CN117808173A - Paddy field fertility detection method, related product and planting method based on related product - Google Patents
Paddy field fertility detection method, related product and planting method based on related product Download PDFInfo
- Publication number
- CN117808173A CN117808173A CN202410225743.2A CN202410225743A CN117808173A CN 117808173 A CN117808173 A CN 117808173A CN 202410225743 A CN202410225743 A CN 202410225743A CN 117808173 A CN117808173 A CN 117808173A
- Authority
- CN
- China
- Prior art keywords
- paddy field
- fertility
- prediction model
- water body
- judging whether
- 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
- 230000035558 fertility Effects 0.000 title claims abstract description 75
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000001514 detection method Methods 0.000 title claims abstract description 50
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 112
- 238000012549 training Methods 0.000 claims abstract description 50
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims abstract description 40
- 238000012706 support-vector machine Methods 0.000 claims abstract description 32
- 230000003595 spectral effect Effects 0.000 claims abstract description 25
- 229910052757 nitrogen Inorganic materials 0.000 claims abstract description 20
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims abstract description 19
- 229910052698 phosphorus Inorganic materials 0.000 claims abstract description 19
- 239000011574 phosphorus Substances 0.000 claims abstract description 19
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 claims abstract description 17
- 239000011591 potassium Substances 0.000 claims abstract description 17
- 229910052700 potassium Inorganic materials 0.000 claims abstract description 17
- 150000003112 potassium compounds Chemical class 0.000 claims abstract description 6
- 238000001228 spectrum Methods 0.000 claims description 54
- 241000209094 Oryza Species 0.000 claims description 39
- 235000007164 Oryza sativa Nutrition 0.000 claims description 39
- 235000009566 rice Nutrition 0.000 claims description 39
- 230000006870 function Effects 0.000 claims description 24
- 238000003973 irrigation Methods 0.000 claims description 20
- 230000002262 irrigation Effects 0.000 claims description 20
- 239000003337 fertilizer Substances 0.000 claims description 18
- 238000007781 pre-processing Methods 0.000 claims description 18
- 239000002689 soil Substances 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 14
- 235000016709 nutrition Nutrition 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 13
- 239000007788 liquid Substances 0.000 claims description 12
- 239000000243 solution Substances 0.000 claims description 12
- 238000000870 ultraviolet spectroscopy Methods 0.000 claims description 10
- 150000002500 ions Chemical class 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 239000013598 vector Substances 0.000 claims description 7
- 238000013461 design Methods 0.000 claims description 6
- -1 nitrate ions Chemical class 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 239000004615 ingredient Substances 0.000 claims description 5
- 230000005070 ripening Effects 0.000 claims description 5
- 239000008267 milk Substances 0.000 claims description 4
- 210000004080 milk Anatomy 0.000 claims description 4
- 235000013336 milk Nutrition 0.000 claims description 4
- 229910017464 nitrogen compound Inorganic materials 0.000 claims description 4
- 150000002830 nitrogen compounds Chemical class 0.000 claims description 4
- 150000003018 phosphorus compounds Chemical class 0.000 claims description 4
- 229910002651 NO3 Inorganic materials 0.000 claims description 3
- NBIIXXVUZAFLBC-UHFFFAOYSA-L Phosphate ion(2-) Chemical compound OP([O-])([O-])=O NBIIXXVUZAFLBC-UHFFFAOYSA-L 0.000 claims description 3
- 230000008602 contraction Effects 0.000 claims description 3
- NBIIXXVUZAFLBC-UHFFFAOYSA-M dihydrogenphosphate Chemical compound OP(O)([O-])=O NBIIXXVUZAFLBC-UHFFFAOYSA-M 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 238000001035 drying Methods 0.000 claims description 3
- 230000031700 light absorption Effects 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 230000035772 mutation Effects 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 claims description 3
- 229910001414 potassium ion Inorganic materials 0.000 claims description 3
- 239000012086 standard solution Substances 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 description 13
- 230000035764 nutrition Effects 0.000 description 8
- 238000003860 storage Methods 0.000 description 7
- 238000010521 absorption reaction Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000009466 transformation Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 150000001875 compounds Chemical class 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000011259 mixed solution Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- 230000017260 vegetative to reproductive phase transition of meristem Effects 0.000 description 2
- 238000009736 wetting Methods 0.000 description 2
- 238000012271 agricultural production Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009614 chemical analysis method Methods 0.000 description 1
- 238000010224 classification analysis Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000006651 lactation Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000618 nitrogen fertilizer Substances 0.000 description 1
- 238000009406 nutrient management Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 238000013515 script Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000002791 soaking Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012306 spectroscopic technique Methods 0.000 description 1
- 238000004611 spectroscopical analysis Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Abstract
The invention relates to the technical field of intelligent detection, in particular to a paddy field fertility detection method, a related product and a planting method based on the same, wherein the detection method comprises the steps of constructing and training a fertility prediction model, acquiring spectral data of a water body sample, judging through the fertility prediction model, judging that the paddy field fertility is up to standard as a whole if nitrogen, phosphorus and potassium reach the standard, and judging that the paddy field fertility is not up to standard if any one of the nitrogen, the phosphorus and the potassium does not reach the standard; according to the method, a fertility prediction model based on a support vector machine is established, spectral data of nitrogen, phosphorus and potassium compounds in a water body are respectively obtained through different types of spectral instruments, training samples of the respective prediction models are formed, and the training samples are used for training the fertility prediction model. In actual detection, spectral data of a water body sample is obtained through a corresponding spectral instrument, and is input into a corresponding prediction model after being preprocessed, so that whether each element meets the standards is judged.
Description
Technical Field
The invention relates to the technical field of intelligent detection, in particular to a paddy field fertility detection method, a related product and a planting method based on the paddy field fertility detection method.
Background
Moisture and nutrient management during rice planting has a decisive influence on yield and quality. Conventional rice planting methods typically involve significant water resource consumption and fertilizer application, which not only results in wasted resources, but may also negatively impact the environment. Therefore, how to reduce the use of water and fertilizer while guaranteeing the water and nutrition required by the growth of rice and improve the environmental friendliness and economic benefit of the rice planting becomes the key point of current research and practice.
Therefore, the monitoring and evaluation of paddy field fertility in the planting process becomes particularly important. Traditional fertility detection methods generally rely on chemical analysis, and although accurate, the methods are often cumbersome, time-consuming and costly to operate. Furthermore, conventional methods have difficulty in achieving rapid, on-site fertility detection, which can lead to delays in the decision making process. Therefore, a rapid, efficient and low-cost paddy field fertility detection technology is developed, and the method has important significance for modern agriculture.
In this context, a fertility detection method based on spectroscopic techniques has received a great deal of attention. The method utilizes a spectroscopic instrument to quickly acquire spectroscopic data of a sample and processes the data through a specific algorithm to evaluate the fertility status. However, the spectral data is often subject to interference by various factors, such as noise, baseline wander, etc., which may affect the accuracy and stability of the detection. Therefore, how to effectively extract useful information from complex spectrum data and accurately predict paddy field fertility becomes one of the key problems in the technical field.
Disclosure of Invention
The invention aims to solve the technical problems, and aims to provide a paddy field fertility detection method, a related product and a planting method based on the paddy field fertility detection method, so that the accurate control of water resource and fertilizer use in the paddy planting process is realized.
The invention is realized by the following technical scheme:
in a first aspect, a method for detecting fertility of a paddy field based on a support vector machine includes:
constructing a fertility prediction model based on a support vector machine, wherein the fertility prediction model comprises an N prediction model, a P prediction model and a K prediction model;
acquiring spectrum data of nitrogen compounds in the model training water body through an ultraviolet-visible spectrophotometer to form a training sample of an N prediction model;
acquiring spectral data of phosphorus compounds in a model training water body through a near infrared photometer to form a training sample of a P prediction model;
acquiring spectrum data of a potassium compound in a model training water body through a visible light photometer to form a training sample of a K prediction model;
after preprocessing a training sample, training a fertility prediction model by using the training sample to obtain a trained N prediction model, a trained P prediction model and a trained K prediction model;
carrying out spectrum scanning on a water body sample by an ultraviolet-visible spectrophotometer to obtain spectrum data, preprocessing the spectrum data, inputting the preprocessed spectrum data into an N prediction model, and judging whether nitrogen reaches the standard or not by the N prediction model;
carrying out spectrum scanning on a water body sample by a near infrared photometer to obtain spectrum data, preprocessing the spectrum data, inputting the preprocessed spectrum data into a P prediction model, and judging whether phosphorus reaches the standard or not by the P prediction model;
carrying out spectrum scanning on a water body sample through a visible light photometer to obtain spectrum data, preprocessing the spectrum data, inputting the preprocessed spectrum data into a K prediction model, and judging whether potassium meets the standard or not by the K prediction model;
if the nitrogen, the phosphorus and the potassium reach the standard, judging that the paddy field fertility is up to the standard as a whole, and if any one of the nitrogen, the phosphorus and the potassium does not reach the standard, judging that the paddy field fertility is not up to the standard.
Specifically, the preparation method of the model training water body comprises the following steps:
setting concentration gradients of nitrate ions, nitrite ions, monohydrogen phosphate, dihydrogen phosphate and potassium ions;
preparing single-component standard solution according to concentration gradient, and obtaining the light absorption characteristics of each ion through an ultraviolet-visible spectrophotometer, a near infrared spectrophotometer and a visible spectrophotometer;
preparing a plurality of multi-component mixed liquids according to an orthogonal test design, and taking the multi-component mixed liquids as a model training water body;
preparing a plurality of multi-component mixed liquids with different concentration ratios of ions in the model training water body, and taking the multi-component mixed liquids as model testing water bodies.
Optionally, the method for preprocessing the optical data comprises:
decomposing spectral data into wavelet coefficients of different scales and locationsWherein->Is wavelet coefficient +.>For the scale factor>For the scale level, ->For displacement (I)>Is a wavelet basis function +.>As a basis function of scale>For raw spectral data, +.>Indicate wavelength, & lt + & gt>Is the coarsest scale level;
thresholding the wavelet coefficients to obtain processed wavelet coefficientsWherein->Is a threshold value;
threshold processing is carried out on the scale coefficient to obtain the processed scale coefficientWherein->For the scale hierarchy->A threshold value of (2);
obtaining reconstructed spectral data。
Specifically, the method for training the fertility prediction model comprises the following steps:
selecting a kernel function of the support vector machine;
determining a minimization optimization problem of a support vector machine:，/>，/>，wherein->Is the normal vector of the hyperplane, +.>For the offset +.>Is a penalty parameter->For relaxation variable, ++>The data points are indexed by the index,total number of data points;
optimizing the core parameters and the penalty parameters, and determining the optimal core parameters and penalty parameters;
determining a decision functionWherein->And->Is Lagrangian multiplier +.>For inputting data +.>Is a kernel function.
Optionally, the method for optimizing the core parameter and the penalty parameter includes:
population initialization, randomly and uniformly generating in solution spaceThe individual is used as a 0 th generation population, wherein each individual contains 2 variables, and the 2 variables are respectively a kernel parameter and a penalty parameter;
variation, at the firstIn several iterations, 3 individuals are randomly selected from the population +.>、/>、/>And (2) andand variation->，/>Wherein,is a differential vector +.>Is a variant scaling factor;
cross atInterval production +.>Random numbers and cross +.>Wherein->Is a crossover probability factor;
select, pairOr->Selecting->，Is a fitness function;
setting iteration termination conditions, if the iteration termination conditions are reached, thenAs the optimal solution output, obtaining the optimal kernel parameter and multiplication parameter; if the termination condition is not reached, the iteration is performed again from the mutation step.
Optionally, the adjustment method of the variant scaling factor is as follows:wherein->For maximum number of iterations +.>For the current iteration number>Is the%>Fitness value of individual->For the average fitness value of the population, +.>Is the maximum variant contraction factor->Is the minimum variant shrinkage factor;
the adjustment method of the cross probability factor comprises the following steps:wherein->Is the maximum crossover probability factor, +.>For the initial crossover probability factor, +.>To adjust the speed control parameters.
In a second aspect, a paddy field fertility detection terminal based on a support vector machine includes a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the method as described above when executing the computer program.
In a third aspect, a computer program product comprising a computer program/instruction which, when executed by a processor, implements the steps of the method as described above.
In a fourth aspect, a water and fertilizer integrated planting method for shallow-wet irrigation of rice is based on the paddy field fertility detection method based on the support vector machine, and the planting method comprises the following steps:
firstly, enabling a paddy field to be in a thin water layer state, acquiring water body samples at a plurality of points of the paddy field, detecting the fertility of the water body samples through the paddy field fertility detection method, judging whether the nutrition components in the water body reach standards, if not, applying corresponding fertilizers, and waiting for a period of time to be detected again;
secondly, transplanting seedlings to a paddy field if the nutritional ingredients in the water body reach the standards, and keeping the paddy field in a shallow water layer state;
thirdly, judging whether the paddy rice completes the turning green period, if so, setting humidity detection points at a plurality of points of the paddy field, detecting the soil humidity of the paddy field, judging whether the soil humidity of the paddy field is higher than a lower limit value, and if so, carrying out thin water irrigation;
fourthly, judging whether the rice reaches the later tillering stage, and if so, removing the humidity detection point;
fifthly, judging whether the rice reaches the jointing booting stage, if so, enabling the paddy field to be in a thin water layer state, acquiring water body samples at a plurality of points of the paddy field, detecting the fertility of the water body samples by the paddy field fertility detection method, judging whether the nutrition components in the water body reach the standards, and if not, applying corresponding fertilizers;
step six, judging whether the paddy rice reaches the milk ripening period, if so, setting humidity detection points at a plurality of points of the paddy field, detecting the soil humidity of the paddy field, judging whether the soil humidity of the paddy field is higher than a lower limit value, and if so, carrying out thin water irrigation;
and seventh, judging whether the rice reaches the yellow ripe stage, if so, removing the humidity detection point and naturally drying the paddy field.
Optionally, the depth of the thin water layer in the first step is 10-30 mm, the depth of the shallow water layer in the second step is 10-50 mm, the depth of the water layer in the third step is 0-40 mm, the water layer in the fourth step is not present, and the depth of the thin water layer in the fifth step is 0-20 mm.
Compared with the prior art, the invention has the following advantages and beneficial effects:
the invention establishes a fertility prediction model based on a support vector machine, wherein the model is divided into three predictor models of nitrogen (N), phosphorus (P) and potassium (K), and spectrum data of nitrogen, phosphorus and potassium compounds in a water body are respectively obtained through different types of spectrum instruments, and training samples of the respective prediction models are formed and used for training the fertility prediction model. In actual detection, spectral data of a water body sample is obtained through a corresponding spectral instrument, and is input into a corresponding prediction model after being preprocessed, so that whether each element meets the standards is judged. Finally, comprehensively evaluating whether the fertility of the paddy field meets the standard according to the detection results of nitrogen, phosphorus and potassium.
By introducing a support vector machine algorithm, the problems of high-dimensional, nonlinear and small sample data can be effectively solved, so that the accuracy and stability of paddy field fertility detection are improved under a complex background. Compared with the traditional chemical analysis method, the method can obtain the detection result more quickly and remarkably improves the detection efficiency.
By means of the spectrum technology, the invention can realize rapid and nondestructive field detection, the portability of spectrum equipment can enable field sampling and data acquisition to be faster, and scientific basis is provided for agricultural production in time.
Noise and other disturbances can be effectively reduced by performing effective preprocessing, such as wavelet transformation and thresholding, on the spectral data, thereby improving the predictive power of the model. In addition, the kernel parameters and the penalty parameters of the SVM are optimized through a differential evolution algorithm, so that the prediction precision and the generalization capability of the model can be further improved.
According to the invention, through real-time monitoring and accurate control of the water body fertilizer soil and the soil humidity, the water and nutrition supply of each stage of rice growth is accurately controlled, the consumption of water resources and chemical fertilizers is effectively reduced, the overall growth state of the rice is improved, and scientific planting is realized and the sustainable development of agriculture is promoted.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the principles of the invention.
Fig. 1 is a flow chart of a paddy field fertility detection method based on a support vector machine according to the invention.
Fig. 2 is a schematic flow chart of a water and fertilizer integrated planting method for shallow-wet irrigation of rice according to the invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and embodiments, for the purpose of making the objects, technical solutions and advantages of the present invention more apparent. It is to be understood that the specific embodiments described herein are merely illustrative of the substances, and not restrictive of the invention.
It should be further noted that, for convenience of description, only the portions related to the present invention are shown in the drawings.
Embodiments of the present invention and features of the embodiments may be combined with each other without conflict. The present invention will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Example 1
As shown in fig. 1, this embodiment provides a paddy field fertility detection method based on a support vector machine, including:
constructing a fertility prediction model based on a support vector machine, wherein the fertility prediction model comprises an N prediction model, a P prediction model and a K prediction model; the Support Vector Machine (SVM) is a supervised learning algorithm and is widely applied to classification and regression analysis. By constructing one or more hyperplanes in a high-dimensional space to distinguish different categories or predictive values, the optimization objective is to maximize the minimum distance between the hyperplane and any sample, thereby providing good generalization capability, a composite predictive model is created in this step consisting of three sub-models corresponding to three key fertilizer components: nitrogen (N), phosphorus (P) and potassium (K).
Acquiring spectrum data of nitrogen compounds in the model training water body through an ultraviolet-visible spectrophotometer to form a training sample of an N prediction model;
acquiring spectral data of phosphorus compounds in a model training water body through a near infrared photometer to form a training sample of a P prediction model;
acquiring spectrum data of a potassium compound in a model training water body through a visible light photometer to form a training sample of a K prediction model;
after preprocessing a training sample, training a fertility prediction model by using the training sample to obtain a trained N prediction model, a trained P prediction model and a trained K prediction model; and training a fertility prediction model by utilizing the preprocessed spectrum data. At this stage, the SVM algorithm will learn and build a model from the input training samples to enable accurate fertility predictions for the new sample data.
Carrying out spectrum scanning on a water body sample by an ultraviolet-visible spectrophotometer to obtain spectrum data, preprocessing the spectrum data, inputting the preprocessed spectrum data into an N prediction model, and judging whether nitrogen reaches the standard or not by the N prediction model;
carrying out spectrum scanning on a water body sample by a near infrared photometer to obtain spectrum data, preprocessing the spectrum data, inputting the preprocessed spectrum data into a P prediction model, and judging whether phosphorus reaches the standard or not by the P prediction model;
carrying out spectrum scanning on a water body sample through a visible light photometer to obtain spectrum data, preprocessing the spectrum data, inputting the preprocessed spectrum data into a K prediction model, and judging whether potassium meets the standard or not by the K prediction model;
if the nitrogen, the phosphorus and the potassium reach the standard, judging that the paddy field fertility is up to the standard as a whole, and if any one of the nitrogen, the phosphorus and the potassium does not reach the standard, judging that the paddy field fertility is not up to the standard. And comprehensively judging the fertility of the paddy field according to the results of the N prediction model, the P prediction model and the K prediction model. If the contents of the nitrogen, the phosphorus and the potassium all reach the established standard, judging that the fertility of the paddy field reaches the standard; and if the content of any element does not reach the standard, judging that the fertility of the paddy field does not reach the standard.
In this example, three different photometers were used to obtain samples of the concentrations of nitrogen (N), phosphorus (P) and potassium (K) for various scientific and technical considerations, with the aim of ensuring the accuracy and efficiency of the measurements. And the spectral interference among different elements can be reduced by using a special photometer. Different elements may exhibit absorption over the same wavelength range, and the optimal wavelength range may be selected using a specialized photometer to minimize the effect of other elements on the measured element concentration determination.
The three elements of nitrogen, phosphorus and potassium have unique spectral characteristics in different wavelength ranges. For example, certain compounds may have strong absorption in the ultraviolet region and weak absorption in the visible or near infrared region. Thus, the concentration of a particular element can be measured more accurately using a photometer specifically designed for the spectral characteristics of each element.
The ultraviolet-visible spectrophotometer is suitable for measuring nitrogen compounds because such compounds have a distinct absorption peak in the ultraviolet-visible region. Near infrared photometers are suitable for measuring phosphorus compounds, whose spectral characteristics in the near infrared region can provide information about the molecular structure. The visible light photometer is then adapted to measure potassium compounds which have specific absorption characteristics in the visible light region.
Example two
The present example provides a method of preparing a model training body of water for use in example one.
Setting concentration gradients of nitrate ions, nitrite ions, monohydrogen phosphate, dihydrogen phosphate and potassium ions; concentration gradients, i.e. sequences of different concentration levels, are used to cover various possible concentration situations in model training, improving the applicability and accuracy of the model.
Preparing single-component standard solution according to concentration gradient, obtaining light absorption characteristics of each ion through an ultraviolet-visible spectrophotometer, a near infrared spectrophotometer and a visible spectrophotometer, and establishing an accurate spectrum-concentration corresponding relation for each ion.
Preparing a plurality of multi-component mixed liquids according to an orthogonal test design, and taking the multi-component mixed liquids as a model training water body; the orthogonal test design is a scientific test design method, and can obtain systematic and comprehensive data information in the minimum test times. And preparing a multi-component mixed solution containing different concentration combinations by using an orthogonal test design method, wherein the mixed solution simulates various combination states possibly existing in various ions in an actual water body sample.
Preparing a plurality of multi-component mixed liquids with different concentration ratios of ions in the model training water body, taking the multi-component mixed liquids as a model test water body, and verifying the prediction accuracy and generalization capability of the model by using the test water body.
Example III
The spectrum data preprocessing method in the embodiment uses wavelet transformation and threshold processing technology to improve the quality and the analysis accuracy of spectrum data, and the spectrum data preprocessing method comprises the following steps:
decomposing spectral data into wavelet coefficients of different scales and locations。
Wherein,the wavelet coefficients reflect the detail information of the signal in the scale and the position; />As scale factors, representing approximate information of the signal at the coarsest scale level; />For the scale level, ->Is displacement; />Is a wavelet basis function +.>Is a scale base function and is used for constructing the representation of the signal at different scales and positions; />For raw spectral data, +.>Indicate wavelength, & lt + & gt>Is the coarsest scale level; wavelet transformation is a technique that enables analysis of signals at multiple scales, where the signal is decomposed by wavelet basis functions to obtain details of the signal at different scales and locations.
Thresholding the wavelet coefficients to obtain processed wavelet coefficientsWherein->Is a threshold value, and is used for controlling the denoising intensity.
Threshold processing is carried out on the scale coefficient to obtain the processed scale coefficientWherein->For the scale hierarchy->Is used to adjust the denoising strength of the coarsest scale level.
After finishing the threshold processing of the wavelet coefficients and the scale coefficients, the processed coefficients need to be reconstructed, and the signals are reconstructed according to the inverse operation of wavelet transformation to obtain the denoised spectrum data, namely the reconstructed spectrum data is obtained。
The embodiment can effectively remove noise from the original spectrum data and improve the signal-to-noise ratio of the data, thereby providing more accurate and reliable input data for a subsequent fertility prediction model. The multi-scale analysis capability of wavelet transformation and the denoising capability of thresholding together make this preprocessing method excellent in processing complex spectral data.
Example IV
The method for training the fertility prediction model comprises the following steps:
selecting a kernel function of the support vector machine; the kernel function is used to map input data to a high-dimensional space such that data that is linearly inseparable in the original space is separable in the high-dimensional space. Common kernel functions include linear kernels, polynomial kernels, radial Basis Function (RBF) kernels, and the like.
The goal of the SVM is to find an optimal hyperplane so that the different classes of data are separated correctly and maximally at intervals, and this goal is achieved by solving a minimization optimization problem, i.e. determining the minimization optimization problem of the support vector machine:，/>，/>，/>wherein->The direction of the hyperplane is determined as the normal vector of the hyperplane; />For the offset, determining the distance between the hyperplane and the origin; />Is a penalty parameter for balancing interval size and classification errors; />To relax the variables, allowing some data points to violate interval boundaries to some extent; />Is data ofPoint index->Total number of data points;
the nuclear parameters and the punishment parameters have obvious influence on the performance of the model, and the accuracy and generalization capability of the model can be improved by selecting proper parameters, so that the nuclear parameters and the punishment parameters need to be optimized, and the optimal nuclear parameters and punishment parameters are determined;
determining a decision function for predicting a class of new data pointsWherein->And->Is Lagrangian multiplier +.>For inputting data +.>Is a kernel function. The lagrangian multiplier represents the importance of each training data point in constructing the optimal classification boundary, and only the lagrangian multipliers of the support vectors (i.e., the data points closest to the separation hyperplane) are non-zero, they contribute to the decision function.
In model training, the method for optimizing the core parameters and the penalty parameters comprises the following steps:
population initialization, randomly and uniformly generating in solution spaceThe individual is used as a 0 th generation population, wherein each individual contains 2 variables, and the 2 variables are respectively a kernel parameter and a penalty parameter; i.e. at the beginning of the parameter optimization, a population needs to be initialized first. A population consists of a plurality of individuals, each individual representing a set of possible solutions, i.e. a set of kernel parameters and penalty parameters.
Variation, variation is differentialThe main way to introduce new solutions in evolutionary algorithms. In the first placeIn several iterations, 3 individuals are randomly selected from the population +.>、/>、/>And->And then makes a variation，/>Wherein (1)>Is a differential vector +.>For varying the scaling factor, a step size for controlling the variation.
Crossover, the crossover operation is used to increase diversity of the population. At the position ofInterval production +.>Random numbers and cross +.>Wherein->Is a crossover probability factor.
Selecting, the selection operation determines which individuals are to be retained to the next generationIn the population. For a pair ofOr->Selecting->，/>As a fitness function. If the fitness of the test individual is better than or equal to the fitness of the target individual, the test individual is selected for the next generation. Otherwise, the target individual is retained.
Setting iteration termination conditions, if the iteration termination conditions are reached, thenAs the optimal solution output, obtaining the optimal kernel parameter and multiplication parameter; if the termination condition is not reached, the iteration is performed again from the mutation step. The termination condition may be that a maximum number of iterations is reached, the fitness reaches a certain threshold, etc. Once the termination condition is reached, the algorithm stops and the parameters of the individuals with the highest fitness in the current population are considered as the optimal solution, i.e. the optimal kernel parameters and penalty parameters.
In addition, a reasonable adjustment of the variant scaling factor and the crossover probability factor can find a good balance between exploration (global search) and development (local search), thereby improving the ability of the algorithm to find the optimal solution.
The adjustment method of the variation scaling factor comprises the following steps:wherein->For maximum number of iterations +.>For the current iteration number>Is the%>Fitness value of individual->For the average fitness value of the population, +.>Is the maximum variant contraction factor->Is the minimum variant shrinkage factor.
The adjustment method dynamically adjusts the variation scaling factor based on the condition that the fitness value of the individual in the population is relative to the average fitness value of the population, when the fitness value of the individualLess than or equal to the population average fitness value +.>When this is the case, the individual's performance is shown to be better. At this time, in order to develop the surrounding solution space carefully, the algorithm is run by reducing +.>To reduce the variation step size.
When the fitness value of an individualIs greater than the average fitness value of the population +.>Indicating that the individual is relatively poor performing. At this time, in order to enhance global search capability, the algorithm is implemented by adding +.>To increase the variation step size.
Adjustment of crossover probability factorsThe method comprises the following steps:wherein->Is the maximum crossover probability factor, +.>For the initial crossover probability factor, +.>To adjust the speed control parameters.
The crossover probability factor determines the exchange degree of parameters between the variant individual and the target individual, and the adjustment method is that the parameters gradually decrease along with the progress of iterationThereby emphasizing global searches at an early stage of the algorithm and local searches at a later stage of the algorithm.
Example five
A paddy field fertility detection terminal based on a support vector machine, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the method as described above when executing the computer program.
The memory may be used to store software programs and modules, and the processor executes various functional applications of the terminal and data processing by running the software programs and modules stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an execution program required for at least one function, and the like.
The storage data area may store data created according to the use of the terminal, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device.
A computer program product comprising computer programs/instructions which when executed by a processor implement the steps of the method as described above.
The computer program product comprises a computer program or set of instructions for performing specific tasks or implementing specific functions. These programs or instructions are designed to be executed by a processor to implement a series of predefined steps or operations. The program product may be stored on various forms of computer storage media, such as memory, hard disk, solid state drive, optical disk, or other forms of digital storage devices. Either in the form of compiled binary code or in the form of scripts or bytecodes that can be executed by an interpreter. The program product enables the processor to process data in a specific order and manner through well-designed algorithms and logic instructions to perform various functions such as data analysis, user interaction, device control, etc.
Example six
As shown in fig. 2, the integrated planting method for shallow-wet irrigation and water and fertilizer of rice is based on the paddy field fertility detection method based on the support vector machine, and the main technical points of the planting method are as follows: thin water transplanting, shallow water turning green, water storage and moisture preservation at the early tillering stage, field sunning at the later tillering stage, thin water recharging at the jointing booting stage, thin water keeping at the heading and flowering stage, wet milk ripening and dry yellow ripening stage. The paddy rice 'shallow wet' irrigation technology is summarized in the whole growth period: "thin, shallow, accumulating, sunning, wet" irrigation.
The method specifically comprises the following steps:
the first step, the paddy field is in a thin water layer state, water samples are obtained at a plurality of points of the paddy field, the fertility detection is carried out on the water samples through the paddy field fertility detection method, whether the nutrition components in the water reach standards is judged, if the nutrition components do not reach the standards, corresponding fertilizers are applied, and the water samples are re-detected after waiting for a period of time. In the rice transplanting period, a water layer of about 10-30 mm is ensured in a paddy field Bao Shuiceng, rice seedling reviving is promoted in the period, a rice base fertilizer is applied, the nutrition components of water bodies in the paddy field are ensured, and a period of time of soaking in the paddy field is ensured.
Secondly, transplanting seedlings to a paddy field if the nutritional ingredients in the water body reach the standards, and keeping the paddy field in a shallow water layer state; and in the returning period of the rice, a shallow water layer of 10-50 mm of the field is ensured, and the growth of seedlings is promoted.
Thirdly, judging whether the paddy rice completes the turning green period, if so, setting humidity detection points at a plurality of points of the paddy field, detecting the soil humidity of the paddy field, judging whether the soil humidity of the paddy field is higher than a lower limit value, and if so, carrying out thin water irrigation; and (3) in the early stage of rice tillering, performing field wetting management, namely, watering for about 5 days, controlling a field aquifer to be 0-40 mm, and keeping the field soil moisture in a saturated state.
Fourthly, judging whether the rice reaches the later tillering stage, and if so, removing the humidity detection point; at the later stage of tillering, the tillering number of the rice reaches 25-30 tillers, at the moment, ineffective tillering of the rice is controlled, effective tillering is consolidated, the rice is lightly sunned to a field crack, and the color of leaves is faded.
Fifthly, judging whether the rice reaches the jointing booting stage, if so, enabling the paddy field to be in a thin water layer state, acquiring water body samples at a plurality of points of the paddy field, detecting the fertility of the water body samples by the paddy field fertility detection method, judging whether the nutrition components in the water body reach the standards, and if not, applying corresponding fertilizers; after the tillering stage is finished, the rice enters a jointing stage, nitrogen fertilizer is applied at the end of the jointing stage (nitrogen content is increased), thin water irrigation (0-20 mm) is carried out in the jointing booting stage, and the water layer in the field naturally falls to dryness and is irrigated again.
Step six, judging whether the paddy rice reaches the milk ripening period, if so, setting humidity detection points at a plurality of points of the paddy field, detecting the soil humidity of the paddy field, judging whether the soil humidity of the paddy field is higher than a lower limit value, and if so, carrying out thin water irrigation; when the rice enters the heading and flowering period, thin water is kept, and when the rice enters the lactation period, soil is kept moist, and a water layer is controlled to be 0-20 mm.
And seventh, judging whether the rice reaches the yellow ripe stage, if so, removing the humidity detection point and naturally drying the paddy field.
The depth of the thin water layer in the first step is 10-30 mm, the depth of the shallow water layer in the second step is 10-50 mm, the depth of the water layer in the third step is 0-40 mm, the water layer in the fourth step is not present, and the depth of the thin water layer in the fifth step is 0-20 mm.
The irrigation rate of shallow irrigation is reduced by 10-30% compared with shallow irrigation and deep irrigation, and the rice yield is improved by 7.5-25%. Shallow irrigation, i.e. shallow irrigation combined with wetting.
In the description of the present specification, reference to the terms "one embodiment/manner," "some embodiments/manner," "example," "specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment/manner or example is included in at least one embodiment/manner or example of the present application. In this specification, the schematic representations of the above terms are not necessarily for the same embodiment/manner or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments/modes or examples. Furthermore, the various embodiments/modes or examples described in this specification and the features of the various embodiments/modes or examples can be combined and combined by persons skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "plurality" is at least two, such as two, three, etc., unless explicitly defined otherwise.
It will be appreciated by persons skilled in the art that the above embodiments are provided for clarity of illustration only and are not intended to limit the scope of the invention. Other variations or modifications of the above-described invention will be apparent to those of skill in the art, and are still within the scope of the invention.
Claims (10)
1. The paddy field fertility detection method based on the support vector machine is characterized by comprising the following steps of:
constructing a fertility prediction model based on a support vector machine, wherein the fertility prediction model comprises an N prediction model, a P prediction model and a K prediction model;
acquiring spectrum data of nitrogen compounds in the model training water body through an ultraviolet-visible spectrophotometer to form a training sample of an N prediction model;
acquiring spectral data of phosphorus compounds in a model training water body through a near infrared photometer to form a training sample of a P prediction model;
acquiring spectrum data of a potassium compound in a model training water body through a visible light photometer to form a training sample of a K prediction model;
after preprocessing a training sample, training a fertility prediction model by using the training sample to obtain a trained N prediction model, a trained P prediction model and a trained K prediction model;
carrying out spectrum scanning on a water body sample by an ultraviolet-visible spectrophotometer to obtain spectrum data, preprocessing the spectrum data, inputting the preprocessed spectrum data into an N prediction model, and judging whether nitrogen reaches the standard or not by the N prediction model;
carrying out spectrum scanning on a water body sample by a near infrared photometer to obtain spectrum data, preprocessing the spectrum data, inputting the preprocessed spectrum data into a P prediction model, and judging whether phosphorus reaches the standard or not by the P prediction model;
carrying out spectrum scanning on a water body sample through a visible light photometer to obtain spectrum data, preprocessing the spectrum data, inputting the preprocessed spectrum data into a K prediction model, and judging whether potassium meets the standard or not by the K prediction model;
if the nitrogen, the phosphorus and the potassium reach the standard, judging that the paddy field fertility is up to the standard as a whole, and if any one of the nitrogen, the phosphorus and the potassium does not reach the standard, judging that the paddy field fertility is not up to the standard.
2. The method for detecting the fertility of a paddy field based on a support vector machine according to claim 1, wherein the method for preparing the model training water body comprises the following steps:
setting concentration gradients of nitrate ions, nitrite ions, monohydrogen phosphate, dihydrogen phosphate and potassium ions;
preparing single-component standard solution according to concentration gradient, and obtaining the light absorption characteristics of each ion through an ultraviolet-visible spectrophotometer, a near infrared spectrophotometer and a visible spectrophotometer;
preparing a plurality of multi-component mixed liquids according to an orthogonal test design, and taking the multi-component mixed liquids as a model training water body;
preparing a plurality of multi-component mixed liquids with different concentration ratios of ions in the model training water body, and taking the multi-component mixed liquids as model testing water bodies.
3. The method for detecting fertility in paddy fields based on a support vector machine according to claim 2, wherein the method for preprocessing the optical data comprises:
decomposing spectral data into wavelet coefficients of different scales and locationsWherein->Is wavelet coefficient +.>For the scale factor>For the scale level, ->For displacement (I)>Is a wavelet basis function +.>As a basis function of scale>For raw spectral data, +.>Indicate wavelength, & lt + & gt>Is the coarsest scale level;
thresholding the wavelet coefficients to obtain processed wavelet coefficientsWherein->Is a threshold value;
threshold processing is carried out on the scale coefficient to obtain the processed scale coefficientWherein->For the scale hierarchy->A threshold value of (2);
obtaining reconstructed spectral data。
4. The method for detecting fertility of paddy fields based on a support vector machine according to claim 1, wherein the method for training the fertility prediction model comprises the steps of:
selecting a kernel function of the support vector machine;
determining a minimization optimization problem of a support vector machine:，/>，/>，wherein->Is the normal vector of the hyperplane, +.>For the offset +.>Is a penalty parameter->For relaxation variable, ++>The data points are indexed by the index,total number of data points;
optimizing the core parameters and the penalty parameters, and determining the optimal core parameters and penalty parameters;
determining a decision functionWherein->And->Is Lagrangian multiplier +.>For inputting data +.>Is a kernel function.
5. The method for detecting fertility in paddy fields based on a support vector machine according to claim 4, wherein the method for optimizing the kernel parameter and the penalty parameter comprises:
population initialization, randomly and uniformly generating in solution spaceThe individual is used as a 0 th generation population, wherein each individual contains 2 variables, and the 2 variables are respectively a kernel parameter and a penalty parameter;
variation, at the firstIn several iterations, 3 individuals are randomly selected from the population +.>、/>、/>And->And variation->，/>Wherein->Is a differential vector +.>Is a variant scaling factor;
cross atInterval production +.>Random numbers and cross +.>Wherein->Is a crossover probability factor;
select, pairOr->Selecting->，/>Is a fitness function;
setting iteration termination conditions, if the iteration termination conditions are reached, thenAs the optimal solution output, obtaining the optimal kernel parameter and multiplication parameter; if the termination condition is not reached, the iteration is performed again from the mutation step.
6. The method for detecting fertility in paddy fields based on a support vector machine according to claim 5, wherein the method for adjusting the variable scaling factor is as follows:wherein->For maximum number of iterations +.>For the current iteration number>Is the%>Fitness value of individual->For the average fitness value of the population, +.>Is the maximum variant contraction factor->Is the minimum variant shrinkage factor;
the adjustment method of the cross probability factor comprises the following steps:wherein->Is the maximum crossover probability factor, +.>For the initial crossover probability factor, +.>To adjust the speed control parameters.
7. A paddy field fertility detection terminal based on a support vector machine, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the method according to any one of claims 1-6 when executing the computer program.
8. A computer program product comprising computer programs/instructions which, when executed by a processor, implement the steps of the method of any of claims 1-4.
9. A paddy rice shallow-wet irrigation water-fertilizer integrated planting method, which is characterized in that the paddy field fertility detection method based on a support vector machine according to any one of claims 1-6 is adopted, and the planting method comprises the following steps:
firstly, enabling a paddy field to be in a thin water layer state, acquiring water body samples at a plurality of points of the paddy field, detecting the fertility of the water body samples by the paddy field fertility detection method according to any one of claims 1-6, judging whether the nutritional ingredients in the water body reach standards, if not, applying corresponding fertilizers, waiting for a period of time, and re-detecting;
secondly, transplanting seedlings to a paddy field if the nutritional ingredients in the water body reach the standards, and keeping the paddy field in a shallow water layer state;
thirdly, judging whether the paddy rice completes the turning green period, if so, setting humidity detection points at a plurality of points of the paddy field, detecting the soil humidity of the paddy field, judging whether the soil humidity of the paddy field is higher than a lower limit value, and if so, carrying out thin water irrigation;
fourthly, judging whether the rice reaches the later tillering stage, and if so, removing the humidity detection point;
fifthly, judging whether the rice reaches the jointing booting stage, if so, enabling the paddy field to be in a thin water layer state, acquiring water body samples at a plurality of points of the paddy field, detecting the fertility of the water body samples by the paddy field fertility detection method according to any one of claims 1-6, judging whether the nutritional ingredients in the water body reach the standards, and if not, applying corresponding fertilizers;
step six, judging whether the paddy rice reaches the milk ripening period, if so, setting humidity detection points at a plurality of points of the paddy field, detecting the soil humidity of the paddy field, judging whether the soil humidity of the paddy field is higher than a lower limit value, and if so, carrying out thin water irrigation;
and seventh, judging whether the rice reaches the yellow ripe stage, if so, removing the humidity detection point and naturally drying the paddy field.
10. The integrated planting method for shallow-wet irrigation and water and fertilizer for rice according to claim 9, wherein the depth of the thin water layer in the first step is 10-30 mm, the depth of the thin water layer in the second step is 10-50 mm, the depth of the water layer in the third step is 0-40 mm, the fourth step is free of the water layer, and the depth of the thin water layer in the fifth step is 0-20 mm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410225743.2A CN117808173B (en) | 2024-02-29 | 2024-02-29 | Paddy field fertility detection method, related product and planting method based on related product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410225743.2A CN117808173B (en) | 2024-02-29 | 2024-02-29 | Paddy field fertility detection method, related product and planting method based on related product |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117808173A true CN117808173A (en) | 2024-04-02 |
| CN117808173B CN117808173B (en) | 2024-04-30 |
Family
ID=90431967
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410225743.2A Active CN117808173B (en) | 2024-02-29 | 2024-02-29 | Paddy field fertility detection method, related product and planting method based on related product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117808173B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160044790A (en) * | 2014-10-16 | 2016-04-26 | 한국수자원공사 | Group management method for hydraulic and water quality model, and recording medium storing program for executing the same, and recording medium storing program for executing the same |
| CN112417655A (en) * | 2020-11-05 | 2021-02-26 | 天津市农业质量标准与检测技术研究所 | Method for establishing farmland soil organic matter prediction model |
| CN113295635A (en) * | 2021-05-27 | 2021-08-24 | 河北先河环保科技股份有限公司 | Water pollution alarm method based on dynamic update data set |
| CN113310909A (en) * | 2021-05-14 | 2021-08-27 | 山东深蓝智谱数字科技有限公司 | Hyperspectrum-based water quality determination method and device |
| CN113916847A (en) * | 2021-07-20 | 2022-01-11 | 江苏省扬州环境监测中心 | Water quality detection method based on spectrum technology and linear support vector algorithm |
| CN114486764A (en) * | 2022-01-26 | 2022-05-13 | 安徽新宇环保科技股份有限公司 | Agricultural non-point source pollution monitoring system based on full-spectrum water quality analyzer |
| US20220397523A1 (en) * | 2021-06-04 | 2022-12-15 | Wisconsin Alumni Research Foundation | Rapid estimation of a soil-water retention curve using visible-near infrared spectroscopy |
| WO2023024463A1 (en) * | 2021-12-30 | 2023-03-02 | 南京大学 | Intelligent tracing method and system for organic pollution of water body |
| CN116385819A (en) * | 2023-02-23 | 2023-07-04 | 广东省科学院广州地理研究所 | Water quality evaluation method, device and equipment based on neural network model |
-
2024
- 2024-02-29 CN CN202410225743.2A patent/CN117808173B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160044790A (en) * | 2014-10-16 | 2016-04-26 | 한국수자원공사 | Group management method for hydraulic and water quality model, and recording medium storing program for executing the same, and recording medium storing program for executing the same |
| CN112417655A (en) * | 2020-11-05 | 2021-02-26 | 天津市农业质量标准与检测技术研究所 | Method for establishing farmland soil organic matter prediction model |
| CN113310909A (en) * | 2021-05-14 | 2021-08-27 | 山东深蓝智谱数字科技有限公司 | Hyperspectrum-based water quality determination method and device |
| CN113295635A (en) * | 2021-05-27 | 2021-08-24 | 河北先河环保科技股份有限公司 | Water pollution alarm method based on dynamic update data set |
| US20220397523A1 (en) * | 2021-06-04 | 2022-12-15 | Wisconsin Alumni Research Foundation | Rapid estimation of a soil-water retention curve using visible-near infrared spectroscopy |
| CN113916847A (en) * | 2021-07-20 | 2022-01-11 | 江苏省扬州环境监测中心 | Water quality detection method based on spectrum technology and linear support vector algorithm |
| WO2023024463A1 (en) * | 2021-12-30 | 2023-03-02 | 南京大学 | Intelligent tracing method and system for organic pollution of water body |
| CN114486764A (en) * | 2022-01-26 | 2022-05-13 | 安徽新宇环保科技股份有限公司 | Agricultural non-point source pollution monitoring system based on full-spectrum water quality analyzer |
| CN116385819A (en) * | 2023-02-23 | 2023-07-04 | 广东省科学院广州地理研究所 | Water quality evaluation method, device and equipment based on neural network model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117808173B (en) | 2024-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106124449B (en) | A kind of soil near-infrared spectrum analysis prediction technique based on depth learning technology | |
| CN108875913B (en) | Tricholoma matsutake rapid nondestructive testing system and method based on convolutional neural network | |
| CN101430276B (en) | Wavelength variable optimization method in spectrum analysis | |
| CN113049530B (en) | Single-seed corn seed moisture content detection method based on near-infrared hyperspectrum | |
| CN107271382A (en) | A kind of different growing rape leaf SPAD value remote sensing estimation methods | |
| CN110455722A (en) | Rubber tree blade phosphorus content EO-1 hyperion inversion method and system | |
| CN111855591A (en) | Rice overground part carbon-nitrogen ratio remote sensing inversion model and method | |
| Pang et al. | Hyperspectral imaging coupled with multivariate methods for seed vitality estimation and forecast for Quercus variabilis | |
| CN111855593A (en) | Remote sensing inversion model and method for starch content of rice leaf | |
| CN111289489A (en) | Raman spectrum-based microbial unicell growth detection method | |
| CN103278467A (en) | Rapid nondestructive high-accuracy method with for identifying abundance degree of nitrogen element in plant leaf | |
| CN107202784B (en) | Method for detecting process nodes in rice seed soaking and germination accelerating process | |
| CN115479902A (en) | Chlorophyll content determination model construction method based on wavelength and system thereof | |
| CN115063252A (en) | Crop fertilizer accurate application method and system based on neural network | |
| CN117808173B (en) | Paddy field fertility detection method, related product and planting method based on related product | |
| CN112651173B (en) | Agricultural product quality nondestructive testing method based on cross-domain spectral information and generalizable system | |
| Wang et al. | Predicting organic matter content, total nitrogen and ph value of lime concretion black soil based on visible and near infrared spectroscopy | |
| CN113049526B (en) | Corn seed moisture content determination method based on terahertz attenuated total reflection | |
| CN115561282A (en) | Detection method and system for heavy metal in underground water | |
| CN105954206B (en) | The measurement method and system of purple maize leaf anthocyanin content | |
| CN111521568B (en) | Soil water content prediction method based on spectrum angle | |
| CN115479903A (en) | Chlorophyll content measuring method and system based on wavelength | |
| Wu et al. | Nitrogen status assessment for multiple cultivars of strawberries using portable FT-NIR spectrometers combined with cultivar recognition and multivariate analysis | |
| CN112326619A (en) | Micro-fluidic pesticide residue detection method based on double-spectrum technology | |
| CN112525831A (en) | Remote sensing inversion model and method for protein nitrogen accumulation of rice overground part based on Catboost regression algorithm |
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 |