CN117152633A - Method for inverting oxygen jump layer of low oxygen area based on Argo buoy and remote sensing data - Google Patents
Method for inverting oxygen jump layer of low oxygen area based on Argo buoy and remote sensing data Download PDFInfo
- Publication number
- CN117152633A CN117152633A CN202311143030.3A CN202311143030A CN117152633A CN 117152633 A CN117152633 A CN 117152633A CN 202311143030 A CN202311143030 A CN 202311143030A CN 117152633 A CN117152633 A CN 117152633A
- Authority
- CN
- China
- Prior art keywords
- data
- oxygen
- neural network
- dissolved oxygen
- layer
- 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
- 229910052760 oxygen Inorganic materials 0.000 title claims abstract description 129
- 239000001301 oxygen Substances 0.000 title claims abstract description 129
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 title claims abstract description 128
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000013528 artificial neural network Methods 0.000 claims abstract description 39
- 238000012549 training Methods 0.000 claims abstract description 30
- 206010021143 Hypoxia Diseases 0.000 claims description 18
- 230000007954 hypoxia Effects 0.000 claims description 13
- 210000002569 neuron Anatomy 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000001146 hypoxic effect Effects 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 6
- 230000000875 corresponding effect Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- SESFRYSPDFLNCH-UHFFFAOYSA-N benzyl benzoate Chemical compound C=1C=CC=CC=1C(=O)OCC1=CC=CC=C1 SESFRYSPDFLNCH-UHFFFAOYSA-N 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 239000013049 sediment Substances 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 1
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Multimedia (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Remote Sensing (AREA)
- Astronomy & Astrophysics (AREA)
- Investigating Or Analyzing Non-Biological Materials By The Use Of Chemical Means (AREA)
Abstract
The invention discloses a method for inverting an oxygen jump layer of a low oxygen area based on an Argo buoy and remote sensing data, which is characterized by comprising the following steps of: constructing a training set; constructing a BP neural network, and training through a training set; acquiring Argo buoy data and dissolved oxygen distribution influence factor data at an oxygen jump layer of a low oxygen area to be inverted in a target area, and taking the Argo buoy data and the dissolved oxygen distribution influence factor data as inversion basic data; inputting inversion basic data into the trained BP neural network, and taking the output of the trained BP neural network as an inversion result of an oxygen jump layer of a low oxygen area to be inverted in a target area. The invention can quickly utilize the dissolved oxygen data which is lost in the traditional Argo data in the BGC-Argo buoy data inversion area in the years, thereby better monitoring the space-time distribution of the dissolved oxygen and oxygen jump layer in the low oxygen area.
Description
Technical Field
The invention relates to the field of inversion of oxygen jump layers in low oxygen areas, in particular to a method for inverting oxygen jump layers in low oxygen areas based on Argo buoys and remote sensing data.
Background
Dissolved oxygen is an indispensable substance for the life activities of the ocean, and its content is one of the important factors for maintaining the balance of the marine ecosystem. When the dissolved oxygen concentration of the water body is lower than 60-120 mu mol.kg -1 When this happens, it will seriously threaten the survival of most large marine animals and even lead to anoxic death. The ocean is distributed with four distinct hypoxic regions, north indian ocean arabic and mendalaan bay, tropical equatorial north pacific (0-25 ° N) and south eastern pacific, respectively.
The existing research for obtaining the dissolved oxygen distribution in the low oxygen area is mainly based on voyage observation, and the obtained data has strong space-time discreteness. The number of sampling points of the navigation observation data is small, the period is short, the seasonal and annual change characteristics of the dissolved oxygen in the sea area can not be obtained, and the monitoring of the sea hypoxia change with a large range of continuous space-time scale is difficult to realize.
The BGC-Argo buoy loaded with the dissolved oxygen sensor, which is put in mass in recent years, provides first-hand information for marine hypoxia research. Although the BGC-Argo buoy can directly acquire the dissolved oxygen data of the water body, the BGC-Argo buoy can only acquire the dissolved oxygen data of a local area due to the small quantity of the BGC-Argo buoy, and the actual monitoring effect is limited.
Therefore, how to invert the oxygen jump layer in the vast hypoxia area based on the limited BGC-Argo buoy and the large number of Argo buoy data to obtain the corresponding dissolved oxygen data is beneficial to saving the cost of monitoring the marine hypoxia change and improving the monitoring efficiency.
Disclosure of Invention
Aiming at the defects in the prior art, the method for inverting the oxygen jump layer of the hypoxia zone based on the Argo buoy and the remote sensing data solves the problem that the prior art is difficult to realize large-scale continuous time-space scale ocean hypoxia change monitoring.
