An agricultural resource and environment monitoring method and system fusing multi-source remote sensing data

Abstract

The application discloses a kind of agricultural resource environment monitoring method and system of fusion multi-source remote sensing data, it is related to agricultural resource environment monitoring technical field, the present application is integrated to multi-source remote sensing data, the evaluation accuracy of the growth cycle of each subarea in the region to be detected is improved, further monitoring of the region to be detected is provided with strong data support, remote sensing far layer technology and unmanned aerial vehicle near layer technology are dynamically combined, and the monitoring effect of the region to be detected is improved, the present application is based on soil nutrient condition, straw quality condition and soil compactness, the harvesting parameter of mature subarea of the region to be detected is determined, the relationship that corn straw retention quantity meets soil nutrient demand and harvesting height meets soil compactness demand is balanced, the matching degree of corn straw retention quantity and soil nutrient demand is improved, and the damage rate of intelligent harvesting equipment is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of agricultural resource monitoring, in particular to an agricultural resource environment monitoring method and system fusing multi-source remote sensing data. BACKGROUND

[0002] The agricultural resource environment monitoring method is irreplaceable in ensuring food security, maintaining ecological balance, supporting policy and scientific research, and is an inevitable choice to meet the needs of fine management in response to complex environmental changes. As an important food crop and economic crop, the growth and yield of corn are affected by many factors. The agricultural resource environment monitoring method plays an irreplaceable role in corn production.

[0003] The prior art such as the patent for invention with publication number CN117575174B discloses an intelligent agricultural monitoring and management system, which includes a data acquisition unit, a transfer learning unit and a monitoring unit. The invention can improve agricultural production efficiency and provide intelligent decision support for agricultural management. The patent for invention with publication number CN105445214B discloses an agricultural engineering remote sensing monitoring method, which uses remote sensing to monitor crops and monitor crop growth conditions and locust diseases. The method improves the monitoring accuracy of agricultural engineering by studying the infrared reflection spectrum of crops, ensures a good growing environment for crops, and promotes the application of remote sensing technology in agricultural engineering.

[0004] By comparing the above scheme, it can be found that the prior art still has some deficiencies, which are specifically reflected in the following aspects: the prior art rarely integrates multi-source remote sensing data to determine the growth cycle of each sub-region in the detection area, which may lead to inaccurate evaluation of the growth cycle of each sub-region in the detection area, making it difficult to provide strong data support for further monitoring of the detection area, and reducing the monitoring effect of the detection area. At the same time, there is a lack of evaluation of the harvesting parameters of mature sub-regions in the detection area, which makes it difficult to balance the relationship between the corn straw retention amount meeting the soil nutrient demand and the harvesting height meeting the soil compactness demand, resulting in a mismatch between the corn straw retention amount and the soil nutrient demand, and increasing the damage rate of intelligent harvesting equipment. SUMMARY

[0005] The present application provides an agricultural resource environment monitoring method and system fusing multi-source remote sensing data, which solves the problems in the background art.

[0006] To solve the above technical problems, the present application adopts the following technical scheme: the present application provides an agricultural resource environment monitoring method fusing multi-source remote sensing data, which comprises the following steps: S1, collecting the detection area by using remote sensing technology to obtain remote sensing monitoring data of the detection area.

[0007] S2, determine a growth cycle set of the to-be-inspected region by using remote sensing monitoring data of the to-be-inspected region, and predict a mature time point set of the to-be-inspected region.

[0008] S3, screen each mature sub-region of the to-be-inspected region according to the growth cycle set of the to-be-inspected region, and perform data collection on each mature sub-region of the to-be-inspected region again to obtain an updated data set of the to-be-inspected region.

[0009] S4, determine a reserved parameter of each mature sub-region of the to-be-inspected region according to the updated data set of the to-be-inspected region, and use the reserved parameter as a harvesting parameter of an intelligent harvesting device of the to-be-inspected region.

[0010] S5, transmit the harvesting parameter of the intelligent harvesting device to a harvesting platform management center of the intelligent harvesting device.

[0011] The second aspect of the application provides a system for performing the agricultural resource environment monitoring method of fusing multi-source remote sensing data, comprising: a remote sensing monitoring data module, configured to collect a to-be-inspected region by using remote sensing technology to obtain remote sensing monitoring data of the to-be-inspected region.

[0012] A growth cycle determination module is configured to determine a growth cycle set of the to-be-inspected region by using remote sensing monitoring data of the to-be-inspected region, and predict a mature time point set of the to-be-inspected region.

[0013] A re-collection module is configured to screen each mature sub-region of the to-be-inspected region according to the growth cycle set of the to-be-inspected region, and perform data collection on each mature sub-region of the to-be-inspected region again to obtain an updated data set of the to-be-inspected region.

[0014] A harvesting parameter determination module is configured to determine a reserved parameter of each mature sub-region of the to-be-inspected region according to the updated data set of the to-be-inspected region, and use the reserved parameter as a harvesting parameter of an intelligent harvesting device of the to-be-inspected region.

[0015] A processing terminal is configured to transmit the harvesting parameter of the intelligent harvesting device to a harvesting platform management center of the intelligent harvesting device.

[0016] The application has the following beneficial effects: (1) the application integrates multi-source remote sensing data to determine the growth cycle of each sub-region in the to-be-inspected region, improves the evaluation accuracy of the growth cycle of each sub-region in the to-be-inspected region, provides strong data support for further monitoring of the to-be-inspected region, and facilitates dynamic joint remote sensing upper layer technology and unmanned aerial vehicle near layer technology to improve the monitoring effect of the to-be-inspected region.

[0017] (2) The application determines the harvesting parameters of the mature sub-regions of the to-be-inspected region based on the soil nutrition condition, the straw quality condition and the soil compactness, balances the relationship between the corn straw retention amount meeting the soil nutrition demand and the harvesting height meeting the soil compactness demand, improves the matching degree of the corn straw retention amount and the soil nutrition demand, and reduces the damage rate of the intelligent harvesting equipment. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0019] Figure 1 The present application is a method for implementing the steps of the flowchart.

[0020] Figure 2 The present application is a system structure connection diagram. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments only constitute some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0022] Referring to Figure 1 The present application provides an agricultural resource environment monitoring method and system fusing multi-source remote sensing data, which comprises the following steps: S1, collecting a to-be-inspected region by using remote sensing technology to obtain remote sensing monitoring data of the to-be-inspected region.

[0023] In specific embodiments of the present application, the remote sensing monitoring data comprises canopy structure features, leaf curling morphological feature values, ear spectral data sets, NDVI time series data sets, REP-Dlared time series data sets and CWSI time series data sets of a plurality of sub-regions in a target period, the canopy structure features comprise ear length, ear diameter and bract color value, and the leaf curling morphological feature value is a numerical value of 0 or 1, when the leaf curling morphological feature value is 1, it indicates that the leaf has a curling morphology.

[0024] It should be noted that the canopy structure features, leaf curling morphological feature values, and ear spectral data set in the target period are obtained by high-resolution satellite images, the NDVI time series data set and the REP-Dλred time series data set are obtained from medium-resolution multispectral data, the day-night temperature difference and the canopy-air temperature difference are obtained by satellite thermal infrared images, and the CWSI time series data set is obtained by combining medium-resolution multispectral data and satellite thermal infrared images.

[0025] Specifically, the canopy structure features such as ear length, ear diameter, and bract color value are important manifestations of the growth status of corn. As corn matures, ear length and ear diameter will gradually increase and tend to be stable. As corn matures, the chlorophyll content in the leaves will gradually decrease, causing the color of the leaves to change, so it is necessary to collect the canopy structure features.

[0026] Specifically, the leaf curling morphology is related to the growth and development stage of corn. As corn matures, the leaves will gradually curl and eventually wither and fall off. Therefore, it is necessary to monitor the leaf curling morphology.

[0027] Specifically, the ear spectral data is specifically to obtain the decline rate of near-infrared reflectance. As corn leaves age and mature, cell structures gradually disintegrate and water content decreases, resulting in a decrease in near-infrared reflectance. Therefore, monitoring the decline rate of near-infrared reflectance can be an important indicator for evaluating the degree of leaf senescence and maturity of corn.

