CN115952931A - Intelligent rice fertilization method, system, equipment and medium - Google Patents
Intelligent rice fertilization method, system, equipment and medium Download PDFInfo
- Publication number
- CN115952931A CN115952931A CN202310238981.2A CN202310238981A CN115952931A CN 115952931 A CN115952931 A CN 115952931A CN 202310238981 A CN202310238981 A CN 202310238981A CN 115952931 A CN115952931 A CN 115952931A
- Authority
- CN
- China
- Prior art keywords
- fertilization
- planned
- crop
- amount
- fertilizing amount
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000004720 fertilization Effects 0.000 title claims abstract description 108
- 235000007164 Oryza sativa Nutrition 0.000 title claims abstract description 54
- 235000009566 rice Nutrition 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 42
- 240000007594 Oryza sativa Species 0.000 title abstract 2
- 239000002689 soil Substances 0.000 claims abstract description 53
- 230000015654 memory Effects 0.000 claims abstract description 49
- 238000003062 neural network model Methods 0.000 claims abstract description 47
- 235000015097 nutrients Nutrition 0.000 claims abstract description 45
- 238000012549 training Methods 0.000 claims abstract description 24
- 230000007787 long-term memory Effects 0.000 claims abstract description 16
- 230000006403 short-term memory Effects 0.000 claims abstract description 16
- 238000009963 fulling Methods 0.000 claims abstract description 13
- 241000209094 Oryza Species 0.000 claims description 52
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims description 46
- 229910052757 nitrogen Inorganic materials 0.000 claims description 23
- 239000003337 fertilizer Substances 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 19
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 claims description 16
- 239000011591 potassium Substances 0.000 claims description 16
- 229910052700 potassium Inorganic materials 0.000 claims description 16
- 238000003860 storage Methods 0.000 claims description 16
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 14
- 229910052698 phosphorus Inorganic materials 0.000 claims description 14
- 239000011574 phosphorus Substances 0.000 claims description 14
- 238000005904 alkaline hydrolysis reaction Methods 0.000 claims description 10
- 230000035558 fertility Effects 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 7
- 238000004519 manufacturing process Methods 0.000 claims description 6
- 239000000618 nitrogen fertilizer Substances 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 4
- 239000002686 phosphate fertilizer Substances 0.000 claims description 3
- 150000001875 compounds Chemical class 0.000 description 3
- 241000196324 Embryophyta Species 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 235000013339 cereals Nutrition 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000002035 prolonged effect Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- KWYUFKZDYYNOTN-UHFFFAOYSA-M Potassium hydroxide Chemical compound [OH-].[K+] KWYUFKZDYYNOTN-UHFFFAOYSA-M 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000012364 cultivation method Methods 0.000 description 1
- 238000012136 culture method Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 229940072033 potash Drugs 0.000 description 1
- 235000015320 potassium carbonate Nutrition 0.000 description 1
- BWHMMNNQKKPAPP-UHFFFAOYSA-L potassium carbonate Substances [K+].[K+].[O-]C([O-])=O BWHMMNNQKKPAPP-UHFFFAOYSA-L 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
Images
Abstract
The invention discloses an intelligent rice fertilization method, system, equipment and medium, which comprises the steps of obtaining soil nutrient data and historical planting data of planned crops in a region to be fertilized, calculating the fertilization amount of the planned crops according to the soil nutrient data, inputting the historical planting data into a preset initial long-short term memory neural network model for training, and obtaining a trained long-short term memory neural network model; and a fertilizing amount predicted value of the area to be fertilized is predicted through the long-term and short-term memory neural network model, and a final fertilizing amount value is calculated according to the bottom-tucking strategy, the planned crop fertilizing amount and the planned crop fertilizing amount predicted value, so that the fertilizing cost is reduced, and the quality of planned crops is improved.
Description
Technical Field
The invention relates to the technical field related to intelligent fertilization, in particular to an intelligent rice fertilization method, system, equipment and medium.
Background
The rice is one of the main grain crops in China, and the yield of the rice not only influences the development of agricultural economy, but also influences the life of people. The management of the whole growth cycle of the rice plays a decisive role in the final yield and quality, and the fertilization in the growth cycle of the rice directly influences the yield and quality.
However, at present, farmers have the problems of blind fertilization and excessive fertilization on rice planting, unnecessary fertilizer waste is caused, certain pollution is caused to the environment, quality safety of agricultural products is threatened, and the farmers know the growth conditions and culture methods of crops cultured by other farmers mutually due to no hidden means in the operation process, and inevitably generate inertia thinking so as to simulate the maintenance mode of other people, so that experimental diversity is possibly deteriorated in experiments, the experimental period is prolonged, even a certain wrong method is possibly adopted in a large amount to cause large-area death of plants, the practicability is poor, meanwhile, the traditional rice planting mainly depends on manual empirical judgment, but the method is limited by factors such as manual fatigue, subjectivity, timeliness and the like, and disastrous loss is caused on monitoring and processing of abnormal states of rice.
Disclosure of Invention
The present invention is directed to at least solving the problems of the prior art. Therefore, the invention provides an intelligent rice fertilization method, system, equipment and medium, which can improve the utilization rate of fertilizer, reduce fertilization cost and improve the quality of planned crops.
The invention provides a first aspect of an intelligent rice fertilization method, which comprises the following steps:
acquiring soil nutrient data and historical planting data of planned crops in a to-be-fertilized area;
calculating a planned crop fertilizing amount according to the soil nutrient data;
inputting the historical planting data into a preset initial long-short term memory neural network model for training to obtain a trained long-short term memory neural network model; predicting a fertilizing amount predicted value of the area to be fertilized through the long-term and short-term memory neural network model;
and calculating to obtain a final fertilization quantity value according to the bottom-tucking strategy, the plan crop fertilization quantity and the plan crop fertilization quantity predicted value.
According to the embodiment of the invention, at least the following technical effects are achieved:
the method comprises the steps of obtaining soil nutrient data and historical planting data of planned crops in a to-be-fertilized area, calculating the fertilizing amount of the planned crops according to the soil nutrient data, inputting the historical planting data into a preset initial long-short term memory neural network model for training, and obtaining a trained long-short term memory neural network model; and a fertilizing amount predicted value of the area to be fertilized is predicted through the long-term and short-term memory neural network model, and a final fertilizing amount value is calculated according to the bottom-tucking strategy, the planned crop fertilizing amount and the planned crop fertilizing amount predicted value, so that the fertilizing cost is reduced, and the quality of planned crops is improved.
According to some embodiments of the invention, the soil nutrient data comprises: the soil alkaline hydrolysis nitrogen, the soil quick-acting phosphorus and the soil can provide potassium.
According to some embodiments of the invention, the calculation of the planned crop fertilization amount from the soil nutrient data is according to the formula:
the method comprises the following steps of A, B, C, D, E, G, H and I, wherein A is the fertilizing amount of a planned crop, B is the total amount of nutrients required by the planned yield, C is the supply amount of soil nutrients, D is the percentage content of nitrogen, phosphorus or potassium of a chemical fertilizer, E is the current season fertilizer utilization rate of a nitrogen fertilizer, a phosphate fertilizer or a potassium fertilizer, F is a preset value of the average yield of the planned crop in 3 years exceeding a region to be fertilized, G is the approximate number value of the nutrients required by the planned crop to form 100kg of economic yield, H is the ppm of the soil nutrients collected through the data of equipment of the Internet of things, and I is a preset ecological category coefficient guide value.
According to some embodiments of the invention, the historical planting data comprises: regional planting batch in a historical period, fertilization stage, average rainfall, soil fertility alkaline hydrolysis nitrogen, available phosphorus, available potassium, average temperature, climate production potential and fertilization amount.
According to some embodiments of the present invention, the inputting the historical planting data into a preset initial long-short term memory neural network model for training to obtain a trained long-short term memory neural network model includes:
inputting the area planting batch, the fertilization stage, the average rainfall, the soil fertility alkaline-hydrolysis nitrogen, the available phosphorus, the quick-acting potassium, the average temperature, the climate production potential and the fertilization amount of the planned crops in the area to be fertilized in the historical period into the initial long-short term memory neural network model for training to obtain a planned crop fertilization amount predicted value in the historical period;
and calculating a root mean square error through a loss function according to the predicted value of the planned crop fertilizing amount in the historical time period and the fertilizing amount in the historical time period, and ending the training if the root mean square error meets a preset value or the iteration times reach the maximum times to obtain the trained long-short term memory neural network model.
According to some embodiments of the invention, the calculating the final fertilization amount value according to the bottom-digging strategy, the planned crop fertilization amount and the planned crop fertilization amount predicted value comprises:
and if the difference value between the planned crop fertilizing amount and the planned crop fertilizing amount predicted value is within the preset range of the bottom-digging strategy, the planned crop fertilizing amount predicted value is the final fertilizing amount value, and if the difference value between the planned crop fertilizing amount and the planned crop fertilizing amount predicted value is larger than the preset range of the bottom-digging strategy, the planned crop fertilizing amount is the final fertilizing amount value.
According to some embodiments of the invention, the calculation formula for calculating the root mean square error according to the predicted value of the planned crop fertilization amount in the historical time period and the fertilization amount in the historical time period through the loss function is as follows:
wherein the content of the first and second substances,is root mean square error->Is the ^ th or ^ th on a batch>The true value of the individual data, and>is the predicted value output by the model.
In a second aspect of the present invention, there is provided an intelligent fertilization system for rice, comprising:
the data acquisition module is used for acquiring soil nutrient data and historical planting data of planned crops in the area to be fertilized;
the planned crop fertilizing amount calculating module is used for calculating planned crop fertilizing amount according to the soil nutrient data;
the planned crop fertilization amount predicted value calculation module is used for inputting the historical planting data into a preset initial long-short term memory neural network model for training to obtain a trained long-short term memory neural network model; predicting a fertilizing amount predicted value of the area to be fertilized through the long-term and short-term memory neural network model;
and the final fertilization quantity value calculation module is used for calculating to obtain a final fertilization quantity value according to the bottom-tucking strategy, the plan crop fertilization quantity and the plan crop fertilization quantity predicted value.
The system obtains soil nutrient data and historical planting data of planned crops in a to-be-fertilized area, calculates the fertilizing amount of the planned crops according to the soil nutrient data, inputs the historical planting data into a preset initial long-short term memory neural network model for training, and obtains a trained long-short term memory neural network model; and a fertilizing amount predicted value of the area to be fertilized is predicted through the long-term and short-term memory neural network model, and a final fertilizing amount value is calculated according to the bottom-tucking strategy, the planned crop fertilizing amount and the planned crop fertilizing amount predicted value, so that the fertilizing cost is reduced, and the quality of planned crops is improved.
In a third aspect of the invention, an electronic intelligent rice fertilization device is provided, which comprises at least one control processor and a memory, wherein the memory is used for being in communication connection with the at least one control processor; the memory stores instructions executable by the at least one control processor to enable the at least one control processor to perform the intelligent rice fertilization method described above.
In a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer-executable instructions for causing a computer to execute the intelligent fertilization method for rice described above.
It should be noted that the beneficial effects between the second to fourth aspects of the present invention and the prior art are the same as the beneficial effects between the above-mentioned intelligent fertilization system for rice and the prior art, and will not be described in detail here.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a flow chart of an intelligent fertilization method for rice according to an embodiment of the present invention;
FIG. 2 is a graph of accuracy of an intelligent fertilization method for rice, which is trained 200 times according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an intelligent fertilization system for rice according to an embodiment of the invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, if there are first, second, etc. described, it is only for the purpose of distinguishing technical features, and it is not understood that relative importance is indicated or implied or that the number of indicated technical features is implicitly indicated or that the precedence of the indicated technical features is implicitly indicated.
In the description of the present invention, it should be understood that the orientation or positional relationship referred to, for example, the upper, lower, etc., is indicated based on the orientation or positional relationship shown in the drawings, and is only for convenience of description and simplification of description, but does not indicate or imply that the device or element referred to must have a specific orientation, be constructed in a specific orientation, and be operated, and thus should not be construed as limiting the present invention.
In the description of the present invention, it should be noted that unless otherwise explicitly defined, terms such as setup, installation, connection, etc. should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention by combining the detailed contents of the technical solutions.
The rice is one of the main grain crops in China, and the yield of the rice not only influences the development of agricultural economy, but also influences the life of people. The management of the whole growth cycle of the rice plays a decisive role in the final yield and quality, and the fertilization in the growth cycle of the rice directly influences the yield and quality.
However, at present, farmers have the problems of blind fertilization and excessive fertilization in rice planting, which causes unnecessary waste of fertilizers and causes certain pollution to the environment, threatens the quality safety of agricultural products, and since farmers do not have hidden means in the operation process, the farmers know the growth conditions and cultivation methods of crops cultivated by other farmers mutually, and inevitably generate inertial thinking so as to simulate the maintenance mode of other people, so that the experimental diversity is possibly deteriorated in experiments, the experimental period is prolonged, even a certain wrong method is possibly adopted in a large amount, which can lead to large-area death of plants, and the practicability is poor.
In order to solve the technical defects, referring to fig. 1, the invention also provides an intelligent rice fertilization method, which comprises the following steps:
s101, acquiring soil nutrient data and historical planting data of planned crops in an area to be fertilized;
step S102, calculating a planned crop fertilizing amount according to soil nutrient data;
step S103, inputting historical planting data into a preset initial long-short term memory neural network model for training to obtain a trained long-short term memory neural network model; predicting a fertilizing amount predicted value of the area to be fertilized through a long-term and short-term memory neural network model;
and step S104, calculating to obtain a final fertilization quantity value according to the bottom-tucking strategy, the planned crop fertilization quantity and the planned crop fertilization quantity predicted value.
The method comprises the steps of obtaining soil nutrient data and historical planting data of planned crops in a to-be-fertilized area, calculating the fertilizing amount of the planned crops according to the soil nutrient data, inputting the historical planting data into a preset initial long-short term memory neural network model for training, and obtaining a trained long-short term memory neural network model; and a fertilizing amount predicted value of the area to be fertilized is predicted through the long-term and short-term memory neural network model, and a final fertilizing amount value is calculated according to the bottom-tucking strategy, the planned crop fertilizing amount and the planned crop fertilizing amount predicted value, so that the fertilizing cost is reduced, and the quality of planned crops is improved.
In some embodiments, data collection of different policies is performed by different types of internet of things devices.
In some embodiments, the bottom-tucking strategy is to warn when the difference between the planned crop fertilizing amount and the planned crop fertilizing amount predicted value exceeds 10%.
In some embodiments, the soil nutrient data comprises: the soil alkaline hydrolysis nitrogen, the soil quick-acting phosphorus and the soil can provide potassium.
In some embodiments, the calculation of the planned amount of crop fertilizer to be applied from the soil nutrient data is according to the formula:
the method comprises the following steps of A, B, C, D, E, G, H and I, wherein A is the fertilizing amount of a planned crop, B is the total amount of nutrients required by the planned yield, C is the supply amount of soil nutrients, D is the percentage content of nitrogen, phosphorus or potassium of a chemical fertilizer, E is the current season fertilizer utilization rate of a nitrogen fertilizer, a phosphorus fertilizer or a potassium fertilizer, F is a preset value of the average yield of the planned crop in 3 years exceeding a region to be fertilized, G is the approximate number value of the nutrients required by the planned crop to form 100kg of economic yield, H is the ppm of the soil nutrients collected through the data of equipment of the Internet of things, and I is a preset ecological category coefficient guide value.
In some embodiments, the historical planting data comprises: regional planting batch in a historical period, fertilization stage, average rainfall, soil fertility alkaline hydrolysis nitrogen, available phosphorus, available potassium, average temperature, climate production potential and fertilization amount.
In some embodiments, inputting the historical planting data into a preset initial long-short term memory neural network model for training to obtain a trained long-short term memory neural network model, including:
inputting the area planting batch, the fertilization stage, the average rainfall, the soil fertility alkaline-hydrolysis nitrogen, the available phosphorus, the quick-acting potassium, the average temperature, the climate production potential and the fertilization amount of the planned crops in the area to be fertilized in the historical period into an initial long-short term memory neural network model for training to obtain a planned crop fertilization amount predicted value in the historical period;
and calculating a root mean square error through a loss function according to the predicted value of the fertilizing amount of the planned crops in the historical time period and the fertilizing amount in the historical time period, and ending the training if the root mean square error meets a preset value or the iteration times reach the maximum times to obtain a trained long-short term memory neural network model.
In some embodiments, calculating the final fertilization quantity value according to the bottom-spading strategy, the planned crop fertilization quantity and the planned crop fertilization quantity predicted value comprises:
and if the difference value between the planned crop fertilization amount and the planned crop fertilization amount predicted value is within the preset range of the bottom-digging strategy, the planned crop fertilization amount predicted value is a final fertilization amount value, and if the difference value between the planned crop fertilization amount and the planned crop fertilization amount predicted value is larger than the preset range of the bottom-digging strategy, the planned crop fertilization amount is the final fertilization amount value.
In some embodiments, the calculation formula for calculating the root mean square error according to the predicted value of the planned crop fertilization amount in the historical period and the fertilization amount in the historical period through the loss function is as follows:
wherein the content of the first and second substances,in root mean square error->Is the ^ th or ^ th on a batch>The true value of the individual data, and>is the predicted value output by the model.
To facilitate understanding by those skilled in the art, a set of experimental data is provided below:
the accuracy of the final fertilizing amount is verified by practice drilling through the technical scheme on the basis of taking the Hunan Dongting lake area of Hunan province of China as an experimental test point and taking the latest 1 year calendar history data of a plurality of points in the area as the basis.
Constructing a fertilization model by taking the ecological early rice as an example of fertilization types and nitrogen fertilizer (the nitrogen fertilizer has the most obvious influence on the yield);
1. basic parameter configuration, the main parameter configuration is as follows:
ecological classification: early rice
Rice variety: intelligent rice 01
Target yield: 450 kg/mu
And (3) fertilizing strategies: compound fertilizer
2. Calculation of soil nutrient supply
The correction coefficient of available nutrients of early rice is as follows:
the soil monitoring data (average) of the planting area are as follows:
the following calculation is carried out:
3. calculation of amount of nitrogen applied
The national standard rice crop has the following approximate quantity table of nutrients required for forming 100kg economic yield:
generally, the current season utilization rate of the fertilizer is as follows: 30-35% of nitrogenous fertilizer, 20-25% of phosphate fertilizer and 25-35% of potash fertilizer.
The first step is as follows: calculating the total nutrient demand
Nitrogen (N): (450/100) × 2.0= 9kg;
the second step is that: calculating the nutrient supply of soil
Nitrogen (N): 118 × 0.0504=5.9kg;
the third step: calculating the fertilizer requirement of the crops
9 - 5.9 = 3.1 ;
The fourth step: selecting compound fertilizer
15-15-15 composite fertilizer
The fifth step: calculating the amount of the compound fertilizer
3.1 /(15%×35%)= 59 kg;
And a sixth step: nitrogen application amount per mu
According to the calculation scheme, the nitrogen application amount per mu is 8.9 kg/mu, the table below shows the nitrogen application amount of the state city rice non-use ecological area newly given by the official of Hunan province, the table below shows the newly recommended nitrogen application amount of 8.5 kg/mu given by the illustrated early season rice and the Hunan province North Hunting lake area, the calculation of the scheme is 8.9 kg/mu, the difference between the nitrogen application amount and the nitrogen application amount is 0.4 kg/mu, the nitrogen application amount is within the upper limit of 10 kg/mu, and the actual situation is relatively met.
4. Analyzing a long and short term memory neural network model of fertilizing amount:
the environment and version built by the long-short term memory neural network model are not lower than ancnda 3.0; python3.8; 10.1 of a pyrtch; cuda10.2.89; a deep learning framework is adopted as a pitorch network architecture; data input is performed by json, analysis data of the past years including currently predicted data are stored in a mysql database, and training is performed 200 times and optimal training weights are saved.
Preparing data: the method mainly comprises 7 columns (date, average rainfall, soil fertility alkaline hydrolysis nitrogen (mg/kg), available phosphorus (mg/kg), quick-acting potassium (mg/kg) and average temperature (DEG C)), wherein historical data of the lake region of North Hunan Dongchun are taken for prediction, 200 pieces of training data are obtained, and part of sample data are as follows:
wherein the fertilizing amount is a value to be predicted, and the accuracy after 200 times of training is shown in figure 2.
And according to the model prediction result, the prediction result is in accordance with the expectation, a bottom-holding strategy analysis is finally carried out aiming at the prediction result to ensure the accuracy of the final fertilizing amount, if the difference between the prediction result and the fertilizing amount calculated by the fertilizing model exceeds 10%, an early warning is carried out, otherwise, the prediction value is used as the final fertilizing amount to be output.
In addition, referring to fig. 3, an embodiment of the present invention provides an intelligent fertilization system for rice, including a data acquisition module 1100, a planned crop fertilization amount calculation module 1200, a planned crop fertilization amount predicted value calculation module 1300, and a final fertilization amount value calculation module 1400, wherein:
the data acquisition module 1100 is used for acquiring soil nutrient data and historical planting data of planned crops in a to-be-fertilized area;
the planned crop fertilizing amount calculating module 1200 is used for calculating planned crop fertilizing amount according to soil nutrient data;
the planned crop fertilizing amount predicted value calculating module 1300 is used for inputting historical planting data into a preset initial long and short term memory neural network model for training to obtain a trained long and short term memory neural network model; predicting a fertilizing amount predicted value of the area to be fertilized through a long-term and short-term memory neural network model;
and the final fertilization quantity value calculation module 1400 is used for calculating a final fertilization quantity value according to the bottom-tucking strategy, the plan crop fertilization quantity and the plan crop fertilization quantity predicted value.
The system obtains soil nutrient data and historical planting data of planned crops in a to-be-fertilized area, calculates the fertilizing amount of the planned crops according to the soil nutrient data, inputs the historical planting data into a preset initial long-short term memory neural network model for training, and obtains a trained long-short term memory neural network model; and a fertilizing amount predicted value of the area to be fertilized is predicted through the long-term and short-term memory neural network model, and a final fertilizing amount value is calculated according to the bottom-tucking strategy, the planned crop fertilizing amount and the planned crop fertilizing amount predicted value, so that the fertilizing cost is reduced, and the quality of planned crops is improved.
It should be noted that the embodiment of the present system and the embodiment of the system described above are based on the same inventive concept, and therefore, the related contents of the embodiment of the method described above are also applicable to the embodiment of the present system, and are not described herein again.
The application also provides a rice intelligence electronic equipment that fertilizies, includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor when executing the computer program implementing: the intelligent rice fertilization method is as described above.
The processor and memory may be connected by a bus or other means.
The memory, as a non-transitory computer-readable storage medium, may be used to store non-transitory software programs as well as non-transitory computer-executable programs. Further, the memory may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory located remotely from the processor, and these remote memories may be connected to the processor through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The non-transitory software programs and instructions required to implement the intelligent fertilization method for rice of the above-mentioned embodiment are stored in the memory, and when being executed by the processor, the intelligent fertilization method for rice of the above-mentioned embodiment is performed, for example, the method steps S101 to S104 in fig. 1 described above are performed.
The present application further provides a computer-readable storage medium having stored thereon computer-executable instructions for performing: the intelligent rice fertilization method is as described above.
The computer-readable storage medium stores computer-executable instructions, which are executed by a processor or controller, for example, by a processor in the above-mentioned embodiment of the electronic device, and can make the processor execute the intelligent fertilization method for rice in the above-mentioned embodiment, for example, execute the above-mentioned steps S101 to S104 of the method in fig. 1.
One of ordinary skill in the art will appreciate that all or some of the steps, systems, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program elements or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program elements, or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as is well known to those of ordinary skill in the art.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (10)
1. An intelligent fertilization method for rice is characterized by comprising the following steps:
acquiring soil nutrient data and historical planting data of planned crops in a to-be-fertilized area;
calculating a planned crop fertilizing amount according to the soil nutrient data;
inputting the historical planting data into a preset initial long-short term memory neural network model for training to obtain a trained long-short term memory neural network model; predicting a fertilizing amount predicted value of the area to be fertilized through the long-term and short-term memory neural network model;
and calculating to obtain a final fertilization quantity value according to the bottom-tucking strategy, the plan crop fertilization quantity and the plan crop fertilization quantity predicted value.
2. The intelligent fertilization method for rice as claimed in claim 1, wherein the soil nutrient data comprises: the soil alkaline hydrolysis nitrogen, the soil quick-acting phosphorus and the soil can provide potassium.
3. The intelligent fertilization method for rice as claimed in claim 2, wherein the calculation formula for calculating the planned crop fertilization amount according to the soil nutrient data is as follows:
the method comprises the following steps of A, B, C, D, E, G, H and I, wherein A is the fertilizing amount of a planned crop, B is the total amount of nutrients required by the planned yield, C is the supply amount of soil nutrients, D is the percentage content of nitrogen, phosphorus or potassium of a chemical fertilizer, E is the current season fertilizer utilization rate of a nitrogen fertilizer, a phosphate fertilizer or a potassium fertilizer, F is a preset value of the average yield of the planned crop in 3 years exceeding a region to be fertilized, G is the approximate number value of the nutrients required by the planned crop to form 100kg of economic yield, H is the ppm of the soil nutrients collected through the data of equipment of the Internet of things, and I is a preset ecological category coefficient guide value.
4. The intelligent fertilization method for rice as claimed in claim 3, wherein the historical planting data comprises: regional planting batch in a historical period, fertilization stage, average rainfall, soil fertility alkaline hydrolysis nitrogen, available phosphorus, available potassium, average temperature, climate production potential and fertilization amount.
5. The intelligent fertilization method for rice according to claim 4, wherein the step of inputting the historical planting data into a preset initial long-short term memory neural network model for training to obtain a trained long-short term memory neural network model comprises the following steps:
inputting the area planting batch, the fertilization stage, the average rainfall, the soil fertility alkaline-hydrolysis nitrogen, the available phosphorus, the quick-acting potassium, the average temperature, the climate production potential and the fertilization amount of the planned crops in the area to be fertilized in the historical period into the initial long-short term memory neural network model for training to obtain a planned crop fertilization amount predicted value in the historical period;
and calculating a root mean square error through a loss function according to the predicted value of the planned crop fertilizing amount in the historical time period and the fertilizing amount in the historical time period, and ending the training if the root mean square error meets a preset value or the iteration times reach the maximum times to obtain the trained long-short term memory neural network model.
6. The intelligent fertilization method of rice as claimed in claim 5, wherein the step of calculating a final fertilization quantity value according to the bottom-tucking strategy, the planned crop fertilization quantity and the planned crop fertilization quantity predicted value comprises:
and if the difference value between the planned crop fertilizing amount and the planned crop fertilizing amount predicted value is within the preset range of the bottom-digging strategy, the planned crop fertilizing amount predicted value is the final fertilizing amount value, and if the difference value between the planned crop fertilizing amount and the planned crop fertilizing amount predicted value is larger than the preset range of the bottom-digging strategy, the planned crop fertilizing amount is the final fertilizing amount value.
7. The intelligent rice fertilization method of claim 6, wherein the calculation formula for calculating the root mean square error according to the predicted planned crop fertilization amount in the historical time period and the fertilization amount in the historical time period through the loss function is as follows:
8. An intelligent rice fertilization system is characterized in that the intelligent rice fertilization method comprises the following steps:
the data acquisition module is used for acquiring soil nutrient data and historical planting data of planned crops in the area to be fertilized;
the planned crop fertilizing amount calculating module is used for calculating planned crop fertilizing amount according to the soil nutrient data;
the planned crop fertilizing amount predicted value calculation module is used for inputting the historical planting data into a preset initial long and short term memory neural network model for training to obtain a trained long and short term memory neural network model; predicting a fertilizing amount predicted value of the area to be fertilized through the long-term and short-term memory neural network model;
and the final fertilization quantity value calculation module is used for calculating to obtain a final fertilization quantity value according to the bottom-tucking strategy, the plan crop fertilization quantity and the plan crop fertilization quantity predicted value.
9. The intelligent rice fertilizing equipment is characterized by comprising at least one control processor and a memory, wherein the memory is in communication connection with the at least one control processor; the memory stores instructions executable by the at least one control processor to enable the at least one control processor to perform a method of intelligent fertilization of rice as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium characterized by: the computer-readable storage medium stores computer-executable instructions for causing a computer to perform a method for intelligent fertilization of rice as recited in any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310238981.2A CN115952931A (en) | 2023-03-14 | 2023-03-14 | Intelligent rice fertilization method, system, equipment and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310238981.2A CN115952931A (en) | 2023-03-14 | 2023-03-14 | Intelligent rice fertilization method, system, equipment and medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115952931A true CN115952931A (en) | 2023-04-11 |
Family
ID=87282825
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310238981.2A Pending CN115952931A (en) | 2023-03-14 | 2023-03-14 | Intelligent rice fertilization method, system, equipment and medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115952931A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117322214A (en) * | 2023-11-30 | 2024-01-02 | 余姚市农业技术推广服务总站 | Crop fertilizer accurate application method and system based on neural network |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101578936A (en) * | 2009-05-27 | 2009-11-18 | 中国农业大学 | Fertilization processing method and system |
CN103823371A (en) * | 2014-02-12 | 2014-05-28 | 无锡中科智能农业发展有限责任公司 | Neural network model-based agricultural precise fertilization system and fertilization method thereof |
CN108811651A (en) * | 2018-05-29 | 2018-11-16 | 安徽润航农业科技开发有限公司 | A kind of method of fertilization compositions based on earth measurement |
CN111427296A (en) * | 2020-04-17 | 2020-07-17 | 天津蓝迪科农业科技有限公司 | Fertilization control system of refined cultivation technology |
CN115530054A (en) * | 2022-10-12 | 2022-12-30 | 河北省科学院应用数学研究所 | Irrigation control method and device, electronic equipment and storage medium |
-
2023
- 2023-03-14 CN CN202310238981.2A patent/CN115952931A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101578936A (en) * | 2009-05-27 | 2009-11-18 | 中国农业大学 | Fertilization processing method and system |
CN103823371A (en) * | 2014-02-12 | 2014-05-28 | 无锡中科智能农业发展有限责任公司 | Neural network model-based agricultural precise fertilization system and fertilization method thereof |
CN108811651A (en) * | 2018-05-29 | 2018-11-16 | 安徽润航农业科技开发有限公司 | A kind of method of fertilization compositions based on earth measurement |
CN111427296A (en) * | 2020-04-17 | 2020-07-17 | 天津蓝迪科农业科技有限公司 | Fertilization control system of refined cultivation technology |
CN115530054A (en) * | 2022-10-12 | 2022-12-30 | 河北省科学院应用数学研究所 | Irrigation control method and device, electronic equipment and storage medium |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117322214A (en) * | 2023-11-30 | 2024-01-02 | 余姚市农业技术推广服务总站 | Crop fertilizer accurate application method and system based on neural network |
CN117322214B (en) * | 2023-11-30 | 2024-02-09 | 余姚市农业技术推广服务总站 | Crop fertilizer accurate application method and system based on neural network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11625798B2 (en) | Environmental management zone modeling and analysis | |
CN108781926B (en) | Greenhouse irrigation system and method based on neural network prediction | |
US20160309646A1 (en) | Agronomic systems, methods and apparatuses | |
CN111557159B (en) | Water and fertilizer integrated machine control system with crop nutrient demand analysis function and control method thereof | |
Wang et al. | Environmental costs and mitigation potential in plastic-greenhouse pepper production system in China: A life cycle assessment | |
CN107392376A (en) | A kind of crops Meteorological Output Forecasting Methodology and system | |
CN105494033B (en) | A kind of intelligent water-saving irrigation method based on crop demand | |
CN108077042A (en) | A kind of winter wheat time of infertility irrigates early warning decision method | |
CN115952931A (en) | Intelligent rice fertilization method, system, equipment and medium | |
Reetz et al. | 4R nutrient stewardship: A global framework for sustainable fertilizer management | |
CN115629585A (en) | Planting management method and system for smart agriculture | |
CN117063818A (en) | Accurate regulation and control system of liquid manure | |
JP2016146046A (en) | Predictor, prediction method and program | |
Saha et al. | Precision Agriculture Using Internet of Things and Wireless Sensor Networks | |
CN117314024B (en) | Wisdom agricultural insect pest cloud platform | |
CN117016151A (en) | Intelligent agricultural water and fertilizer integrated irrigation system | |
CN115392016A (en) | Silage corn growth and development prediction method based on remote sensing data assimilation | |
CN213848015U (en) | Crop water-saving irrigation measurement and control system based on multi-source information fusion | |
Battilani | Fertirrigere V2. 11: a multi-target DSS to manage water and nutrient supply at macrozone level | |
CN116595333B (en) | Soil-climate intelligent rice target yield and nitrogen fertilizer consumption determination method | |
Guzmán et al. | Risk management system for the monitoring and control of a small lettuce greenhouse | |
Wang et al. | The application of the internet of things technology in apple production | |
Hunt et al. | Dividing the risk-theoretical exploration of increasing N management temporal granularity in maize | |
CN103636340B (en) | Method for applying fertilizer in fruiting period according to fruit growth speed of crops | |
CN113867456B (en) | Greenhouse intelligent monitoring method and system based on Internet of things technology |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230411 |