Optimization method and device for irrigation and fertilization of maize-soybean intercropping and storage medium

Abstract

The application discloses a corn-soybean intercropping irrigation and fertilization optimization method and device and a storage medium. It relates to the technical field of irrigation and fertilization optimization. The method comprises the following steps: acquiring historical light intensity information of a first region at a current time point; soybeans are planted in the first region, and corn is planted in a second region adjacent to the first region; the first region comprises at least two sub-regions arranged in sequence away from the second region; the historical light intensity information comprises historical light intensity information of all the sub-regions; according to the historical light intensity information, a neural network model is used to determine light intensity prediction information of each sub-region within a preset time after the current time point; and according to the light intensity prediction information, an irrigation and fertilization scheme of each sub-region at the current time point is determined from an irrigation and fertilization scheme set. The technical problem that the irrigation and fertilization scheme in the corn-soybean intercropping mode does not consider the shading effect of corn on soybeans and seriously affects the yield of intercropped soybeans is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of irrigation and fertilization optimization, in particular to a corn-soybean intercropping irrigation and fertilization optimization method, device and storage medium. BACKGROUND

[0002] In the soybean-corn intercropping mode, soybean as a low crop is easily affected by the shading of adjacent high crop corn. This shading effect intensifies after the corn enters the jointing stage, which is manifested as the rapid growth of corn plants, with a height of 250-300 cm, significantly blocking the light of soybean, so that the soybean next to the corn row is most strongly shaded. The light energy utilization rate of soybean decreases in this case, and the competition for water and nutrients by corn makes the soybean stem become slender compared with monocropping, and the plant height is higher than monocropping, and the lodging rate is greatly improved. Unreasonable fertilization will further lead to soybean lodging, which seriously affects the yield and quality of crops.

[0003] Current irrigation and fertilization practices only consider that soybean can meet half of its nitrogen demand through biological nitrogen fixation, so soybean does not need a large amount of nitrogen fertilizer, and if the supply of nitrogen fertilizer to corn is insufficient, it will cause a reduction in yield. If uniform fertilization is applied in the whole field, it will lead to insufficient fertilizer supply for corn or excessive growth and lodging of soybean, so the selection is based on crop type and fertilization is applied to the two crops respectively. However, this irrigation and fertilization method only applies general fertilization according to crop type, without fully considering the differences in the growth environment of soybean caused by corn shading, and cannot cope with the shading effect of corn on soybean, which seriously affects the yield of intercropped soybean.

[0004] In view of the technical problem in the prior art that the irrigation and fertilization scheme in the corn-soybean intercropping mode does not consider the shading effect of corn on soybean, which seriously affects the yield of intercropped soybean, no effective solution has been proposed so far. SUMMARY

[0005] Embodiments of the present disclosure provide a corn-soybean intercropping irrigation and fertilization optimization method, device and storage medium. At least to solve the technical problem in the prior art that the irrigation and fertilization scheme in the corn-soybean intercropping mode does not consider the shading effect of corn on soybean, which seriously affects the yield of intercropped soybean.

[0006] According to an aspect of embodiments of the present disclosure, a method for optimizing irrigation and fertilization of corn-soybean intercropping is provided, including: obtaining historical light intensity information of a first area at a current time point; wherein the first area is planted with soybeans, and a second area adjacent to the first area is planted with corn; the first area includes at least two sub-areas arranged in sequence away from the second area; the historical light intensity information includes historical light intensity information of all sub-areas; determining light intensity prediction information of each sub-area within a preset time after the current time point by using a pre-trained neural network model according to the historical light intensity information; wherein the preset time is a next fertilization period of the soybeans; and determining an irrigation and fertilization scheme of each sub-area at the current time point from a set of preset irrigation and fertilization schemes according to the light intensity prediction information.

[0007] According to another aspect of embodiments of the present disclosure, a storage medium is also provided, which includes a stored program, wherein the program is executed by a processor when running to perform the above method.

[0008] According to another aspect of embodiments of the present disclosure, a device for optimizing irrigation and fertilization of corn-soybean intercropping is also provided, including: an information obtaining module, configured to obtain historical light intensity information of a first area at a current time point; wherein the first area is planted with soybeans, and a second area adjacent to the first area is planted with corn; the first area includes at least two sub-areas arranged in sequence away from the second area; the historical light intensity information includes historical light intensity information of all sub-areas; an information determining module, configured to determine light intensity prediction information of each sub-area within a preset time after the current time point by using a pre-trained neural network model according to the historical light intensity information; wherein the preset time is a next fertilization period of the soybeans; and a scheme determining module, configured to determine an irrigation and fertilization scheme of each sub-area at the current time point from a set of preset irrigation and fertilization schemes according to the light intensity prediction information.

[0009] According to another aspect of the embodiments of the present disclosure, a corn-soybean intercropping irrigation and fertilization optimization system is also provided, comprising a processor; and a memory connected with the processor, configured to provide the processor with instructions for processing the following processing steps: at a current time point, obtaining historical light intensity information of a first area; wherein the first area is planted with soybeans, and a second area adjacent to the first area is planted with corn; the first area comprises at least two sub-areas arranged in sequence away from the second area; the historical light intensity information comprises historical light intensity information of all sub-areas; according to the historical light intensity information, using a pre-trained neural network model to determine light intensity prediction information of each sub-area within a preset time after the current time point; wherein the preset time is the next fertilization period of the soybeans; and according to the light intensity prediction information, determining an irrigation and fertilization scheme of each sub-area at the current time point from a preset irrigation and fertilization scheme set.

[0010] The present application considers that there is a significant difference in the shading effect between the position adjacent to the corn and the position away from the corn in the first area, and the first area is divided into at least two sub-areas arranged in sequence away from the second area. When irrigation and fertilization of the intercropped soybeans are needed at the current time point, first, the historical light intensity information of all sub-areas in the first area is obtained to provide data support for subsequent prediction of light intensity. Then, considering that the degrees of influence of corn shading on different sub-areas are different, and the differences in the fertilization period of soybeans at different growth stages, according to these historical light intensity information, using a pre-trained neural network model, the light intensity prediction information of each sub-area within the next fertilization period of soybeans after the current time point is determined to achieve fine and differentiated dynamic prediction. Finally, according to the light intensity prediction information, an irrigation and fertilization scheme of each sub-area at the current time point is determined from a preset irrigation and fertilization scheme set to achieve personalized response to the growth needs of soybeans under different light conditions. Thus, the present application accurately considers the shading effect of corn on soybeans, and achieves fine irrigation and fertilization according to local conditions and time. Further, the technical problem that the irrigation and fertilization scheme under the corn-soybean intercropping mode in the prior art does not consider the shading effect of corn on soybeans, which seriously affects the yield of intercropped soybeans, is solved. BRIEF DESCRIPTION OF DRAWINGS

[0011] The accompanying drawings, which are included to provide a further understanding of the present disclosure and constitute a part of this application, illustrate certain illustrative embodiments of the present disclosure and are used to explain the present disclosure, but do not limit the present disclosure. In the drawings:

[0012] Figure 1 is a hardware structure block diagram of a computing device for implementing the method according to Embodiment 1 of the present application;

[0013] Figure 2a is a schematic diagram of each region of corn-soybean intercropping according to Embodiment 1 of the present application;

[0014] Figure 2b is another schematic diagram of each region of corn-soybean intercropping according to Embodiment 1 of the present application;

[0015] Figure 3 is a flowchart of the irrigation and fertilization optimization method of corn-soybean intercropping according to Embodiment 1 of the present application;

[0016] Figure 4 is a schematic diagram of the irrigation and fertilization optimization device of corn-soybean intercropping according to Embodiment 2 of the present application; and

[0017] Figure 5 is a schematic diagram of the irrigation and fertilization optimization system of corn-soybean intercropping according to Embodiment 3 of the present application. DETAILED DESCRIPTION

[0018] In order to make the personnel in the technical field better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in combination with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, not all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative labor should be within the scope of protection of the present disclosure.

[0019] It should be noted that the terms "first", "second", and the like in the specification and claims of the present disclosure and the above-described drawings are used to distinguish similar objects, and do not necessarily have to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0020] Embodiment 1

[0021] According to the embodiment, a method embodiment of the corn-soybean intercropping irrigation and fertilization optimization method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from here.

[0022] The method embodiment provided by the embodiment can be executed in a mobile terminal, a computer terminal, a server or similar computing device. Figure 1 A hardware structure block diagram of a computing device for implementing the corn-soybean intercropping irrigation and fertilization optimization method is shown. As shown in the figure, Figure 1 The computing device can include one or more processors (the processor can include but not limited to a microprocessor MCU or a programmable logic device FPGA processing device, etc.), a memory for storing data, a transmission device for communication function and an input / output interface. The memory, the transmission device and the input / output interface are connected with the processor through a bus. In addition, it can also include a display, a keyboard and a cursor control device connected with the input / output interface. Those skilled in the art can understand that, Figure 1 The structure shown in the figure is only a schematic, which does not limit the structure of the above-mentioned electronic device. For example, the computing device can include more or less components than Figure 1 shown in the figure, or have a different configuration from Figure 1 shown in the figure.

[0023] It should be noted that the one or more processors and / or other data processing circuits described above can be referred to herein as "data processing circuits" in general. The data processing circuit can be embodied in whole or in part as software, hardware, firmware or any other combination. In addition, the data processing circuit can be a single independent processing module, or all or part of any one of the other elements combined into the computing device. As referred to in the embodiments of the present disclosure, the data processing circuit serves as a processor to control (for example, the selection of the variable resistance terminal path connected with the interface).

[0024] The memory can be used to store software programs of application software and modules, such as program instructions / data storage devices corresponding to the corn-soybean intercropping irrigation and fertilization optimization method in the embodiments of the present disclosure. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, implements the corn-soybean intercropping irrigation and fertilization optimization method of the application program described above. The memory can include a high-speed random access memory, and can also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory can further include a memory remotely arranged with respect to the processor, which can be connected to the computing device through a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0025] The transmission device is used to receive or send data via a network. Specific examples of the above-mentioned network can include a wireless network provided by a communication provider of the computing device. In one example, the transmission device includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device can be a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet in a wireless manner.

[0026] The display can be, for example, a touch screen type liquid crystal display (LCD), which can enable a user to interact with the user interface of the computing device.

[0027] It should be noted that, in some optional embodiments, the above-mentioned Figure 1 The computing device shown can include hardware elements (including circuitry), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. It should be noted that, Figure 1 is only one example of a particular concrete instance, and is intended to show the types of components that can be present in the above-mentioned computing device.

[0028] Figure 2a is a schematic view of each region of the corn-soybean intercropping according to the embodiments. Referring to Figure 2a As shown, soybeans are planted in the first region, and corn is planted in the second region adjacent to one side (which can be the left side or the right side) of the first region. Considering that the soybeans planted at a position adjacent to the second region in the first region are significantly affected by the shade of the corn than the soybeans planted at other positions away from the second region, the first region can be sequentially divided into two sub-regions in the direction away from the second region, such as Figure 2aThe first sub-region and the second sub-region are shown in FIG. 1. The first sub-region is closer to the second region than the second sub-region, i.e., the soybeans planted in the first sub-region are more affected by the shade of the corn planted in the second region.

[0029] Figure 2b is another schematic diagram of the corn-soybean intercropping regions according to the present embodiment. Referring to Figure 2b As shown, the first region is planted with soybeans, and the second regions adjacent to the two sides (including the left side and the right side) of the first region are planted with corn. Similarly, considering that the soybeans planted in the positions adjacent to the second regions in the first region are more affected by the shade of the corn than the other positions away from the second regions, the first region can be sequentially divided into three sub-regions in the direction away from the second regions, as shown in Figure 2b The two first sub-regions and one second sub-region are shown in FIG. 1. The left first sub-region is closer to the second region arranged on the left side of the first region than the second sub-region, and the right first sub-region is closer to the second region arranged on the right side of the first region than the second sub-region, i.e., the soybeans planted in the two first sub-regions are more affected by the shade of the corn planted in the second region.

