CN111366555A - Detection method for agricultural film residue in farmland soil - Google Patents
Detection method for agricultural film residue in farmland soil Download PDFInfo
- Publication number
- CN111366555A CN111366555A CN202010124191.8A CN202010124191A CN111366555A CN 111366555 A CN111366555 A CN 111366555A CN 202010124191 A CN202010124191 A CN 202010124191A CN 111366555 A CN111366555 A CN 111366555A
- Authority
- CN
- China
- Prior art keywords
- agricultural film
- soil
- terahertz
- samples
- agricultural
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000002689 soil Substances 0.000 title claims abstract description 65
- 238000001514 detection method Methods 0.000 title claims abstract description 25
- 238000000034 method Methods 0.000 claims abstract description 24
- 230000004927 fusion Effects 0.000 claims abstract description 13
- 239000000126 substance Substances 0.000 claims abstract description 13
- 230000003595 spectral effect Effects 0.000 claims abstract description 11
- 239000003344 environmental pollutant Substances 0.000 claims abstract description 8
- 231100000719 pollutant Toxicity 0.000 claims abstract description 8
- 238000000611 regression analysis Methods 0.000 claims abstract description 7
- 238000001228 spectrum Methods 0.000 claims description 21
- 230000009466 transformation Effects 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 5
- 238000007477 logistic regression Methods 0.000 claims description 4
- 238000004817 gas chromatography Methods 0.000 claims description 3
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 2
- 230000004913 activation Effects 0.000 claims description 2
- 230000003044 adaptive effect Effects 0.000 claims description 2
- 230000008034 disappearance Effects 0.000 claims description 2
- 230000006870 function Effects 0.000 claims description 2
- 238000005457 optimization Methods 0.000 claims description 2
- 238000003825 pressing Methods 0.000 claims description 2
- 230000007547 defect Effects 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 239000004743 Polypropylene Substances 0.000 description 6
- 239000010410 layer Substances 0.000 description 6
- 229920006267 polyester film Polymers 0.000 description 6
- 229920001155 polypropylene Polymers 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 239000002362 mulch Substances 0.000 description 4
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 3
- 229910001710 laterite Inorganic materials 0.000 description 3
- 239000011504 laterite Substances 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- -1 polypropylene Polymers 0.000 description 3
- 239000004800 polyvinyl chloride Substances 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 244000005700 microbiome Species 0.000 description 2
- 229910052757 nitrogen Inorganic materials 0.000 description 2
- 239000002985 plastic film Substances 0.000 description 2
- 229920006255 plastic film Polymers 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 239000002344 surface layer Substances 0.000 description 2
- 238000001328 terahertz time-domain spectroscopy Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 231100000357 carcinogen Toxicity 0.000 description 1
- 239000003183 carcinogenic agent Substances 0.000 description 1
- 238000012569 chemometric method Methods 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 238000002290 gas chromatography-mass spectrometry Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- QJGQUHMNIGDVPM-UHFFFAOYSA-N nitrogen group Chemical group [N] QJGQUHMNIGDVPM-UHFFFAOYSA-N 0.000 description 1
- 238000006303 photolysis reaction Methods 0.000 description 1
- 238000005375 photometry Methods 0.000 description 1
- 230000015843 photosynthesis, light reaction Effects 0.000 description 1
- 230000008635 plant growth Effects 0.000 description 1
- 239000004033 plastic Substances 0.000 description 1
- 229920003023 plastic Polymers 0.000 description 1
- 125000005575 polycyclic aromatic hydrocarbon group Chemical group 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000003900 soil pollution Methods 0.000 description 1
- 238000002076 thermal analysis method Methods 0.000 description 1
- 238000000870 ultraviolet spectroscopy Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3581—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using far infrared light; using Terahertz radiation
- G01N21/3586—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using far infrared light; using Terahertz radiation by Terahertz time domain spectroscopy [THz-TDS]
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
Abstract
The invention discloses a method for detecting agricultural film residue in farmland soil, which belongs to the technology for detecting agricultural film residue in farmland soil, and comprises the steps of establishing a regression analysis model according to the combination of the content of agricultural film pollutant substances in soil samples in all regions in a modeling set and the refractive index of a corresponding terahertz time-domain transform line, respectively substituting the spectral refractive index values of the agricultural film pollutants in soil in each geographical position in a prediction set into the regression analysis model to obtain the corresponding substances and content of the agricultural film in the soil, predicting and comparing the difference of correlation coefficients to obtain the differentiability of the soil agricultural film pollution in different geographical positions in terahertz detection, constructing a fusion model of various soil agricultural films by fusing the agricultural film residue in different geographical positions and terahertz spectral signals thereof, and predicting the agricultural film residue by using the fusion model. The method has the advantages of realizing rapid detection of agricultural film residue in the cultivated land soil, having low detection cost and high accuracy, and overcoming the defects of complex procedure, higher cost, great damage to samples and the like of the traditional detection method.
Description
Technical Field
The invention relates to a detection technology of agricultural film residue in farmland soil, in particular to a detection method of agricultural film residue in farmland soil.
Background
Various agricultural plastic films are widely used as plastic greenhouse and plastic film mulching materials, and if the management and recovery are not good, a large amount of residual film fragments are scattered in the field, so that the white pollution of the field can be caused. Most agricultural films have stable performance, and have poor photolysis and biological decomposability in natural environment, and residual films are still left in soil and are difficult to degrade. The microorganisms are continuously adsorbed and retained in the soil, so that the microorganisms in the soil are killed in a large quantity, and the normal growth of plants planted in the soil is influenced. In particular, polycyclic aromatic hydrocarbons in soil belong to strong carcinogens, can enter human bodies through skin, breath, diet and other modes, and are harmful to human health.
Therefore, soil pollution has become a worldwide environmental problem, and the detection of the agricultural film pollution in the soil has important significance for environmental monitoring and pollution recovery and treatment. At present, the detection of substances in soil mainly comprises a cracking-gas chromatography/mass spectrometry combined method, an ultraviolet spectroscopy method, a gravimetric method, an infrared photometry and the like, a complex operation process is required, the requirement on the professional degree of operators is high, the detection period is long, and the efficient and accurate detection of the substances in the soil cannot be realized.
Chinese patent publication No. CN106644939A discloses a method for measuring residual quantity of residual film on surface of farmland soil, comprising the following steps: step 1, obtaining residual film residual quantity image information on the surface of a farmland; step 2, preprocessing the residual film residual quantity image information on the surface of the farmland; step 3, counting and measuring the residual quantity of the residual film on the surface of the farmland; and 4, performing mathematical analysis calculation according to the residual quantity information of the residual mulch on the surface layer, counting the numerical relationship between the residual mulch on the surface layer and the residual mulch on the plough layer, and calculating the residual quantity of the residual mulch on the plough layer.
In the above method of performing the residual film measurement, the acquisition of the image requires the image capturing of the measurement area by the unmanned aerial vehicle, and the image capturing needs to be performed on the spot, which results in a great increase in the workload.
Disclosure of Invention
The invention aims to provide a method for detecting agricultural film residue in farmland soil,
in order to achieve the purpose, the method for detecting the agricultural film residue in the farmland soil provided by the invention comprises the following steps:
1) sampling soil samples polluted by agricultural films at different geographical positions on the spot, respectively taking different samples from different plots at the same geographical position, respectively reserving at least three samples, and pressing the samples into tabletting samples;
2) placing the tabletting sample at a detection site of a projection module of the terahertz spectrograph, collecting terahertz spectrum signals of the tabletting sample, and making an original terahertz spectrum time-domain transformation curve, which is marked as X;
3) the actual substance of the agricultural film in the sample soil and the corresponding real content value are measured by adopting a thermal gas chromatography, and the agricultural film and the concentration of each sample corresponding to different sampling soils are respectively recorded as YiCollectively called Y;
4) according to an original terahertz spectrum time-domain transformation curve, by combining the characteristic frequency and the corresponding relation of the substance structure of the corresponding agricultural film measured in the step 3), finding out a characteristic frequency domain value corresponding to agricultural film pollutants, and dividing the obtained data (X, Y) into a modeling set and a prediction set in proportion;
5) establishing a regression analysis model according to the combination of the agricultural film pollutant content in soil samples of all regions in the modeling set and the refractive index of the corresponding terahertz time-domain transform spectral line, respectively substituting the spectral refractive index values of the agricultural film pollutants of the soil of each geographic position in the prediction set into the regression analysis model to obtain the corresponding agricultural film substances and content in the soil, predicting and comparing the difference of correlation coefficients to obtain the differentiability of detecting the soil agricultural film pollution of different geographic positions in the terahertz mode, fusing the agricultural film residual quantity of different geographic positions and the terahertz spectrum signals thereof to construct a fusion model of various soil agricultural films, and predicting the soil agricultural film residual condition by using the fusion model.
The terahertz time-domain spectroscopy (THz-TDS) is a spectroscopic detection method for extracting internal information of a material by carrying medium information through broadband terahertz pulses, and is often used in the field of nondestructive detection of materials. The spectrum refractive index of the residual agricultural film under the terahertz waveband is combined with a chemometric method, so that the rapid nondestructive detection of the agricultural film pollution in the soil can be realized. According to the technical scheme, the rapid detection of the agricultural film residue in the cultivated land soil is realized, the characteristics of simplicity in operation, low detection cost, high accuracy and the like are realized, and the defects of complex program, high cost, large damage to samples and the like of the traditional detection method are effectively overcome.
Preferably, in the step 1), the dimensional parameters of the tabletting sample are optimized, and the optimized parameters are as follows: the weight is 400 plus or minus 2mg, the thickness is 1.2 plus or minus 0.2mm, and the diameter is 12 plus or minus 0.4 mm.
Preferably, in the step 2), the original terahertz spectrum time-domain transformation curve is obtained by calculating time-domain spectrum information and sample thickness data obtained by the terahertz time-domain spectrometer through fourier transformation.
Preferably, in the step 2), system parameters for collecting terahertz spectrum signals of the tabletting samples are optimized, and the obtained optimized parameters are as follows: a1560 nm femtosecond laser is adopted to generate 780nm femtosecond pulses with the bandwidth of 100fs, and the average collection frequency is 150 times.
Preferably, in step 5), the first half of the fusion model adopts a sparse self-coding network, the self-coding unsupervised self-learning mode reconstructs input in an error minimization mode, typical features in terahertz spectrum information are extracted, and the second half adopts a logistic regression model, processes the typical features extracted by the sparse self-coding network, and predicts the agricultural film residue.
Preferably, in the step 5), the sparse self-coding network adopts a 5-layer symmetrical n-64-10-64-n coding and decoding network structure, the input dimension n is determined by a spectral dimension, wherein an optimization algorithm for enabling the whole structure to achieve output equal to input reconstruction adopts an adaptive learning rate Adam, the learning rate is 0.001, first-order and second-order momentum parameters are 0.9 and 0.999 respectively, and the learning rate attenuation value of each update is 1 e-7; the activation function adopts elu to accelerate the training process and relieve the disappearance of the gradient; in addition, in order to improve the generalization capability of the model, l1 regularization factors are added to the input layer to increase the data sparsity, and the parameter is 0.01; and then, the output of a second layer hidden layer of an encoder in self-coding is used as the input of logistic regression, and the residue of the agricultural film in the prediction set is predicted.
Compared with the prior art, the invention has the beneficial effects that:
the method realizes the fusion recognition detection of the agricultural film residue in the soil, explores the agricultural film residue differentiability of different farmland soils by adopting a fusion model method, utilizes the rapid detection of the agricultural film residue in the farmland soils based on the terahertz spectrum technology, overcomes the defects of the traditional detection, selects a representative frequency domain value of the agricultural film residue, and further develops and uses a more portable sensing instrument.
Drawings
Fig. 1 is a prediction result diagram of a sparse self-coding fusion model of agricultural film residue in a farmland soil sample in an embodiment of the invention, wherein (a) is a prediction result diagram of polyester film (PET), (b) is a prediction result diagram of polypropylene (PP), and (c) is a prediction result diagram of polyvinyl chloride (PVC).
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described with reference to the following embodiments and accompanying drawings.
Examples
The method for detecting the agricultural film residue in the farmland soil comprises the following steps:
s1, sample preparation, the experimental samples adopted in the embodiment are sampled from black soil of great Xingan mountain of Heilongjiang, loess and laterite of Cantonese of Guangdong province, laterite of red river of Yunnan province, laterite of Zhangzhou of Fujian province, brown soil of fixed west of Gansu province and loess of Shaanxi province, which are marked as So1, So2, So3, So4, So5, So6 and So7, 10 samples of polluted farmland soil remained by agricultural films are distributed in different plots, three parts of the samples are reserved respectively, the samples are put into a tablet press to be pressed into tablets, square samples with the specification of 12mm × 12mm × 1.2.2 mm are manufactured by using the tablet press (the pressure of 10MPa lasts for 30S), each tablet has the mass of 0.4g, 30 samples are prepared from each farmland soil, and 210 soil tabletting samples are obtained.
And S2, collecting the terahertz spectrum signal of the sample. The chamber to be tested of the experimental instrument is filled with nitrogen for 30min to reach a stable state. Firstly, collecting a nitrogen signal in a room to be tested of an experimental instrument as a background signal, and removing the influence of moisture as much as possible. Then placing the soil tabletting sample to be detected in a room to be detected, setting the average collection frequency to be 150, starting to collect signals, and making an original terahertz spectrum time-domain transformation curve, which is marked as X;
and S3, detecting the actual substances and the true values of the residual agricultural film in the sample soil. Detecting agricultural film residues in seven sampling points by adopting a thermal analysis gas chromatography, wherein samples from So 1-So 7 contain polyester film (PET), polypropylene (PP) and polyvinyl chloride (PVC) with different content gradients, and the real concentration values are respectively marked as Y1, Y2, Y3, Y4, Y5, Y6 and Y7 and are totally marked as Y;
s4, finding out frequency domain values of frequency domain spectral lines of main characteristics of the contents of 3 substances including polyester film (PET), polypropylene (PP) and polyvinyl chloride (PVC) in soil of residual films in cultivated land according to an original terahertz time-domain transformation curve (X), wherein the frequency domain values are respectively 1.4-1.8, 0.6-1.2 and 0.6-1.2 THz as shown in (a), (b) and (c) in figure 1, and the obtained data are obtained according to a ratio of 2: the samples are divided according to the proportion of 1, so that 140 modeling set samples and 70 prediction set samples are obtained.
S5, establishing a convolution neural network combined regression analysis fusion prediction model according to the spectral refractive index value of the agricultural film residue in the soil of the modeling concentrated farmland and the indexes of agricultural film substances and content. And (4) bringing the intensities of spectral lines of the residual agricultural films in the prediction set into an analysis model for prediction. The result shows that in the fusion model, the refractive index of the terahertz spectrum is used for predicting the agricultural film residue in the farmland soil, the prediction goodness of fit of So1 is high, the overall correlation coefficient is as high as 0.98, and the correlation coefficients of So 2-So 7 are respectively 0.94, 0.96, 0.92, 0.90, 0.93 and 0.92. Satisfactory results are also obtained. The results show that the method can realize the rapid detection of the agricultural film residue in the soil of different cultivated lands, and has good application prospect.
Claims (6)
1. A detection method for agricultural film residue in farmland soil is characterized by comprising the following steps:
1) sampling soil samples polluted by agricultural films at different geographical positions on the spot, respectively taking different samples from different plots at the same geographical position, respectively reserving at least three samples, and pressing the samples into tabletting samples;
2) placing the tabletting sample at a detection site of a projection module of the terahertz spectrograph, collecting terahertz spectrum signals of the tabletting sample, and making an original terahertz spectrum time-domain transformation curve, which is marked as X;
3) the actual substance of the agricultural film in the sample soil and the corresponding real content value are measured by adopting a thermal gas chromatography, and the agricultural film and the concentration of each sample corresponding to different sampling soils are respectively recorded as YiCollectively called Y;
4) according to an original terahertz spectrum time-domain transformation curve, by combining the characteristic frequency and the corresponding relation of the substance structure of the corresponding agricultural film measured in the step 3), finding out a characteristic frequency domain value corresponding to agricultural film pollutants, and dividing the obtained data (X, Y) into a modeling set and a prediction set in proportion;
5) establishing a regression analysis model according to the combination of the agricultural film pollutant content in soil samples of all regions in the modeling set and the refractive index of the corresponding terahertz time-domain transform spectral line, respectively substituting the spectral refractive index values of the agricultural film pollutants of the soil of each geographic position in the prediction set into the regression analysis model to obtain the corresponding agricultural film substances and content in the soil, predicting and comparing the difference of correlation coefficients to obtain the differentiability of detecting the soil agricultural film pollution of different geographic positions in the terahertz mode, fusing the agricultural film residual quantity of different geographic positions and the terahertz spectrum signals thereof to construct a fusion model of various soil agricultural films, and predicting the soil agricultural film residual condition by using the fusion model.
2. The method for detecting the residual agricultural film in the cultivated land soil according to claim 1, characterized in that in step 1), the dimensional parameters of the pressed sheet sample are optimized, and the optimized parameters are as follows: the weight is 400 plus or minus 2mg, the thickness is 1.2 plus or minus 0.2mm, and the diameter is 12 plus or minus 0.4 mm.
3. The method for detecting agricultural film residue in arable soil according to claim 1, wherein in step 2), the original terahertz spectrum time-domain transformation curve is obtained by calculating time-domain spectrum information obtained by a terahertz time-domain spectrometer and sample thickness data through Fourier transform.
4. The method for detecting the agricultural film residue in the arable soil according to claim 1, wherein in the step 2), system parameters for collecting terahertz spectrum signals of the tabletting samples are optimized, and the obtained optimized parameters are as follows: a1560 nm femtosecond laser is adopted to generate 780nm femtosecond pulses with the bandwidth of 100fs, and the average collection frequency is 150 times.
5. The method for detecting agricultural film residues in cultivated land soil according to claim 1, wherein in step 5), the first half of the fusion model adopts a sparse self-coding network, a self-coding unsupervised self-learning mode reconstructs input in an error minimization mode, typical features in terahertz spectrum information are extracted, and the second half adopts a logistic regression model to process the typical features extracted by the sparse self-coding network and predict agricultural film residues.
6. The method for detecting agricultural film residues in cultivated land soil according to claim 5, wherein in step 5), the sparse self-coding network adopts a 5-layer symmetrical n-64-10-64-n coding and decoding network structure, the input dimension n is determined by the spectral dimension, wherein the optimization algorithm for achieving the output of the whole structure equal to the input reconstruction adopts an adaptive learning rate Adam, the learning rate is 0.001, the first-order and second-order momentum parameters are 0.9 and 0.999 respectively, and the learning rate attenuation value of each update is 1 e-7; the activation function adopts elu to accelerate the training process and relieve the disappearance of the gradient; in addition, in order to improve the generalization capability of the model, l1 regularization factors are added to the input layer to increase the data sparsity, and the parameter is 0.01; and then, the output of a second layer hidden layer of an encoder in self-coding is used as the input of logistic regression, and the residue of the agricultural film in the prediction set is predicted.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010124191.8A CN111366555B (en) | 2020-02-27 | 2020-02-27 | Detection method for agricultural film residue in farmland soil |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010124191.8A CN111366555B (en) | 2020-02-27 | 2020-02-27 | Detection method for agricultural film residue in farmland soil |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111366555A true CN111366555A (en) | 2020-07-03 |
CN111366555B CN111366555B (en) | 2021-01-26 |
Family
ID=71204179
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010124191.8A Active CN111366555B (en) | 2020-02-27 | 2020-02-27 | Detection method for agricultural film residue in farmland soil |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111366555B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20220110241A1 (en) * | 2020-10-09 | 2022-04-14 | Deere & Company | Machine control using a predictive map |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008026523A1 (en) * | 2006-08-28 | 2008-03-06 | Tohoku University | Near-field light measuring method and near-field light measuring device |
CN101178355A (en) * | 2007-11-01 | 2008-05-14 | 浙江大学 | Page quantitative determination device and methods based on terahertz time-domain spectroscopic technology |
JP2008151591A (en) * | 2006-12-15 | 2008-07-03 | Canon Inc | Detection method of moisture and film deposition device |
WO2008093647A1 (en) * | 2007-01-31 | 2008-08-07 | Tohoku University | Microarray, method for production thereof, and method for detection of interaction between organic molecule and active substance |
JP2010156544A (en) * | 2008-12-26 | 2010-07-15 | Aisin Seiki Co Ltd | Terahertz light measuring device |
CN103323411A (en) * | 2013-05-30 | 2013-09-25 | 中国石油大学(北京) | Method and device for detecting plasticizer |
CN103364363A (en) * | 2013-06-28 | 2013-10-23 | 中国科学院西安光学精密机械研究所 | Device and method for acquiring absorption coefficient and refractive index of substance in terahertz waveband |
CN104076002A (en) * | 2013-03-29 | 2014-10-01 | 佳能株式会社 | Information acquiring apparatus and information acquiring method of acquiring information of sample by using terahertz wave |
CN104864817A (en) * | 2015-05-06 | 2015-08-26 | 中国矿业大学 | Terahertz time domain spectrum technology-based plastic film thickness detection device and method |
CN107273925A (en) * | 2017-06-12 | 2017-10-20 | 太原理工大学 | A kind of Lung neoplasm diagnostic method based on local receptor field and semi-supervised depth own coding |
CN110308108A (en) * | 2019-07-15 | 2019-10-08 | 山东省科学院自动化研究所 | Content of baicalin detection method and system based on terahertz time-domain spectroscopic technology |
-
2020
- 2020-02-27 CN CN202010124191.8A patent/CN111366555B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008026523A1 (en) * | 2006-08-28 | 2008-03-06 | Tohoku University | Near-field light measuring method and near-field light measuring device |
JP2008151591A (en) * | 2006-12-15 | 2008-07-03 | Canon Inc | Detection method of moisture and film deposition device |
WO2008093647A1 (en) * | 2007-01-31 | 2008-08-07 | Tohoku University | Microarray, method for production thereof, and method for detection of interaction between organic molecule and active substance |
CN101178355A (en) * | 2007-11-01 | 2008-05-14 | 浙江大学 | Page quantitative determination device and methods based on terahertz time-domain spectroscopic technology |
JP2010156544A (en) * | 2008-12-26 | 2010-07-15 | Aisin Seiki Co Ltd | Terahertz light measuring device |
CN104076002A (en) * | 2013-03-29 | 2014-10-01 | 佳能株式会社 | Information acquiring apparatus and information acquiring method of acquiring information of sample by using terahertz wave |
CN103323411A (en) * | 2013-05-30 | 2013-09-25 | 中国石油大学(北京) | Method and device for detecting plasticizer |
CN103364363A (en) * | 2013-06-28 | 2013-10-23 | 中国科学院西安光学精密机械研究所 | Device and method for acquiring absorption coefficient and refractive index of substance in terahertz waveband |
CN104864817A (en) * | 2015-05-06 | 2015-08-26 | 中国矿业大学 | Terahertz time domain spectrum technology-based plastic film thickness detection device and method |
CN107273925A (en) * | 2017-06-12 | 2017-10-20 | 太原理工大学 | A kind of Lung neoplasm diagnostic method based on local receptor field and semi-supervised depth own coding |
CN110308108A (en) * | 2019-07-15 | 2019-10-08 | 山东省科学院自动化研究所 | Content of baicalin detection method and system based on terahertz time-domain spectroscopic technology |
Non-Patent Citations (4)
Title |
---|
R. PIESIEWICZ,ET AL: "Properties of Building and Plastic Materials in the THz Range", 《INT J INFRARED MILLI WAVES》 * |
吴建 等: "基于太赫兹光谱的奶粉中葡萄糖及蔗糖定性定量检测方法", 《光谱学与光谱分析》 * |
王鹤 等: "几种塑料的太赫兹光谱检测", 《光子学报》 * |
赵鑫 等: "基于局部感受野和半监督深度自编码的肺结节检测方法", 《赵鑫 等》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20220110241A1 (en) * | 2020-10-09 | 2022-04-14 | Deere & Company | Machine control using a predictive map |
US11711995B2 (en) * | 2020-10-09 | 2023-08-01 | Deere & Company | Machine control using a predictive map |
Also Published As
Publication number | Publication date |
---|---|
CN111366555B (en) | 2021-01-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhou et al. | Hyperspectral inversion of soil heavy metals in Three-River Source Region based on random forest model | |
Zhang et al. | Constructing a PM2. 5 concentration prediction model by combining auto-encoder with Bi-LSTM neural networks | |
Faurtyot et al. | Vegetation water and dry matter contents estimated from top-of-the-atmosphere reflectance data: A simulation study | |
CN101915744B (en) | Near infrared spectrum nondestructive testing method and device for material component content | |
CN108875913B (en) | Tricholoma matsutake rapid nondestructive testing system and method based on convolutional neural network | |
D'Alimonte et al. | Phytoplankton determination in an optically complex coastal region using a multilayer perceptron neural network | |
Mao et al. | Coupled LAI assimilation and BEPS model for analyzing the spatiotemporal pattern and heterogeneity of carbon fluxes of the bamboo forest in Zhejiang Province, China | |
CN108152235B (en) | Heavy metal content inversion method combining soil indoor and outdoor spectra | |
Gross et al. | Applying artificial neural network methodology to ocean color remote sensing | |
CN109508824A (en) | A kind of detection of crop growth situation and yield predictor method | |
CN114460013B (en) | Coastal wetland vegetation overground biomass GAN model self-learning remote sensing inversion method | |
CN103389323A (en) | Method for evaluating ages of precious medicinal materials quickly and losslessly | |
CN111366555B (en) | Detection method for agricultural film residue in farmland soil | |
CN113436153A (en) | Method for predicting carbon components of undisturbed soil profile based on hyperspectral imaging and support vector machine technology | |
Korrensalo et al. | Varying vegetation composition, respiration and photosynthesis decrease temporal variability of the CO 2 sink in a boreal bog | |
Hang et al. | Estimation of chlorophyll-a concentration in Lake Taihu from Gaofen-1 wide-field-of-view data through a machine learning trained algorithm | |
CN114372707A (en) | High-cold-wetland degradation degree monitoring method based on remote sensing data | |
Pu et al. | The remote sensing of radiative forcing by light-absorbing particles (LAPs) in seasonal snow over northeastern China | |
Lu et al. | Prediction of diffuse solar radiation by integrating radiative transfer model and machine-learning techniques | |
CN116148188A (en) | Air-space-ground integrated lake water quality tracing method, system, equipment and storage medium | |
CN113408644B (en) | Satellite data reconstruction method and method for detecting response of upper ocean to typhoon | |
Wang et al. | Application of hyperspectral technology combined with bat algorithm-AdaBoost model in field soil nutrient prediction | |
CN111595806A (en) | Method for monitoring soil carbon component by using mid-infrared diffuse reflection spectrum | |
CN208476785U (en) | A kind of laser induced breakdown spectroscopy detection device suitable for aquatic products heavy metal analysis | |
CN112949182B (en) | Method for calculating regional scale maximum pore conductance of coupling surface soil water content |
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 |