CN111723522B - Calculation method of exchange flux of dissolved organic carbon in lakes and rivers - Google Patents
Calculation method of exchange flux of dissolved organic carbon in lakes and rivers Download PDFInfo
- Publication number
- CN111723522B CN111723522B CN202010535291.XA CN202010535291A CN111723522B CN 111723522 B CN111723522 B CN 111723522B CN 202010535291 A CN202010535291 A CN 202010535291A CN 111723522 B CN111723522 B CN 111723522B
- Authority
- CN
- China
- Prior art keywords
- lake
- doc
- river
- data
- remote sensing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000004907 flux Effects 0.000 title claims abstract description 31
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 10
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 10
- 238000004364 calculation method Methods 0.000 title description 8
- 238000000034 method Methods 0.000 claims abstract description 23
- 238000013528 artificial neural network Methods 0.000 claims abstract description 18
- 238000012937 correction Methods 0.000 claims abstract description 11
- 230000001360 synchronised effect Effects 0.000 claims abstract description 10
- 238000002310 reflectometry Methods 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 7
- 238000005259 measurement Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 238000005192 partition Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 239000005446 dissolved organic matter Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 206010021198 ichthyosis Diseases 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- MWJBSSXENNRICD-UHFFFAOYSA-N 6-(2-methoxyphenyl)-1,3-dimethyl-5-phenylpyrrolo[3,4-d]pyrimidine-2,4-dione Chemical compound COC1=CC=CC=C1N1C(C=2C=CC=CC=2)=C2C(=O)N(C)C(=O)N(C)C2=C1 MWJBSSXENNRICD-UHFFFAOYSA-N 0.000 description 1
- 241000894006 Bacteria Species 0.000 description 1
- 150000001335 aliphatic alkanes Chemical class 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000003139 buffering effect Effects 0.000 description 1
- 150000001720 carbohydrates Chemical class 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000031700 light absorption Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- IFYDWYVPVAMGRO-UHFFFAOYSA-N n-[3-(dimethylamino)propyl]tetradecanamide Chemical compound CCCCCCCCCCCCCC(=O)NCCCN(C)C IFYDWYVPVAMGRO-UHFFFAOYSA-N 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000002352 surface water Substances 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G06N3/045—Combinations of networks
-
- 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
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N2021/1793—Remote sensing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
A method for calculating dissolved organic carbon exchange flux of lakes and rivers, comprising: dividing lakes according to river zone positions to obtain different lake zones; collecting remote sensing data and synchronous actually measured DOC concentration data; performing atmospheric coarse correction on the remote sensing data; with atmospheric rough corrected remote sensing reflectivityR rc For input, actually measuring DOC concentration, and establishing a multi-layer backward feedback neural network for output, wherein the multi-layer backward feedback neural network comprises an input layer, three hidden layers and an output layer; the trained multilayer backward feedback neural network is utilized to remotely sense and invert the DOC concentration of the lake at different moments, the month average DOC concentration of each lake area is calculated, and the product of the river outlet lake flow and the month average DOC concentration of the river mouth adjacent to the lake area is the outlet lake DOC flux; the product of the river inflow and the measured average DOC concentration of the river is the DOC flux of the inflow. The method can realize real-time remote sensing estimation of the DOC concentration of the lake and remote sensing estimation of the DOC exchange flux of the lake and the river.
Description
Technical Field
The invention relates to a satellite remote sensing technology and the application field thereof, which mainly utilizes satellite remote sensing data and river actual measurement data which can be acquired in real time to realize remote sensing estimation of lake and river Dissolved Organic Carbon (DOC) exchange flux, namely, in a certain time: how many DOCs flow out of the lake into the river, and how many DOCs are transported by the river into the lake.
Background
The water body dissolved organic matter contains various organic molecules such as saccharides, fat, alkanes and the like, and is widely existed in water bodies of lakes and rivers, and the content flux of the water body dissolved organic matter is quantified by using Dissolved Organic Carbon (DOC). Dissolved organics are a source of energy for the survival of heterotrophic bacteria, and their decomposition consumes oxygen from the water and produces harmful substances, thereby destroying the water environment. The lake and the adjacent river have DOC exchange, the lake DOC is output by the river coming out of the lake, and the land source DOC is input into the lake by the river coming in the lake. Thus, there is a need to know the dynamics of lake DOC to better manage lake water quality. In order to estimate the DOC exchange flux of lakes and rivers, the traditional method is to calculate the DOC exchange flux according to the actual measured flow rate and DOC concentration of the rivers. However, because of the highly dynamic change of dissolved organic carbon in the river DOC, measured DOC data at a certain moment in time often cannot represent the average DOC concentration in that time, especially in the river under the influence of strong artificial activity in the eastern part of the river. Therefore, the remote sensing technology high-frequency observation advantage is necessary to be utilized to realize remote sensing estimation of the DOC exchange flux of the lake and the river. At present, the remote sensing of the lake DOC has the problem that the traditional remote sensing data band ratio cannot be well used for remote sensing monitoring of the lake DOC, and the lake DOC product is not reported.
Disclosure of Invention
In order to realize remote sensing estimation of lake and river DOC exchange flux, the invention constructs a calculation method of lake and river dissolved organic carbon exchange flux by means of high-time-resolution remote sensing data and field measured data in different seasons.
The technical scheme adopted by the invention is as follows:
a method for calculating dissolved organic carbon exchange flux of lakes and rivers, comprising:
dividing lakes according to river zone positions to obtain different lake zones;
collecting remote sensing data and synchronous actually measured DOC concentration data;
performing atmospheric coarse correction on the remote sensing data;
with atmospheric rough corrected remote sensing reflectivity R rc For input, actually measuring DOC concentration, and establishing a multi-layer backward feedback neural network for output, wherein the multi-layer backward feedback neural network comprises an input layer, three hidden layers and an output layer;
the trained multilayer backward feedback neural network is utilized to remotely sense and invert the DOC concentration of the lake at different moments, the month average DOC concentration of each lake area is calculated, and the product of the river outlet lake flow and the month average DOC concentration of the river mouth adjacent to the lake area is the outlet lake DOC flux; the product of the river inflow and the measured average DOC concentration of the river is the DOC flux of the inflow.
Further, the input layer comprises 5 nodes; selecting remote sensing reflectivity R of 5 wave bands of 469nm,555nm,645nm,859nm and 2130nm rc The data is taken as input.
Further, each hidden layer contains 10 nodes.
Further, the calculation modes of the hidden layer and the output layer node values are as follows:
y＝f(-bias+∑w i ×x i )
fhidden＝2/(1+e -2×x )-1
f output ＝a×x+b (1)
wherein x is the value of each node of the previous layer; omega is the weight; f (f) hidden And f output The activation functions used for the hidden layer and the output layer, respectively.
Further, the measured DOC concentration includes field measured DOC concentration data for different seasons.
Further, the matched satellite-ground synchronous data are screened for neural network training, and the screening mode is as follows: for all DOC concentration measured data, selecting clear sky and R without cloud influence according to time window + -3 hours and space window 3X 3 pixels rc Data.
Further, 70% of the satellite-to-ground synchronous data are randomly selected for training the neural network, and the rest 30% of the data are used for model verification.
Further, the lake area is divided in such a way that the boundary of the lake is internally buffered with a plurality of pixels; for each river region boundary, drawing a vertical drainage basin connecting line to determine the corresponding lake.
Further, the error transfer is carried out by adopting a Levenberg-Marquardt optimization method and a Bayesian normalization algorithm. Overfitting can be effectively avoided; and adjusting the weight according to the fed-back error.
Further, the remote sensing data is MODIS remote sensing data.
According to field measured data and remote sensing data in different seasons, a remote sensing algorithm of the lake DOC is constructed; dividing lakes according to river region positions to obtain different lake regions, and then calculating the month average DOC concentration of the different lake regions; and (3) sampling the actual measurement value of the DOC concentration of the river entering the lake and the river, adopting the remote sensing average value of the river mouth close to the lake area for the DOC of the river exiting the lake and the river, and multiplying the remote sensing average value by the flow to obtain the DOC flux of the river entering and exiting the lake of different rivers, namely the DOC exchange flux of the lake and the river. The applicant researches find that for an internal lake, the atmospheric correction is positive and negative, and larger errors can be caused, so that specific wave band remote sensing product data of atmospheric coarse correction is directly used, a lake DOC remote sensing algorithm is built by combining a multi-layer backward feedback neural network, finally lake river DOC concentration is calculated by utilizing the lake region division and the river mouth close to the lake region division, for flux estimation, the existing method utilizes actual DOC concentration and flux calculation at a certain position of the river, and the sampling data is usually only once in one season or month. However, the DOC concentration of the river is continuously changed, so that the calculated DOC flux is greatly uncertain. The invention estimates the DOC flux of the lake month by using a remote sensing method, and the DOC concentration used is the average value of DOC concentrations on different days of each month, thereby having obvious advantages in timeliness and representativeness. The method can realize real-time remote sensing estimation of the DOC concentration of the lake and remote sensing estimation of the DOC exchange flux of the lake and the river.
