CN103235982A - BNM-based (Bayesian network model-based) fishery forecasting method - Google Patents
BNM-based (Bayesian network model-based) fishery forecasting method Download PDFInfo
- Publication number
- CN103235982A CN103235982A CN2013101320534A CN201310132053A CN103235982A CN 103235982 A CN103235982 A CN 103235982A CN 2013101320534 A CN2013101320534 A CN 2013101320534A CN 201310132053 A CN201310132053 A CN 201310132053A CN 103235982 A CN103235982 A CN 103235982A
- Authority
- CN
- China
- Prior art keywords
- bayesian network
- fishing ground
- network model
- data
- procedure based
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a BNM-based (Bayesian network model-based) fishery forecasting method. The method includes the steps of discretizing historical ocean information datasets of fishery environment; establishing a table of conditional probability between Bayesian network structure charts and Bayesian network nodes; calculating a posterior probability distribution formula of fishery by the Bayesian network structure chart obtained by optimal learning algorithm; and forecasting the fishery by the obtained posterior probability distribution formula. The function of rapidly forecasting for the fishery can be realized by the BNM-based fishery forecasting method.
Description
Technical field
The present invention relates to movement pattern of fish forecasting technique field, fishing ground, particularly relate to a kind of fishing ground forecasting procedure based on Bayesian network model.
Background technology
The fundamental space that the ocean water body environment is depended on for existence as sea life and marine fishes, the growing of sea life and fish, life habit, spatial and temporal distributions etc. are inseparable with marine environment, can develop and then carry out fishing ground fishing mutual affection and analyse forecast by the space-time dynamic of the information of ocean water body environmental element being obtained, the fishing ground is studied in the grasp of marine fishes life habit accordingly.During traditional fishery was fished for, the captain judged possible position, fishing ground according to straightforward procedures such as visual color intensity of sea water, the ocean current flow direction, one-point measurement sea surface temperatures, and this method is comparatively backward, is difficult to accurately seek the formation position in fishing ground.Because oceanic fishes generally has migration habit highly transboundary, the fishing ground distributes and has characteristics such as regionality, space-time changeableness, complicacy, defectives such as being subjected to the shortage of fishing ground environment information and fishing ground rule research deficiency is fished in traditional fishery, limited catching rate and output widely, corresponding fishing ground fishery forescast method research also seldom.
Because satellite remote sensing technology can be on a large scale, standard is obtained marine environment information synchronously, rapidly, the information such as ocean temperature, ocean chlorophyll concentration and sea level height of therefore utilizing the satellite remote sensing technology monitoring to obtain are used relative ripe in fisheriesx hydrography.At present, the forecast relations of considering one or both environmental elements and position, fishing ground in fishing ground seldom relate to the relation research of multiple environmental element and position, fishing ground more, more do not consider whether to have a condition correlationship between the environmental element.
Summary of the invention
Technical matters to be solved by this invention provides a kind of fishing ground forecasting procedure based on Bayesian network model, can realize the speed forecast function in fishing ground.
The technical solution adopted for the present invention to solve the technical problems is: a kind of fishing ground forecasting procedure based on Bayesian network model is provided, may further comprise the steps:
(1) each the historical marine information data set to fishing ground environment carries out the discretize processing;
(2) set up the conditional probability table between the node in bayesian network structure figure and the Bayesian network;
(3) choose the bayesian network structure figure that optimum learning algorithm obtains and calculate the posterior probability distribution formula in fishing ground;
(4) according to the posterior probability distribution formula that obtains the fishing ground is forecast.
Utilize the definition of fractile in the described step (1), respectively each environmental variance has been carried out the discretize classification and handled.
Set up bayesian network structure figure in the described step (2) and comprise following substep:
(21) the marine information data after repairing are carried out isoline and contour surface drawing;
(22) demonstrate marine information with labeling form, show that with the different colours classification contour surface distributes, make each environmental data in fishing ground be stored in different figure layers respectively;
(23) difference figure layer is superposeed obtain bayesian network structure figure.
Marine information in the described step (21) is repaired by anti-distance weighting method.
Described step (22) medium value line adopts and extracts the isoline rough set earlier, and the mode of refinement is drawn or carried out equivalent search by the regular triangulation network or quadrilateral and generates again.
Figure layer in the described step (22) represents with the combining form of grid and vector data.
Optimum learning algorithm in the described step (3) is divided into learning data set and test data set two parts by the data with discretize, selects different learning algorithms for use, and marks with two or more functions, filters out that the highest learning algorithm of scoring obtains.
Optimum learning algorithm in the described step (3) is the structure learning algorithm based on constraint.
Beneficial effect
Owing to adopted above-mentioned technical scheme, the present invention compared with prior art, have following advantage and good effect: the present invention adopts the Bayesian network model principle, by the study to marine environment data and the fishery output data of history, made up about several fishing ground environment data and the bayesian network structure figure that fishes for data, determined the posterior probability distribution formula that the fishing ground forms according to this, thereby obtain the fishing ground probability in each fishing zone in the selected marine site, can realize the speed forecast function in fishing ground, for modernized fishery provides a kind of new fishing ground forecasting procedure.
Description of drawings
Fig. 1 is process flow diagram of the present invention;
Fig. 2 is southeast Pacific Chile position, jack mackerel fishing ground and Bayesian network fishing ground probability comparison diagram.
Embodiment
Below in conjunction with specific embodiment, further set forth the present invention.Should be understood that these embodiment only to be used for explanation the present invention and be not used in and limit the scope of the invention.Should be understood that in addition those skilled in the art can make various changes or modifications the present invention after the content of having read the present invention's instruction, these equivalent form of values fall within the application's appended claims institute restricted portion equally.
Embodiments of the present invention relate to a kind of fishing ground forecasting procedure based on Bayesian network model, as shown in Figure 1, adopt sea surface temperature (SST), chlorophyll concentration (chl-a), sea surface temperature anomaly (△ SST), chlorophyll concentration anomaly (△ chl-a) and sea surface temperature gradient intensity 5 envirment factors such as (Grad) of satellite remote sensing technology acquisition as predictor, with the response factor of catch per unit effort (CPUE) as model.For classification capacity and the raising counting yield that improves data, at first each history data set is carried out discretize and handle; Set up the conditional probability table between the node in bayesian network structure figure and the Bayesian network; Choose the bayesian network structure figure that optimum learning algorithm obtains and calculate the posterior probability distribution formula in fishing ground, finally become the fishing ground forecast model products to be distributed to fisheries management department and manufacturing enterprise in conjunction with the GIS technical drawing.
The present invention mainly comprises Bayesian network study and drawing issue two parts:
(1) machine learning process
1. the fishing ground environment historical data is obtained and is handled.Monthly average sea surface temperature SST and chlorophyll-a concentration chl-a data all can provide three grades of products from the polar orbit environmental remote sensing satellite MODIS of NASA website, and spatial resolution is 9km.Sea surface temperature anomaly △ SST and chlorophyll-a concentration anomaly △ chl-a and sea surface temperature gradient intensity Grad data are also obtained by above-mentioned data computation.
Historical fishery harvesting production data is the production statistical data of zone of the open sea, the Pacific Ocean Chinese large-scale trawlboat of fishing for southeast, and gridding is processed into 1 ° * 1 ° fishing zone, by formula (1) unit of account fishing effort catch (CPUE),
CPUE＝C
month/N
month （1）
C wherein
MonthRepresent in each fishing zone one month output, N
MonthRepresent in this fishing zone total net of one month.
The discretize of data has very important meaning to machine learning or data mining, utilizes the definition of fractile α (0＜α＜1), respectively each environmental variance has been carried out the discretize classification and has handled.Chlorophyll a concentration c hl-a, sea surface temperature SST in the environmental variance and sea surface temperature gradient intensity Grad are divided into 4 grades, fractile α is respectively 0,0.25,0.50,0.75 with 1, and sea surface temperature anomaly △ SST, chlorophyll-a concentration anomaly △ Chl-a and catch per unit effort CPUE data are divided into 3 grades, fractile α is respectively 0,0.333,0.667 and 1.
2. the foundation of Bayesian network model, Bayesian network claims belief network again, is the graphical model of probabilistic relation between a series of variablees.The data of discretize are divided into learning data set (2002-2008) and test data set (2009) two parts, wherein for totally 942 of the data of learning.Select different learning algorithms for use, and mark with five kinds of functions, filter out optimum learning algorithm (namely based on the structure learning algorithm that retrains, IAMB) carry out the calculating of fishing ground conditional probability, a plurality of environmental factors have been considered to greatest extent in the network structure that algorithm obtains thus, so the bayesian network structure figure that selects for use this algorithm to obtain calculates the fishing ground probability.This model has reflected that between fishing ground formation and month, sea surface temperature, chlorophyll-a concentration, sea surface temperature gradient, sea surface temperature anomaly and the chlorophyll concentration anomaly be that condition is relevant.
Bayesian network has than higher advantage at fishing ground forecast probability, and it is the combination of directed acyclic graph and probability theory, and the joint probability between stochastic variable is expressed intuitively, has solid probability theory basis.And in general recurrence and classification problems such as (as decision tree and artificial neural networks), and exceed the correlationship of considering between variable, Bayesian network then provides probability incidence relation clearly.
(2) businessization drawing and issue
1. the pre-service of real time data.Top layer marine environment information (SST, chl-a) mainly obtain by remote sensing satellite monitoring inverting, but the reasons such as time, weather conditions of passing by owing to satellite, the remotely-sensed data that obtains can lack to some extent, need to adopt different interpolation methods (as Kriging, Spline, IDW, Naturalneighbor) that sampled point is encrypted interpolation and repair data, carry out equivalent search by the regular triangulation network or quadrilateral again and generate the view picture isogram.The U.S. MODIS remotely-sensed data that sea surface temperature and chlorophyll real time data adopt East Sea aquatic products research institute fishing remote sensing information laboratory to receive, interpolation utilization " extra large temperature chlorophyll data handling system " software (National Copyright Administration of the People's Republic of China's computer software registration number 0258719) is finished.
2. the calculating of fishery field probability.In the middle of the posterior probability distribution formula of the Bayesian network model that the substitution of above-mentioned real time environment data is filtered out, with reference to by the resultant probability distribution table of machine learning, the fishing ground probability in each fishing zone in the selected marine site is calculated in pointwise.
3. fishing area chart is made and output.Fishing ground and environmental product are made the map delamination technology that adopts, sea surface temperature figure layer, chlorophyll figure layer, fishing ground probability graph layer, current chart layer, geographic coordinate, land terrestrial reference etc. are stored in different figure layers respectively, construct a control tree simultaneously, figure layer interpolation, deletion, modification, stack etc. are controlled respectively, and with different colours and symbol sea surface temperature, chlorophyll and ocean current etc. are carried out visual mark, probability size in fishing ground adopts the grid of different colours to represent.After handling again at the quasi real time marine environment data of obtaining weekly, calculate fishing ground probability forecast figure according to Bayesian network model, preserve into that the JPG picture format carries out the network issue or mail sends to relevant fishing sector and manufacturing enterprise.
Chilean jack mackerel fishing ground (zone is 20～50 ° of S, 80～130 ° of W) forecast with the southeast Pacific marine site is that example further specifies the present invention below.
At first, read the satellite remote sensing data and utilize " extra large temperature chlorophyll data handling system " software that the data of disappearance are carried out interpolation and repairing, the ocean current data are by buying the product acquisition of U.S. ASA company and using " 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 and the flow direction.
Secondly, data such as the sea surface temperature after repairing, chlorophyll are carried out isoline and contour surface drawing, demonstrate temperature value and chlorophyll test value with labeling form, show that with the different colours classification contour surface distributes, sea surface temperature gradient, sea surface temperature anomaly and chlorophyll concentration anomaly are also finished by this software, and each environmental data after the drafting is stored in different figure layers respectively.Wherein sea surface temperature and chlorophyll data modification method adopt the anti-distance weighting of IDW() method, the characteristics intensive at data point, that the drawing scope is big adopt isoline rough set, the method for refinement again extracted earlier, reduce taking of memory source, accelerated to follow the tracks of and generate the speed of isoline.Adopt the different figure layers of electronic chart management, made things convenient for demonstration, convergent-divergent and the roaming of whole marine site image.The method that the figure layer has adopted grid to be combined with vector data, stack order to difference figure layer can freely customize, can carry out that figure is stacked to be added to environmental datas such as sea surface temperature, chlorophyll and ocean currents, finally be presented at a window, make things convenient for relatively fishing ground environment situation of change of user.
At last, utilize Bayesian network model forecast module to calculate Chilean jack mackerel fishing sea situation prior probability table (Fig. 2) and each fishing zone probable value, and it is graphical, and be stored as the polar plot layer.With the stack with it respectively of information such as sea surface temperature figure layer, chlorophyll figure layer, current chart layer, geographic coordinate.Two kinds of patterns are adopted in issue: (1) preserves into the JPG picture format, utilizes fax to send to relevant fishing sector and manufacturing enterprise by EMAIL or after printing.(2) at first the figure layer data of whole electronic chart is compressed (zip form), recycling is installed to user's software client self-timing and is downloaded, carry out decompress(ion) again and restore, the user's that is more convenient for operation with browse.
Be not difficult to find, the present invention adopts the Bayesian network model principle, by the study to marine environment data and the fishery output data of history, made up about several fishing ground environment data and the bayesian network structure figure that fishes for data, determined the posterior probability distribution formula that the fishing ground forms according to this, thereby obtain the fishing ground probability in each fishing zone in the selected marine site, can realize the speed forecast function in fishing ground, for modernized fishery provides a kind of new fishing ground forecasting procedure.
Claims (9)
1. the fishing ground forecasting procedure based on Bayesian network model is characterized in that, may further comprise the steps:
(1) each the historical marine information data set to fishing ground environment carries out the discretize processing;
(2) set up the conditional probability table between the node in bayesian network structure figure and the Bayesian network;
(3) choose the bayesian network structure figure that optimum learning algorithm obtains and calculate the posterior probability distribution formula in fishing ground;
(4) according to the posterior probability distribution formula that obtains the fishing ground is forecast.
2. the fishing ground forecasting procedure based on Bayesian network model according to claim 1 is characterized in that described step
(1) utilizes the definition of fractile in, respectively each environmental variance has been carried out the discretize classification and handled.
3. the fishing ground forecasting procedure based on Bayesian network model according to claim 1 is characterized in that, described marine information data comprise sea surface temperature, chlorophyll concentration, sea surface temperature anomaly, chlorophyll concentration anomaly and sea surface temperature gradient intensity.
4. the fishing ground forecasting procedure based on Bayesian network model according to claim 1 is characterized in that described step
(2) set up bayesian network structure figure in and comprise following substep:
(21) the marine information data after repairing are carried out isoline and contour surface drawing;
(22) demonstrate marine information with labeling form, show that with the different colours classification contour surface distributes, make each environmental data in fishing ground be stored in different figure layers respectively;
(23) difference figure layer is superposeed obtain bayesian network structure figure.
5. the fishing ground forecasting procedure based on Bayesian network model according to claim 4 is characterized in that described step
(21) marine information in is repaired by anti-distance weighting method.
6. the fishing ground forecasting procedure based on Bayesian network model according to claim 4 is characterized in that described step
(22) the medium value line adopts and extracts the isoline rough set earlier, and the mode of refinement is drawn or carried out equivalent search by the regular triangulation network or quadrilateral and generates again.
7. the fishing ground forecasting procedure based on Bayesian network model according to claim 4 is characterized in that described step
(22) the figure layer in represents with the combining form of grid and vector data.
8. the fishing ground forecasting procedure based on Bayesian network model according to claim 1 is characterized in that described step
(3) the optimum learning algorithm in is divided into learning data set and test data set two parts by the data with discretize, selects different learning algorithms for use, and marks with two or more functions, filters out that the highest learning algorithm of scoring obtains.
9. the fishing ground forecasting procedure based on Bayesian network model according to claim 1 is characterized in that described step
(3) the optimum learning algorithm in is the structure learning algorithm based on constraint.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013101320534A CN103235982A (en) | 2013-04-16 | 2013-04-16 | BNM-based (Bayesian network model-based) fishery forecasting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013101320534A CN103235982A (en) | 2013-04-16 | 2013-04-16 | BNM-based (Bayesian network model-based) fishery forecasting method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103235982A true CN103235982A (en) | 2013-08-07 |
Family
ID=48884021
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013101320534A Pending CN103235982A (en) | 2013-04-16 | 2013-04-16 | BNM-based (Bayesian network model-based) fishery forecasting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103235982A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103942286A (en) * | 2014-04-10 | 2014-07-23 | 北京邮电大学 | Bayesian classification data mining method for conducting correlation analysis by correlation coefficients |
| CN104217254A (en) * | 2014-08-29 | 2014-12-17 | 中国水产科学研究院东海水产研究所 | Construction method of quick forecasting operation system of fishery fishing condition |
| CN104834966A (en) * | 2015-04-15 | 2015-08-12 | 中国水产科学研究院东海水产研究所 | Fishery forecasting method based on ant colony classifying algorithm |
| CN105654210A (en) * | 2016-02-26 | 2016-06-08 | 中国水产科学研究院东海水产研究所 | Ensemble learning fishery forecasting method utilizing ocean remote sensing multi-environmental elements |
| CN105787591A (en) * | 2016-02-26 | 2016-07-20 | 中国水产科学研究院东海水产研究所 | Fishing ground forecast method through adoption of multi-scale environment characteristics |
| CN106250980A (en) * | 2016-07-22 | 2016-12-21 | 上海海洋大学 | The sliding squid cental fishing ground Forecasting Methodology of a kind of Argentina |
| CN107944590A (en) * | 2016-10-13 | 2018-04-20 | 阿里巴巴集团控股有限公司 | A kind of method and apparatus of fishing condition analysis and forecasting |
| CN108665104A (en) * | 2018-05-14 | 2018-10-16 | 华际卫星通信有限公司 | A kind of fishing ground forecasting procedure based on LSTM |
| CN111275065A (en) * | 2018-12-05 | 2020-06-12 | 中国科学院烟台海岸带研究所 | Aquaculture space partitioning method based on marine environment multiple attributes |
| CN114819271A (en) * | 2022-03-22 | 2022-07-29 | 中国水产科学研究院东海水产研究所 | Saury fishing ground detection route and fish finding method based on refined marine environment characteristic field |
| US11452286B2 (en) | 2016-07-22 | 2022-09-27 | Shanghai Ocean University | Method of predicting central fishing ground of flying squid family ommastrephidae |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101452077A (en) * | 2007-12-03 | 2009-06-10 | 中国水产科学研究院东海水产研究所 | Tunny fishing ground forecasting method |
| JP4849797B2 (en) * | 2004-12-03 | 2012-01-11 | 喜代志 伊藤 | Fishing ground prediction device |
| CN102833680A (en) * | 2012-09-11 | 2012-12-19 | 中国水产科学研究院东海水产研究所 | Position-based marine fishery information serving method |
-
2013
- 2013-04-16 CN CN2013101320534A patent/CN103235982A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4849797B2 (en) * | 2004-12-03 | 2012-01-11 | 喜代志 伊藤 | Fishing ground prediction device |
| CN101452077A (en) * | 2007-12-03 | 2009-06-10 | 中国水产科学研究院东海水产研究所 | Tunny fishing ground forecasting method |
| CN102833680A (en) * | 2012-09-11 | 2012-12-19 | 中国水产科学研究院东海水产研究所 | Position-based marine fishery information serving method |
Non-Patent Citations (2)
| Title |
|---|
| 周为峰等: "基于贝叶斯概率的印度洋大眼金枪鱼渔场预报", 《渔业信息与战略》 * |
| 周为峰等: "基于贝叶斯概率的印度洋大眼金枪鱼渔场预报", 《渔业信息与战略》, vol. 27, no. 3, 25 August 2012 (2012-08-25), pages 214 - 218 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103942286A (en) * | 2014-04-10 | 2014-07-23 | 北京邮电大学 | Bayesian classification data mining method for conducting correlation analysis by correlation coefficients |
| CN104217254A (en) * | 2014-08-29 | 2014-12-17 | 中国水产科学研究院东海水产研究所 | Construction method of quick forecasting operation system of fishery fishing condition |
| CN104834966B (en) * | 2015-04-15 | 2018-07-24 | 中国水产科学研究院东海水产研究所 | A kind of fishing ground forecasting procedure based on ant colony sorting algorithm |
| CN104834966A (en) * | 2015-04-15 | 2015-08-12 | 中国水产科学研究院东海水产研究所 | Fishery forecasting method based on ant colony classifying algorithm |
| CN105787591B (en) * | 2016-02-26 | 2019-08-20 | 中国水产科学研究院东海水产研究所 | A kind of fishing ground forecasting procedure using multiple dimensioned environmental characteristic |
| CN105787591A (en) * | 2016-02-26 | 2016-07-20 | 中国水产科学研究院东海水产研究所 | Fishing ground forecast method through adoption of multi-scale environment characteristics |
| CN105654210A (en) * | 2016-02-26 | 2016-06-08 | 中国水产科学研究院东海水产研究所 | Ensemble learning fishery forecasting method utilizing ocean remote sensing multi-environmental elements |
| CN106250980A (en) * | 2016-07-22 | 2016-12-21 | 上海海洋大学 | The sliding squid cental fishing ground Forecasting Methodology of a kind of Argentina |
| US11452286B2 (en) | 2016-07-22 | 2022-09-27 | Shanghai Ocean University | Method of predicting central fishing ground of flying squid family ommastrephidae |
| CN107944590A (en) * | 2016-10-13 | 2018-04-20 | 阿里巴巴集团控股有限公司 | A kind of method and apparatus of fishing condition analysis and forecasting |
| CN107944590B (en) * | 2016-10-13 | 2022-02-22 | 阿里巴巴集团控股有限公司 | Method and equipment for analyzing and forecasting fishing situations |
| CN108665104A (en) * | 2018-05-14 | 2018-10-16 | 华际卫星通信有限公司 | A kind of fishing ground forecasting procedure based on LSTM |
| CN111275065A (en) * | 2018-12-05 | 2020-06-12 | 中国科学院烟台海岸带研究所 | Aquaculture space partitioning method based on marine environment multiple attributes |
| CN111275065B (en) * | 2018-12-05 | 2023-08-15 | 中国科学院烟台海岸带研究所 | Marine environment multi-attribute-based aquaculture space partitioning method |
| CN114819271A (en) * | 2022-03-22 | 2022-07-29 | 中国水产科学研究院东海水产研究所 | Saury fishing ground detection route and fish finding method based on refined marine environment characteristic field |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103235982A (en) | BNM-based (Bayesian network model-based) fishery forecasting method | |
| Zhao et al. | Classifying airborne LiDAR point clouds via deep features learned by a multi-scale convolutional neural network | |
| Wu | GIS and remote sensing applications in wetland mapping and monitoring | |
| Leon et al. | Improving the synoptic mapping of coral reef geomorphology using object-based image analysis | |
| Dewi et al. | Fuzzy classification for shoreline change monitoring in a part of the northern coastal area of Java, Indonesia | |
| CN108153861B (en) | River mouth fishery resource cluster distribution analysis method based on GIS | |
| Matić et al. | Oscillating Adriatic temperature and salinity regimes mapped using the Self-Organizing Maps method | |
| CN105787501A (en) | Vegetation classification method capable of automatically selecting features in power transmission line corridor area | |
| Gleason et al. | A Fusion Approach for Tree Crown Delineation from Lidar Data. | |
| CN113971769B (en) | Coastal zone regional function long time sequence identification method based on multi-source big data | |
| CN116467565A (en) | Enteromorpha green tide plaque optimal search area forecasting method | |
| Yousef et al. | Shoreline extraction from the fusion of LiDAR DEM data and aerial images using mutual information and genetic algrithms | |
| CN108038433A (en) | Urban trees carbon content method of estimation based on more echo airborne laser scanning datas | |
| CN109658477A (en) | A kind of DEM generating algorithm based on LIDAR data | |
| Leon et al. | Morphological characterisation of reef types in Torres Strait and an assessment of their carbonate production | |
| Liu et al. | Using the ART-MMAP neural network to model and predict urban growth: a spatiotemporal data mining approach | |
| Markogianni et al. | Landuse and NDVI change analysis of Sperchios river basin (Greece) with different spatial resolution sensor data by Landsat/MSS/TM and OLI | |
| Cheng et al. | High-resolution mapping of seaweed aquaculture along the Jiangsu coast of China using Google Earth Engine (2016–2022) | |
| Li et al. | A novel method for cliff vegetation estimation based on the unmanned aerial vehicle 3D modeling | |
| Ma et al. | XGBoost-based analysis of the relationship between urban 2D/3D morphology and seasonal gradient land surface temperature | |
| CN101561882A (en) | Sub-pixel spatial mapping method based on spatial correlation | |
| CN101452077A (en) | Tunny fishing ground forecasting method | |
| Yuan et al. | Spatial scaling in geomorphology: Extrapolating micro-erosion measurements to the landform scale on shore platforms using unoccupied aerial vehicles | |
| CN116183868A (en) | Remote sensing estimation method and system for organic carbon in soil of complex ecological system | |
| Li et al. | Measuring detailed urban vegetation with multisource high-resolution remote sensing imagery for environmental design and planning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130807 |
|
| RJ01 | Rejection of invention patent application after publication |