In order to achieve the aim of the invention, the invention adopts the following technical scheme:
the method for inverting the oxygen jump layer of the low oxygen area based on the Argo buoy and the remote sensing data is characterized by comprising the following steps of:
s1, constructing a training set: the method comprises the steps of obtaining dissolved oxygen data based on a BGC-Argo buoy of a target area, and taking the dissolved oxygen data as a training label; acquiring Argo buoy data and dissolved oxygen distribution influencing factors of a target area, and taking the Argo buoy data and the dissolved oxygen distribution influencing factors as training data;
s2, constructing a BP neural network, and training through a training set to obtain the trained BP neural network;
s3, acquiring Argo buoy data and dissolved oxygen distribution influence factor data at an oxygen jump layer of a low oxygen region to be inverted in a target region, and taking the Argo buoy data and the dissolved oxygen distribution influence factor data as inversion basic data;
s4, inputting inversion basic data into the trained BP neural network, and taking the output of the trained BP neural network as an inversion result of an oxygen jump layer of a low oxygen area to be inverted in the target area.
Further, the dissolved oxygen distribution influencing factors in step S1 include 23 ℃, 24 ℃, 25 ℃, 26 ℃ and sea surface height anomaly data.
Further, after the dissolved oxygen distribution influence factor data is obtained, the maximum value, the minimum value and the average value of each dissolved oxygen distribution influence factor are read, and according to the formula:
normalizing, and taking normalized data as training data; wherein X is norm Is a normalization result; x is the data value of the dissolved oxygen distribution influencing factor; x is X mean An average value of the dissolved oxygen distribution influencing factors; x is X max Is the maximum value of the dissolved oxygen distribution influencing factors; x is X min Is the minimum value of the dissolved oxygen distribution influencing factor.
Further, the BP neural network in step S2 includes an input layer, an hidden layer, and an output layer; the number of neurons of the input layer is equal to the number of dissolved oxygen distribution influencing factors; the number of hidden layer neurons is determined in the BP neural network training process; the number of neurons of the output layer is one; the transfer functions of the input layer to the hidden layer and the hidden layer to the output layer are both the tranlm functions.
Further, the number of hidden layer neurons is 10.
Further, the training process of the BP neural network is as follows:
and carrying out error calculation on the output data of the current BP neural network and the corresponding training label, and adjusting the parameters of the current BP neural network in a counter-propagation mode according to an error calculation result until the error value of the output result of the current BP neural network and the corresponding training label is smaller than or equal to a threshold value, and storing the parameters of the current BP neural network to obtain the trained BP neural network.
Further, the trained BP neural network outputs the inversion result into an excel format.
The beneficial effects of the invention are as follows:
1. the inversion of the dissolved oxygen data in the past year is realized based on the isothermal line depth of the Argo buoy at 23-26 ℃ and the remote sensing sea surface height abnormal data, and the dissolved oxygen data which are lost in the past year of the traditional Argo data in the BGC-Argo buoy data inversion area can be rapidly utilized, so that the space-time distribution of the dissolved oxygen and oxygen jump layer in the low oxygen area can be better monitored.
2. The method can approach any nonlinear function, further improve inversion accuracy, and is simple in calculation, short in calculation time and high in efficiency.
3. The invention solves the problem of accurately and rapidly inverting the depth of the oxygen jump layer of the low oxygen area under the given related parameters, and can establish an inversion model of the depth of the oxygen jump layer of the low oxygen area only by carrying out limited learning training, thereby inverting the data of the oxygen jump layer of the low oxygen area in different sea areas.
Drawings
FIG. 1 is a schematic flow chart of the method;
fig. 2 is a schematic structural diagram of a BP neural network in the present embodiment;
FIG. 3 is a graph showing the comparison of predicted and measured values of a BP neural network according to an embodiment;
FIG. 4 is a graph showing a fit between predicted and measured values of a test sample according to an embodiment.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and all the inventions which make use of the inventive concept are protected by the spirit and scope of the present invention as defined and defined in the appended claims to those skilled in the art.
As shown in fig. 1, the method for inverting the oxygen jump layer of the low oxygen area based on the Argo buoy and the remote sensing data comprises the following steps:
s1, constructing a training set: the method comprises the steps of obtaining dissolved oxygen data based on a BGC-Argo buoy of a target area, and taking the dissolved oxygen data as a training label; acquiring Argo buoy data and dissolved oxygen distribution influencing factors of a target area, and taking the Argo buoy data and the dissolved oxygen distribution influencing factors as training data;
s2, constructing a BP neural network, and training through a training set to obtain the trained BP neural network;
s3, acquiring Argo buoy data and dissolved oxygen distribution influence factor data at an oxygen jump layer of a low oxygen region to be inverted in a target region, and taking the Argo buoy data and the dissolved oxygen distribution influence factor data as inversion basic data;
s4, inputting inversion basic data into the trained BP neural network, and taking the output of the trained BP neural network as an inversion result of an oxygen jump layer of a low oxygen area to be inverted in the target area.