[0030] Under the above operating environment, according to a first aspect of the present embodiment, a corn-soybean intercropping irrigation and fertilization optimization method is provided. Figure 3 A flowchart of the method is shown, referring to Figure 3 The method includes the following steps:

[0031] S102: At a current time point, historical light intensity information of a first region is obtained; wherein the first region is planted with soybeans, and a second region adjacent to the first region is planted with corn; the first region includes at least two sub-regions arranged sequentially in the direction away from the second region; and the historical light intensity information includes historical light intensity information of all sub-regions;

[0032] S104: According to the historical light intensity information, a pre-trained neural network model is used to determine light intensity prediction information of each sub-region within a preset time after the current time point; wherein the preset time is the next fertilization period of the soybeans.

[0033] S106: According to the light intensity prediction information, an irrigation and fertilization scheme of each sub-region at the current time point is determined from a set of preset irrigation and fertilization schemes.

[0034] Specifically, referring to Figure 2a and Figure 2bAs shown, the first region specifically refers to the area where soybeans are planted, while the second region adjacent to the first region is planted with corn. Considering that there is a significant difference in the shading effect between the position close to corn and the position far away from corn in the first region, the first region is further divided into multiple sub-regions in the direction away from the second region according to the distance from the corn, which aims to capture the changes in light conditions due to different distances from the corn. For each sub-region, considering that the shadow effect of corn on soybeans changes over time and season, it is necessary to obtain the light intensity records of the sub-region in the past period at the current time point to determine the historical light intensity information of all sub-regions (corresponding to step 102), which provides data support for subsequent prediction of light intensity.

[0035] Then, considering that different sub-regions are affected by the degree of corn shading, based on the historical light intensity information of these sub-regions, the light intensity information of each sub-region in a future specific period is predicted by a pre-trained neural network model (corresponding to step 104). Considering the difference in the fertilization period of soybeans in different growth stages, the future specific period here refers to the period from the current time point to the end of the next fertilization period of soybeans, ensuring that the prediction result is directly related to the actual management decision of crops. Thus, the predicted light intensity value of each sub-region in the future fertilization period is determined by the neural network model, which reflects the influence of the corn shading effect on the light receiving conditions of each sub-region, achieving fine and differentiated dynamic prediction.

[0036] Finally, according to the light intensity prediction information, the irrigation and fertilization scheme of each sub-region at the current time point is determined from a pre-set irrigation and fertilization scheme set (corresponding to step 106). The irrigation and fertilization scheme set includes various possible irrigation and fertilization schemes for different light conditions and soybean growth stages. The irrigation and fertilization scheme of each sub-region will be customized according to its specific light intensity prediction information, so that in the same field, different sub-regions should receive different water and fertilizer inputs according to their light conditions, in order to optimize the growth conditions of soybeans, ensuring that the soybeans in each sub-region can receive the most suitable care for their light conditions and growth status, thereby achieving personalized response to the growth needs of soybeans under different light conditions.

[0037] As described in the background, in the soybean-corn intercropping mode, soybean as a low-position crop is easily affected by the shading of the adjacent high-position crop corn, and the current irrigation and fertilization practice only considers that soybean can meet half of its nitrogen demand through biological nitrogen fixation, so soybean does not need a large amount of nitrogen fertilizer, and corn will cause yield reduction if the nitrogen supply is insufficient. If uniform fertilization is carried out in the whole field, it will lead to insufficient fertilizer supply for corn or excessive growth and lodging of soybean, so fertilization is selected according to crop type and fertilization is carried out for the two crops respectively. However, this irrigation and fertilization method only carries out universal fertilization according to crop type, and does not fully consider the difference in the growth environment of soybean caused by the shading of corn, and cannot cope with the shading effect of corn on soybean, which seriously affects the yield of intercropped soybean.

[0038] Therefore, the present application considers that there is a significant difference between the shading effect of the position close to corn and the position far away from corn in the first area, and the first area is divided into at least two sub-areas arranged in turn away from the second area. When irrigation and fertilization of intercropped soybean are needed at the current time point, first, the historical light intensity information of all sub-areas in the first area is obtained to provide data support for subsequent prediction of light intensity. Then, considering that the degree of influence of corn shading on different sub-areas is different, and the difference in the fertilization cycle of soybean at different growth stages, according to these historical light intensity information, the pre-trained neural network model is used to determine the light intensity prediction information of each sub-area in the next fertilization cycle of soybean after the current time point, to realize fine and differentiated dynamic prediction. Finally, according to the light intensity prediction information, the irrigation and fertilization scheme of each sub-area at the current time point is determined from the preset irrigation and fertilization scheme set, to realize the individualized response to the growth demand of soybean under different light conditions. Thus, the present application accurately considers the shading effect of corn on soybean, and realizes the fine irrigation and fertilization purpose of adapting to local conditions and time. Further, the technical problem that the irrigation and fertilization scheme in the corn-soybean intercropping mode in the prior art does not consider the shading effect of corn on soybean, which seriously affects the yield of intercropped soybean, is solved.

[0039] Optionally, light-sensitive sensors are arranged at intervals on each sub-area, and the interval distance of the light-sensitive sensors on all sub-areas arranged in turn away from the second area increases in turn; the light intensity information of each sub-area is collected by the corresponding light-sensitive sensor.

[0040] Specifically, since the sub-regions close to the corn (i.e. the part of the first region closer to the second region) are more significantly affected by the shading effect, and the shadow effect of the corn on the soybean changes over time and season, the change of the light intensity is also more complex and frequent. In contrast, the farther away from the corn, the change tends to be flat. In order to accurately reflect this change, the present application chooses to arrange the photosensitive sensors densely in the sub-regions close to the corn, and gradually widen the spacing between the sensors in the sub-regions far from the corn, as shown in Figure 2a and Figure 2b Such a layout ensures that high-density data points are obtained in the area where the light conditions are most variable, while avoiding excessive investment in hardware resources in areas where the light is relatively stable. Then, the light intensity information of each sub-region can be continuously collected by the corresponding photosensitive sensor at different time periods to provide a detailed record of the light changes at different times and places, providing a solid data support for the subsequent light intensity prediction and irrigation and fertilization strategy making.

[0041] In this way, even in an environment where the light conditions change rapidly, enough data points can be ensured to depict the true distribution of the light intensity, which is crucial for the subsequent light intensity prediction and irrigation and fertilization scheme making. At the same time, this non-uniform distribution of sensor layout strategy effectively balances the accuracy and cost of data collection, avoiding unnecessary economic burden caused by uniformly deploying a large number of sensors throughout the area.

[0042] Optionally, a drip irrigation pipe for irrigation and fertilization is installed at the position of each sub-region where the photosensitive sensor is arranged.

[0043] Specifically, as shown in Figure 2a and Figure 2b , a drip irrigation pipe for irrigation and fertilization is installed at the position of each sub-region where the photosensitive sensor is arranged. Through the drip irrigation pipe, accurate delivery of water and fertilizer can be achieved, avoiding the waste caused by traditional flooding irrigation. And by closely combining the monitoring point (photosensitive sensor) with the intervention point (drip irrigation pipe), consistency and coherence between data collection and actual action are ensured to achieve independent control of each small environment and truly fine management according to local conditions.

[0044] Optionally, the method further comprises: determining the length of time within the preset time after the current time point; inputting the historical light intensity information of each sub-region and the length of time into the pre-trained neural network model to determine the light intensity prediction information of the sub-region within the preset time after the current time point.

[0045] Specifically, considering that the fertilization cycle of soybeans varies at different growth stages, for example, but not limited to, the fertilization cycle of soybean germination period is 7 days, the fertilization cycle of branching period is 10 days, the fertilization cycle of flowering and podding period is 12 days, and the fertilization cycle of maturation period is 15 days. Therefore, before prediction using the pre-trained neural network model, the target time period (corresponding to a preset time after the current time point) needs to be determined, that is, the time length from the current time point to the end of the next fertilization cycle of soybeans. Then, for each sub-region, the historical light intensity information of the sub-region and the aforementioned determined time length are input into the pre-trained neural network model to generate the light intensity prediction value of each sub-region in the target time period, thereby realizing the conversion from historical light intensity data to future light condition prediction and providing an important basis for subsequent irrigation and fertilization decision-making.

[0046] Optionally, the neural network model is a recurrent neural network model, a unidirectional long short-term memory network model, or a gated recurrent unit model.

[0047] Specifically, considering that the historical light intensity information of each sub-region changes over time and exhibits obvious sequence characteristics. The recurrent neural network (RNN) can process sequence data with time dependence through its recurrent connection structure, so it can capture the time sequence correlation of historical light intensity information and provide a basis for prediction. The unidirectional long short-term memory network (LSTM) effectively solves the gradient vanishing / explosion problem of RNN when processing long sequences by introducing a special gating mechanism (input gate, forget gate, and output gate), which enables it to remember long-term dependencies and is very suitable for prediction tasks that need to consider the impact of historical data on the current state. GRU is a simplified version of LSTM, which combines the input gate and the forget gate into a single update gate, reducing the complexity of the model and speeding up the training. Moreover, GRU still retains the ability to process long sequence data, making it perform well in scenarios that require fast response and lower computing resources. Therefore, the neural network model proposed in the present application is a recurrent neural network model, a unidirectional long short-term memory network model, or a gated recurrent unit model.

[0048] Optionally, the neural network model is trained by: obtaining historical light intensity sample data of all sub-regions of the first region in the entire growth cycle of soybeans; determining a training set of the neural network model according to the historical light intensity sample data; wherein each sample data in the training set is light intensity data of each sub-region in a period of time, and the label of each sample data is light intensity data of a soybean fertilization cycle after the period of time; and training the neural network model based on the training set until the neural network model meets a preset training termination condition.

[0049] Specifically, it is necessary to collect historical light intensity data of all sub-regions in the first area throughout the entire growth period of soybeans. These data can be obtained through continuous monitoring by previously installed photosensitive sensors, ensuring coverage from sowing to harvesting, including light conditions under different weather conditions and seasonal changes. Since the collected raw data often contains noise and missing values, preprocessing can be performed, including removing outliers, filling missing data, and normalizing numerical values to eliminate dimension effects and improve the stability and efficiency of model training.

[0050] Then, a training set is constructed, and each sample data in the training set represents a light intensity sequence of a sub-region in a certain period of time, and the corresponding label is the light intensity data of a soybean fertilization period after this period of time. This design enables the model to learn the pattern of light intensity evolution over time and its indicative significance for future fertilization period light conditions.

[0051] Secondly, the time length of the sample data (i.e., the length of the input sequence) and the time point of the prediction target (i.e., the time corresponding to the label) are determined. The selection of these two parameters should be based on the understanding of the growth habits of soybeans and the influence mechanism of light, as well as the results of preliminary experiments. Then, a suitable neural network architecture (such as RNN, LSTM, GRU, etc.) is selected, and initial parameters are set, including the number of hidden layer nodes, the type of activation function, the loss function, and the optimizer. Set the training termination condition, such as the prediction error of the model on the validation set being lower than a certain threshold, or the performance on the validation set no longer significantly improving after a certain number of iterations. In addition, to avoid infinite loops, a maximum number of iterations is usually set, and once this upper limit is reached, the training will be terminated even if the performance criteria are not fully met.

[0052] Finally, the constructed training set is used to train the model multiple times. In each iteration, the model attempts to predict future light intensity based on the input light intensity sequence and adjusts the weights through the backpropagation algorithm to minimize the difference between the predicted value and the true label. During training, a portion of the data should be reserved as a validation set to evaluate the model's generalization ability and prevent overfitting. Based on the performance on the validation set, model structure or training parameters such as learning rate and batch size may need to be adjusted. After training is complete, the best-performing model version is saved for deployment in actual agricultural production. Over time, as new light data accumulates, the model should be periodically retrained or fine-tuned to adapt to environmental changes and new patterns of crop growth, ensuring the accuracy of predictions and the effectiveness of decisions.

[0053] Therefore, through the above carefully designed training process, the neural network model can learn to extract valuable information from historical light intensity data, ensuring the prediction accuracy and reliability of the model to accurately predict the light intensity information in the future time period.

[0054] Optionally, different irrigation and fertilization schemes in the set of irrigation and fertilization schemes are associated with different light intensity intervals and corresponding soybean growth periods; and determining, according to the light intensity prediction information, the irrigation and fertilization scheme of each sub-region at the current time point from the set of preset irrigation and fertilization schemes comprises: determining the growth period of soybean at the current time point; determining the light intensity interval to which the light intensity prediction information of each sub-region belongs; and taking the irrigation and fertilization scheme in the set of preset irrigation and fertilization schemes that is associated with the light intensity interval to which the light intensity prediction information of each sub-region belongs and the growth period of soybean at the current time point as the irrigation and fertilization scheme of each sub-region at the current time point.

[0055] Specifically, the light intensity can be divided into several levels, such as low light, medium light, high light, etc., according to historical light data and the actual growth performance of soybeans. Each level corresponds to the typical growth characteristics and water and fertilizer demand pattern of soybeans under that light condition. For each light intensity level, a corresponding irrigation and fertilization scheme is developed in combination with the growth stage of soybeans and the water and fertilizer demand pattern. For example, during the flowering and podding period of soybeans and under high light conditions, the irrigation amount should be moderately reduced to avoid excessive water inhibiting root respiration, and the proportion of phosphorus and potassium fertilizers should be increased to promote grain formation and enrichment. However, during the flowering and podding period of soybeans and under low light conditions, attention should be paid to increasing the proportion of nitrogen fertilizer to stimulate the internal metabolic activity of the plant. Then, all customized irrigation and fertilization schemes are integrated into a comprehensive scheme set to ensure coverage of the entire growth period from sowing to harvesting to meet the nutritional needs of soybeans at different growth stages and under different light conditions. At the same time, through field tests and data analysis, the details of each scheme are continuously optimized to better meet the actual production needs.

[0056] Therefore, when determining the irrigation and fertilization scheme of each sub-region at the current time point, the current growth period of soybeans needs to be determined. That is, at any given time point, it is necessary to determine which growth stage the soybeans are in, which can be achieved by observing the appearance characteristics of the plants, consulting growth records, or using sensor data. The light intensity prediction information of each sub-region is mapped into the corresponding light intensity interval. Since the set of preset irrigation and fertilization schemes contains multiple schemes, each of which is bound to a specific light intensity interval and soybean growth period, through a lookup table or a rule engine, the irrigation and fertilization scheme that matches the current light intensity prediction information and the growth period can be quickly located.

[0057] For example but not limited to, the light intensity prediction information of the first sub-region falls in the medium light interval, and at this time the soybeans are in the flowering and podding stage, so the irrigation and fertilization scheme specially designed for the medium light condition and the flowering and podding stage can be determined from the preset irrigation and fertilization scheme set, which emphasizes the supplement of nitrogen, phosphorus, potassium and other elements to promote flower opening and pod formation, and adjusts the irrigation water volume considering the light level to avoid excessive evaporation or water accumulation.

[0058] For another example, it is predicted by the neural network model that the light intensity of the second sub-region will be in the high light interval in the next 7 days, and it is judged according to the growth model that the soybeans in this sub-region are in the flowering and podding stage. Then, the scheme specially designed for the flowering and podding stage under high light condition can be selected from the preset irrigation and fertilization scheme set, which suggests to moderately reduce the irrigation amount to avoid excessive water from inhibiting root respiration, and to increase the proportion of phosphorus and potassium fertilizer to promote the formation and enrichment of grains.

[0059] In this way, it can be ensured that the irrigation and fertilization scheme of each sub-region can closely match the actual light condition and the growth demand of soybeans, so as to realize the precise allocation of resources and significantly improve the efficiency and sustainability of agricultural production.

[0060] In addition, according to the embodiment, a storage medium is also provided. The storage medium includes a stored program, wherein the program is executed by a processor when the program is running to perform the method of any one of the above.

[0061] The present application considers that there is a significant difference between the shading effect of the position close to the corn and the position far away from the corn in the first region, and the first region is divided into at least two sub-regions arranged in turn away from the second region. When irrigation and fertilization of the intercropped soybeans is needed at the current time point, the historical light intensity information of all sub-regions in the first region is first obtained to provide data support for subsequent prediction of light intensity. Then, considering that the degree of influence of corn shading on different sub-regions is different, and the difference of fertilization period of soybeans in different growth stages, according to these historical light intensity information, the light intensity prediction information of each sub-region in the next fertilization period of soybeans after the current time point is determined by using a pre-trained neural network model, to realize fine and differentiated dynamic prediction. Finally, according to the light intensity prediction information, the irrigation and fertilization scheme of each sub-region at the current time point is determined from the preset irrigation and fertilization scheme set, to realize individual response to the growth demand of soybeans under different light conditions. Thus, the present application accurately considers the shading effect of corn on soybeans, and realizes fine irrigation and fertilization according to local conditions and time. Further, the technical problem that the irrigation and fertilization scheme for the intercropping mode of corn and soybeans does not consider the shading effect of corn on soybeans in the prior art, which seriously affects the yield of intercropped soybeans, is solved.

[0062] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a combination of a series of actions, but those skilled in the art should know that the present application is not limited by the order of the described actions, because according to the present application, certain steps can be performed in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily necessary for the present application.

[0063] Embodiment 2

[0064] Figure 4 A structural schematic diagram of the irrigation and fertilization optimization device 400 for corn-soybean intercropping according to the present embodiment is shown. The device 400 comprises: an information acquisition module 410, configured to acquire historical light intensity information of a first region at a current time point; wherein the first region is planted with soybeans, and a second region adjacent to the first region is planted with corn; the first region comprises at least two sub-regions arranged in sequence away from the second region; the historical light intensity information comprises historical light intensity information of all sub-regions; an information determination module 420, configured to determine, according to the historical light intensity information, light intensity prediction information of each sub-region within a preset time after the current time point by using a pre-trained neural network model; wherein the preset time is a next fertilization period of the soybeans; and a scheme determination module 430, configured to determine, according to the light intensity prediction information, an irrigation and fertilization scheme of each sub-region at the current time point from a set of pre-set irrigation and fertilization schemes.

[0065] Optionally, light-sensitive sensors are arranged at intervals on each sub-region, and the interval distances of the light-sensitive sensors on all sub-regions arranged in sequence away from the second region increase in sequence; the light intensity information of each sub-region is collected by the corresponding light-sensitive sensor.

[0066] Optionally, a drip irrigation pipe for irrigation and fertilization is installed at the position of each sub-region where the light-sensitive sensor is arranged.

[0067] Optionally, the determination of the light intensity prediction information of each sub-region within the preset time after the current time point according to the historical light intensity information by using the pre-trained neural network model comprises: determining a time length within the preset time after the current time point; inputting, for each sub-region, the historical light intensity information of the sub-region and the time length into the pre-trained neural network model to determine the light intensity prediction information of the sub-region within the preset time after the current time point.

[0068] Optionally, the neural network model is a recurrent neural network model, a unidirectional long short-term memory network model, or a gated recurrent unit model.

[0069] Optionally, the neural network model is trained by: obtaining historical light intensity sample data of all sub-regions of the first region in an entire growth period of soybeans; determining a training set of the neural network model according to the historical light intensity sample data; wherein each sample data in the training set is light intensity data of each sub-region in a period of time, and a label of each sample data is light intensity data of a soybean fertilization period after the period of time; and training the neural network model based on the training set until the neural network model meets a preset training stop condition.

[0070] Optionally, different irrigation and fertilization schemes in the set of irrigation and fertilization schemes are associated with different light intensity intervals and corresponding soybean growth periods; and the determining, according to the light intensity prediction information, of an irrigation and fertilization scheme of each sub-region at the current time point from the set of preset irrigation and fertilization schemes comprises: determining a growth period of soybeans at the current time point; determining a light intensity interval to which the light intensity prediction information of each sub-region belongs; and determining, as the irrigation and fertilization scheme of each sub-region at the current time point, an irrigation and fertilization scheme in the set of preset irrigation and fertilization schemes that is associated with the light intensity interval to which the light intensity prediction information of each sub-region belongs and the growth period of soybeans at the current time point.

[0071] Thus, according to the present embodiment, considering that there is a significant difference between the shading effect on the position close to corn and the position far away from corn in the first area, the first area is divided into at least two sub-areas arranged in sequence in the direction away from the second area. When irrigation and fertilization of the intercropped soybeans at the current time point is needed, the historical light intensity information of all sub-areas in the first area is first obtained to provide data support for subsequent prediction of light intensity. Then, considering that the degree of influence of corn shading on different sub-areas is different, and the difference in the fertilization cycle of soybeans at different growth stages, according to these historical light intensity information, the light intensity prediction information of each sub-area in the next fertilization cycle of soybeans after the current time point is determined by using a pre-trained neural network model, to achieve fine and differentiated dynamic prediction. Finally, according to the light intensity prediction information, the irrigation and fertilization scheme of each sub-area at the current time point is determined from a preset irrigation and fertilization scheme set, to achieve personalized response to the growth needs of soybeans under different light conditions. Thus, the present application accurately considers the shading effect of corn on soybeans, and achieves the purpose of fine irrigation and fertilization according to local conditions and time. Further, the technical problem that the irrigation and fertilization scheme under the corn-soybean intercropping mode in the prior art does not consider the shading effect of corn on soybeans, which seriously affects the yield of intercropped soybeans, is solved.

[0072] Embodiment 3

[0073] Figure 5 The corn-soybean intercropping irrigation and fertilization optimization system 500 according to the present embodiment is shown, which comprises a processor 510 and a memory 520 connected with the processor 510, for providing the processor 510 with instructions to process the following processing steps: at a current time point, obtaining historical light intensity information of a first area; wherein the first area is planted with soybeans, and a second area adjacent to the first area is planted with corn; the first area includes at least two sub-areas arranged in sequence in the direction away from the second area; the historical light intensity information includes the historical light intensity information of all sub-areas; according to the historical light intensity information, using a pre-trained neural network model to determine the light intensity prediction information of each sub-area within a preset time after the current time point; wherein the preset time is the next fertilization cycle of the soybeans; and according to the light intensity prediction information, determining the irrigation and fertilization scheme of each sub-area at the current time point from a preset irrigation and fertilization scheme set.

[0074] Optionally, light-sensitive sensors are arranged on each sub-area at intervals, and the interval distance of the light-sensitive sensors on all sub-areas arranged in sequence in the direction away from the second area increases in sequence; the light intensity information of each sub-area is collected by the corresponding light-sensitive sensor.

[0075] Optionally, a drip irrigation pipe for irrigation and fertilization is installed at the position of each sub-region where the photosensitive sensor is arranged.

[0076] Optionally, the determining, according to the historical light intensity information, of the light intensity prediction information of each sub-region within a preset time after the current time point by using the pre-trained neural network model comprises: determining a time length within the preset time after the current time point; and inputting, for each sub-region, the historical light intensity information of the sub-region and the time length into the pre-trained neural network model to determine the light intensity prediction information of the sub-region within the preset time after the current time point.

[0077] Optionally, the neural network model is a recurrent neural network model, a unidirectional long short-term memory network model, or a gated recurrent unit model.

[0078] Optionally, the neural network model is trained by: obtaining historical light intensity sample data of all sub-regions of the first region within an entire growth cycle of soybeans; determining a training set of the neural network model according to the historical light intensity sample data; wherein each sample data in the training set is light intensity data of each sub-region within a period of time, and a label of each sample data is light intensity data of a soybean fertilization period after the period of time; and training the neural network model based on the training set until the neural network model meets a preset training termination condition.

[0079] Optionally, different irrigation and fertilization schemes in the set of irrigation and fertilization schemes are associated with different light intensity intervals and corresponding soybean growth cycles; and the determining, according to the light intensity prediction information, of an irrigation and fertilization scheme of each sub-region at the current time point from a set of preset irrigation and fertilization schemes comprises: determining a growth cycle of soybeans at the current time point; determining a light intensity interval to which the light intensity prediction information of each sub-region belongs; and determining, as the irrigation and fertilization scheme of each sub-region at the current time point, an irrigation and fertilization scheme in the set of preset irrigation and fertilization schemes that is associated with the light intensity interval to which the light intensity prediction information of each sub-region belongs and the growth cycle of soybeans at the current time point.

[0080] Thus, according to the embodiment, considering that there is a significant difference between the shading effect on the position close to corn and the position far away from corn in the first area, the first area is divided into at least two sub-areas arranged in turn in the direction away from the second area. When irrigation and fertilization of the intercropped soybeans at the current time point is needed, the historical light intensity information of all sub-areas in the first area is first obtained to provide data support for subsequent prediction of light intensity. Then, considering that the degrees of influence of corn shading on different sub-areas are different, and the differences in the fertilization cycle of soybeans at different growth stages, according to the historical light intensity information, the light intensity prediction information of each sub-area in the next fertilization cycle of soybeans after the current time point is determined by using the pre-trained neural network model, so as to realize fine and differentiated dynamic prediction. Finally, according to the light intensity prediction information, the irrigation and fertilization scheme of each sub-area at the current time point is determined from the preset irrigation and fertilization scheme set, so as to realize individualized response to the growth needs of soybeans under different light conditions. Thus, the shading effect of corn on soybeans is accurately considered, and the fine irrigation and fertilization purpose of adapting to local conditions and time is realized. Further, the technical problem that the irrigation and fertilization scheme under the intercropping mode of corn and soybeans in the prior art does not consider the shading effect of corn on soybeans, which seriously affects the yield of intercropped soybeans, is solved.

[0081] The above-mentioned serial numbers of the embodiments of the application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0082] In the above-mentioned embodiments of the application, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0083] In several embodiments provided in the present application, it should be understood that the disclosed technical content can be implemented by other ways. Among them, the above-mentioned device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division way, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be through some interface, indirect coupling or communication connection between units or modules, which can be electrical or other forms.

[0084] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. According to actual needs, part or all of the units can be selected to achieve the purpose of the embodiment scheme.

[0085] In addition, each function unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software function unit.

[0086] When the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application, essentially or the part that contributes to the prior art, or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various program code storage media.

[0087] The above is only the preferred embodiment of the present application, it should be noted that for those skilled in the art, without departing from the principles of the present application, can make a number of improvements and refinements, these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. An optimized irrigation and fertilization method for intercropping corn and soybeans, characterized in that, include: At the current point in time, obtain the historical light intensity information for the first region; The first area is planted with soybeans, and the second area adjacent to the first area is planted with corn; the first area includes at least two sub-areas arranged sequentially in a direction away from the second area; the historical light intensity information includes the historical light intensity information of all sub-areas; each sub-area is provided with a photosensitive sensor at intervals, and the interval between the photosensitive sensors in all sub-areas arranged sequentially in a direction away from the second area increases sequentially; the light intensity information of each sub-area is collected by the corresponding photosensitive sensor; and a drip irrigation pipe for irrigation and fertilization is installed at the location of the photosensitive sensor in each sub-area. Based on the historical light intensity information, a pre-trained neural network model is used to determine the predicted light intensity information for each sub-region within a preset time period after the current time point; wherein, the preset time period is the next fertilization cycle for the soybean; the predicted light intensity information reflects the degree of influence of the corn shading effect on the light reception of each sub-region; and Based on the light intensity prediction information, an irrigation and fertilization scheme for each sub-region at the current time point is determined from a preset set of irrigation and fertilization schemes; wherein, the set of irrigation and fertilization schemes includes various possible irrigation and fertilization schemes for different light conditions and soybean growth stages; The step of determining the predicted illumination intensity for each sub-region within a preset time period after the current time point using a pre-trained neural network model based on the historical illumination intensity information includes: Determine the length of time within a preset time period after the current time point; wherein, the length of time is the time from the current time point until the end of the next soybean fertilization cycle; For each sub-region, the historical illumination intensity information of the sub-region and the time length are input into the pre-trained neural network model to determine the illumination intensity prediction information of the sub-region within a preset time period after the current time point; The different irrigation and fertilization schemes in the set of irrigation and fertilization schemes are correlated with different light intensity ranges and corresponding soybean growth cycles; and, determining the irrigation and fertilization scheme for each sub-region at the current time point from the preset set of irrigation and fertilization schemes based on the light intensity prediction information includes: Determine the growth cycle of soybeans at the current point in time; Determine the light intensity interval to which the light intensity prediction information for each sub-region belongs; The irrigation and fertilization schemes that are related to the light intensity range of the light intensity prediction information of each sub-region and the growth cycle of soybeans at the current time point in the preset set of irrigation and fertilization schemes are taken as the irrigation and fertilization schemes of each sub-region at the current time point. The neural network model is a recurrent neural network model, a unidirectional long short-term memory network model, or a gated recurrent unit model; The neural network model is trained in the following manner: Obtain historical light intensity sample data for all sub-regions of the first region throughout the entire growth cycle of soybeans; The training set of the neural network model is determined based on the historical light intensity sample data; wherein each sample data in the training set is the light intensity data of each sub-region over a period of time, and the label of each sample data is the light intensity data of a soybean fertilization cycle after the period of time. The neural network model is trained based on the training set until it meets a preset training cutoff condition.

2. A storage medium, characterized in that, The storage medium includes a stored program, wherein the method described in claim 1 is executed by a processor when the program is run.

3. An irrigation and fertilization optimization device for corn-soybean intercropping, comprising: The information acquisition module is used to acquire historical light intensity information of the first area at the current time. The first area is planted with soybeans, and the second area adjacent to the first area is planted with corn; the first area includes at least two sub-areas arranged sequentially in a direction away from the second area; the historical light intensity information includes the historical light intensity information of all sub-areas; each sub-area is provided with a photosensitive sensor at intervals, and the interval between the photosensitive sensors in all sub-areas arranged sequentially in a direction away from the second area increases sequentially; the light intensity information of each sub-area is collected by the corresponding photosensitive sensor; and a drip irrigation pipe for irrigation and fertilization is installed at the location of the photosensitive sensor in each sub-area. The information determination module is used to determine, based on the historical light intensity information and using a pre-trained neural network model, the predicted light intensity information for each sub-region within a preset time period after the current time point; wherein, the preset time period is the next fertilization cycle for the soybean; the predicted light intensity information reflects the degree of influence of the corn shading effect on the light reception of each sub-region; and The scheme determination module is used to determine the irrigation and fertilization scheme for each sub-region at the current time point from the preset set of irrigation and fertilization schemes based on the light intensity prediction information; wherein, the set of irrigation and fertilization schemes includes various possible irrigation and fertilization schemes for different light conditions and soybean growth stages; The information determination module is specifically used to perform the following steps: Determine the length of time within a preset time period after the current time point; wherein, the length of time is the time from the current time point until the end of the next soybean fertilization cycle; For each sub-region, the historical illumination intensity information of the sub-region and the time length are input into the pre-trained neural network model to determine the illumination intensity prediction information of the sub-region within a preset time period after the current time point; The different irrigation and fertilization schemes in the set of schemes are correlated with different light intensity ranges and corresponding soybean growth cycles; and the scheme determination module is specifically used to perform the following steps: Determine the growth cycle of soybeans at the current point in time; Determine the light intensity interval to which the light intensity prediction information for each sub-region belongs; The irrigation and fertilization schemes that are related to the light intensity range of the light intensity prediction information of each sub-region and the growth cycle of soybeans at the current time point in the preset set of irrigation and fertilization schemes are taken as the irrigation and fertilization schemes of each sub-region at the current time point. The neural network model is a recurrent neural network model, a unidirectional long short-term memory network model, or a gated recurrent unit model; The neural network model is trained in the following manner: Obtain historical light intensity sample data for all sub-regions of the first region throughout the entire growth cycle of soybeans; The training set of the neural network model is determined based on the historical light intensity sample data; wherein each sample data in the training set is the light intensity data of each sub-region over a period of time, and the label of each sample data is the light intensity data of a soybean fertilization cycle after the period of time. The neural network model is trained based on the training set until it meets a preset training cutoff condition.

4. An optimized irrigation and fertilization system for intercropping corn and soybeans, characterized in that, include: processor; as well as A memory, connected to the processor, for providing the processor with instructions to perform the following processing steps: At the current time point, historical light intensity information of a first region is acquired; wherein soybeans are planted in the first region, and corn is planted in a second region adjacent to the first region; the first region includes at least two sub-regions arranged sequentially in a direction away from the second region; the historical light intensity information includes the historical light intensity information of all sub-regions; each sub-region is provided with a photosensitive sensor at intervals, and the interval between the photosensitive sensors in all sub-regions arranged sequentially in a direction away from the second region increases sequentially; light intensity information of each sub-region is collected through the corresponding photosensitive sensor; a drip irrigation pipe for irrigation and fertilization is installed at the location where the photosensitive sensor is set in each sub-region; Based on the historical light intensity information, a pre-trained neural network model is used to determine the predicted light intensity information for each sub-region within a preset time period after the current time point; wherein, the preset time period is the next fertilization cycle for the soybean; the predicted light intensity information reflects the degree of influence of the corn shading effect on the light reception of each sub-region; and Based on the light intensity prediction information, an irrigation and fertilization scheme for each sub-region at the current time point is determined from a preset set of irrigation and fertilization schemes; wherein, the set of irrigation and fertilization schemes includes various possible irrigation and fertilization schemes for different light conditions and soybean growth stages; The step of determining the predicted illumination intensity for each sub-region within a preset time period after the current time point using a pre-trained neural network model based on the historical illumination intensity information includes: Determine the length of time within a preset time period after the current time point; wherein, the length of time is the time from the current time point until the end of the next soybean fertilization cycle; For each sub-region, the historical illumination intensity information of the sub-region and the time length are input into the pre-trained neural network model to determine the illumination intensity prediction information of the sub-region within a preset time period after the current time point; The different irrigation and fertilization schemes in the set of irrigation and fertilization schemes are correlated with different light intensity ranges and corresponding soybean growth cycles; and, determining the irrigation and fertilization scheme for each sub-region at the current time point from the preset set of irrigation and fertilization schemes based on the light intensity prediction information includes: Determine the growth cycle of soybeans at the current point in time; Determine the light intensity interval to which the light intensity prediction information for each sub-region belongs; The irrigation and fertilization schemes that are related to the light intensity range of the light intensity prediction information of each sub-region and the growth cycle of soybeans at the current time point in the preset set of irrigation and fertilization schemes are taken as the irrigation and fertilization schemes of each sub-region at the current time point. The neural network model is a recurrent neural network model, a unidirectional long short-term memory network model, or a gated recurrent unit model; The neural network model is trained in the following manner: Obtain historical light intensity sample data for all sub-regions of the first region throughout the entire growth cycle of soybeans; The training set of the neural network model is determined based on the historical light intensity sample data; wherein each sample data in the training set is the light intensity data of each sub-region over a period of time, and the label of each sample data is the light intensity data of a soybean fertilization cycle after the period of time. The neural network model is trained based on the training set until it meets a preset training cutoff condition.

Images