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

Abstract

The invention discloses an agricultural resource environment monitoring method and system fused with multi-source remote sensing data, relates to the technical field of agricultural resource environment monitoring, integrates the multi-source remote sensing data, improves the evaluation accuracy of the growth cycle of each sub-region in a to-be-detected region, and improves the evaluation accuracy of the growth cycle of each sub-region in the to-be-detected region. The method provides powerful data support for subsequent further monitoring of the to-be-detected area, facilitates dynamic combination of a remote sensing far-layer technology and an unmanned aerial vehicle near-layer technology, improves the monitoring effect of the to-be-detected area, determines harvesting parameters of the mature sub-area of the to-be-detected area based on the soil nutrition condition, the straw quality condition and the soil compactness, and improves the monitoring accuracy of the to-be-detected area. The relation that the remaining amount of the corn straw meets the soil nutrient requirement and the harvesting height meets the soil compactness requirement is balanced, the matching degree of the remaining amount of the corn straw and the soil nutrient requirement is improved, and the damage rate of intelligent harvesting equipment is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural resource monitoring, and particularly relates to a method and system for monitoring agricultural resource environment by integrating multi-source remote sensing data. Background Art

[0002] The method for monitoring agricultural resource environment is of irreplaceable importance in ensuring food security, maintaining ecological balance, supporting policies and scientific research, and is an inevitable choice for coping with complex environmental changes and meeting the needs of refined management. As an important food crop and cash crop, the growth status and yield of corn are affected by various factors. The method for monitoring agricultural resource environment plays an irreplaceable role in corn production.

[0003] The prior art, such as the invention application patent with the publication number of CN117575174B, discloses an intelligent agricultural monitoring and management system, including: a data acquisition unit, a transfer learning unit, and a monitoring unit. This invention can improve agricultural production efficiency and provide intelligent decision-making support for agricultural management. Another example is the invention application patent with the publication number of CN105445214B, which discloses an agricultural engineering remote sensing monitoring method. It uses remote sensing to monitor crops and monitors the growth status of crops and locust diseases. Through the research on the infrared reflection spectrum of crops, it improves the monitoring accuracy of agricultural engineering, ensures a good growth environment for crops, and promotes the application of remote sensing technology in agricultural engineering.

[0004] Comparing with the above solutions, it can be found that there are still certain deficiencies in the prior art, which are specifically reflected in the following aspects: In the prior art, there is little integration of multi-source remote sensing data to determine the growth cycles of each sub-region within the area to be inspected, and it is easy to have inaccurate evaluation of the growth cycles of each sub-region within the area to be inspected, making it difficult to provide strong data support for further monitoring of the area to be inspected. It is difficult to dynamically combine remote sensing far-layer technology and unmanned aerial vehicle near-layer technology, reducing the monitoring effect of the area to be inspected. At the same time, there is also a lack of evaluation of the harvesting parameters of the mature sub-regions in the area to be inspected, making it difficult to balance the relationship between the corn straw retention amount meeting the soil nutrient requirements and the harvesting height meeting the soil compaction requirements, resulting in a mismatch between the corn straw retention amount and the soil nutrient requirements and increasing the damage rate of intelligent harvesting equipment. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for monitoring agricultural resource environment by integrating multi-source remote sensing data, which solves the problems in the background art.

[0006] To solve the above technical problems, the present invention adopts the following technical solutions: In the first aspect of the present invention, a method for monitoring agricultural resource environment by integrating multi-source remote sensing data is provided, including: S1. Using remote sensing technology to collect the area to be inspected to obtain the remote sensing monitoring data of the area to be inspected.

[0007] S2. Use the remote sensing monitoring data of the area to be inspected to determine the growth cycle set of the area to be inspected, and predict the set of maturity time points of the area to be inspected.

[0008] S3. According to the growth cycle set of the area to be inspected, screen each mature sub-region of the area to be inspected, and collect data again for each mature sub-region of the area to be inspected to obtain an updated data set of the area to be inspected.

[0009] S4. According to the updated data set of the area to be inspected, determine the reserved parameters of each mature sub-region of the area to be inspected, and use them as the harvesting parameters of the intelligent harvesting equipment for the area to be inspected.

[0010] S5. Transmit the harvesting parameters of the intelligent harvesting equipment to the harvesting platform management center of the intelligent harvesting equipment.

[0011] In the second aspect of the present invention, there is provided a system for implementing the agricultural resource environment monitoring method for fusing multi-source remote sensing data according to the present invention, including: a remote sensing monitoring data module for collecting the area to be inspected by using remote sensing technology to obtain the remote sensing monitoring data of the area to be inspected.

[0012] A growth cycle determination module for using the remote sensing monitoring data of the area to be inspected to determine the growth cycle set of the area to be inspected and predict the set of maturity time points of the area to be inspected.

[0013] A re-collection module for screening each mature sub-region of the area to be inspected according to the growth cycle set of the area to be inspected, and collecting data again for each mature sub-region of the area to be inspected to obtain an updated data set of the area to be inspected.

[0014] A harvesting parameter determination module for determining the reserved parameters of each mature sub-region of the area to be inspected according to the updated data set of the area to be inspected, and using them as the harvesting parameters of the intelligent harvesting equipment for the area to be inspected.

[0015] A processing terminal: for transmitting the harvesting parameters of the intelligent harvesting equipment to the harvesting platform management center of the intelligent harvesting equipment.

[0016] The beneficial effects of the present invention are as follows: (1) The present invention integrates multi-source remote sensing data to determine the growth cycles of each sub-region within the area to be inspected, improves the evaluation accuracy of the growth cycles of each sub-region within the area to be inspected, provides strong data support for subsequent further monitoring of the area to be inspected, facilitates the dynamic combination of remote sensing far-layer technology and unmanned aerial vehicle near-layer technology, and improves the monitoring effect of the area to be inspected.

[0017] (2) The present invention determines the harvesting parameters of the mature sub-regions in the area to be inspected based on the soil nutrient status, straw quality status, and soil compactness, balances the relationship between the maize straw retention amount to meet the soil nutrient requirements and the harvesting height to meet the soil compactness requirements, improves the matching degree between the maize straw retention amount and the soil nutrient requirements, and reduces the damage rate of intelligent harvesting equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 It is a schematic flowchart of the implementation steps of the method of the present invention.

[0020] Figure 2 It is a schematic connection diagram of the system structure of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0022] Referring to Figure 1 As shown, the present invention provides an agricultural resource and environment monitoring method and system integrating multi-source remote sensing data, including: S1. Using remote sensing technology to collect the area to be inspected to obtain the remote sensing monitoring data of the area to be inspected.

[0023] In the specific embodiments of the present invention, the remote sensing monitoring data includes the canopy structure characteristics, leaf curling morphological characteristic values, ear spectral data sets, NDVI time series data sets, REP-Dλred time series data sets, and CWSI time series data sets of several sub-regions within the target period. The canopy structure characteristics include ear length, ear diameter, and bract chromaticity values. The leaf curling morphological characteristic value is a numerical value of 0 or 1. When the leaf curling morphological characteristic value is 1, it indicates that the leaf has a curling morphology.

[0024] It should be noted that the canopy structure characteristics, leaf curling morphological characteristic values, and ear spectral data sets within the target period are specifically obtained through high-resolution satellite images. The NDVI time series data sets and REP-Dλred time series data sets are specifically obtained from medium-resolution multispectral data. The diurnal temperature difference and canopy-air temperature difference are specifically obtained through satellite thermal infrared images. The CWSI time series data set is specifically obtained by combining medium-resolution multispectral data and satellite thermal infrared images.

[0025] Specifically, the canopy structure characteristics such as ear length, ear diameter, and bract color chromaticity values are important reflections of the growth status of corn. As corn matures, the 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, resulting in changes in leaf color. Therefore, it is necessary to collect the canopy structure characteristics.

[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 for obtaining the decline rate of near-infrared reflectance. As the corn leaves age and mature, the cell structure gradually disintegrates and the 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 senescence degree and maturity of corn leaves.

[0028] Specifically, for the NDVI (Normalized Difference Vegetation Index) time series data sets, on the one hand, it is for obtaining the decline rate after the NDVI peak. The NDVI value shows a trend of first increasing and then decreasing during the corn growth season. When the NDVI starts to decline after reaching the peak, it indicates that the corn has passed the stage of the most vigorous vegetative growth and begins to transition to reproductive growth. Therefore, it is necessary to evaluate the decline rate after the NDVI peak. On the other hand, it is for obtaining the average ratio of Dλred-NDVI by combining with the REP-Dλred time series data sets. Drought stress accelerates chlorophyll degradation, resulting in an earlier blue shift of REP, but the interference can be excluded through the processing method of the Dλred-NDVI ratio.

[0029] Specifically, for the REP-Dλred time series dataset, in the REP blue shift interval, the blue shift interval refers to the region in the REP curve where the reflectance decreases as the wavelength increases. As the chlorophyll content decreases and other biochemical components change during the aging and maturation of corn leaves, the REP blue shift interval will also change accordingly. For the Dλred change interval, similar to the analysis method of the REP blue shift interval, the Dλred change interval refers to the characteristic difference in the reflectance of the red light band as the wavelength changes. As the pigment composition and cell structure change during the aging and maturation of corn leaves, Dλred will also change accordingly. Therefore, analyzing the REP blue shift interval and the Dλred change interval can also provide strong support for evaluating the growth cycle of corn.

[0030] Specifically, for the CWSI (Crop Water Stress Index) time series dataset, as corn gradually matures, its water demand and utilization efficiency will change. CWSI can reflect the water stress status of corn in real time, thus indirectly reflecting its growth cycle.

[0031] S2. Using the remote sensing monitoring data of the area to be inspected, determine the growth cycle set of the area to be inspected and predict the set of maturity time points of the area to be inspected.

[0032] In a specific embodiment of the present invention, the method for specifically determining the growth cycle set of the area to be inspected is as follows: Based on the remote sensing monitoring data of the area to be inspected, construct a set of corn characteristic data for several sub-areas of the area to be inspected within the target cycle, and compare it with the set of required corn characteristic data corresponding to each growth cycle stored in the data warehouse, and screen the growth cycles of several sub-areas of the area to be inspected within the target cycle to construct the growth cycle set E = (α _1 , α _2 , α _3 ,..., α _i ,..., α _n ), where α _1 , α _2 , α _3 , α _i , α _n respectively represent the growth cycle of the first sub-area, the growth cycle of the second sub-area, the growth cycle of the third sub-area, the growth cycle of the i-th sub-area, and the growth cycle of the n-th sub-area in the growth cycle set of the area to be inspected. i is the number of several sub-areas, i = 1, 2,..., n, and n is an integer greater than 2.

[0033] It should be noted that the collection of demand corn characteristic data corresponding to each growth cycle stored in the data warehouse is specifically sourced as follows: For example, experts, relying on their profound professional knowledge in multiple fields such as agronomy, plant physiology, and agricultural meteorology, as well as their long-term observation and research experience of the corn growth process, can understand the physiological characteristics, morphological changes, and environmental response laws of corn at different growth stages. For instance, based on the photosynthesis mechanism and pigment change law of corn, experts can determine the reasonable range of relevant indicators of NDVI (Normalized Difference Vegetation Index) in different growth cycles. Another example is to deploy various sensors in the corn planting area, such as spectral sensors, temperature sensors, humidity sensors, pressure sensors, etc., to obtain environmental information and the physiological information of the crop itself during the corn growth process in real time. By analyzing and processing a large amount of data collected by the sensors, characteristic data related to the corn growth cycle is extracted. For example, by using a spectral sensor to obtain the reflectance spectral data of the corn canopy, indicators such as the NDVI value and near-infrared reflectance at different growth stages are obtained through calculation and analysis, and the corresponding interval range is determined according to the data change trend.

[0034] In a specific embodiment of the present invention, the method for specifically constructing the collection of corn characteristic data for several sub-regions within the target cycle in the to-be-inspected area is as follows: Extract the REP-Dλred time-series dataset and NDVI time-series dataset for several sub-regions within the target cycle from the remote sensing monitoring data of the to-be-inspected area, and obtain the average ratio of Dλred-NDVI for several sub-regions within the target cycle in the to-be-inspected area through data processing.

[0035] Specifically, divide several Dλred in the REP-Dλred time-series dataset by NDVI to obtain the ratio of several Dλred to NDVI, form the Dλred-NDVI dataset, and obtain the average ratio of Dλred-NDVI for several sub-regions within the target cycle in the to-be-inspected area through mean processing.

[0036] Obtain the leaf curling morphological characteristic values and ear spectral dataset for several sub-regions within the target cycle from the remote sensing monitoring data of the to-be-inspected area, and obtain the decreasing rate of near-infrared reflectance from the ear spectral dataset.

[0037] Obtain the NDVI time-series dataset, REP-Dλred time-series dataset, and CWSI time-series dataset for several sub-regions within the target cycle from the remote sensing monitoring data of the to-be-inspected area, and obtain the post-peak decreasing rate of NDVI, REP blue shift interval, Dλred change interval, and CWSI change interval for several sub-regions within the target cycle in the to-be-inspected area.

[0038] Obtain several data in the canopy structure characteristics for several sub-regions within the target cycle from the remote sensing monitoring data of the to-be-inspected area.

[0039] Summarize the above data and construct a set of corn feature data for several sub - regions in the area to be inspected within the target period.

[0040] The set of predicted maturity time points for the area to be inspected. The specific prediction method is as follows: Based on the set of growth cycles of the area to be inspected, extract the growth cycles of several sub - regions in the area to be inspected, and obtain the mature growth cycle from the data warehouse, so as to obtain the mature duration of several sub - regions in the area to be inspected. Combine with the current time point to obtain the mature time points of several sub - regions in the area to be inspected, and construct a set of mature time points for the area to be inspected.

[0041] It should be noted that the set of predicted maturity time points for the area to be inspected is specifically for facilitating the subsequent adjustment of the monitoring frequency of several sub - regions in the area to be inspected. For example, if the time interval between the maturity time point of a certain sub - region and the current time point is too long, the monitoring frequency of this sub - region in the area to be inspected can be reduced in the future; if the time interval is medium, the monitoring frequency of this sub - region in the area to be inspected can be maintained; if the time interval is too short, the monitoring frequency of this sub - region in the area to be inspected can be increased. While meeting the monitoring requirements, it also saves monitoring resources.

[0042] S3. According to the set of growth cycles of the area to be inspected, screen out the mature sub - regions of the area to be inspected, and conduct data collection on each mature sub - region of the area to be inspected again to obtain an updated data set of the area to be inspected.

[0043] It should be noted that the specific screening method for screening out the mature sub - regions of the area to be inspected is as follows: Based on the set of growth cycles of the area to be inspected, that is, the growth cycles of several sub - regions, and record the several sub - regions with the growth cycle in the mature stage as mature sub - regions to obtain each mature sub - region of the area to be inspected.

[0044] In a specific embodiment of the present invention, the specific data collection method for conducting data collection on each mature sub - region of the area to be inspected again is as follows: Obtain the center points of each mature sub - region of the area to be inspected, fit to obtain a secondary collection path for the area to be inspected, and dispatch drones to conduct data collection according to the secondary collection path. At the same time, conduct data collection again through the fixed sensors of each mature sub - region of the area to be inspected.

[0045] The fixed sensors include soil organic matter sensors, soil pH value sensors, soil total nitrogen sensors, resistive soil compactness sensors, etc.

[0046] In a specific embodiment of the present invention, the updated dataset includes the planting density of each mature sub-region, the average height of corn plants, the characteristic values of various soil nutrient-related data, three-dimensional images, the average reference base area of straws, the characteristic values of various straw-related data, and soil compactness.

[0047] It should be noted that the unmanned aerial vehicle is equipped with a lidar sensor to perform three-dimensional scanning and modeling on each mature sub-region, so as to obtain the planting density, the average height of corn plants, three-dimensional images, the average reference base area of straws, and the characteristic values of various straw-related data. The characteristic values of various soil nutrient-related data and soil compactness are specifically collected by fixed sensors.

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

[0049] The characteristic values of various straw-related data include average moisture content, average cellulose content, average hemicellulose content, and average lignin content, etc., which are monitored by the unmanned aerial vehicle equipped with a multispectral camera.

[0050] The present invention integrates multi-source remote sensing data to determine the growth cycles of each sub-region within the area to be inspected, improves the accuracy of evaluating the growth cycles of each sub-region within the area to be inspected, provides strong data support for subsequent further monitoring of the area to be inspected, facilitates the dynamic combination of remote sensing far-layer technology and unmanned aerial vehicle near-layer technology, and improves the monitoring effect of the area to be inspected.

[0051] S4. According to the updated dataset of the area to be inspected, determine the reserved parameters of each mature sub-region of the area to be inspected, and use them as the harvesting parameters of the intelligent harvesting equipment for the area to be inspected.

[0052] In a specific embodiment of the present invention, the method for specifically determining the reserved parameters of each mature sub-region of the area to be inspected is as follows: Obtain the characteristic values of various soil-related data of each mature sub-region from the updated dataset of the area to be inspected, perform normalization processing on each of them, and then import them into the soil negative nutrition evaluation model where β _mp is the characteristic value of the p-th soil-related data of the m-th mature sub-region after normalization processing, is the required characteristic value of the p-th soil-related data of the m-th mature sub-region, m is the number of each mature sub-region, m = 1, 2,..., l, l is an integer greater than 2, p is the number of each soil-related data, p = 1, 2,..., q, q is an integer greater than 2, and output the soil negative nutrition indicators of each mature sub-region of the area to be inspected.

[0053] The characteristic values ​​of each straw-related data of each mature sub-region are obtained from the updated data set of the area to be inspected, imported into the straw quality assessment model, and the straw quality index of each mature sub-region of the area to be inspected is output.

[0054] It should be added that the characteristic values ​​of the soil-related data are homogenized, specifically by extracting the upper and lower limits of several soil-related data from the database, so as to homogenize each soil-related data.

[0055] The soil negative nutrition index and straw quality index of each mature sub-area in the area to be inspected are introduced into the required straw volume model to obtain the required straw volume A of each mature sub-area in the area to be inspected. _m .

[0056] The soil compactness of each mature sub-area in the area to be inspected is compared with the suitable harvesting height intervals corresponding to each soil compactness interval stored in the data warehouse, and the suitable harvesting height intervals of each mature sub-area in the area to be inspected are screened.

[0057] It should be noted that the suitable harvesting height ranges corresponding to the soil compaction ranges are specifically set by corn harvesting experts. As the soil compaction increases, the suitable harvesting height decreases, thereby reducing the risk of blades of the intelligent harvesting equipment being suspended in the air and protecting the machinery. As the soil compaction decreases, the suitable harvesting height increases, thereby preventing the intelligent harvesting equipment from getting stuck and ensuring cutting continuity.

[0058] If TY _m > 0, then based on the three-dimensional image in the updated data set of the area to be inspected, a number of lodging areas of each mature sub-area of ​​the area to be inspected are identified, and the number of lodging areas of each mature sub-area of ​​the area to be inspected R is summarized. _m , if R _m = 0, then based on the area S occupied by each mature sub-area of ​​the area to be inspected _m , planting density ρ _m , Average height of corn plants G _m , average reference base area of ​​straw _m , predict the straw volume A of each mature sub-area in the inspection area _ ' m =(ρ _m *S _m )*s _m *G _m , if A _m ≥A _ ' m , then the upper limit of the suitable harvesting height range of the mature sub-area is used as the reserved height. If A _m <A _ ' m, then calculate the initial reserved height of the mature sub-region Import it into the initial reserved height correction model Output the reserved height GI of the mature sub-region _m , and record the reserved method of the mature sub-region as full reservation, forming the reserved parameters of the mature sub-region.

[0059] Specifically, the above planting density is specifically the number of plants per unit area.

[0060] If R _m > 0, then obtain the areas of several lodging areas of the mature sub-region of the area to be inspected, and accumulate to obtain the total lodging area of the mature sub-region Obtain the straw volume of the mature sub-region through processing Predict the straw volume of the mature sub-region. If A _m ≥B _ ′ m , then use the upper limit value of the suitable harvesting height range of the mature sub-region as the reserved height. If A _m <B _ ′ m , then calculate the initial reserved height of the mature sub-region And through the initial reserved height correction model, obtain the reserved height of the mature sub-region. Record the reserved method of the mature sub-region as partial reservation, and record the remaining area excluding several lodging areas as the partial reservation area, obtaining the reserved height, reserved method and partial reservation area of the mature sub-region, forming the reserved parameters of the mature sub-region.

[0061] Obtain the reserved parameters of each mature sub-region of the area to be inspected according to the above processing method.

[0062] In a specific embodiment of the present invention, the straw quality evaluation model is specifically:

[0063]

[0064] Where is the eigenvalue of the jth straw-related data of the mth mature sub-region, is the eigenvalue interval of the jth straw-related data of the mth mature sub-region stored in the data warehouse. j is the number of each straw-related data, j = 1, 2,..., k, and k is an integer greater than 2.

[0065] In a specific embodiment of the present invention, the required straw volume model is specifically A _m =(TY _m -TY′)*λ _m .

[0066] Where λ_m TY′ is the benchmark soil negative nutrient index in the data warehouse, and it is the required straw volume corresponding to the increase in the unit soil negative nutrient index of the m-th mature sub-region obtained from the data warehouse.

[0067] The method for specifically obtaining the required straw volume corresponding to the increase in the unit soil negative nutrient index of each mature sub-region is as follows: If JY _m ∈γ _m , then obtain the required straw volume λ corresponding to the increase in the unit soil negative nutrient index of this mature sub-region at this straw quality level from the data warehouse _m , and γ _m is the straw quality index range corresponding to the m-th straw quality level in the data warehouse.

[0068] Based on the soil nutrient situation, straw quality situation, and soil compactness, the present invention determines the harvesting parameters of the mature sub-regions of the area to be inspected, balances the relationship between the remaining amount of corn straw to meet the soil nutrient requirements and the harvesting height to meet the soil compactness requirements, improves the matching degree of the remaining amount of corn straw and the soil nutrient requirements, and reduces the damage rate of intelligent harvesting equipment.

[0069] S5. Transmit the harvesting parameters of the intelligent harvesting equipment to the harvesting platform management center of the intelligent harvesting equipment.

[0070] Refer to Figure 2 As shown, the second aspect of the present invention provides a system for implementing the agricultural resource and environment monitoring method for fusing multi-source remote sensing data of the present invention, including: a remote sensing monitoring data module for collecting the area to be inspected using remote sensing technology to obtain the remote sensing monitoring data of the area to be inspected.

[0071] A growth cycle determination module for using the remote sensing monitoring data of the area to be inspected to determine the growth cycle set of the area to be inspected and predict the set of mature time points of the area to be inspected.

[0072] A re-collection module for screening the mature sub-regions of the area to be inspected according to the growth cycle set of the area to be inspected and re-collecting data for each mature sub-region of the area to be inspected to obtain an updated data set of the area to be inspected.

[0073] A harvesting parameter determination module for determining the reserved parameters of each mature sub-region of the area to be inspected according to the updated data set of the area to be inspected and using them as the harvesting parameters of the intelligent harvesting equipment for the area to be inspected.

[0074] A processing terminal: for transmitting the harvesting parameters of the intelligent harvesting equipment to the harvesting platform management center of the intelligent harvesting equipment.

[0075] It should be noted that the present invention further includes a data warehouse. The remote sensing monitoring data module is connected to the growth cycle determination module, the growth cycle determination module is connected to the re-acquisition module, the re-acquisition module is connected to the harvesting parameter determination module, the harvesting parameter determination module is connected to the processing terminal, and the data warehouse is respectively connected to the growth cycle determination module and the harvesting parameter determination module.

[0076] The above content is only an example and illustration of the concept of the present invention. Those skilled in the art of this technology can make various modifications, supplements, or use similar methods to replace the specific embodiments described, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all fall within the protection scope of the present invention.

Claims

1. An agricultural resource and environment monitoring method integrating multi-source remote sensing data, characterized in that, Including: S1. Use remote sensing technology to collect the area to be inspected, and obtain the remote sensing monitoring data of the area to be inspected; S2. Use the remote sensing monitoring data of the area to be inspected to determine the growth cycle set of the area to be inspected, and predict the set of maturity time points of the area to be inspected; S3. According to the growth cycle set of the area to be inspected, screen each mature sub-area of the area to be inspected, and collect data again for each mature sub-area of the area to be inspected to obtain the updated data set of the area to be inspected; S4. According to the updated data set of the area to be inspected, determine the reserved parameters of each mature sub-area of the area to be inspected, and use them as the harvesting parameters of the intelligent harvesting equipment for the area to be inspected; S5. Transmit the harvesting parameters of the intelligent harvesting equipment to the harvesting platform management center of the intelligent harvesting equipment.

2. The agricultural resource and environment monitoring method for fusing multi-source remote sensing data according to claim 1, wherein, The remote sensing monitoring data includes the canopy structure characteristics, leaf curling morphological characteristic values, ear spectral data sets, NDVI time series data sets, REP-Dλred time series data sets, and CWSI time series data sets of several sub-areas within the target period. The canopy structure characteristics include ear length, ear diameter, and bract chromaticity values. The leaf curling morphological characteristic value is a numerical value of 0 or 1. When the leaf curling morphological characteristic value is 1, it indicates that the leaf has a curling morphology.

3. The agricultural resource and environment monitoring method for fusing multi-source remote sensing data according to claim 2, wherein, The specific determination method for determining the growth cycle set of the area to be inspected is as follows: Based on the remote sensing monitoring data of the area to be inspected, a set of corn characteristic data for several sub-areas of the area to be inspected within the target period is constructed, and it is compared with the set of required corn characteristic data corresponding to each growth period stored in the data warehouse to screen the growth periods of several sub-areas of the area to be inspected within the target period, and a set of growth periods E=(α _1 ,α _2 ,α _3 ,...,α _i ,...,α _n ) of the area to be inspected is constructed, where α _1 , α _2 , α _3 , α _i , α _n 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 set of growth periods of the area to be inspected. i is the number of several sub-areas, i = 1, 2,..., n, and n is an integer greater than 2.

4. The agricultural resource and environment monitoring method for fusing multi-source remote sensing data according to claim 3, wherein The specific construction method for constructing the corn characteristic data set of several sub-areas in the area to be inspected within the target period is as follows: Extract the REP-Dλred time series data set and NDVI time series data set of several sub-areas within the target period from the remote sensing monitoring data of the area to be inspected, and obtain the average ratio of Dλred-NDVI of several sub-areas in the area to be inspected within the target period through data processing; Obtain the leaf curling morphological characteristic values and ear spectral data sets of several sub-areas within the target period from the remote sensing monitoring data of the area to be inspected, and obtain the decline rate of the near-infrared reflectance from the ear spectral data set; Obtain the NDVI time series data set, REP-Dλred time series data set, and CWSI time series data set of several sub-areas within the target period from the remote sensing monitoring data of the area to be inspected, and obtain the decline rate after the NDVI peak, REP blue shift interval, Dλred change interval, and CWSI change interval of several sub-areas in the area to be inspected within the target period; Obtain several data in the canopy structure characteristics of several sub-areas within the target period from the remote sensing monitoring data of the area to be inspected; Summarize the above data to construct the corn characteristic data set of several sub-areas in the area to be inspected within the target period.

5. The agricultural resource and environment monitoring method for fusing multi-source remote sensing data according to claim 1, wherein The specific data collection method for collecting data again for each mature sub-area of the area to be inspected is as follows: Obtain the center points of each mature sub-area of the area to be inspected, fit to obtain the secondary collection path of the area to be inspected, and dispatch drones to collect data according to the secondary collection path. At the same time, collect data again through the fixed sensors of each mature sub-area of the area to be inspected.

6. The agricultural resource and environment monitoring method for fusing multi-source remote sensing data according to claim 5, characterized in that, The updated dataset includes the planting density of each mature sub-region, the average height of corn plants, the eigenvalue of each soil nutrient-related data, 3D images, the average reference base area of straws, the eigenvalue of each straw-related data, and soil compactness.

7. The agricultural resource and environment monitoring method for fusing multi-source remote sensing data according to claim 6, wherein The method for determining the reserved parameters of each mature sub-region of the area to be inspected is as follows: Obtain the eigenvalues of the soil-related data of each mature sub-region from the updated dataset of the area to be inspected, perform normalization processing on each of them respectively, and then import them into the soil negative nutrition assessment model where β _mp is the eigenvalue of the p-th soil-related data of the m-th mature sub-region after normalization processing, is the demand eigenvalue of the p-th soil-related data of the m-th mature sub-region, m is the number of each mature sub-region, m = 1, 2,..., l, l is an integer greater than 2, p is the number of each soil-related data, p = 1, 2,..., q, q is an integer greater than 2, and output the soil negative nutrition indicators of each mature sub-region of the area to be inspected; Obtain the eigenvalues of each straw-related data of each mature sub-region from the updated dataset of the area to be inspected, import them into the straw quality assessment model, and output the straw quality indicators of each mature sub-region of the area to be inspected; Import the soil negative nutrient index and straw quality index of each mature sub-region in the area to be inspected into the demand straw volume model to obtain the demand straw volume A of each mature sub-region in the area to be inspected _m ; Screen the appropriate harvesting height intervals for each mature sub-region of the area to be inspected based on the soil compactness of each mature sub-region of the area to be inspected and the appropriate harvesting height intervals corresponding to each soil compactness interval stored in the data warehouse. If TY _m > 0, then based on the three-dimensional image in the updated dataset of the area to be inspected, identify several lodging areas in each mature sub-area of the area to be inspected, and summarize the number R of lodging areas in each mature sub-area of the area to be inspected _m , if R _m = 0, then predict the straw volume A _ ′ m of each mature sub-area of the area to be inspected. If A _m ≥A _ ′ m , then use the upper limit value of the suitable harvesting height interval of this mature sub-area as the reserved height. If A _m <A _ ′ m , then calculate the initial reserved height G _ ′ m of this mature sub-area, import it into the initial reserved height correction model , output the reserved height GI _m of this mature sub-area, and record the reserved method of this mature sub-area as full reservation to form the reserved parameters of this mature sub-area; If R _m > 0, then obtain the areas of a number of lodging areas in this mature sub-region of the area to be inspected, and through similar processing, obtain the reserved parameters of this mature sub-region; Obtain the reserved parameters of each mature sub-region of the area to be inspected according to the above processing method.

8. The agricultural resource and environment monitoring method for fusing multi-source remote sensing data according to claim 7, wherein The straw quality assessment model is specifically as follows: where is the eigenvalue of the j-th straw-related data in the m-th mature sub-region, is the eigenvalue interval of the j-th straw-related data in the m-th mature sub-region stored in the data warehouse, j is the number of each straw-related data, j = 1, 2,..., k, and k is an integer greater than 2.

9. A method for monitoring agricultural resources and environment by fusing multi-source remote sensing data according to claim 7, characterized in that, The described straw volume model is specifically A _m =(TY _m -TY′)*λ _m ; where λ _m is the required straw volume corresponding to the increase in the unit soil negative nutrition index of the m-th mature sub-region obtained from the data warehouse, and TY′ is the benchmark soil negative nutrition index in the data warehouse; For the required straw volume corresponding to the increase in the unit soil negative nutrition index of each mature sub-region, the specific acquisition method is as follows: If JY _m ∈γ _m , then obtain the required straw volume λ _m corresponding to the increase in the unit soil negative nutrition index of this mature sub-region at this straw quality level from the data warehouse, where γ _m is the straw quality index range corresponding to the m-th straw quality level in the data warehouse.

10. A system for implementing the agricultural resource and environment monitoring method for fusing multi-source remote sensing data according to any one of claims 1-9, characterized in that, It includes: A remote sensing monitoring data module, which is used to collect the area to be inspected by using remote sensing technology to obtain the remote sensing monitoring data of the area to be inspected; A growth cycle determination module, which is used to use the remote sensing monitoring data of the area to be inspected to determine the growth cycle set of the area to be inspected and predict the set of mature time points of the area to be inspected; A re-collection module, which is used to screen each mature sub-region of the area to be inspected according to the growth cycle set of the area to be inspected, and re-collect data for each mature sub-region of the area to be inspected to obtain the updated dataset of the area to be inspected; A harvesting parameter determination module, which is used to determine the reserved parameters of each mature sub-region of the area to be inspected according to the updated dataset of the area to be inspected, and use them as the harvesting parameters of the intelligent harvesting equipment in the area to be inspected; A processing terminal: used to transmit the harvesting parameters of the intelligent harvesting equipment to the harvesting platform management center of the intelligent harvesting equipment.

Images