In one embodiment of the invention, the world ocean hypoxic region is approximately 15 x 10 in volume 6 km 3 Wherein the Bengala bay and Arabian sea account for about 21% of the global hypoxic region volume, and are about 3.13×10 6 km 3 . While the marine sediments produced by the gulf of manglar and the arabic sea account for about 59% of the marine sediments produced in the global hypoxic region. As one of four regions of hypoxia, the hypoxia of the gulf of Bengala severely affects the ecological environment and fishery resources of the sea area。
In the embodiment, the vertical distribution characteristics of dissolved oxygen in the upper ocean layer (0-200 m) in the Bengala bay area are analyzed by using BGC-Argo buoy data and satellite remote sensing data in the sea area in 2013-2017 by taking the Bengala bay hypoxia area as a research object. As a result, it was found that the depth of oxygen jump layer (DO 50. Mu. Mol. Kg) -1 ，D DO50 ) The correlation coefficient r is 0.93 and 0.81 respectively, and the correlation coefficient is positively correlated with an isothermal line (DT 23) at 23 ℃ and sea surface height abnormality (SLA). The sea surface temperature in the middle hypoxia zone of the Bengal bay is one of the main factors affecting the change of the dissolved oxygen in the sea surface, and the change of the oxygen jump layer is closely related to the mesoscale vortex in the sea.
By 2021, 9 months, a total of 426 BGC-argos are distributed throughout the sea, but only 3 BGCs-argos are running in the bay of the banglas. During 2010-2020, traditional Argo provided 2000 m 23826 sets of warm salt data on the ocean upper layer, while BGC-Argo provided only 3140 sets of dissolved oxygen data, only 13.2% of the former.
Based on the above study, 23 ℃, 24 ℃, 25 ℃, 26 ℃ and sea surface height anomaly data (SLA) were used as dissolved oxygen distribution influencing factors in the present implementation, namely, the five data were used as input variables of the BP neural network model. Specifically, based on BGC-Argo buoy data at three stations of the 2013-2016 montalakast, 23 ℃ isotherms (D T23 ) Isotherms at 24 ℃ (D) T24 ) Isotherms at 25 ℃ (D) T25 ) Isotherms at 26 ℃ (D) T26 ) And sea surface height anomalies (SLA) and the like.
Collecting actual observation values of oxygen jump layers of three BGC-Argo stations 2013-2016 in Bengal bay, carrying out one-to-one correspondence on the actual observation values and the generation time of each dissolved oxygen distribution influence factor, and taking the processed parameters as learning samples of a BP neural network model. And carrying out normalization processing on the acquired sample data by using a linear function conversion method, so that the value range of the sample data is-1- +1.
In this embodiment, the actual observed values of the oxygen jump layer of the low oxygen area output by the network and the oxygen jump layer of the low oxygen area of the corresponding area are compared until the mean square error of the network training meets the requirement, and the method determines and optimizesThe number of hidden layer nodes, weight and threshold of the BP neural network. As shown in FIG. 2, in this example there are 5 neurons at the input layer node, respectively 23℃isotherms (D T23 ) Isotherms at 24 ℃ (D) T24 ) Isotherms at 25 ℃ (D) T25 ) Isotherms at 26 ℃ (D) T26 ) And sea level height anomalies (SLA). The hidden layer neuron number is 10. The output layer is 1 neuron with the depth of oxygen jump layer of hypoxia zone (DO 50 mu mol kg) -1 ，D DO50 ). Both the transfer functions of the hidden layer neurons and the output layer neurons employ the tranlm function.
And collecting dissolved oxygen distribution influence factors of a required reconstruction region, correspondingly arranging the generation time of each dissolved oxygen distribution influence factor, inputting the generated time into the trained BP neural network, and outputting data of an output layer into an excel format.
In this embodiment, BP neural network test is performed by using parameters related to oxygen jump layer in the low oxygen area of Bengalese Bay of 2013-2016 year to obtain predicted value of oxygen jump layer in the low oxygen area of Bengalese Bay, and fitting the predicted value and measured value of BP neural network to those shown in FIG. 3 to obtain fitting coefficient R of predicted value and actual value of test sample 2 0.90793, adjusted R 2 0.90746, the rms error RMSE is 7.9318, the mean absolute percentage error MAPE is 7.2425%, the mean absolute error MAE is 6.0898, and the fit of the predicted and measured values of the test samples is shown in fig. 4. As can be seen from fig. 3 and 4, the inversion result of the method is quite consistent with the actual result, which shows that the method can be completely used for inversion of the data of the oxygen jump layer of the low oxygen area.
In conclusion, inversion of the annual dissolved oxygen data is achieved based on the isothermal line depth of the Argo buoy at 23-26 ℃ and the remote sensing sea surface height abnormal data, the BGC-Argo buoy data can be used for inverting the traditional annual missing dissolved oxygen data of the Argo data in the area, and further the space-time distribution of the dissolved oxygen and oxygen jump layers in the low-oxygen area can be monitored better.
Claims (7)
1. The method for inverting the oxygen jump layer of the low oxygen area based on the Argo buoy and the remote sensing data is characterized by comprising the following steps of:
s1, constructing a training set: the method comprises the steps of obtaining dissolved oxygen data based on a BGC-Argo buoy of a target area, and taking the dissolved oxygen data as a training label; acquiring Argo buoy data and dissolved oxygen distribution influencing factors of a target area, and taking the Argo buoy data and the dissolved oxygen distribution influencing factors as training data;
s2, constructing a BP neural network, and training through a training set to obtain the trained BP neural network;
s3, acquiring Argo buoy data and dissolved oxygen distribution influence factor data at an oxygen jump layer of a low oxygen region to be inverted in a target region, and taking the Argo buoy data and the dissolved oxygen distribution influence factor data as inversion basic data;
s4, inputting inversion basic data into the trained BP neural network, and taking the output of the trained BP neural network as an inversion result of an oxygen jump layer of a low oxygen area to be inverted in the target area.
2. The method for inverting a hypoxia zone oxygen jump based on Argo buoy and remote sensing data according to claim 1, wherein the dissolved oxygen profile influencing factors in step S1 include 23 ℃, 24 ℃, 25 ℃, 26 ℃ and sea surface altitude anomaly data.
3. The method for inverting an oxygen jump layer in a low oxygen area based on an Argo buoy and remote sensing data according to claim 1, wherein after obtaining the data of the dissolved oxygen distribution influencing factors, the maximum value, the minimum value and the average value of each dissolved oxygen distribution influencing factor are read, and according to the formula:
normalizing, and taking normalized data as training data; wherein X is norm Is a normalization result; x is the data value of the dissolved oxygen distribution influencing factor; x is X mean An average value of the dissolved oxygen distribution influencing factors; x is X max Is the maximum value of the dissolved oxygen distribution influencing factors; x is X min Is the minimum value of the dissolved oxygen distribution influencing factor.
4. A method for inverting a hypoxia zone oxygen jump layer based on Argo buoy and remote sensing data according to claim 3, wherein the BP neural network in step S2 comprises an input layer, an hidden layer and an output layer; the number of neurons of the input layer is equal to the number of dissolved oxygen distribution influencing factors; the number of hidden layer neurons is determined in the BP neural network training process; the number of neurons of the output layer is one; the transfer functions of the input layer to the hidden layer and the hidden layer to the output layer are both the tranlm functions.
5. The method for inverting a hypoxic zone oxygen jump layer based on an Argo buoy and remote sensing data as claimed in claim 4, wherein the number of hidden layer neurons is 10.
6. The method for inverting an oxygen jump layer in a low oxygen area based on an Argo buoy and remote sensing data according to claim 4, wherein the training process of the BP neural network is as follows:
and carrying out error calculation on the output data of the current BP neural network and the corresponding training label, and adjusting the parameters of the current BP neural network in a counter-propagation mode according to an error calculation result until the error value of the output result of the current BP neural network and the corresponding training label is smaller than or equal to a threshold value, and storing the parameters of the current BP neural network to obtain the trained BP neural network.
7. The method for inverting an oxygen jump layer in a low oxygen area based on an Argo buoy and remote sensing data according to claim 4, wherein the trained BP neural network outputs the inversion result in an excel format.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311143030.3A CN117152633A (en) | 2023-09-06 | 2023-09-06 | Method for inverting oxygen jump layer of low oxygen area based on Argo buoy and remote sensing data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311143030.3A CN117152633A (en) | 2023-09-06 | 2023-09-06 | Method for inverting oxygen jump layer of low oxygen area based on Argo buoy and remote sensing data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117152633A true CN117152633A (en) | 2023-12-01 |
Family
ID=88905809
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311143030.3A Pending CN117152633A (en) | 2023-09-06 | 2023-09-06 | Method for inverting oxygen jump layer of low oxygen area based on Argo buoy and remote sensing data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117152633A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102662039A (en) * | 2012-04-17 | 2012-09-12 | 戴会超 | BP neutral network-based method for predicting dissolved oxygen saturation in water body |
| CN111259943A (en) * | 2020-01-10 | 2020-06-09 | 天津大学 | Thermocline prediction method based on machine learning |
| CN112345473A (en) * | 2020-10-23 | 2021-02-09 | 中国水利水电科学研究院 | Method for identifying dissolved oxygen control factors of thermal stratification reservoir |
-
2023
- 2023-09-06 CN CN202311143030.3A patent/CN117152633A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102662039A (en) * | 2012-04-17 | 2012-09-12 | 戴会超 | BP neutral network-based method for predicting dissolved oxygen saturation in water body |
| CN111259943A (en) * | 2020-01-10 | 2020-06-09 | 天津大学 | Thermocline prediction method based on machine learning |
| CN112345473A (en) * | 2020-10-23 | 2021-02-09 | 中国水利水电科学研究院 | Method for identifying dissolved oxygen control factors of thermal stratification reservoir |
Non-Patent Citations (2)
| Title |
|---|
| D. GIGLIO ET AL.: "Estimating Oxygen in the Southern Ocean Using Argo Temperature and Salinity", 《JOURNAL OF GEOPHYSICAL RESEARCH: OCEANS》, pages 4282 - 4283 * |
| 杨胜龙;张忭忭;唐宝军;化成君;张胜茂;范秀梅;戴阳;冯春雷;: "基于GAM模型分析水温垂直结构对热带大西洋大眼金枪鱼渔获率的影响", 中国水产科学, no. 04 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lu et al. | Hybrid decision tree-based machine learning models for short-term water quality prediction | |
| Huo et al. | Using artificial neural network models for eutrophication prediction | |
| CN111199270A (en) | Regional wave height forecasting method and terminal based on deep learning | |
| Liu et al. | Prediction of dissolved oxygen content in aquaculture of Hyriopsis cumingii using Elman neural network | |
| Wenxiang et al. | Optimization of deep learning model for coastal chlorophyll a dynamic forecast | |
| Islam et al. | Numerical modeling on transition of dominant algae in Lake Kitaura, Japan | |
| Wang et al. | Light regulation of phytoplankton growth in San Francisco Bay studied using a 3D sediment transport model | |
| Li et al. | Prediction on daily spatial distribution of chlorophyll-a in coastal seas using a synthetic method of remote sensing, machine learning and numerical modeling | |
| Verity et al. | The Ocean Margins Program: An interdisciplinary study of carbon sources, transformations, and sinks in a temperate continental margin system | |
| Vassallo et al. | How ecosystems adapt to face disruptive impact? The case of a commercial harbor benthic community | |
| CN117152633A (en) | Method for inverting oxygen jump layer of low oxygen area based on Argo buoy and remote sensing data | |
| Müller-Karulis et al. | Modeling the long-term dynamics of nutrients and phytoplankton in the Gulf of Riga | |
| Lilover et al. | The variability of parameters controlling the cyanobacteria bloom biomass in the Baltic Sea | |
| Nion et al. | Seasonal and tidal dynamics of nutrients and chlorophyll a concentration in water at the Sundarbans mangrove ecosystems of Bangladesh | |
| Singh et al. | A Review of Phytoplankton Primary Production in Relation to Environmental Forcing in Indian Estuaries | |
| CN113155751B (en) | Remote sensing identification method for POC vertical structure type of eutrophic lake | |
| Owens et al. | 15N and the assimilation of nitrogen by marine phytoplankton: the past, present and future? | |
| Gao et al. | Characteristics and particularities of bacterial community variation in the offshore shellfish farming waters of the North Yellow Sea | |
| Poornima et al. | Computational Methods for Long Term Monitoring of New Production and f-ratio Variability in Bay of Bengal | |
| CN118052373B (en) | Ocean resource environment bearing capacity assessment method | |
| CN117290792B (en) | Air pressure forecasting system and method based on machine learning | |
| Hasnan et al. | NARX-based water quality index model of Air Busuk River using chemical parameter measurements | |
| Busecke et al. | Future Expansion of the Pacific Oxygen Minimum Zone | |
| Liu | Chlorophyll-a Analysis Based on Hilbert Huang Transformation and Convolutional Neural Network | |
| Icarus Allen et al. | Changes in DMS production and flux in relation to decadal shifts in ocean circulation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |