EP4597099A1 - System and method for determining a crop status - Google Patents

Abstract

Method and system for determining a crop status at a target date, wherein a limit date for the crop is determined, the limit date being earlier than the target date, further comprising receiving image data from a first date, earlier or equal to the first date, processing the first image data, determining a crop status at the first date based on the processed first image data and adjusting the crop status based on the time difference between the first date and the target date. Further embodiments comprise generating an agricultural measure recommendation based on the adjusted crop status.

Description

Technical field
• The present disclosure relates to a method and system for determining a crop status and belongs to the field of precision agriculture.
Background
• Determining a crop status for the farmer to guide their actions and take the necessary agricultural measures is a challenging task. In-field analysis and visual inspection of crops is a time-consuming activity. The use of remote imagery generated by satellites or other equivalent unmanned aerial vehicles has gained importance due to the availability of public imagery from long standing satellite platforms (SENTINEL and LANDSAT amongst others). Remote sensing allows determination of the crop status of remote fields without the need of in-field inspection in a time and cost saving manner.
• However, the use of remote imagery entails well-known disadvantages. Due to the remote distance from where the images are taken, a closer look at the traits of crops is not possible and the consideration of other effects present crops for the evaluation of growth stages and changes in physiology of the plants is cumbersome. For example, in the development of corn and other cereals, the different phases leading to the development of leaves, stalks, tassel and grain result in variations on the observable traits present in remote imagery.
• Due to these growth stage changes, remote imagery based on specific wavelengths related to development traits of plants, lose accuracy towards the end of the crop season.
• It is an object of the current disclosure to establish a method which improves the determination of the crop status like the nitrogen uptake, the dry matter or fresh matter in later stages of crop development, stages at which the decision making gets crucial due to the short time left for ha rvest.
Summary
• According to a first aspect of the present disclosure, this and other objectives are achieved by a computer implemented method for determining a crop status at a target date, the method comprising determining an agricultural field comprising at least one crop; determining a target date for the crop status to be determined; determining a growing degree day value of the crop, comprising determining a limit value for the growing degree day value and a limit date when the limit value is reached, wherein the limit date is earlier than the target date; receiving remote data, the remote data comprising first image data of the agricultural field, wherein the first image data is from a first date equal to or earlier than the limit date; processing the first image data; determining a crop status at the first date based on the processed first image data and adjusting the crop status based on the time difference between the first date and the target date.
• Following this approach, an accurate determination of the crop status can be achieved for later stages of the crop development.
• According to a second aspect of the present disclosure, determining a crop status at the first date further comprises receiving second image data from a second date, wherein the second date is earlier than the first date; processing the received second image data and determining a crop status based on the processed second image data and adjusting the determined crop status at the first date based on the second image data.
• Following this approach, possible inaccuracies present in the first image can be compensated.
• According to a third aspect of the present disclosure, determining a growing degree day value of the crop comprises receiving weather data of the growing season, and the growing degree day value is determined based on the weather data of the growing season.
• Following this approach, an accurate determination of the growing degree day and the limit date can be achieved.
• According to a fourth aspect of the present disclosure, receiving weather data of the growing season comprises receiving at least one of an average daily temperature, a minimum daily temperature and a maximum daily temperature.
• Following this approach, the determination of the growing degree day can be improved.
• According to a fifth aspect of the present disclosure, further comprising adjusting the crop status based on the time difference between a first predetermined date and a second predetermined date, wherein the second predetermined date is later than the first predetermined date, comprising determining the crop's dry matter value at the first predetermined date; simulating the evolution of the crop's dry matter value between the first predetermined date and the second predetermined date; wherein simulating the evolution of the crop's dry matter value comprises receiving historic weather data and iteratively updating the crop's dry matter value based on the weather data between the first predetermined date and the second predetermined date; and adjusting the crop status at the second predetermined date based on the simulation of the crop's dry matter value.
• Following this approach, an accurate evolution of the crop status between the predetermined dates can be achieved.
• According to a further aspect of the present disclosure, receiving historic weather data for simulating the evolution of the crop's dry matter further comprises receiving daily temperature and daily solar irradiance values, and wherein iteratively updating the crop's dry matter value further comprises updating the dry matter value by a generated value proportional to the crop's capability to absorb photosynthetic active radiation (f_APAR) and the daily solar irradiance.
• Following this approach, the different factors influencing the crop development can be correctly assessed.
• According to a further aspect of the present disclosure, the crop's capability to absorb photosynthetic active radiation (f_APAR) is calculated from the first image.
• Following this approach, the crop's capability to absorb photosynthetic active radiation can be assessed.
• According to a further aspect of the present disclosure, calculating crop's capability to absorb photosynthetic active radiation (f_APAR) further comprises receiving a further image, wherein the further image is from a date later than the limit date; processing the received first and further image and determining a first crop's capability to absorb photosynthetic active radiation (f_APAR1) from the first image data and a second crop's capability to absorb photosynthetic active radiation (f_APAR3) from the further image; determine the daily crop's capability to absorb photosynthetic active radiation (f_APAR) based on the first and second crop's capability to absorb photosynthetic active radiation.
• Following this approach, an improved determination of the crop's capability to absorb photosynthetic active radiation can be achieved.
• According to a further aspect of the present disclosure, iteratively updating the crop's dry matter value comprises generating a daily dry matter value (DM_i+1) based on the dry matter value from the previous day (DM_i) and a daily increment.
• Following this approach, the crop status can be accurately adjusted based on the daily updated crop's dry matter.
• According to a further aspect of the present disclosure, an agricultural measure recommendation is generated based on the adjusted crop status.
• Following this approach, the farmers can adapt the agricultural measures based on an accurate and updated crop status.
• According to a further aspect of the present disclosure, the agricultural measure recommendation is used to produce a machine-readable prescription map used to control an agricultural application system and/or carry out the agricultural measure by and agricultural application system.
• According to a further aspect, the crop status is at least one of nitrogen uptake, dry matter, or fresh matter. Preferably, the dry matter in later stages of crop development, or the fresh matter in later stages of crop development.
• According to further aspects, a system, a data processing apparatus, a computer-readable storage medium, and a computer program product configured to carry out the above discussed methods are envisaged within the present disclosure.
Brief description of the drawings
• The accompanying drawings, which are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the principles of the disclosure.
• Figure 1 shows an agricultural field according to the field of application of the present disclosure and a schematic representation of a system according to the main embodiment of the present disclosure.
• Figure 2a and 2b show an example of the evolution of a crop status for earlier crop stages and the iterative update method according to another embodiment of the current disclosure.
• Figures 3 shows the evolution of the crop status throughout the different growth stages and the adaptations following embodiments of the current disclosure.
• Figure 4 shows the different nitrogen uptake processes and evolution through the different growth stages in a crop.
• Figure 5a and 5b show workflows according to different embodiment of the current disclosure.
• The accompanying drawings are used to help easily understand the technical idea of the present disclosure and it should be understood that the idea of the present disclosure is not limited by the accompanying drawings. The idea of the present disclosure should be construed to extend to any alterations, equivalents and substitutes besides the accompanying drawings. Reference will now be made in detail to several embodiments, examples of which are illustrated in the accompanying figures.
Detailed description
• As used below in this text, the singular forms "a", "an", "the" include both the singular and the plural, unless the context clearly indicates otherwise. The terms "comprise", "comprises" as used below are synonymous with "including", "include" or "contain", "contains" and are inclusive or open and do not exclude additional unmentioned parts, elements or method steps. Where this description refers to a product or process which "comprises" specific features, parts or steps, this refers to the possibility that other features, parts or steps may also be present, but may also refer to embodiments which only contain the listed features, parts or steps.
• Unless defined otherwise, all terms present in the current disclosure, including technical and scientific terms, have the meaning which a person skilled in the art usually gives them. For further guidance, definitions are included to further explain terms which are used in the description of the disclosure.
• Figure 1 depicts an agricultural field 20 comprising a crop within an agricultural field with other systems and apparatus with which the system 100 may interoperate. System 100 of the current disclosure is configured to determine fertilizer recommendations to be carried out in farms and agricultural fields. The agricultural field 20 may comprise crops and forestry areas. The agricultural field 20 may further comprise a network of dedicated agricultural sensors 270 comprising: soil sensors, moisture sensors and other state of the art sensors; and one or more weather stations 260 comprising rain, wind, temperature, solar irradiance, humidity sensors and the like. Figure 1 further depicts the usual remote sensing devices which are referred to in the current disclosure. Remote sensing devices like satellite imaging system 250 and other aerial vehicles 240 like aircrafts or unmanned aerial vehicles (UAV) are considered to be within the scope of the current disclosure. Additionally, or alternatively, imagery from ground-based sensors which generate an image of the crop canopy may be used within the present disclosure.
• Figure 1 further shows a schematic representation of the system of the current application according to one embodiment of the current disclosure. System 100, according to the present disclosure, comprises several components such as a memory unit 110, a processor 120, a wired/wireless communication unit 130, an input/output unit 140. The system 100 may be operatively connected with a further personal or mobile device 200 by means of the communication unit 130.
• System 100 comprises an internal agricultural recommendation engine 220. However, the agricultural recommendation engine 220 may be external, to which the system may be remotely connected by means of the communication unit 130. In this case, the remote agricultural recommendation engine 220 may be represented by a computer, a remotely accessible server, other client-server architectures or any other electronic devices usually encompassed under the term data processing apparatus. System 100 does not need to be located within the vicinities of the agricultural field where the recommendation is supposed to take place.
• System 100 can be represented as well by a laptop computer or handheld computing device directly operated by the farmers or users at the location of the agricultural field or not. In this case, the system may include an integrated agricultural recommendation engine 150 which can be fully operated at the farm's location and may comprise a GPS unit 180, or any other suitable localization means. It is to be understood that the presence of remote and integrated recommendation engines are not mutually excluding. Integrated agricultural recommendation engine 150 can be a local copy of remote agricultural recommendation engine 220, or a light version of the remote agricultural recommendation engine 220, to support periods of low network connectivity and offline work. Further, mobile or personal device is considered to be any state-of-the-art mobile computing device which allows the input and output of data by the users and comprise the usual features, such as a screen, antenna, camera, I/O module, central processing unit, and storage unit, amongst others.
• System 100 and remote or integrated agricultural recommendation engines may comprise field, farm data, and/or external data; and/or be configured to receive said data. Here, external data comprises weather data, remote data comprising remote image data and further data provided by weather forecast providers or other third parties. Field data may comprise, amongst others, current and past data of at least one of the following: field and geographic identifiers regarding the geometry of the boundaries of the agricultural field, including the presence of areas within the agricultural field which are not managed, topographic data, crop identifiers (such as crop variety and type, growth status, planting data and date, plant nutrition and health status) of current and past crops, harvest data (such as yield, value, product quality, estimated or recorded historic values), soil data (such as type, pH, soil organic matter (SOM) and/or cation exchange capacity, CEC). Finally, farm data may comprise data regarding planned and past tasks, like field maintenance practices and agricultural practices, fertilizer application data, pesticide application data, irrigation data and other field reports as well as historic series of the data, allowing the comparison of the data with past data, and the processing of further administrative data like work shifts, logs and other organizational data. Planned and past tasks may comprise further activities like surveillance of plants and pests, application of pesticides, fungicides or crop nutrition products, measurements of at least one farm or field parameter, maintenance and repair of ground hardware and other similar activities.
• System 100 may be further configured to receive any of the above-mentioned data inputted manually by the users/farmers by means of the input/output unit 140 or the mobile/handheld computing device or received by the communication unit 130 from the dedicated sensors or data-processing equipment. Further, system 100 and agricultural recommendation engine may be configured to receive weather data from nearby weather stations 260 and/or external crop/farm sensors 270, configured to communicate via one or more networks.
• System 100 may further be operatively connected to an agricultural apparatus 300. Examples of agricultural apparatus 300 include tractors, combines, harvesters, planters, trucks, fertilizer application equipment, and any other item of physical machinery or hardware, typically mobile machinery, and which may be used in tasks associated with agriculture, harvesting and agricultural product application, including the application of fertilizers, fungicide/herbicides, growth regulators or any other kind of biostimulants and/or pesticides. In one embodiment, system 100 may be configured to communicate with the agricultural apparatus 300 by means of wireless networks in order to carry out the agricultural product application for the determined crop. System 100 may be further configured to produce a machine-readable script file for the agricultural apparatus 300.
• The present application makes use of suitable remote image data for remotely determining the crop status. Remote image data may include image data provided by one or more imaging satellites 250 or one or more suitable manned or unmanned imaging aerial vehicles 240. Remote image data may also include image data provided by more proximal mobile and stationary sensing systems which are configured to capture or receive image data from at least a part of the agricultural field. These satellite, mobile or stationary sensing systems are configured to communicate by means of dedicated networks and usual methods which do not need being disclosed herein. Amongst the different remote data available for use, satellite data are nowadays widely available from numerous public (LANDSAT from NASA, SENTINEL from ESA) and/or private providers. The system and method of the present application are however not limited to a satellite data platform, since the spectral bands which can be of use for the present system and method are provided in a big range of the standard satellite data available publicly and privately. Due to the differences present across different satellite and optical sensor platforms, it is hereby not intended to limit the support of the current disclosure to exact and specific wavelengths and the wavelengths recited hereinbelow are provided solely for illustration. While different factors and corrections can be introduced to account for these variabilities, the use of wavelengths proximate to the ones mentioned below should be understood since the specifications of said platforms vary accordingly.
• Within the present disclosure, image data may refer to any data representative of optical intensity received by an imaging sensor, in its broadest sense. Due to the widely available imaging standards, image data may refer to specific image data formats or numerical values representative of a light intensity at a single or different wavelengths, generated by active or passive optical systems. For example, RGB or multi-spectral image sensors situated at a certain height from the crop canopy suffer from the same issues like remote imagery, in which only the crop canopy can be detected and only changes related to the top surface of the canopy are reflected. Any suitable imaging system of the kind is considered to be included in the current disclosure.
• In an embodiment, remote data is obtained from the Sentinel-2 satellite. The Sentinel-2 satellite includes a MSI (Multi Spectral Instrument) that takes high spatial resolution data in order to monitor Earth's surface. A MSI works passively, by collecting sunlight reflected from the Earth and is therefore a more efficient and less energy consuming detection method. The Sentinel-2 MSI consists of 13 bands with different spatial resolutions (10m, 20m or 60m), in the visible, near infrared, and short-wave infrared part of the spectrum. In an embodiment, the current method uses image data related to spectral bands with at least a plurality of wavelengths comprised approximately between 700 and 850 nm. In a further embodiment, the present method uses image data related to at least one of a plurality of spectral bands with wavelengths of approximately 800 nm, 900 nm and 1600 nm. The use of spectral bands from the Sentinel-2 MSI produces measurements with a high resolution (approx. 20 m) and is therefore preferred for the implementation of the current disclosure. Data from the Sentinel-2 MSI has, however, the known disadvantage of not being available on cloudy days and of being influenced by the presence of moisture in the atmosphere.
• In an embodiment, remote data may comprise data relating to different spectral bands used for improving the determination of the present method. Further compensation and calibration algorithms are considered in the present application, depending on the nature and origin of the remote data.
• Receiving the remote data comprises receiving image data of the at least one agricultural field, wherein each image data comprises a time stamp indicative of when the image data was obtained, e.g. , when an image was taken. Once the image data has been received, the method is configured to process the image data.
• Processing the image data may refer to any of the suitable methods to derive agricultural properties from the image data. For example, deterministic methods as explained below related to the determination of vegetation indices representative of a crop status can be used. However, other methods like machine learning derived from calibrated images by means of ground truthing or any other methods are included within the present disclosure.
• In one embodiment, processing the image data comprises generating at least one coefficient (or vegetation index) indicative of a crop status, derived from the image data. Different coefficients or indexes are known for obtaining different agricultural, soil and vegetation information, like the difference vegetation index and the normalized difference vegetation index (NDVI). However, the NDVI is sensitive to the effects of soil brightness, soil color, atmosphere, clouds, cloud shadows, and leaf canopy shadows and requires remote sensing calibration. In that sense, further coefficients contemplated may comprise the Atmospherically Resistant Vegetation Index (ARVI) to reduce the dependence of atmospheric effects; the Soil-Adjusted Vegetation Index (SAVI) or the Type Soil Atmospheric Impedance Vegetation Index (TSARVI) which take into consideration the distinction of vegetation from the different types of soil background.
• Figure 2a shows an example of the evolution of a crop status for earlier crop stages and the iterative update method according to another embodiment of the current disclosure can be seen in Figure 2b. As mentioned above for some embodiments, the crop status can be derived from the suitable vegetation index and has a close relation to the evolution of the used vegetation index.
• As depicted in Figure 2a, the evolution of the crop status is usually continuously increasing for the earlier stages of the growth season. However, some dips in the evolution may appear due to the presence of haze, or moisture, in the atmosphere in the case of remote imagery. Such dips can be adequately dealt with by means of the iterative adjustment method of the current disclosure, according to a further embodiment which will be made clear below. As can be seen in figure 2a, the availability of image data (depicted by crosses 51 along the solid line representing the continuous evolution of the vegetation index) is not always that continuous and poses one of the greatest problems when dealing with remote imagery data. Due to the presence of clouds, in some locations, availability of image data may be spaced even by weeks. Similar issues arise when considering image data as provided by UAVs or optical sensing systems mounted on land vehicles: these are not permanently deployed on the fields, thereby justifying the further use of the features present in the different embodiments of the present disclosure.
• As can be seen towards the end of the crop status evolution in Figure 2a, the crop status as derived from typical chlorophyll- or water-based vegetation indices, as listed above, tends to decrease with the advancement of the crop season. This will be made clearer in combination with Figure 3 and 4.
• Figure 3 shows the evolution of a crop status according to one embodiment of the current disclosure. Specifically, Figure 3 shows the nitrogen uptake evolution of the crop 50, as derived from the processed image data (see explanation for Figure 2a, above), e. g. from a chlorophyll- related vegetation index evolution, such as NDVI. In Figure 3, the points along the dash-dotted line 50 represent the available image data. Figure 3 also shows the actual nitrogen uptake evolution 40 (solid line). Both the nitrogen uptake evolution 50 and the actual nitrogen uptake evolution 40 are depicted throughout the whole growing season. The nitrogen uptake value evolution 50, peaks around mid-season. The actual nitrogen uptake evolution of the crop 40 keeps rising until it plateaus towards the last third of the crop season.
• Despite the decreasing values of the nitrogen uptake evolution 50, shown in Figure 3, the true actual nitrogen uptake 40 keeps growing. This effect is explained in Figure 4, which depicts, as an example, the nitrogen uptake evolution for corn. There are, however, different evolutions for different crops and different nutrients. As it can be seen, around the limit date 60 (shown in Figure 4 as a vertical dashed line), growth of the nitrogen uptake for leaf tissue as depicted by area 31, decreases, similar to the nitrogen uptake growth for stalk and leaf sheaths depicted by area 32. From limit date 60 however, nitrogen uptake for tassel, cob and husks starts developing as seen by area 33, and a bit later most of the nitrogen uptake is then directed to grain growth (see area 34). Together with other crop growth specific processes (e.g. senescence turning the leaves from green to yellow, development of grain which takes nutrients but not visible in the images) it turns out that the image data, and therefore as well those vegetation indexes which are chlorophyll- or water-related (and deriving from there crop status like the nitrogen or nutrient uptake and the biomass development) are not depicting truthfully the evolution of the crop regarding the crop productivity and/or nutrient status. This has implications for yield, productivity, nutrient, biomass and other growth-related parameters of the crop, hence representing a huge challenge for farmers who want to follow the evolution of their crops remotely, in a cheap manner, for the second half of the growing season. The advantages of the different embodiments of the current disclosure will be made clear below.
• In the following paragraphs, the methods of the current disclosure according to the different embodiments will be explained, and reference can be made to Figure 5a and Figure 5b regarding the schematic workflows.
• According to the main embodiment of the present disclosure, a computer implemented method for determining a crop status at a first date is provided, the method comprising determining S10 an agricultural field comprising at least one crop. A non-limiting example of how the current method may determine at least one agricultural field may be the user providing a predetermined agricultural field. Alternatively, the method of the current disclosure may be configured to automatically retrieve the field for which the recommendation is intended, based on farm and/or field data. The agricultural field may be determined as well based on a position of the user, which may be given by the mobile device, by the gps unit 180 of the system 100, or the agricultural apparatus 300, depending on where the user may be implementing the method of the current disclosure.
• The method further comprises determining S20 a target date for the crop status to be determined. According to different embodiments, the target date may be selected by the farmers by means of the input unit 140 or may be determined according to planned agricultural measures or tasks. For example, based on a planned application of an agricultural product or harvesting schedule, system 100 may determine a target date which suits the planned task based on weather data or crop growth data, indicating when it is best to apply the agricultural product or to carry out harvesting operations and carry out the application of the agricultural product or the harvesting operation according to the adjusted crop status.
• The method further comprises determining S30 a growing degree day value of the crop, comprising determining a limit value for the growing degree day value and a limit date when the limit value is reached, wherein the limit date is earlier than the target date;
• Growing degree days values are used to estimate the growth and development of certain crops during the growing season. They can be used retrospectively to calculate a current, past or predicted growth stage of a crop. As such, the method of the current disclosure comprises determining a growing degree day value which determines the limit date 60 when the limit value is reached. As such, as intrinsic part of the method of the current disclosure, the limit date is earlier than the target date, hence implying that the target date at which the crop status shall be determined happens after the growing degree day value reaches a limit value. The limit value indicates the moment in the season in which the crop status is no longer represented by image data, and correspondingly neither by the vegetation index derived from the image data, nor the values acquired by processing the image data by machine learning or by any other suitable method.
• The method further comprises receiving S40 remote data, the remote data comprising first image data of the agricultural field, wherein the first image data is from a date equal to or earlier than the determined limit date. As explained above, image data, such as images, obtained later than the determined limit date do not correctly represent the status of the crop. Hence, counterintuitively, older images are preferred over newer, more recent ones, even though newer images would normally be expected to depict better the status of the crop. This counterintuitive concept is part of the advantageous solution of the current disclosure.
• The method further comprises processing S50 the first image data, determining S60 a crop status at the date of the first image based on the processed first image data and adjusting S70 the crop status based on the time difference between the date of the first image and the determined target date.
• According to further embodiments, processing the first image data comprises determining at least one vegetation index indicative of a crop status based on the image.
• Following this embodiment, determining S60 a crop status based on the processed first image data comprises determining a vegetation index, wherein the vegetation index may be a specific one closely related to the specific crop status which may be of interest for the farmers: e. g. nitrogen uptake for fertilization approaches, biomass for growth regulators or fungicide/pesticide applications, or the like. As the vegetation index is derived from an older date, the determined crop status is then adjusted S70 based on the time difference between the first date and the determined target date. According to different embodiments, this adjustment may be made following different approaches and the advantages will be made clear below.
• According to a further embodiment, determining a growing degree day value of the crop comprises receiving weather data of the growing season, and the growing degree day value is determined based on the weather data of the growing season.
• According to a further embodiment, receiving weather data of the growing season comprises receiving at least one of an average daily temperature, a minimum daily temperature and a maximum daily temperature.
• The usual ways of determining a growing degree day value comprise estimating a number of temperature degrees above a certain threshold. However, for this aim, different methods are usually employed. For example, according to an embodiment, the growing degree day (GDD) value is calculated according to the following equation: $$\mathit{GDD}={\displaystyle \int \left(T\left(t\right)-T_{\mathit{base}}\right)\mathit{dt},}$$ where integration is performed over the time period where the temperature, T, is greater than the base temperature, T_base, wherein the base temperature may be a crop-dependent temperature which can be received from field data.
• According to a further embodiment, simplifying the above mentioned equation, determining a growing degree day (GDD) value is performed according to the following equation: $$\mathit{GDD}={\displaystyle \sum \left[\left(\frac{T_{\mathit{max}}+T_{\mathit{min}}}{2}\right)-T_{\mathit{base}}\right],}$$ where T_max and T_min are the daily maximum and minimum air temperature, respectively, and T_base is the base temperature and where the summation only takes part over those days where (T_max+T_min)/2 > T_base. According to further embodiments, the average daily temperature over a base temperature may be as well used.
• According to a further embodiment, adjusting the crop status based on the time difference between a first predetermined date and a second predetermined date, wherein the second date is later than the first date, comprises determining the crop's dry matter value at the first predetermined date; simulating the evolution of the crop's dry matter value between the first predetermined date and the second predetermined date, wherein simulating the evolution of the crop's dry matter value comprises receiving historic weather data and iteratively updating the crop's dry matter value based on the weather data between the first predetermined date and the second predetermined date; and adjusting the crop status at the second predetermined date based on the simulation of the crop's dry matter value. Preferably, the historic weather data are historic weather data of the at least one agricultural field.
• According to a further embodiment, receiving historic weather for simulating the evolution of the crop's dry matter value further comprises receiving daily temperature and solar irradiance values, and wherein iteratively updating the crop's dry matter value further comprises updating the dry matter value by a generated value proportional to the crop's capability to absorb photosynthetic active radiation (f_APAR) and the solar irradiance. The historic weather data preferably comprises historic weather data of the at least one agricultural field. According to a further embodiment, the dry matter value may be calibrated by a temperature efficiency factor and/or a humidity efficiency factor. The crop's capability to absorb photosynthetic active radiation can be directly derived from image data through usual methods, e. g. derived from the vegetation index as an indicator of the chlorophyll content of the crop canopy. The specific details regarding the computation of f_APAR are well known from publications like: "Pellegrini, P., Mariano Cossani, C., Di Mella, C. M., Pineiro, G., Sadras, V. O., Oesterheld, M., Simple regression models to estimate light interception in wheat crops with Sentinel-2 and a handheld sensor, Crop Science (2020), 1-10"; "Dong, T., Meng, J., Shang, J., Liu, J., Wu, B., Evaluation of chlorophyll-related vegetation indices using simulated Sentinel-2 data for estimation of crop fraction of absorbed photosynthetically active radiation, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 8, No. 8. (2015) 4049-4059". However, unlike the nitrogen uptake or other crop status, like biomass, the crop's capability to absorb photosynthetic active radiation (f_APAR) does not suffer from the disparities present between the crop status and what the image data can represent, since f_APAR is directly related to the crop canopy status and suffers no influence from the different growth stages as shown in Figure 4.
• According to a further embodiment, the crop's capability to absorb photosynthetic active radiation (f_APAR) is calculated from the first image data. When no further image data is available between the first date and the target date, the current method may still use the first image data to determine the crop's capability to absorb photosynthetic active radiation.
• According to a further embodiment, calculating the crop's capability to absorb photosynthetic active radiation (f_APAR) further comprises receiving further image data, wherein the further image data is from a date later than the limit date; processing the received first and further image data and determining a first crop's capability to absorb photosynthetic active radiation (f_APAR1) from the first image data and a second crop's capability to absorb photosynthetic active radiation (f_APAR3) from the further image data and determining the daily crop's capability to absorb photosynthetic active radiation (f_APAR) based on the first and second crop's capability to absorb photosynthetic active radiation.
• As mentioned before, the disparities between crop status and the image data do not affect the determination of the capability to absorb photosynthetic active radiation. Hence, by employing more current image data, closer to the target date, to derive the capability to absorb photosynthetic active radiation, the accuracy of the method of the current disclosure may be improved. According to an embodiment, a daily value of the crop's capability to absorb photosynthetic active radiation may be generated by interpolating the first and second values of the crop's capability to absorb photosynthetic active radiation at the first and further date. Herewith, the simulation of the crop's dry matter value can be generated using an up-to-date value for each daily iteration of the crop's capability to absorb photosynthetic active radiation.
• In a further embodiment, iteratively updating 1400 the crop's dry matter value may be carried out following the diagram flow shown in Figure 5b. The method of the current application may be further configured to iteratively update the crop's dry matter value by a generated value proportional to the crop's capability to absorb photosynthetic active radiation (f_APAR) and the solar irradiance. According to a further embodiment, said value is calibrated by a temperature efficiency factor and/or a humidity efficiency factor. Once the dry matter value has been determined 1410 at the first date, an iterative scheme as depicted in Figure 5B for updating the dry matter value based on weather data is presented. Following the present embodiment, a daily dry matter value (DM_i+1) is generated 1430 based on the dry matter value from the previous day (DM_i) and a daily increment. The daily increment is added to the dry matter value. According to a non-limiting example, the daily increment is determined 1420 based on the daily absorbed photosynthetic active radiation derived from the crop's capability to absorb photosynthetic active radiation (f_APAR) and the solar irradiance, the daily temperature and different calibration factors. This operation is then repeated over the number of days comprised between the first date and the target date until a final dry matter value is computed (DM_end). Based on the computed dry matter value, the crop status is adjusted 1440 for the target date, hereby achieving a more accurate depiction of the crop status. Following the iterative approach, the dry matter evolution may look as follows according to an embodiment of the present disclosure: $${\mathit{DM}}_{i+1}={\mathit{DM}}_i+k\ast f_{\mathit{APAR}}\ast E_i\ast f_T\left(T_i\right)\ast {\mathrm{f}}_{\mathit{VPD}}\left({\mathrm{VPD}}_i\right)$$
• This iteration is carried out for i=1, ..., n; wherein n represents the number of days between the first date and the target date and wherein k represents a constant which may take different values based on crop data, f_APAR is the daily crop's capability to absorb photosynthetic active radiation, E_i is the daily solar irradiance, function f_T is a temperature efficiency factor which is a function of the daily temperature, T_i , and f_VPD represents a humidity factor. In an embodiment, the function f_T may be defined as a function of the daily average temperature and crop-specific maximum and minimum temperature values.
• According to a further embodiment, determining a crop status at the first date further comprises receiving second image data from a second date, wherein the second date is earlier than the first date, processing the received second image data and determining a crop status based on the second image data, adjusting the determined crop status at the first date based on the first image data and the second image data.
• Following this embodiment, despite the suitability and convenience of the choice of a first image at or earlier than the limit date, the case in which the received image data at the first date may be affected by haze, or impaired by clouds, the crop status may be adjusted based on an earlier second image data. Following this embodiment, the crop status may be adjusted as previously mentioned for the time between the target and the first date, wherein the crop status may be iteratively updated as above.
• According to a further embodiment, adjusting the determined crop status at the first date based on the first image data and the second image data may further comprise interpolating the iteratively updated crop status and the crop status at the first date. Following this embodiment, a good compromise can be found between the modelled iterative updating of the crop status and the previously determined crop status at the first date.
• This can be conveniently explained based on Figure 2B, which represents a close-up view of Figure 2A. As it can be seen, during the still increasing evolution of the determined crop status, e. g. the nitrogen uptake, 50 during the crop season prior to the limit date, dips and even a certain overshoot can be observed. This can be due to data artifacts in general image data obtained by ground sensors and/or presence of haze/humidity in the atmosphere when using satellite image data. In Figure 2B, dark bold crosses 51 represent the individual values of a crop status available from the dates where image data is available and not occluded by clouds, obtained by the processing of the image data. By interpolating the value of the iteratively updated adjusted crop status 41, which departs from the continuous line depicting the continuous evolution crop status, as marked by the dark bold crosses 51, a more reliable value for the vegetation index can be obtained. This more reliable value neither follows the artifacts present in the image data overshooting the results, nor is affected by the dips caused by haze/humidity. Hence, an interpolated evolution (dashed line 50') comprised between the respective hollow cross 41 and the dark bold cross 51 of the following available image data, is therefore more consistent with the true evolution of the crop status. Such a consideration when starting the iterative updating from the first date, whenever the first date may be determined, guarantees a better starting point for the further simulation and iterative update between the first date and the target date, although an even older image data is being considered for the determination at the first date.
• As explained already, by combination of the afore-mentioned embodiments, according to a further embodiment, the first predetermined date is the date of the second image data and the second predetermined date is the first date, wherein adjusting the determined crop status at the limit date based on the first image data and the second image data further comprises interpolating between the adjusted crop status at the first date and the determined crop status at the first date.
• According to a further embodiment, an agricultural measure recommendation may be generated based on the adjusted crop status at the target date. The agricultural measure may be one of applying an agricultural product, e. g. a fertilizer, a growth regulator or a fungicide/pesticide, or carrying out a harvesting operation. All these actions are closely related to either the nitrogen uptake (e. g. for fertilizer application) or the crop dry or fresh matter (e. g. for growth regulator, fungicide or pesticide application, for determination of harvesting operation date, or for pre-adjustment of the harvester settings).
• According to a further embodiment, the method further comprises producing a machine-readable script file based on the adjusted crop status for an agricultural apparatus to carry out the corresponding agricultural measure recommendation. Following this embodiment, the system of the current disclosure, or alternatively the agricultural recommendation engine may be configured to produce a machine-readable script which can be uploaded, by means of wireless or other data transmission means, to an agricultural apparatus configured to automatically carry out the measure.
• According to a further embodiment, the method further comprises the implementing of the agricultural measure by an agricultural application system. For example, the agricultural measure may comprise a fertilization recommendation to be implemented by means of an agricultural apparatus 300 configured to carry out a fertilizer application based on the adjusted crop status (nitrogen uptake and/or crop dry matter). Further, based on the crop's fresh matter or nitrogen uptake, the agricultural measure may be a harvesting operation and a date for the harvesting operation and/or a preadjustment of the harvester settings can be carried out.
• While the present disclosure has been illustrated by a description of various embodiments and while these embodiments have been described in considerable detail, it is not the intention of the applicant to restrict or in any way limit the scope of the appended claims to such detail. Additional advantages and modifications will readily appear to those skilled in the art. The disclosure in its broader aspects is therefore not limited to the specific details, representative apparatus and method, and illustrative example shown and described.
• Accordingly, the detailed description thereof should not be construed as restrictive in all aspects but considered as illustrative. The scope of the disclosure should be determined by reasonable interpretation of the appended claims and all changes that come within the equivalent scope are included in the scope of the current disclosure.
• The process steps, method steps, algorithms or the like may be described in a sequential order, such processes, methods and algorithms may be configured to work in alternate orders. In other words, any sequence or order of steps that may be described does not necessarily indicate a requirement that the steps be performed in that order. The steps of processes described herein may be performed in any order practical. Further, some steps may be performed simultaneously, in parallel, or concurrently. Various methods described herein may be practiced by combining one or more machine-readable storage media containing the code according to the present disclosure with appropriate standard computer hardware to execute the code contained therein. An apparatus for practicing various embodiments of the present disclosure may involve one or more computers (or one or more processors within a single computer) and storage systems containing or having network access to computer program(s) coded in accordance with various methods described herein, and the method steps of the disclosure could be accomplished by modules, routines, subroutines, or subparts of a computer program product. While the foregoing describes various embodiments of the disclosure, other and further embodiments of the disclosure may be devised without departing from the basic scope thereof. The scope of the disclosure is determined by the claims that follow. The disclosure is not limited to the described embodiments, versions or examples, which are included to enable a person having ordinary skill in the art to make and use the disclosure when combined with information and knowledge available to the person having ordinary skill in the art.

Claims (15)

1. Computer implemented method for determining a crop status at a target date, the method comprising:

   - determining (S10) an agricultural field comprising at least one crop;

   - determining (S20) a target date for the crop status to be determined;

   - determining (S30) a growing degree day value of the crop, comprising determining a limit value for the growing degree day value and a limit date when the limit value is reached, wherein the limit date is earlier than the target date;

   - receiving remote data (S40), the remote data comprising first image data of the agricultural field, wherein the first image data is from a first date equal to or earlier than the limit date;

   - processing (S50) the first image data;

   - determining (S60) a crop status at the first date based on the processed first image data;

   - adjusting (S70) the crop status based on the time difference between the first date and the target date.
2. The method of claim 1, wherein determining a crop status at the first date further comprises:

   - receiving second image data from a second date, wherein the second date is earlier than the first date;

   - processing the received second image data and determining a crop status based on the processed second image data;

   - adjusting the determined crop status at the first date based on the second image data.
3. The method of any one of the preceding claims, wherein determining a growing degree day value of the crop comprises receiving weather data of the growing season, and the growing degree day value is determined based on the weather data of the growing season.
4. The method of claim 3, wherein receiving weather data of the growing season comprises receiving at least one of an average daily temperature, a minimum daily temperature and a maximum daily temperature.
5. The method of any one of the preceding claims, further comprising adjusting the crop status based on the time difference between a first predetermined date and a second predetermined date, wherein the second predetermined date is later than the first predetermined date, comprising:

   - determining the crop's dry matter value at the first predetermined date;

   - simulating the evolution of the crop's dry matter value between the first predetermined date and the second predetermined date;

   - wherein simulating the evolution of the crop's dry matter value comprises receiving historic weather data and iteratively updating the crop's dry matter value based on the weather data between the first predetermined date and the second predetermined date; and

   - adjusting the crop status at the second predetermined date based on the simulation of the crop's dry matter value.
6. The method of claim 5, wherein receiving historic weather data for simulating the evolution of the crop's dry matter further comprises receiving daily temperature and daily solar irradiance values, and wherein iteratively updating the crop's dry matter value further comprises updating the dry matter value by a generated value proportional to the crop's capability to absorb photosynthetic active radiation (f_APAR) and the daily solar irradiance.
7. The method of claim 6, wherein the crop's capability to absorb photosynthetic active radiation (f_APAR) is calculated from the first image data.
8. The method of claim 6, where calculating crop's capability to absorb photosynthetic active radiation (f_APAR) further comprises:

   - receiving further image data, wherein the further image data is from a date later than the limit date;

   - processing the received first and further image data and determining a first crop's capability to absorb photosynthetic active radiation (f_APAR1) from the first image data and a second crop's capability to absorb photosynthetic active radiation (f_APAR3) from the further image data;

   - determining the daily crop's capability to absorb photosynthetic active radiation (f_APAR) based on the first and second crop's capability to absorb photosynthetic active radiation.
9. The method according to claims 5 to 8, wherein iteratively updating the crop's dry matter value comprises:

   - generating a daily dry matter value (DM_i+1) based on the dry matter value from the previous day (DM_i) and a daily increment.
10. A method according to any of the preceding claims, wherein an agricultural measure recommendation is generated based on the adjusted crop status.
11. A method according to claim 10, wherein the agricultural measure recommendation is used to produce a machine-readable prescription map used to control an agricultural application system and/or carry out the agricultural measure by an agricultural application system.
12. A system configured to carry out the method according to any one of the claims 1 to 11.
13. A data processing apparatus comprising means for carrying out the method of any one of the claims 1 to 11.
14. A computer-readable storage medium comprising instructions which, when executed by a computer system, cause the computer system to carry out the method of any one of the claims 1 to 11.
15. A computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method of any one of the claims 1 to 11.