CN116485210B - Neural network-based method and device for generating emission reduction strategy of agricultural management activity - Google Patents
Neural network-based method and device for generating emission reduction strategy of agricultural management activity Download PDFInfo
- Publication number
- CN116485210B CN116485210B CN202310699503.1A CN202310699503A CN116485210B CN 116485210 B CN116485210 B CN 116485210B CN 202310699503 A CN202310699503 A CN 202310699503A CN 116485210 B CN116485210 B CN 116485210B
- Authority
- CN
- China
- Prior art keywords
- neural network
- data
- initial
- agricultural management
- generating
- 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.)
- Active
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 243
- 230000000694 effects Effects 0.000 title claims abstract description 140
- 230000009467 reduction Effects 0.000 title claims abstract description 117
- 238000000034 method Methods 0.000 title claims abstract description 34
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims abstract description 162
- 229910052799 carbon Inorganic materials 0.000 claims abstract description 162
- 238000012549 training Methods 0.000 claims abstract description 82
- 239000005431 greenhouse gas Substances 0.000 claims description 45
- 230000006870 function Effects 0.000 claims description 33
- 230000005284 excitation Effects 0.000 claims description 28
- 239000007789 gas Substances 0.000 claims description 21
- 238000004140 cleaning Methods 0.000 claims description 15
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 239000013598 vector Substances 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 abstract description 6
- 238000013473 artificial intelligence Methods 0.000 abstract description 6
- 238000007726 management method Methods 0.000 description 94
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 8
- GQPLMRYTRLFLPF-UHFFFAOYSA-N Nitrous Oxide Chemical compound [O-][N+]#N GQPLMRYTRLFLPF-UHFFFAOYSA-N 0.000 description 8
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 229910002092 carbon dioxide Inorganic materials 0.000 description 4
- 239000001569 carbon dioxide Substances 0.000 description 4
- 239000003337 fertilizer Substances 0.000 description 4
- 239000001272 nitrous oxide Substances 0.000 description 4
- 239000012773 agricultural material Substances 0.000 description 3
- 238000003973 irrigation Methods 0.000 description 3
- 230000002262 irrigation Effects 0.000 description 3
- 244000144972 livestock Species 0.000 description 3
- 239000000575 pesticide Substances 0.000 description 3
- 244000105624 Arachis hypogaea Species 0.000 description 2
- 240000002791 Brassica napus Species 0.000 description 2
- 244000068988 Glycine max Species 0.000 description 2
- 235000010469 Glycine max Nutrition 0.000 description 2
- 241000209140 Triticum Species 0.000 description 2
- 235000021307 Triticum Nutrition 0.000 description 2
- 240000008042 Zea mays Species 0.000 description 2
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 2
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 235000005822 corn Nutrition 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000002283 diesel fuel Substances 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 235000020232 peanut Nutrition 0.000 description 2
- 239000004033 plastic Substances 0.000 description 2
- 229920003023 plastic Polymers 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 235000017060 Arachis glabrata Nutrition 0.000 description 1
- 235000010777 Arachis hypogaea Nutrition 0.000 description 1
- 235000018262 Arachis monticola Nutrition 0.000 description 1
- 238000012935 Averaging Methods 0.000 description 1
- 241000283690 Bos taurus Species 0.000 description 1
- 235000011293 Brassica napus Nutrition 0.000 description 1
- 235000004977 Brassica sinapistrum Nutrition 0.000 description 1
- 241000283707 Capra Species 0.000 description 1
- 241000283086 Equidae Species 0.000 description 1
- 241000283074 Equus asinus Species 0.000 description 1
- 241001331845 Equus asinus x caballus Species 0.000 description 1
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 241001494479 Pecora Species 0.000 description 1
- 241000282887 Suidae Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002550 fecal effect Effects 0.000 description 1
- 238000000855 fermentation Methods 0.000 description 1
- 230000004151 fermentation Effects 0.000 description 1
- 230000000968 intestinal effect Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 235000015112 vegetable and seed oil Nutrition 0.000 description 1
- 239000008158 vegetable oil Substances 0.000 description 1
- 235000013311 vegetables Nutrition 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/84—Greenhouse gas [GHG] management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Business, Economics & Management (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Mining & Mineral Resources (AREA)
- Marine Sciences & Fisheries (AREA)
- Animal Husbandry (AREA)
- Probability & Statistics with Applications (AREA)
- Agronomy & Crop Science (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, and discloses an emission reduction strategy generation method and device for agricultural management activities based on a neural network, wherein the method comprises the following steps: initializing a preset neural network structure to obtain an initial neural network; generating a training set by using the acquired historical data of the agricultural management activities; inputting the training set into the initial neural network to obtain an initial output value, and updating the weight of the initial neural network according to the initial output value to obtain an updated neural network; acquiring real-time data of agricultural management activities, and generating classification data of the real-time data by using an updated neural network; generating real-time carbon emission of the agricultural management activity according to the classification data and a preset carbon emission algorithm; and generating an emission reduction value of the agricultural management activity according to the real-time carbon emission and the historical data, and generating an emission reduction strategy of the agricultural management activity by using the emission reduction value. The invention can improve the accuracy of agricultural carbon emission analysis.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an emission reduction strategy generation method and device for agricultural management activities based on a neural network.
Background
At present, the world is faced with a great challenge of climate change, agriculture is an important source of greenhouse gas emission in China, and the carbon emission amount of the agricultural greenhouse gas emission is about 17% of the total carbon emission amount in China. With the increase of population size and the acceleration of the urbanization process, the amount of arable land available for agricultural production is gradually reduced, and the amount of arable land is hard to match with the population amount, which means that the agricultural yield must keep a stable growth speed in the future, but the carbon emission amount needs to be controlled.
At present, the analysis of the agricultural carbon emission mainly uses a gray prediction model to analyze the future development trend of the carbon emission, and is only suitable for the middle-short-term agricultural carbon emission analysis and the agricultural carbon emission which is similar to exponential growth, so that the error of the accuracy of the agricultural carbon emission analysis can lead to the wrong implementation of an emission reduction strategy, and therefore, how to improve the accuracy of the agricultural carbon emission analysis in the prior art becomes a problem to be solved urgently.
Disclosure of Invention
The invention provides an emission reduction strategy generation method and device for agricultural management activities based on a neural network, and mainly aims to solve the problem of low accuracy of agricultural carbon emission analysis in the prior art.
In order to achieve the above object, the present invention provides a method for generating an emission reduction strategy for agricultural management activities based on a neural network, including:
establishing an initial neural network;
acquiring historical data of agricultural management activities, and generating a training set of the initial neural network by utilizing the historical data;
inputting training values in the training set into the initial neural network to obtain initial output values of the initial neural network, and updating weights of the initial neural network according to node output values in the initial output values to obtain updated neural network of the initial neural network;
acquiring real-time data of the agricultural management activity, and performing data classification on the real-time data by utilizing the updated neural network to obtain classified data of the real-time data;
generating real-time carbon emission of the agricultural management activity according to the classification data and a preset carbon emission algorithm, wherein the preset carbon emission algorithm is as follows:
；
wherein ,is the real-time carbon emission of the agricultural management activities, < >>Is +.o in the agricultural management activities>Agricultural carbon source emission-like +.>Greenhouse gas like->Is->Conversion coefficient of greenhouse gases and standard carbon, +. >A carbon source class identifier of said agricultural carbon source,/-for>A gas class identifier of said greenhouse gas, +.>Is the total number of carbon source categories of the agricultural carbon source, < > or->Is the total number of gas categories of the greenhouse gas;
and generating an emission reduction value of the agricultural management activity according to the real-time carbon emission and the historical data, and generating an emission reduction strategy of the agricultural management activity by using the emission reduction value.
Optionally, the establishing an initial neural network includes:
initial parameter configuration is carried out on a preset neural network structure, and a parameter neural network of the preset neural network structure is obtained;
and performing excitation function configuration on the parameter neural network to obtain an excitation function neural network of the parameter neural network, and determining the excitation function neural network as an initial neural network of the preset neural network structure.
Optionally, the generating the training set of the initial neural network by using the historical data includes:
extracting features of the historical data to obtain data features of the historical data;
carrying out feature identification on the data features to obtain feature labels of the data features;
and generating a training set of the initial neural network according to the characteristic labels and the data characteristics.
Optionally, the feature extracting the historical data to obtain the data feature of the historical data includes:
performing data cleaning on the historical data to obtain cleaning data of the historical data;
performing data vectorization on the cleaning data to obtain a data vector of the cleaning data;
and carrying out feature dimension reduction on the data vector to obtain the data features of the historical data.
Optionally, the inputting the training values in the training set to the initial neural network to obtain an initial output value of the initial neural network includes:
determining an excitation function of the initial neural network, and generating an output algorithm of the initial neural network according to the excitation function;
performing numerical operation on training values in the training set by using the output algorithm to obtain a layer output value of the initial neural network, wherein the output algorithm is as follows:
；
wherein ,is the +.o of the initial neural network>Node output values of the intermediate nodes, +.>Excitation coefficients, which are the excitation functions, +.>Is the +.>A training value in the first part of the initial neural network>Weights of the intermediate nodes +. >Is the +.>Training value->Node identification being an intermediate node of said initial neural network,/-for>Is an identification of training values in said training set, < >>Is the total number of training values in the training set, < >>Is->Node threshold of each of said intermediate nodes, +.>Is an exponential function;
and generating an initial output value of the initial neural network according to the node output value.
Optionally, the updating the weight of the initial neural network according to the node output value in the initial output value to obtain an updated neural network of the initial neural network includes:
the initial neural network is updated with the weight value by using the following weight value updating algorithm and the node output value in the initial output value to obtain the updated neural network of the initial neural network,
wherein, the weight updating algorithm is as follows:
；
wherein ,is the +.o of the initial neural network>First->Update weight of secondary update +_>Is the +.o of the initial neural network>First->Update weight of secondary update +_>Is the update step size of the weight update of the initial neural network,/-for the initial neural network>Is the +.o of the initial neural network>The desired output of the individual intermediate nodes, Is the +.o of the initial neural network>Node output values of the intermediate nodes, +.>Is the +.>Training value->Is an identification of training values in the training set.
Optionally, the generating the real-time carbon emissions of the agricultural management activities according to the classification data and a preset carbon emissions algorithm includes:
determining greenhouse gas data of the agricultural management activities according to the classification data, and generating gas categories of greenhouse gases of the agricultural management activities according to the greenhouse gas data;
generating agricultural carbon source data of the agricultural management activities according to the classification data, and establishing an association relationship between the agricultural carbon source data and the gas category;
and generating the real-time carbon emission of the agricultural management activity according to the association relation, the greenhouse gas data, the agricultural carbon source data and a preset carbon emission algorithm.
Optionally, the generating the emission reduction value of the agricultural management activity according to the real-time carbon emissions and the historical data includes:
determining a historical carbon emission for the agricultural management activity based on the historical data;
and generating a carbon emission difference value of the agricultural management activity according to the historical carbon emission and the real-time carbon emission, and determining the carbon emission difference value as an emission reduction value of the agricultural management activity.
Optionally, the generating the emission reduction policy of the agricultural management activity using the emission reduction value includes:
generating an emission reduction curve of the agricultural management activity according to the emission reduction value and the real-time data of the agricultural management activity;
determining an emission reduction peak value of the emission reduction curve, and determining an optimal emission reduction factor of the agricultural management activity according to the emission reduction peak value;
and generating an emission reduction strategy of the agricultural management activity according to the optimal emission reduction factor.
In order to solve the above problems, the present invention also provides an emission reduction policy generation device for agricultural management activities based on a neural network, the device comprising:
the neural network establishment module is used for establishing an initial neural network;
the training set generation module is used for acquiring historical data of agricultural management activities and generating a training set of the initial neural network by utilizing the historical data;
the weight updating module is used for inputting training values in the training set into the initial neural network to obtain initial output values of the initial neural network, and updating the weight of the initial neural network according to node output values in the initial output values to obtain updated neural networks of the initial neural network;
The data classification module is used for acquiring real-time data of the agricultural management activities, and performing data classification on the real-time data by utilizing the updated neural network to obtain classified data of the real-time data;
the real-time carbon emission generation module is used for generating real-time carbon emission of the agricultural management activity according to the classification data and a preset carbon emission algorithm, wherein the preset carbon emission algorithm is as follows:
；
wherein ,is the real-time carbon emission of the agricultural management activities, < >>Is +.o in the agricultural management activities>Agricultural carbon source emission-like +.>Greenhouse gas like->Is->Conversion coefficient of greenhouse gases and standard carbon, +.>A carbon source class identifier of said agricultural carbon source,/-for>A gas class identifier of said greenhouse gas, +.>Is the total number of carbon source categories of the agricultural carbon source, < > or->Is the total number of gas categories of the greenhouse gas;
and the emission reduction strategy generation module is used for generating an emission reduction value of the agricultural management activity according to the real-time carbon emission and the historical data, and generating an emission reduction strategy of the agricultural management activity by utilizing the emission reduction value.
According to the embodiment of the invention, the initial neural network to be trained is determined by initializing the preset neural network structure, the training set of the initial neural network is generated by utilizing the acquired historical data of the agricultural management activities, and the weight of the initial neural network is updated by utilizing the training set, so that the neural network for data classification is more accurate, the carbon emission under a certain agricultural management activity is determined according to the classification data generated by updating the neural network, and the optimal emission reduction strategy can be determined according to the carbon emission and the historical carbon emission, so that the emission reduction efficiency is higher.
Drawings
Fig. 1 is a schematic flow chart of a method for generating an emission reduction strategy of an agricultural management activity based on a neural network according to an embodiment of the present application;
FIG. 2 is a flow chart illustrating the generation of an initial output value according to an embodiment of the present application;
FIG. 3 is a schematic flow chart of generating real-time carbon emissions for agricultural management activities according to an embodiment of the present application;
FIG. 4 is a functional block diagram of an emission reduction strategy generation device for agricultural management activities based on a neural network according to an embodiment of the present application;
the achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The embodiment of the application provides an emission reduction strategy generation method for agricultural management activities based on a neural network. The execution subject of the neural network-based method for generating the emission reduction policy for agricultural management activities includes, but is not limited to, at least one of a server, a terminal, and the like, which can be configured to execute the method provided by the embodiment of the application. In other words, the method for generating the emission reduction policy of the agricultural management activity based on the neural network may be performed by software or hardware installed in the terminal device or the server device. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
Referring to fig. 1, a flow chart of a method for generating an emission reduction strategy for agricultural management activities based on a neural network according to an embodiment of the present invention is shown. In this embodiment, the method for generating an emission reduction policy for agricultural management activities based on a neural network includes:
s1, establishing an initial neural network.
In an embodiment of the present invention, the establishing an initial neural network includes:
initial parameter configuration is carried out on a preset neural network structure, and a parameter neural network of the preset neural network structure is obtained;
and performing excitation function configuration on the parameter neural network to obtain an excitation function neural network of the parameter neural network, and determining the excitation function neural network as an initial neural network of the preset neural network structure.
In detail, the preset neural network structure refers to a binary tree structure, which is composed of a plurality of nodes and leaves, each node is a classifier, the classifiers are composed of higher-order neural networks, and each leaf represents a different class and is the final classification result.
Furthermore, the high-order neural network has no trouble of hidden layer nodes, and the training speed is faster; secondly, although the form of the higher-order neural network is simpler, the mode classification capability of the higher-order neural network is stronger, and because the mode discrimination interface of the higher-order neural network is nonlinear, the higher-order neural network can better process irregularly distributed complex data; finally, the method has no problem of local minimum, and the pattern classification precision is higher.
In detail, the preset neural network has no intermediate hidden layer like the multi-layer perceptron neural network, so that the trouble of selecting the intermediate hidden layer number and the hidden layer node number is omitted, and meanwhile, the reverse transmission error is avoided due to the simplification of the network structure, so that the learning efficiency of the network is fundamentally improved.
In detail, the initial parameter configuration of the preset neural network structure refers to initial weight assignment of each higher-order neural network of the preset neural network; the parametric neural network is a neural network composed of a higher order neural network indicating an initial weight.
In detail, the excitation function is used for providing large-scale nonlinear capability, so that the neural network can arbitrarily approximate any nonlinear function to simulate the state change of the excited neurons; if the neural network does not use an excitation function, each layer of output is a linear function of the upper layer of input, and no matter how many layers the neural network has, the output is a linear combination of the inputs; the excitation function may employ a bipolar function.
S2, acquiring historical data of agricultural management activities, and generating a training set of the initial neural network by utilizing the historical data.
In embodiments of the present invention, the agricultural management activities refer to some agricultural activities based on reducing carbon emissions, and the historical data includes, but is not limited to: carbon source data such as fertilizers, pesticides, agricultural plastics, irrigation and diesel oil, carbon emission coefficients, total agricultural carbon emission, and crop data such as paddy fields, wheat, corn, soybean, peanut, vegetable oil, and rapeseed.
In an embodiment of the present invention, the generating the training set of the initial neural network using the historical data includes:
extracting features of the historical data to obtain data features of the historical data;
carrying out feature identification on the data features to obtain feature labels of the data features;
and generating a training set of the initial neural network according to the characteristic labels and the data characteristics.
In detail, the feature extraction of the historical data is to convert the historical data into a vector form which can be identified by a neural network; the data characteristics of the historical data may be generated using a bag of words model.
In detail, the feature identification of the data features is to determine useful information in the data features, because not all data in the historical data are useful information, only useful information is identified in the feature identification process, and features irrelevant to problems are removed, and in the feature identification process, a variance filtering method can be adopted, wherein the variance filtering method considers that the information of the data depends on the degree of variation of the information. For example, for the field of "whether the sun is rising from the east", all values thereof are "yes", the data has no variation, the variance of the strain magnitude is 0, and such data is without information; for the field of 'solar black activity intensity', the data variation is relatively large, which may contain information that people want to know, and the larger the data variation is, the more information contained in the field should be kept; and (3) eliminating the data without any variation, and carrying out characteristic identification on the history data with larger variation.
In detail, the generating the training set of the initial neural network according to the feature tag and the data feature is generating an association relation between the feature tag and the data feature, and the history data is selected by using the association relation between the feature tag and the data feature to obtain the training set of the initial neural network.
In detail, the feature extraction of the historical data to obtain the data feature of the historical data includes:
performing data cleaning on the historical data to obtain cleaning data of the historical data;
performing data vectorization on the cleaning data to obtain a data vector of the cleaning data;
and carrying out feature dimension reduction on the data vector to obtain the data features of the historical data.
In detail, the data cleansing of the history data is to delete repeated information in the history data, correct errors in the history data, and provide consistency of the history data, and may adopt methods of taking logarithms, averaging, and filling blank values.
In detail, the data vectorization of the cleaning data can use single-heat coding, and if the cleaning data is fertilizer, pesticide, agricultural plastic, irrigation and agricultural mechanization, the cleaning data sequentially corresponds to data vectors after single-heat coding: 00001 01000, 00100, 00010 and 00001.
In detail, as the data dimension is continuously reduced, the space required for data storage is reduced, and when the low-dimension data is helpful to reduce training, the maximum value pooling or average value pooling can be adopted to perform feature dimension reduction on the data vector, so as to obtain the data features of the historical data.
S3, inputting training values in the training set into the initial neural network to obtain initial output values of the initial neural network, and updating weights of the initial neural network according to node output values in the initial output values to obtain updated neural networks of the initial neural network.
In an embodiment of the present invention, referring to fig. 2, the inputting training values in the training set into the initial neural network to obtain initial output values of the initial neural network includes:
s31, determining an excitation function of the initial neural network, and generating an output algorithm of the initial neural network according to the excitation function;
s32, carrying out numerical operation on training values in the training set by using the output algorithm to obtain a layer output value of the initial neural network, wherein the output algorithm is as follows:
；
wherein ,is the +.o of the initial neural network>Nodes of the intermediate nodesOutput value->Excitation coefficients, which are the excitation functions, +.>Is the +.>A training value in the first part of the initial neural network>Weights of the intermediate nodes +.>Is the +.>Training value->Node identification being an intermediate node of said initial neural network,/-for>Is an identification of training values in said training set, < >>Is the total number of training values in the training set, < >>Is->Node threshold of each of said intermediate nodes, +.>Is an exponential function;
s33, generating an initial output value of the initial neural network according to the node output value.
In detail, when the excitation coefficients in the excitation function take different values, the speed of convergence of the excitation function to the two poles is different, and the excitation coefficients are not suitable in size, and are generally selected to be 1.
In the embodiment of the present invention, the updating the weight of the initial neural network according to the node output value in the initial output value to obtain an updated neural network of the initial neural network includes:
the initial neural network is updated with the weight value by using the following weight value updating algorithm and the node output value in the initial output value to obtain the updated neural network of the initial neural network,
The weight updating algorithm comprises the following steps:
；
wherein ,is the +.o of the initial neural network>First->Update weight of secondary update +_>Is the +.o of the initial neural network>First->Update weight of secondary update +_>Is the update step size of the weight update of the initial neural network,/-for the initial neural network>Is the initial oneNo. 5 of neural network>The desired output of the individual intermediate nodes,is the +.o of the initial neural network>Node output values of the intermediate nodes, +.>Is the +.>Training value->Is an identification of training values in the training set.
In detail, the weight updating of the initial neural network according to the node output values in the initial output values is to update the weight of the initial neural network by using the difference value between the node output values in the initial output values and the expected output.
And S4, acquiring real-time data of the agricultural management activity, and performing data classification on the real-time data by using the updated neural network to obtain classified data of the real-time data.
In the embodiment of the present invention, the data classification of the real-time data by using the updated neural network refers to inputting the real-time data into the updated neural network, so as to obtain classified data of the real-time data.
In detail, the real-time data includes, but is not limited to: agricultural materials such as chemical fertilizers, pesticides, agricultural films and diesel oil, carbon emission coefficients of carbon sources, agricultural irrigation areas, crops such as rice fields, wheat, corn, soybeans, peanuts, vegetables and rapeseeds, livestock types such as cattle, horses, donkeys, mules, pigs, goats and sheep, and intestinal fermentation and fecal emission data of livestock.
In detail, the classification data is determined according to the greenhouse gas type and the agricultural carbon source type.
And S5, generating real-time carbon emission of the agricultural management activity according to the classification data and a preset carbon emission algorithm.
In an embodiment of the present invention, referring to fig. 3, the generating the real-time carbon emissions of the agricultural management activities according to the classification data and the preset carbon emission algorithm includes:
s51, determining greenhouse gas data of the agricultural management activities according to the classification data, and generating gas categories of greenhouse gases of the agricultural management activities according to the greenhouse gas data;
s52, generating agricultural carbon source data of the agricultural management activities according to the classification data, and establishing an association relationship between the agricultural carbon source data and the gas category;
And S53, generating real-time carbon emission of the agricultural management activity according to the association relation, the greenhouse gas data, the agricultural carbon source data and a preset carbon emission algorithm.
In detail, the greenhouse gas data refers to data of isothermal chamber gases such as carbon dioxide, methane and nitrous oxide; the agricultural carbon source data refer to data of carbon sources such as agricultural materials, crops, livestock and the like.
In detail, the gas class refers to the type of greenhouse gas including, but not limited to: carbon dioxide, methane and nitrous oxide; the establishment of the association relationship between the agricultural carbon source data and the gas category refers to determining the greenhouse gas emission of different carbon sources according to the agricultural carbon source number, for example: the discharge of nitrous oxide from the soil in the paddy field in crops, and the discharge of carbon dioxide from the fertilizer in agricultural materials.
In detail, the generation of the real-time carbon emission of the agricultural management activity according to the association relationship, the greenhouse gas data, the agricultural carbon source data and a preset carbon emission algorithm means that the greenhouse gas data and the corresponding agricultural carbon source number determine the carbon emission of a certain carbon source, and then the carbon emissions of all the carbon sources are summed to obtain the real-time carbon emission of the agricultural management activity.
In detail, the preset carbon emission algorithm is:
；
wherein ,is the real-time carbon emission of the agricultural management activities, < >>Is +.o in the agricultural management activities>Agricultural carbon source emission-like +.>Greenhouse gas like->Is->Conversion coefficient of greenhouse gases and standard carbon, +.>A carbon source class identifier of said agricultural carbon source,/-for>A gas class identifier of said greenhouse gas, +.>Is the total number of carbon source categories of the agricultural carbon source, < > or->Is the total number of gas categories of the greenhouse gas.
In detail, the firstThe conversion coefficient of the greenhouse gas-like and the standard carbon varies depending on the kind of greenhouse gas, for example: the carbon dioxide to standard carbon conversion was 1, the methane to standard carbon conversion was 6.8182 and the nitrous oxide to standard carbon conversion was 81.2727.
S6, generating an emission reduction value of the agricultural management activity according to the real-time carbon emission and the historical data, and generating an emission reduction strategy of the agricultural management activity by using the emission reduction value.
In an embodiment of the present invention, the generating the emission reduction value of the agricultural management activity according to the real-time carbon emission and the historical data includes:
determining a historical carbon emission for the agricultural management activity based on the historical data;
And generating a carbon emission difference value of the agricultural management activity according to the historical carbon emission and the real-time carbon emission, and determining the carbon emission difference value as an emission reduction value of the agricultural management activity.
In detail, the determining the historical carbon emission of the agricultural management activity according to the historical data refers to extracting the carbon emission value in the historical data to obtain the historical carbon emission of the agricultural management activity.
In an embodiment of the present invention, the generating the emission reduction policy of the agricultural management activity using the emission reduction value includes:
generating an emission reduction curve of the agricultural management activity according to the emission reduction value and the real-time data of the agricultural management activity;
determining an emission reduction peak value of the emission reduction curve, and determining an optimal emission reduction factor of the agricultural management activity according to the emission reduction peak value;
and generating an emission reduction strategy of the agricultural management activity according to the optimal emission reduction factor.
In detail, the generation of the emission reduction curve of the agricultural management activity according to the emission reduction value and the real-time data of the agricultural management activity refers to the establishment of a mapping relation between the real-time data of the agricultural management activity and the emission reduction value, and the emission reduction curve is the embodiment of the mapping relation; the emission reduction peak value of the emission reduction curve can be determined by deriving the emission reduction curve, the extremum of the emission reduction curve is determined by deriving, all mechanisms are compared to obtain the maximum value of the emission reduction curve, the maximum value is determined to be the emission reduction peak value of the emission reduction curve, and the emission reduction peak value is also the value at which the emission reduction of the agricultural management activity reaches the maximum.
In detail, the determining the optimal emission reduction factor of the agricultural management activity according to the emission reduction peak value refers to determining the optimal emission reduction factor of the agricultural management activity according to the corresponding value of the emission reduction peak value, and the optimal emission reduction factor refers to a parameter capable of maximizing the emission reduction of the agricultural management activity; the optimal emission abatement strategy for the agricultural management activity is generated according to parameters that maximize the emission abatement of the agricultural management activity, making the management of carbon emissions for the agricultural management activity more efficient.
According to the embodiment of the invention, the initial neural network to be trained is determined by initializing the preset neural network structure, the training set of the initial neural network is generated by utilizing the acquired historical data of the agricultural management activities, and the weight of the initial neural network is updated by utilizing the training set, so that the neural network for data classification is more accurate, the carbon emission under a certain agricultural management activity is determined according to the classification data generated by updating the neural network, and the optimal emission reduction strategy can be determined according to the carbon emission and the historical carbon emission, so that the emission reduction efficiency is higher.
Fig. 4 is a functional block diagram of an emission reduction strategy generation device for agricultural management activities based on a neural network according to an embodiment of the present invention.
The emission reduction policy generation device 100 for agricultural management activities based on the neural network can be installed in electronic equipment. According to the implemented functions, the emission reduction policy generation device 100 for agricultural management activities based on the neural network may include a neural network establishment module 101, a training set generation module 102, a weight update module 103, a data classification module 104, a real-time carbon emission generation module 105, and an emission reduction policy generation module 106. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
In the present embodiment, the functions concerning the respective modules/units are as follows:
the neural network establishing module 101 is configured to establish an initial neural network;
the training set generating module 102 is configured to obtain historical data of an agricultural management activity, and generate a training set of the initial neural network using the historical data;
the weight updating module 103 is configured to input training values in the training set to the initial neural network to obtain an initial output value of the initial neural network, and update weights of the initial neural network according to node output values in the initial output value to obtain an updated neural network of the initial neural network;
The data classification module 104 is configured to obtain real-time data of the agricultural management activity, and perform data classification on the real-time data by using the updated neural network to obtain classified data of the real-time data;
the real-time carbon emission generation module 105 is configured to generate real-time carbon emission of the agricultural management activity according to the classification data and a preset carbon emission algorithm, where the preset carbon emission algorithm is:
；
wherein ,is the real-time carbon emission of the agricultural management activities, < >>Is +.o in the agricultural management activities>Agricultural carbon source emission-like +.>Greenhouse gas like->Is->Conversion coefficient of greenhouse gases and standard carbon, +.>A carbon source class identifier of said agricultural carbon source,/-for>A gas class identifier of said greenhouse gas, +.>Is the total number of carbon source categories of the agricultural carbon source, < > or->Is the total number of gas categories of the greenhouse gas;
the emission reduction strategy generation module 106 is configured to generate an emission reduction value of the agricultural management activity according to the real-time carbon emission and the historical data, and generate an emission reduction strategy of the agricultural management activity according to the emission reduction value.
According to the embodiment of the invention, the initial neural network to be trained is determined by initializing the preset neural network structure, the training set of the initial neural network is generated by utilizing the acquired historical data of the agricultural management activities, and the weight of the initial neural network is updated by utilizing the training set, so that the neural network for data classification is more accurate, the carbon emission under a certain agricultural management activity is determined according to the classification data generated by updating the neural network, and the optimal emission reduction strategy can be determined according to the carbon emission and the historical carbon emission, so that the emission reduction efficiency is higher.
In the several embodiments provided in the present invention, it should be understood that the disclosed method and apparatus may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application that uses a digital computer or a digital computer-controlled machine to simulate, extend and expand human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. A plurality of units or means recited in the apparatus claims can also be implemented by means of one unit or means in software or hardware. The terms first, second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present application and not for limiting the same, and although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present application without departing from the spirit and scope of the technical solution of the present application.
Claims (9)
1. An emission reduction strategy generation method for agricultural management activities based on a neural network, which is characterized by comprising the following steps:
initializing a preset neural network structure to obtain an initial neural network of the preset classified neural network;
acquiring historical data of agricultural management activities, and generating a training set of the initial neural network by utilizing the historical data;
inputting training values in the training set into the initial neural network to obtain initial output values of the initial neural network, and updating weights of the initial neural network according to node output values in the initial output values to obtain updated neural network of the initial neural network;
the step of updating the weight of the initial neural network according to the node output values in the initial output values to obtain an updated neural network of the initial neural network comprises the following steps:
and updating the weight of the initial neural network by using the following weight updating algorithm and the node output values in the initial output values to obtain an updated neural network of the initial neural network:
；
wherein ,is the +.o of the initial neural network>First- >The update weight of the secondary update,is the +.o of the initial neural network>First->Update weight of secondary update +_>Is the update step size of the weight update of the initial neural network,/-for the initial neural network>Is the +.o of the initial neural network>The desired output of the intermediate nodes,/>Is the initial oneNo. 5 of neural network>Node output values of the intermediate nodes, +.>Is the +.>Training value->Is the identity of the training values in the training set;
acquiring real-time data of the agricultural management activity, and performing data classification on the real-time data by utilizing the updated neural network to obtain classified data of the real-time data;
generating real-time carbon emission of the agricultural management activity according to the classification data and a preset carbon emission algorithm, wherein the preset carbon emission algorithm is as follows:
；
wherein ,is the real-time carbon emission of the agricultural management activities, < >>Is +.o in the agricultural management activities>Agricultural carbon source emission-like +.>Greenhouse gas like->Is->Conversion coefficient of greenhouse gases and standard carbon, +.>A carbon source class identifier of said agricultural carbon source,/-for>A gas class identifier of said greenhouse gas, +.>Is the total number of carbon source categories of the agricultural carbon source, < > or- >Is the total number of gas categories of the greenhouse gas;
and generating an emission reduction value of the agricultural management activity according to the real-time carbon emission and the historical data, and generating an emission reduction strategy of the agricultural management activity by using the emission reduction value.
2. The method for generating the emission reduction policy for the agricultural management activities based on the neural network according to claim 1, wherein the initializing the preset neural network structure to obtain the initial neural network of the preset classified neural network comprises:
initial parameter configuration is carried out on the preset neural network structure, and a parameter neural network of the preset neural network structure is obtained;
and performing excitation function configuration on the parameter neural network to obtain an excitation function neural network of the parameter neural network, and determining the excitation function neural network as an initial neural network of the preset classification neural network.
3. The method for generating an emission reduction policy for a neural network-based agricultural management activity of claim 1, wherein said generating a training set of the initial neural network using the historical data comprises:
extracting features of the historical data to obtain data features of the historical data;
Carrying out feature identification on the data features to obtain feature labels of the data features;
and generating a training set of the initial neural network according to the characteristic labels and the data characteristics.
4. The method for generating an emission reduction policy for an agricultural management activity based on a neural network according to claim 3, wherein the feature extracting the historical data to obtain the data feature of the historical data comprises:
performing data cleaning on the historical data to obtain cleaning data of the historical data;
performing data vectorization on the cleaning data to obtain a data vector of the cleaning data;
and carrying out feature dimension reduction on the data vector to obtain the data features of the historical data.
5. The method for generating an emission reduction policy for agricultural management activities based on a neural network according to claim 1, wherein the inputting training values in the training set into the initial neural network to obtain initial output values of the initial neural network comprises:
determining an excitation function of the initial neural network, and generating an output algorithm of the initial neural network according to the excitation function;
performing numerical operation on training values in the training set by using the output algorithm to obtain a layer output value of the initial neural network, wherein the output algorithm is as follows:
；
wherein ,is the +.o of the initial neural network>Node output values of the intermediate nodes, +.>Excitation coefficients, which are the excitation functions, +.>Is the +.>A training value in the first part of the initial neural network>The weight of the individual intermediate nodes is calculated,is the +.>Training value->Node identification being an intermediate node of said initial neural network,/-for>Is an identification of training values in said training set, < >>Is the total number of training values in the training set, < >>Is->Node threshold of each of said intermediate nodes, +.>Is an exponential function;
and generating an initial output value of the initial neural network according to the node output value.
6. The method for generating emission reduction strategies for agricultural management activities based on neural networks according to claim 1, wherein the generating real-time carbon emissions for the agricultural management activities according to the classification data and a preset carbon emission algorithm comprises:
determining greenhouse gas data of the agricultural management activities according to the classification data, and generating gas categories of greenhouse gases of the agricultural management activities according to the greenhouse gas data;
generating agricultural carbon source data of the agricultural management activities according to the classification data, and establishing an association relationship between the agricultural carbon source data and the gas category;
And generating the real-time carbon emission of the agricultural management activity according to the association relation, the greenhouse gas data, the agricultural carbon source data and a preset carbon emission algorithm.
7. The method for generating an emission reduction strategy for an agricultural management activity based on a neural network according to claim 1, wherein the generating an emission reduction value for the agricultural management activity based on the real-time carbon emissions and the historical data comprises:
determining a historical carbon emission for the agricultural management activity based on the historical data;
and generating a carbon emission difference value of the agricultural management activity according to the historical carbon emission and the real-time carbon emission, and determining the carbon emission difference value as an emission reduction value of the agricultural management activity.
8. The emission reduction policy generation method of an agricultural management activity based on a neural network according to any one of claims 1 to 7, wherein the generating an emission reduction policy of the agricultural management activity using the emission reduction value comprises:
generating an emission reduction curve of the agricultural management activity according to the emission reduction value and the real-time data of the agricultural management activity;
determining an emission reduction peak value of the emission reduction curve, and determining an optimal emission reduction factor of the agricultural management activity according to the emission reduction peak value;
And generating an emission reduction strategy of the agricultural management activity according to the optimal emission reduction factor.
9. An emission reduction policy generation device for agricultural management activities based on a neural network, the device comprising:
the structure initialization module is used for initializing a preset neural network structure to obtain an initial neural network of the preset classified neural network;
the training set module is used for generating a training set of the initial neural network by utilizing the historical data of the agricultural management activity due to the acquisition of the historical data of the agricultural management activity;
the weight updating module is used for inputting training values in the training set into the initial neural network to obtain an initial output value of the initial neural network, and updating the weight of the initial neural network according to the node output value in the initial output value to obtain an updated neural network of the initial neural network;
the step of updating the weight of the initial neural network according to the node output values in the initial output values to obtain an updated neural network of the initial neural network comprises the following steps:
and updating the weight of the initial neural network by using the following weight updating algorithm and the node output values in the initial output values to obtain an updated neural network of the initial neural network:
；
wherein ,is the +.o of the initial neural network>First->The update weight of the secondary update,is the +.o of the initial neural network>First->Update weight of secondary update +_>Is the update step size of the weight update of the initial neural network,/-for the initial neural network>Is the +.o of the initial neural network>The desired output of the intermediate nodes,/>Is the +.o of the initial neural network>Node output values of the intermediate nodes, +.>Is the +.>Training value->Is the identity of the training values in the training set;
the data classification module is used for acquiring real-time data of the agricultural management activities, and performing data classification on the real-time data by utilizing the updated neural network to obtain classified data of the real-time data;
and the real-time carbon emission module is used for generating real-time carbon emission of the agricultural management activity according to the classification data and a preset carbon emission algorithm, wherein the preset carbon emission algorithm is as follows:
；
wherein ,is the real-time carbon emission of the agricultural management activities, < >>Is +.o in the agricultural management activities>Agricultural carbon source emission-like +.>Greenhouse gas like->Is->Conversion coefficient of greenhouse gases and standard carbon, +. >A carbon source class identifier of said agricultural carbon source,/-for>A gas class identifier of said greenhouse gas, +.>Is the total number of carbon source categories of the agricultural carbon source, < > or->Is the total number of gas categories of the greenhouse gas;
and the emission reduction strategy module is used for generating an emission reduction strategy of the agricultural management activity by utilizing the emission reduction value due to the fact that the emission reduction value of the agricultural management activity is generated according to the real-time carbon emission and the historical data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310699503.1A CN116485210B (en) | 2023-06-14 | 2023-06-14 | Neural network-based method and device for generating emission reduction strategy of agricultural management activity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310699503.1A CN116485210B (en) | 2023-06-14 | 2023-06-14 | Neural network-based method and device for generating emission reduction strategy of agricultural management activity |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116485210A CN116485210A (en) | 2023-07-25 |
| CN116485210B true CN116485210B (en) | 2023-09-05 |
Family
ID=87215926
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310699503.1A Active CN116485210B (en) | 2023-06-14 | 2023-06-14 | Neural network-based method and device for generating emission reduction strategy of agricultural management activity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116485210B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117742160A (en) * | 2024-02-09 | 2024-03-22 | 广州市威士丹利智能科技有限公司 | Artificial intelligence-based carbon emission optimization control method and system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160132697A (en) * | 2015-05-11 | 2016-11-21 | 주식회사 팬더아이앤씨 | Method and system of green chain management for greenhouse gas reduction |
| CN114330659A (en) * | 2021-12-29 | 2022-04-12 | 辽宁工程技术大学 | BP neural network parameter optimization method based on improved ASO algorithm |
| US11531387B1 (en) * | 2022-04-11 | 2022-12-20 | Pledgeling Technologies, Inc. | Methods and systems for real time carbon emission determination incurred by execution of computer processes and the offset thereof |
| CN115719152A (en) * | 2022-11-29 | 2023-02-28 | 布瑞克农业大数据科技集团有限公司 | Agricultural carbon emission management method and system |
| CN115797093A (en) * | 2022-11-11 | 2023-03-14 | 苏州规划设计研究院股份有限公司 | Farmland ecosystem carbon sink estimation method based on agricultural input-output data |
| CN115860351A (en) * | 2022-09-21 | 2023-03-28 | 国网青海省电力公司经济技术研究院 | Method and system for determining energy-saving emission-reducing target of high-energy-consumption enterprise |
| CN115983458A (en) * | 2022-12-26 | 2023-04-18 | 海南电网有限责任公司 | Power carbon emission peak value prediction method and system based on grey BP neural network |
| CN115983671A (en) * | 2022-12-06 | 2023-04-18 | 中建科技集团有限公司 | Method and system for measuring and calculating carbon emission of industrial park |
| CN116029883A (en) * | 2023-01-10 | 2023-04-28 | 中国科学院空天信息创新研究院 | Carbon dioxide laser radar-based mesoscale carbon emission positioning and checking method and system |
-
2023
- 2023-06-14 CN CN202310699503.1A patent/CN116485210B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160132697A (en) * | 2015-05-11 | 2016-11-21 | 주식회사 팬더아이앤씨 | Method and system of green chain management for greenhouse gas reduction |
| CN114330659A (en) * | 2021-12-29 | 2022-04-12 | 辽宁工程技术大学 | BP neural network parameter optimization method based on improved ASO algorithm |
| US11531387B1 (en) * | 2022-04-11 | 2022-12-20 | Pledgeling Technologies, Inc. | Methods and systems for real time carbon emission determination incurred by execution of computer processes and the offset thereof |
| CN115860351A (en) * | 2022-09-21 | 2023-03-28 | 国网青海省电力公司经济技术研究院 | Method and system for determining energy-saving emission-reducing target of high-energy-consumption enterprise |
| CN115797093A (en) * | 2022-11-11 | 2023-03-14 | 苏州规划设计研究院股份有限公司 | Farmland ecosystem carbon sink estimation method based on agricultural input-output data |
| CN115719152A (en) * | 2022-11-29 | 2023-02-28 | 布瑞克农业大数据科技集团有限公司 | Agricultural carbon emission management method and system |
| CN115983671A (en) * | 2022-12-06 | 2023-04-18 | 中建科技集团有限公司 | Method and system for measuring and calculating carbon emission of industrial park |
| CN115983458A (en) * | 2022-12-26 | 2023-04-18 | 海南电网有限责任公司 | Power carbon emission peak value prediction method and system based on grey BP neural network |
| CN116029883A (en) * | 2023-01-10 | 2023-04-28 | 中国科学院空天信息创新研究院 | Carbon dioxide laser radar-based mesoscale carbon emission positioning and checking method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116485210A (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Issad et al. | A comprehensive review of Data Mining techniques in smart agriculture | |
| Kour et al. | Recent developments of the internet of things in agriculture: a survey | |
| CN111581343A (en) | Reinforced learning knowledge graph reasoning method and device based on graph convolution neural network | |
| Sahu et al. | An efficient analysis of crop yield prediction using Hadoop framework based on random forest approach | |
| CN116485210B (en) | Neural network-based method and device for generating emission reduction strategy of agricultural management activity | |
| Kanuru et al. | Prediction of pesticides and fertilizers using machine learning and Internet of Things | |
| Ranjani et al. | Crop yield prediction using machine learning algorithm | |
| CN113378706B (en) | Drawing system for assisting children in observing plants and learning biological diversity | |
| CN117540908A (en) | Agricultural resource integration method and system based on big data | |
| CN115376008A (en) | Method and device for identifying plant diseases and insect pests, electronic equipment and storage medium | |
| Karnati et al. | Deep computation model to the estimation of sulphur dioxide for plant health monitoring in IoT | |
| CN113379188B (en) | Tobacco crop rotation planting method and system based on Internet of things | |
| Vivekanandhan et al. | Adaptive neuro fuzzy inference system to enhance the classification performance in smart irrigation system | |
| Raviraja et al. | Machine learning based mobile applications for autonomous fertilizer suggestion | |
| Anamisa et al. | Technologies. Methods, and Approaches on Detection System of Plant Pests and Diseases | |
| Tripathy et al. | Smart Farming based on Deep Learning Approaches | |
| Chaudhari et al. | Bayesian optimization with deep learning based crop type classification on UAV imagery | |
| Golestani et al. | Multifractal phenomena in EcoSim, a large scale individual-based ecosystem simulation | |
| Dos Santos et al. | Package proposal for data pre-processing for machine learning applied to precision irrigation | |
| Chegini et al. | An agriprecision decision support system for weed management in pastures | |
| Parmar et al. | Crop Yield Prediction based on Feature Selection and Machine Learners: A Review | |
| Ramachandra et al. | Crop Recommendation Using Machine Learning | |
| Saranya et al. | Multi-model ensemble depth adaptive deep neural network for crop yield prediction | |
| CN116107630B (en) | Multi-platform adaptation method for big data operation and maintenance monitoring | |
| Boonyopakorn et al. | Applying Neuro Fuzzy System to Analyze Durian Minerals within Soil for Precision Agriculture |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |