Method for identifying soil-borne pathogens affecting target crops in agricultural plots.

Abstract

The present invention relates to a method for identifying a soil-borne pathogen for a target crop on an agricultural land plot, the method comprising the steps of: acquiring a first digital image of the agricultural land plot during a first harvest cycle, where a target crop is grown on the agricultural land plot during the first harvest cycle; acquiring a reference digital image of the agricultural land plot during a reference harvest cycle, where a reference crop is grown on the agricultural land plot during the reference harvest cycle, the reference crop being different from the target crop; calculating a first vegetation index associated with a first pixel in the first digital image; determining a first signed distance between the first pixel and pixels surrounding the first pixel based on the first vegetation index, and detecting a first anomaly for the first pixel if the first signed distance is less than a defined threshold; defining a reference anomaly for the reference pixel of the reference digital image; and identifying a soil-borne pathogen for the first pixel if the first anomaly does not match the reference anomaly.

Description

Technical Field

[0001] The present invention relates to a method for identifying soil-borne pathogens for target crops in agricultural fields, and particularly to a remote sensing method for mapping and managing soybean nematode pressure. More specifically, the present invention relates to a method for remotely sensing and assessing damage to soybean fields caused by nematodes, and more generally, to a method for monitoring the health of crops in a field.

Background Art

[0002] Identifying and monitoring soil-borne pathogens such as diseases or pests is extremely important for ensuring high productivity in the field. Those pathogens can generally survive in the soil for several years and can rapidly multiply with the presence of host crops. Nematodes are plant-parasitic soil-borne pathogens that can infect more than 200 different plant species in 23 families. They inhabit the soil and feed on plant roots. Soybean crops are hosts for approximately 100 nematode species, among which soybean cyst nematode (Heterodera glycines), root-lesion nematode (Pratylenchus brachyurus), root-knot nematode (Meloidogyne incognita / javanica), reniform nematode (Rotylenchus reniformis), and spiral nematode (Helicotylenchus spp.) are the most common. The life cycle of nematodes varies slightly by species. However, they all feed on the root system.

[0003] Nematodes occur within plots of fields and have low mobility. Crop damage occurs when nematodes invade and feed on soybean roots, reducing the plant's ability to obtain water and nutrients, potentially leading to decreased productivity. Ground-level infection symptoms are not unique to nematode infections and can be confused with nutrient deficiencies, drought stress, phytotoxicity, or other pests and diseases. This is why methods for assessing nematode-related stress are limited. Conventional methods rely on human reconnaissance using expert visual assessment of the typical uneven shape of nematode stress. Such assessments rely on the eyes of trained assessors, which can be biased, inaccurate, and not repeatable, and cannot be extended to large geographical areas. Ultimately, the presence of nematodes can also be confirmed by local soil sampling and laboratory procedures to identify different nematode species and count individuals. In this case too, such techniques cannot be well extended to large geographical areas, are costly, and may not capture the local spatial variability of nematode populations. Countermeasures to reduce the impact of nematodes include agricultural practices such as crop rotation, the use of resistant varieties, and the use of nematicides. In particular, crop rotation involves alternating soybeans with other non-host crops or plants less susceptible to nematodes, such as maize, to reduce the number of nematodes in the soil.

[0004] Therefore, there is a need for improved methods to map soilborne pathogens, such as nematode stress in crops, that are reliable and effective, especially across large geographical areas. Such methods would enable better management of soilborne pathogens, ultimately leading to higher crop yields. [Overview of the project] [Problems that the invention aims to solve]

[0005] As mentioned above, there is a need to provide a highly reliable, effective, and computer-assisted assessment of soil-borne pathogens in fields for target crops, particularly nematode stress on soybean crops. [Means for solving the problem]

[0006] According to the present invention, this need is solved by a method for identifying soil-borne pathogens to target crops in agricultural plots, as defined by the features of independent claim 1. Preferred embodiments are subject to the dependent claims.

[0007] In one embodiment, the present invention relates to a method for identifying soil-borne pathogens for a target crop in a farm plot. The method comprises the steps of: acquiring a first digital image of a farm plot in a first crop cycle, wherein the target crop is growing in the farm plot during the first crop cycle; acquiring a reference digital image of a farm plot in a reference crop cycle, wherein the reference crop is growing in the farm plot during the reference crop cycle and the reference crop is different from the target crop; calculating a first vegetation index associated with a first pixel in the first digital image; and determining a first signed distance between the first pixel and surrounding pixels based on the first vegetation index. decision The method includes the steps of: detecting a first anomaly in a first pixel if the first signed distance is less than a predefined threshold; defining a reference anomaly for a reference pixel in a reference digital image; and identifying a soil-borne pathogen in the first pixel if the first anomaly does not match the reference anomaly.

[0008] The method according to the present invention can be implemented as a computer program that processes digital images of crops and detects soil-borne pathogens against target crops with relatively little human intervention. In other words, the method relates to a computer implementation invention, and the steps of the method described above and below can be implemented in a computer program. The computer program can be stored in non-volatile memory. A computer can use its operating system and hardware components to run the computer program to identify soil-borne pathogens against target crops in a field plot. The term "computer" can refer to a system that includes not only several computers or computing units in a distributed manner, but also other electronic devices such as cameras and drones for acquiring digital images.

[0009] In another aspect, the present invention relates to a system for identifying soil-borne pathogens for a target crop in a farm plot, comprising an image capture device configured to acquire a first digital image of the farm plot in a first harvest cycle and a reference digital image of the farm plot in a reference harvest cycle. In the first harvest cycle, the target crop grows in the farm plot. In the reference harvest cycle, the target crop grows in the farm plot. The reference crop is different from the target crop. The system calculates a first vegetation index associated with a first pixel in the first digital image and calculates a first signed distance between the first pixel and surrounding pixels based on the first vegetation index. decision The system further comprises a computing unit configured to detect a first anomaly in a first pixel if a first signed distance is less than a predefined threshold. The computing unit is further configured to define a reference anomaly for a reference pixel in a reference digital image and to identify a soil-borne pathogen in the first pixel if the first anomaly does not match the reference anomaly.

[0010] The term "soilborne pathogen" refers to pests or diseases that typically inhabit and reproduce in the soil and / or roots. It can cause damage to the root system and direct or indirect damage to plant communities. Soilborne pathogens typically include fungi, bacteria, and nematodes. Crops in agricultural plots attacked or stressed by soilborne pathogens, particularly nematodes, exhibit symptoms such as stunted growth, leaf yellowing, and wilting. Such damage to crops results in reduced yields. These symptoms in plant communities are recognizable by the human eye or by computer-aided image processing.

[0011] The term “digital image” in relation to farm plots refers to a digital image or photograph, which is a visual photographic representation of crops within a farm plot. A digital image includes photographic elements, also called pixels. Each pixel is given a finite and discrete numerical value representing its intensity. If necessary, a digital image in a typical invention may have a spatial resolution of 50 meters. In this case, one pixel of the digital image represents a 50 x 50 meter area of ​​crops. For more advanced analysis, the spatial resolution may be finer, i.e., 20 meters or less. Digital images can be acquired, for example, by an aerial transport platform such as a drone, balloon, or airplane, or by a space transport platform such as a satellite. Digital images may be cropped using the boundaries of the farm plot in question, thereby selecting usable images, e.g., images without potential clouds.

[0012] The term "target crop" refers to a crop growing within a farm plot that needs to be assessed. In other words, the target crop is a candidate crop on which the presence of soil-borne pathogens is identified using the method of the present invention. In exemplary embodiments, the target crop is soybean.

[0013] The term "reference crop" refers to a crop grown during a reference harvest cycle. To compare a digital image of a target crop with a digital image of a reference crop, the reference crop is a different crop from the target crop. The reference harvest cycle may be more recent than the target harvest cycle. For example, to assess nematode pressure on a target crop in a field 12 months prior, a reference harvest cycle from 6 months prior may be used, as long as it is present. Alternatively, the reference harvest cycle may also be earlier than the target harvest cycle. In exemplary embodiments, the reference crop is a non-host crop different from the target crop.

[0014] The term "vegetation index" refers to one of the indicators used for observing and analyzing vegetation on the Earth's surface, more specifically, the Earth's vegetation. In relation to pixels in a digital image, the vegetation index indicates the vigor of the vegetation in a farm plot represented by that pixel. A vegetation index can be derived from a digital image of a farm plot. It relates to the vegetation characteristics of the farm plot. The vegetation index can be used to indicate the health of the vegetation in a farm plot, including the soil and the crops growing on it. Typically, the Normalized Difference Vegetation Index (NDVI) is used as a benchmark, but other indices such as the Green Normalized Difference Vegetation Index (GNDVI) or single-spectral band may also be used.

[0015] The term "signed distance" quantifies how much a given pixel's vegetation index deviates from the average vegetation index of its surrounding pixels, preferably the NDVI. The signed distance may also be calculated as defined by equation (1), where x is the vegetation index value of the central pixel being assessed, and μ and σ are the mean and standard deviation of the surrounding pixels.

number

[0016] "Surrounding pixels" refer to neighboring pixels that are not directly adjacent to or next to a given pixel, but rather have a predefined distance to that pixel. For example, the predefined distance may be at least 70 meters and at most 310 meters in terms of spatial distance within the farm plot, i.e., neighboring pixels have a distance of 70 to 310 meters from the given pixel. From a geometric point of view, surrounding pixels form a donut-shaped window. Depending on the type of crop, the predefined distance may also be 80 to 310 meters, or 100 to 250 meters.

[0017] The term "abnormal" in relation to pixels in digital images refers to the state of pixels that may contain soil-borne pathogens. For example, a pixel in a digital image under nematode stress is a pixel that is detected as abnormal during the first harvest cycle and is not detected as abnormal at any point in the baseline harvest cycle. A pixel under stress unrelated to nematodes is a pixel that is detected as abnormal during both the first harvest cycle and the baseline harvest cycle of the subject.

[0018] This invention provides a reliable assessment of soilborne pathogen stress in fields, such as nematode stress on target crops like soybeans, by utilizing distinguishable image patterns. The method according to the present invention is based on remote sensing aerial or satellite imagery and is extendable to large geographical areas. In particular, it relies on time-series images that capture crop rotation between target crops such as soybeans and reference crops such as non-host plants to separate ground-based soilborne pathogen stress, such as nematode stress, from other non-nematode stresses. The underlying isolation strategy is that nematode stress is visible only during the soybean cycle at the same specific location in the field and not during the non-host plant cycle, while other stresses are visible during both the soybean and non-host crop cycles. The same isolation strategy applies to other crop-specific pathogens such as Fusarium virguliforme (sudden death syndrome) in soybeans or Plasmodiophora brassicae (clubroot disease) in rapeseed.

[0019] Preferably, the reference anomaly is calculated by the steps of: calculating a reference vegetation index that indicates the degree of vegetation life of a farm plot for a reference pixel in a reference digital image; and determining the reference signed distance between the reference pixel and the surrounding pixels. decision This can be defined by the steps of: 1) determining the reference signed distance and 2) detecting a reference anomaly in the reference pixel if the reference signed distance is less than a predefined threshold. Alternatively, the reference anomaly can be determined using conventional methods, for example, relying on human intervention. decision This may also be done. Furthermore, the criterion anomalies may already be classified and stored in a historical database. In comparison, the present invention utilizes a computational method for detecting criterion anomalies, thereby further improving the reliability of detection. Since the detection of criterion anomalies using the above steps does not rely on human eyes, the reliability and effectiveness may be further improved. However, if the criterion anomalies have already been classified using conventional methods such as human eyes, they may be used without being reclassified according to the above steps.

[0020] Preferably, the method includes a further step of using digital images from an additional harvest cycle to refine the identification of soil-borne pathogens. The use of an additional crop is a step of acquiring a second digital image of a farm plot in a second harvest cycle, wherein the target crop is growing in the farm plot in the second harvest cycle; a step of calculating a second vegetation index indicating the vegetation viability of the farm plot for a second pixel in the second digital image; and a second signed distance between the second pixel and the surrounding pixels. decisiona step of doing so, and a step of detecting a second abnormality of the second pixel when the second coded distance is less than a defined threshold value. Thus, the identification result of the soil-borne pathogen can, for example, increase the accuracy of detecting the soil-borne pathogen of the target crop and can be further improved from the perspective of reliability. By using an additional harvest cycle of the target crop, that is, an image from the second harvest cycle, nematode stress can be further classified into two categories: (i) non-recurrent nematode stress when nematode stress is detected only on the first pixel and not detected on the second pixel; (ii) recurrent nematode stress when nematode stress is detected on both the first pixel and the second pixel. Generally, in accordance with the fact that nematodes can survive in the soil for several years, recurrent nematode stress can also be considered as a more reliable classification.

[0021] Preferably, the first coded distance is obtained by comparing the first vegetation index with the average and standard deviation of the vegetation indices of the pixels around the first pixel. decision As described above, the first coded distance may be calculated using Equation (1), or a threshold value may be directly applied to the vegetation index. For example, separating pixels with abnormally low vegetation index values may also be used.

[0022] Preferably, the reference coded distance and the second coded distance can be calculated in the same manner as above. That is, the reference coded distance can be obtained by comparing the reference vegetation index with the average and standard deviation of the vegetation indices of the pixels around the reference pixel. decision The second coded distance can be obtained by comparing the second vegetation index with the average and standard deviation of the vegetation indices of the pixels around the second pixel. decision Similar to the first coded distance, the reference coded distance and the second coded distance may be calculated using Equation (1), or a respective threshold value may be directly applied to each vegetation index. For example, separating pixels with abnormally low vegetation index values may also be used.

[0023] Preferably, the second harvest cycle can be used to assist in identifying soil-borne pathogens of the target crop in a timely manner before or after the first harvest cycle. Digital images of a plurality of second harvest cycles may be stored in a database and the database may be searched if necessary.

[0024] Preferably, the method further includes generating a first signed distance map, a reference signed distance map, and a second signed distance map, each including the signed distances of a plurality of first pixels, reference pixels, and second pixels, respectively.

[0025] Preferably, the first signed distance map, the reference signed distance map, and the second signed distance map may each include a plurality of reference harvest cycles and the second harvest cycle. For example, an average reference signed distance map is calculated for each reference harvest cycle using mathematical operators. For example, the signed distances of these multiple cycles may be merged by a minimum operator to emphasize the most severe past stress. The signed distance map is also an image that visually represents anomalies or abnormal pixels. In particular, the signed distance map is a digital image having pixels, where pixel values close to 0 represent normal pixels, pixel values exceeding 0 correspond to abnormally high vegetation indices, and pixel values less than 0 correspond to abnormally low vegetation indices. A further advantage of using the average signed distance map is to reduce the effect of the occurrence of low signed distances on a single image. Low signed distances on a single image are believed to be due to noise such as an image having small clouds or cloud shadows that are not detected. In comparison, nematode damage is expected to result in vegetation stress that persists across multiple images.

[0026] Instead of using the signed distance map, any other method of separating pixels having abnormally low vegetation index values may also be used. Such alternative methods include, for example, directly separating abnormal pixels having vegetation index values below a fixed threshold.

[0027] Preferably, the method further includes the steps of: calculating a target stress state for each of several target crops using an average operator; and updating the target signed distance map by applying a minimum operator to each target stress state of the several target crops. The step using the minimum operator is not mandatory. The step using the average operator may be necessary because multiple images may also exist within the target period.

[0028] Preferably, the method further includes the steps of: calculating a baseline stress state for each of a plurality of reference crops using an average operator; and updating a baseline signed distance map by applying a minimum operator to each of the baseline stress states for the plurality of reference crops.

[0029] Preferably, the method further includes the steps of: calculating a second stress state for each of a plurality of second crops using an average operator; and updating a second signed distance map by applying a minimum operator to the second stress state for each of the plurality of second crops.

[0030] As mentioned above, low values ​​in the signed distance map correspond to abnormally low vegetation indices, which are vegetation holes. Therefore, by using the minimum operator over multiple cycles, the occurrence of the most severe stress may be maintained, while using the average operator over a given harvest cycle attempts to reduce false stress detection due to noise. Here, "noise" refers to something that leads to small signed distances on a single image, e.g., an image with small clouds that were not filtered out. In comparison, it can be expected that nematode stress will persist across multiple images.

[0031] Preferably, the method further includes the step of identifying a soil-borne pathogen in a first pixel if the first anomaly is not present in the reference signed distance map.

[0032] Preferably, the method further includes the step of identifying that the first anomaly is a recurrent soil-borne pathogen if the first anomaly is present on a second signed distance map, or identifying that the first anomaly is a non-recurrent soil-borne pathogen if the first anomaly is not present on the second signed distance map. In particular, if the anomaly occurs only during a first harvest cycle and not during a second harvest cycle, the anomaly may be classified as a non-recurrent nematode.

[0033] In other words, a more specific identification of soil-borne pathogens can be described by comparing the first signed distance map with the reference signed distance map and the second signed distance map. In particular, if the first anomaly is not present in the reference signed distance map, the target crop may have a soil-borne pathogen. Furthermore, if the first anomaly is present in the second signed distance map, it means that the target crop may have a relapsing soil-borne pathogen, or if the first anomaly is not present in the second signed distance map, it means that the target crop may have a non-relapsing soil-borne pathogen. If the first anomaly is present in the reference signed distance map, it means that the target crop may not have a soil-borne pathogen.

[0034] Preferably, the method further includes the step of modifying a predefined threshold for adjusting the level of identified soil-borne pathogens. Different thresholds may be useful to define an increase in the stress level of soil-borne pathogens.

[0035] In particular, it can be used to separate pixels that are below a certain value. Thus, the method may further include the step of separating a first pixel by a pixel having a signed distance less than a predefined threshold, wherein the predefined threshold corresponds to the probability of a false alarm.

[0036] Preferably, the digital image has a spatial resolution of 50 meters or less, preferably 20 meters or less. The required image resolution depends on the type of crop and the soil-borne pathogen being assessed.

[0037] Preferably, each of the first vegetation index, the reference vegetation index, and the second vegetation index includes at least one of the normalized differential vegetation index, the green normalized differential vegetation index, and the near-infrared zone.

[0038] This invention provides a method for detecting areas of soybean crops experiencing above-ground stress caused by soil-borne pathogens, such as nematode stress, within a given geographical area. For example, this makes it possible to map soybean fields and identify areas infested with nematodes. The method relies on time-series remote sensing aerial or satellite imagery capturing crop rotation between soybeans and non-host plants to separate above-ground nematode stress from other non-nematode stresses. Non-nematode stresses may include soil compaction, nutrient deficiency, drought stress, and other non-soybean-specific stresses. The method provides a reliable map of soybean nematode stress over a large geographical area. Such information is useful for better nematode management and ultimately for improving soybean production.

[0039] The method according to the present invention is described in detail below as an exemplary embodiment of the present invention with reference to the accompanying drawings. [Brief explanation of the drawing]

[0040] [Figure 1] A flowchart of the steps for an exemplary embodiment of identifying soybean regions under nematode stress is shown. [Figure 2] This document presents an exemplary embodiment that relies on time-series multispectral remote sensing images encompassing past cycles of soybeans and non-host plants. [Figure 3] An exemplary embodiment of the calculation of the NDVI for each digital image, and then the signed distance for a donut-shaped sliding window, is shown. [Figure 4] An exemplary embodiment is shown in which a donut-shaped window is used to compare the pixel value of the central pixel with the mean and standard deviation of neighboring pixels. [Figure 5]An exemplary embodiment is shown in which a first signed distance map, a second signed distance map, and a reference signed distance map are transformed into a first anomaly map, a second anomaly map, and a reference anomaly map, respectively, using predefined thresholds. [Figure 6] An exemplary embodiment is shown in which a signed distance map is joined to a map for the current soybean cycle, a map for past soybean cycles, and a map for past non-host plant cycles, the joining being performed through average and minimum operators. [Figure 7] An exemplary embodiment is shown in which a decision tree is used to determine whether the pixel stress during the current soy cycle is related to nematodes or has other causes. [Figure 8] An exemplary embodiment is shown in which the coupling of anomaly maps to the output indicates regions under nematode stress with three stress intensities: high, medium, and low. [Figure 9] An exemplary embodiment is shown in which the output of the method indicates regions under nematode stress with three stress intensities: high, medium, and low, and drone images taken during the current soybean cycle are shown on the output map highlighting the nematode compartments. [Modes for carrying out the invention]

[0041] In the exemplary embodiment, the soilborne pathogen is a nematode and the target crop is soybean. This is merely for better understanding and should not limit the scope of the claims to a general application of a method for identifying soilborne pathogens against the target crop.

[0042] In the following description, certain terms are used for convenience and are not intended to limit the invention. "Right," "left," "up," "down," "under," and "above" refer to directions in the drawings. Technical terms include not only the terms explicitly mentioned, but also their derivatives and terms with similar meanings. In addition, spatial relative terms such as "beneath," "below," "lower," "above," "upper," "proximal," and "distal" may be used to describe the relationship of one element or feature to another element or feature shown in the drawings. These spatial relative terms are intended to encompass different locations and orientations of the device in use or operation, in addition to the location and orientation shown in the drawings. For example, if a device in a drawing is inverted, an element described as “below” or “beneath” another element or feature becomes “above” or “over” that other element or feature. Therefore, the exemplary term “below” can encompass both above and below positions and orientations. A device may also be oriented in other ways (rotated 90 degrees or oriented in other ways), and the spatial relative descriptors used herein are interpreted accordingly. Similarly, descriptions of movement along and about various axes include various spatial device positions and orientations.

[0043] To avoid repetition of drawings and descriptions of various aspects and exemplary embodiments, please understand that many features are common to many aspects and embodiments. The omission of an aspect from the description or drawings does not imply that the aspect is missing from the embodiment that incorporates it. Rather, aspects may be omitted for clarity and to avoid redundant descriptions. In this context, the following applies to the remainder of this description: To clarify the drawings, if a drawing contains reference numerals not described in the directly relevant part of the description, it refers to a previous or subsequent description section. Furthermore, for clarity, if not all features of a part are given reference numerals in a drawing, it refers to another drawing showing the same part. Similar numbers in two or more drawings represent the same or similar elements.

[0044] The following is a detailed description of an exemplary embodiment of the present invention, namely, a method for a highly reliable and scalable assessment of the impact of nematodes on soybean crops in fields using remote sensing aerial or satellite imagery.

[0045] Figure 1 shows flowcharts of some key and optional steps of exemplary embodiments of the present invention, where the steps of assembling a signed distance map and isolating nematode stress are preferred but entirely optional.

[0046] In the first step, time-series multispectral remote sensing images are acquired. These digital images are a visual photographic representation of crops within a farm plot. In the second step, comprehensive stress can be detected by calculating signed distances for vegetation indices. In the third step, signed distance maps can be constructed for each harvest cycle. In the fourth step, nematode stress can be isolated based on a decision tree applied to the stress map.

[0047] In particular, the first step may involve preparing time-series multispectral remote sensing images of the fields to be analyzed. The images include spectral bands that allow for the calculation of a vegetation index correlated with vegetation health. The Normalized Difference Vegetation Index (NDVI) is used here as the preferred index, but other indices such as the Green Normalized Difference Vegetation Index (GNDVI) or single spectral band may also be used, insofar as they emphasize vegetation viability. The NDVI is defined as the normalized difference between the near-infrared band and the red band using the following equation (2):

number

[0048] Figure 2 shows a time-series image encompassing multiple harvest cycles. Here, to assess nematode stress for a recent soybean cycle, the time series includes three past soybean cycles and three past non-host plants used in rotation with soybeans. Some past cycles may not have available cloud-free images. This is acceptable as long as there is at least one past cycle for soybeans and non-host plants with cloud-free images that provide a sufficient visual representation of the crop. Finally, all images may be cropped to the boundaries of the field being analyzed and resampled on a common pixel grid to allow pixel comparison across images. This may be considered an optional preprocessing step; for example, the digital image in Figure 2 shows only pixels within the plot. Pixels outside the plot are masked or blacked out and so-called cropped to the field boundaries. Then, in the case of some satellite source, or when different satellites are used, the images may be sampled on different pixel grids. Since a given pixel spanning multiple images is to be analyzed, the images should all be sampled on the same pixel grid. Recently, satellite imagery is increasingly being provided in formats that allow for multi-point-of-time comparisons.

[0049] In this embodiment, there are three soybean cycles as past second harvest cycles and three non-host crop cycles as past baseline harvest cycles. These harvest cycles are shown in very accurate locations on the time scale, indicating the potential for nematodes in the target crop, which is currently soybeans. decision It is used for this purpose. In other embodiments, the second harvest cycle is more recent than the target harvest cycle, and the reference harvest cycle may also be more recent than the target harvest cycle.

[0050] The second step, shown in Figure 1, may involve identifying pixels of fields under stress compared to neighboring pixels. First, NDVI is calculated for each image as a surrogate to assess the overall vegetation health.

[0051] Figure 3 shows a sliding window applied to an NDVI image to calculate the signed distance, defined by equation (1). The signed distance can be quantified by how far the NDVI of a given pixel deviates from the mean NDVI of its neighbors. This quantity may be normalized by the standard deviation of neighboring pixels to handle images with crops at different maturity levels. The window used to calculate the signed distance may have a donut shape, thereby allowing for the ignoring of pixels that are close to a given central pixel and may be under stress. The size of the window should not be smaller than the typical size of expected nematode stress, nor should it be larger than other large-scale heterogeneities in the field.

[0052] In particular, NDVI images of the target crop, including the first vegetation index, can be generated using digital photographs (digital images) of the target crop. Based on the NDVI images, signed distance maps can be calculated.

[0053] Figure 4 shows an exemplary donut-shaped window with an outer radius of 310 meters and an inner radius of 70 meters. The output of the second step is a set of signed distance maps, one for each image in the time series. The pixel to be assessed is located in the center of the donut. Neighboring pixels adjacent to or immediately next to this pixel will be ignored from the analysis. Neighboring pixels surrounding the pixel to be assessed, which are at a distance of 70 to 310 meters from the pixel to be assessed, are used to calculate the vegetation index of the pixel.

[0054] Figure 5 shows the first signed distance map (current soybeans), the second signed distance map (past soybeans), and the reference signed distance map (past non-host crops) in grayscale (top image), and their respective anomalous maps after transformation using a predefined threshold, with anomalous pixels highlighted in gray (bottom image). As mentioned above, low values ​​in the signed distance maps correspond to anomalously low vegetation indices, which are holes in the vegetation. Accordingly, the three signed distance maps show anomalous pixels highlighted in black representing holes, and the three anomalous maps show anomalous pixels highlighted in (light) gray. Exemplary nematode sections (np) on the first anomalous map are highlighted with white arrows. On the reference anomalous map, the same region includes non-nematode regions (nn). In other words, the first anomalous map does not coincide with the reference anomalous map in this exemplary region.

[0055] The third step shown in Figure 1 may involve combining multiple signed distance maps for each harvest cycle into three maps: a map for the current soybean cycle, a map for past soybean cycles, and a map for past non-host plant cycles.

[0056] As shown in Figure 6, first, an average signed distance map is calculated for each harvest cycle, and then past cycles for a given crop are aggregated together using a pixel-level minimum operator. The average operator captures the overall stress state of a given harvest cycle and can handle a variable number of input images. The minimum operator isolates the worst stress events from all past cycles. In this case, the non-host crop corresponds to the reference crop in the general definition of the method according to the present invention. Furthermore, in the general definition of the method according to the present invention, past soybeans correspond to the second crop, and current soybeans correspond to the target crop.

[0057] The final step, shown in Figure 1, combines three signed distance maps through a decision tree, as shown in Figure 6, to determine whether the stress on a given pixel during the current soy cycle is related to the nematode or has other causes. decision This may include the following: On each signed distance map, a pixel is considered stressed if its signed distance value is less than a given threshold. In other words, a pixel is stressed if it corresponds to a negative NDVI anomaly. Different thresholds may be used to define an increase in stress levels. For example, from equation (1), a threshold of -2 separates pixels less than -2σ. Assuming that unstressed NDVI pixels follow a Gaussian statistical distribution, such a threshold corresponds to a 2.3% probability of a false alarm. Equation (3) gives the probability of a false alarm (PFA) as a function of threshold t, mean μ, and standard deviation σ. The function erf is the error function. JPEG0007886895000003.jpg22170

[0058] Figure 7 shows a decision tree for anomalies using signed distance pixels for the target harvest cycle, which is the current soybean cycle. In particular, if an anomaly occurs during the first harvest cycle and also occurs during the second harvest cycle, the anomaly is classified as a recurrent nematode. Pixels under stress unrelated to nematodes are pixels detected as an anomaly during the target's first harvest cycle and during the baseline harvest cycle. If the first anomaly is a recurrent soilborne pathogen, it means that the target crop has a recurrent soilborne pathogen. If the first anomaly is a non-recurrent soilborne pathogen, it means either (i) the target crop has a potential new soilborne pathogen when the second target cycle is timely before the first harvest cycle, as shown in Figure 7, or (ii) the target crop has a non-recurrent soilborne pathogen when the second target cycle is more recent than the first harvest cycle.

[0059] Figure 8 shows an example of the output map of the method using the decision tree according to Figure 7, combining the first anomaly map, the second anomaly map, and the reference anomaly map, and indicating regions under nematode stress. Three intensities of nematode stress are highlighted on the output map (low, medium, high). Regions under non-nematode stress are not shown, but are a useful by-product of the method of the present invention. Non-nematode stress may correspond to soil compaction, water stress, water logging, nutrient deficiency, and other non-soybean-specific stresses. Here, the severity levels of the three stresses "low," "medium," and "high" correspond to three thresholds t=-1.04 (15% PFA), t=-1.44 (7.5% PFA), and t=-2.33 (1% PFA), respectively. White arrows point to exemplary nematode compartments (np) on the output map.

[0060] In general, there are many advantages to using the method according to the present invention, for example, that it can increase farm profits, meaning higher yields and reduced input.

[0061] Furthermore, the method can identify the location of nematode-infested fields. A nematode infestation map with GPS coordinates of infested areas can be used for different purposes, for example: (i) for directly targeted nematicide application, where the application of nematicides to treated seeds or furrows is applied only to infested areas; (ii) for targeted soil sampling to confirm a diagnosis and accurately assess nematode pressure in infested areas; (iii) for crop rotation optimization, where specific crop rotations can be selected for the entire field or a portion thereof to reduce nematode pressure, particularly in fields where high nematode pressure is expected; and (iv) to assess the progression of nematode pressure over time in fields.

[0062] In addition, the method can be used to compare nematode pressures across different fields. For example, the method can be used to identify the most infested fields in order to optimize and prioritize farm management. The progression of nematode pressures over time in different fields can also be assessed to evaluate the effectiveness of applied countermeasures.

[0063] Finally, Figure 9 shows aerial drone images taken during the current soybean cycle, illustrating the nematode compartment (np), with the nematode compartment (np) highlighted by arrows on the output map on the left. On the output map, regions under nematode stress are again shown with three stress intensities: high, medium, and low.

[0064] This description and accompanying drawings illustrating aspects and embodiments of the present invention should not be taken as limiting the claims defining the protected invention. In other words, although the present invention is illustrated and described in detail using examples such as nematodes and soybean crops, and standard-illustrated distance maps in the drawings and the foregoing description, such illustrations and descriptions should be considered illustrative or illustrative, not limiting. Various mechanical, compositional, structural, electrical, and operational modifications may be made without departing from the spirit and scope of this description and the claims. In some cases, well-known circuits, structures, and techniques are not shown in detail so as not to obscure the present invention. Therefore, it should be understood that changes and modifications may be made by those skilled in the art within the scope and spirit of the following claims. In particular, the present invention encompasses further embodiments having any combination of features from the different embodiments described above and described below. For example, it is possible to operate the present invention in embodiments in which a reference-illustrated distance map is not used, as defined in claim 1 of the present invention.

[0065] The disclosure also individually encompasses all further features shown in the drawings, which may not be described in the above or below description. Furthermore, a single alternative to the embodiments described in the drawings and description, and a single alternative to those features, may be discarded from the subject matter of the invention or from the disclosed subject matter. The disclosure includes subject matter comprising the features defined in the claims or exemplary embodiments, and subject matter containing such features.

[0066] Furthermore, in the claims, the word “comprising” does not exclude other elements or steps, and the indefinite article “a” or “an” does not exclude plurality. A single unit or step may perform the functions of multiple features enumerated in the claims. The mere fact that a means is mentioned in different dependent claims does not indicate that a combination of these means cannot be used advantageously. Terms such as “essentially,” “about,” and “approximately” related to attributes or values ​​also specifically define the attribute or value precisely, respectively. In the context of a given calculable value or range, the term “about” refers to a value or range that is, for example, within 20%, 10%, 5%, or 2% of a given value or range. Components described as being joined or connected may be directly joined electrically or mechanically, or they may be indirectly joined through one or more intermediate components. No reference numeral in the claims should be construed as limiting the scope.

[0067] Computer programs may be stored / distributed on suitable media such as optical storage media or solid-state media supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems. In particular, for example, a computer program may be a computer program product stored on a computer-readable medium, and that computer program product may have computer executable program code adapted to be executed to carry out a particular method, such as the method according to the present invention. Furthermore, a computer program may also be a data structure product or signal for embodying a particular method, such as the method according to the present invention. Another aspect of the present invention may be as follows: (1) A method for identifying soil-borne pathogens for target crops in agricultural plots, A step of acquiring a first digital image of the farm plot during a first harvest cycle, wherein the target crop grows in the farm plot during the first harvest cycle. A step of acquiring a reference digital image of the farm plot at a reference harvest cycle, wherein at the reference harvest cycle, a reference crop grows in the farm plot, and the reference crop is different from the target crop. A step of calculating a first vegetation index associated with a first pixel in the first digital image; a step of determining a first signed distance between the first pixel and surrounding pixels based on the first vegetation index; and a step of detecting a first anomaly in the first pixel if the first signed distance is less than a predefined threshold. The steps include defining a reference anomaly for a reference pixel of the reference digital image, If the first abnormality does not match the standard abnormality, the steps include identifying the soil-borne pathogen in the first pixel. Methods that include... (2) The step of defining the standard abnormality is The method of (1), comprising the steps of: calculating a reference vegetation index related to a reference pixel in the reference digital image; determining a reference signed distance between the reference pixel and the surrounding pixels of the reference pixel; and detecting the reference anomaly of the reference pixel if the reference signed distance is less than the predefined threshold. (3) A step of acquiring a second digital image of the farm plot during the second harvest cycle, wherein the target crop grows in the farm plot during the second harvest cycle. A step of calculating a second vegetation index indicating the degree of vegetation viability of the farmland plot for a second pixel in the second digital image; a step of determining a second signed distance between the second pixel and the surrounding pixels; and a step of detecting a second anomaly of the second pixel if the second signed distance is less than the defined threshold. The method according to (1) or (2), further comprising: (4) The method according to any one of (1) to (3), further comprising the step of determining the first signed distance by comparing the first vegetation index with the mean and standard deviation of the vegetation indices of the surrounding pixels of the first pixel. (5) A step of determining the reference signed distance by comparing the reference vegetation index with the mean and standard deviation of the vegetation indices of the surrounding pixels of the reference pixel, and / or The second signed distance is determined by comparing the second vegetation index with the mean and standard deviation of the vegetation indices of the surrounding pixels of the second pixel. The method according to (3) or (4), further comprising: (6) The method according to any one of (3) to (6), further comprising the step of generating a first signed distance map, a reference signed distance map, and a second signed distance map, each including the signed distances of a plurality of the first pixels, the reference pixels, and the second pixels, respectively. (7) The first signed distance map, the reference signed distance map, and the second signed distance map each include a plurality of first harvest cycles, the reference harvest cycles, and the second harvest cycles, The method according to (6), wherein the plurality of first harvest cycles, the standard harvest cycle, and the second harvest cycle alternate with each other. (8) A step of calculating the target stress state for each of the multiple target crops using an average operator, A step of calculating the standard stress state for each of the aforementioned multiple standard crops using the average operator, The steps of updating the reference signed distance map by applying the minimum operator to the reference stress state of each of the plurality of reference crops, and / or A step of calculating a second stress state for each of the plurality of second crops using an average operator, The step of updating the second signed distance map by applying a minimum operator to the second stress state of each of the plurality of second crops. The method of (7), further including the method of (7). (9) The method according to any one of (6) to (8), further comprising the step of identifying the soil-borne pathogen of the first pixel of the target crop if the first abnormality is not present in the reference signed distance map. (10) If the first anomaly is present on the second signed distance map, the step of identifying that the first anomaly is a recurrent soilborne pathogen, or Step 1: If the first anomaly is not present in the second signed distance map, identify that the first anomaly is a non-recurrent soilborne pathogen. The method described in (9), further including the method described in (9). (11) The method according to any one of (1) to (10), further comprising the step of modifying the predefined threshold for adjusting the level of the identified soil-borne pathogen. (12) The method according to any one of (1) to (11), further comprising the step of separating the first pixels of the target crop by pixels having a signed distance less than the predefined threshold, wherein the predefined threshold corresponds to the probability of a false alarm. (13) The method according to any one of (1) to (12), wherein the soilborne pathogen is nematode stress, the target crop is soybean, and the reference crop is a non-host crop. (14) Non-volatile memory containing a computer program for performing any of the steps described in (1) to (13). (15) A system for identifying soil-borne pathogens for target crops in agricultural plots, An image capture device for acquiring a first digital image of the farm plot in a first harvest cycle and a reference digital image of the farm plot in a reference harvest cycle, wherein in the first harvest cycle, the target crop grows in the farm plot, and in the reference harvest cycle, the reference crop grows in the farm plot, and the reference crop is different from the target crop, and the image capture device is otherwise provided. A computing unit calculates a first vegetation index associated with a first pixel in the first digital image, determines a first signed distance between the first pixel and surrounding pixels based on the first vegetation index, and detects a first anomaly in the first pixel if the first signed distance is less than a predefined threshold. Equipped with, A system in which the calculation unit further defines a reference anomaly for a reference pixel of the reference digital image, and identifies the soil-borne pathogen in the first pixel if the first anomaly does not match the reference anomaly.

Claims

1. A method for identifying soil-borne pathogens affecting target crops in agricultural plots, A step of acquiring a first digital image of the farm plot during a first harvest cycle, wherein the target crop grows in the farm plot during the first harvest cycle. A step of acquiring a reference digital image of the farm plot at a reference harvest cycle, wherein at the reference harvest cycle, a reference crop grows in the farm plot, and the reference crop is different from the target crop. A step of calculating a first vegetation index associated with a first pixel in the first digital image; a step of determining a first signed distance between the first pixel and surrounding pixels based on the first vegetation index; and a step of detecting a first anomaly in the first pixel if the first signed distance is less than a predefined threshold. The steps include defining a reference anomaly for a reference pixel of the reference digital image, If the first abnormality does not match the standard abnormality, the steps include identifying the soil-borne pathogen in the first pixel. Includes, A method wherein the target crop is a host crop, and the reference crop is a non-host crop.

2. The step of defining the aforementioned criterion abnormality is, The method according to claim 1, comprising the steps of: calculating a reference vegetation index related to a reference pixel in the reference digital image; determining a reference signed distance between the reference pixel and surrounding pixels; and detecting the reference anomaly of the reference pixel if the reference signed distance is less than the defined threshold.

3. A step of acquiring a second digital image of the farm plot during a second harvest cycle, wherein the target crop grows in the farm plot during the second harvest cycle. The steps include: calculating a second vegetation index indicating the vegetation viability of the farmland plot for a second pixel in the second digital image; determining a second signed distance between the second pixel and surrounding pixels; and detecting a second anomaly in the second pixel if the second signed distance is less than the defined threshold. The method according to claim 1, further comprising:

4. The method according to claim 1, further comprising the step of determining the first signed distance based on the first vegetation index and the mean and standard deviation of the vegetation indices of pixels surrounding the first pixel.

5. A step of determining a reference signed distance between a reference pixel and the surrounding pixels, based on a reference vegetation index indicating the degree of vegetation activity of a farm plot for a reference pixel in the reference digital image, and the mean and standard deviation of the vegetation indices of the surrounding pixels of the reference pixel, and / or A step of determining the second signed distance based on the second vegetation index and the mean and standard deviation of the vegetation indices of pixels surrounding the second pixel. The method according to claim 3, further comprising:

6. The method according to claim 3, further comprising the step of generating a first signed distance map, a reference signed distance map, and a second signed distance map, each including the signed distances of a plurality of first pixels, a reference pixel, and a second pixel, respectively.

7. The first signed distance map, the reference signed distance map, and the second signed distance map each include a plurality of first harvest cycles, reference harvest cycles, and second harvest cycles, The method according to claim 6, wherein the plurality of first harvest cycles, the standard harvest cycle, and the second harvest cycle alternate with each other.

8. A step of calculating the target stress state for each of the multiple target crops using an average operator, A step of calculating the baseline stress state for each of the multiple reference crops using the average operator, The steps of updating the reference signed distance map by applying a minimum operator to each of the reference stress states of a plurality of reference crops, and / or The steps include: calculating the second stress state for each of several second crops using the average operator; Steps to update the second signed distance map by applying a minimum operator to the second stress state of each of the multiple second crops: The method according to claim 7, further comprising:

9. The method according to claim 6, further comprising the step of identifying the soil-borne pathogen of the first pixel of the target crop if the first anomaly is not present in the reference-signed distance map.

10. If the first anomaly is present on the second signed distance map, the step of identifying that the first anomaly is a recurrent soilborne pathogen, or Step 1: If the first anomaly is not present on the second signed distance map, identify that the first anomaly is a non-recurrent soil-borne pathogen. The method according to claim 9, further comprising:

11. The method according to claim 1, further comprising the step of modifying the predefined threshold for adjusting the level of the identified soil-borne pathogen.

12. The method according to claim 1, further comprising the step of separating the first pixels of the target crop by pixels having a signed distance less than the predefined threshold, wherein the predefined threshold corresponds to the probability of indicative a false alarm.

13. The method according to claim 1, wherein the soilborne pathogen is nematode stress, the target crop is soybean, and the reference crop is a non-host crop.

14. A non-volatile memory comprising a computer program for performing the steps described in any one of claims 1 to 13.

15. A system for identifying soil-borne pathogens affecting target crops in agricultural plots, An image capture device for acquiring a first digital image of the farm plot in a first harvest cycle and a reference digital image of the farm plot in a reference harvest cycle, wherein in the first harvest cycle, the target crop grows in the farm plot, and in the reference harvest cycle, the reference crop grows in the farm plot, and the reference crop is different from the target crop. The image capture device comprises the subject crop being the host crop and the reference crop being the non-host crop. A computing unit that calculates a first vegetation index associated with a first pixel in the first digital image, determines a first signed distance between the first pixel and surrounding pixels based on the first vegetation index, and detects a first anomaly in the first pixel if the first signed distance is less than a predefined threshold. Equipped with, A system in which the calculation unit further defines a reference anomaly for a reference pixel of the reference digital image, and identifies the soil-borne pathogen in the first pixel if the first anomaly does not match the reference anomaly.

Images