CN111652347A - Method for inverting leaf area index by improving neural network through particle swarm algorithm - Google Patents
Method for inverting leaf area index by improving neural network through particle swarm algorithm Download PDFInfo
- Publication number
- CN111652347A CN111652347A CN202010329275.5A CN202010329275A CN111652347A CN 111652347 A CN111652347 A CN 111652347A CN 202010329275 A CN202010329275 A CN 202010329275A CN 111652347 A CN111652347 A CN 111652347A
- Authority
- CN
- China
- Prior art keywords
- leaf area
- area index
- neural network
- wheat
- particle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000002245 particle Substances 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 14
- 241000209140 Triticum Species 0.000 claims abstract description 21
- 235000021307 Triticum Nutrition 0.000 claims abstract description 21
- 240000008042 Zea mays Species 0.000 claims abstract description 19
- 235000002017 Zea mays subsp mays Nutrition 0.000 claims abstract description 19
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 claims abstract description 13
- 235000005822 corn Nutrition 0.000 claims abstract description 13
- 230000005540 biological transmission Effects 0.000 claims abstract description 8
- 230000005855 radiation Effects 0.000 claims abstract description 8
- 238000003062 neural network model Methods 0.000 claims abstract description 7
- 235000016383 Zea mays subsp huehuetenangensis Nutrition 0.000 claims abstract description 6
- 235000009973 maize Nutrition 0.000 claims abstract description 6
- 238000002310 reflectometry Methods 0.000 claims abstract description 6
- 230000004927 fusion Effects 0.000 claims abstract description 3
- 238000012549 training Methods 0.000 claims abstract description 3
- 238000005316 response function Methods 0.000 abstract description 3
- 230000003595 spectral effect Effects 0.000 abstract description 3
- 229930002875 chlorophyll Natural products 0.000 abstract description 2
- 235000019804 chlorophyll Nutrition 0.000 abstract description 2
- ATNHDLDRLWWWCB-AENOIHSZSA-M chlorophyll a Chemical compound C1([C@@H](C(=O)OC)C(=O)C2=C3C)=C2N2C3=CC(C(CC)=C3C)=[N+]4C3=CC3=C(C=C)C(C)=C5N3[Mg-2]42[N+]2=C1[C@@H](CCC(=O)OC\C=C(/C)CCC[C@H](C)CCC[C@H](C)CCCC(C)C)[C@H](C)C2=C5 ATNHDLDRLWWWCB-AENOIHSZSA-M 0.000 abstract description 2
- 238000012360 testing method Methods 0.000 abstract description 2
- 238000011160 research Methods 0.000 description 4
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000013179 statistical model Methods 0.000 description 2
- 241000132092 Aster Species 0.000 description 1
- 244000068988 Glycine max Species 0.000 description 1
- 235000010469 Glycine max Nutrition 0.000 description 1
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004173 biogeochemical cycle Methods 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 230000029553 photosynthesis Effects 0.000 description 1
- 238000010672 photosynthesis Methods 0.000 description 1
- 229910052700 potassium Inorganic materials 0.000 description 1
- 239000011591 potassium Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000005068 transpiration Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
- 229910001868 water Inorganic materials 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Strategic Management (AREA)
- Animal Husbandry (AREA)
- Agronomy & Crop Science (AREA)
- Marine Sciences & Fisheries (AREA)
- General Business, Economics & Management (AREA)
- Mining & Mineral Resources (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for inverting a leaf area index by a particle swarm algorithm improved neural network, which comprises the following steps: step 1) based on a PROSAIL radiation transmission model, inputting parameters of chlorophyll, solar altitude, leaf area index and the like of the actually measured corn and wheat, and combining a spectral response function of a GF-1 satellite, respectively outputting the canopy reflectivity of the corn and the wheat in the booting stage. And 2) improving a neural network model based on a particle swarm algorithm, determining the dimension of each particle by the weight and the threshold number of the position vector of each particle in the particle swarm corresponding to the connection function in the neural network, taking the output error of the neural network of a given training sample set as a fitness function, expressing the error of the neural network by a fitness value, and indicating that the particle has better performance in the search if the error is smaller. The particles are moved and searched in the space of the weight value, so that the error of the network output layer is minimum, and the weight value of the network is updated by changing the speed of the particles. Inputting the canopy reflectivity and the actually measured leaf area index, and outputting a predicted leaf area index value. And 3) combining the predicted maize and wheat leaf area index values, inverting the maize and wheat leaf area index values, and forming a map, wherein the inversion accuracy of the leaf area index is further improved by GF-1 satellite WFV data and a multi-model fusion test.
Description
Technical Field
The invention relates to a method for inverting a leaf area index by a neural network improved by a particle swarm algorithm, in particular to a method for rapidly inverting the leaf area index in a large area by applying a GF-1 satellite WFV image.
Background
The Leaf Area Index (LAI) is one of important vegetation structure parameters in the biogeochemical cycle, and is closely related to the biophysical processes of respiration, photosynthesis, transpiration and the like of vegetation, the nitrogen, potassium and water circulation and the like of the earth ecosystem. LAI is defined as half of the sum of all leaf areas on a unit area, is also an important agricultural physiological and ecological parameter for evaluating vegetation growth and predicting yield, and is also an important index for carrying out drought monitoring and crop yield estimation.
Leaf area indexes are inverted based on a traditional empirical model, Sunwood and the like establish an optimal estimation model of the LAI by researching and measuring the correlation between the LAI and series vegetation indexes based on HYPERION images and utilizing three regression analysis technologies. The Zhao Juan and the like adopt six kinds of broadband vegetation indexes and four kinds of narrow-band vegetation indexes, and analysis and comparison of the LAI inversion accuracy by using different vegetation indexes in the whole growth period of winter wheat show that the LAI inversion accuracy can be improved by using different vegetation indexes to construct in different growth periods. High forest class and the like respectively construct an empirical regression model based on hyperspectral data, unmanned aerial vehicle multispectral images and high-resolution first-order images by combining 5 vegetation indexes and ground actual measurement LAI, and differences of 3 types of remote sensing data for inverting the soybean leaf area indexes are compared. The method inverts the leaf area index through the vegetation index regression model, although the method is efficient and simple, the complex transmission process of photons in the vegetation canopy is ignored, the universality is poor, and the transportability is lacked. Based on the radiation transmission model, the leaf area index, Liu Xianchen and the like are based on the simulation data of the PROSAIL model and the ground actual measurement data, the LAI is inverted by respectively utilizing a statistical model, a mixed model, a second-order differential and a directional differential which take NDVI as independent variables, and the inversion result is compared and analyzed. The Lishumin takes Qingyun shops, Wei-good villages and Korea campuses in Beijing as research areas, adopts MODIS and ASTER remote sensing data with different spatial resolutions, discusses feasibility of inversion of winter wheat leaf area index by a PROSAIL physical model, especially stability of the remote sensing data with different spatial resolutions, and carries out comparative analysis with an empirical model. Aiming at the defects that the Leaf Area Index (LAI) inversion by a traditional statistical model method has instability and non-uniformity in areas, such as plum sea and the like, the research starts from a physical mechanism, establishes a lookup table to invert the LAI from a TM image on the basis of PROSPECT, LIBERTY and GEOSAIL models, and compares the LAI with the LAI actually measured by TRAC. The result shows that the LAI reversely calculated by the method based on the mechanism model and the lookup table has better consistency with the actually measured LAI, and the actually measured precision reaches 83.7 percent. Compared with the traditional method, the method has the advantages that the leaf area index is inverted through the non-parametric physical model, the abnormal precision and the efficiency are greatly improved, but the method for inverting the LAI of the corn and the wheat can meet the requirement of high precision, and the explanation is still lacked.
In summary, a single model is mostly adopted for research in home and abroad inversion of leaf area indexes, and the problems of low inversion accuracy and low speed of the maize and wheat leaf area indexes can be solved by using a multi-model fusion method. By comprehensively considering the problems, the invention develops a method for inverting the area indexes of the corn and the wheat leaves by using the WFV data of the GF-1 satellite with typical regional characteristics by utilizing the characteristics of high-grade data.
Disclosure of Invention
Aiming at the problems of insufficient speed, low precision and the like of a model single-leaf LAI inversion method, the invention provides a leaf area index inversion method based on GF-1 satellite WFV data and multispectral data.
The purpose of the invention is realized by the following technical steps:
step 1) based on a PROSAIL radiation transmission model, the canopy reflectivity of the corn and the wheat in the booting stage is respectively output and established by inputting the actually measured chlorophyll, the solar altitude angle and the like of the corn and the wheat and combining the spectral response function of a satellite.
And 2) improving a neural network model based on a particle swarm algorithm, determining the dimension of each particle by the weight and the threshold number of the position vector of each particle in the particle swarm corresponding to the connection function in the neural network, taking the output error of the neural network of a given training sample set as a fitness function, expressing the error of the neural network by a fitness value, and indicating that the particle has better performance in the search if the error is smaller. The particles are moved and searched in the space of the weight value, so that the error of the network output layer is minimum, and the weight value of the network is updated by changing the speed of the particles. Inputting the canopy reflectivity and the actually measured leaf area index, and outputting a predicted leaf area index value.
And 3) inverting the LAI image of the corn and the wheat by combining the predicted LAI value, wherein the method is based on GF-1 satellite WFV data and adopts multi-model fusion, so that the LAI inversion precision can be further improved.
Drawings
FIG. 1 is a flow chart of a particle swarm algorithm improved neural network model;
FIG. 2 is a graph of inversion results of area indexes of corn and wheat leaves in corridor city of Hebei province based on GF-1 WFV;
FIG. 3 is a diagram of various model accuracy contrasts (from left to right, top to bottom: VEVI-LAI, VEVI2-LAI, VMSAVI-LAI, VNDVI-LAI, respectively);
Detailed Description
The invention 'a method for inverting the leaf area index by using the particle swarm optimization algorithm' will be further explained with reference to the attached drawings.
The invention relates to an inversion method of a leaf area index based on a GF-1WFV image, which is an important method innovation of the leaf area index. The method combines a neural network model with a particle swarm algorithm to establish a leaf area index inversion method and is applied to the corridor city of Hebei province, realizes the effect of a multi-model combination test, and enables the leaf area index inversion result to have certain reliability.
The inversion method of the leaf area index based on the WFV image of the GF-1 satellite is an inversion method of the leaf area index based on a PROSAIL radiation transmission model and a particle swarm neural network model, and is applied to an experimental area of a corridor city in Hebei province. Firstly, setting the value range of input parameters in a PROSAIL radiation transmission model based on field measured data and optimal input parameters provided by existing research and by combining spectral response functions of different sensors and a typical object spectrum knowledge base in China. Then, the input parameter values are used as samples, the particle swarm neural network model is used for screening the samples, the optimization of the corn and wheat leaf area indexes is completed (figure 1), and a result graph of corridor city in Hebei province (figure 2) is obtained. Finally, a model of the maize and wheat leaf area indices was established and its reliability was verified (fig. 3).
Claims (4)
1. A method for improving neural network inversion leaf area index by a particle swarm algorithm comprises the following steps:
and acquiring canopy reflectivity images of the corn and the wheat in the booting stage based on a PROSAIL radiation transmission model.
A neural network model is improved based on a particle swarm algorithm, the dimension of each particle is determined by the weight and the threshold number of the position vector of each particle in the particle swarm, which correspond to the weight and the threshold number playing a role in connection in the neural network, the output error of the neural network of a given training sample set is used as a fitness function, the error of the neural network is represented by a fitness value, and the smaller the error is, the better performance of the particle in searching is indicated. The particles are moved and searched in the space of the weight value, so that the error of the network output layer is minimum, and the weight value of the network is updated by changing the speed of the particles. And inputting the canopy reflectivity and the actually measured leaf area index to obtain a predicted leaf area index value.
The inversion image of the area indexes of the corn and the wheat is obtained by combining the actually measured corn and wheat leaf area index values, and the inversion accuracy of the leaf area index is further improved by GF-1WFV data and multi-model fusion.
2. The apparatus of claim 1, wherein: a PROSAIL radiation transmission model and a corn and wheat booting stage canopy radiation model are provided.
3. The method of claim 1, wherein: inversion of maize and wheat leaf area index values based on GF-1WFV data radiance is presented.
4. The method of claim 1, wherein: the optimal maize and wheat inversion leaf area index of the example graph of the corridor city of the Hebei province based on GF-1WFV data is provided.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010329275.5A CN111652347A (en) | 2020-04-23 | 2020-04-23 | Method for inverting leaf area index by improving neural network through particle swarm algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010329275.5A CN111652347A (en) | 2020-04-23 | 2020-04-23 | Method for inverting leaf area index by improving neural network through particle swarm algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111652347A true CN111652347A (en) | 2020-09-11 |
Family
ID=72348270
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010329275.5A Pending CN111652347A (en) | 2020-04-23 | 2020-04-23 | Method for inverting leaf area index by improving neural network through particle swarm algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111652347A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112595267A (en) * | 2020-12-09 | 2021-04-02 | 中国科学院空天信息创新研究院 | Summer corn LAI inversion method fusing factor analysis and ant colony wavelet neural network model |
| CN116593419A (en) * | 2023-04-14 | 2023-08-15 | 南京农业大学 | Wheat green LAI estimation method for relieving influence of LCC and straw-soil background |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103942459A (en) * | 2014-05-13 | 2014-07-23 | 扬州大学 | Method for remotely sensing and monitoring leaf area index of wheat |
| CN105469144A (en) * | 2015-11-19 | 2016-04-06 | 东北大学 | Mobile communication user loss prediction method based on particle classification and BP neural network |
| CN108229403A (en) * | 2018-01-08 | 2018-06-29 | 中国科学院遥感与数字地球研究所 | A kind of mixed model construction method for being used to estimate vegetation leaf area index |
| CN109115725A (en) * | 2018-06-14 | 2019-01-01 | 中国农业大学 | A kind of maize canopy LAI and chlorophyll content joint inversion method and equipment |
| CN110544277A (en) * | 2019-08-12 | 2019-12-06 | 蔡建楠 | Method for inverting subtropical vegetation leaf area index by unmanned aerial vehicle-mounted hyperspectral imager |
-
2020
- 2020-04-23 CN CN202010329275.5A patent/CN111652347A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103942459A (en) * | 2014-05-13 | 2014-07-23 | 扬州大学 | Method for remotely sensing and monitoring leaf area index of wheat |
| CN105469144A (en) * | 2015-11-19 | 2016-04-06 | 东北大学 | Mobile communication user loss prediction method based on particle classification and BP neural network |
| CN108229403A (en) * | 2018-01-08 | 2018-06-29 | 中国科学院遥感与数字地球研究所 | A kind of mixed model construction method for being used to estimate vegetation leaf area index |
| CN109115725A (en) * | 2018-06-14 | 2019-01-01 | 中国农业大学 | A kind of maize canopy LAI and chlorophyll content joint inversion method and equipment |
| CN110544277A (en) * | 2019-08-12 | 2019-12-06 | 蔡建楠 | Method for inverting subtropical vegetation leaf area index by unmanned aerial vehicle-mounted hyperspectral imager |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112595267A (en) * | 2020-12-09 | 2021-04-02 | 中国科学院空天信息创新研究院 | Summer corn LAI inversion method fusing factor analysis and ant colony wavelet neural network model |
| CN116593419A (en) * | 2023-04-14 | 2023-08-15 | 南京农业大学 | Wheat green LAI estimation method for relieving influence of LCC and straw-soil background |
| CN116593419B (en) * | 2023-04-14 | 2024-02-27 | 南京农业大学 | Wheat LAI estimation method for relieving influence of LCC and straw-soil background |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cai et al. | Feedback convolutional network for intelligent data fusion based on near-infrared collaborative IoT technology | |
| CN111007021A (en) | Hyperspectral water quality parameter inversion system and method based on one-dimensional convolution neural network | |
| CN110174359B (en) | Aviation hyperspectral image soil heavy metal concentration assessment method based on Gaussian process regression | |
| CN113128134B (en) | Mining area ecological environment evolution driving factor weight quantitative analysis method | |
| CN105608293B (en) | Merge Biomass retrieval method and system on the woodland of spectrum and textural characteristics | |
| CN109212505B (en) | A kind of forest stand characteristics inversion method based on the multispectral high degree of overlapping image of unmanned plane | |
| CN110927082A (en) | Winter wheat yield prediction method based on unmanned aerial vehicle imaging hyperspectral remote sensing | |
| CN106290197A (en) | The estimation of rice leaf total nitrogen content EO-1 hyperion and estimation models construction method | |
| CN111028096A (en) | System and method for integrating space, air and ground data | |
| CN115356249B (en) | Satellite polarization PM2.5 estimation method and system based on machine learning fusion model | |
| CN115481368B (en) | Vegetation coverage estimation method based on full remote sensing machine learning | |
| CN107688003B (en) | Blade reflectivity satellite remote sensing extraction method for eliminating vegetation canopy structure and earth surface background influence | |
| CN111652347A (en) | Method for inverting leaf area index by improving neural network through particle swarm algorithm | |
| CN108520127A (en) | A kind of EO-1 hyperion inversion method of seeds leaf area index | |
| Liu et al. | Estimating potato above-ground biomass by using integrated unmanned aerial system-based optical, structural, and textural canopy measurements | |
| CN115015258B (en) | Crop growth vigor and soil moisture association determination method and related device | |
| CN115494007A (en) | Random forest based high-precision rapid detection method and device for soil organic matters | |
| Lou et al. | An effective method for canopy chlorophyll content estimation of marsh vegetation based on multiscale remote sensing data | |
| Ma et al. | A review on sensing technologies for high-throughput plant phenotyping | |
| Gong et al. | Spectral reflectance reconstruction from red-green-blue (RGB) images for chlorophyll content detection | |
| Guo et al. | Inversion of maize leaf area index from UAV hyperspectral and multispectral imagery | |
| Wang et al. | Application of hyperspectral technology combined with bat algorithm-AdaBoost model in field soil nutrient prediction | |
| CN113537108A (en) | Crop chlorophyll content inversion method based on unmanned aerial vehicle hyperspectral remote sensing | |
| CN116403048B (en) | Crop growth estimation model construction method based on multi-mode data fusion | |
| CN114460015A (en) | Method and model for predicting chlorophyll content of canopy of rice in cold region |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200911 |
|
| WD01 | Invention patent application deemed withdrawn after publication |