[0028] Specifically, the NDVI (Normalized Difference Vegetation Index) time series data set is used to obtain the post-peak NDVI decline rate. The NDVI value increases first and then decreases during the corn growing season. When NDVI reaches the peak value and starts to decline, it indicates that corn has passed the most vigorous stage of vegetative growth and has begun to transition to reproductive growth. Therefore, it is necessary to evaluate the post-peak NDVI decline rate. On the other hand, it is used to obtain the average ratio of Dλred-NDVI in combination with the REP-Dλred time series data set. Drought stress accelerates chlorophyll degradation, resulting in early REP blue shift, but the Dλred-NDVI ratio processing method can exclude interference.

[0029] Specifically, the REP-Dλred time series dataset, wherein the REP blue shift interval refers to a region in the REP curve where the reflectivity decreases with the increase of wavelength. With the decrease of chlorophyll content and the change of other biochemical components during the aging and maturation of the corn leaves, the REP blue shift interval also changes accordingly, and the Dλred change interval, similar to the analysis method of the REP blue shift interval, refers to the characteristic difference of the reflectivity in the red light band with the change of wavelength. With the change of the pigment composition and the cell structure during the aging and maturation of the corn leaves, the Dλred also changes accordingly. Therefore, the analysis of the REP blue shift interval and the Dλred change interval can also provide strong support for the evaluation of the growth cycle of the corn.

[0030] Specifically, the CWSI (crop water stress index) time series dataset, with the gradual maturation of the corn, the demand and utilization efficiency of water change. The CWSI can reflect the water stress condition of the corn in real time, thereby indirectly reflecting the growth cycle of the corn.

[0031] S2, determining the growth cycle set of the to-be-inspected region by using the remote sensing monitoring data of the to-be-inspected region, and predicting the set of maturation time points of the to-be-inspected region.

[0032] In specific embodiments of the present application, the growth cycle set of the to-be-inspected region is determined in the following manner: based on the remote sensing monitoring data of the to-be-inspected region, a set of corn feature data of a plurality of sub-regions of the to-be-inspected region in a target period is constructed, and compared with a set of demand corn feature data corresponding to each growth cycle stored in the data warehouse, to screen the growth cycle of the plurality of sub-regions of the to-be-inspected region in the target period, thereby constructing the growth cycle set of the to-be-inspected region. wherein , , , , represents the growth cycle of the 1st sub-region, the growth cycle of the 2nd sub-region, the growth cycle of the 3rd sub-region, the growth cycle of the ith sub-region, and the growth cycle of the nth sub-region in the growth cycle set of the to-be-inspected region, is the number of the plurality of sub-regions, , is an integer greater than 2.

[0033] It should be noted that the demand corn characteristic data set corresponding to each growth cycle stored in the data warehouse is specifically derived from: like experts rely on their deep professional knowledge in agronomy, plant physiology, agricultural meteorology and other fields, and long-term observation and research experience of corn growth process, can understand the physiological characteristics of corn in different growth stages, morphological changes and response law to environment. For example, according to the mechanism of corn photosynthesis and the change rule of pigment, the expert can determine the reasonable range of NDVI (normalized difference vegetation index) related index in different growth cycle. For example, various sensors such as spectrum sensor, temperature sensor, humidity sensor, pressure sensor are arranged in the corn planting area, and the environmental information and physiological information of the crop itself in the corn growth process are obtained in real time. Through analysis and processing of a large amount of data collected by the sensor, the characteristic data related to the growth cycle of corn is extracted. For example, the reflectance spectrum data of corn canopy is obtained by using the spectrum sensor, and the NDVI value, near infrared reflectivity and other indexes in different growth stages are obtained through calculation and analysis, and the corresponding interval range is determined according to the data trend.

[0034] In a specific embodiment of the application, the method for constructing the corn characteristic data set of the plurality of sub-regions of the to-be-inspected region in the target period is: extracting the REP-Dλred time series data set and the NDVI time series data set of the plurality of sub-regions in the target period from the remote sensing monitoring data of the to-be-inspected region, and obtaining the average ratio of Dλred-NDVI of the plurality of sub-regions of the to-be-inspected region in the target period through data processing.

[0035] Specifically, the ratio of Dλred to NDVI is obtained by dividing a plurality of Dλred in the REP-Dλred time series data set by NDVI, to form a Dλred-NDVI data set, and the average ratio of Dλred-NDVI of the plurality of sub-regions of the to-be-inspected region in the target period is obtained through mean processing.

[0036] The leaf curling morphological feature value, ear spectral data set of the plurality of sub-regions in the target period are obtained from the remote sensing monitoring data of the to-be-inspected region, and the decline rate of near infrared reflectivity is obtained from the ear spectral data set.

[0037] The NDVI time series data set, REP-Dλred time series data set and CWSI time series data set of the plurality of sub-regions in the target period are obtained from the remote sensing monitoring data of the to-be-inspected region, and the NDVI post-peak decline rate, REP blue shift interval, Dλred change interval and CWSI change interval of the plurality of sub-regions of the to-be-inspected region in the target period are obtained.

[0038] The plurality of data in the canopy structure feature of the plurality of sub-regions in the target period are obtained from the remote sensing monitoring data of the to-be-inspected region.

[0039] The above data is summarized to construct a corn feature data set of a plurality of sub-regions of the to-be-inspected region in a target period.

[0040] The mature time point set of the to-be-inspected region is predicted, and the specific prediction method is as follows: based on the growth period set of the to-be-inspected region, the growth periods of a plurality of sub-regions of the to-be-inspected region are extracted, and a mature growth period is obtained from the data warehouse, so as to obtain the mature duration of the plurality of sub-regions of the to-be-inspected region, and in combination with a current time point, the mature time points of the plurality of sub-regions of the to-be-inspected region are obtained, and a mature time point set of the to-be-inspected region is constructed.

[0041] It should be noted that the mature time point set of the to-be-inspected region is specifically for subsequent adjustment of the monitoring frequency of the plurality of sub-regions of the to-be-inspected region, for example, if the mature time point of a sub-region is too long from the current time point, the monitoring frequency of the sub-region of the to-be-inspected region can be reduced in the future, if the mature time point of a sub-region is moderately long from the current time point, the monitoring frequency of the sub-region of the to-be-inspected region can be maintained in the future, and if the mature time point of a sub-region is too short from the current time point, the monitoring frequency of the sub-region of the to-be-inspected region can be increased in the future, so that the monitoring demand is met while the monitoring resources are saved.

[0042] S3, based on the growth period set of the to-be-inspected region, each mature sub-region of the to-be-inspected region is screened, and each mature sub-region of the to-be-inspected region is again data collected to obtain an updated data set of the to-be-inspected region.

[0043] It should be noted that the mature sub-regions of the to-be-inspected region are screened, and the specific screening method is as follows: based on the growth period set of the to-be-inspected region, that is, the growth periods of a plurality of sub-regions, and a plurality of sub-regions in the mature period are recorded as mature sub-regions, to obtain each mature sub-region of the to-be-inspected region.

[0044] In specific embodiments of the present application, the data collection of each mature sub-region of the to-be-inspected region is again collected, and the specific collection method is as follows: the center point of each mature sub-region of the to-be-inspected region is obtained, a secondary collection path of the to-be-inspected region is fitted, and a UAV is dispatched to collect data according to the secondary collection path, and the fixed sensor of each mature sub-region of the to-be-inspected region is used to collect data again.

[0045] The fixed sensor is, for example, a soil organic matter sensor, a soil pH value sensor, a soil total nitrogen sensor, a resistance type soil tightness sensor, etc.

[0046] In specific embodiments of the present application, the update dataset includes the planting density of each mature sub-region, the average height of corn plants, the characteristic values of each soil nutrient-related data, a three-dimensional image, the average reference base area of straw, and the characteristic values of each straw-related data, and soil compaction.

[0047] It should be noted that the unmanned aerial vehicle is equipped with a laser radar sensor to perform three-dimensional scanning modeling on each mature sub-region, thereby obtaining the planting density, the average height of corn plants, the three-dimensional image, the average reference base area of straw, and the characteristic values of each straw-related data.

[0048] Specifically, the characteristic values of each soil nutrient-related data include organic matter content, pH value, total nitrogen content, etc.

[0049] The characteristic values of each straw-related data include average moisture content, average cellulose content, average hemicellulose content, and average lignin content, etc., which are obtained by monitoring with a multi-spectral camera carried by the unmanned aerial vehicle.

[0050] The present application integrates multi-source remote sensing data to determine the growth cycle of each sub-region in the to-be-inspected area, thereby improving the evaluation accuracy of the growth cycle of each sub-region in the to-be-inspected area, providing strong data support for further monitoring of the to-be-inspected area, and facilitating the dynamic combination of remote sensing upper-layer technology and unmanned aerial vehicle lower-layer technology to improve the monitoring effect of the to-be-inspected area.

[0051] S4, according to the update dataset of the to-be-inspected area, determining the reserved parameters of each mature sub-region of the to-be-inspected area, and taking them as the harvesting parameters of the intelligent harvesting equipment of the to-be-inspected area.

[0052] In specific embodiments of the present application, the determination of the reserved parameters of each mature sub-region of the to-be-inspected area is specifically determined by obtaining the characteristic values of each soil-related data of each mature sub-region from the update dataset of the to-be-inspected area, and importing them into a soil negative nutrition evaluation model after being uniformly processed respectively , wherein is the characteristic value of the pth soil-related data of the mth mature sub-region after uniform processing, is the demand characteristic value of the pth soil-related data of the mth mature sub-region, is the number of each mature sub-region, , is an integer greater than 2, is the number of each soil-related data, , is an integer greater than 2, and the soil negative nutrition index of each mature sub-region of the to-be-inspected area is output.

[0053] The characteristic values of the straw-related data of each mature sub-region are obtained from the updated data set of the to-be-inspected region, and are introduced into the straw quality evaluation model to output the straw quality indicators of each mature sub-region of the to-be-inspected region.

[0054] It should be noted that the characteristic values of the soil-related data are subjected to uniformization processing, specifically, the upper limit values and the lower limit values of a plurality of soil-related data are extracted from the database, so that each soil-related data is subjected to uniformization processing.

[0055] The soil negative nutrition indicators and the straw quality indicators of each mature sub-region of the to-be-inspected region are introduced into the demand straw volume model to obtain the demand straw volume of each mature sub-region of the to-be-inspected region .

[0056] The soil compaction degree of each mature sub-region of the to-be-inspected region is matched with the corresponding suitable harvesting height interval of each soil compaction degree interval stored in the data warehouse to screen the suitable harvesting height interval of each mature sub-region of the to-be-inspected region .

[0057] It should be noted that the suitable harvesting height interval corresponding to each soil compaction degree interval is specifically set by a corn harvesting expert. When the soil compaction degree increases, the suitable harvesting height decreases, which reduces the risk of blade suspension of the intelligent harvesting equipment, protects the machinery, and when the soil compaction degree decreases, the suitable harvesting height increases, which prevents the intelligent harvesting equipment from being trapped in the vehicle and ensures the continuity of cutting.

[0058] If , the number of lodging regions of each mature sub-region of the to-be-inspected region is identified based on the three-dimensional image in the updated data set of the to-be-inspected region , if , the straw volume of each mature sub-region of the to-be-inspected region is predicted based on the floor area , the planting density , the average height of corn plants , and the average reference basic area of straw . If , the upper limit value of the suitable harvesting height interval of the mature sub-region is taken as the reserved height, and if , the initial reserved height of the mature sub-region is calculated , which is introduced into the initial reserved height correction model to output the reserved height of the mature sub-region , and the reserved mode of the mature sub-region is recorded as full reservation, forming the reserved parameters of the mature sub-region.

[0059] Specifically, the planting density is specifically the planting quantity per unit area.

[0060] If , the area of the several stalk-laying areas of the mature sub-area of the inspection area is obtained, and the total stalk-laying area of the mature sub-area is accumulated , the stalk volume of the mature sub-area is obtained through processing , the stalk volume of the mature sub-area is predicted, if , the upper limit value of the suitable harvesting height interval of the mature sub-area is taken as the reserved height, if , the initial reserved height of the mature sub-area is calculated , the reserved height of the mature sub-area is obtained through the initial reserved height correction model, the reserved mode of the mature sub-area is recorded as partial reservation, and the remaining area excluding the several stalk-laying areas is recorded as a partial reservation area, so as to obtain the reserved height, the reserved mode and the partial reservation area of the mature sub-area, and form the reserved parameters of the mature sub-area.

[0061] The reserved parameters of each mature sub-area of the inspection area are obtained according to the processing method.

[0062] In specific embodiments of the present application, the stalk quality evaluation model is specifically .

[0063] In the formula, is the feature value of the jth stalk-related data of the mth mature sub-area, is the feature value interval of the jth stalk-related data of the mth mature sub-area stored in the data warehouse, is the number of each stalk-related data, , is an integer greater than 2.

[0064] In specific embodiments of the present application, the demand stalk volume model is specifically .

[0065] In the formula, is the demand stalk volume corresponding to the increase of the unit soil negative nutrient index of the mth mature sub-area obtained from the data warehouse, is the reference soil negative nutrient index in the data warehouse.

[0066] The demand stalk volume corresponding to the increase of the unit soil negative nutrient index of each mature sub-area is specifically obtained in the following manner: if , the demand stalk volume corresponding to the increase of the unit soil negative nutrient index of the stalk quality grade of the mature sub-area is obtained from the data warehouse , A straw quality index range corresponding to the mth straw quality grade in the data warehouse.

[0067] The present application determines the harvesting parameters of the mature sub-regions of the to-be-inspected region based on the soil nutrition condition, the straw quality condition and the soil compactness, balances the relationship between the corn straw retention amount satisfying the soil nutrition demand and the harvesting height satisfying the soil compactness demand, improves the matching degree of the corn straw retention amount and the soil nutrition demand, and reduces the damage rate of the intelligent harvesting equipment.

[0068] S5, transmitting the harvesting parameters of the intelligent harvesting equipment to a harvesting platform management center of the intelligent harvesting equipment.

[0069] Referring to Figure 2 The second aspect of the present application provides a system for performing the agricultural resource environment monitoring method of fusing multi-source remote sensing data, comprising: a remote sensing monitoring data module for collecting the to-be-inspected region by using remote sensing technology to obtain remote sensing monitoring data of the to-be-inspected region.

[0070] A growth cycle determination module is configured to determine a growth cycle set of the to-be-inspected region by using the remote sensing monitoring data of the to-be-inspected region, and predict a set of maturation time points of the to-be-inspected region.

[0071] A re-collection module is configured to filter each mature sub-region of the to-be-inspected region according to the growth cycle set of the to-be-inspected region, and collect data of each mature sub-region of the to-be-inspected region again to obtain an updated data set of the to-be-inspected region.

[0072] A harvesting parameter determination module is configured to determine the reservation parameters of each mature sub-region of the to-be-inspected region according to the updated data set of the to-be-inspected region, and use the reservation parameters as the harvesting parameters of the intelligent harvesting equipment of the to-be-inspected region.

[0073] A processing terminal is configured to transmit the harvesting parameters of the intelligent harvesting equipment to a harvesting platform management center of the intelligent harvesting equipment.

[0074] It should be noted that the present application also includes a data warehouse, the remote sensing monitoring data module is connected with the growth cycle determination module, the growth cycle determination module is connected with the re-collection module, the re-collection module is connected with the harvesting parameter determination module, the harvesting parameter determination module is connected with the processing terminal, and the data warehouse is connected with the growth cycle determination module and the harvesting parameter determination module.

[0075] The above content is only an example and description of the concept of the present application, and those skilled in the art can make various modifications or supplements or use similar ways to replace the described specific embodiments, as long as they do not deviate from the concept of the present application or exceed the scope defined by the present application, which should belong to the protection scope of the present application.

Claims

1. Agricultural resource and environment monitoring method for fusing multi-source remote sensing data, characterized in that, The method comprises the following steps: S1, collecting the to-be-inspected area by using remote sensing technology to obtain remote sensing monitoring data of the to-be-inspected area; S2, determining a growth cycle set of the to-be-inspected area by using the remote sensing monitoring data of the to-be-inspected area, and predicting a set of mature time points of the to-be-inspected area; S3, screening each mature sub-area of the to-be-inspected area according to the growth cycle set of the to-be-inspected area, and performing data collection on each mature sub-area of the to-be-inspected area again to obtain an updated data set of the to-be-inspected area; S4, determining a reserved parameter of each mature sub-area of the to-be-inspected area according to the updated data set of the to-be-inspected area, and taking the reserved parameter as a harvesting parameter of an intelligent harvesting device of the to-be-inspected area; The updated data set comprises a planting density, an average height of corn plants, characteristic values of soil nutrition related data, a three-dimensional image, an average reference basic area of straw, and characteristic values of straw related data, and soil compaction degree of each mature sub-area; The specific determination method of the reserved parameter of each mature sub-area of the to-be-inspected area is as follows: The characteristic values of each soil-related data of each mature sub-region are obtained from the updated data set of the region to be detected, and are respectively subjected to uniformization processing and then introduced into a soil negative nutrition evaluation model In the method, wherein is the characteristic value of the pth soil-related data of the mth mature sub-region after uniformization processing, is the demand characteristic value of the pth soil-related data of the mth mature sub-region, is the number of each mature sub-region, , is an integer greater than 2, is the number of each soil-related data, , is an integer greater than 2, and a soil negative nutrition index of each mature sub-region of the region to be detected is output. The characteristic values of the straw related data of each mature sub-area are obtained from the updated data set of the to-be-inspected area, and are input into a straw quality evaluation model to output a straw quality index of each mature sub-area of the to-be-inspected area; The soil negative nutrition index and the straw quality index of each mature sub-region of the to-be-inspected area are introduced into the demand straw volume model to obtain the demand straw volume of each mature sub-region of the to-be-inspected area ; The soil compactness of each mature sub-region of the to-be-inspected area is matched with the suitable harvesting height interval corresponding to each soil compactness interval stored in the data warehouse, and a suitable harvesting height interval of each mature sub-region of the to-be-inspected area is obtained through screening ; like Based on the 3D images in the updated dataset of the region to be inspected, several lodged areas in each mature sub-region of the region to be inspected are identified, and the number of lodged areas in each mature sub-region of the region to be inspected is summarized. ,like Then, the straw volume of each mature subregion of the area to be inspected is predicted. ,like Then, the upper limit of the suitable harvesting height range for that mature sub-region is used as the reserved height. Then calculate the initial reserved height of the mature sub-region. Import it into the initial reserved height correction model In the middle, output the reserved height of the mature sub-region. The reservation method of the mature sub-region is recorded as full reservation, forming the reservation parameters of the mature sub-region; If , the area of several lodging areas of the mature sub-region of the detection area is obtained, and the reserved parameter of the mature sub-region is obtained through the same processing. The reserved parameter of each mature sub-area of the to-be-inspected area is obtained according to the above processing method; S5, transmitting the harvesting parameter of the intelligent harvesting device to a harvesting platform management center of the intelligent harvesting device. 2.The agricultural resource and environment monitoring method of fusing multi-source remote sensing data according to claim 1, characterized in that, The remote sensing monitoring data comprises canopy structure characteristics, leaf curling morphology characteristic values, ear spectral data sets, NDVI time series data sets, REP-Dλred time series data sets, and CWSI time series data sets of a plurality of sub-areas in a target period, the canopy structure characteristics comprise ear length, ear diameter, and bract color value, and the leaf curling morphology characteristic value is a numerical value of 0 or 1, and when the leaf curling morphology characteristic value is 1, it indicates that the leaf has a curling morphology. 3.The agricultural resource and environment monitoring method of fusing multi-source remote sensing data according to claim 2, characterized in that, The specific determination method of the growth cycle set of the to-be-inspected area is as follows: Based on remote sensing monitoring data of the to-be-inspected area, a corn feature data set of a plurality of sub-areas in the target period of the to-be-inspected area is constructed, and compared with the demand corn feature data set corresponding to each growth period stored in the data warehouse, to screen the growth period of the plurality of sub-areas in the target period of the to-be-inspected area, and construct a growth period set of the to-be-inspected area , , , , , respectively represent the growth period of the first sub-area, the growth period of the second sub-area, the growth period of the third sub-area, the growth period of the i-th sub-area, and the growth period of the n-th sub-area in the growth period set of the to-be-inspected area, is the number of the plurality of sub-areas, , is an integer greater than 2. 4.The agricultural resource and environment monitoring method of fusing multi-source remote sensing data according to claim 3, characterized in that, The specific construction method of the corn feature data set of the plurality of sub-areas of the to-be-inspected area in the target period is as follows: The REP-Dλred time series data set and the NDVI time series data set of the plurality of sub-areas in the target period are extracted from the remote sensing monitoring data of the to-be-inspected area, and the average ratio of Dλred-NDVI of the plurality of sub-areas of the to-be-inspected area in the target period is obtained through data processing; The leaf curling morphology characteristic value and the ear spectral data set of the plurality of sub-areas in the target period are obtained from the remote sensing monitoring data of the to-be-inspected area, and the decline rate of near-infrared reflectivity is obtained from the ear spectral data set; The NDVI time series data set, the REP-Dλred time series data set, and the CWSI time series data set of the plurality of sub-areas in the target period are obtained from the remote sensing monitoring data of the to-be-inspected area, and the NDVI post-peak decline rate, the REP blue shift interval, the Dλred change interval, and the CWSI change interval of the plurality of sub-areas of the to-be-inspected area in the target period are obtained; A plurality of data in the canopy structure characteristics of the plurality of sub-areas in the target period are obtained from the remote sensing monitoring data of the to-be-inspected area; The above data is summarized to construct a corn feature data set of a plurality of sub-regions of the to-be-inspected region in a target period. 5.The agricultural resource and environment monitoring method of fusing multi-source remote sensing data according to claim 1, characterized in that, The mature sub-regions of the to-be-inspected region are again subjected to data collection, and the specific collection method is as follows: The center points of the mature sub-regions of the to-be-inspected region are obtained, a secondary collection path of the to-be-inspected region is fitted, and a UAV is dispatched to collect data according to the secondary collection path, while the fixed sensors of the mature sub-regions of the to-be-inspected region are again subjected to data collection. 6.The agricultural resource and environment monitoring method of fusing multi-source remote sensing data according to claim 1, characterized in that, The straw quality evaluation model is specifically: ; In the formula is a feature value of the jth straw-related data of the mth mature sub-region, is a feature value interval of the jth straw-related data of the mth mature sub-region stored in the data warehouse, is the number of each straw-related data, , is an integer greater than 2. 7.The agricultural resource and environment monitoring method of fusing multi-source remote sensing data according to claim 1, characterized in that, The demand straw body quantity model, in particular, is ; In the formula is the demand straw volume corresponding to the increase of the unit soil negative nutrient index of the mth mature sub-region obtained from the data warehouse, is the reference soil negative nutrient index in the data warehouse; The demand straw body volume corresponding to the unit soil negative nutrient index increase of each mature sub-region is specifically obtained as follows: if , then the demand straw body volume corresponding to the unit soil negative nutrient index increase of the mature sub-region in the straw quality grade is obtained from the data warehouse , is the straw quality index range corresponding to the mth straw quality grade in the data warehouse.

8. A system for performing the agricultural resource and environment monitoring method of fusing multi-source remote sensing data according to any one of claims 1-7, characterized in that, It comprises: a remote sensing monitoring data module for collecting the to-be-inspected region by using remote sensing technology to obtain remote sensing monitoring data of the to-be-inspected region; a growth period determination module for determining a growth period set of the to-be-inspected region by using the remote sensing monitoring data of the to-be-inspected region, and predicting a set of mature time points of the to-be-inspected region; a re-collection module for screening the mature sub-regions of the to-be-inspected region according to the growth period set of the to-be-inspected region, and again collecting data of the mature sub-regions of the to-be-inspected region to obtain an updated data set of the to-be-inspected region; a harvesting parameter determination module for determining the reserved parameters of the mature sub-regions of the to-be-inspected region according to the updated data set of the to-be-inspected region, and taking the reserved parameters as the harvesting parameters of the intelligent harvesting equipment of the to-be-inspected region; a processing terminal for transmitting the harvesting parameters of the intelligent harvesting equipment to a harvesting platform management center of the intelligent harvesting equipment.

Images