) (table 1, fig. 2 c).
Correlation analysis of the time series of chl a concentrations of 0.5 ° × 0.5 ° for each of months 11 and 12 (25 ° -40 ° N, 125 ° -140 ° E) in the egg-laying field region with the time series of next-year CPUE revealed: month 11, the maximum correlation of chl a concentration with CPUE of the next year occurs at 26 ° N, 126 ° E (Point4) (table 1, fig. 2 d); month 12, the maximum correlation of chl a concentration with CPUE of the next year occurs at 28 ° N, 125.5 ° E (Point5) (table 1, fig. 2E).
Correlation analysis of the time series of PS values with the time series of next year CPUE found that: there was no significant correlation between the proportion of the optimal sea surface temperature range in the 10-12 months to the total area of the spawning site and the next year CPUE (table 2).
TABLE 1 correlation analysis parameters of key sea area environmental factors and resource replenishment
TABLE 2 optimal surface temperature ratio P of spawning siteSCorrelation analysis parameter with next year CPUE
(6) Respectively selecting sea surface temperature data (SST), chlorophyll a concentration data (chl a) and PSPerforming multiple linear regression analysis on points with high correlation between the time sequence of the values and the time sequence of unit fishing Nu force fishing yield (CPUE);
according to the result of (5), selecting the time series of the sea surface temperatures of point1, point2 and point3, and establishing a multivariate linear model by the time series of the chlorophyll a concentrations of point4 and point5 and the time series of the fishing amount of the unit fishing effort in the next year, wherein the equation is as follows:
Y＝0.1809X1-0.1419X2+0.4458X3+2.0182X4+0.3955X5-9.2025
the correlation coefficient R is 0.955(P ═ 0.004< 0.05).
(7) Respectively selecting sea surface temperature data (SST), chlorophyll a concentration data (chl a) and PSPredicting the point with high correlation between the time sequence of the values and the time sequence of the unit fishing Nu force fishing yield (CPUE) in the next year by using a BP neural network model;
and constructing various BP forecasting models by using different combinations of the selected key sea area environmental factors and the PS as input factors of the BP forecasting models, wherein the combinations are respectively as follows:
scheme 1: three factors including SST of Point1, chl a concentration of Point4 and PS are selected as input layers to construct a 3-2-1 BP network structure.
Scheme 2: four factors including SST of Point2, SST of Point3, chl a concentration of Point5 and PS are selected as input layers to construct a 4-3-1 BP network structure.
Scheme 3: 6 factors including SST of Point1, Point2 and Point3, chl a concentration of Point4 and Point5 and PS are selected as input layers to construct a 6-4-1 BP network structure.
And repeatedly fitting the models constructed by the three schemes for 10 times to obtain an optimal result. The fitting results of the three schemes are shown in FIG. 3 (see FIG. 3a for scheme 1, FIG. 3b for scheme 2, and FIG. 3c for scheme 3).
The fit residuals for the BP neural networks of schemes 1, 2, and 3 are 0.0284, 0.0103, and 0.0000996, respectively.
(8) Selecting sea surface temperature data (SST), chlorophyll a concentration data (chl a) and P of points with high correlation in 2010-2012SAnd obtaining a predicted value of the amount of the Nubian force Catch (CPUE) caught by the unit of the northwest Pacific ocean plecoglossus in 2011-2013, and calculating the prediction precision of the quantity.
The prediction accuracy of the three BP network models and the multivariate linear model are shown in table 3.
TABLE 3 prediction accuracy comparison of models
In prediction, the Pacific ocean Pleurotus giganteus is suitable for spawning in 10-12 months, and the Pleurotus giganteus is suitable for spawning at 15-20 deg.C.
The invention has the beneficial effects that: the BP neural network model can predict about 90% of the change of the Pacific ocean Pleurotus giganteus resource abundance. The prediction result of the Pacific ocean velvetfish resource replenishment quantity is timely provided for users and relevant departments for scientific reference, and can be released in real time as a product in future.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are given by way of illustration of the principles of the present invention, and that various changes and modifications may be made without departing from the spirit and scope of the invention as defined by the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (7)
1. A Pacific ocean Pleurotus fasciatus resource replenishment quantity prediction method is used for guiding pelagic ocean fishing of Pacific ocean Pleurotus fasciatus, and is characterized by comprising the following steps:
(1) counting the sea surface temperature data (SST) of sea areas of 125-140 degrees E and 25-40 degrees N in 10-12 months and every year in 1997-2009;
(2) counting the chlorophyll a concentration data, namely chl a, of the 10-12 months, 125-140 degrees E and 25-40 degrees N waters of each year in 1997-2009;
(3) calculating the unit fishing effort and the fishing amount of autumn-born populations of Pacific ocean Plectranthus fasciatus in 1998-2010, namely CPUE;
(4) counting the sea area with the sea surface temperature of 15-20 ℃ in the sea area of 125-140 DEG E and 25-40 DEG N in 10-12 months of each year in 1997-2009, and then calculating the ratio of the sea area with the area accounting for the ranges of 125-140 DEG E and 25-40 DEG N, namely PS；
(5) Obtaining the time sequence of the fishing amount CPUE of unit fishing effort amount and the sea surface temperature data SST, chlorophyll a concentration data chl a and P by statistical analysisSThe point at which the time series of values is most correlated;
(6) respectively selecting sea surface temperature data SST, chlorophyll a concentration data chl a and PSPerforming multivariate linear regression analysis on points with high correlation between the time sequence of the values and the time sequence of the unit fishing effort fishing amount CPUE;
(7) respectively selecting sea surface temperature data SST, chlorophyll a concentration data chl a and PSThe point with high correlation between the time sequence of the value and the time sequence of the fishing amount CPUE of the unit fishing effort of the next year is used as BP neural network model prediction;
(8) and (4) selecting the optimal model in the BP neural network model obtained in the step (7), obtaining surface temperature data SST and chlorophyll a concentration data chl a of the sea area by using ocean remote sensing, inputting the optimal model into the selected model, and obtaining the fishing amount CPUE of the Nubian strength captured in the next annual unit, namely completing the prediction of the resource supplement amount of the Pacific pleus next year.
2. The method for predicting resource replenishment quantity of pacific plectropods according to claim 1, wherein the optimal model in the BP neural network models obtained in the selecting step (7) is specifically: selecting sea surface temperature data SST and chlorophyll a concentration data chl a and P with high correlation in 2010-2012SAnd obtaining a predicted value of the fishing yield CPUE of the unit fishing effort of Pacific ocean Pleurotus fasciatus in 2011-2013, calculating the prediction accuracy of the CPUE, and selecting the BP neural network model with the highest prediction accuracy as the optimal model.
3. The method according to claim 1, wherein the BP model uses a minimum fitting residual as a criterion for determining an optimal model; the fitting residual is a value obtained by comparing the CPUE predicted value and the measured value outputted by the output layer, and the function definition is as follows:
whereinEThe fitting residual value is represented as a value of,y k as an actual measurement value of the CPUE,
in order to predict the value of the CPUE,Nindicates the number of the CPUEs,kindicating CPUE ordinal numbers.
4. The method for predicting resource replenishment quantity of pacific plectropods according to claim 2, wherein the forecasting accuracy is calculated by the following formula:
whereinPThe rate of accuracy of the prediction is represented,y k as an actual measurement value of the CPUE,
is a predicted value of the CPUE.
5. The method for predicting resource replenishment amount of pacific ocean juveniles according to claim 1, wherein suitable time for pacific ocean juveniles to spawn is 10-12 months in the step (4).
6. The method for predicting resource replenishment quantity of pacific plenard juveniles according to claim 1, wherein the temperature suitable for the pacific plenard juveniles to spawn is 15-20 ℃ in the step (4).
7. Use of the pacific pinus juveniles resource replenishment quantity prediction method of any one of claims 1 to 6 in a fishery forecasting technique.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510253869.1A CN106295833B (en) | 2015-05-18 | 2015-05-18 | Pacific ocean Pleurotus giganteus resource replenishment quantity prediction method and application thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510253869.1A CN106295833B (en) | 2015-05-18 | 2015-05-18 | Pacific ocean Pleurotus giganteus resource replenishment quantity prediction method and application thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106295833A CN106295833A (en) | 2017-01-04 |
| CN106295833B true CN106295833B (en) | 2021-06-29 |
Family
ID=57633069
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510253869.1A Active CN106295833B (en) | 2015-05-18 | 2015-05-18 | Pacific ocean Pleurotus giganteus resource replenishment quantity prediction method and application thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106295833B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107341565A (en) * | 2017-06-15 | 2017-11-10 | 上海海洋大学 | Northwest Pacific Japan anchovy resource abundance Forecasting Methodology |
| CN107403237A (en) * | 2017-07-03 | 2017-11-28 | 上海海洋大学 | West and central Pacific ocean stripped tuna fishing ground forecasting procedure based on Different climate condition |
| CN109063189A (en) * | 2018-08-28 | 2018-12-21 | 国家卫星海洋应用中心 | A kind of date storage method and device |
| CN109460860A (en) * | 2018-10-18 | 2019-03-12 | 上海海洋大学 | Argentinian squid Resources Prediction method based on Antarctic Oscillations index |
| JP7157479B2 (en) * | 2018-11-02 | 2022-10-20 | 上海海洋大学 | Prediction method and application of Japanese flying squid abundance based on the Pacific Oscillation Index |
| CN110135559A (en) * | 2019-04-28 | 2019-08-16 | 中国水产科学研究院东海水产研究所 | A method of it is thrown the net based on ship position data acquisition and nets position and fishing effort |
| CN110222832A (en) * | 2019-06-19 | 2019-09-10 | 中国水产科学研究院东海水产研究所 | Entrance of Changjiang River salt marshes macrobenthos habitat simulation prediction technique |
| 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 |
| CN114444819B (en) * | 2022-04-11 | 2022-06-28 | 山东省海洋资源与环境研究院(山东省海洋环境监测中心、山东省水产品质量检验中心) | Fishery resource prediction method and device, storage medium and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120158495A1 (en) * | 2010-12-20 | 2012-06-21 | Jayavel Shanmugasundaram | Inventory allocation in advertising systems |
| 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 |
| CN103053450A (en) * | 2012-12-24 | 2013-04-24 | 上海海洋大学 | Southwest Atlantic illex argentinus resource supplement quantity forecasting method |
-
2015
- 2015-05-18 CN CN201510253869.1A patent/CN106295833B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120158495A1 (en) * | 2010-12-20 | 2012-06-21 | Jayavel Shanmugasundaram | Inventory allocation in advertising systems |
| 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 |
| 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 |
|---|
| An implemented architecture for construction of hybrid intelligent forecasting systems;Narate Lertpalangsunti等;《1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation》;IEEE;20020806;第934-939页 * |
| 鱿鱼类资源量变化与海洋环境;曹杰等;《上海海洋大学学报》;20100315;第19卷(第2期);第232-239页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106295833A (en) | 2017-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106295833B (en) | Pacific ocean Pleurotus giganteus resource replenishment quantity prediction method and application thereof | |
| Finstad et al. | Migrate or stay: terrestrial primary productivity and climate drive anadromy in Arctic char | |
| Papastamatiou et al. | Telemetry and random‐walk models reveal complex patterns of partial migration in a large marine predator | |
| Bolduc et al. | Terrestrial arthropod abundance and phenology in the Canadian Arctic: modelling resource availability for Arctic-nesting insectivorous birds | |
| Farley Jr et al. | Response of Pink salmon to climate warming in the northern Bering Sea | |
| CN103004664B (en) | Method for forecasting northwest Pacific Ocean squids resource stock recruitment and application method thereof | |
| Bever et al. | Linking hydrodynamic complexity to Delta Smelt (Hypomesus transpacificus) distribution in the San Francisco Estuary, USA | |
| Ruiz et al. | The Bolivar Channel Ecosystem of the Galapagos Marine Reserve: Energy flow structure and role of keystone groups | |
| Gourault et al. | Modeling reproductive traits of an invasive bivalve species under contrasting climate scenarios from 1960 to 2100 | |
| Boeing et al. | Ichthyoplankton dynamics and biodiversity in the Gulf of Alaska: responses to environmental change | |
| Fisher et al. | Copepod responses to, and recovery from, the recent marine heatwave in the Northeast Pacific | |
| Dai et al. | Comparative performance of modelling approaches for predicting fish species richness in the Yangtze River Estuary | |
| Pezy et al. | The environmental impact from an offshore windfarm: Challenge and evaluation methodology based on an ecosystem approach | |
| Moon et al. | Projected impact of sea-level rise and urbanization on mottled duck (Anas fulvigula) habitat along the Gulf Coast of Louisiana and Texas through 2100 | |
| Oyaizu et al. | Modeling the growth, transport, and feeding migration of age-0 Pacific saury Cololabis saira | |
| Rice et al. | Monitoring ecosystem response to restoration and climate change in the Snohomish River Estuary | |
| Stepputtis | Distribution patterns of Baltic sprat (Sprattus sprattus L.): causes and consequences | |
| Bloor | The ecology, distribution and spawning behaviour of the commercially important common cuttlefish (Sepia officinalis) in the inshore waters of the English Channel | |
| Brewer-Dalton et al. | Oceanographic conditions of salmon farming areas with attention to those factors that may influence the biology and ecology of sea lice, Lepeophtherius salmonis and Caligus spp., and their control | |
| Myksvoll et al. | Modelling salmon lice copepodids along the Norwegian coast–comparing old and new particle tracking models | |
| Liu et al. | Incorporating egg-transporting pathways into conservation plans of spawning areas: An example of small yellow croaker (Larimichthys polyactis) in the East China Sea zone | |
| Herstrøm | Fine scale haul-out behaviour of harbour seals (Phoca vitulina) at different localities in northern Norway | |
| Lu | Data-driven integrated assessment of global wild-caught seafood exported to Hong Kong by 2030 in different representative concentration and shared socioeconomic pathways | |
| Spires | The exchange of eastern oyster (Crassostrea virginica) larvae between subpopulations in the choptank and little choptank rivers: Model simulations, the influence of salinity, and implications for restoration | |
| Prowse et al. | Response models for key waterbird species of the Coorong |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |