Method and device for estimating straw yield at field site

Abstract

This invention provides a method and apparatus for estimating field straw yield. The method includes: acquiring target data; acquiring the target crop yield at a target time within a target area based on the target data; and acquiring the corresponding field straw yield at the target time within the target area based on the target crop yield. The target data includes the target vegetation index of a target remote sensing image and meteorological and topographic data of the target area at the target time. The target remote sensing image is a remote sensing image of the original area at the target time. The target area is an area within the original area where the target crop is planted. The target time is the period from when the target crop is planted in the target area until the target crop is harvested. The method and apparatus for estimating field straw yield provided by this invention can combine the influence of regional meteorological and topographic factors on field straw yield, thereby improving the accuracy of field straw yield estimation.

Description

Technical Field

[0001] This invention relates to the field of remote sensing technology, and in particular to a method and apparatus for estimating field straw yield. Background Technology

[0002] Straw is a general term for the stems and leaves (ears) of mature crops, typically referring to the residue remaining after the grains of wheat, rice, corn, potatoes, rapeseed, cotton, sugarcane, and other crops (usually coarse grains) are harvested. Straw in the field can be recycled as fertilizer, or it can be chopped and returned to the field to increase soil fertility. Returning straw to the field also helps with carbon sequestration. Therefore, estimating the yield of straw in the field is of great significance.

[0003] In existing technologies, the yield of field straw is typically estimated based on the planting area of ​​the current season's crop and historical yield data of field straw, relying on experience. These traditional methods for estimating field straw yield are easily affected by experience levels, the amount of historical yield data, and other uncontrollable factors, resulting in low accuracy in estimating field straw yield. Therefore, how to more accurately estimate field straw yield is a pressing technical problem that needs to be solved in this field. Summary of the Invention

[0004] This invention provides a method and apparatus for estimating field straw yield, which solves the problem of low accuracy in estimating field straw yield in the prior art, and achieves a more accurate estimation of field straw yield.

[0005] This invention provides a method for estimating field straw yield, comprising:

[0006] Obtain the target data;

[0007] Based on the target data, obtain the target crop yield at the target time within the target area;

[0008] Based on the target crop yield, obtain the site straw yield at the target time within the target area;

[0009] The target data includes the target vegetation index of the target remote sensing image and the meteorological and topographic data of the target area at the target time; the target remote sensing image is the remote sensing image of the original area at the target time; the target area is the area in the original area where the target crop is planted; the target time is the period from when the target crop is planted in the target area to when the target crop is harvested.

[0010] According to the present invention, a method for estimating field straw yield includes obtaining the target crop yield at a target time within a target area based on the target data, comprising:

[0011] The target data is input into the crop yield estimation model to obtain the target crop yield output by the crop yield estimation model;

[0012] The crop yield estimation model is constructed based on a hierarchical linear model. The model parameters of the crop yield estimation model are obtained by inverting the sample crop yield and sample data corresponding to the sample time in the sample area. The sample data includes the target vegetation index of the sample remote sensing image and the meteorological and topographic data of the original sample area at the sample time. The sample area is the area in the original sample area where the sample crop is planted. The sample remote sensing image is the remote sensing image of the original sample area at the sample time. The sample time is the period from when the sample crop is planted in the sample area to when the sample crop is harvested. The sample crop is the same type as the target crop.

[0013] According to the present invention, a method for estimating field straw yield is provided, wherein the crop yield estimation model includes: a first crop yield estimation sub-model and a second crop yield estimation sub-model; the second crop yield estimation sub-model is nested within the first crop yield estimation sub-model.

[0014] Accordingly, the step of inputting the target data into the crop yield estimation model and obtaining the target crop yield output by the crop yield estimation model includes:

[0015] The meteorological and topographic data of the target area at the target time are input into the second crop yield estimation sub-model to obtain the target parameters output by the second crop yield estimation sub-model;

[0016] The target vegetation index and the target parameters of the target remote sensing image are input into the first crop yield estimation sub-model to obtain the target crop yield output by the first crop yield estimation sub-model.

[0017] According to the present invention, a method for estimating field straw yield is provided, wherein the target area is obtained based on the following method:

[0018] Input the target vegetation index of the target remote sensing image into the crop monitoring model to obtain the target area output by the crop monitoring model;

[0019] The crop monitoring model is constructed based on the random forest algorithm and trained based on the target vegetation index of the sample remote sensing image and the sample area.

[0020] According to the present invention, a field straw yield estimation method is provided, wherein the target plant index includes the normalized vegetation index; the target vegetation index is determined based on the correlation between the vegetation index and crop yield.

[0021] According to the present invention, a method for estimating field straw yield, when there are multiple original regions, after obtaining the field straw yield corresponding to the target time within the target region based on the target crop yield, the method further includes:

[0022] Based on the site straw yield, a site straw yield distribution map is generated.

[0023] According to the present invention, a method for estimating field straw yield, when there are multiple target times, after obtaining the field straw yield corresponding to the target time within the target area based on the target crop yield, the method further includes:

[0024] Based on the site straw yield, a time-series distribution map of site straw yield is generated.

[0025] The present invention also provides a field straw yield estimation device, comprising:

[0026] The target data acquisition module is used to acquire target data.

[0027] The crop yield inversion module is used to obtain the target crop yield at a target time within a target area based on the target data.

[0028] The straw yield estimation module is used to obtain the site straw yield at the target time within the target area based on the target crop yield.

[0029] The target data includes the target vegetation index of the target remote sensing image and the meteorological and topographic data of the target area at the target time; the target remote sensing image is the remote sensing image of the original area at the target time; the target area is the area in the original area where the target crop is planted; the target time is the period from when the target crop is planted in the target area to when the target crop is harvested.

[0030] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the field straw yield estimation method as described above.

[0031] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the field straw yield estimation method as described above.

[0032] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the field straw yield estimation method as described above.

[0033] The present invention provides a method and apparatus for estimating field straw yield. Based on target data, it obtains the target crop yield at a target time within a target area, and then, based on the target crop yield at that time, obtains the corresponding field straw yield within the target area. The target data includes the target vegetation index from a target remote sensing image, as well as meteorological and topographic data of the target area at the target time. The target remote sensing image is the original remote sensing image of the area at the target time, and the target area is the area within the original area where the target crop is planted. The target time is the period from when the target crop is planted in the target area until the target crop is harvested. By combining the influence of regional meteorological and topographic factors on field straw yield, the accuracy of estimating field straw yield can be improved. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0035] Figure 1 This is one of the flowcharts illustrating the field straw yield estimation method provided by the present invention;

[0036] Figure 2 This is the second flowchart of the field straw yield estimation method provided by the present invention;

[0037] Figure 3 This is a schematic diagram of the field straw yield estimation device provided by the present invention;

[0038] Figure 4 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0040] In the description of the invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0041] It should be noted that corn, as an important crop, has advantages such as wide planting range and high yield. The standing corn stalks after harvest can be recycled as fertilizer, or chopped and returned to the field to increase soil fertility. Returning stalks to the field also plays a role in carbon sequestration, and the rate of stalk return is related to the carbon balance of the agricultural system. Therefore, estimating the yield of standing corn stalks can provide data support for stalk recycling, subsequent composting, and the diversified utilization of stalk resources.

[0042] Traditional methods for estimating field straw yield typically rely on the planted area of ​​the current crop and historical straw yield data, depending on experience. These traditional methods are susceptible to the influence of experience level, the amount of historical yield data, and other uncontrollable factors, resulting in low accuracy in estimating field straw yield. However, with the rapid development of remote sensing technology, remote sensing imagery, due to its high image clarity, rich objective information, timeliness, and strong practicality, is widely used in environmental protection, land resource surveys, disaster monitoring, and other fields.

[0043] To address this issue, the present invention provides a method and apparatus for estimating field straw yield. The method provided by the present invention can comprehensively invert corn yield based on remote sensing data, meteorological data, and topographic data. Furthermore, it can estimate field straw yield based on the correlation between field straw yield and corn yield, taking into account the influence of regional meteorological and topographic factors on field straw yield, thereby improving the accuracy of field straw yield estimation.

[0044] Figure 1 This is one of the flowcharts illustrating the field straw yield estimation method provided by this invention. The following is a combination of... Figure 1 This invention describes a method for estimating field straw yield. For example... Figure 1 As shown, the method includes: step 101, obtaining target data.

[0045] The target data includes the target vegetation index of the target remote sensing image, as well as the meteorological and topographic data of the target area at the target time; the target remote sensing image is the remote sensing image of the original area at the target time; the target area is the area in the original area where the target crop is planted; the target time is the period from when the target crop is planted in the target area to when the target crop is harvested.

[0046] It should be noted that the implementing entity of this embodiment of the invention is a field-based straw monitoring device.

[0047] It should be noted that the field straw in this embodiment of the invention refers to the remaining part of mature crops after grain harvest. These crops may include, but are not limited to, wheat, rice, corn, potatoes, rapeseed, cotton, and sugarcane. The specific type of field straw in this embodiment of the invention is not limited. The following example uses the remaining part of mature corn after grain harvest to illustrate the field straw yield estimation method provided by this invention, where both the target crop and the sample crop are corn.

[0048] In this embodiment of the invention, the GEE (Google Earth Engine) platform can be used to acquire remote sensing images of the original target area at a given time, which can then be used as target remote sensing images.

[0049] It should be noted that, in this embodiment of the invention, the area in the original region where corn is planted can be used as the target area. The target area can be obtained in advance or based on remote sensing imagery of the target area. This embodiment of the invention does not specifically limit the method of obtaining the target area.

[0050] It is understandable that the straw yield at the target time within the target area is the same as the straw yield at the target time within the original area.

[0051] The GEE platform is a remote sensing cloud computing platform that integrates massive amounts of geospatial data, imagery data, meteorological and weather data, and geophysical data. It possesses corresponding visualization and analytical computing capabilities, as well as a standard set of Application Program Interfaces (APIs) for exchanging information and commands with computer operating systems. Imagery data includes Landsat series, Sentinel series, MODIS, and high-resolution imagery of local areas; weather and meteorological data includes surface variables such as surface temperature and emissivity, long-term climate predictions and historical differences, atmospheric data retrieved from satellite observations, and short-term forecasts and observations of weather data; geophysical data includes topographic data, land cover data, farmland distribution data, and nighttime light data.

[0052] It should be noted that the target timeframe is the period from when the corn is planted in the target area until the corn is harvested. For example, the target timeframe could be between April and October of the same year.

[0053] In this embodiment of the invention, any time within the period from when the corn is planted in the target area to when the corn is harvested can be defined as the target time; alternatively, a specific time within the period from when the corn is planted in the target area to when the corn is harvested can be defined as the target time based on actual conditions and / or prior knowledge. This embodiment of the invention does not impose a specific limitation on the target time.

[0054] It should be noted that there can be one or more target times.

[0055] Optionally, since the corn growing season (July-September) is a cloudy and rainy season, cloud cover is very likely to occur, making it impossible to use optical images during some important periods. SAR images have the characteristics of strong penetration and are not affected by clouds, which can make up for the defects of optical images. Therefore, the target remote sensing image in the embodiments of the present invention can be a combination of Sentinel-2 optical images and Sentinel-1 SAR images. The cloud cover problem can be solved by combining optical and SAR images, making up for the defects of optical images, and thus avoiding affecting the accuracy of field straw yield estimation.

[0056] It should be noted that the Sentinel-2 optical images are L2A level data, which have already undergone radiometric and geometric corrections, and do not require further correction. After acquiring the Sentinel-2 optical images, they can be used directly after appropriate mosaicking and cropping as needed.

[0057] After acquiring the remote sensing image of the target, the target vegetation index can be obtained through numerical calculation and / or mathematical statistics.

[0058] Based on the above embodiments, the target plant index includes the normalized vegetation index; the target vegetation index is determined based on the correlation between the vegetation index and crop yield.

[0059] Optionally, in this embodiment of the invention, the Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Difference Vegetation Index (DVI), Green Chlorophyll Index (CIgreen), Structure-Insensitive Pigment Index (SIPI), Normalized Difference Water Index (NDWI), and Normalized Area Vegetation Index (NAVI) of the target remote sensing image can also be obtained by numerical calculation as the original vegetation index of the target remote sensing image.

[0060] The Normalized Difference Vegetation Index (NDVI) can be calculated based on the following formula:

[0061]

[0062] The Enhanced Vegetation Index (EVI) can be calculated based on the following formula:

[0063]

[0064] The Difference Vegetation Index (DVI) can be calculated based on the following formula:

[0065] DVI = ρ nir -ρ r (3)

[0066] The Ratio Vegetation Index (RVI) can be calculated based on the following formula:

[0067]

[0068] The green chlorophyll index CIgreen can be calculated based on the following formula:

[0069]

[0070] NAVI can be calculated based on the following formula:

[0071]

[0072] The structure-insensitive pigment index (SIPI) can be calculated based on the following formula:

[0073]

[0074] The Normalized Difference Water Index (NDWI) can be calculated based on the following formula:

[0075]

[0076] Where, ρ r ρ represents the red band reflectance of remotely sensed images. b ρ represents the blue band reflectance of remotely sensed images. g ρ represents the green band reflectance of remotely sensed images. nir This indicates the reflectance of the near-infrared band in remote sensing images.

[0077] To avoid feature redundancy and improve image classification efficiency, after obtaining the original vegetation index of the target remote sensing image, the original vegetation index of the target remote sensing image can be used as an independent variable to analyze the correlation between the original vegetation index and maize yield. The Normalized Difference Vegetation Index (NDVI) with the highest correlation to maize yield among the original vegetation indices is then determined as the target vegetation index.

[0078] In this embodiment of the invention, meteorological data of the target area at the target time can be obtained in a variety of ways. For example, meteorological data of the target area at the target time can be obtained through data query.

[0079] Optionally, the meteorological data mentioned above may include, but are not limited to, at least one of the following: daily minimum temperature (Tmin, °C), daily maximum temperature (Tmax, °C), sunshine duration (RAD), and rainfall (PRE, mm).

[0080] In this embodiment of the invention, terrain data of the target area at the target time can be obtained in a variety of ways. For example, terrain data of the target area at the target time can be obtained through data query.

[0081] Optionally, the aforementioned topographic data may include, but is not limited to, elevation (E), slope (S), and aspect (A).

[0082] Step 102: Based on the target data, obtain the target crop yield at the target time within the target area.

[0083] Specifically, after obtaining the target data, the corn yield at the target time within the target area can be obtained through numerical calculation.

[0084] Step 103: Based on the target crop yield, obtain the on-site straw yield corresponding to the target time within the target area.

[0085] Specifically, after obtaining the corn yield at the target time within the target area, the corn stalk yield at the target time within the target area can be obtained through numerical calculation.

[0086] It should be noted that the calculation of the dry weight of corn stalks is divided into two parts: the above-ground part and the root part. The dry weight of the above-ground part of the corn stalk can be calculated based on the following formula:

[0087] Ps = AMP × MSI (9)

[0088] Where Ps represents the dry weight of the aboveground part of the corn stalk; AMP represents the average annual corn yield; and MSI represents the corn stalk index.

[0089] The corn stalk index (MSI) can be calculated using the following formula:

[0090]

[0091] HI represents the harvest index.

[0092] The Harvest Index (HI) can be calculated using the following formula:

[0093]

[0094] Grain dry weight refers to the dry weight of the corn; Aboveground dry matter refers to the weight of the corn.

[0095] The dry weight of the root portion of corn stalks can be calculated using the following formula:

[0096]

[0097] Wherein, Pr represents the dry weight of the aboveground part of the corn stalk; R / S represents the root-to-shoot ratio at the corn maturity stage.

[0098] The dry weight of corn stalks can be calculated using the following formula:

[0099] P = P s +P r (13)

[0100] Taking the northern corn-growing area as an example, HI = 0.52, MSI = 0.98, R / S = 0.063, then the calculation formula for northern corn stalks is P = AMP × 0.98 + (AMP / 0.52) × 0.063.

[0101] This invention, through its embodiments, obtains the target crop yield at a target time within a target area based on target data. Then, based on the target crop yield at the target time within the target area, it obtains the corresponding site straw yield at the target time within the target area. The target data includes the target vegetation index of the target remote sensing image, as well as the meteorological and topographic data of the target area at the target time. The target remote sensing image is the remote sensing image of the original area at the target time, and the target area is the area within the original area where the target crop is planted. The target time is the period from when the target crop is planted in the target area until the target crop is harvested and the seeds are filled. By combining the influence of regional meteorological and topographic factors on site straw yield, the accuracy of field site straw yield estimation can be improved.

[0102] Based on the above embodiments, obtaining the target crop yield at a target time within a target area based on target data includes: inputting the target data into a crop yield estimation model and obtaining the target crop yield output by the crop yield estimation model.

[0103] The crop yield estimation model is constructed based on a hierarchical linear model. The model parameters of the crop yield estimation model are obtained by inverting the sample crop yield and sample data corresponding to the sample time in the sample area. The sample data includes the target vegetation index of the sample remote sensing image and the meteorological and topographic data of the original sample area at the sample time. The sample area is the area in the original sample area where the sample crop is planted. The sample remote sensing image is the remote sensing image of the original sample area at the sample time. The sample time is within the period from when the sample crop is planted in the sample area to when the sample crop is harvested. The sample crop is the same as the target crop.

[0104] Specifically, the hierarchical linear model (HLM) is a type of multivariate statistical analysis. It is a least squares regression analysis model that takes into account the nested structure of the data. It can stratify the data based on the interaction of the data, so as to consider the variation of the data at the same level as a whole, as well as the variation of the data between different levels.

[0105] The embodiments of the present invention can construct a crop yield estimation model based on a hierarchical linear model, and can invert the model parameters of the crop yield estimation model based on the sample crop yield and sample data corresponding to the sample time in the original sample area.

[0106] Optionally, in this embodiment of the invention, HLM7.03 Student software can be used to construct the crop yield estimation model.

[0107] It should be noted that the method of obtaining sample data can be the same as the method of obtaining target data. The specific process of obtaining sample data can be found in the above embodiments, and will not be repeated in this embodiment.

[0108] Optionally, multiple sample times can be determined between July, August and September, and remote sensing images of the original sample area can be acquired at each sample time, along with VV and VH polarization characteristics of SAR images for periods when optical images are missing, to obtain sample remote sensing images.

[0109] After obtaining the target data, the target data can be input into the crop yield estimation model, and then the corn yield at the target time within the target area can be obtained from the output of the crop yield estimation model.

[0110] This invention provides an embodiment of the invention that inputs target data into a crop yield estimation model constructed based on a hierarchical linear model, and obtains the yield of the target crop within the target area output by the crop yield estimation model. It can comprehensively invert crop yield based on remote sensing data, meteorological data, and topographic data, thereby estimating crop yield more accurately and efficiently, and further improving the accuracy of field straw yield estimation.

[0111] Based on the above embodiments, the crop yield estimation model includes: a first crop yield estimation sub-model and a second crop yield estimation sub-model; the second crop yield estimation sub-model is nested within the first crop yield estimation sub-model.

[0112] Accordingly, the target data is input into the crop yield estimation model to obtain the target crop yield output by the crop yield estimation model, including: inputting the meteorological data and topographic data of the target area at the target time into the second crop yield estimation sub-model to obtain the target parameters output by the second crop yield estimation sub-model.

[0113] Specifically, the crop yield estimation sub-model in this embodiment of the invention includes a first crop yield estimation sub-model and a second crop yield estimation sub-model. The first crop yield estimation sub-model can invert the yield of maize based on vegetation indices; the second crop yield estimation sub-model can invert the model parameters (intercept and efficiency) in the first crop yield estimation sub-model based on meteorological and topographic data.

[0114] After inputting the meteorological and topographic data of the target area at the target time into the second crop yield estimation sub-model, the second crop yield estimation sub-model can obtain and output the target parameters through numerical calculation based on the meteorological data of the target area at the target time and the topographic data of the original area.

[0115] The specific calculation formula for the second crop yield estimation sub-model is as follows:

[0116] β0=γ 00 +γ 01 ×RAD+γ 02 ×T max +γ 03 ×T min+γ 04 ×PRE+γ 05 ×E+γ 06 ×S+γ 07 ×S+μ0 (14)

[0117] β1=γ 10 +γ 11 ×RAD+γ 12 ×T max +γ 13 ×T min +γ 14 ×PRE+γ 15 ×E+γ 16 ×S+γ 17 ×S+μ1 (15)

[0118] Where β0 and β1 both represent objective parameters, β0 represents the intercept of the first crop yield estimation sub-model, and β1 represents the slope of the first crop yield estimation sub-model; γ 00 To γ 10 γ represents the intercept of the second crop yield estimation sub-model; 11 -γ 17 μ0 and μ1 represent the slopes corresponding to the meteorological and topographic data of the target area at the target time in the second crop yield estimation sub-model; μ0 and μ1 represent the random errors of the second crop yield estimation sub-model.

[0119] It should be noted that γ 00 To γ 07 and γ 11 To γ 17 These are the parameters for the second crop yield estimation sub-model. Where γ... 00 This indicates the 0th parameter in Formula 14; the first "0" in the subscript can correspond to β0. 10 This indicates the 0th parameter in Formula 15, and the first "1" in the subscript can correspond to β1.

[0120] Input the target parameters and the target vegetation index of the target remote sensing image into the first crop yield estimation sub-model, and obtain the target crop yield output by the first crop yield estimation sub-model.

[0121] Specifically, after obtaining the target parameters, the target parameters and the target vegetation index of the target remote sensing image can be input into the first crop yield estimation sub-model. The first crop yield estimation sub-model can obtain and output the target crop yield of the target area at the target time based on the target parameters and the target vegetation index of the target remote sensing image. The specific calculation formula is as follows:

[0122] Yield=β0+β1×NDVI+e (16)

[0123] Where Yield represents the crop yield of the original area; NDVI represents the normalized vegetation index of the target remote sensing image.

[0124] The crop yield estimation sub-model in this embodiment of the invention includes a first crop yield estimation sub-model and a second crop yield estimation sub-model. The first crop yield estimation sub-model can invert the yield of maize based on the vegetation index; the second crop yield estimation sub-model can invert the model parameters in the first crop yield estimation sub-model based on meteorological data and topographic data, which can obtain the yield of the target crop in the target area more accurately and efficiently.

[0125] Based on the above embodiments, the target area is obtained in the following way: the target vegetation index of the target remote sensing image is input into the crop monitoring model to obtain the target area output by the crop monitoring model.

[0126] The crop monitoring model is built based on the random forest algorithm and trained using the target vegetation index and sample area from sample remote sensing images.

[0127] Optionally, in this embodiment of the invention, the number of sample remote sensing images is 700, of which 60% are used for training and 40% for validation.

[0128] After obtaining sample remote sensing images, the target vegetation index of each sample remote sensing image can be obtained through numerical calculation.

[0129] A field survey was conducted on the original sample area, and the location information of the cornfield was recorded using a portable GPS positioning device with an error within 5m. The collected point information can be imported into ArcGIS to determine the sample area corresponding to each sample remote sensing image.

[0130] The main land features in the original sample area can include five types: corn, grassland, villages and towns, roads (bare land), and water bodies.

[0131] Using the target vegetation index of each remote sensing image as a sample and the sample area corresponding to each remote sensing image as a sample label, a crop monitoring model based on the random forest algorithm can be trained, thereby obtaining a trained crop monitoring model.

[0132] After obtaining the trained crop monitoring model, the target vegetation index of the target remote sensing image can be input into the trained crop monitoring model, and then the target area output by the trained crop monitoring model can be obtained.

[0133] Optionally, in this embodiment of the invention, the estimation of corn yield within the target area can be achieved based on the BandMath and LayerStaking modules in the ENVI software.

[0134] This invention provides an embodiment of the invention that inputs the target vegetation index of the target remote sensing image into the crop monitoring model to obtain the target area output by the crop monitoring model, thereby obtaining the target area more accurately and efficiently.

[0135] Based on the above embodiments, when there are multiple original regions, after obtaining the site straw yield corresponding to the target time within the target region based on the target crop yield, the method further includes: generating a site straw yield distribution map based on the site straw yield.

[0136] Specifically, when there are multiple original regions, after obtaining the corn stalk yield corresponding to the target time in each target region, a local stalk yield distribution map can be generated based on the corn stalk yield corresponding to the target time in each target region. This map is used to describe the distribution of corn stalk yield corresponding to the target time in each target region.

[0137] Optionally, in this embodiment of the invention, a local straw yield distribution map can be generated based on ArcGIS, wherein ArcGIS can provide users with a scalable and comprehensive GIS platform.

[0138] Optionally, the corn stalk yield distribution map can use the shade of color to represent the corn stalk yield. The darker the color in the corn stalk yield distribution map, the higher the corn stalk yield in that area; the darker the color in the corn stalk yield distribution map, the lower the corn stalk yield in that area.

[0139] Optionally, when there are multiple original regions, after obtaining the corn yield at the target time in each target region, a corn yield distribution map can be generated based on the corn yield at the target time in each target region. This map describes the distribution of corn yield at the target time in each target region. Furthermore, band calculations can be performed in ENVI software based on the model parameters and independent variable parameters in the crop monitoring model, thereby obtaining a spatial distribution map of crop yield.

[0140] This invention, in the case of multiple original regions, generates a field straw yield distribution map based on the field straw yield at the target time in each target region. This provides a more intuitive and accurate representation of the field straw yield distribution at the target time in each target region, thereby improving user experience.

[0141] Based on the above embodiments, when there are multiple target times, after obtaining the site straw yield corresponding to the target time in the target area based on the yield of the target crop in the target area, the method further includes: generating a site straw yield time series distribution map based on the site straw yield.

[0142] Specifically, when there are multiple original regions and multiple target times, after obtaining the corn stalk yield corresponding to each target time in each target region, a local straw yield time series distribution map can be generated based on the corn stalk yield corresponding to each target time in each target region, which is used to describe the time series distribution of corn stalk yield in each target region.

[0143] Optionally, if there are multiple original regions and each target time corresponds to a specific time, after obtaining the corn yield corresponding to each target time within the target region, a crop yield time-series distribution map can be generated based on the corn yield corresponding to each target time within the target region to describe the time-series distribution of corn yield within each target region.

[0144] This invention, in the case of multiple original regions and multiple target times, generates a time-series distribution map of site straw yield based on the site straw yield corresponding to each target time in each target region. This can present the time-series distribution of site straw yield in each target region more intuitively and accurately, and improve user perception.

[0145] To facilitate understanding of the field straw yield estimation method provided by this invention, an example is given below to illustrate the field straw yield estimation method provided by this invention. Figure 2 This is the second flowchart illustrating the field straw yield estimation method provided by this invention. Figure 2 As shown, when estimating the site straw yield based on the field site straw yield estimation method provided by the present invention, firstly, optical and SAR remote sensing images of the original area at the target time can be obtained, and then target remote sensing images can be obtained.

[0146] Secondly, the target vegetation index of the target remote sensing image can be obtained. Based on the target vegetation index of the target remote sensing image, the target area can be determined within the original area.

[0147] Secondly, meteorological and topographic data of the target area at the target time can be obtained, so that the target vegetation index of the target remote sensing image and the meteorological and topographic data of the target area at the target time can be input into the crop yield estimation model, and the target crop yield of the target area at the target time can be inverted by the crop yield estimation model.

[0148] Furthermore, based on the target crop yield at the target time in the target area, the corresponding site straw yield at the target time in the target area can be obtained;

[0149] Finally, a site straw yield distribution map can be generated based on the site straw yield at the target time in the target area.

[0150] Figure 3 This is a schematic diagram of the field straw yield estimation device provided by the present invention. The following is in conjunction with... Figure 3 The field straw yield estimation device provided by this invention is described below. The field straw yield estimation device described below can be referred to in correspondence with the field straw yield estimation method provided by this invention described above. For example... Figure 3 As shown, the device includes: a target data acquisition module 301, a crop yield inversion module 302, and a straw yield estimation module 303.

[0151] The target data acquisition module 301 is used to acquire target data.

[0152] The crop yield inversion module 302 is used to obtain the target crop yield at a target time within a target area based on target data.

[0153] The straw yield estimation module 303 is used to obtain the site straw yield at a target time within a target area based on the target crop yield.

[0154] The target data includes the target vegetation index of the target remote sensing image, as well as the meteorological and topographic data of the target area at the target time; the target remote sensing image is the remote sensing image of the original area at the target time; the target area is the area in the original area where the target crop is planted; the target time is the period from when the target crop is planted in the target area to when the target crop is harvested.

[0155] Specifically, the target data acquisition module 301, the crop yield inversion module 302, and the straw yield estimation module 303 are electrically connected.

[0156] The target data acquisition module 301 can be used to acquire remote sensing images of the original target area at the target time using the GEE (Google Earth Engine) platform, as the target remote sensing image; it can also be used to acquire the target vegetation index of the target remote sensing image through numerical calculation and / or mathematical statistics; it can also be used to acquire meteorological data and topographic data of the target area at the target time through various methods.

[0157] The crop yield inversion module 302 can be used to obtain the corn yield at a target time within a target area through numerical calculation.

[0158] The straw yield estimation module 303 can be used to obtain the corn straw yield at a target time within a target area through numerical calculation.

[0159] Optionally, the crop yield inversion module 302 can also be specifically used to input target data into the crop yield estimation model and obtain the target crop yield output by the crop yield estimation model; wherein, the crop yield estimation model is constructed based on a hierarchical linear model; the model parameters of the crop yield estimation model are obtained by inversion based on the sample crop yield and sample data corresponding to the sample time in the sample area; the sample data includes the target vegetation index of the sample remote sensing image and the meteorological data and topographic data of the original sample area at the sample time; the sample area is the area in the original sample area where the sample crop is planted; the sample remote sensing image is the remote sensing image of the original sample area at the sample time; the sample time is within the period from when the sample crop is planted in the sample area to when the sample crop is harvested; the sample crop is the same type as the target crop.

[0160] Optionally, the crop yield inversion module 302 can also be specifically used to input meteorological data and topographic data of the target area at the target time into the second crop yield estimation sub-model to obtain the target parameters output by the second crop yield estimation sub-model; and to input the target vegetation index and target parameters of the target remote sensing image into the first crop yield estimation sub-model to obtain the target crop yield output by the first crop yield estimation sub-model.

[0161] Optionally, the field straw yield estimation device may also include a crop monitoring module.

[0162] The crop monitoring module can be used to input the target vegetation index of the target remote sensing image into the crop monitoring model to obtain the target area output by the crop monitoring model. The crop monitoring model is built based on the random forest algorithm and trained based on the target vegetation index of the sample remote sensing image and the sample area.

[0163] Optionally, the field straw yield estimation device may also include an image generation module.

[0164] The image generation module can be used to generate a site straw yield distribution map based on site straw yield.

[0165] The image generation module can also be used to generate a time-series distribution map of straw yield based on the local straw yield.

[0166] The field straw yield estimation device in this embodiment of the invention obtains the target crop yield at a target time within a target area based on target data, and then obtains the corresponding field straw yield at the target time within the target area based on the target crop yield at the target time within the target area. The target data includes the target vegetation index of the target remote sensing image and the meteorological and topographic data of the target area at the target time. The target remote sensing image is the remote sensing image of the original area at the target time, and the target area is the area within the original area where the target crop is planted. The target time is the period from when the target crop is planted in the target area to when the target crop is harvested. It can combine the influence of regional meteorological and topographic factors on the field straw yield to improve the accuracy of field straw yield estimation.

[0167] Figure 4 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4 As shown, the electronic device may include a processor 410, a communication interface 420, a memory 430, and a communication bus 440. The processor 410, communication interface 420, and memory 430 communicate with each other via the communication bus 440. The processor 410 can call logical instructions in the memory 430 to execute a field straw yield estimation method. This method includes: acquiring target data; acquiring the target crop yield at a target time within the target area based on the target data; and acquiring the corresponding field straw yield at the target time within the target area based on the target crop yield. The target data includes the target vegetation index of the target remote sensing image and meteorological and topographic data of the target area at the target time. The target remote sensing image is a remote sensing image of the original area at the target time. The target area is the area within the original area where the target crop is planted. The target time is the period from when the target crop is planted in the target area until the target crop is harvested.

[0168] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0169] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the field straw yield estimation method provided by the above methods. The method includes: acquiring target data; acquiring the target crop yield at a target time within a target area based on the target data; and acquiring the field straw yield at the target time within the target area based on the target crop yield. The target data includes the target vegetation index of a target remote sensing image and meteorological and topographic data of the target area at the target time. The target remote sensing image is a remote sensing image of the original area at the target time. The target area is an area within the original area where the target crop is planted. The target time is the period from when the target crop is planted in the target area until the target crop is harvested.

[0170] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the field straw yield estimation method provided by the methods described above. This method includes: acquiring target data; acquiring the target crop yield at a target time within a target area based on the target data; and acquiring the field straw yield at the target time within the target area based on the target crop yield. The target data includes the target vegetation index of a target remote sensing image and meteorological and topographic data of the target area at the target time. The target remote sensing image is a remote sensing image of the original area at the target time. The target area is an area within the original area where the target crop is planted. The target time is the period from when the target crop is planted in the target area until the target crop is harvested.

[0171] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0172] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0173] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method of estimating the yield of standing crop in a field, characterized by, The method comprises: acquiring target data; based on the target data, acquiring target crop yield at a target time in a target area; based on the target crop yield, acquiring a standing straw yield corresponding to the target time in the target area; wherein the target data comprises a target vegetation index of a target remote sensing image, and meteorological data and terrain data of the target area at a target time; the target remote sensing image is a remote sensing image of the original area at the target time; the target area is an area in the original area where the target crop is planted; the target time is within a period from when the target crop is planted in the target area to when the target crop is harvested for seeds; standing straw is the remaining part of a mature crop after harvesting seeds; the mature crop includes corn, and the calculation of the dry weight of corn straw is divided into two parts: the above-ground part and the root part; the dry weight of the above-ground part of corn straw can be calculated based on the following formula: Ps=AMPxMSI; wherein Ps represents the dry weight of the above-ground part of corn straw; AMP represents the average annual yield of corn; MSI represents the corn straw index; the dry weight of the root part of corn straw can be calculated based on the following formula: Pr=(AMP / HI)xR / S; wherein Pr represents the dry weight of the root part of corn straw; R / S represents the root-shoot ratio of corn at the mature stage; the dry weight of corn straw can be calculated based on the following formula: P=Ps+Pr.

2. The field site straw yield estimation method according to claim 1, characterized by, The method comprises: inputting the target data into a crop yield estimation model to acquire the target crop yield output by the crop yield estimation model; wherein the crop yield estimation model is constructed based on a hierarchical linear model; the model parameters of the crop yield estimation model are obtained based on sample crop yield and sample data corresponding to a sample time in a sample area; the sample data comprises a target vegetation index of a sample remote sensing image, and meteorological data and terrain data of an original sample area at a sample time; the sample area is an area in the original sample area where the sample crop is planted; the sample remote sensing image is a remote sensing image of the original sample area at the sample time; the sample time is within a period from when the sample crop is planted in the sample area to when the sample crop is harvested for seeds; the sample crop is of the same type as the target crop.

3. The field site stalk yield estimation method of claim 2, wherein, The crop yield estimation model comprises a first crop yield estimation sub-model and a second crop yield estimation sub-model; the second crop yield estimation sub-model is nested in the first crop yield estimation sub-model; correspondingly, the method comprises: inputting the meteorological data and terrain data of the target area at the target time into the second crop yield estimation sub-model to acquire target parameters output by the second crop yield estimation sub-model; inputting the target vegetation index of the target remote sensing image and the target parameters into the first crop yield estimation sub-model to acquire the target crop yield output by the first crop yield estimation sub-model.

4. The field site stalk yield estimation method of claim 3, wherein, The target region is obtained based on the following manner: inputting the target vegetation index of the target remote sensing image into a crop monitoring model to obtain the target region output by the crop monitoring model; The crop monitoring model is constructed based on a random forest algorithm and is trained based on the target vegetation index of the sample remote sensing image and the sample region.

5. The field site stalk yield estimation method of claim 1, wherein, The target vegetation index includes a normalized vegetation index, and the target vegetation index is determined based on the correlation between the vegetation index and the crop yield.

6. The field site stalk yield estimation method according to any one of claims 1 to 5, characterized by, In the case where the number of original regions is multiple, after obtaining the site straw yield corresponding to the target time in the target region based on the target crop yield, the method further comprises: generating a site straw yield distribution map based on the site straw yield.

7. The field site stalk yield estimation method of claim 6, wherein, In the case where the number of target times is multiple, after obtaining the site straw yield corresponding to the target time in the target region based on the target crop yield, the method further comprises: generating a site straw yield time series distribution map based on the site straw yield.

8. A field site straw yield estimation device for use in the field site straw yield estimation method according to claim 1, characterized by, It comprises: a target data acquisition module for acquiring target data; a crop yield inversion module for obtaining the target crop yield of the target time in the target region based on the target data; a straw yield estimation module for obtaining the site straw yield corresponding to the target time in the target region based on the target crop yield; The target data includes the target vegetation index of the target remote sensing image and the meteorological data and topographic data of the target region at the target time; the target remote sensing image is a remote sensing image of the original region at the target time; the target region is a region in the original region where target crops are planted; the target time is within the period from when the target crops are planted in the target region to when the target crops are harvested for seeds.

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to realize the field site straw yield estimation method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the field site straw yield estimation method according to any one of claims 1 to 7.

Images