Drawings
FIG. 1 is a lake DOC remote sensing multilayer backward feedback neural network.
FIG. 2 is an R of measured DOC concentration and synchronous monitoring rc (469) Is a relationship of (3).
FIG. 3 is a Tai lake and its drainage basin partition.
Detailed Description
For a typical lake-Taihu lake in China, the DOC exchange flux of the lake and the river is estimated based on MODIS remote sensing data, and the specific implementation mode is further described with reference to the accompanying figures 1-3:
a method for calculating dissolved organic carbon exchange flux of lakes and rivers, comprising:
(1) The lakes are divided according to the river locations to obtain different lake areas, as shown in fig. 3. By buffering the lake boundary inwards by a plurality of pixels, for each river region boundary, a connecting line of the vertical river basin is drawn to determine the corresponding lake. For the Tai lake, the Tai lake boundary was buffered 5km inward (corresponding to 10 pels of MODIS data used) for lake region division.
(2) Collecting remote sensing data and synchronous actually measured DOC concentration data;
the remote sensing data is MODIS L1B level data downloaded by a network; the actually measured DOC concentration data is that a surface water sample is collected when no cloud exists on a sunny day, and the laboratory returns to carry out filtering measurement on the day so as to ensure synchronous acquisition of the synchronously actually measured DOC and remote sensing.
(3) Atmospheric rough correction of remote sensing data. The network downloaded MODIS data is a product which is not subjected to atmospheric correction, and more than 90% of the data signals are noise signals generated by the atmosphere and the like. Therefore, the SeaWiFS data analysis system (SeaDAS) is utilized to perform the rough atmospheric correction on the original remote sensing data so as to remove Rayleigh scattering influence of atmospheric molecules and the like, and the product R after the rough atmospheric correction is obtained rc 。R rc Values R comprising bands of central wavelengths 469nm,555nm, 640nm, 859nm, 460 nm,1640nm,2130nm rc (469),R rc (555),R rc (645),R rc (859),R rc (1240),R rc (1640) And R is rc (2130)。
(4) Matching of satellite-ground synchronous data. For all DOC concentration measured data of the Taihu lake, determining whether effective R with clear sky and no cloud influence exists according to time window + -3 hours and space window of 3X 3 pixels rc As a result.
(5) And training and checking the multi-layer backward feedback neural network.
(1) And randomly selecting 70% of the found star-ground synchronous matching data for training the multi-layer backward feedback neural network.
(2) Establishing a multi-layer backward feedback neural network model;
it is generally considered that too many hidden layers/nodes increase the computational load and increase the interference, and too few hidden layers/nodes are difficult to achieve the goal, but no related theoretical method has been determined at present regarding the number of hidden layers/nodes. The method adopts a mode of gradually increasing the number to carry out multiple attempts, and finally establishes a multi-layer backward feedback neural network model based on three hidden layers and 10 nodes in each layer.
The calculation modes of the node values of the hidden layer and the output layer are as follows:
y＝f(-bias+∑w i ×x i )
f hidden ＝2/(1+e -2×x )-1
f output ＝a×x+b (1)
wherein x is the value of each node of the previous layer; omega is the weight; f (f) hidden And f output The activation functions used for the hidden layer and the output layer, respectively.
The output range of f (x) of the activation function used in the invention is-1, and a wider DOC range can be obtained through simulation.
(3) Screening an input wave band;
performing element analysis on the inverted lake, wherein the DOC has strong light absorption performance in a short wave band, and after preliminary test, R is calculated rc (469) Determining as input an approximate range of DOC concentrations (as shown in fig. 2); secondly, the phytoplankton production can release a large amount of DOC, and the sensitive wave band of the phytoplankton is R rc (555) And R is rc (645) The contribution of phytoplankton to the DOC will therefore be considered as input; thirdly, the atmospheric fine correction of the inland turbid water body has a difficult problem, and R is increased after test rc (859) And R is rc (1230) The wave band is used as input, DOC remote sensing can be realized based on the rough corrected remote sensing data, and the atmospheric fine correction difficulty is avoided or solved.
(4) Training a multi-layer backward feedback neural network model;
by R rc (469),R rc (555),R rc (645),R rc (859) And R is rc (2130) As an input value of the input layer node, the corresponding measured DOC concentration is taken as the value of the output layer node (fig. 1). Model training iteration is carried out, error transmission is carried out on the result of each cycle to the hidden layer and the output layer node, and the weight omega is adjusted according to the transmitted error delta until the output nodeThe fruit is stable to obtain a trained model. Error transfer uses a Levenberg-Marquardt optimization method and a Bayesian normalization algorithm.
