CN104217254A - Construction method of quick forecasting operation system of fishery fishing condition - Google Patents
Construction method of quick forecasting operation system of fishery fishing condition Download PDFInfo
- Publication number
- CN104217254A CN104217254A CN201410438468.9A CN201410438468A CN104217254A CN 104217254 A CN104217254 A CN 104217254A CN 201410438468 A CN201410438468 A CN 201410438468A CN 104217254 A CN104217254 A CN 104217254A
- Authority
- CN
- China
- Prior art keywords
- fishing ground
- fishing
- fishery
- forecast
- ground
- 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
Abstract
The invention relates to a construction method of the quick forecasting operation system of fishery fishing condition. The construction method comprises the following steps: adopting a satellite remote sensing system, a geographic information system and a fishery environment feature library to establish a multi-granularity fishery industry fishing condition analysis database; adopting a generalized additive model to carry out quantitative analysis on relationship between the fishery and a plurality of environment factors and fishing factors, definitizing the center fishery space-time change rule and the influence factors thereof of a long time sequence, and mastering the center fishery space-time change rule and a formation mechanism; and according to the fishery space-time change rule and the formation mechanism, constructing a fishery forecasting model based on a key marine environment factor driving mechanism, establishing various fishery forecasting models to realize the comprehensive forecast of a fishery, and proposing a fishery forecasting accuracy improvement scheme. Since a control is used for carrying out visual representation to main environment factors, a series of standard business-oriented flows is constructed to determine the analysis, the charting and the quick release of a fishery fishing condition forecast map, and reference and guide are provided for fishery quest for direct scene fishery industry production.
Description
Technical field
The present invention relates to fishing ground fishery forescast and system cloud gray model technical field, particularly relate to the construction method of a kind of fishing ground fishing feelings speed forecast operational system.
Background technology
Chile's jack mackerel (Trachurus murphyi) is one of marine economy fish of outbalance in the world, belongs to ocean property, at the middle and upper levels height migration fishes.Position is at the forefront in the world always for many years for the Chilean jack mackerel fishery output of southeast Pacific.From 1978 to 2005 years its total productions all more than 1,000,000 tons, be distributed widely in the whole South Pacific Ocean, all there is distribution the state exclusive economic zone such as Ecuador, Peru, Chile and New Zealand and contiguous zone of the open sea.The Chilean jack mackerel fishing ground exploitation of China is more late (starting in 2000), but development is very fast, has become zone of the open sea, South Pacific Ocean Chile the important of jack mackerel and has fished for state.Within 2003 ~ 2008 years, Chile of China jack mackerel total production reaches more than 100,000 tons, accounts for 1/3 ~ 1/4 of this marine site output; Ship number also reaches 9 ~ 13, accounts for the half of fishing ground, Chilean jack mackerel ocean operation ship number, and annual value of production is 0.5 ~ 1.5 hundred million dollar.The development of southeast Pacific Chile jack mackerel fishery not only makes China rank among the row of important deep-sea fishing country of the world, and for improving China's International Fisheries status, the pressure alleviating coastal water fishery resource has made significant contribution.But also should see, still there is larger gap in Chile of China jack mackerel fishing operation overall technology level, Development for Distant Water Fishery still faces technical bottleneck compared with some fishery developed countries (Holland, Greece etc.).Outstanding behaviours exists: the shortage of fishing ground information, and fishing ground fishing condition is failed to understand; The research of comprehensive study and analysis is lacked to fishing ground and the Changing Pattern of fishing season; Zonal Fisheries Information service is left to be desired, the problems such as fishing ground fishing feelings information service and fast forecast model products shortage.
In the face of the jack mackerel Fisheries Development an urgent demand of Chile of China, the development of the problem long-standing problem Chinese large-sized trawl-net fishings such as fishing ground environment sea situation is failed to understand, fishing ground fishing feelings information service and fast forecast model products shortage, the particularly domestic Chilean jack mackerel speed forecast system also not having to realize businessization and run.
Summary of the invention
Technical matters to be solved by this invention is to provide the construction method of a kind of fishing ground fishing feelings speed forecast operational system, can understand and grasp the possible position in fishing ground simply.
The technical solution adopted for the present invention to solve the technical problems is: the construction method providing a kind of fishing ground fishing feelings speed forecast operational system, comprises the following steps:
(1) adopt satellite remote sensing, fishery fishery stock assessment database that Geographic Information System, fishing ground environment feature database set up many granularities;
(2) adopt Generalized Additive Models to carry out quantitative test to fishing ground and multiple envirment factor with the relation of fishing for the factor, specify cental fishing ground space-time Fluctuation and the influence factor thereof of long-term sequence, grasp cental fishing ground space-time Fluctuation and Forming Mechanism;
(3) the fishing ground forecasting model based on crucial marine environment factor driving mechanism is built according to cental fishing ground space-time Fluctuation and Forming Mechanism, set up multiple fishing ground forecast model to realize the comprehensive forecasting in fishing ground, and the raising scheme of fishing ground forecast accuracy is proposed, build a series of standardization business flow process to guarantee fishing ground fishery forescast.
Database in described step (1) adopts multiple document interface, main client area shows each layer with electronic chart, client area is split in different forms and is arranged, and comprises individually diagram form, a line two column split, two row one column splits and two row two column splits, 4 kinds of forms.
Fishing ground forecasting model in described step (3) is bayesian probability model, and described bayesian probability model is
Wherein, h
0for being assumed to be the situation of "True", namely fishing ground is the situation of "True"; h
1for being assumed to be " non-real " situation; E is environmental baseline; P (h
0/ e) be the probability in fishing ground under given environmental baseline, i.e. posterior probability; P (e/h
0) and P (e/h
1) be the conditional probability in fishing ground and non-fishing ground, P (h
0) and P (h
1) for not considering given environmental baseline time fishing ground and the prior probability in non-fishing ground.
Fishing ground forecasting model in described step (3) is case based reasoning model, using Current central fishing ground as present case, the history example maximum with present case similarity is found out by three grades of similar to searchs, one-level similar to search is time similarity retrieval, secondary similar to search is environment field similar to search, three grades of similar to searchs are fishing ground similar to search, by above three grades of similar to searchs, can obtain one group of fishing ground case the most similar to present case from case library, the weighted mean of the next period fishing ground centre of gravity place of these similar cases is the center of gravity in forecast fishing ground.
Fishing ground forecasting model in described step (3) is decision-tree model, have chosen six main environment variablees, utilizing the decision-tree model based on post-class processing algorithm, after this marine site fishing ground environment and fishery harvesting data are trained, obtaining the optimal tree for carrying out fishing ground forecast.
It is abnormal that described envirment factor comprises sea surface temperature, chlorophyll-a concentration, table temperature anomaly, chlorophyll-a concentration anomaly, gradient of sea surface temperature intensity and sea level height.
Described step (3) utilizes in real time/and the fishing ground environment factor quasi real time carries out fishing ground forecast as the model-driven factor, and realize the accurate forecast in fishing ground by the selection of fishing ground forecasting model and human expert knowledge.
Beneficial effect
Owing to have employed above-mentioned technical scheme, the present invention compared with prior art, there is following advantage and good effect: the present invention is from the quick extraction of fishing ground environment key element and Visualization, the integrated data base of history and on-the-spot fish production and environmental characteristic field builds, the multiple forecasting model of cental fishing ground and key environmental factors is set up, the aspects such as the structure of fishing ground forecast system and business operational support are set about, the businessization realizing fishing ground speed forecast is run and is instructed, management fish production, thus can realize in real time, the fishing ground fishing feelings speed reporting services of tool business operational support, user can understand and grasp the possible position in fishing ground simply, for fish production and management decision provide scientific basis.
Accompanying drawing explanation
Fig. 1 is the frame diagram that Chilean jack mackerel fishing ground fishing feelings speed forecasts services operational system builds;
Fig. 2 is Chilean jack mackerel fishing ground fishing feelings database interface;
Fig. 3 is Chilean jack mackerel bayesian probability model forecast result schematic diagram;
Fig. 4 is Chilean jack mackerel case based reasoning model forecast result schematic diagram;
Fig. 5 is Chilean jack mackerel decision-tree model forecast result schematic diagram;
Fig. 6 is the speed forecast of Chilean jack mackerel fishing ground and business operational system.
Embodiment
Below in conjunction with specific embodiment, set forth the present invention further.Should be understood that these embodiments are only not used in for illustration of the present invention to limit the scope of the invention.In addition should be understood that those skilled in the art can make various changes or modifications the present invention, and these equivalent form of values fall within the application's appended claims limited range equally after the content of having read the present invention's instruction.
Fig. 1 is the frame diagram that Chilean jack mackerel fishing ground fishing feelings speed forecasts services operational system builds.First, standard data format, automatic input etc. is carried out by remotely-sensed data, Arogs data, fish production and site environment enquiry data etc.; Formulate the target realizing remote sensing image and automatically issue, solved all drawbacks manually uploaded and issue image, simultaneously by the thumbnail pre-review information of image, reduce the download time of picture.Adopt the mode of magnetic disc array storage data, realize the efficient storage to mass data.System that employs the interface of many documents, main client area shows each layer with electronic chart.Client area can be split in different forms and arrange.Comprise individually diagram form, a line two column split, two row one column splits and two row two column splits, 4 kinds of forms, select for the management of multiple environmental data with when comparing, the stacking diagram (as Fig. 2) of the sea surface temperature in region, fishing ground, chlorophyll, ocean current and 3 kinds of environmental factors can be shown simultaneously.Interpolation and the deletion of map are controlled by the tree structure on the left side.This tree structure is divided into 3 grades.On the date of the 1st grade of expression thematic map, the 2nd grade has 4 nodes, represents 4 above-mentioned width maps respectively; 3rd level represents the title of each layer.Background data base adopts SQLSERVER2005 to manage.
Secondly, Generalized Additive Models (GAM) is adopted to carry out quantitative examination to southeast Pacific Chile jack mackerel fishing ground and multiple envirment factor with the relation of fishing for the factor, analyze cental fishing ground space-time Fluctuation, the main environment factor has sea surface temperature, chlorophyll, sea level height, thermograde etc.Use multiple fishing ground forecast model to carry out comprehensive forecasting to fishing ground, model has bayesian probability model, case based reasoning model and decision-tree model (as Fig. 3,4 and 5).
Wherein, bayesian probability model formula:
In formula, h
0for being assumed to be the situation of "True", namely fishing ground is the situation of "True"; h
1for being assumed to be " non-real " situation; E is environmental baseline.P (h
0/ e) be the probability in fishing ground under given environmental baseline, i.e. posterior probability.P (e/h
0) and P (e/h
1) be the conditional probability in fishing ground and non-fishing ground, P (h
0) and P (h
1) for not considering given environmental baseline time fishing ground and the prior probability in non-fishing ground.Because every day is fished for 20 tons for its work production cost in Chilean jack mackerel fish production, threshold value when the present invention is provided with that every day, fishing ground was "True" is 20 tons, is namely greater than this threshold value and then thinks that fishing ground resource is better.
Case based reasoning model: adopt three grades of similar to searchs to carry out the jack mackerel fishing ground fishery forescast of southeast Pacific Chile, by Current central fishing ground as present case, find out the history example maximum with present case similarity by three grades of similar to searchs.One-level similar to search be time similarity retrieval, carried out time retrieval to 2001 ~ 2010 years by the history case library of Zhou Jianli, find out in history the same period example.Secondary similar to search is environment field similar to search, on the basis of time similarity retrieval, finds out the history case similar to current sea surface temperature field.Three grades of similar to searchs are fishing ground similar to search.On the basis of time, environment similar to search, find out maximum position, fishing ground similar cases.By above three grades of similar to searchs, can obtain one group of fishing ground case the most similar to present case from case library, the weighted mean of the next period fishing ground centre of gravity place of these similar cases is the center of gravity in forecast fishing ground.Through the data verification of 2001-2008, forecast precision can reach 68%.
Decision-tree model: in have chosen southeast Pacific 6 main environment variablees (comprise sea surface temperature, chlorophyll-a concentration, table temperature anomaly, chlorophyll-a concentration anomaly, gradient of sea surface temperature intensity and sea level height abnormal), utilize the decision-tree model based on post-class processing algorithm, after this marine site fishing ground environment and fishery harvesting data are trained, obtain the optimal tree that can be used for carrying out fishing ground forecast, through the fishing ground precision test of the 4-10 month in 2009, effect is better, can reach more than 70%.But the data parameters of this kind of model needs is relatively many, needs more professional personnel to carry out fishing ground modeling.
The design of fishing ground forecast module is based on following two principles: one is based on modularization, the identical fingerling in identical sea area, more than one of the Forecasting Methodology possibility of its correspondence.The equal stand-alone development of different models, generates dynamic link libraries feed system respectively and calls.Two is data and code dehind, same prediction module can be enjoyed to make the prediction of different fingerling (or marine site), different fingerling (or marine site) is predicted that Relational database (or data file) is placed in the middle of different catalogues, that is, the predicted data of different fingerling manages with directory tree, and the forecast model of this fingerling may be one or more.The debugging of fishing ground forecasting model is divided into three steps: one is that model module debugging fishing ground, each fishing ground forecasting model has multiple, the object of sub-module debugging ensures that each module itself can normally be run, for avoiding forecasting the precision in fishing ground, debugging is divided into manually walking to lead to and upper machine is debugged two steps and carried out by we.Unrealistic fishing ground probability results producing cause is investigated, and source code is revised; Two is that fishing ground prediction subsystem divides and adjusts the module formation subsystem of putting together through debugging to debug.Mainly debug coordination between each module and subsystem and communicate, the interface of each module in the prediction subsystem of emphasis debugging fishing ground; Three is that the data (comprising fishing ground environment, fishing ground information, historical probabilities information etc.) of having carried out result that primal system manual work mode draws after system debug subsystem has been dispatched correct carry out actual forecast as the input data of new system, at this moment except actual fishing ground and forecast result are checked, also the validity of whole fishing ground forecast system, reliability and efficiency are tested, and forecast result is supplied to fish production department, listen to their feedback opinion, participate in system debug work together.
Again, after setting up fishing ground forecasting model module, be integrated in Chilean jack mackerel fishing ground fishing feelings speed forecasts services operational system, utilize the fishing ground environment factor of in real time (quasi real time) to carry out fishing ground forecast as the model-driven factor, and realize the accurate forecast in fishing ground by the selection of model and human expert knowledge.This cover system on every Tuesdays, carry out fishing ground fishing feelings thematic mapping and issue (Fig. 6) in the five morning 10.Issue form has client, fax and mail issue etc. 3 kinds, can meet the demand of different user.
Further illustrate below in conjunction with a specific embodiment:
The server of this cover business operational system is located at fishing remote sensing room.With the Chilean jack mackerel fishing ground fishing feelings in southeast Pacific marine site for business object, region is 20 ~ 50 ° of S, 75 ~ 110 ° of W, and fishing ground and environmental data are 2001 ~ 2013 years.Main working process is as follows:
(1) every day, the fishing ground environment Modis data to southeast Pacific carried out automatically downloading leaving server in, carried out business issue on every Tuesdays with morning Friday.Utilize " extra large temperature chlorophyll data handling system V1.0 " software (National Copyright Administration of the People's Republic of China computer software registration number 2010SR070446) to carry out interpolation and repairing to the gentle chlorophyll data in the sea of disappearance, ocean current data obtain by buying U.S. ASA Products and use " ocean ocean current data handling system V1.0 " software (National Copyright Administration of the People's Republic of China's computer software registration number 0258718) to carry out the graphical treatment of ocean current flow velocity size and the flow direction.File after process is the * .env lattice point file of autonomous definition, is convenient to data layout unified, can carries out various dimensions storage.Then, be that * .bmp file carries out two-dimensional visualization expression by lattice point file translations.
(2) use the isoline of Contourocx control to the main environment factor (sea surface temperature and chlorophyll) of independent research automatically to generate, level and smooth and mark, mark can realize color grading and numerical value two kinds of forms.Further, the environment stacking diagram of Hai Wen, chlorophyll and ocean current can be realized, as Fig. 2.Fishery user and administrative authority so more can be made to understand environmental characteristic and the comparative analysis in fishing ground pure and freshly.
(3) forecasting model is selected: have the catalogue depositing forecasting model (existing with dll form) and forecasting model data in service end, according to the sea area of selection and the kind of fish, and the relevant data of automatic synchronization client and server and model.As downloaded three kinds of fishing ground forecasting models in the present invention, i.e. bayesian probability model, case based reasoning model and decision-tree model, by choosing the driven factor of corresponding envirment factor as model, can realize the forecast function in Chilean jack mackerel fishing ground.In actual forecasting process, be generally analyzed three kinds of forecasting model results, the forecast position that degree of overlapping is high has higher confidence level.
(4) forecast model products storage and publish picture: the output button on click tools hurdle, adopts JPG picture format, exports the content of current required map.
(5) release quickly of fishing ground fishery forescast figure: after prog chart is made, upload onto the server, be transmitted through the network to subscription client, client can be quick-downloading, also by mail sending on Fishery Enterprise and fishing boat, for commanding production.The Production Time of whole fishing ground fishery forescast figure completed in 40 minutes, can realize the needs that businessization is run.Simultaneously also can according to the more diversified forecast model products of user's request customization.
Be not difficult to find, the present invention is from the quick extraction of fishing ground environment key element and Visualization, the integrated data base of history and on-the-spot fish production and environmental characteristic field builds, the multiple forecasting model of cental fishing ground and key environmental factors is set up, the aspects such as the structure of fishing ground forecast system and business operational support are set about, the businessization realizing fishing ground speed forecast is run and is instructed, management fish production, thus can realize in real time, the fishing ground fishing feelings speed reporting services of tool business operational support, user can understand and grasp the possible position in fishing ground simply, for fish production and management decision provide scientific basis.
Claims (7)
1. a construction method for fishing ground fishing feelings speed forecast operational system, is characterized in that, comprise the following steps:
(1) adopt satellite remote sensing, fishery fishery stock assessment database that Geographic Information System, fishing ground environment feature database set up many granularities;
(2) adopt Generalized Additive Models to carry out quantitative test to fishing ground and multiple envirment factor with the relation of fishing for the factor, specify cental fishing ground space-time Fluctuation and the influence factor thereof of long-term sequence, grasp cental fishing ground space-time Fluctuation and Forming Mechanism;
(3) the fishing ground forecasting model based on crucial marine environment factor driving mechanism is built according to cental fishing ground space-time Fluctuation and Forming Mechanism, set up multiple fishing ground forecast model to realize the comprehensive forecasting in fishing ground, and the raising scheme of fishing ground forecast accuracy is proposed, build a series of standardization business flow process to guarantee fishing ground fishery forescast.
2. the construction method of fishing ground fishing feelings speed forecast operational system according to claim 1, it is characterized in that, database in described step (1) adopts multiple document interface, main client area shows each layer with electronic chart, client area is split in different forms and is arranged, comprise individually diagram form, a line two column split, two row one column splits and two row two column splits, 4 kinds of forms.
3. the construction method of fishing ground fishing feelings speed forecast operational system according to claim 1, it is characterized in that, the fishing ground forecasting model in described step (3) is bayesian probability model, and described bayesian probability model is
Wherein, h
0for being assumed to be the situation of "True", namely fishing ground is the situation of "True"; h
1for being assumed to be " non-real " situation; E is environmental baseline; P (h
0/ e) be the probability in fishing ground under given environmental baseline, i.e. posterior probability; P (e/h
0) and P (e/h
1) be the conditional probability in fishing ground and non-fishing ground, P (h
0) and P (h
1) for not considering given environmental baseline time fishing ground and the prior probability in non-fishing ground.
4. the construction method of fishing ground fishing feelings speed forecast operational system according to claim 1, it is characterized in that, fishing ground forecasting model in described step (3) is case based reasoning model, using Current central fishing ground as present case, the history example maximum with present case similarity is found out by three grades of similar to searchs, one-level similar to search is time similarity retrieval, secondary similar to search is environment field similar to search, three grades of similar to searchs are fishing ground similar to search, by above three grades of similar to searchs, one group of fishing ground case the most similar to present case is obtained from case library, the weighted mean of the next period fishing ground centre of gravity place of these similar cases is the center of gravity in forecast fishing ground.
5. the construction method of fishing ground fishing feelings speed forecast operational system according to claim 1, it is characterized in that, fishing ground forecasting model in described step (3) is decision-tree model, have chosen six main environment variablees, utilize the decision-tree model based on post-class processing algorithm, after this marine site fishing ground environment and fishery harvesting data are trained, obtain the optimal tree for carrying out fishing ground forecast.
6. the construction method of fishing ground fishing feelings speed forecast operational system according to claim 1, it is characterized in that, it is abnormal that described envirment factor comprises sea surface temperature, chlorophyll-a concentration, table temperature anomaly, chlorophyll-a concentration anomaly, gradient of sea surface temperature intensity and sea level height.
7. the construction method of fishing ground fishing feelings speed forecast operational system according to claim 1, it is characterized in that, described step (3) utilizes in real time/and the fishing ground environment factor quasi real time carries out fishing ground forecast as the model-driven factor, and realize the accurate forecast in fishing ground by the selection of fishing ground forecasting model and human expert knowledge.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410438468.9A CN104217254A (en) | 2014-08-29 | 2014-08-29 | Construction method of quick forecasting operation system of fishery fishing condition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410438468.9A CN104217254A (en) | 2014-08-29 | 2014-08-29 | Construction method of quick forecasting operation system of fishery fishing condition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104217254A true CN104217254A (en) | 2014-12-17 |
Family
ID=52098714
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410438468.9A Pending CN104217254A (en) | 2014-08-29 | 2014-08-29 | Construction method of quick forecasting operation system of fishery fishing condition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104217254A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106769903A (en) * | 2017-01-12 | 2017-05-31 | 南京渔管家物联网科技有限公司 | A kind of breeding water body algae concentration detection method |
| CN107766974A (en) * | 2017-09-30 | 2018-03-06 | 浙江海洋大学 | A kind of ocean fishing feelings Forecasting Methodology for merging a variety of data |
| CN108710979A (en) * | 2018-03-31 | 2018-10-26 | 西安电子科技大学 | A kind of Internet of Things yard craft dispatching method based on decision tree |
| CN109034105A (en) * | 2018-08-15 | 2018-12-18 | 上海海洋大学 | Tunny fishing ground position predicting method based on unmanned plane |
| CN109543612A (en) * | 2018-11-22 | 2019-03-29 | 浙江海洋大学 | A kind of Remote Sensing Data Processing method based on more granularities |
| CN109552570A (en) * | 2018-12-03 | 2019-04-02 | 华东师范大学 | A kind of unmanned boat for marine environmental monitoring |
| CN112052625A (en) * | 2020-08-13 | 2020-12-08 | 五邑大学 | Method for estimating and predicting building life based on big data |
| CN113268535A (en) * | 2021-06-03 | 2021-08-17 | 青岛励图高科信息技术有限公司 | System and method for performing efficient space-time extraction on ocean forecast data |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7844517B2 (en) * | 1996-01-18 | 2010-11-30 | Planalytics, Inc. | System, method, and computer program product for forecasting weather-based demand using proxy data |
| CN103235982A (en) * | 2013-04-16 | 2013-08-07 | 中国水产科学研究院东海水产研究所 | BNM-based (Bayesian network model-based) fishery forecasting method |
-
2014
- 2014-08-29 CN CN201410438468.9A patent/CN104217254A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7844517B2 (en) * | 1996-01-18 | 2010-11-30 | Planalytics, Inc. | System, method, and computer program product for forecasting weather-based demand using proxy data |
| CN103235982A (en) * | 2013-04-16 | 2013-08-07 | 中国水产科学研究院东海水产研究所 | BNM-based (Bayesian network model-based) fishery forecasting method |
Non-Patent Citations (3)
| Title |
|---|
| 崔学森等: "基于分类回归树算法的东南太平洋智利竹筴鱼渔场预报", 《中国海洋大学学报》 * |
| 张衡等: "基于遥感数据的智利竹筴鱼渔场预报系统", 《农业工程学报》 * |
| 牛明香等: "基于广义可加模型和案例推理的东南太平洋智利竹筴鱼中心渔场预报", 《海洋环境科学》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106769903A (en) * | 2017-01-12 | 2017-05-31 | 南京渔管家物联网科技有限公司 | A kind of breeding water body algae concentration detection method |
| CN106769903B (en) * | 2017-01-12 | 2020-05-19 | 南京渔管家物联网科技有限公司 | Method for detecting concentration of algae in aquaculture water |
| CN107766974A (en) * | 2017-09-30 | 2018-03-06 | 浙江海洋大学 | A kind of ocean fishing feelings Forecasting Methodology for merging a variety of data |
| CN108710979A (en) * | 2018-03-31 | 2018-10-26 | 西安电子科技大学 | A kind of Internet of Things yard craft dispatching method based on decision tree |
| CN108710979B (en) * | 2018-03-31 | 2022-02-18 | 西安电子科技大学 | Internet of things port ship scheduling method based on decision tree |
| CN109034105A (en) * | 2018-08-15 | 2018-12-18 | 上海海洋大学 | Tunny fishing ground position predicting method based on unmanned plane |
| CN109034105B (en) * | 2018-08-15 | 2020-08-04 | 上海海洋大学 | Tuna fishery position prediction method based on unmanned aerial vehicle |
| CN109543612A (en) * | 2018-11-22 | 2019-03-29 | 浙江海洋大学 | A kind of Remote Sensing Data Processing method based on more granularities |
| CN109543612B (en) * | 2018-11-22 | 2023-04-21 | 浙江海洋大学 | Multi-granularity-based remote sensing data processing method |
| CN109552570A (en) * | 2018-12-03 | 2019-04-02 | 华东师范大学 | A kind of unmanned boat for marine environmental monitoring |
| CN112052625A (en) * | 2020-08-13 | 2020-12-08 | 五邑大学 | Method for estimating and predicting building life based on big data |
| CN113268535A (en) * | 2021-06-03 | 2021-08-17 | 青岛励图高科信息技术有限公司 | System and method for performing efficient space-time extraction on ocean forecast data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104217254A (en) | Construction method of quick forecasting operation system of fishery fishing condition | |
| Sohl et al. | Modeled historical land use and land cover for the conterminous United States | |
| Li et al. | Distribution of hotspots of chub mackerel based on remote-sensing data in coastal waters of China | |
| Honey et al. | From rags to fishes: data-poor methods for fishery managers | |
| CN105787591B (en) | A kind of fishing ground forecasting procedure using multiple dimensioned environmental characteristic | |
| Hill et al. | The Australian Integrated Marine Observing System: delivering data streams to address national and international research priorities | |
| Pécuchet et al. | Impacts of the local environment on recruitment: a comparative study of North Sea and Baltic Sea fish stocks | |
| Spillman et al. | Predicting environmental drivers for prawn aquaculture production to aid improved farm management | |
| Wang et al. | Spatio-temporal distribution of skipjack in relation to oceanographic conditions in the west-central Pacific Ocean | |
| Jansen | First‐year survival of North East Atlantic mackerel (Scomber scombrus) from 1998 to 2012 appears to be driven by availability of Calanus, a preferred copepod prey | |
| Sutrisno et al. | The development of spatial decision support system tool for marine spatial planning | |
| Raffaelli et al. | Big data and ecosystem research programmes | |
| Jacobsen et al. | Climate-mediated stock redistribution causes increased risk and challenges for fisheries management | |
| McMahan et al. | Curating and visualizing dense networks of monsoon precipitation data: integrating computer science into forward looking climate services development | |
| Suprenand et al. | Strategic assessment of fisheries independent monitoring programs in the Gulf of Mexico | |
| Meaden | Geographical Information Systems (GIS) in fisheries management and research | |
| Wang et al. | The effects of climate-induced environmental variability on Pacific Ocean squids | |
| Kelly et al. | Capturing big fisheries data: Integrating fishers’ knowledge in a web-based decision support tool | |
| Vergara‐Solana et al. | Growth and survival model of Pacific bluefin tuna (Thunnus orientalis) for capture‐based aquaculture in Mexico | |
| Wanchana et al. | Application of GIS and remote sensing for advancing sustainable fisheries management in Southeast Asia | |
| Buxton et al. | Review of the harvest strategy and MCDA process for the Tasmanian abalone fishery | |
| Lara-Lopez et al. | From research to end-users, tracing the path of ocean observations in Australia | |
| Schwing et al. | Future research requirements for understanding the effects of climate variability on fisheries for their management | |
| McClenachan et al. | Global research priorities for historical ecology to inform conservation | |
| Kyllingstad et al. | SMARTFISH H2020 D5. 3: FishData analysis (Open access revision) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20141217 |
|
| WD01 | Invention patent application deemed withdrawn after publication |