CN107025505A - A kind of paddy water requirement prediction method based on principal component analysis and neutral net - Google Patents
A kind of paddy water requirement prediction method based on principal component analysis and neutral net Download PDFInfo
- Publication number
- CN107025505A CN107025505A CN201710278851.6A CN201710278851A CN107025505A CN 107025505 A CN107025505 A CN 107025505A CN 201710278851 A CN201710278851 A CN 201710278851A CN 107025505 A CN107025505 A CN 107025505A
- Authority
- CN
- China
- Prior art keywords
- paddy
- growth
- principal component
- characteristic
- component analysis
- 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
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- 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
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
Abstract
The invention discloses a kind of paddy water requirement prediction method based on principal component analysis and neutral net, every factor of influence data in the regional process of crop growth of experiment are obtained first and are pre-processed, then to according to meteorological condition, growing environment condition, these three aspects of own growth characteristic selected characteristic from the factor of influence data during paddy growth carries out the principal component analysis of feature based number adjusting thresholds, so as to find different combinations of features, to the RBF neural network model of different combinations of features training particle cluster algorithm optimization, find out accuracy rate highest weight iterative parameter and combinations of features, so as to which the RBF neural network model built can realize that water shortage status degree is predicted in the whole growth course of paddy rice, it is efficiently quick, and it is accurate to predict the outcome.
Description
Technical field
The present invention relates to Data Mining, specifically a kind of water requirement of rice based on principal component analysis and neutral net
Forecasting Methodology.
Background technology
Data mining theories have been applied in every field, current comparative maturity just have bank, telecommunications, insurance, traffic,
Retail(Such as supermarket)Deng commercial field, be also embodied in reading intelligent agriculture, natural resources analysis, weather forecast, environmental monitoring and
Many fields such as physiology studies of lesions.Agriculturally, such as the prediction of the water demand of crop, it can be detected by big data means
The growing state of some regional crops and irrigation are instructed.
The application of data mining theories technology described above is that the part crop grown for nature carries out research processing mostly,
And paddy water requirement prediction method is directed to currently without special, it is the Drought Condition detection for relying on manually to enter row crop mostly,
Lack of wisdom.This between both time costs that paddy water requirement prediction accuracy rate and characteristic dimension are big to be brought disappears
That length can not really apply to forecasting system exploitation.
The content of the invention
The technical problem to be solved in the present invention is to provide a kind of water requirement of rice based on principal component analysis and neutral net
Forecasting Methodology, solve paddy rice Traditional Man formulate irrigation requirement exist error it is larger in the case of the water resource waste brought ask
Topic, efficiently prediction field rice growth course in water shortage situation, furnish a forecast warning information.
The technical scheme is that:
A kind of paddy water requirement prediction method based on principal component analysis and neutral net, has specifically included following steps:
(1), obtain every factor of influence data during the regional paddy growth of experiment, the instruction for building neural network model
Practice collection and test set, the quality of constructed neural network model is judged by predictablity rate;
(2), completion, interpolation, denoising and normalized are carried out to the factor of influence data during the paddy growth of acquisition;
(3), according to meteorological condition, growing environment condition, own growth characteristic these three aspects from the shadow during paddy growth
Selected characteristic in factor data is rung, and the principal component analysis of feature based number adjusting thresholds is carried out respectively in terms of these three, from
And find different combinations of features;
(4), the structure of RBF neural network model is carried out to different combinations of features, be primarily based on particle cluster algorithm to use
RBF neural optimizes processing, by adjusting weight parameter and iterative parameter between the connection of neutral net neuron, looks for
Go out accuracy rate highest weight parameter and iterative parameter, according to constructed by the weight parameter found out, iterative parameter and combinations of features
Optimal RBF neural network model water shortage status degree in the whole growth course of paddy rice is predicted, obtain paddy rice demand
That measures predicts the outcome.
Factor of influence data during described paddy growth include sunshine time, daily mean temperature, day highest gas
Temperature, daily minimal tcmperature, per day wind speed, average relative humidity, maximum relative humidity, minimum relative humidity, crop superficial radiation
Amount, blade saturation vapour pressure, blade actual water vapor pressure, blade area, crop plant height, density of crop, earth surface reflection
Amount, soil heat flux, the soil weight, soil acidity or alkalinity, water capacity and soil desertification rate.
The characteristic component of described meteorological condition includes daily mean temperature, daily maximum temperature, and daily minimal tcmperature is per day
Relative humidity, maximum relative humidity, minimum relative humidity, sunshine time, wind speed and crop superficial radiation amount;Described growth ring
The characteristic component of border condition includes the paddy growth soil weight, field-moisture capacity, desertification of land rate and soil heat flux;
The characteristic component of described own growth characteristic includes species density in planting, plant height and blade surface actual water vapor pressure.
The principal component analysis of described feature based number adjusting thresholds has specifically included following steps:To the spy of meteorological condition
Levy component and carry out principal component contributor rate calculating, choose its validity feature value;The characteristic component of growing environment condition is carried out it is main into
Divide contribution rate to calculate, choose its validity feature value;Principal component contributor rate calculating, choosing are carried out to the characteristic component of own growth characteristic
Take its validity feature value;The validity feature for obtaining three aspects carries out different characteristic combination, particular by based on validity feature
The PCA for being worth number adjusting thresholds is calculated, and by different characteristic value number adjusting thresholds and value, can obtain different features
Combination.
Described optimizes comprising the following steps that for processing based on particle cluster algorithm to the RBF neural of use:It is first
The hidden layer number of plies of RBF neural is first determined, a group particle is randomly generated, coding determines that population scale and parameter are initial
Value, and particle position, initial randomization of speed are carried out, good and bad judgement, more new particle individual pole are then carried out to particle position
Value and population global extremum, so as to adjust particles spatial speed and flying speed, finally meet most when training forecast model
When big iterations and minimum adaptation threshold value, i.e., the iterations of particle is no more than maximum iteration, adapts to threshold value more than most
During small adaptation threshold value, accuracy rate highest weight parameter and iterative parameter are obtained.
Advantages of the present invention:
The present invention obtains every factor of influence data in the regional process of crop growth of experiment and pre-processed, then to basis
These three aspects of meteorological condition, growing environment condition, own growth characteristic are from the factor of influence data during paddy growth
Selected characteristic carries out the principal component analysis of feature based number adjusting thresholds, so that different combinations of features are found, to different spies
The RBF neural network model of combined training particle cluster algorithm optimization is levied, accuracy rate highest weight iterative parameter and spy is found out
Combination is levied, so that the RBF neural network model built can realize that water shortage status degree is predicted in the whole growth course of paddy rice, it is high
Effect is quick and predicts the outcome accurately.
Brief description of the drawings
Fig. 1 is the flow chart of the present invention.
Fig. 2 is the flow chart that the present invention is optimized based on particle cluster algorithm to RBF neural.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
See Fig. 1, a kind of paddy water requirement prediction method based on principal component analysis and neutral net has been specifically included following
Step:
(1), obtain every factor of influence data during the regional paddy growth of experiment(Include sunshine time, per day gas
Temperature, daily maximum temperature, daily minimal tcmperature, per day wind speed, average relative humidity, maximum relative humidity, minimum relative humidity is made
Thing superficial radiation amount, blade saturation vapour pressure, blade actual water vapor pressure, blade area, crop plant height, crop-planting is close
Degree, earth surface reflection amount, soil heat flux, the soil weight, soil acidity or alkalinity, water capacity and soil desertification rate), for building
The training set and test set of neural network model, the quality of constructed neural network model is judged by predictablity rate;
(2), completion, interpolation, denoising and normalized are carried out to the factor of influence data during the paddy growth of acquisition;
(3), according to meteorological condition(The characteristic component of meteorological condition includes daily mean temperature, daily maximum temperature, day minimum gas
Temperature, per day relative humidity, maximum relative humidity, minimum relative humidity, sunshine time, wind speed and crop superficial radiation amount), it is raw
Long environmental condition(It is husky that the characteristic component of growing environment condition includes the paddy growth soil weight, field-moisture capacity, soil
Rate and soil heat flux), own growth characteristic(The characteristic component of own growth characteristic includes species density in planting, and plant is high
Degree and blade surface actual water vapor pressure)These three aspect selected characteristics from the factor of influence data during paddy growth, and
The principal component analysis of feature based number adjusting thresholds is carried out respectively in terms of these three, so as to find different combinations of features;
(4), the structure of RBF neural network model is carried out to different combinations of features, be primarily based on particle cluster algorithm to use
RBF neural optimizes processing, by adjusting weight parameter and iterative parameter between the connection of neutral net neuron, looks for
Go out accuracy rate highest weight parameter and iterative parameter, according to constructed by the weight parameter found out, iterative parameter and combinations of features
Optimal RBF neural network model water shortage status degree in the whole growth course of paddy rice is predicted, obtain paddy rice demand
That measures predicts the outcome.
Wherein, the principal component analysis of feature based number adjusting thresholds has specifically included following steps:To the spy of meteorological condition
Levy component and carry out principal component contributor rate calculating, choose its validity feature value, its validity feature value number is 2-3;To growth ring
The characteristic component of border condition carries out principal component contributor rate calculating, chooses its validity feature value, and its validity feature value is 2-3;It is right
The characteristic component of own growth characteristic carries out principal component contributor rate calculating, chooses its validity feature value, and its validity feature value is 3-4
It is individual;Therefore, characteristic value number in terms of the characteristic value number value in terms of meteorological effect factor is 2 and 3, growing environment influence factor
Value is 2 and 3, and own growth influential factors aspect characteristic value number value is 3 and 4.So, different values can be obtained
To different combinations of features;Combinations of features refers to calculate by the PCA based on validity feature value number adjusting thresholds, passes through difference
Characteristic value number adjusting thresholds and value, 8 kinds of different combinations of features can be obtained, feature set is labeled as T1-T8。
Wherein, see Fig. 2, the specific steps of processing are optimized such as to the RBF neural of use based on particle cluster algorithm
Under:The hidden layer number of plies of RBF neural is determined first, a group particle is randomly generated, and coding determines population scale and parameter
Initial value, and particle position, initial randomization of speed are carried out, good and bad judgement, more new particle are then carried out to particle position
Body extreme value and population global extremum, so that particles spatial speed and flying speed are adjusted, it is finally full when training forecast model
When sufficient maximum iteration and minimum adaptation threshold value, i.e. the iterations of particle is big no more than maximum iteration, adaptation threshold value
When minimum adapts to threshold value, the RBF neural parameter after being optimized, i.e. accuracy rate highest weight parameter and iteration ginseng
Number.
Although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of changes, modification can be carried out to these embodiments, replace without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention is defined by the appended.
Claims (5)
1. a kind of paddy water requirement prediction method based on principal component analysis and neutral net, it is characterised in that:Specifically include
Following steps:
(1), obtain every factor of influence data during the regional paddy growth of experiment, the instruction for building neural network model
Practice collection and test set, the quality of constructed neural network model is judged by predictablity rate;
(2), completion, interpolation, denoising and normalized are carried out to the factor of influence data during the paddy growth of acquisition;
(3), according to meteorological condition, growing environment condition, own growth characteristic these three aspects from the shadow during paddy growth
Selected characteristic in factor data is rung, and the principal component analysis of feature based number adjusting thresholds is carried out respectively in terms of these three, from
And find different combinations of features;
(4), the structure of RBF neural network model is carried out to different combinations of features, be primarily based on particle cluster algorithm to use
RBF neural optimizes processing, by adjusting weight parameter and iterative parameter between the connection of neutral net neuron, looks for
Go out accuracy rate highest weight parameter and iterative parameter, according to constructed by the weight parameter found out, iterative parameter and combinations of features
Optimal RBF neural network model water shortage status degree in the whole growth course of paddy rice is predicted, obtain paddy rice demand
That measures predicts the outcome.
2. a kind of paddy water requirement prediction method based on principal component analysis and neutral net according to claim 1, its
It is characterised by:Factor of influence data during described paddy growth include sunshine time, daily mean temperature, day highest gas
Temperature, daily minimal tcmperature, per day wind speed, average relative humidity, maximum relative humidity, minimum relative humidity, crop superficial radiation
Amount, blade saturation vapour pressure, blade actual water vapor pressure, blade area, crop plant height, density of crop, earth surface reflection
Amount, soil heat flux, the soil weight, soil acidity or alkalinity, water capacity and soil desertification rate.
3. a kind of paddy water requirement prediction method based on principal component analysis and neutral net according to claim 1, its
It is characterised by:The characteristic component of described meteorological condition includes daily mean temperature, daily maximum temperature, puts down daily minimal tcmperature, day
Equal relative humidity, maximum relative humidity, minimum relative humidity, sunshine time, wind speed and crop superficial radiation amount;Described growth
It is logical that the characteristic component of environmental condition includes the paddy growth soil weight, field-moisture capacity, desertification of land rate and Soil Thermal
Amount;The characteristic component of described own growth characteristic includes species density in planting, plant height and blade surface actual water vapor pressure.
4. a kind of paddy water requirement prediction method based on principal component analysis and neutral net according to claim 1, its
It is characterised by:The principal component analysis of described feature based number adjusting thresholds has specifically included following steps:To meteorological condition
Characteristic component carries out principal component contributor rate calculating, chooses its validity feature value;The characteristic component of growing environment condition is led
Components contribution rate is calculated, and chooses its validity feature value;Principal component contributor rate calculating is carried out to the characteristic component of own growth characteristic,
Choose its validity feature value;The validity feature for obtaining three aspects carries out different characteristic combination, particular by based on effective spy
The PCA of value indicative number adjusting thresholds is calculated, and by different characteristic value number adjusting thresholds and value, can obtain different spies
Levy combination.
5. a kind of paddy water requirement prediction method based on principal component analysis and neutral net according to claim 1, its
It is characterised by:Described optimizes comprising the following steps that for processing based on particle cluster algorithm to the RBF neural of use:It is first
The hidden layer number of plies of RBF neural is first determined, a group particle is randomly generated, coding determines that population scale and parameter are initial
Value, and particle position, initial randomization of speed are carried out, good and bad judgement, more new particle individual pole are then carried out to particle position
Value and population global extremum, so as to adjust particles spatial speed and flying speed, finally meet most when training forecast model
When big iterations and minimum adaptation threshold value, i.e., the iterations of particle is no more than maximum iteration, adapts to threshold value more than most
During small adaptation threshold value, accuracy rate highest weight parameter and iterative parameter are obtained.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710278851.6A CN107025505A (en) | 2017-04-25 | 2017-04-25 | A kind of paddy water requirement prediction method based on principal component analysis and neutral net |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710278851.6A CN107025505A (en) | 2017-04-25 | 2017-04-25 | A kind of paddy water requirement prediction method based on principal component analysis and neutral net |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107025505A true CN107025505A (en) | 2017-08-08 |
Family
ID=59528166
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710278851.6A Pending CN107025505A (en) | 2017-04-25 | 2017-04-25 | A kind of paddy water requirement prediction method based on principal component analysis and neutral net |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107025505A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107766938A (en) * | 2017-09-25 | 2018-03-06 | 南京律智诚专利技术开发有限公司 | A kind of plant cover cultivation methods based on BP neural network |
CN109934400A (en) * | 2019-03-08 | 2019-06-25 | 河北工程大学 | Based on the collection rain readjust-loss water demand of crop prediction technique for improving neural network |
CN111221880A (en) * | 2020-04-23 | 2020-06-02 | 北京瑞莱智慧科技有限公司 | Feature combination method, device, medium, and electronic apparatus |
CN114528040A (en) * | 2022-01-26 | 2022-05-24 | 高新兴科技集团股份有限公司 | Environment self-adaption method, device, medium and roadside perception and calculation system |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1631098A (en) * | 2003-12-25 | 2005-06-29 | 中国农业大学 | Insufficient irrigation forecast and control method |
CN101953287A (en) * | 2010-08-25 | 2011-01-26 | 中国农业大学 | Multi-data based crop water demand detection system and method |
CN102163301A (en) * | 2011-04-12 | 2011-08-24 | 上海大学 | Method for predicting emergence size of crop pests based on BP (back propagation) artificial neural network |
CN105184400A (en) * | 2015-08-31 | 2015-12-23 | 中国烟草总公司广东省公司 | Tobacco field soil moisture prediction method |
CN105938564A (en) * | 2016-04-29 | 2016-09-14 | 无锡中科智能农业发展有限责任公司 | Rice disease recognition method based on principal component analysis and neural network and rice disease recognition system thereof |
CN106557658A (en) * | 2016-11-10 | 2017-04-05 | 水利部交通运输部国家能源局南京水利科学研究院 | Irrigation requirement computing system and its method under a kind of climate change background |
-
2017
- 2017-04-25 CN CN201710278851.6A patent/CN107025505A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1631098A (en) * | 2003-12-25 | 2005-06-29 | 中国农业大学 | Insufficient irrigation forecast and control method |
CN101953287A (en) * | 2010-08-25 | 2011-01-26 | 中国农业大学 | Multi-data based crop water demand detection system and method |
CN102163301A (en) * | 2011-04-12 | 2011-08-24 | 上海大学 | Method for predicting emergence size of crop pests based on BP (back propagation) artificial neural network |
CN105184400A (en) * | 2015-08-31 | 2015-12-23 | 中国烟草总公司广东省公司 | Tobacco field soil moisture prediction method |
CN105938564A (en) * | 2016-04-29 | 2016-09-14 | 无锡中科智能农业发展有限责任公司 | Rice disease recognition method based on principal component analysis and neural network and rice disease recognition system thereof |
CN106557658A (en) * | 2016-11-10 | 2017-04-05 | 水利部交通运输部国家能源局南京水利科学研究院 | Irrigation requirement computing system and its method under a kind of climate change background |
Non-Patent Citations (1)
Title |
---|
刘婧然: ""人工神经网络智能节水灌溉浅析"", 《吉林水利》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107766938A (en) * | 2017-09-25 | 2018-03-06 | 南京律智诚专利技术开发有限公司 | A kind of plant cover cultivation methods based on BP neural network |
CN109934400A (en) * | 2019-03-08 | 2019-06-25 | 河北工程大学 | Based on the collection rain readjust-loss water demand of crop prediction technique for improving neural network |
CN109934400B (en) * | 2019-03-08 | 2023-05-16 | 河北工程大学 | Rain collecting, regulating and deficiency crop water demand prediction method based on improved neural network |
CN111221880A (en) * | 2020-04-23 | 2020-06-02 | 北京瑞莱智慧科技有限公司 | Feature combination method, device, medium, and electronic apparatus |
CN114528040A (en) * | 2022-01-26 | 2022-05-24 | 高新兴科技集团股份有限公司 | Environment self-adaption method, device, medium and roadside perception and calculation system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112602563A (en) | Water-saving irrigation system and accurate irrigation method | |
Tshiala et al. | Analysis of temperature trends over Limpopo province, South Africa | |
CN107025505A (en) | A kind of paddy water requirement prediction method based on principal component analysis and neutral net | |
CN109272146A (en) | A kind of Forecasting Flood method corrected based on deep learning model and BP neural network | |
Jing-Song et al. | Climatic suitability of the distribution of the winter wheat cultivation zone in China | |
CN106557658A (en) | Irrigation requirement computing system and its method under a kind of climate change background | |
WO2023179167A1 (en) | Crop irrigation water demand prediction method based on aquacrop model and svr | |
CN109978234A (en) | Soil moisture content prediction, irrigation decision method and apparatus | |
ZHOU et al. | A simulation of winter wheat crop responses to irrigation management using CERES-Wheat model in the North China Plain | |
CN112837169A (en) | Gridding drought comprehensive monitoring, early warning and evaluating method in drought process | |
CN108428017A (en) | Wind power interval prediction method based on core extreme learning machine quantile estimate | |
Deng et al. | Economics of land degradation in China | |
CN112215716A (en) | Crop growth intervention method, device, equipment and storage medium | |
Chen et al. | Informing the SWAT model with remote sensing detected vegetation phenology for improved modeling of ecohydrological processes | |
CN110516943B (en) | Surface temperature-based dynamic monitoring and remote sensing method for irrigation area in spring irrigation period | |
Hapuarachchi et al. | Investigation of the Mekong River basin hydrology for 1980–2000 using the YHyM | |
Zhang et al. | Research on the optimal allocation of agricultural water and soil resources in the Heihe River Basin based on SWAT and intelligent optimization | |
Feng et al. | Temporal and Spatial Variation Characteristics of NDVI and Its Relationship with Environmental Factors in Huangshui River Basin from 2000 to 2018. | |
Huang et al. | Research of soil moisture content forecast model based on genetic algorithm BP neural network | |
CN109934400B (en) | Rain collecting, regulating and deficiency crop water demand prediction method based on improved neural network | |
CN110458438A (en) | The calculation method and device of the impact factor of vegetation water use efficiency WUE | |
CN113873459B (en) | Multi-sensor optimized deployment method for soil component collection | |
CN115033833B (en) | Agricultural irrigation water quota computing system | |
Barkey et al. | Model of climate and LAND-USE changes impact on water security in Ambon city, Indonesia | |
Chen et al. | Review of research on irrigation decision control |
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: 20170808 |