CN-122022020-A - Method for predicting machine cotton picking yield based on temperature-light cooperative model

CN122022020ACN 122022020 ACN122022020 ACN 122022020ACN-122022020-A

Abstract

The invention relates to the technical field of agricultural management, in particular to a method for predicting machine cotton yield based on a temperature-light cooperative model, which comprises the following steps of S1, multi-source data acquisition, namely acquiring meteorological data, remote sensing data and ground agricultural data of a target cotton field; S2, calculating a warm light cooperative index, namely calculating an effective temperature accumulation amount, an effective radiation accumulation amount and a leaf area index based on meteorological data, remote sensing data and ground agronomic data of a target cotton field, and calculating the warm light cooperative index based on the effective temperature accumulation amount and the effective radiation accumulation amount, S3, constructing a comprehensive prediction model by utilizing a gradient lifting decision tree algorithm, and S4, predicting yield and quality, namely inputting the warm light cooperative index serving as an input characteristic into the comprehensive prediction model, and obtaining a yield predicted value and a quality predicted value of machine-harvested cotton. According to the method, through the design of the temperature light cooperative index, the cooperative effect of temperature and illumination on cotton can be quantized, and the prediction accuracy is improved.

Inventors

WANG LIANG
ZHANG NA
LIANG FUBIN
LV QINGQING
Ilshati Abuleti
ZHANG HONG
LIN TAO
WANG JING
LIU ZIQIANG
CUI JIANPING
WU YING
GUO RENSONG
TIAN LIWEN
TANG QIUXIANG

Assignees

新疆维吾尔自治区农业科学院

Dates

Publication Date: 20260512
Application Date: 20260113

Claims (10)

1. The method for predicting the machine-harvested cotton yield based on the temperature-light cooperative model is characterized by comprising the following steps of: S1, multi-source data acquisition, namely acquiring meteorological data, remote sensing data and ground agronomic data of a target cotton field; S2, calculating a temperature-light synergy index, namely calculating an effective temperature accumulation amount, an effective radiation accumulation amount, a leaf area index and a water stress index based on meteorological data, remote sensing data and ground agronomic data of a target cotton field, and calculating a temperature-light synergy index based on the effective temperature accumulation amount, the effective radiation accumulation amount, the leaf area index and the water stress index; S3, constructing a comprehensive prediction model, namely constructing the comprehensive prediction model by utilizing a gradient lifting decision tree algorithm, training the comprehensive prediction model by utilizing meteorological data, remote sensing data and ground agronomic data of a plurality of cotton fields, and acquiring the trained comprehensive prediction model; And S4, predicting the yield and the quality, namely taking the temperature and light synergy index as an input characteristic, inputting the input characteristic into a comprehensive prediction model, and obtaining a yield predicted value and a quality predicted value of the machine-harvested cotton.
2. The method for predicting machine-harvested cotton yield based on a temperature-light cooperative model according to claim 1, wherein in S1, the meteorological data includes total solar radiation, highest daily temperature and lowest daily temperature; in S2, an effective temperature accumulation amount is calculated based on the day maximum temperature and the day minimum temperature, and an effective radiation accumulation amount is calculated based on the day total radiation.
3. The method for predicting machine-acquired cotton yield based on a temperature-light cooperative model according to claim 1, wherein in S1, the remote sensing data comprises multispectral images; In S2, the leaf area index is calculated based on the multispectral image.
4. The method for predicting machine-produced cotton yield based on a temperature-light cooperative model according to claim 1, wherein in S1, the ground agronomic data includes planting density, cotton variety, soil moisture content and field water holding capacity; the water stress index is calculated based on soil moisture content and field water holding capacity.
5. The method for predicting machine-harvested cotton yield based on a temperature-light cooperative model according to claim 1, wherein in S2, the calculation formula of the effective temperature accumulation amount is as follows: CGDD=D·[(Tmax+Tmin)/2-Tbase] (1); Wherein CGDD is an effective temperature accumulation amount, D is the growth days of cotton, tmax is the average day maximum temperature of the growth days, tmin is the average day minimum temperature of the growth days, and Tbase is the cotton base temperature.
6. The method for predicting machine-produced cotton yield based on a temperature-light cooperative model according to claim 5, wherein in S2, the calculation formula of the effective radiation accumulation amount is as follows: CPAR = D-solar total radiation/2 (2); Wherein CPAR is the cumulative amount of effective radiation.
7. The method for predicting machine-harvested cotton yield based on a temperature-light cooperative model according to claim 6, wherein in S2, a calculation formula of the water stress index is as follows: WSI=1-(W1/W2) (3); Wherein WSI is water stress index, W1 is soil water content, and W2 is field water holding capacity.
8. The method for predicting machine-harvested cotton yield based on a temperature-light cooperative model as claimed in claim 7, wherein in S2, a calculation formula of the temperature-light cooperative index is as follows: TCI=(CGDD·CPAR·LAI)/(Var+WSI) (4); wherein TCI is a temperature light synergy index, var is a canopy temperature variance, and LAI is a leaf area index.
9. The method for predicting machine-harvested cotton yield based on a temperature-light cooperative model according to claim 8, wherein in S4, the input characteristics when calculating the cotton yield prediction value include a historical average yield, a historical average density, a historical temperature-light cooperative index, a current temperature-light cooperative index and a current planting density of the same cotton variety of the target cotton field; The cotton yield prediction value is calculated as follows: Y 1 =（TCI 1 /TCI 0 ）×(M 1 /M 0 )×Y 0 (5); wherein Y 1 is a yield predicted value, TCI 1 is a current temperature light synergy index, TCI 0 is a historical temperature light synergy index, M 1 is a current planting density, M 0 is a historical average planting density, and Y 0 is a historical average yield.
10. The method for predicting machine-harvested cotton yield based on a temperature-light cooperative model according to claim 9, wherein in S4, the input characteristics when calculating the cotton quality predicted value comprise historical quality parameters, historical temperature-light cooperative indexes and current temperature-light cooperative indexes of the same cotton variety of the target cotton field, the cotton quality predicted value comprises at least one of average fiber length, fracture ratio strength and micronaire value, the historical quality parameters comprise average fiber length, historical fracture ratio strength and historical micronaire value, and the average fiber length, the historical fracture ratio strength and the historical micronaire value are obtained by sampling and measuring cotton; F 1 =（TCI 1 /TCI 0 ）×S 0 (6); wherein F 1 is a quality predicted value, TCI 1 is a current temperature light synergy index, and S 0 is any one of a historical fiber average length, a historical fracture ratio strength and a historical micronaire value.

Description

Method for predicting machine cotton picking yield based on temperature-light cooperative model Technical Field The invention relates to the technical field of agricultural management, in particular to a method for predicting machine-harvested cotton yield based on a temperature-light cooperative model. Background Cotton is one of the most important commercial crops worldwide, and with the acceleration of the modern agricultural progress and the continuous increase of labor cost, the mechanized harvesting of cotton has become a necessary trend for the production and development of cotton. Under different varieties and planting modes, the yield forming process of the machine-harvested cotton is more concentrated and is more sensitive to the influence of dynamic changes of environmental factors such as ambient temperature light and the like. Therefore, accurate prediction of the machine-harvested cotton yield is realized, a reliable and efficient machine-harvested cotton yield and quality prediction technology is developed, and the machine-harvested cotton yield and quality prediction method has extremely important practical significance for planting planning, optimizing water and fertilizer resource allocation management for cotton production, guaranteeing raw cotton market supply and demand balance, stabilizing market price, improving cotton planting benefits and industrial economic benefits of cotton farmers and collaborative development of whole industrial chains. The yield and quality of the cotton picked form the coupling synergistic effect of the deep-temperature-receiving light factor, and the effect of temperature light on the formation of the cotton yield is a core physiological and ecological process. Cotton yield is essentially the result of the accumulation and distribution of dry matter produced by photosynthesis in different organs (especially bolls), while temperature and light are the two most critical environmental energy factors driving this process. The effect of warm light on cotton yield extends through the whole growth period of cotton, and the effect is not simply overlapped, but is a complex process of warm light synergy and interaction. The plant type is loose, pollen tubes are restrained from being elongated when the pollen tube is exposed to low temperature, pollination is poor, and the shedding of the bolls is increased, and the activity of photosynthetic enzyme is directly reduced, fertilization is failed or the growth of young bolls is stopped when the plant type is exposed to high temperature or overcast and rainy, so that the shedding rate is greatly increased, and even if the bolls are formed, the weight and quality of the bolls are reduced. The proper temperature and sufficient illumination are important conditions for guaranteeing high yield and high quality, otherwise, the yield is easily reduced and fiber dysplasia is easily caused. Therefore, environmental factors such as temperature, illumination and the like do not independently act, but cooperate with each other to control physiological processes such as photosynthesis, substance accumulation, distribution and the like together by a synergistic and interactive effect, so that the formation of cotton yield and quality is controlled. Methods of the prior art for predicting machine-harvested cotton yield based on a temperature-light collaborative model, such as WOFOST model, simulate potential growth and moisture-limited growth levels of crops by inputting weather data (e.g., solar radiation, temperature, and precipitation), soil data (e.g., moisture characteristics and nutrient status), and crop parameters (e.g., variety characteristics and growth period) day by day. The method is strong in theory and has definite physiological and physical mechanisms, so that the yield and quality of the mechanically-picked cotton are predicted. The formation of cotton yield and quality is deeply affected by the synergistic effect of environmental factors such as temperature (temperature) and illumination (light), and the like, and the prediction method in the prior art considers the influence of temperature and illumination on the cotton yield and quality respectively, but ignores the synergistic effect of temperature and light, does not consider the temperature light conduction rule under the micro-environment of a group, and cannot reasonably reflect the quantitative relation between the temperature light coupling parameters and physiological indexes of the key growth period of the mechanically picked cotton, so that the deviation between the prediction result and the actual result is larger. Therefore, it is necessary to construct a machine-harvested cotton temperature-light cooperative prediction model with clear mechanism, reliable parameters and strong universality, and provide a novel method for predicting machine-harvested cotton yield based on the temperature-light cooperative model, which can quantify the temperature-light c