CN103472009B - The monitoring method of wheat plant water percentage under a kind of different plants nitrogen content level - Google Patents
The monitoring method of wheat plant water percentage under a kind of different plants nitrogen content level Download PDFInfo
- Publication number
- CN103472009B CN103472009B CN201310422607.4A CN201310422607A CN103472009B CN 103472009 B CN103472009 B CN 103472009B CN 201310422607 A CN201310422607 A CN 201310422607A CN 103472009 B CN103472009 B CN 103472009B
- Authority
- CN
- China
- Prior art keywords
- plant water
- different
- wheat
- pwc
- monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention belongs to crop growth monitoring field, disclose the monitoring method of wheat plant water percentage under a kind of different plants nitrogen content level, wheat canopy blade reflected spectrum data is combined with PWC data, according to different PNC size horizontal classification, determine the core bands general character region under different PNC level, build the optimum spectrum index based on core bands general character region, set up the monitoring model based on the general wheat plant water percentage of optimum spectrum index.The present invention has taken into full account the impact that basic, normal, high different nitrogen nutritional condition is monitored PWC, selected optimum spectrum index is applicable to the wheat PWC EO-1 hyperion monitoring under multiclass nitrogen nutrition, can fast, can't harm, estimate different water nitrogen condition accurately under wheat PWC.This invention provides important technology to support by the EO-1 hyperion monitoring of the wheat plant moisture under different nitrogen nutritional condition in accurate agricultural.
Description
Technical field
The invention belongs to crop growth monitoring field, relate to the monitoring method of wheat plant water percentage under a kind of different plants nitrogen content level, be specifically related to the optimum spectrum index in a kind of wheat plant water percentage core bands general character region based under hyperspectral technique determination different plants nitrogen content level, set up the method for the wheat PWC monitoring model based on optimum spectrum index, be specially adapted to the EO-1 hyperion study on monitoring of wheat plant water percentage under different nitrogen nutrition level.
Background technology
Real-Time Monitoring and the quick diagnosis of crop water status can be realized based on high spectrum resolution remote sensing technique, to raising crop irrigation management level and water use efficiency significant.
Plant water content (PWC) can react crop water information comprehensively.In recent years, Chinese scholars has done large quantity research to the sensitive band of crop PWC and characteristic spectrum parameter, proposes various informative moisture spectrum index, but the single moisture effects that these spectrum indexes often only considered.There are some researches prove, do to there is strong correlativity between biochemical component in object, wherein nitrogen (N) element is by chlorophyll, lignin and cellulose etc. and crop water indirect correlation, therefore, different plants nitrogen content (PNC) level must affect crop growth, thus remote effect crop PWC monitors.Owing to often relating to different nitrogen amount applied in actual Production of Large Fields, and existing moisture spectrum index rarely has the impact considering different nitrogen trophic level, and though partial spectrum index has degree of precision to overall PWC study on monitoring, but it is then lower to the monitoring accuracy of PWC under some PNC level, error is larger, therefore, in the urgent need to a kind of techniques and methods determining the PWC spectrum index be applicable under different PNC level conditions.
Summary of the invention
The object of the invention is for above-mentioned the deficiencies in the prior art, take into full account the impact that different nitrogen nutrition level is monitored wheat water content, by by all PWC and corresponding canopy spectra reflectivity according to different PNC size horizontal classification, find the PWC core bands general character region under different PNC level, determine to be applicable to the optimum spectrum index of PWC under different PNC level conditions, thus set up based on the wheat PWC monitoring model of optimum spectrum index, the method can fast, can't harm, estimate different water nitrogen condition accurately under wheat PWC.
The object of the invention is to be achieved through the following technical solutions:
A monitoring method for wheat plant water percentage under different plants nitrogen content level, comprises the following steps:
Step one, sampling, gather wheat canopy spectral reflectivity, PNC and PWC numerical value; Sample point picks up from different growing, different in moisture process, different nitrogen amount applied and different year;
Step 2, by different PNC level, whole PWC and canopy spectra reflectivity are divided into three sub-data sets;
Step 3, obtain the coefficient of determination (R of PWC and NDSI under the horizontal subdata collection of different PNC
2) result set;
Step 4, the PWC core bands general character region determined under different PNC level;
Step 5, the optimum spectrum index determining based on core bands general character region;
Step 6, set up wheat PWC monitoring model based on optimum spectrum index;
The accuracy of step 7, inspection wheat PWC monitoring model and universality.
In step, the wheat field experiment that different in moisture process and different nitrogen amount applied are done mutually is set, gather jointing to each crucial growthdevelopmental stage canopy spectra reflectivity that is in the milk, the inter-sync of Bing Mei community is chosen 10 single stems that can characterize the average growing way in community and is carried out destructiveness sampling, weigh fresh weight and dry weight, calculate PWC result, grind away adopts the corresponding PNC of Kjeldahl nitrogen determination after weighing.
Gather Canop hyperspectrum reflectivity resolution high, contain much information, spectral band scope is 350-2500nm, and wave band is spaced apart 1nm.
The account form of PWC is: Plant water content (PWC) (%)=(W
f-W
d)/W
f× 100, wherein W
ffor plant fresh weight (g) summation, W
dfor plant weights (g) summation.
In step 2, consider PNC magnitude range, and data volume distribution situation in each scope, PNC is divided into PNC<1.3%, PNC1.3-1.6%, PNC>1.6% tri-scopes, according to corresponding PNC value scope, whole PWC and corresponding canopy spectra reflectivity are divided into three sub-data sets of corresponding different PNC level.
Basic classification principle is: ensure on the scope basis that there is some difference of each horizontal PNC value, and the data volume controlling subdata collection belonging to each PNC level is without too big-difference.Total amount of data more contributes to more greatly finding core bands general character region.
In step 3, use Matlab9.0 program calculation, obtain the NDSI of any two band combinations in PWC and 350-2500nm wavelength band under different PNC horizontal subdata collection build the coefficient of determination (R of corresponding model
2) result set; And by the model R of band combinations all in each result set
2matrix data is depicted as contour map, with color depth change display R
2the change of size.
R
2result set is specially: in 350-2500nm wave band, take 1nm as the R of NDSI and the PWC institute established model of the correspondence of the wave band between two combination at interval
2collection, arranges in matrix.
In step 4, with the above-mentioned each coefficient of determination (R
2) R in result set
2maximal value be standard, definition R
2the contour map region of front 10% correspondence is core bands region; Found the same section in the core bands region of the horizontal subdata collection of each PNC by Matlab9.0, be core bands general character region.
In step 5, in step 4 fixed core bands general character region, calculate the modeling accuracy (R corresponding to all NDSI and PWC institutes established model of band combination between two
2) and verify error (RRMSE), choose R
2spectrum index corresponding to-RRMSE maximal value is optimum spectrum index, determines that optimum spectrum index is NDSI (1302,1190).
In step 6, the wheat PWC monitoring model based on optimum spectrum index NDSI (1302,1190) is: Y=-1289.4X+78.29, wherein, and model R
2be 0.876, SE be 2.702.
In step 7, utilize accuracy and the universality of independent time wheat test figure checking monitoring model, adopt coefficient of multiple correlation R
2, relatively root mean square deviation RRMSE comprehensive evaluation (inspection monitoring model R is carried out to monitoring model
2be 0.7979, RRMSE be 0.0662), and verify susceptibility (the PNC testing model R of monitoring model to PNC
2be 0.3242, RRMSE be 45.7011).
The advantage of the relative conventional art of the present invention:
The present invention is based on the NDSI optimal bands composite that PWC core bands general character region under different PNC categorization levels filters out, taken into full account the impact that basic, normal, high different nitrogen nutritional condition is monitored PWC, selected spectrum index is applicable to the wheat PWC EO-1 hyperion monitoring under different nitrogen nutrition.Transmission spectra index construction triage techniques then often just for the research of PWC, seldom considers the impact of different nitrogen nutrition condition, particularly rarely has the PWC monitoring eurytopicity under different nitrogen nutrition level conditions and mentions.The present invention can fast, harmless, estimate wheat PWC under different water nitrogen condition accurately, provide important technology to support by the EO-1 hyperion monitoring of the wheat plant moisture under different nitrogen nutritional condition in accurate agricultural.
Accompanying drawing explanation
Fig. 1 is 10% contour map (A:PNC<1.3% before the NDSI coefficient of determination of wheat PWC under different PNC level and any two band combinations; B:PNC1.3-1.6%; And general character areal map (D) C:PNC>1.6%).
Fig. 2 is wheat PWC model construction (A) based on the horizontal core bands general character region NDSI (1302,1190) of different PNC and model testing (B).
Fig. 3 is the NDSI coefficient of determination contour map of wheat PWC based on total data collection and any two band combinations.
Fig. 4 is wheat PWC model construction (A) based on total data collection NDSI (1727,1539) and model testing (B).
Fig. 5 is the monitoring method process flow diagram of wheat plant water percentage under different plants nitrogen content level of the present invention.
Embodiment
Two wheat tests that the present invention does mutually by implementing different year, different nitrogen amount applied and different in moisture process, by reference to the accompanying drawings, have investigated the application advantage based on the optimum spectrum index in the PWC core bands general character region under the different PNC levels of hyperspectral technique.
As shown in Figure 5, the monitoring method of wheat plant water percentage under different plants nitrogen content level, comprises the following steps:
S101: sampling, gathers wheat canopy spectral reflectivity, PNC and PWC numerical value; Sample point picks up from different growing, different in moisture process, different nitrogen amount applied and different year;
S102: PWC and canopy spectra reflectivity data are divided into three sub-data sets by different PNC level;
S103: the coefficient of determination (R obtaining PWC and NDSI under the horizontal subdata collection of different PNC
2) result set;
S104: determine the PWC core bands general character region under different PNC level;
S105: the optimum spectrum index determining core bands general character region;
S106: set up the wheat PWC monitoring model based on optimum spectrum index;
The accuracy of S107: inspection wheat PWC monitoring model and universality.
The present invention utilizes the wheat field test of different year (continuous two season 2010.11-2011.06,2011.11-2012.06), different in moisture process, different nitrogen amount applied and different growing, gather the wheat plant water percentage under different nitrogen contents level and corresponding canopy spectra reflectivity, according to different PNC size horizontal classification, find the PWC core bands general character region under different PNC level, determine to be applicable to the optimum spectrum index of PWC under different PNC level conditions, thus build the monitoring model towards wheat jointing to the pustulation period based on optimum spectrum index.
Wheat breed is for raising wheat 18, and planting patterns adopts drilling, and line-spacing is 25cm, and Basic Seedling is every mu of 120,000 strains, and plot area is 10m
2.
Test 1(2010.11-2011.06) in 4 moisture solution levels are set, for 9.5-10.5%, 15.5-16.5%, 21.5-22.5% and 29.5-30.5%(represent with volumetric water content); Arranging 2 nitrogen amount applied, is 150kg/hm
2, 300kg/hm
2.Test 2(2011.11-2012.06) in arrange 3 moisture solution be 13.5-14.5%, 21.5-22.5%, 29.5-30.5%; Arranging 3 nitrogen amount applied, is 90kg/hm
2, 180kg/hm
2, 270kg/hm
2.Test 1 is for setting up monitoring model, and test 2 is for checking monitoring model.
Specifically comprise the following steps:
S101: sampling, gathers wheat canopy spectral reflectivity, PNC and PWC numerical value.The wheat field experiment that enforcement different in moisture process and different nitrogen amount applied are done mutually, arranges 4 moisture solution levels, for 9.5-10.5%, 15.5-16.5%, 21.5-22.5% and 29.5-30.5%(represent with volumetric water content), 2 nitrogen amount applied are 150kg/hm
2, 300kg/hm
2.
Gather 2010.11-2011.06 and raise wheat 18 from jointing to the canopy spectra reflectivity of each crucial growthdevelopmental stage of grouting, canopy spectra reflectivity adopts field EO-1 hyperion radiation gauge, and wavelength band is 350-2500nm, and wave band is spaced apart 1nm; Canopy spectra measuring reflectance: the weather selecting ceiling unlimited, 10:00-14:00,1m test above canopy.
Choose the 10 strain list stems that can characterize the average growing way in this community in each cell synchronous and carry out destructiveness sampling, weigh fresh weight and dry weight, calculate PWC, grind away adopts the corresponding PNC of Kjeldahl's method measuring and calculation after weighing.
PWC account form: Plant water content (PWC) (%)=(W
f-W
d)/W
f× 100, wherein W
ffor plant fresh weight (g) summation, W
dfor plant weights (g) summation.
S102: PWC and canopy spectra reflectivity data are divided into three sub-data sets by different PNC level.By the PWC that gathers and the total data collection of corresponding canopy spectra reflectivity according to PNC value magnitude range and data volume distribution situation, be divided into PNC<1.3%, PNC1.3-1.6%, PNC>1.6% tri-scopes, according to corresponding PNC value scope, whole PWC and corresponding canopy spectra reflectivity are divided into three sub-data sets of corresponding different PNC level.
Basic classification principle: ensure on the scope basis that there is some difference of each horizontal PNC value, controls the data volume of subdata collection belonging to each PNC level without crossing big-difference.Wherein, three sub-data set data volumes that in test 1, PNC<1.3%, PNC1.3-1.6%, PNC>1.6% are corresponding are respectively: 32,27,21, test 2 neutron data collection data volumes and are respectively: 23,38,46.
S103: the coefficient of determination (R obtaining PWC and NDSI under the horizontal subdata collection of different PNC
2) result set.Use Matlab9.0 program calculation, obtain the NDSI of any two band combinations in PWC and 350-2500nm wavelength band under different PNC horizontal subdata collection build the coefficient of determination (R of corresponding model
2) result set; And by the model R of band combinations all in each result set
2matrix data is depicted as contour map and exports, with color depth change display R
2the change of size.
R
2result set is specially: in 350-2500nm wave band, take 1nm as the R of NDSI and the PWC institute established model of the correspondence of the wave band between two combination at interval
2collection, arranges in matrix.
S104: determine the PWC core bands general character region under different PNC level.With the above-mentioned each coefficient of determination (R
2) R in result set
2maximal value be standard, definition R
2the contour map region of front 10% correspondence is core bands region (as A, B, C in Fig. 1); Found the same section in the core bands region of the horizontal subdata collection of each PNC by Matlab9.0, be core bands general character region, export (as D in Fig. 1) with contour map form.
S105: determine the optimum spectrum index based on core bands general character region.Modeling accuracy (the R corresponding to all NDSI and PWC institutes established model of COMPREHENSIVE CALCULATING band combination between two in the above-mentioned core bands general character region determined
2) with verify error (relative root mean square deviation RRMSE), consider R
2with RRMSE size, choose R
2core bands general character region band combination NDSI (1302,1190) corresponding to-RRMSE maximal value is optimum spectrum index, and wherein 1190nm is positioned near water characteristic absorption bands 1200nm, and 1302nm is near the optimum sensitive band 1300nm of PWC.
S106: as Fig. 2 A, sets up the wheat PWC monitoring model based on optimum spectrum index NDSI (1302,1190): Y=-1289.4X+78.29, wherein, and detection model R
2be 0.876, SE be 2.702.
S107: as Fig. 2 B, utilizes accuracy and the universality of independent time (test 2,2011.11-2012.06) wheat test figure checking monitoring model, adopts coefficient of multiple correlation R
2, relatively root mean square deviation RRMSE comprehensive evaluation (inspection monitoring model R is carried out to monitoring model
2be 0.7979, RRMSE be 0.0662), and verify susceptibility (the PNC testing model R of monitoring model to PNC
2be 0.3242, RRMSE be 45.7011).
Wherein, the computing formula of RRMSE is as follows:
n is sample number, P
ifor model predication value, O
ifor experimental observation value,
for observing mean value.
If spectrum index determination mode traditionally, namely the optimum spectrum index of PWC is calculated under the total data collection regardless of different PNC level, then result is as shown in Figure 3: the optimum spectrum index band combination of PWC is NDSI(1727, and 1539), wherein core bands is all positioned at short-wave infrared scope.This spectrum index has higher modeling and testing accuracy to total data collection, but the monitoring and prediction unstable properties to different PNC level, as: the monitoring accuracy of model very low (R during PNC>1.6
2, and there is obvious saturated phenomenon (see Fig. 4 A, B dashed circle inner region)=0.5064); Predictive ability under PNC1.3-1.6 level is (R on the low side also
2=0.6702) (see Fig. 4 B).
Based on the optimum spectrum index NDSI (1302 in different PNC horizontal core bands general character region in the present invention, 1190) the wheat PWC monitoring model set up, higher monitoring and forecasting ability is all demonstrated to the PWC under different PNC level, simultaneously insensitive to PNC, and relatively the monitoring model of transmission spectra index construction overcomes the easy saturated phenomenon of PWC model under high PNC level dramatically.The spectrum index proposed with forefathers further compares discovery, and total monitoring predictive ability of NDSI (1302,1190) is much better than forefathers' spectrum index.Illustrate that the wheat that the present invention is based under different PNC levels that hyperspectral technique determines is planted the optimum spectrum index NDSI (1302,1190) in PWC core bands general character region and had good application prospect.The method overcome classic method and incomplete defect is considered to experimental factor, be equally applicable to the production estimation study on monitoring of other multifactor mutual works.
Table 1 based on different spectrum index wheat plant water percentage modeling (n=271) and inspection (n=308) effect
Claims (8)
1. the monitoring method of wheat plant water percentage under different plants nitrogen content level, is characterized in that comprising the following steps:
Step one, sampling, gather wheat canopy spectral reflectivity, N content of crop tissue and Plant water content numerical value; Sample point picks up from different growing, different in moisture process, different nitrogen amount applied and different year;
Step 2, by different plants nitrogen content level, whole Plant water content and canopy spectra reflectivity are divided into three sub-data sets;
Step 3, obtain Plant water content and two band combinations any in 350-2500nm wavelength band under different plants nitrogen content horizontal subdata collection normalization spectrum index NDSI build the coefficient of determination result set of corresponding model;
Step 4, the Plant water content core bands general character region determined under different plants nitrogen content level: with the maximal value of the coefficient of determination in above-mentioned each coefficient of determination result set for standard, before the definition coefficient of determination, the contour map region of 10% correspondence is core bands region; Find the same section in the core bands region of the horizontal subdata collection of each N content of crop tissue, be core bands general character region;
Step 5, determine the optimum spectrum index in core bands general character region: all normalization spectrum index NDSI calculating band combination between two in step 4 fixed core bands general character region and modeling accuracy and the error-checking relative root square mean error amount corresponding to Plant water content institute established model, choosing the normalization spectrum index that modeling accuracy-root square error maximal value is corresponding is relatively optimum spectrum index;
Step 6, set up wheat plant water percentage monitoring model based on optimum spectrum index;
The accuracy of step 7, inspection wheat plant water percentage monitoring model and universality.
2. the monitoring method of wheat plant water percentage under a kind of different plants nitrogen content level according to claim 1, it is characterized in that in step one, the wheat field experiment that different in moisture process and different nitrogen amount applied are done mutually is set, gather jointing to each crucial growthdevelopmental stage canopy spectra reflectivity that is in the milk, the inter-sync of Bing Mei community is chosen 10 single stems that can characterize the average growing way in community and is carried out destructiveness sampling, weigh fresh weight and dry weight, calculate Plant water content result, grind away adopts Kjeldahl nitrogen determination corresponding plants nitrogen content after weighing.
3. the monitoring method of wheat plant water percentage under a kind of different plants nitrogen content level according to claim 1, it is characterized in that in step 2, N content of crop tissue is divided into N content of crop tissue <1.3%, N content of crop tissue 1.3-1.6%, N content of crop tissue >1.6% tri-scopes, according to corresponding plants nitrogen content, whole Plant water contents and corresponding canopy spectra reflectivity are divided into three sub-data sets of corresponding different plants nitrogen content level.
4. the monitoring method of wheat plant water percentage under a kind of different plants nitrogen content level according to claim 1, it is characterized in that in step 3, the coefficient of determination matrix data of the model of band combinations all in each result set is depicted as contour map, with the change of color depth change display coefficient of determination size.
5. the monitoring method of wheat plant water percentage under a kind of different plants nitrogen content level according to claim 1, it is characterized in that in step 4, found the same section in the core bands region of the horizontal subdata collection of each N content of crop tissue by Matlab9.0, be core bands general character region.
6. the monitoring method of wheat plant water percentage under a kind of different plants nitrogen content level according to claim 1, it is characterized in that in step 5, optimum spectrum index is NDSI (1302,1190).
7. the monitoring method of wheat plant water percentage under a kind of different plants nitrogen content level according to claim 1, is characterized in that wheat plant water percentage monitoring model is: Y=-1289.4NDSI (1302,1190)+78.29.
8. the monitoring method of wheat plant water percentage under a kind of different plants nitrogen content level according to claim 1, it is characterized in that in step 7, utilize accuracy and the universality of independent time wheat test figure checking monitoring model, adopt multiple correlation coefficient, relatively root mean square deviation to carry out comprehensive evaluation to monitoring model, and check monitoring model to the susceptibility of N content of crop tissue.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310422607.4A CN103472009B (en) | 2013-09-16 | 2013-09-16 | The monitoring method of wheat plant water percentage under a kind of different plants nitrogen content level |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310422607.4A CN103472009B (en) | 2013-09-16 | 2013-09-16 | The monitoring method of wheat plant water percentage under a kind of different plants nitrogen content level |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103472009A CN103472009A (en) | 2013-12-25 |
| CN103472009B true CN103472009B (en) | 2015-11-18 |
Family
ID=49796949
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310422607.4A Active CN103472009B (en) | 2013-09-16 | 2013-09-16 | The monitoring method of wheat plant water percentage under a kind of different plants nitrogen content level |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103472009B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103868880B (en) * | 2014-01-24 | 2016-08-17 | 河南农业大学 | Wheat leaf blade nitrogen content monitoring method based on the bimodal index of spectrum and the construction method of monitoring model thereof |
| CN105158177B (en) * | 2015-09-30 | 2019-03-05 | 江苏大学 | The method of hyper-spectral image technique quantitative detection solid state fermentation moisture distribution uniformity |
| CN107316116B (en) * | 2017-08-23 | 2020-11-10 | 吉林大学 | Leaf vegetable yield prediction method |
| CN108387534A (en) * | 2018-03-15 | 2018-08-10 | 中国农业科学院农田灌溉研究所 | Measure plant water content method and apparatus |
| CN110082300B (en) * | 2019-05-20 | 2020-03-03 | 中国水利水电科学研究院 | Method for establishing winter wheat canopy water content monitoring model based on spectral parameters |
| CN110333195A (en) * | 2019-07-15 | 2019-10-15 | 北华航天工业学院 | Water content in plant leaf detection method and device |
| CN111721738A (en) * | 2020-06-23 | 2020-09-29 | 陕西理工大学 | Hyperspectrum-based analysis method for relationship between plant growth state and soil nitrogen content |
| CN112287886B (en) * | 2020-11-19 | 2023-09-22 | 安徽农业大学 | Wheat plant nitrogen content estimation method based on hyperspectral image fusion map features |
| DE202022102591U1 (en) | 2022-05-12 | 2022-06-27 | Deepak Batham | System for monitoring plant health in precision agriculture using image processing and convolutional neural network |
| CN115015132A (en) * | 2022-06-01 | 2022-09-06 | 南京农业大学 | Winter wheat moisture condition monitoring method based on data fusion |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102313699A (en) * | 2011-05-26 | 2012-01-11 | 北京农业信息技术研究中心 | Estimation method of total nitrogen content in crop canopy leaf |
| CN102426153A (en) * | 2011-11-21 | 2012-04-25 | 南京农业大学 | Wheat plant moisture monitoring method based on canopy high spectral index |
| CN102636439A (en) * | 2012-04-16 | 2012-08-15 | 南京农业大学 | Method for determining wheat plant nitrogen sucking quantity core wave band |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FI20061153L (en) * | 2006-12-22 | 2008-06-23 | Kemira Growhow Oyj | Method, device and system for determining the need for growth aids to promote plant growth |
-
2013
- 2013-09-16 CN CN201310422607.4A patent/CN103472009B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102313699A (en) * | 2011-05-26 | 2012-01-11 | 北京农业信息技术研究中心 | Estimation method of total nitrogen content in crop canopy leaf |
| CN102426153A (en) * | 2011-11-21 | 2012-04-25 | 南京农业大学 | Wheat plant moisture monitoring method based on canopy high spectral index |
| CN102636439A (en) * | 2012-04-16 | 2012-08-15 | 南京农业大学 | Method for determining wheat plant nitrogen sucking quantity core wave band |
Non-Patent Citations (2)
| Title |
|---|
| 不同施氮条件下小麦冠层的高光谱和多光谱反射特征;李映雪等;《麦类作物学报》;20061231;第26卷(第2期);103-108 * |
| 作物水分和氮素光谱诊断研究进展;薛利红等;《遥感学报》;20030131;第7卷(第1期);73-80 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103472009A (en) | 2013-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103472009B (en) | The monitoring method of wheat plant water percentage under a kind of different plants nitrogen content level | |
| CN102426153B (en) | A kind of Wheat plant moisture monitoring method based on canopy high spectral index | |
| Hussein et al. | Simulating cotton yield response to deficit irrigation with the FAO AquaCrop model | |
| CN107024439A (en) | A kind of paddy rice different growing chlorophyll content EO-1 hyperion estimating and measuring method | |
| CN102435564B (en) | Method for estimating plant nitrogen content based on three-band spectral index | |
| CN103293111A (en) | Wheat leaf layer nitrogen content spectral monitoring mode under soil background interference and modeling method | |
| CN104502283A (en) | Two-band hyperspectral index and prediction model for estimating yield and shoot dry weight of soybean | |
| CN103185695A (en) | Spectrum-based flue-cured tobacco maturity field quick judgment method | |
| CN110567892B (en) | Summer corn nitrogen hyperspectral prediction method based on critical nitrogen concentration | |
| CN109187441A (en) | The construction method of summer corn nitrogen content monitoring model based on canopy spectrum information | |
| CN103868880A (en) | Wheat leaf nitrogen content monitoring method based on spectrum double-peak index and method for establishing monitoring model | |
| CN103528965B (en) | A kind of wheat leaf equivalent water thickness EO-1 hyperion monitoring method | |
| CN104483271A (en) | Forest biomass amount retrieval method based on collaboration of optical reflection model and microwave scattering model | |
| CN102374971A (en) | Method for estimating LNC (leaf nitrogen content) of corns based on hyperspectral technique | |
| CN104820065B (en) | A kind of carbon remittance measuring method of city individual plant arbor | |
| CN106469240A (en) | Rape leaf SPAD estimation based on spectral index and estimation models construction method | |
| CN110987830A (en) | Model, method and application for rapidly determining chlorophyll content of plant canopy leaves | |
| CN106485345A (en) | Cotton Gossypii time of infertility canopy SPAD value remote sensing appraising and appraising model construction method | |
| CN109060676A (en) | Based on the determination method of the Summer Corn Canopy SPAD value appraising model of EO-1 hyperion | |
| CN101158576A (en) | Embedded program type electric theodolites angle gage automatic stereo tree-measuring technology | |
| Guan et al. | The relationship between sap flow of intercropped young poplar trees (Populus× euramericana cv. N3016) and environmental factors in a semiarid region of northeastern China | |
| Kilinc et al. | An analysis of the surface energy budget above the world's tallest angiosperm forest | |
| CN112270131A (en) | Remote sensing inversion model and method for rice leaf area index based on ARD regression algorithm | |
| CN115184322A (en) | Rice leaf water content monitoring method | |
| CN105954207A (en) | Method for detecting content of chlorophyll b in canopy of jujube tree |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |