A Maize Yield Prediction Method Based on Artificial Neural Network

Abstract

The present invention discloses a method for predicting maize yield based on an artificial neural network. The method includes the following steps: obtaining the flowering period data, plant type trait data, and ear trait data of maize; constructing a maize yield prediction model based on the artificial neural network, using the flowering period data, plant type trait data, and ear trait data of maize to construct a training set and a test set, and using the training set and the test set to train and test the maize yield prediction model; obtaining the flowering period data, plant type trait data, and ear trait data of the maize to be measured, and obtaining the maize yield prediction result according to the tested maize yield prediction model and the flowering period data, plant type trait data, and ear trait data of the maize to be measured. The present invention takes into account the influence of multiple factors on maize yield and can make the finally obtained prediction result have higher accuracy.

Description

Technical Field

[0001] The present invention relates to the field of crop yield prediction, and particularly to a method for predicting maize yield based on an artificial neural network. Background Art

[0002] Crop yield prediction is one of the important contents of modern agricultural scientific research and an important basis for production guidance and agricultural decision-making. In previous production, maize yield prediction was mainly carried out manually by experienced experts in the industry. With the development of smart agriculture, more and more maize yield prediction models are currently applied to the field of crop yield prediction.

[0003] The current maize yield prediction method using a random forest model can predict maize yield to a certain extent. However, due to ignoring the influence of multiple factors on maize yield, the accuracy of the final prediction result still needs to be improved. Summary of the Invention

[0004] In view of the above deficiencies in the prior art, the present invention provides a method for predicting maize yield based on an artificial neural network.

[0005] In order to achieve the above invention object, the technical solution adopted by the present invention is as follows:

[0006] A method for predicting maize yield based on an artificial neural network, comprising the following steps:

[0007] S1. Obtain the flowering period data, plant type trait data, and ear trait data of maize;

[0008] S2. Construct a maize yield prediction model based on an artificial neural network, use the flowering period data, plant type trait data, and ear trait data of maize to construct a training set and a test set, and use the training set and the test set to train and test the maize yield prediction model;

[0009] S3. Obtain the flowering period data, plant type trait data, and ear trait data of the maize to be measured, and obtain the maize yield prediction result according to the tested maize yield prediction model and the flowering period data, plant type trait data, and ear trait data of the maize to be measured.

[0010] Further, in step S1, the flowering stage data of corn includes the tasseling stage, the pollen shedding stage, and the silking stage; the plant type trait data of corn includes plant height, ear height, number of leaves above the ear, length of the main axis of the male inflorescence, number of branches of the male inflorescence, length of the first leaf below the ear, width of the first leaf below the ear, length of the ear leaf, width of the ear leaf, length of the first leaf above the ear, length of the second leaf above the ear, length of the third leaf above the ear, width of the first leaf above the ear, width of the second leaf above the ear, width of the third leaf above the ear, included angle of the first leaf above the ear, included angle of the second leaf above the ear, included angle of the third leaf above the ear, length from the ear leaf to the highest point of the first leaf above the ear, length from the ear leaf to the highest point of the second leaf above the ear, length from the ear leaf to the highest point of the third leaf above the ear; the ear trait data of corn includes ear weight, ear length, ear diameter, number of rows of kernels, tip length, 100-kernel weight, and grain weight.

[0011] Further, the process of obtaining the flowering stage data of corn is as follows: collect the number of days from the sowing date to the date when the tips of the male inflorescences of more than half of the plants in the sowing area emerge from the top leaves to obtain the tasseling stage; collect the number of days from the sowing date to the date when the male inflorescences of more than half of the plants in the sowing area start to shed pollen to obtain the pollen shedding stage; collect the number of days from the sowing date to the date when the silks of more than half of the plants in the sowing area emerge from the bracts to obtain the silking stage.

[0012] Further, 10 days after the pollen shedding of corn ends, measure the length from the root of the plant on the ground surface to the top of the main axis of the male inflorescence to obtain the plant height, measure the length from the root of the plant on the ground surface to the first node where the ear is borne to obtain the ear height, measure all the leaves above the ear leaf to obtain the number of leaves above the ear, measure the distance from the highest branch of the male inflorescence to the top of the main axis to obtain the length of the main axis of the male inflorescence, measure all the first-order branches of the male inflorescence to obtain the number of branches of the male inflorescence, measure the ear leaf to obtain the length of the first leaf below the ear, measure the length from the auricle to the tip of the plant leaf to obtain the length of the first leaf above the ear, the length of the second leaf above the ear, and the length of the third leaf above the ear, measure the width at the widest part of the plant leaf to obtain the width of the first leaf above the ear, the width of the second leaf above the ear, and the width of the third leaf above the ear, measure the angle between the main vein of the plant leaf and the stem to obtain the included angle of the first leaf above the ear, the included angle of the second leaf above the ear, and the included angle of the third leaf above the ear, measure the length from the auricle of the plant leaf to the highest point of the leaf to obtain the length from the ear leaf to the highest point of the first leaf above the ear, the length from the ear leaf to the highest point of the second leaf above the ear, and the length from the ear leaf to the highest point of the third leaf above the ear; collect the ears at the late stage of the corn maturity period, dry the ears, and measure the dried ears to obtain the ear weight, ear length, ear diameter, number of rows of kernels, tip length, 100-kernel weight, and grain weight.

[0013] Further, in step S2, the corn yield prediction model includes an input layer, a hidden layer, and an output layer connected in sequence;

[0014] The input layer includes 31 input neurons; the input layer is used to input the flowering stage data, plant type trait data, and ear trait data of corn, and perform data processing on the flowering stage data, plant type trait data, and ear trait data of corn according to the first connection weight to output the first input variable to the hidden layer;

[0015] The hidden layer includes a set number of internal neurons; the hidden layer is used to process the first input variable according to a transfer function to output a second input variable to the output layer;

[0016] The output layer includes 1 output neuron; the output layer is used to process the second input variable according to the second connection weight to obtain the predicted maize yield result.

[0017] Furthermore, in the input layer, the flowering stage data, plant type trait data, and ear trait data of maize are processed according to the first connection weight to obtain the first input variable, expressed as:

[0018]

[0019] Where: is the first input variable obtained by the th internal neuron, is the serial number of the internal neuron, is the serial number of the input neuron, is the total number of input neurons, is the th input neuron and the th internal neuron's first connection weight, is the th input neuron's input, with the flowering stage data, plant type trait data, and ear trait data of maize as the input, is the th input neuron and the th internal neuron's bias.

[0020] Furthermore, in the hidden layer, the first input variable is processed according to the transfer function to obtain the second input variable, expressed as:

[0021]

[0022] Where: is the second input variable output by the th internal neuron, is the hyperbolic tangent function, is the th internal neuron's obtained first input variable.

[0023] Furthermore, in the output layer, the second input variable is processed according to the second connection weight to obtain the predicted maize yield result, expressed as:

[0024]

[0025] Where: is the predicted value of the maize ear weight, is the serial number of the internal neuron, is the number of internal neurons, is the second connection weight between the th internal neuron and the output neuron, is the second input variable output by the th internal neuron, is the bias between the th internal neuron and the output neuron.

[0026] Furthermore, the number of internal neurons is set to 32.

[0027] Furthermore, in step S2, a training set and a test set are constructed by using the flowering period data, plant type trait data, and ear trait data of corn. The specific process is as follows: the flowering period data, plant type trait data, and ear trait data of corn are classified according to phenotypic traits and sample labels, and the classified flowering period data, plant type trait data, and ear trait data of corn are randomly sampled according to a ratio of 7:3 as the training set and the test set respectively.

[0028] The present invention has the following beneficial effects:

[0029] (1) By obtaining the flowering period data, plant type trait data, and ear trait data of corn, constructing a corn yield prediction model based on an artificial neural network, and obtaining a corn yield prediction result according to the tested corn yield prediction model and the flowering period data, plant type trait data, and ear trait data of the corn to be measured, the present invention considers the influence of multiple factors on corn yield and can make the finally obtained prediction result more accurate;

[0030] (2) By setting the number of internal neurons in the hidden layer to 32, the present invention can avoid the overfitting phenomenon caused by overtraining of the corn yield prediction model on the basis of ensuring the prediction fitting degree, thereby enhancing the accuracy of the prediction result. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 is a schematic flow chart of a corn yield prediction method based on an artificial neural network. DETAILED DESCRIPTION OF THE INVENTION

[0032] The following describes the specific embodiments of the present invention to facilitate those skilled in the art to understand the present invention. However, it should be clear that the present invention is not limited to the scope of the specific embodiments. For those of ordinary skill in the art, as long as various changes are within the spirit and scope of the present invention defined and determined by the appended claims, these changes are obvious, and all inventions created using the concept of the present invention are within the scope of protection.

[0033] AsFigure 1 As shown in Figure 1 , a method for predicting corn yield based on an artificial neural network includes the following steps:

[0034] S1. Obtain the flowering period data, plant type traits data, and ear traits data of corn.

[0035] In an alternative embodiment of the present invention, the flowering period data of corn includes the tasseling stage, pollen shedding stage, and silking stage; the plant type traits data of corn includes plant height, ear height, number of leaves above the ear, length of the main axis of the male inflorescence, number of branches of the male inflorescence, length of the first leaf below the ear, width of the first leaf below the ear, length of the ear leaf, width of the ear leaf, length of the first leaf above the ear, length of the second leaf above the ear, length of the third leaf above the ear, width of the first leaf above the ear, width of the second leaf above the ear, width of the third leaf above the ear, included angle of the first leaf above the ear, included angle of the second leaf above the ear, included angle of the third leaf above the ear, length from the ear leaf auricle to the highest point of the first leaf above the ear, length from the ear leaf auricle to the highest point of the second leaf above the ear, length from the ear leaf auricle to the highest point of the third leaf above the ear; the ear traits data of corn includes ear weight, ear length, ear diameter, number of rows of kernels, number of kernels per row, tip elongation, 100-kernel weight, and grain weight.

[0036] The process of obtaining the flowering period data of corn in the present invention is as follows: collect the number of days from the sowing date to when the tips of the male inflorescences of more than half of the plants in the sowing area emerge from the top leaves to obtain the tasseling stage; collect the number of days from the sowing date to when the male inflorescences of more than half of the plants in the sowing area start to shed pollen to obtain the pollen shedding stage; collect the number of days from the sowing date to when the silk threads of more than half of the plants in the sowing area emerge from the bracts to obtain the silking stage.

[0037] The process of obtaining the plant type traits data and ear traits data of corn in the present invention is as follows: 10 days after the pollen shedding of corn ends, measure the length from the root of the plant on the ground surface to the top of the main axis of the male inflorescence to obtain the plant height, measure the length from the root of the plant on the ground surface to the first ear-bearing node to obtain the ear height, measure all the leaves above the ear leaf to obtain the number of leaves above the ear, measure the distance from the highest branch of the male inflorescence to the top of the main axis to obtain the length of the main axis of the male inflorescence, measure all the first-order branches of the male inflorescence to obtain the number of branches of the male inflorescence, measure the ear leaf to obtain the length of the first leaf below the ear, measure the length from the auricle to the tip of the leaf of the plant to obtain the length of the first leaf above the ear, the length of the second leaf above the ear, and the length of the third leaf above the ear, measure the width at the widest part of the leaf of the plant to obtain the width of the first leaf above the ear, the width of the second leaf above the ear, and the width of the third leaf above the ear, measure the angle between the main vein of the leaf of the plant and the stem to obtain the included angle of the first leaf above the ear, the included angle of the second leaf above the ear, and the included angle of the third leaf above the ear, measure the length from the auricle of the leaf of the plant to the highest point of the leaf to obtain the length from the auricle to the highest point of the first leaf above the ear, the length from the auricle to the highest point of the second leaf above the ear, and the length from the auricle to the highest point of the third leaf above the ear; at the later stage of the corn maturity period, harvest the ears, dry the ears, and measure the dried ears to obtain the ear weight, ear length, ear diameter, number of rows of kernels, number of kernels per row, tip elongation, 100-kernel weight, and grain weight.

[0038] S2. Construct a corn yield prediction model based on an artificial neural network, use the flowering period data, plant type traits data, and ear traits data of corn to construct a training set and a test set, and use the training set and the test set to train and test the corn yield prediction model.

[0039] In an alternative embodiment of the present invention, a maize yield prediction model is constructed with the flowering period, plant type, and ear traits of maize as inputs and the ear weight as the output. The maize yield prediction model includes an input layer, a hidden layer, and an output layer connected in sequence.

[0040] The input layer includes 31 input neurons; the input layer is used to input the flowering period data, plant type trait data, and ear trait data of maize, and perform data processing on the flowering period data, plant type trait data, and ear trait data of maize according to the first connection weights to output a first input variable to the hidden layer.

[0041] The present invention performs data processing on the flowering period data, plant type trait data, and ear trait data of maize according to the first connection weights to obtain a first input variable, expressed as:

[0042]

[0043] Where: is the first input variable obtained by the th internal neuron, is the serial number of the internal neuron, is the serial number of the input neuron, is the total number of input neurons, is the th first connection weight between the input neuron and the is the th input of the input neuron, and the flowering period data, plant type trait data, and ear trait data of maize are used as inputs, is the th

[0044] The hidden layer includes a set number of internal neurons, and the number of internal neurons is set to 32; the hidden layer is used to perform data processing on the first input variable using a transfer function to output a second input variable to the output layer.

[0045] The present invention performs data processing on the first input variable according to the transfer function to obtain a second input variable, expressed as:

[0046]

[0047] Where: is the second input variable output by the th internal neuron, is the hyperbolic tangent function, is the The first input variable obtained by an internal neuron.

[0048] The output layer includes 1 output neuron; the output layer is used to process the second input variable according to the second connection weight to obtain the corn yield prediction result.

[0049] The present invention processes the second input variable according to the second connection weight to obtain the corn yield prediction result, expressed as:

[0050]

[0051] Where: is the predicted value of the ear weight of corn, is the serial number of the internal neuron, is the number of internal neurons, is the second connection weight between the th internal neuron and the output neuron, is the second input variable output by the th internal neuron, is the bias between the

[0052] The present invention constructs a training set and a test set by using the flowering period data, plant type trait data, and ear trait data of corn. The specific process is as follows: classify the phenotypic traits and sample labels of the flowering period data, plant type trait data, and ear trait data of corn, and randomly extract the classified flowering period data, plant type trait data, and ear trait data of corn according to a ratio of 7:3 as the training set and the test set respectively.

[0053] The present invention trains and tests the corn yield prediction model by using the training set and the test set. During the whole process, the learning rate of the corn yield prediction model is set to 0.1, and the determination coefficient and the root mean square error are used to update the parameters of the corn yield prediction model.

[0054] S3. Obtain the flowering period data, plant type trait data, and ear trait data of the corn to be measured, and obtain the corn yield prediction result according to the tested corn yield prediction model and the flowering period data, plant type trait data, and ear trait data of the corn to be measured.

[0055] In an optional embodiment of the present invention, the present invention obtains the flowering period data, plant type trait data, and ear trait data of the corn to be measured, and inputs the flowering period data, plant type trait data, and ear trait data of the corn to be measured into the tested corn yield prediction model to obtain the corn yield prediction result.

[0056] Simulation experiment:

[0057] Based on the same flowering stage data, plant type trait data, and ear trait data of corn, simulation experiments were conducted using different inputs (using flowering stage, plant type traits, ear traits as inputs respectively, and using these three parts together as inputs) and different models (MLR, PLSR, RF, and the model of the present invention, where MLR is a multiple linear regression model, PLSR is a partial least squares regression model, and RF is a random forest model). The evaluation indicators selected were the coefficient of determination and the root mean square error. The simulation results are shown in Table 1:

[0058]

[0059] As can be seen from Table 1, the method provided by the present invention, which uses the flowering stage data, plant type trait data, and ear trait data of corn as input data and utilizes the model constructed by the present invention, is superior to other prediction methods in both the coefficient of determination and the root mean square error. Therefore, the prediction results finally obtained by the method provided by the present invention can be more accurate.

[0060] Then, the present invention conducted simulation experiments on setting different ratios of the training set and the test set. The simulation results are shown in Table 2:

[0061]

[0062] As can be seen from Table 2, the present invention randomly extracts data in a ratio of 7:3 as the training set and the test set respectively, which can perform better in both the coefficient of determination and the root mean square error, is conducive to improving the prediction accuracy of the model, and further makes the prediction results finally obtained more accurate.

[0063] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 a block or multiple blocks.

[0064] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device realizes the functions in one process Figure 1 one process or multiple processes and / or blocksFigure 1 The functions specified in one or more boxes.

[0065] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 process or multiple processes and / or boxes Figure 1 or more boxes.

[0066] In the present invention, specific embodiments are used to elaborate on the principles and implementation manners of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present invention.

[0067] Those of ordinary skill in the art will realize that the embodiments described herein are for helping the reader understand the principles of the present invention, and it should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those of ordinary skill in the art can make various other specific deformations and combinations that do not depart from the essence of the present invention according to the technical revelations disclosed in the present invention, and these deformations and combinations are still within the protection scope of the present invention.

Claims

1. A maize yield prediction method based on artificial neural network, characterized in that, It includes the following steps: S1. Obtain the flowering stage data, plant type traits data, and ear traits data of corn; The flowering stage data of corn includes the tasseling stage, pollen shedding stage, and silking stage; the plant type traits data of corn includes plant height, ear height, number of leaves above the ear, length of the main axis of the male inflorescence, number of branches of the male inflorescence, length of the first leaf below the ear, width of the first leaf below the ear, length of the ear leaf, width of the ear leaf, length of the first leaf above the ear, length of the second leaf above the ear, length of the third leaf above the ear, width of the first leaf above the ear, width of the second leaf above the ear, width of the third leaf above the ear, included angle of the first leaf above the ear, included angle of the second leaf above the ear, included angle of the third leaf above the ear, length from the ear leaf auricle to the highest point of the first leaf above the ear, length from the ear leaf auricle to the highest point of the second leaf above the ear, length from the ear leaf auricle to the highest point of the third leaf above the ear; the ear traits data of corn includes ear weight, ear length, ear diameter, number of rows of kernels, tip elongation, 100-kernel weight, and grain weight; To obtain the plant type traits data and ear traits data, the specific process is as follows: 10 days after the pollen shedding of corn ends, measure the length from the root of the plant on the ground surface to the top of the main axis of the male inflorescence to obtain the plant height, measure the length from the root of the plant on the ground surface to the first ear-bearing node to obtain the ear height, measure all the leaves above the ear leaf to obtain the number of leaves above the ear, measure the distance from the highest branch of the male inflorescence to the top of the main axis to obtain the length of the main axis of the male inflorescence, measure all the first-order branches of the male inflorescence to obtain the number of branches of the male inflorescence, measure the ear leaf to obtain the length of the first leaf below the ear, measure the length from the auricle to the tip of the leaf of the plant to obtain the length of the first leaf above the ear, the length of the second leaf above the ear, and the length of the third leaf above the ear, measure the length at the widest part of the leaf of the plant to obtain the width of the first leaf above the ear, the width of the second leaf above the ear, and the width of the third leaf above the ear, measure the angle between the main vein of the leaf of the plant and the stem to obtain the included angle of the first leaf above the ear, the included angle of the second leaf above the ear, and the included angle of the third leaf above the ear, measure the length from the auricle of the leaf of the plant to the highest point of the leaf to obtain the length from the auricle of the ear leaf to the highest point of the first leaf above the ear, the length from the auricle of the ear leaf to the highest point of the second leaf above the ear, and the length from the auricle of the ear leaf to the highest point of the third leaf above the ear; Harvest the ears in the late maturity stage of corn, dry the ears, and measure the dried ears to obtain the ear weight, ear length, ear diameter, number of rows of kernels, tip elongation, 100-kernel weight, and grain weight; S2. Build a corn yield prediction model based on an artificial neural network, use the flowering stage data, plant type traits data, and ear traits data of corn to build a training set and a test set, and use the training set and the test set to train and test the corn yield prediction model; S3. Obtain the flowering stage data, plant type traits data, and ear traits data of the corn to be measured, and obtain the corn yield prediction result according to the tested corn yield prediction model and the flowering stage data, plant type traits data, and ear traits data of the corn to be measured.

2. The maize yield prediction method based on artificial neural network according to claim 1, wherein To obtain the flowering stage data of corn, the specific process is as follows: Collect the number of days from the sowing date to the date when the tips of the male inflorescences of more than half of the plants in the sowing area emerge from the top leaves to obtain the tasseling stage; collect the number of days from the sowing date to the date when the male inflorescences of more than half of the plants in the sowing area start to shed pollen to obtain the pollen shedding stage; collect the number of days from the sowing date to the date when the silk threads of more than half of the plants in the sowing area emerge from the bracts to obtain the silking stage.

3. The maize yield prediction method based on artificial neural network according to claim 1, characterized in that In step S2, the corn yield prediction model includes an input layer, a hidden layer, and an output layer connected in sequence; The input layer includes 31 input neurons; the input layer is used to input the flowering stage data, plant type trait data, and ear trait data of corn, and perform data processing on the flowering stage data, plant type trait data, and ear trait data of corn according to the first connection weight to output the first input variable to the hidden layer; The hidden layer includes a set number of internal neurons; the hidden layer is used to perform data processing on the first input variable according to the transfer function to output the second input variable to the output layer; The output layer includes 1 output neuron; the output layer is used to perform data processing on the second input variable according to the second connection weight to obtain the corn yield prediction result.

4. The maize yield prediction method based on artificial neural network according to claim 3, characterized in that, In the input layer, data processing is performed on the flowering stage data, plant type trait data, and ear trait data of corn according to the first connection weight to obtain the first input variable, expressed as: Wherein: is the first input variable obtained by the th internal neuron, is the serial number of the internal neuron, is the serial number of the input neuron, is the total number of input neurons, is the first connection weight between the th input neuron and the th internal neuron, is the input of the th input neuron, and the flowering stage data, plant type trait data and ear trait data of corn are used as inputs, is the bias between the th input neuron and the th internal neuron.

5. The maize yield prediction method based on artificial neural network according to claim 3, characterized in that, In the hidden layer, data processing is performed on the first input variable according to the transfer function to obtain the second input variable, expressed as: Wherein: is the second input variable output by the th internal neuron, is the hyperbolic tangent function, is the first input variable obtained by the th internal neuron.

6. The maize yield prediction method based on artificial neural network according to claim 3, characterized in that, In the output layer, data processing is performed on the second input variable according to the second connection weight to obtain the corn yield prediction result, expressed as: Wherein: is the predicted value of the ear weight of corn, is the serial number of the internal neuron, is the number of internal neurons, is the second connection weight between the th internal neuron and the output neuron, is the second input variable output by the th internal neuron, is the bias between the th internal neuron and the output neuron.

7. The maize yield prediction method based on artificial neural network according to claim 3, wherein The number of internal neurons is set to 32.

8. The maize yield prediction method based on artificial neural network according to claim 1, characterized in that, In step S2, the training set and the test set are constructed using the flowering stage data, plant type trait data, and ear trait data of corn. The specific process is as follows: the flowering stage data, plant type trait data, and ear trait data of corn are classified according to phenotypic traits and sample labels, and the classified flowering stage data, plant type trait data, and ear trait data of corn are randomly sampled according to a ratio of 7:3 to be used as the training set and the test set respectively.

Images