CN114782816A - Remote sensing extraction method for crop multiple cropping index - Google Patents

Remote sensing extraction method for crop multiple cropping index Download PDF

Info

Publication number
CN114782816A
CN114782816A CN202210462211.1A CN202210462211A CN114782816A CN 114782816 A CN114782816 A CN 114782816A CN 202210462211 A CN202210462211 A CN 202210462211A CN 114782816 A CN114782816 A CN 114782816A
Authority
CN
China
Prior art keywords
crop
ndvi
remote sensing
time
multiple cropping
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
Application number
CN202210462211.1A
Other languages
Chinese (zh)
Other versions
CN114782816B (en
Inventor
刘冰宣
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tianjin University
Original Assignee
Tianjin University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tianjin University filed Critical Tianjin University
Priority to CN202210462211.1A priority Critical patent/CN114782816B/en
Publication of CN114782816A publication Critical patent/CN114782816A/en
Application granted granted Critical
Publication of CN114782816B publication Critical patent/CN114782816B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/587—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Library & Information Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Cultivation Of Plants (AREA)

Abstract

The invention relates to a remote sensing extraction method of crop multiple cropping indexes, which comprises the following steps: acquiring high-time-resolution remote sensing data, acquiring a crop planting area, and constructing an NDVI-t two-dimensional rectangular coordinate system to obtain a time-series NDVI crop phenological curve; and judging the crop planting stubble number based on the crop phenological curve of the NDVI of the time sequence and the high-time resolution remote sensing data, and acquiring the multiple cropping index of the planting area based on the crop planting stubble number. Compared with the traditional method, the method has the advantages of scientificity and higher precision, combines different crop phenological information, utilizes the medium-high resolution remote sensing data to obtain the NDVI value of the time node of the key phenological period, establishes the crop multiple cropping index, and achieves the purpose of accurately identifying the spatial-temporal distribution of the multiple cropping index.

Description

Remote sensing extraction method for crop multiple cropping index
Technical Field
The invention relates to the technical field of agriculture and remote sensing, in particular to a remote sensing extraction method for crop multiple cropping indexes.
Background
The multiple cropping index is the average number of times of planting crops on the same cultivated land area in a certain period (generally 1 year), namely the average number of times of planting crops on the cultivated land area in the year, and the numerical value is equal to the ratio of the total seeding area of the crops on the cultivated land in the year to the cultivated land area. The multiple cropping index is equal to the ratio of the total seeding area of the crops to the cultivated area in the whole year on the cultivated land. Is an index reflecting the utilization degree of cultivated land and is expressed by percentage. The calculation formula is as follows: the multiple cropping index is the total area of the crop sowed (or transplanted) all year round divided by the total area of the cultivated land multiplied by 100%. It reflects the degree of multiple cropping and is used for comparing the utilization conditions of cultivated land among different years, different regions and different production units. Obtaining the multiple cropping index and the distribution information of the farmland is very important for the aspects of crop growth vigor, yield estimation, farmland management and the like. Therefore, the accurate space-time distribution of the multiple cropping index of the farmland is very important for crop yield estimation, scientific management and scientific allocation of water resources.
At present, methods for obtaining farmland multi-cropping index information of space-time distribution comprise a manual statistical method and a remote sensing method, wherein the remote sensing method comprises a land utilization analysis method, a time sequence analysis method and the like. The manual statistical method is an earlier used method, and mainly obtains the multiple cropping information of the farmland through manual field statistics, summarization and reporting. The method has the problems of being not objective enough and being difficult to obtain the multi-species index distribution information of space-time dynamic state. The remote sensing method is the most common method applied at home and abroad, and has the advantages of objectivity, rapidness, low cost and the like. The land utilization method in the remote sensing method is to estimate farmland information obtained by a remote sensing technology method and combine experience, and the method can effectively obtain farmland distribution and experience information, but can be identified by combining local planting habits and combining reported data. The time sequence extraction method mainly develops an information extraction method according to the time sequence change characteristics of the crops and statistically analyzes the multiple cropping indexes of the crops. However, due to the limitation of spatial resolution, the method is difficult to be popularized and applied to the broken or small region of the land.
With the development of remote sensing technology, the spatial resolution of remote sensing data tends to be improved, and the number of satellite emissions with medium and high resolution is greatly increased, so that it is possible to obtain multiple kinds of space-time distribution information of farmlands by applying medium and high resolution.
Aiming at the problems, the invention provides a remote sensing extraction method and a remote sensing extraction system for crop multiple cropping indexes, which comprehensively consider the phenological information of crops and NDVI characteristics of time sequences in consideration of the limitation of the current extraction method.
Disclosure of Invention
The invention provides a remote sensing extraction method of a crop multiple cropping index, which combines different crop phenological information, utilizes medium-high resolution remote sensing data to obtain an NDVI value of a time node of a key phenological period, establishes the crop multiple cropping index and achieves the purpose of accurately identifying the spatial-temporal distribution of the multiple cropping index.
In order to achieve the purpose, the invention provides the following scheme:
a remote sensing extraction method for crop multiple cropping indexes comprises the following steps:
acquiring high-time-resolution remote sensing data, acquiring a crop planting area, and constructing an NDVI-t two-dimensional rectangular coordinate system to obtain a time-series NDVI crop phenological curve;
and judging the crop planting stubble number based on the crop phenological curve of the NDVI of the time sequence and the high-time-resolution remote sensing data, and acquiring the multiple cropping index of the planting area based on the crop planting stubble number.
Preferably, a crop identification index is calculated based on the high-time-resolution remote sensing data, and if the crop identification index is not less than a preset threshold a4Determining farmland coverage information, determining the area to be monitored according to the farmland coverage information, selecting remote sensing data of crop planting, growing and harvesting according to the range and time period of the area to be monitored, and determining the crop planting area; wherein the preset threshold a4And comprehensively determining according to the type of the remote sensing image and the characteristics of the underlying surface of the farmland coverage area.
Preferably, the crop identification index is calculated by the formula:
Figure BDA0003620764100000031
wherein CRI is the crop identification index, NDVIiNDVI value of ith scene data covering the same area; i is the ith scene data of the remote sensing image participating in calculation; n is1The number of scenes of the remote sensing image is;
Figure BDA0003620764100000032
is the average value of NDVI in a time series,
Figure BDA0003620764100000033
NDVI is the normalized vegetation index, RnirIs the reflectivity of the near infrared band, RrThe reflectance of the red band.
Preferably, the process of obtaining the crop planting area comprises:
ZWI＝A1∪A2∪...∪An
in the formula, ZWI is the maximum area of a planting area; a1 and a2 … An are sets with pixels as units, which are obtained based on remote sensing image statistics.
Preferably, the process of obtaining a time-series NDVI crop phenology curve comprises:
and establishing the NDVI-t two-dimensional rectangular coordinate system based on the crop planting area, and acquiring the relation between NDVI of different crop growth periods and time in the same time sequence through the NDVI-t two-dimensional rectangular coordinate system so as to obtain a crop phenological curve of the NDVI of the time sequence.
Preferably, the maximum value NDV I of the crop phenology curve of the NDVI of different crop types is determined based on the crop phenology curve of the NDVI of the time series and the high-time resolution remote sensing datamaxAnd median value
Figure BDA0003620764100000041
Preferably, the process of judging the number of crop planting stubbles comprises the following steps:
and acquiring crop planting starting point information and crop maturity starting point information based on the phenological curve, and determining the number of planted stubbles of crops with the same pixel.
Preferably, the NDVI of the point where the phenological curve reaches the median is set based on the number of planted stubbles of the same pixel cropp10、NDVIp11、NDVIp20、NDVIp21、NDVIp30、NDVIp31If overwintering crops are involved, the value NDV I is takenp4。
Preferably, the formula for calculating the multiple cropping index is as follows:
Figure BDA0003620764100000042
in the formula, KijThe planting condition of the j-th crop in the ith year is shown, n is the counted number of years, m is the number of stubbles planted by the crop, and FI is a multiple cropping index.
The invention has the beneficial effects that:
compared with the traditional method, the method has the advantages of scientificity and higher precision, combines different crop phenological information, utilizes the medium-high resolution remote sensing data to obtain the NDVI value of the time node of the key phenological period, establishes the crop multiple cropping index, and achieves the purpose of accurately identifying the spatial-temporal distribution of the multiple cropping index.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a remote sensing extraction method of crop multiple cropping index according to an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Referring to the attached figure 1, a remote sensing extraction method for crop multiple cropping indexes comprises the following steps:
acquiring high-time-resolution remote sensing data to obtain farmland coverage information, and determining a region to be monitored according to the farmland coverage information;
determining a crop planting area based on the area to be monitored, and constructing an NDVI-t two-dimensional rectangular coordinate system to obtain a time-series NDVI crop phenological curve;
and obtaining crop planting stubble number based on the crop phenological curve of the NDVI of the time sequence and the high-time-resolution remote sensing data, and obtaining the multiple cropping index of the area to be monitored based on the crop planting stubble number.
Calculating a crop identification index based on the high temporal resolution remote sensing data:
Figure BDA0003620764100000061
wherein CRI is the crop identification index, NDVIiNDVI value of ith scene data covering the same area; i is ith scene data of the remote sensing image participating in calculation; n is1The number of scenes of the remote sensing image is;
Figure BDA0003620764100000062
is the average value of the NDVI over a time series,
Figure BDA0003620764100000063
NDVI is the normalized vegetation index, RnirIs the reflectivity of the near infrared band, RrThe reflectance of the red band.
If the crop identification index CRI is not less than a preset threshold value a4Determining the farmland coverage information, and determining the area to be monitored according to the farmland coverage information, wherein the preset threshold value a4And comprehensively determining according to the type of the remote sensing image and the characteristics of the underlying surface of the farmland coverage area.
Selecting suitable time-series remote sensing data according to the range and the time period of the area to be monitored, and determining a crop planting area:
ZWI＝A1∪A2∪...∪An
in the formula, ZWI is the maximum area of the planting area; a1 and a2 … An are pixel-based sets obtained by remote sensing image statistics.
And further optimizing the scheme, establishing the NDVI-t two-dimensional rectangular coordinate system based on the crop planting area, wherein the NDVI is taken as a longitudinal axis, and the time t is taken as a transverse axis.
And obtaining the relation between NDVI and time in different crop growth periods in the same time sequence through the NDVI-t two-dimensional rectangular coordinate system, and further obtaining a crop phenological curve of the NDVI in the time sequence. Time series NDVI crop climatic Curve to determine key nodes for crop growth, the time points are determined from this curve
Further optimizing the scheme, determining the maximum value NDV I of the crop phenological curve of the NDVI of different crop types based on the crop phenological curve of the NDVI of the time sequence and the high-time resolution remote sensing datamaxAnd median value
Figure BDA0003620764100000071
And determining the planting stubbles of the same pixel crop based on the crop planting starting point information and the crop maturity starting point information. Setting the point NDVI at which the phenological curve reaches the median value based on the number of stubbles planted on the cropsp10、NDV Ip11、NDV Ip20、NDV Ip21、NDV Ip30、NDV Ip31If overwintering crops are included, the value NDV I is takenp4. The phenological curve presents a sine curve, and the middle points on the two sides are taken.
(1) For an area with at most one crop in one year, the following steps are adopted:
if both are satisfied:
Figure BDA0003620764100000072
and:
Figure BDA0003620764100000073
tp11and tp10NDVI betweenThe large value satisfies the condition: | NDVImax1-NDVImax|≤a1And determining the crop as a crop. Therefore, the corresponding pixel value is set to 1.
In the formula, t10And t11Are each tp10Time points of remote sensing images obtained before and after the point (the middle point of the first crop planting period); t is t20And t21Are each tp11Time points of remote sensing images obtained before and after the point (the midpoint of the mature period of the first crop); NDVImax1NDVI peak for this time period.
(2) For an area where two crops are likely to be planted in a year, the following are adopted:
on the basis of (1), if the following conditions are satisfied:
Figure BDA0003620764100000081
and:
Figure BDA0003620764100000082
tp21and tp20The maximum value of NDVI between satisfies the condition: i NDV Imax2-NDV Imax|≤a2And determining the crop as the second crop. Therefore, the corresponding pixel value is set to 2.
In the formula, t30And t31Are each tp20Time points of remote sensing images obtained before and after the point (the midpoint of the second crop planting period); t is t40And t41Are each tp21Time points of remote sensing images obtained before and after the point (the midpoint of the mature period of the second crop); NDVImax2The NDVI peak for this time period.
(3) For an area where three crops are likely to be planted in a year, the following are adopted:
on the basis of (2), if the following conditions are met:
Figure BDA0003620764100000083
Figure BDA0003620764100000091
and:
Figure BDA0003620764100000092
tp31and tp30The maximum value of NDVI in between satisfies the condition: i NDV Imax3-NDV Imax|≤a3And then the crop is determined as the third crop 3. Therefore, the corresponding pixel value is set to 3.
In the formula, t50And t51Are each tp30Time points of remote sensing images obtained before and after the point (the midpoint of the third crop planting period); t is t60And t61Are each tp31Time points of remote sensing images obtained before and after the point (the midpoint of the mature period of the third crop); NDVImax3The NDVI peak for this time period.
(4) If there are overwintering crops:
if the plants are planted in autumn and harvested in spring and summer of the next year, the plants are determined to be overwintering crops. Therefore, the time point of the germination period or the growth period starting in the next year of the planting is determined by combining the physical and weather data.
Figure BDA0003620764100000093
Identified as overwintering crops.
For the calculation of the generally multiple seed index:
Figure BDA0003620764100000094
in the formula, KijThe planting condition of the j-th crop in the ith year is shown, n is the counted number of years, m is the number of stubbles planted by the crop, and FI is a multiple cropping index. If the j th crop of the ith year is planted, KjThe value is 1, otherwise it is zero
Compared with the traditional method, the method has the advantages of scientificity and higher precision, different crop phenology information is combined, the NDVI value of the time node of the key phenology period is obtained by using the remote sensing data with medium and high resolution, the crop multiple cropping index is established, and the purpose of accurately identifying the time-space distribution of the multiple cropping index is achieved.
The above-described embodiments are only intended to describe the preferred embodiments of the present invention, and not to limit the scope of the present invention, and various modifications and improvements made to the technical solution of the present invention by those skilled in the art without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

Claims (9)

1. A remote sensing extraction method for crop multiple cropping indexes is characterized by comprising the following steps:
collecting high-time-resolution remote sensing data, acquiring a crop planting area, constructing an NDVI-t two-dimensional rectangular coordinate system, and obtaining a time-series NDVI crop phenology curve;
and judging the crop planting stubble number based on the crop phenological curve of the NDVI of the time sequence and the high-time-resolution remote sensing data, and acquiring the multiple cropping index of the planting area based on the crop planting stubble number.
2. The remote sensing extraction method for crop multi-cropping index according to claim 1, characterized in that a crop identification index is calculated based on the high time resolution remote sensing data, and if the crop identification index is not less than a preset threshold a4Determining farmland coverage information, determining the area to be monitored according to the farmland coverage information, selecting remote sensing data of crop planting, growth and harvesting according to the range and time period of the area to be monitored, and determining the crop planting area; wherein the preset threshold a4And comprehensively determining according to the type of the remote sensing image and the characteristics of the underlying surface of the farmland coverage area.
3. The remote sensing extraction method for the crop multi-cropping index according to claim 2, characterized in that the calculation formula of the crop identification index is as follows:
Figure FDA0003620764090000011
wherein CRI is crop identification index, NDVIiNDVI value of ith scene data covering the same area; i is ith scene data of the remote sensing image participating in calculation; n is1The number of scenes of the remote sensing image is;
Figure FDA0003620764090000012
is the average value of the NDVI over a time series,
Figure FDA0003620764090000013
NDVI is the normalized vegetation index, RnirIs the reflectivity of the near infrared band, RrThe reflectance of the red band.
4. The remote sensing extraction method for the crop multiple cropping index according to claim 2, wherein the process of obtaining the crop planting area comprises:
ZWI＝A1∪A2∪...∪An
in the formula, ZWI is the maximum area of the planting area; a1 and a2 … An are pixel-based sets obtained by remote sensing image statistics.
5. The remote sensing extraction method for crop multiple cropping index according to claim 1, characterized in that the process of obtaining the time-series NDVI crop climatic curve comprises:
and establishing the NDVI-t two-dimensional rectangular coordinate system based on the crop planting area, and acquiring the relation between NDVI of different crop growth periods and time in the same time sequence through the NDVI-t two-dimensional rectangular coordinate system so as to obtain a crop phenological curve of the NDVI of the time sequence.
6. The remote sensing extraction method for crop multiple cropping index according to claim 5, characterized in that the crop phenological curve of NDVI of different crop types is determined based on the crop phenological curve of NDVI of the time series and the high-time resolution remote sensing dataMaximum value of line NDVImaxAnd median value
Figure FDA0003620764090000021
7. The remote sensing extraction method for crop multiple cropping index according to claim 1, characterized in that the process of judging the number of crop planting stubbles comprises:
and acquiring crop planting starting point information and crop maturity starting point information based on the phenological curve, and determining the number of planted stubbles of crops with the same pixel.
8. The remote sensing extraction method for crop multi-cropping index according to claim 7, characterized in that the point NDVI at which the phenological curve reaches the median is set based on the number of planted stubbles of the same pixel cropp10、NDVIp11、NDVIp20、NDVIp21、NDVIp30、NDVIp31If overwintering crops are included, the value NDV I is takenp4。
9. The remote sensing extraction method for the crop multiple cropping index according to claim 1, wherein the calculation formula of the multiple cropping index is as follows:
Figure FDA0003620764090000031
in the formula, KijThe planting condition of the j-th crop in the ith year is shown, n is the counted number of years, m is the number of stubbles planted by the crop, and FI is a multiple cropping index.
CN202210462211.1A 2022-04-28 2022-04-28 Remote sensing extraction method for crop multiple cropping index Active CN114782816B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210462211.1A CN114782816B (en) 2022-04-28 2022-04-28 Remote sensing extraction method for crop multiple cropping index

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210462211.1A CN114782816B (en) 2022-04-28 2022-04-28 Remote sensing extraction method for crop multiple cropping index

Publications (2)

Publication Number Publication Date
CN114782816A true CN114782816A (en) 2022-07-22
CN114782816B CN114782816B (en) 2023-03-24

Family

ID=82435117

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210462211.1A Active CN114782816B (en) 2022-04-28 2022-04-28 Remote sensing extraction method for crop multiple cropping index

Country Status (1)

Country Link
CN (1) CN114782816B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116579521A (en) * 2023-05-12 2023-08-11 中山大学 Yield prediction time window determining method, device, equipment and readable storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109614891A (en) * 2018-11-27 2019-04-12 北京师范大学 Crops recognition methods based on phenology and remote sensing
CN110909679A (en) * 2019-11-22 2020-03-24 中国气象科学研究院 Remote sensing identification method and system for fallow crop rotation information of winter wheat historical planting area
CN111448956A (en) * 2020-04-24 2020-07-28 广西壮族自治区农业科学院 Method for cultivating Luffa acutangula and Luffa acutangula high-quality rice wheel in open field in coastal region of south China for three crops in one year
CN112001809A (en) * 2020-07-31 2020-11-27 中科海慧（天津）科技有限公司 Method for acquiring farmland returning information of agriculture and forestry area
CN112418050A (en) * 2020-11-18 2021-02-26 中国科学院空天信息创新研究院 Remote sensing identification method and device for land withdrawal information
CN113421273A (en) * 2021-06-30 2021-09-21 中国气象科学研究院 Remote sensing extraction method and device for forest and grass collocation information

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109614891A (en) * 2018-11-27 2019-04-12 北京师范大学 Crops recognition methods based on phenology and remote sensing
CN110909679A (en) * 2019-11-22 2020-03-24 中国气象科学研究院 Remote sensing identification method and system for fallow crop rotation information of winter wheat historical planting area
CN111448956A (en) * 2020-04-24 2020-07-28 广西壮族自治区农业科学院 Method for cultivating Luffa acutangula and Luffa acutangula high-quality rice wheel in open field in coastal region of south China for three crops in one year
CN112001809A (en) * 2020-07-31 2020-11-27 中科海慧（天津）科技有限公司 Method for acquiring farmland returning information of agriculture and forestry area
CN112418050A (en) * 2020-11-18 2021-02-26 中国科学院空天信息创新研究院 Remote sensing identification method and device for land withdrawal information
CN113421273A (en) * 2021-06-30 2021-09-21 中国气象科学研究院 Remote sensing extraction method and device for forest and grass collocation information

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
欧立业 等: "基于NDVI时间序列数据的江西省水稻种植制度变化研究", 《测绘与空间地理信息》 *
王文静 等: "综合多特征的Landsat 8时序遥感图像棉花分类方法", 《遥感学报》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116579521A (en) * 2023-05-12 2023-08-11 中山大学 Yield prediction time window determining method, device, equipment and readable storage medium
CN116579521B (en) * 2023-05-12 2024-01-19 中山大学 Yield prediction time window determining method, device, equipment and readable storage medium

Also Published As

Publication number Publication date
CN114782816B (en) 2023-03-24

Similar Documents

Publication Publication Date Title
CN110909679B (en) Remote sensing identification method and system for fallow crop rotation information of winter wheat historical planting area
WO2019046967A1 (en) Generating a yield map for an agricultural field using classification and regression methods
Barungi et al. Adoption of soil management technologies by smallholder farmers in central and southern Malawi
Elias Influence of agroforestry practices on the structure and spatiality of shea trees (Vitellaria paradoxa CF Gaertn.) in central-west Burkina Faso
CN114782816B (en) Remote sensing extraction method for crop multiple cropping index
CN108345992B (en) Multiple cropping index extraction method and device
Hamre et al. Plant species richness, composition and habitat specificity in a Norwegian agricultural landscape
Oyewole et al. Factors influencing sustainable agricultural practices among smallholder farmers in Ogun State of Nigeria
CN112001809A (en) Method for acquiring farmland returning information of agriculture and forestry area
Pembleton et al. Yield, yield components and shoot morphology of four contrasting lucerne (Medicago sativa) cultivars grown in three cool temperate environments
CN112418050B (en) Remote sensing identification method and device for land withdrawal information
Economou et al. Weed flora distribution in Greek cotton fields and its possible influence by herbicides
CN116843217A (en) Agricultural drought monitoring method based on European spatial distance method
CN114782835B (en) Crop lodging area proportion detection method and device
Ullah et al. The determinants of technical efficiency of peach growers: Evidence from Khyber Pakhtunkhwa, Pakistan
Owoeye et al. Effect of climate change on cocoa production in Ondo state, Nigeria
CN114092807B (en) Actual irrigation area identification method based on time interval accumulated evapotranspiration
Ong'Ala et al. Determinants of sugarcane smut prevalence in the Kenya Sugar Industry.
Müller et al. Impacts of climate change on agriculture and recommendations for adaptation measures in the Western Balkans
Fackler et al. Forecasting crop yields and condition indices
CN113376123B (en) Cultivated land waste information extraction method based on vegetation-pigment-soil time sequence coupling dispersion
Oughton Seasonality, wage labour and women’s contribution to household income in western India
CN115349340B (en) Sorghum fertilization control method and system based on artificial intelligence
Fijen Towards ecological intensification: the relative importance of wild pollinators as an agricultural input in seed production
Raufu et al. Technological Gap Analyses of Mena and Southern African Countries’ Agricultural Productivity

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