CN112380984A - Remote sensing-based saline marsh vegetation slow flow capacity space evaluation method - Google Patents
Remote sensing-based saline marsh vegetation slow flow capacity space evaluation method Download PDFInfo
- Publication number
- CN112380984A CN112380984A CN202011266175.9A CN202011266175A CN112380984A CN 112380984 A CN112380984 A CN 112380984A CN 202011266175 A CN202011266175 A CN 202011266175A CN 112380984 A CN112380984 A CN 112380984A
- Authority
- CN
- China
- Prior art keywords
- vegetation
- information
- evaluation
- biomass
- slow flow
- 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.)
- Granted
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 147
- FAPWRFPIFSIZLT-UHFFFAOYSA-M Sodium chloride Chemical compound [Na+].[Cl-] FAPWRFPIFSIZLT-UHFFFAOYSA-M 0.000 title abstract description 5
- 239000011780 sodium chloride Substances 0.000 title abstract description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 84
- 239000002028 Biomass Substances 0.000 claims abstract description 81
- 238000000034 method Methods 0.000 claims abstract description 27
- 150000003839 salts Chemical class 0.000 claims abstract description 25
- 238000013145 classification model Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 16
- 238000005070 sampling Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 16
- 238000013210 evaluation model Methods 0.000 claims description 13
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000005259 measurement Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000003306 harvesting Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000001360 synchronised effect Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 2
- 239000000523 sample Substances 0.000 description 51
- 241000202758 Scirpus Species 0.000 description 8
- 241001149258 Sporobolus alterniflorus Species 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000009826 distribution Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 241000746413 Spartina Species 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 241000196324 Embryophyta Species 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003628 erosive effect Effects 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 244000003416 Asparagus officinalis Species 0.000 description 1
- 102000004190 Enzymes Human genes 0.000 description 1
- 108090000790 Enzymes Proteins 0.000 description 1
- YXOLAZRVSSWPPT-UHFFFAOYSA-N Morin Chemical compound OC1=CC(O)=CC=C1C1=C(O)C(=O)C2=C(O)C=C(O)C=C2O1 YXOLAZRVSSWPPT-UHFFFAOYSA-N 0.000 description 1
- 235000014676 Phragmites communis Nutrition 0.000 description 1
- 241000245565 Sporobolus anglicus Species 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- UXOUKMQIEVGVLY-UHFFFAOYSA-N morin Natural products OC1=CC(O)=CC(C2=C(C(=O)C3=C(O)C=C(O)C=C3O2)O)=C1 UXOUKMQIEVGVLY-UHFFFAOYSA-N 0.000 description 1
- 235000007708 morin Nutrition 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Images
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
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Geometry (AREA)
- Medical Informatics (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a remote sensing-based spatial evaluation method for slow flow capacity of salt marsh vegetation, and belongs to the technical field of evaluation. The method comprises the following steps: establishing the relation between the slow flow coefficient of the different types of salt marsh vegetation and the biomass, flow rate, gradient, water depth and water depth of the vegetation; actually measuring to obtain terrain gradient information, and establishing a remote sensing classification and biomass estimation model of a region to be evaluated; determining initial flow velocity information and initial water depth information; establishing an evaluation grid and determining remote sensing image information, terrain slope information, vegetation leading vegetation and biomass information of each evaluation unit; sequentially calculating the vegetation zone slow flow coefficients of all the evaluation units according to the direction from sea to land to obtain the output results of the flow velocity and the water depth; and evaluating the flow slowing capacity of the saline marsh vegetation zone of the area to be evaluated. According to the vegetation zone slow flow evaluation method, the vegetation zone space growth difference, the difference of vegetation slow flow capacity under different water depths and flow speed conditions are considered, evaluation is carried out based on remote sensing image data, the vegetation real situation can be accurately reflected, and the evaluation efficiency is improved.
Description
Technical Field
The invention relates to the field of vegetation slow flow capacity evaluation, in particular to a remote sensing-based saline marsh vegetation slow flow capacity space evaluation method.
Background
The coastal zone area is one of the most important areas for economic and social development, the most frequent human activities and the weaker areas, and is easily affected by natural disasters such as coastal erosion, storm surge, sea wave, tsunami and the like. In order to deal with the threat, a large number of hard seawalls are built in domestic and foreign coastal cities, but the defense capability of the hard seawalls is weakened continuously due to the fact that the hard seawalls are large in economic investment and difficult to adjust along with the rise of sea level, and the sustainable utilization rate is low.
The saline marsh vegetation in the Coastal zone forms obstruction to wave movement due to the structure of the vegetation, and can effectively provide a low-cost, high-benefit and sustainable ecological coast bank protection scheme (Ecosystem-based coast refuse) in the aspects of exerting wave-dissipating and slow flow, fixing a bank, protecting the bank, resisting coast erosion, storm tide disasters and the like.
In order to effectively evaluate the spatial difference of the slow flow capacity of the salt marsh vegetation, a model needs to be established for evaluation, and the evaluation model is mainly a numerical model and a spatial explicit model at present.
Most numerical models are built based primarily on the flow rate monitored at real-time sites (0D) and calculate the decay process along a 1D cross-shore section. The traditional numerical model mainly focuses on the scale from the blade to the meadow, and the influence of vegetation is simply regarded as increasing the bottom roughness coefficient by applying an average depth model. In recent years, vegetation has been parameterized as a source of form resistance, producing friction against the direction of water and sand transport, as the water flow resistance produced by vegetation is often described by the Manning coefficient or Darcy-Weisbach friction factor, on the basis of which the ability to retard the flow of vegetation on a sample belt has been evaluated (Morin et al; marjioribanks et al).
And in order to adapt to the evaluation of a large scale range, the attenuation of the flow velocity is quantified as the attenuation rate of unit distance in the horizontal direction to the land, and the risk exposure condition of the salt marsh vegetation in the coastal zone area is simulated from the geographic information system model based on available data (such as terrain, vegetation distribution, population, hydrology and the like) and relatively simple assumptions. With the maturation of remote sensing technology, some foreign researchers have tried to establish a spatial explicit evaluation model by using optical and radar images. For example, Antoine et al utilize WV-3 green, red-edge, near-infrared band and field observation data, and utilize a multivariate linear regression construction model to evaluate, showing the change of attenuation ability from low marsh to high marsh; mury and the like utilize data of various wave bands of visible light of the unmanned aerial vehicle and Lidar products, correlation analysis is carried out between wave band information and observation results, and finally visible light blue wave bands, radar altitude products and field observation results are selected to establish a linear model to evaluate the difference of coastal protection capability.
However, both of the above models have their own drawbacks:
1. the technology for constructing the evaluation model by utilizing the hydrodynamic numerical model can effectively model the evolution of the water flow velocity in space from the physical and mathematical angles, and has higher accuracy. However, the parameters, grid setting, application time and technical threshold of the numerical model are high, the numerical model is limited to professionals, and the numerical model is difficult to apply across disciplines. In addition, the slow flow capacity of the salt marsh vegetation is closely related to the plant density and the plant height, most of the numerical models do not consider the space structure difference of the vegetation and the complex process and the wave attenuation effect brought by the gradient zonal distribution of the vegetation, and the method cannot be popularized in a large range and is actually applied to the precise protection function evaluation of the wave attenuation and slow flow of the vegetation in the coastal zone.
2. The existing space model technology quantifies the difference of the types and the growth conditions of the salt marsh vegetation in space, establishes the relation between the growth conditions of the vegetation and the slow flow capacity, and accordingly realizes the evaluation of the slow flow capacity of the salt marsh vegetation in different areas on a small scale. However, the model only contains the wave band information of the image, so that the difference of the slow flow capacity of the salt marsh vegetation is difficult to explain from the mechanism. In addition, the current slowing capacities under different water depths and flow speed conditions are obviously different, the existing modeling method does not consider different water depths and flow speed conditions for each evaluation module, the simulation of the tidal current and flow speed attenuation process from sea to land in an evaluation unit cannot be realized, and a large error is caused to an evaluation result.
The technical problem is mainly that the vegetation space distribution, the growth condition and the evolution of the flow speed in the vegetation zone are not combined, the consideration of vegetation space difference and the evolution of the trend from land to sea is lacked, and the evaluation result has larger deviation.
Disclosure of Invention
Aiming at the problem that the vegetation zone current slowing coefficient empirical model in the prior art does not fully consider the vegetation zone current slowing capability influence caused by the vegetation zone current slowing coefficient spatial distribution, the growth condition, different water depths and different flow rates, the invention aims to provide a remote sensing-based salt marsh vegetation current slowing capability spatial evaluation method.
In order to achieve the purpose, the technical scheme of the invention is as follows:
a remote sensing-based spatial evaluation method for slow flow capacity of salt marsh vegetation comprises the following steps,
establishing a vegetation zone slow flow coefficient empirical model of the relation among different salt marsh vegetation slow flow coefficients, terrain gradient, vegetation biomass, water depth and flow rate, wherein the slow flow coefficient is the ratio of the attenuation of the flow rate in unit distance to the input flow rate;
obtaining remote sensing image classification and vegetation biomass estimation model and terrain slope information of a region to be evaluated, and setting initial flow velocity information and initial water depth information;
establishing an evaluation grid, and dividing the area to be evaluated into a plurality of evaluation units;
determining vegetation biomass information of each evaluation unit according to the remote sensing image classification and the vegetation biomass estimation model;
sequentially determining the vegetation zone unit distance current slowing coefficients of the evaluation units according to the initial flow velocity information, the initial water depth information, the vegetation biomass information and the terrain slope information of the evaluation units and the vegetation zone current slowing coefficient empirical model from the sea to the land to obtain water depth and flow velocity output results;
and evaluating the vegetation zone slow flow capacity of the area to be evaluated according to the vegetation zone unit distance slow flow coefficient of each evaluation unit.
Preferably, the step of establishing the vegetation zone runoff coefficient empirical model of the relationship between different saltmarsh vegetation runoff coefficients and terrain slopes, vegetation biomass, water depth and flow rate comprises,
obtaining a plurality of sample data of a long-time-sequence observation sample band, wherein the sample data comprises terrain slope information, vegetation biomass information and hydrological information, and the hydrological information comprises initial water depth information before water flows through the observation sample band, incoming flow velocity information before the water flows through the observation sample band and outgoing flow velocity information after the water flows through the observation sample band;
obtaining a plurality of actually measured slow flow coefficients of the observation sample band according to the incoming flow velocity information and the outgoing flow velocity information in the plurality of sample data;
training an evaluation model according to a plurality of sample data and a plurality of actually measured slow flow coefficients, wherein the evaluation model is R ═ av+bh+csveg+dbveg+e；
Wherein v is the information of the flow velocity in the forward direction of the water flow flowing through the observation sample zone, h is the information of the initial water depth of the water flow flowing through the observation sample zone, and svegFor the topographic gradient information of the observation sample band, bvegAnd vegetation biomass information of the observation sample band.
Preferably, the step of determining the vegetation biomass information of each evaluation unit according to the remote sensing image classification and the vegetation biomass estimation model comprises,
establishing a ground feature classification model and a biomass estimation model by combining ground sampling points and sampling synchronous remote sensing images;
acquiring information of each wave band of each pixel in the remote sensing image information of each evaluation unit;
determining the vegetation type corresponding to each pixel according to the wave band information of each pixel and the ground feature classification model;
obtaining a feature set S of the vegetation coefficient of each pixel according to the vegetation coefficient calculation formula and the information of each wave band of each pixel1；
Rejecting the feature set S1To obtain a dimension set S2；
Calculating a dimension set S from biomass obtained from contemporaneous harvest measurements2The importance of each feature in the dimension set S is determined according to the order of the importance from high to low2Screening by greedy algorithm to obtain training set S3；
Selecting a vegetation biomass estimation model according to the vegetation type corresponding to each pixel;
according to the training set S3The vegetation biomass estimation model is used for obtaining vegetation biomass information of each pixel;
and determining the vegetation biomass information of each evaluation unit according to the vegetation biomass information of each pixel.
Preferably, the step of determining the vegetation biomass information of each evaluation unit according to the vegetation biomass information of each pixel is that,
determining the type of the dominant vegetation in each evaluation unit, wherein the dominant vegetation is the vegetation type occupying the most pixels in each evaluation unit;
and multiplying the ratio of the number of the pixels occupied by the dominant vegetation to the total number of the pixels in the evaluation unit by the average vegetation biomass information of the pixels in the evaluation unit, namely the vegetation biomass information of the evaluation unit.
Preferably, the step of determining the vegetation type corresponding to each pixel according to the information of each wave band of each pixel and the ground feature classification model comprises,
converting each wave band information of each pixel into a point element;
processing the point elements by using the point element map layer, respectively extracting the waveband information of each pixel to a point, and generating a csv file;
substituting the csv file into the ground feature classification model to obtain the vegetation type corresponding to each pixel, wherein the ground feature classification model is a pre-established ensemble learning classification model.
Preferably, there are a plurality of the empirical models of vegetation zone current slowing coefficients, and each empirical model of vegetation zone current slowing coefficient corresponds to one or more types of vegetation.
Preferably, the step of establishing an evaluation grid and dividing the area to be evaluated into a plurality of evaluation units comprises,
determining a bank segment boundary of the area to be evaluated;
equally dividing the bank segment boundary into a plurality of sub bank segments;
and according to the direction from land to sea, equally extending the sub-bank segments at least twice by using a buffer area to obtain the plurality of evaluation units.
Preferably, the step of determining the vegetation zone unit distance current slowing coefficients of each evaluation unit in sequence from the direction from sea to land according to the initial flow velocity information, the initial water depth information, the vegetation biomass information and the terrain slope information of each evaluation unit and the vegetation zone current slowing coefficient empirical model to obtain the water depth and flow velocity output results comprises,
determining a vegetation zone slow flow coefficient of a first evaluation unit from the sea to the land according to the input initial flow information, the initial water depth information, the obtained vegetation biomass information and terrain slope information of the first evaluation unit from the sea to the land and the vegetation zone slow flow coefficient empirical model, wherein the initial flow information is the incoming flow information of the first evaluation unit from the sea to the land;
determining the incoming flow velocity information and the initial water depth information of a second evaluation unit from the sea to the land according to the vegetation zone slow flow coefficient and terrain slope information of the first evaluation unit from the sea to the land, the empirical model of the vegetation zone slow flow coefficient, and the initial flow velocity information and the initial water depth information, wherein the incoming flow velocity information of the second evaluation unit from the sea to the land is the outgoing flow velocity information of the first evaluation unit from the sea to the land;
determining vegetation zone slow flow coefficient and heading flow rate information of the second evaluation unit from the sea to the land according to the heading flow rate information of the second evaluation unit from the sea to the land, initial water depth information of the second evaluation unit from the sea to the land, vegetation biomass information and terrain slope information of the second evaluation unit from the sea to the land and the vegetation zone slow flow coefficient empirical model;
and determining the vegetation zone slow flow coefficient of the rest evaluation units from the sea to the land by analogy.
Preferably, before training the empirical model of vegetation zone runoff coefficients, preprocessing of hydrological information in sample data is further included.
Preferably, the preprocessing includes missing value filling of missing water depth information and extraction of abnormal flow velocity information.
By adopting the technical scheme, when the vegetation slow flow capacity is evaluated, the difference of the vegetation slow flow capacity under the conditions of different water depths and flow velocities is fully considered, so that the result is more accurate; in addition, the vegetation slow flow capacity difference caused by vegetation space growth difference is fully considered, namely, the refined space grid division is carried out on the area to be evaluated, and more refined data are obtained so as to facilitate the overall evaluation; meanwhile, the vegetation biomass information is obtained in a remote sensing image information mode, so that the evaluation process is more efficient and the result is more accurate.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a flow chart of a method for building an empirical model of a vegetation zone current slowing coefficient in the invention;
FIG. 3 is a schematic view of the arrangement of an observation sample band and sampling points in the present invention;
FIG. 4 is a comparison graph of vegetation zone current-slowing coefficient empirical model calculation data and actual measurement data of current-slowing capability of scirpus marigolense/scripus triqueter and spartina alterniflora/cord grass in the invention;
FIG. 5 is a flowchart of a method for establishing an evaluation grid for an area to be evaluated according to the present invention;
FIG. 6 is a schematic diagram of gridding of a region to be evaluated in the present invention;
FIG. 7 is a flow chart of a method of determining vegetation biomass information within an evaluation unit according to the present invention;
FIG. 8 is a flow chart of a method of determining vegetation type in the present invention;
fig. 9 is a schematic diagram of an evaluation result of the slow flow capability of the area to be evaluated in the embodiment of the present invention.
Detailed Description
The following further describes embodiments of the present invention with reference to the drawings. It should be noted that the description of the embodiments is provided to help understanding of the present invention, but the present invention is not limited thereto. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The embodiment of the invention specifically provides a remote sensing-based spatial evaluation method for slow flow capacity of salt marsh vegetation, and as shown in fig. 1, the method specifically comprises the steps of S102, S104, S106, S108, S1010 and S1012.
Step S102, establishing vegetation zone slow flow coefficient empirical models of relations among slow flow coefficients of different salt marsh vegetation, terrain gradient, vegetation biomass, water depth and flow rate, wherein the slow flow coefficient refers to a ratio of attenuation of the flow rate in unit distance to input flow rate;
step S104, obtaining remote sensing image classification and vegetation biomass estimation model and terrain slope information of the area to be evaluated, and setting initial flow velocity information and initial water depth information;
step S106, establishing an evaluation grid, and dividing a region to be evaluated into a plurality of evaluation units;
step S108, determining vegetation biomass information of each evaluation unit according to the remote sensing image classification and the vegetation biomass estimation model;
step S1010, sequentially determining the vegetation zone unit distance current slowing coefficients of all the evaluation units in the step S106 according to the direction from sea to land according to the vegetation zone current slowing coefficient empirical model in the step S102, the initial flow speed information, the initial water depth information and the terrain slope information set in the step S104 and the vegetation biomass information of all the evaluation units obtained in the step S108, and obtaining water depth and flow speed output results;
step S1012, evaluating the vegetation zone current slowing capability of the area to be evaluated according to the vegetation zone unit distance current slowing coefficient of each evaluation unit.
In step S102, the present embodiment builds an empirical model of vegetation zone current slowing coefficient through steps S1022, S1024 and S1026 shown in fig. 2.
Step S1022, obtaining a plurality of sample data obtained by periodic measurement of the long-sequence observation sample band, where each sample data includes terrain slope information, vegetation biomass information, and hydrologic information, and the hydrologic information includes initial water depth information before the water flow passes through the observation sample band, incoming flow velocity information before the water flow passes through the observation sample band, and outgoing flow velocity information after the water flow passes through the observation sample band.
The terrain gradient information is measured by a fragmentary part measuring method of an RTK-GPS, and a calculation formula is as follows:
in the formula, HiIs the elevation of the ith point, di,i-1Is the distance between the ith point and the (i-1) th point.
The vegetation biomass information in the sample data is obtained by the following steps: arranging a plurality of parallel samples in an observation sample band by a sample method; cutting and harvesting vegetation in all parallel samples in a flush manner, cleaning, deactivating enzymes in an oven at 105 ℃ for 2h, drying at 65 ℃ to constant weight, and weighing; and calculating the weight average value of the single parallel sample, obtaining the weight of the unit area through the weight average value and the area of the parallel sample, and obtaining the vegetation biomass information of the observation sample band after conversion.
Wherein, the boundary of observing the land and sea direction of sample area all is provided with the sampling point, and two sampling points are highly unanimous and with the same frequency sampling apart from the ground, and depth of water measuring equipment and velocity of flow measuring equipment have been put to every sampling point equipartition. In this embodiment, the water depth measuring device is a pressure type wave tide meter, the flow velocity measuring device is an electromagnetic type flow velocity meter, and the probe heads of the sensors are all the same in height from the ground, for example, 20 cm. The two instruments perform hydrological information sampling in the same time interval sampling mode, for example, the instrument starting interval is 5 min/time, the electromagnetic type current meter sampling frequency is 1 time/s, each sampling interval is 30 times, and the pressure type tide meter sampling frequency is 4Hz, as shown in FIG. 3. Or in one embodiment, the flow rate information may be other types of flow meters such as doppler acoustic flow meters; the water depth information can be obtained by adopting other water level sensors such as a water level gauge and the like.
Step S1024, calculating and obtaining a plurality of actually measured buffer coefficients of the observation sample band according to the incoming flow rate information and the outgoing flow rate information in the plurality of sample data in step S1022. The actually measured slow flow coefficient calculation formula is as follows:
R＝(1/di)×(1-(vi+1/vi))×100％ (2)；
wherein v isiIs the information of the flow velocity of water flow in the forward direction before the water flow passes through the ith segment of vegetation zone, vi+1Is the water flow passing through the i section of vegetationInformation of the flow velocity of the outgoing flow after the strip, diThe width of the ith vegetation zone. As for the observation bands in this example, viIs the information of the flow velocity of water flow in the forward direction before passing through the observation sample zone, vi+1Is the information of the flow velocity of water after passing through the observation sample band, diTo observe the width of the sample strip. According to the formula (2), each group of sample data acquisition can be obtained through calculation, and the slow flow coefficient of the observation sample belt to the water flow is obtained, namely the actually measured slow flow coefficient.
Step S1026, training a vegetation zone slow flow coefficient empirical model according to the plurality of sample data obtained in step S1022 and the plurality of actually measured slow flow coefficients obtained in step S1024, wherein the vegetation zone slow flow coefficient empirical model is
R＝av+bh+csveg+dbveg+e (3)；
Wherein v is the information of the flow velocity in the forward direction of the water flow flowing through the observation sample zone, h is the information of the initial water depth of the water flow flowing through the observation sample zone, and svegFor the topographic gradient information of the observation sample band, bvegAnd vegetation biomass information of the observation sample band.
It can be understood that since the measured slow flow coefficient is known, that is, the R value on the left side of the equal sign of formula (3) is known, and v, h and s on the right side of the equal sign of formula (3) are knownveg、bvegThe values are also known, so that the values of a, b, c, d and e in the formula (3) can be obtained by calculation according to a plurality of sample data and a plurality of measured slow flow coefficients, and an empirical model of the vegetation zone slow flow coefficient can be obtained.
The method comprises the steps that the sample data are acquired, wherein accidents may occur during acquisition of the sample data, particularly hydrological information, so that the hydrological information in the sample data needs to be preprocessed before the vegetation zone slow flow coefficient empirical model is trained, and preprocessing specifically comprises missing value filling of missing water depth information and extraction of abnormal flow rate information.
Wherein, the water depth information is filled by a cubic spline interpolation method. First, let S (x) satisfy the sample point requirement, i.e. Sj(x)＝yiWhile the derivative S '(x) is hit, the second derivative S' (x) continues in intervals, then in each subinterval [ x ]j,xj+1](j＝0, 1.. n-1) determining 1 cubic polynomial, wherein the formula is as follows:
Si(x)＝aj+bj(xj+1-xj)+cj(xj+1-xj)2+dj(xj+1-xj) (4)；
in the formula, aj，bj，cj，djUnknown coefficients that need to be calculated.
The identification of abnormal data in the flow rate information measured by the electromagnetic flow meter in the inundation period is carried out by using a time series sliding window and a DBSCAN (DensityBased spatial clustering of application switching noise) clustering algorithm, so that the abnormal identification is carried out on the sample data in the window. The size of the sliding window is 30, the sliding step is 1, the radius of the scanning radius (eps) is 1.5 times the difference between the upper quartile and the lower quartile of the samples in the sliding window, and the minimum number of the samples in the sliding window comprises 20% of the number of points (minPts). In this embodiment, for the identification of abnormal data in the flow rate information, the sliding window is used to identify the data in the window, and the DBSCAN algorithm based on the density is used to identify the abnormal point through the dynamic threshold. The influence of abnormal flow rate data on a modeling result is solved, and meanwhile, the subjectivity of manually setting a fixed threshold is reduced by the dynamic threshold.
In the embodiment, the values of a, b, c, d and e in the formula of the evaluation model of scirpus maritima/scirpus, spartina alterniflora/spartina through calculation of sample data obtained from the chongming laid observation sample zone are shown in the following table 1.
| a | b | c | d | e | |
| Scirpus maritima/Scirpus maritima | 0.019 | -0.623 | 0.099 | 1.821 | 1.469 |
| Spartina alterniflora/spartina alterniflora | 0.025 | -1.568 | 0.098 | 0.554 | 2.285 |
TABLE 1
As can be seen, for different vegetation types, according to the empirical model construction method for vegetation zone runoff slowing coefficients provided by the embodiment, different evaluation models can be obtained, so that in actual use, a corresponding evaluation model is selected according to the vegetation type in the area to be evaluated to evaluate the vegetation runoff capacity.
Generally, after the empirical model of vegetation zone slow flow coefficient is obtained through training, more sample data (test data) are brought into the evaluation model, and the calculated value obtained through the formula (3) is compared with the measured value obtained through the formula (2) to judge whether the precision of the evaluation model meets the requirement, and the training is continued when the precision of the evaluation model does not meet the requirement, as shown in fig. 4.
In step S104, the remote sensing image may be a low-tide-level non-cloud optical image obtained by a centinel-2 satellite in the european space; in one embodiment, the data of the Landsat-8 optical satellite, or other multispectral optical satellite image data and the data acquired by the multispectral sensor of the unmanned aerial vehicle can also be used. And the data of the terrain gradient information, the initial flow velocity and the initial water depth are based on historical observation data of the area to be evaluated or self-defined input values of open documents. The terrain classification model and the vegetation biomass estimation model are preset in advance.
In step S106, the present embodiment is obtained by step S1062, step S1064, and step S1066 as shown in fig. 5.
Step S1062, first, a bank segment boundary of the area to be evaluated is obtained. The land segment boundaries are typically irregular line segments.
And step S1064, equally dividing the bank segment boundary into a plurality of sub bank segments.
Step S1066, extending the sub-bank segment at equal distance at least twice by using the buffer area according to the direction from the bank to the sea, so as to obtain an evaluation unit.
The evaluation units are numbered to obtain a spatial grid of the region to be evaluated, as shown in fig. 6, for example, (i, j) represents the jth evaluation unit of the ith sub-bank segment. In this embodiment, the spatial grid specifically includes four pieces of information: the land section boundary, the number of the sub-land sections, the unit width and the unit number, wherein the number of the sub-land sections is the number of the sub-land sections which are divided at equal intervals, the unit width is the length of the sub-land sections which are extended at equal intervals in one time from the land direction to the sea direction, and the unit number is the number of times of the sub-land sections which are extended at equal intervals from the land direction to the sea direction.
In step S108, the present embodiment obtains vegetation biomass information of the evaluation unit through step S1080, step S1082, step S1084, step S1086, step S1088, step S10810, step S10812, step S10814, and step S10816 as shown in fig. 7.
And S1080, establishing a ground feature classification model and a biomass estimation model by combining ground sampling points and sampling synchronous remote sensing images.
And step S1082, obtaining information of each wave band of each pixel in the remote sensing image information of each evaluation unit.
The remote sensing image information is generally multi-band data, each pixel has multi-band information, and each band information of each pixel is input.
And S1084, determining the vegetation type corresponding to each pixel according to each wave band information of each pixel and the ground feature classification model.
In the present embodiment, as shown in fig. 8, the vegetation type in each pixel element is determined by step S10842, step S10844, and step S10846.
Step S10842, converting each band information of each pixel into a point element. Specifically, ArcMAP software is used to convert the input information of each wave band of each pixel into point elements.
Step S10844, the point elements are processed by the point element layer, information of each wave band of each pixel is extracted to a point, and a csv file is generated. Similarly, this step is also implemented using ArcMAP software, and is typically added with coordinate information to generate the csv file.
And S10846, substituting the csv file into the ground object classification model to obtain the vegetation type corresponding to each pixel. And obtaining point diagram layer files of different ground object types such as water bodies, light beaches, vegetations (reed, scirpus marigolensis/scripus triqueter, sparrow/cord grass and the like) and the like for use.
The feature classification model is an ensemble learning classification model, which has a plurality of types, and as shown in table 2 below, different ensemble learning classification models have different classification accuracies. In the embodiment, the csv files are preferably classified by using an integrated learning XGboost algorithm, and vegetation types corresponding to the pixels are obtained.
| Integrated learning classification model | KNN | SVM | RF | GBDT | XGBoost |
| Accuracy (%) | 90.84 | 91.82 | 92.71 | 92.50 | 94.82 |
TABLE 2
It can be understood that different types of vegetation can build different vegetation zone current slowing coefficient empirical models, and generally, there are a plurality of vegetation zone current slowing coefficient empirical models, and each vegetation zone current slowing coefficient empirical model corresponds to one or more types of vegetation, as shown in table 1. And selecting and using a corresponding vegetation zone runoff slowing coefficient empirical model according to the obtained vegetation type when evaluating the vegetation runoff capacity.
After the vegetation type of each pixel is determined, step S1086 continues.
Step S1086, a vegetation coefficient calculation formula is determined according to the vegetation type corresponding to each pixel, and a feature set S of the vegetation coefficient of each pixel is obtained according to the vegetation coefficient calculation formula and the information of each wave band of each pixel1。
In the embodiment, point map layer files of different ground feature types are added into ArcMAP software, pixel waveband information destination points are extracted by using different vegetation element layer, and finally, csv files are exported. And vegetation coefficients were calculated by the calculation formula in table 3 below.
Wherein L ═
TABLE 3
Step S1088, rejecting feature set S1To obtain a dimension set S2。
Establishing a correlation matrix for all dimension information data, wherein a correlation formula between the characterization dimension i and the characterization dimension j is as follows:
then, the similarity d of two dimensions i and j is calculated by applying the Euclidean distancei,jThe calculation formula is as follows:
in this example, take di,jIf the number of the dimensionalities is more than 0.05m, determining that the collinearity exists between the two dimensionalities, and iteratively calculating until the collinearity does not exist between the information of each dimensionality, thereby obtaining a dimensionality set S2。
Step S10810, inputting biomass obtained by contemporaneous harvest measurement and dimension set S2Calculating the importance of each feature by using a random forest variable selection algorithm (VSURF), and performing dimension set S according to the order of the importance from high to low2Screening by greedy algorithm to obtain training set S3。
Wherein for the importance x of the ith variableiThe calculation formula is as follows:
in the formula, ntreeFor the number of random forest trees, errobb_noiseError outside the bag for noise disturbance, errobbOut-of-bag data errors. For importance ofHigh-direction low-direction arrangement, substituting sequence forward selection algorithm to select under corresponding model, and outputting set S for model training3。
In this embodiment, the actual measurement data before and after 8 months and 13 days of 2020 in the field of Chongmingtong beach is substituted for calculation to obtain a feature set S for scirpus maritima/scirpus maritima input model training1Is { NDVI, MSR, ARVI }, a feature set S trained by the spartina alterniflora/spartina anglica input model1Is { MS, NDVI }.
And S10812, selecting a vegetation biomass estimation model according to the vegetation type corresponding to each pixel.
Step S10814, according to the training set S3And a vegetation biomass estimation model for obtaining the vegetation biomass information of each pixel.
In this embodiment, there are various vegetation biomass estimation models, which can be selected according to specific vegetation types. The vegetation type determined above in the respective picture element can thus play a role here. In actual operation, firstly, selecting a corresponding vegetation biomass estimation model according to the vegetation type actually determined by a certain pixel, and specifically referring to tables 4 and 5; then the training set S3And (4) carrying the image element into the vegetation biomass estimation model to calculate and obtain the vegetation biomass information of the image element.
TABLE 4
TABLE 5
And S10816, determining vegetation biomass information of each evaluation unit according to the vegetation biomass information of each pixel.
Since each evaluation unit comprises a plurality of pixels, it can be understood that the vegetation type of each pixel is not completely consistent, even no vegetation. Therefore, when calculating vegetation biomass information of the evaluation unit, it can be calculated in the following manner.
When the dominant ground feature type is vegetation, determining the type of the dominant vegetation in the evaluation unit, wherein the dominant vegetation refers to the vegetation occupying the most pixels in the evaluation unit; and multiplying the ratio of the number of the pixels occupied by the dominant vegetation to the total number of the pixels in the evaluation unit by the average vegetation biomass information of the pixels in the evaluation unit, namely the vegetation biomass information of the evaluation unit.
On the basis of determining the vegetation zone current slowing coefficient empirical model, the specific implementation process of the step S1010 is as follows:
firstly, according to input initial flow velocity information and initial water depth information, vegetation biomass information and terrain gradient information of a first evaluation unit in a sea-to-land direction and an empirical model of vegetation zone buffer flow coefficients are obtained, the vegetation zone buffer flow coefficients of the first evaluation unit in the sea-to-land direction can be determined, wherein the initial flow velocity information is incoming flow velocity information of the first evaluation unit in the sea-to-land direction.
Then, according to the vegetation zone slow flow coefficient and terrain gradient information of the first evaluation unit in the sea-land direction, the vegetation zone slow flow coefficient empirical model, the initial flow velocity information and the initial water depth information, the coming flow velocity information and the initial water depth information of the second evaluation unit in the sea-land direction can be determined.
The incoming flow speed information of the second evaluation unit from the sea to the land is the outgoing flow speed information of the first evaluation unit from the sea to the land; the calculation formula is as follows:
in the formula, veli，jThe input flow rate of the jth evaluation unit of the ith sub-bank segment is shown, and the Width is the unit Width of the evaluation unit.
Wherein, the initial water depth information of the second evaluation unit is obtained from the sea-to-land direction; the calculation formula is as follows:
in the formula, hi，jThe initial water depth of the jth evaluation unit of the ith sub-bank segment is shown, and Slope is the mean Slope value in the evaluation unit. And, when calculating the obtained hi，jWhen the current flow is smaller than the set tidal current distance to ground height, the current cannot flow into the jth evaluation unit of the ith sub-bank section (the current cannot pass through the previous evaluation unit), the evaluation is finished, and the subsequent evaluation unit does not calculate; at this time, the evaluation grid can be encrypted, that is, the width of the evaluation unit is reduced, and the position of the water depth equal to the height of the tidal current from the ground is determined, so that accurate calculation can be performed.
And then, determining the vegetation zone slow flow coefficient and the arrival flow rate information of the second evaluation unit from the sea to the land direction according to the arrival flow rate information of the second evaluation unit from the sea to the land direction, the initial water depth information of the second evaluation unit from the sea to the land direction, the vegetation biomass information and the terrain slope information of the second evaluation unit from the sea to the land direction and the vegetation zone slow flow coefficient empirical model.
And finally, by analogy, determining the vegetation zone slow flow coefficient of the rest evaluation units from the sea to the land.
In step S1012, by performing meshing splitting on the area to be evaluated and calculating the vegetation slow flow coefficients of each evaluation unit one by one, the influence of the evolution law of the tidal current from sea to land on the vegetation slow flow capability can be visually seen, so that the evaluation result is more in accordance with the actual situation, as shown in fig. 9. Therefore, the actual situation that the vegetation area is not interacted with the tidal current due to gradual reduction of the flow speed and influence of the terrain slope in the process that the tidal current advances from sea to land is considered in space, and the evaluation result is combined with the actual situation. In addition, on the one hand, the method fully considers the difference of the influence of the ground feature type and the vegetation biomass on the vegetation runoff capacity based on the remote sensing image data, and brings the two information into the vegetation runoff capacity evaluation, so that the vegetation runoff capacity difference caused by the vegetation space growth difference can be effectively evaluated; on the other hand, the difference of the vegetation slow flow capacity under the conditions of different water depths and flow velocities is fully considered, so that the result is more accurate.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the described embodiments. It will be apparent to those skilled in the art that various changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, and the scope of protection is still within the scope of the invention.
Claims (10)
1. A remote sensing-based spatial evaluation method for slow flow capacity of salt marsh vegetation is characterized by comprising the following steps: comprises the following steps of (a) carrying out,
establishing a vegetation zone slow flow coefficient empirical model of the relation among different salt marsh vegetation slow flow coefficients, terrain gradient, vegetation biomass, water depth and flow rate, wherein the slow flow coefficient is the ratio of the attenuation of the flow rate in unit distance to the input flow rate;
obtaining remote sensing image classification and vegetation biomass estimation model and terrain slope information of a region to be evaluated, and setting initial flow velocity information and initial water depth information;
establishing an evaluation grid, and dividing the area to be evaluated into a plurality of evaluation units;
determining vegetation biomass information of each evaluation unit according to the remote sensing image classification and the vegetation biomass estimation model;
sequentially determining the vegetation zone unit distance current slowing coefficients of the evaluation units according to the initial flow velocity information, the initial water depth information, the vegetation biomass information and the terrain slope information of the evaluation units and the vegetation zone current slowing coefficient empirical model from the sea to the land to obtain water depth and flow velocity output results;
and evaluating the vegetation zone slow flow capacity of the area to be evaluated according to the vegetation zone unit distance slow flow coefficient of each evaluation unit.
2. The remote sensing-based spatial evaluation method for slow flow capacity of salt marsh vegetation according to claim 1, wherein the method comprises the following steps: the step of establishing the vegetation zone slow flow coefficient empirical model of the relationship among the slow flow coefficients of different salt marsh vegetation, terrain slope, vegetation biomass, water depth and flow rate comprises the following steps,
obtaining a plurality of sample data of a long-time-sequence observation sample band, wherein the sample data comprises terrain slope information, vegetation biomass information and hydrological information, and the hydrological information comprises initial water depth information before water flows through the observation sample band, incoming flow velocity information before the water flows through the observation sample band and outgoing flow velocity information after the water flows through the observation sample band;
obtaining a plurality of actually measured slow flow coefficients of the observation sample band according to the incoming flow velocity information and the outgoing flow velocity information in the plurality of sample data;
training an evaluation model according to the plurality of sample data and the plurality of actually measured slow flow coefficients, wherein the evaluation model is R ═ av + bh + csveg+dbveg+e；
Wherein v is the information of the flow velocity in the forward direction of the water flow flowing through the observation sample zone, h is the information of the initial water depth of the water flow flowing through the observation sample zone, and svegFor the topographic gradient information of the observation sample band, bvegAnd vegetation biomass information of the observation sample band.
3. The remote sensing-based spatial evaluation method for slow flow capacity of salt marsh vegetation according to claim 1, wherein the method comprises the following steps: the step of determining vegetation biomass information for each of the evaluation units based on the remote sensing image classification and the vegetation biomass estimation model includes,
establishing a ground feature classification model and a biomass estimation model by combining ground sampling points and sampling synchronous remote sensing images;
acquiring information of each wave band of each pixel in the remote sensing image information of each evaluation unit;
determining the vegetation type corresponding to each pixel according to the wave band information of each pixel and the ground feature classification model;
obtaining a feature set S of the vegetation coefficient of each pixel according to the vegetation coefficient calculation formula and the information of each wave band of each pixel1；
Rejecting the feature set S1To obtain a dimension set S2；
Calculating a dimension set S from biomass obtained from contemporaneous harvest measurements2The importance of each feature in the dimension set S is determined according to the order of the importance from high to low2Screening by greedy algorithm to obtain training set S3；
Selecting a vegetation biomass estimation model according to the vegetation type corresponding to each pixel;
according to the training set S3The vegetation biomass estimation model is used for obtaining vegetation biomass information of each pixel;
and determining the vegetation biomass information of each evaluation unit according to the vegetation biomass information of each pixel.
4. The remote sensing-based spatial evaluation method for slow flow capacity of salt marsh vegetation according to claim 3, wherein the method comprises the following steps: the step of determining the vegetation biomass information of each evaluation unit according to the vegetation biomass information of each pixel comprises the following steps,
determining the type of the dominant vegetation in each evaluation unit, wherein the dominant vegetation is the vegetation type occupying the most pixels in each evaluation unit;
and multiplying the ratio of the number of the pixels occupied by the dominant vegetation to the total number of the pixels in the evaluation unit by the average vegetation biomass information of the pixels in the evaluation unit, namely the vegetation biomass information of the evaluation unit.
5. The remote sensing-based spatial evaluation method for slow flow capacity of salt marsh vegetation according to claim 3, wherein the method comprises the following steps: the step of determining the vegetation type corresponding to each pixel according to the waveband information of each pixel and the surface feature classification model comprises the steps of,
converting each wave band information of each pixel into a point element;
processing the point elements by using the point element map layer, respectively extracting the waveband information of each pixel to a point, and generating a csv file;
substituting the csv file into the ground feature classification model to obtain the vegetation type corresponding to each pixel, wherein the ground feature classification model is a pre-established ensemble learning classification model.
6. The remote sensing-based spatial evaluation method for slow flow capacity of salt marsh vegetation according to claim 5, wherein the method comprises the following steps: the vegetation zone current slowing coefficient empirical model is multiple, and each vegetation zone current slowing coefficient empirical model corresponds to one or multiple types of vegetation.
7. The remote sensing-based spatial evaluation method for slow flow capacity of salt marsh vegetation according to claim 1, wherein the method comprises the following steps: the step of establishing an evaluation grid and dividing the area to be evaluated into a plurality of evaluation units comprises,
determining a bank segment boundary of the area to be evaluated;
equally dividing the bank segment boundary into a plurality of sub bank segments;
and according to the direction from land to sea, equally extending the sub-bank segments at least twice by using a buffer area to obtain the plurality of evaluation units.
8. The remote sensing-based spatial evaluation method for slow flow capacity of salt marsh vegetation according to claim 1, wherein the method comprises the following steps: the step of obtaining the water depth and flow velocity output result comprises the steps of determining the vegetation zone unit distance current slowing coefficients of each evaluation unit in turn according to the sea-to-land direction according to the initial flow velocity information, the initial water depth information, the vegetation biomass information and the terrain slope information of each evaluation unit and the vegetation zone current slowing coefficient empirical model,
determining a vegetation zone slow flow coefficient of a first evaluation unit from the sea to the land according to the input initial flow information, the initial water depth information, the obtained vegetation biomass information and terrain slope information of the first evaluation unit from the sea to the land and the vegetation zone slow flow coefficient empirical model, wherein the initial flow information is the incoming flow information of the first evaluation unit from the sea to the land;
determining the incoming flow velocity information and the initial water depth information of a second evaluation unit from the sea to the land according to the vegetation zone slow flow coefficient and terrain slope information of the first evaluation unit from the sea to the land, the empirical model of the vegetation zone slow flow coefficient, and the initial flow velocity information and the initial water depth information, wherein the incoming flow velocity information of the second evaluation unit from the sea to the land is the outgoing flow velocity information of the first evaluation unit from the sea to the land;
determining vegetation zone slow flow coefficient and heading flow rate information of the second evaluation unit from the sea to the land according to the heading flow rate information of the second evaluation unit from the sea to the land, initial water depth information of the second evaluation unit from the sea to the land, vegetation biomass information and terrain slope information of the second evaluation unit from the sea to the land and the vegetation zone slow flow coefficient empirical model;
and determining the vegetation zone slow flow coefficient of the rest evaluation units from the sea to the land by analogy.
9. The remote sensing-based spatial evaluation method for slow flow capacity of salt marsh vegetation according to claim 2, wherein the method comprises the following steps: and before training the vegetation zone slow flow coefficient empirical model, preprocessing hydrological information in sample data.
10. The remote sensing-based spatial evaluation method for slow flow capacity of salt marsh vegetation according to claim 9, wherein: the preprocessing comprises missing value filling of missing water depth information and extraction of abnormal flow velocity information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011266175.9A CN112380984B (en) | 2020-11-13 | 2020-11-13 | Remote sensing-based salt-biogas vegetation slow-flow capacity space evaluation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011266175.9A CN112380984B (en) | 2020-11-13 | 2020-11-13 | Remote sensing-based salt-biogas vegetation slow-flow capacity space evaluation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112380984A true CN112380984A (en) | 2021-02-19 |
| CN112380984B CN112380984B (en) | 2024-04-30 |
Family
ID=74583683
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011266175.9A Active CN112380984B (en) | 2020-11-13 | 2020-11-13 | Remote sensing-based salt-biogas vegetation slow-flow capacity space evaluation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112380984B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102332110A (en) * | 2011-07-05 | 2012-01-25 | 北京师范大学 | Swampiness degree evaluation technology based on geographic information system (GIS) grid |
| CN104484710A (en) * | 2014-11-19 | 2015-04-01 | 华侨大学 | Method of predicting erosion amount of soft sea cliff surface caused by wave action |
| CN107347410A (en) * | 2017-07-27 | 2017-11-17 | 中国环境科学研究院 | A kind of more habitat solid vegetation construction methods of embankment type lakeside zone |
| CN110378926A (en) * | 2019-06-17 | 2019-10-25 | 成都理工大学 | A kind of aboveground vegetation ecological water evaluation method based on airborne LiDAR and Sentinel-2A data |
| CN110909494A (en) * | 2018-09-13 | 2020-03-24 | 中国石油化工股份有限公司 | Safety evaluation method for beach, sea and shore facilities |
| CN111401529A (en) * | 2020-04-21 | 2020-07-10 | 中国水利水电科学研究院 | River ecological flow supervision method based on remote sensing technology |
| CN111738561A (en) * | 2020-05-29 | 2020-10-02 | 中国电建集团华东勘测设计研究院有限公司 | Regional water and soil loss dynamic monitoring method based on deep learning |
| US20200334458A1 (en) * | 2019-04-16 | 2020-10-22 | Precision Silver, LLC | Systems and methods for rating vegetation health and biomass from remotely sensed morphological and radiometric data |
-
2020
- 2020-11-13 CN CN202011266175.9A patent/CN112380984B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102332110A (en) * | 2011-07-05 | 2012-01-25 | 北京师范大学 | Swampiness degree evaluation technology based on geographic information system (GIS) grid |
| CN104484710A (en) * | 2014-11-19 | 2015-04-01 | 华侨大学 | Method of predicting erosion amount of soft sea cliff surface caused by wave action |
| CN107347410A (en) * | 2017-07-27 | 2017-11-17 | 中国环境科学研究院 | A kind of more habitat solid vegetation construction methods of embankment type lakeside zone |
| CN110909494A (en) * | 2018-09-13 | 2020-03-24 | 中国石油化工股份有限公司 | Safety evaluation method for beach, sea and shore facilities |
| US20200334458A1 (en) * | 2019-04-16 | 2020-10-22 | Precision Silver, LLC | Systems and methods for rating vegetation health and biomass from remotely sensed morphological and radiometric data |
| CN110378926A (en) * | 2019-06-17 | 2019-10-25 | 成都理工大学 | A kind of aboveground vegetation ecological water evaluation method based on airborne LiDAR and Sentinel-2A data |
| CN111401529A (en) * | 2020-04-21 | 2020-07-10 | 中国水利水电科学研究院 | River ecological flow supervision method based on remote sensing technology |
| CN111738561A (en) * | 2020-05-29 | 2020-10-02 | 中国电建集团华东勘测设计研究院有限公司 | Regional water and soil loss dynamic monitoring method based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 徐海珏;胡萍;白玉川;杨波;: "木本植被覆盖岸坡上波浪爬升过程的数值模拟研究", 海洋学报, no. 03, 15 March 2020 (2020-03-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112380984B (en) | 2024-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Samanta et al. | Interpolation of climate variables and temperature modeling | |
| Gourley et al. | A method for evaluating the accuracy of quantitative precipitation estimates from a hydrologic modeling perspective | |
| Chen et al. | Aboveground biomass of salt-marsh vegetation in coastal wetlands: Sample expansion of in situ hyperspectral and Sentinel-2 data using a generative adversarial network | |
| CN105115469B (en) | Paddy rice spike of rice phenotypic parameter automatic measurement and fringe weight Forecasting Methodology | |
| Dolling et al. | The use of the deviation angle variance technique on geostationary satellite imagery to estimate tropical cyclone size parameters | |
| CN112903606B (en) | Mangrove forest ecological restoration force assessment method based on unmanned aerial vehicle hyperspectrum | |
| Billah et al. | Random forest classifications for landuse mapping to assess rapid flood damage using Sentinel-1 and Sentinel-2 data | |
| Tarwidi et al. | An optimized XGBoost-based machine learning method for predicting wave run-up on a sloping beach | |
| Chiang et al. | Multi-source rainfall merging and reservoir inflow forecasting by ensemble technique and artificial intelligence | |
| Kulawardhana et al. | Airborne lidar remote sensing applications in non-forested short stature environments: a review | |
| Khan et al. | Assessment of the hydrological and coupled soft computing models, based on different satellite precipitation datasets, to simulate streamflow and sediment load in a mountainous catchment | |
| Zhu et al. | An extraction method for long-term tropical cyclone precipitation from daily rain gauges | |
| Wang et al. | Early warning of debris flow using optimized self-organizing feature mapping network | |
| Ayub et al. | Wheat Crop Field and Yield Prediction using Remote Sensing and Machine Learning | |
| Antonarakis et al. | Retrieval of vegetative fluid resistance terms for rigid stems using airborne lidar | |
| CN112380984A (en) | Remote sensing-based saline marsh vegetation slow flow capacity space evaluation method | |
| CN112836449B (en) | Method for calibrating hydrologic model | |
| Makungu | A Combined Modelling Approach for Simulating Channel–Wetland Exchanges in Large African River Basins | |
| Kalinga et al. | Merging WSR-88D stage III radar rainfall data with rain gauge measurements using wavelet analysis | |
| Caccetta et al. | Aspects of reasoning with uncertainty in an agricultural GIS environment | |
| Lussana et al. | Evaluation of seNorge2, a conventional climatological datasets for snow-and hydrological modeling in Norway | |
| Nghiem et al. | Application of GIS and remote sensing for predicting land-use change in the French Jura Mountains with the LCM model: the impact of variables on the disturbance model | |
| Kim-Anh et al. | Soil salinity assessment by using near-infrared channel and Vegetation Soil Salinity Index derived from Landsat 8 OLI data: a case study in the Tra Vinh Province, Mekong Delta, Vietnam | |
| Bachour | Evapotranspiration modeling and forecasting for efficient management of irrigation command areas | |
| Domakonda et al. | An Empirical Evaluation of Machine Learning Algorithms for Groundwater Quality Classification |
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 |