CN114639012A - Grassland degradation evaluation method based on unmanned aerial vehicle hyperspectral remote sensing - Google Patents
Grassland degradation evaluation method based on unmanned aerial vehicle hyperspectral remote sensing Download PDFInfo
- Publication number
- CN114639012A CN114639012A CN202210126115.XA CN202210126115A CN114639012A CN 114639012 A CN114639012 A CN 114639012A CN 202210126115 A CN202210126115 A CN 202210126115A CN 114639012 A CN114639012 A CN 114639012A
- Authority
- CN
- China
- Prior art keywords
- grassland
- degradation
- plant
- unmanned aerial
- aerial vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of grassland degradation evaluation, in particular to a grassland degradation evaluation method based on unmanned aerial vehicle hyperspectral remote sensing, which comprises the following steps: firstly, acquiring a hyperspectral image of an unmanned aerial vehicle in a typical sample area, a spectral curve of a typical plant and community structure information of a sample; establishing plant types and coverage threshold values at different degradation stages, and establishing a grassland degradation evaluation standard based on community species composition; establishing a typical alpine grassland plant spectrum library based on a spectrum curve of a typical plant, and screening out a spectrum characteristic variable and a sensitive wave band which are beneficial to grass seed identification by using a Mahalanobis distance method; identifying the species composition of the grassland plants by using a combined sparse unmixing model based on the unmanned aerial vehicle image, and analyzing and counting to obtain the total community coverage, the types of established species and degraded grass species and the sub-coverage; and fifthly, evaluating the degradation degree of the alpine grassland by combining the grassland degradation evaluation standard according to the structural information of the plant community. The invention can better monitor the degradation of the grassland on a large scale.
Description
Technical Field
The invention relates to the technical field of grassland degradation evaluation, in particular to a grassland degradation evaluation method based on unmanned aerial vehicle hyperspectral remote sensing.
Background
In recent years, the ecosystem of alpine grasses in parts of Qinghai-Tibet plateau is subject to severe deterioration due to the influence of multiple factors such as climate change and human activity expansion. The accurate and quantitative evaluation of the degradation condition of the alpine grassland is the basis of the protection and reasonable utilization of the grassland in the vulnerable area of the ecological environment of the Qinghai-Tibet plateau. At present, the whole space distribution condition of grassland ecosystem degeneration in the alpine and fragile ecological region of the Qinghai-Tibet plateau needs to be cleared urgently.
In the grassland degradation monitoring work, the traditional field on-site investigation method is difficult to obtain the overall situation of the grassland degradation in the regional scale, and the current grassland degradation remote sensing monitoring method based on the reduction of the vegetation index, the vegetation coverage, the productivity and the grass yield cannot accurately reflect the plant species composition change characteristics in the degradation process of the grassland ecosystem. Grassland deterioration is often accompanied by a reduction or even disappearance of the population and dominant species coverage of the plants, and the types of grassland vegetation and the structural characteristics of the population are often significantly changed.
Disadvantages of field investigation: the traditional field investigation method wastes time and energy, consumes time and money, acquires grassland degradation characteristics of a sample party/small scale, and cannot acquire grassland degradation space distribution conditions of regional scales. The cause is as follows: the traditional grassland degradation monitoring mainly adopts a method for field sample investigation, but the method has the limitations of long time consumption, low efficiency, small investigation range and the like, and is difficult to monitor and evaluate the degradation degree of high-cold grassland on a regional scale in a short time.
(2) The traditional grassland degradation remote sensing monitoring method has the following defects: the traditional grassland degradation remote sensing monitoring method based on vegetation index, vegetation coverage, productivity and grass yield reduction can not accurately reflect species composition degradation characteristics of grassland plants. The cause is as follows: the conventional remote sensing monitoring method for the grassland degradation usually assumes that the vegetation index, the vegetation coverage and the productivity are reduced in the process of the grassland degradation, and the grass yield of the grassland is reduced. However, biomass and vegetation coverage do not necessarily decrease during grassland deterioration. For example, there may be populations with a reduced dominant population and a degraded indicator of increased species or toxic weeds, and the corresponding NDVI or vegetation coverage of the population may remain unchanged or even increase. The common remote sensing monitoring method for the grassland degradation still has more problems.
Therefore, a grassland degradation remote sensing monitoring method based on unmanned aerial vehicle hyperspectral remote sensing needs to be constructed, a new thought and a new method can be provided for grassland degradation monitoring on the basis of hyperspectral remote sensing identification formed by species of grassland plant communities, and a basis is provided for sustainable utilization and management of alpine grasslands.
Disclosure of Invention
The invention provides a grassland degradation evaluation method based on unmanned aerial vehicle hyperspectral remote sensing, which can accurately and quantitatively evaluate the grassland degradation degree.
The grassland degradation evaluation method based on the hyperspectral remote sensing of the unmanned aerial vehicle comprises the following steps:
firstly, acquiring a hyperspectral image of an unmanned aerial vehicle in a typical sample area, a spectral curve of a typical plant and community structure information of a sample;
establishing plant types and coverage threshold values at different degradation stages based on plant community structure information of a typical sample, and establishing a grassland degradation evaluation standard based on community species composition;
thirdly, establishing a typical alpine grassland plant spectrum library based on the spectrum curve of the typical plant, and screening out a spectrum characteristic variable and a sensitive wave band which are beneficial to grass seed identification by using a Mahalanobis distance method;
identifying the species composition of the grassland plants by using a combined sparse unmixing model based on the unmanned aerial vehicle image, and further analyzing and counting to obtain the total community coverage, the types of the established population and the degraded grass and the sub-coverage;
and fifthly, evaluating the degradation degree of the alpine grassland by combining the grassland degradation evaluation standard according to the structural information of the plant community, thereby achieving the purpose of quantitatively evaluating and monitoring the grassland degradation.
Preferably, in the first step, in a plant growth peak period, typical alpine grassland field sampling areas of different degradation stages of the grassland are respectively selected, and under a clear weather condition, unmanned aerial vehicle hyperspectral images of the typical grassland degradation sample areas are respectively obtained, spectral curves of typical alpine plants are tested, and community structure information of ground samples is recorded.
Preferably, the different degradation stages of the grass comprise non-degradation, light degradation, moderate degradation, severe degradation and extremely severe degradation stages; and respectively acquiring a hyperspectral image of the unmanned aerial vehicle in the grassland degradation typical sample area, testing a spectral curve of a typical alpine plant and recording community structure information of a ground sample by using the unmanned aerial vehicle carrying the hyperspectral camera and a ground object spectrometer.
Preferably, in the second step, based on the plant community information of different degradation stages of a typical alpine grassland investigated in the field, the difference of the constitutional features of the grassland plant community with different degradation degrees is analyzed, and the threshold value of the evaluation index between different degradation grades is defined, so that the grassland degradation evaluation standard based on the community species composition is constructed.
Preferably, the community species composition includes the type and area proportion of the colonizing species, the companion species, the degeneration-indicating species.
Preferably, in the third step, a plant spectrum library of the alpine grassland is established; and (3) extracting hyperspectral characteristic variables by utilizing spectral characteristic transformation and operation, and screening out wave bands or characteristic variables with large plant differences as spectral characteristic variables and sensitive wave bands which are beneficial to grass seed identification based on the Mahalanobis distance method.
Preferably, the spectral feature transformation and operation includes a first derivative, a second derivative and a spectral index; the hyperspectral characteristic variables include red-edge characteristics, normalized vegetation index NDVI and simple ratio vegetation index SR.
Preferably, in the fourth step, a hyperspectral data set corresponding to the hyperspectral image of the unmanned aerial vehicle is calculated and constructed based on the screened sensitive wave band; based on the data set, plant type information collected on the ground is used as a training sample, the types and the abundances of the alpine plants are extracted by using a combined sparse and unmixed model, and the coverage of the region scale plant community established species and the degraded grass species and the total coverage of the plant community are further analyzed and counted.
Preferably, in the fifth step, the plant community structure information is extracted from the hyperspectral data set of the unmanned aerial vehicle.
The invention provides a grassland degradation evaluation method based on unmanned aerial vehicle hyperspectral remote sensing, which takes species composition and community structure of grassland plants as starting points, acquires key index information such as group establishment and degradation indication grass type and coverage of alpine grassland based on unmanned aerial vehicle hyperspectral remote sensing images, and further quantitatively evaluates degradation degree and spatial distribution rule of the alpine grassland in Qinghai-Tibet plateau by combining an evaluation index system. The evaluation indexes adopted by the invention are species composition of the grassland community, and are not the traditional indexes such as vegetation index, vegetation coverage, productivity and the like. The deterioration of grass is often accompanied by a change in the composition of the species of the grass vegetation. Plant type information of the grassland community can be extracted based on the hyperspectral image of the unmanned aerial vehicle. The grassland degradation monitoring method based on the hyperspectral remote sensing images can accurately reflect the species composition change characteristics of degraded grasslands, and can avoid the problem that the community structure characteristic change of the grasslands cannot be accurately reflected by the traditional grassland degradation remote sensing monitoring method. Compared with the traditional field investigation, the method can greatly improve the working efficiency and realize the large-scale grassland degradation monitoring.
Drawings
Fig. 1 is a flowchart of a grassland degradation evaluation method based on unmanned aerial vehicle hyperspectral remote sensing in embodiment 1.
Detailed Description
For a further understanding of the present invention, reference is made to the following detailed description taken in conjunction with the accompanying drawings and examples. It is to be understood that the examples are illustrative of the invention and not limiting.
Example 1
As shown in fig. 1, the embodiment provides a grassland degradation evaluation method based on unmanned aerial vehicle hyperspectral remote sensing, and the method is suitable for degradation monitoring of alpine grasslands, and specifically comprises the following steps:
1. in the plant growth peak period (7-8 months), typical alpine grassland field sampling areas of different degradation stages (non-degradation, light degradation, moderate degradation, heavy degradation and extremely heavy degradation) of the grassland are respectively selected, and under the clear weather condition, unmanned aerial vehicle hyperspectral images of typical grassland degradation sample areas, spectral curves of typical alpine plants and community structure information of ground samples are respectively obtained by means of unmanned aerial vehicles (carrying hyperspectral cameras), surface feature spectrometers and other equipment.
2. Based on the plant community information of different degradation stages of a typical alpine grassland researched in the field, the difference of the composition characteristics of the grassland plant communities with different degradation degrees (plant types, the coverage of each plant, the total community coverage and the like) is analyzed, and the threshold values of evaluation indexes (established species, associated species and the area proportion of each species) between different degradation levels are defined, so that the grassland degradation evaluation standard based on community species composition (type of established species/associated species/degradation indicator species, area proportion and the like) is constructed.
3. And establishing a plant spectrum library of the alpine grassland based on the spectrum curve of the typical plant. The method comprises the steps of extracting hyperspectral characteristic variables (redside characteristics, NDVI, SR and the like) by utilizing spectral characteristic transformation and operation (first-order derivatives, second-order derivatives, spectral indexes and the like), and screening out wave bands with large plant differences or characteristic variables (such as near infrared, redside and the like) as spectral characteristic variables and sensitive wave bands which are beneficial to grass seed identification based on a Mahalanobis Distance method (Mahalanobis Distance).
4. And calculating and constructing a hyperspectral data set corresponding to the hyperspectral image of the unmanned aerial vehicle according to the screened sensitive waveband. Based on the data set, plant type information collected on the ground is used as a training sample, the type and abundance of the alpine plants are extracted by using a combined sparse unmixing model (a mixed pixel decomposition method), and community structure key information such as community building degree, community coverage of degraded grass and community total coverage of the plant community of regional scale is further analyzed and counted.
5. According to the plant community structure information extracted from the hyperspectral data set of the unmanned aerial vehicle, the degradation degree of the alpine grassland is further evaluated by combining the established grassland degradation evaluation standard, so that the aims of quantitatively evaluating and monitoring the grassland degradation are fulfilled.
The embodiment provides a method for monitoring grassland degradation by utilizing hyperspectral images of an unmanned aerial vehicle. Compared with the traditional method, the biggest difference is that the principle and the means of the grassland degradation monitoring are different. The method utilizes the hyperspectral image (with high spatial resolution and high spectral resolution) of the unmanned aerial vehicle in the growth period of the grassland, extracts community structure information such as grassland plant types and plant coverage of the grassland plants based on the spectral feature difference of different plants (population establishment, degradation indication grass seeds and the like), and further utilizes the grassland community structure information difference to divide the grassland degradation grade.
The present invention and its embodiments have been described above schematically, without limitation, and what is shown in the drawings is only one of the embodiments of the present invention, and the actual structure is not limited thereto. Therefore, if the person skilled in the art receives the teaching, without departing from the spirit of the invention, the person skilled in the art shall not inventively design the similar structural modes and embodiments to the technical solution, but shall fall within the scope of the invention.
Claims (9)
1. A grassland degradation evaluation method based on unmanned aerial vehicle hyperspectral remote sensing is characterized by comprising the following steps: the method comprises the following steps:
firstly, acquiring a hyperspectral image of an unmanned aerial vehicle in a typical sample area, a spectral curve of a typical plant and community structure information of a sample;
establishing plant types and coverage threshold values at different degradation stages based on plant community structure information of a typical sample, and establishing a grassland degradation evaluation standard based on community species composition;
establishing a typical alpine grassland plant spectrum library based on a spectrum curve of a typical plant, and screening out a spectrum characteristic variable and a sensitive wave band which are beneficial to grass seed identification by using a Mahalanobis distance method;
identifying the species composition of the grassland plants by using a combined sparse unmixing model based on the unmanned aerial vehicle image, and further analyzing and counting to obtain the total community coverage, the types of the established population and the degraded grass and the sub-coverage;
and fifthly, evaluating the degradation degree of the alpine grassland by combining the grassland degradation evaluation standard according to the structural information of the plant community, thereby achieving the purpose of quantitatively evaluating and monitoring the grassland degradation.
2. The grassland degradation evaluation method based on unmanned aerial vehicle hyperspectral remote sensing according to claim 1 is characterized in that: in the first step, in the plant growth peak period, typical alpine grassland field sampling areas of different degradation stages of the grassland are respectively selected, and under the clear weather condition, unmanned aerial vehicle hyperspectral images of typical grassland degradation sample areas are respectively obtained, spectral curves of typical alpine plants are tested, and community structure information of ground samples is recorded.
3. The grassland degradation evaluation method based on unmanned aerial vehicle hyperspectral remote sensing according to claim 2 is characterized in that: different degradation stages of the grassland comprise non-degradation, light degradation, moderate degradation, severe degradation and extremely severe degradation stages; and respectively acquiring the hyperspectral image of the unmanned aerial vehicle in the grassland degradation typical sample area, testing the spectral curve of a typical alpine plant and recording community structure information of the ground sample by means of the unmanned aerial vehicle carrying the hyperspectral camera and a ground object spectrometer.
4. The grassland degradation evaluation method based on unmanned aerial vehicle hyperspectral remote sensing according to claim 1 is characterized in that: and in the second step, based on the plant community information of different degradation stages of the typical alpine grassland researched in the field, analyzing the difference of the composition characteristics of the grassland plant communities with different degradation degrees, and defining the threshold value of the evaluation index between different degradation grades, thereby constructing the grassland degradation evaluation standard based on community species composition.
5. The grassland degradation evaluation method based on unmanned aerial vehicle hyperspectral remote sensing according to claim 4 is characterized in that: the community species composition comprises types and area ratios of community species, companion species and degeneration indicator species.
6. The grassland degradation evaluation method based on unmanned aerial vehicle hyperspectral remote sensing according to claim 1 is characterized in that: in the third step, a plant spectrum library of the alpine grassland is established; and (3) extracting hyperspectral characteristic variables by utilizing spectral characteristic transformation and operation, and screening out wave bands or characteristic variables with large plant differences as spectral characteristic variables and sensitive wave bands which are beneficial to grass seed identification based on the Mahalanobis distance method.
7. The grassland degradation evaluation method based on unmanned aerial vehicle hyperspectral remote sensing according to claim 6 is characterized in that: the spectral feature transformation and operation comprises a first derivative, a second derivative and a spectral index; the hyperspectral characteristic variables include red-edge characteristics, normalized vegetation index NDVI and simple ratio vegetation index SR.
8. The grassland degradation evaluation method based on unmanned aerial vehicle hyperspectral remote sensing according to claim 1 is characterized in that: calculating and constructing a hyperspectral data set corresponding to the hyperspectral image of the unmanned aerial vehicle according to the screened sensitive wave band; based on the data set, plant type information collected on the ground is used as a training sample, the type and abundance of the alpine plants are extracted by using a combined sparse unmixing model, and the coverage of the region scale plant community established species and the degraded grass species and the total coverage of the plant community are further analyzed and counted.
9. The grassland degradation evaluation method based on unmanned aerial vehicle hyperspectral remote sensing according to claim 8 is characterized in that: and fifthly, extracting the plant community structure information from the high-spectrum data set of the unmanned aerial vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210126115.XA CN114639012A (en) | 2022-02-10 | 2022-02-10 | Grassland degradation evaluation method based on unmanned aerial vehicle hyperspectral remote sensing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210126115.XA CN114639012A (en) | 2022-02-10 | 2022-02-10 | Grassland degradation evaluation method based on unmanned aerial vehicle hyperspectral remote sensing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114639012A true CN114639012A (en) | 2022-06-17 |
Family
ID=81946546
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210126115.XA Pending CN114639012A (en) | 2022-02-10 | 2022-02-10 | Grassland degradation evaluation method based on unmanned aerial vehicle hyperspectral remote sensing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114639012A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115294460A (en) * | 2022-10-08 | 2022-11-04 | 杭州领见数字农业科技有限公司 | Method for determining degradation degree of phyllostachys praecox forest, medium and electronic device |
| CN116090674A (en) * | 2023-04-07 | 2023-05-09 | 中国科学院空天信息创新研究院 | Early warning method, device and system for grassland degradation |
| CN116233208A (en) * | 2023-05-05 | 2023-06-06 | 四川省核工业地质调查院 | Mine ecological monitoring system and method based on artificial intelligence layout |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102288954A (en) * | 2011-08-01 | 2011-12-21 | 高吉喜 | Remote sensing estimation method for vegetation coverage of grassland |
| CN102323974A (en) * | 2011-06-08 | 2012-01-18 | 北京师范大学 | Method for evaluating degradation degree of alpine grassland based on visual vegetation indexes |
| CN103674247A (en) * | 2013-11-21 | 2014-03-26 | 中国科学院上海技术物理研究所 | Controllable-abundance grassland mixed spectrum acquisition experimental method |
| CN112766227A (en) * | 2021-02-04 | 2021-05-07 | 中国地质调查局武汉地质调查中心 | Hyperspectral remote sensing image classification method, device, equipment and storage medium |
| CN113252583A (en) * | 2021-06-25 | 2021-08-13 | 成都信息工程大学 | Method for calculating alpine hay coverage based on hay vegetation index |
-
2022
- 2022-02-10 CN CN202210126115.XA patent/CN114639012A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102323974A (en) * | 2011-06-08 | 2012-01-18 | 北京师范大学 | Method for evaluating degradation degree of alpine grassland based on visual vegetation indexes |
| CN102288954A (en) * | 2011-08-01 | 2011-12-21 | 高吉喜 | Remote sensing estimation method for vegetation coverage of grassland |
| CN103674247A (en) * | 2013-11-21 | 2014-03-26 | 中国科学院上海技术物理研究所 | Controllable-abundance grassland mixed spectrum acquisition experimental method |
| CN112766227A (en) * | 2021-02-04 | 2021-05-07 | 中国地质调查局武汉地质调查中心 | Hyperspectral remote sensing image classification method, device, equipment and storage medium |
| CN113252583A (en) * | 2021-06-25 | 2021-08-13 | 成都信息工程大学 | Method for calculating alpine hay coverage based on hay vegetation index |
Non-Patent Citations (3)
| Title |
|---|
| 安如等: ""三江源典型区草地退化Hyperion高光谱遥感识别研究"", 《武汉大学学报》 * |
| 张丽云: ""基于高光谱遥感数据的森林树种分类"", 《中国优秀硕士学位论文全文数据库农业科技辑》 * |
| 潘多锋: ""三江源区"黑土型"退化草地的类型及等级划分标准研究"", 《中国优秀硕士学位论文全文数据库农业科技辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115294460A (en) * | 2022-10-08 | 2022-11-04 | 杭州领见数字农业科技有限公司 | Method for determining degradation degree of phyllostachys praecox forest, medium and electronic device |
| CN115294460B (en) * | 2022-10-08 | 2023-01-17 | 杭州领见数字农业科技有限公司 | Method for determining degradation degree of phyllostachys praecox forest, medium and electronic device |
| CN116090674A (en) * | 2023-04-07 | 2023-05-09 | 中国科学院空天信息创新研究院 | Early warning method, device and system for grassland degradation |
| CN116233208A (en) * | 2023-05-05 | 2023-06-06 | 四川省核工业地质调查院 | Mine ecological monitoring system and method based on artificial intelligence layout |
| CN116233208B (en) * | 2023-05-05 | 2023-07-25 | 四川省核地质调查研究所 | Mine ecological monitoring system and method based on artificial intelligence layout |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114639012A (en) | Grassland degradation evaluation method based on unmanned aerial vehicle hyperspectral remote sensing | |
| CN109345555B (en) | Method for identifying rice based on multi-temporal multi-source remote sensing data | |
| Hall et al. | Optical remote sensing applications in viticulture‐a review | |
| Yang et al. | Impact of band-ratio enhanced AWIFS image to crop classification accuracy | |
| Onojeghuo et al. | Applications of satellite ‘hyper-sensing’in Chinese agriculture: Challenges and opportunities | |
| Goodwin et al. | Assessing plantation canopy condition from airborne imagery using spectral mixture analysis and fractional abundances | |
| CN101692037B (en) | Method for analyzing chlorophyll distribution on surface of leaves of plant by hyperspectral image and independent component | |
| CN101299237B (en) | High spectroscopic data supervision classifying method based on information quantity dimensionality sequence | |
| Nidamanuri et al. | Use of field reflectance data for crop mapping using airborne hyperspectral image | |
| Sun et al. | Monitoring maize canopy chlorophyll density under lodging stress based on UAV hyperspectral imagery | |
| Lavanya et al. | Terrain mapping of LandSat8 images using MNF and classifying soil properties using ensemble modelling | |
| Ahmad | A review of remote sensing data change detection: Comparison of Faisalabad and Multan Districts, Punjab Province, Pakistan | |
| CN111126511B (en) | Vegetation index fusion-based LAI quantitative model establishment method | |
| CN113505635A (en) | Method and device for identifying winter wheat and garlic mixed planting area based on optics and radar | |
| US6763136B1 (en) | Method and apparatus for determining spectral similarity | |
| WO2023197496A1 (en) | Comprehensive evaluation indicator monitoring and evaluation method and system for machine-harvested cotton defoliation effects | |
| CN110849821B (en) | Black and odorous water body remote sensing identification method based on Bayesian theorem | |
| Singh et al. | Multitemporal spectral analysis for cheatgrass (Bromus tectorum) classification | |
| CN114398595B (en) | Fire point remote sensing identification method based on BP neural network | |
| Warner et al. | Remote sensing of land cover change | |
| CN115718075A (en) | Model and method for evaluating different degradation degrees of grassland | |
| GB2620469A (en) | Spatial prediction and evaluation method of soil organic matter content based on partition algorithm | |
| Woodcock et al. | Vegetation mapping and monitoring | |
| CN115424006A (en) | Multi-source multi-level data fusion method applied to crop phenotypic parameter inversion | |
| Qu et al. | A fast and efficient approach to estimate wild blueberry yield using machine learning with drone photography: Flight altitude, sampling method and model effects |
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 |