(5) And (5) checking a model.
The model results were checked using the remaining 30% of the matched data, mean absolute percent error (MAPD), root Mean Square Error (RMSE), bias (bias) of 18.78%,1.38mg/L and-3.15%, respectively. MDPD, RMSE and bias are defined as in formula (2).
(6) DOC remote sensing of the Taihu day scale. Applying the trained multilayer backward feedback neural network to MODIS remote sensing R of each day rc And (5) data to obtain a DOC product with a daily scale.
(7) The average DOC concentration in different lake regions is calculated. Using the DOC results of each day, an arithmetic average calculation was performed to obtain an average DOC concentration per month. The average DOC concentration for different months in each lake region was further calculated from the partitions in fig. 3.
(8) Calculation of DOC exchange flux of lakes and rivers. For lake basin partitioning (fig. 3), each lake basin partitioning contains several rivers whose monthly in and out lake flow is available to the Tai lake authority. For the river of each river basin partition, the product of the lake outlet flow rate and the average DOC of the month of the river mouth close to the lake region is the lake outlet DOC flux, and the product of the lake inlet flow rate and the measured average DOC concentration of the river is the lake inlet DOC flux.
Claims (9)
1. A method for calculating the flux of dissolved organic carbon exchange between lakes and rivers, comprising:
dividing lakes according to river zone positions to obtain different lake zones;
collecting remote sensing data and synchronous actually measured DOC concentration data;
performing atmospheric coarse correction on the remote sensing data;
with atmospheric rough corrected remote sensing reflectivityR rc For input, actually measuring DOC concentration, and establishing a multi-layer backward feedback neural network for output, wherein the multi-layer backward feedback neural network comprises an input layer, three hidden layers and an output layer; the input layer comprises 5 nodes; selecting the remote sensing reflectivity of 5 wave bands of 469nm,555nm,645nm,859nm and 2130nmR rc Data is taken as input;
the trained multilayer backward feedback neural network is utilized to remotely sense and invert the DOC concentration of the lake at different moments, the month average DOC concentration of each lake area is calculated, and the product of the river outlet lake flow and the month average DOC concentration of the river mouth adjacent to the lake area is the outlet lake DOC flux; the product of the river inflow and the measured average DOC concentration of the river is the DOC flux of the inflow.
2. The method of claim 1, wherein each hidden layer comprises 10 nodes.
3. The method according to claim 1, wherein the implicit layer and output layer node values are calculated as follows:
(1)
wherein the method comprises the steps ofxValues for nodes of the previous layer; w is a weight;f hidden andf output the activation functions used for the hidden layer and the output layer, respectively.
4. The method of claim 1, wherein the measured DOC concentration comprises field measured DOC concentration data for different seasons.
5. The method of claim 1, wherein the matched satellite-to-ground synchronization data is screened for neural network training by: for all DOC concentration measured data, selecting clear sky and no cloud influence according to time window + -3 hours and space window 3 multiplied by 3 pixelsR rc Data.
6. The method of claim 1, wherein 70% of the satellite-to-ground synchronization data is randomly selected for training the neural network and the remaining 30% of the data is used for model verification.
7. The method of claim 1, wherein the lake region is partitioned in such a way that a lake boundary is buffered inward by a number of pixels; for each river region boundary, drawing a vertical drainage basin connecting line to determine the corresponding lake.
8. The method of claim 1 wherein the error is transferred using a Levenberg-Marquardt optimization method and a Bayesian normalization algorithm, and the weights are adjusted based on the fed back error.
9. The method of claim 1, wherein the telemetry data is MODIS telemetry data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010535291.XA CN111723522B (en) | 2020-06-12 | 2020-06-12 | Calculation method of exchange flux of dissolved organic carbon in lakes and rivers |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010535291.XA CN111723522B (en) | 2020-06-12 | 2020-06-12 | Calculation method of exchange flux of dissolved organic carbon in lakes and rivers |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111723522A CN111723522A (en) | 2020-09-29 |
| CN111723522B true CN111723522B (en) | 2023-11-10 |
Family
ID=72566525
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010535291.XA Active CN111723522B (en) | 2020-06-12 | 2020-06-12 | Calculation method of exchange flux of dissolved organic carbon in lakes and rivers |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111723522B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112881353B (en) * | 2021-01-11 | 2022-11-15 | 江西师范大学 | Method and device for measuring concentration of soluble organic carbon in water body |
| CN114357894B (en) * | 2022-03-11 | 2022-07-12 | 阿里巴巴达摩院(杭州)科技有限公司 | Atmospheric pollutant processing method, storage medium and computer terminal |
| CN118261483B (en) * | 2024-04-03 | 2024-09-10 | 生态环境部华南环境科学研究所(生态环境部生态环境应急研究所) | Method and system for estimating flux of dissolved organic carbon in river entering sea |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108896501A (en) * | 2018-07-07 | 2018-11-27 | 中国科学院南京地理与湖泊研究所 | A kind of remote sensing estimation method of the effective Sea―going flux of river dissolved organic carbon |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109489637B (en) * | 2018-11-08 | 2019-10-18 | 清华大学 | Water variation monitoring method, apparatus, computer equipment and storage medium |
-
2020
- 2020-06-12 CN CN202010535291.XA patent/CN111723522B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108896501A (en) * | 2018-07-07 | 2018-11-27 | 中国科学院南京地理与湖泊研究所 | A kind of remote sensing estimation method of the effective Sea―going flux of river dissolved organic carbon |
Non-Patent Citations (3)
| Title |
|---|
| Carbon outwelling and outgassing vs. burial in an estuarine tidal creek surrounded by mangrove and saltmarsh wetlands;Santos, IR等;《LIMNOLOGY AND OCEANOGRAPHY》;全文 * |
| 利用高光谱数据估算太湖水体CDOM浓度的神经网络模型;孙德勇等;《武汉大学学报(信息科学版)》;20090705(第07期);正文第1-4节 * |
| 基于反射率的太湖典型湖区溶解性有机碳的反演;张运林等;《地球科学进展》;20060201(第07期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111723522A (en) | 2020-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111723522B (en) | Calculation method of exchange flux of dissolved organic carbon in lakes and rivers | |
| CN112070234B (en) | Water chlorophyll and phycocyanin land-based remote sensing machine learning algorithm under complex scene | |
| CN109828089B (en) | DBN-BP-based water quality parameter nitrous acid nitrogen online prediction method | |
| Tanaka et al. | Development of a neural network algorithm for retrieving concentrations of chlorophyll, suspended matter and yellow substance from radiance data of the ocean color and temperature scanner | |
| CN109406457B (en) | Submerged vegetation spectrum water body influence correction method based on semi-analytical model | |
| Wei et al. | Transparency estimation of narrow rivers by UAV-borne hyperspectral remote sensing imagery | |
| CN109086948A (en) | Lake and reservoir eutrophication method for early warning based on data assimilation | |
| Song et al. | The application of Artificial Neural Network (ANN) model to the simulation of denitrification rates in mesocosm-scale wetlands | |
| CN108896501B (en) | Remote sensing estimation method for effective sea-entering flux of river dissolved organic carbon | |
| Rounds | Development of a neural network model for dissolved oxygen in the Tualatin River, Oregon | |
| Zhang et al. | Numerical modelling of storm surge, nutrient pollution and saltwater intrusion in a large estuary with typhoon effects | |
| CN113552034B (en) | Remote sensing inversion method for MODIS (moderate resolution imaging spectroradiometer) image of suspended particulate matter concentration in shallow lake | |
| Cao et al. | Spatio-temporal analysis of colored dissolved organic matter over Ebinur Lake in Xinjiang, China | |
| Newcomer et al. | Estuarine sediment deposition during wetland restoration: a GIS and remote sensing modeling approach | |
| Sanders et al. | Nutrients and chlorophyll at two sites in the Thames plume and southern North Sea | |
| Kazemzadeh et al. | Remote sensing of temporal and spatial variations of suspended sediment concentration in Bahmanshir Estuary, Iran | |
| Zhang et al. | An optical mechanism-based deep learning approach for deriving water trophic state of China's lakes from Landsat images | |
| Liu et al. | Artificial neural network and random forest approaches for modeling of sea surface salinity | |
| CN116229288A (en) | Urban river TSM concentration inversion method based on unmanned aerial vehicle multispectral image | |
| CN109900645A (en) | A kind of oyster Measuring Method of Heavy Metal based on hyper-spectral image technique | |
| CN115711838A (en) | Method for inverting suspended sediment in water body based on artificial neural network and high-resolution No. 1 satellite and application of method | |
| Barnhart et al. | Improved stream temperature simulations in SWAT using NSGA-II for automatic multi-site calibration | |
| CN114965300A (en) | Lake turbidity mapping method for constructing BP-TURB based on optical water body type and BP neural network algorithm | |
| Riha et al. | Development of a remote sensing algorithm for cyanobacterial phycocyanin pigment in the Baltic Sea using neural network approach | |
| Carpintero et al. | Estimation of turbidity along the Guadalquivir estuary using Landsat TM and ETM+ images |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |