Method for providing a trigger value setting

Abstract

The present invention relates to a computer-implemented method for generating a trigger value for monitoring and / or controlling at least one application device configured to apply an agricultural product to an agricultural field, wherein the trigger value relates to a field condition to be treated by the agricultural product, the method comprising: providing (310) historical efficacy data of one or more agricultural fields comprising information on efficacies against at least one harmful organism when the agricultural product is appled at at least two different trigger values; generating (320) at least two trigger values, wherein the generation includes a maximum trigger value determined based on a minimal efficacy of the agricultural product according to the historical efficacy data and a minimum trigger value determined based on a smallest amount of the at least one harmful organism per surface unit that is detectable by a sensor of the at least one application device; and providing (330) the at least two trigger values for selecting a control and / or monitoring mode of at least one application device configured to apply an agricultural product to an agricultural field according to the selected a control and / or monitoring mode.

Description

[0001] METHOD FOR PROVIDING A TRIGGER VALUE SETTING

[0002] TECHNICAL FIELD

[0003] The present disclosure relates to a computer-implemented method, to a data processing apparatus, to a harmful organism manamgneent system, and to a computer-readable storage medium for generating a trigger value for monitoring and / or controlling at least one application device configured to apply an agricultural product to an agricultural field.

[0004] TECHNICAL BACKGROUND

[0005] The general background of this invention is the treatment of plantation in an agricultural field. The treatment of the field comprises the treatment of weed, insects, pathogens, diseases, and / or pests in the agricultural field. For more sustainable treatment the application of agricultural products may be enhanced by controlling machinery in a data- driven manner. Such control may be based on sensors attached to the machinery and historical data as for example disclosed in WO2022079172A1 or WO2022184827A1 .

[0006] SUMMARY OF THE INVENTION

[0007] There may be a need to trigger the application of an agricultural product in a robust way to avoid unnecessary treating and / or over treatment of the agricultural field and / or to save amounts of agricultural products.

[0008] The object of the present invention is solved by the subject-matter of the independent claims, wherein further embodiments are incorporated in the dependent claims. It should be noted that the following described aspects of the invention apply also for the computer- implemented method, the data processing apparatus, the harmful organism manamgneent system, and the computer-readable storage medium for generating a trigger value for monitoring and / or controlling at least one application device configured to apply an agricultural product to an agricultural field.

[0009] According to a first aspect of the present invention, there is provided a computer- implemented method for generating a trigger value for monitoring and / or controlling at least one application device configured to apply an agricultural product to an agricultural field, wherein the trigger value relates to a field condition to be treated by the agricultural product, the method comprising: providing historical efficacy data of one or more agricultural fields comprising information on efficacies against at least one harmful organism when the agricultural product is appled at at least two different trigger values; generating at least two trigger values, wherein the generation includes a maximum trigger value determined based on a minimal efficacy of the agricultural product according to the historical efficacy data and a minimum trigger value determined based on a smallest amount of the at least one harmful organism per surface unit that is detectable by a sensor of the at least one application device; and providing the at least two trigger values for at least two control and / or monitoring modes, wherein each control and / or monitoring mode has a respective trigger value for monitoring and / or controlling the at least one application device for the application of the agricultural product.

[0010] The disclosed methods, apparatuses, systems, computer elements, and contral data provide for field-specific, reliable and effective treatment of field condition. In particular, by providing at least two trigger values the treatment may be conducted in different modes allowing to adjust to the situational specifics of the field condition. For example the treatment may be conducted in a cost efficient mode targeting the minimal required amount of agricultural product, an efficacy mode targetting maximum efficacy, and any mode balancing the two targets. The trigger values may be threshold values for an agricultural treatment device, e.g. a spraying device, and may determine the on- and off- ratio of a valve for spraying an agricultural product, e.g. a herbicide or fungicide, to a field. The trigger values may be stored in a register of a computer memory. There may exist a register for a minimum value, a maximum value and a balanced value. The content of the corresponding register may be determined by the above mentioned generating of at least two trigger values.

[0011] The trigger value(s) may be provided to the machine, e.g. by writing the corresponding value in the corresponding register. In an example an input device may be provided which may be adapted to allow a farmer for selecting between the modes and / or the different registers. For example the trigger values may include the maximum trigger value focusing on cost efficiency and / or the efficacy trigger value focusing on the treatment control of the field condition, such as the treatment of at least one harmful organism (e.g., control of weeds). This may allow the use of a more optimal dose of the agricultural product avoiding unnecessary treating and / or over treatment of the agricultural field, and saving money and amounts of agricultural products. In other words, the balanced setup may provide for a predefined field a good compromise between efficacy and savings. If a user may prefer more efficacy, the user may set a trigger value below the balanced set up. If however, the user desires a good saving and may take the risk of not eliminating all weed, the user may set a trigger value above the balanced trigger value. The more parameters, such as soil type, may be known for the field, the more precise the user may set the desired trigger value by selecting the right curves from a set of curves.

[0012] The balanced set up may be a starting point for fine tuning the setup of a treatment device. In an example, the balanced set up may be provided by the above described method.

[0013] The trigger value may include any metric quantifying the harmful organism, which may be used to control an application of the agricultural product. For example, such a trigger value may refer to a ground coverage per unit area, plants per unit area, number of pests per plant, moisture per unit area, etc.

[0014] The agricultural product may include any product / object / material which may be applied on an agricultural field using trigger values.

[0015] In the context of the present disclosure, the term agricultural product may comprise: chemical products such as fungicide, herbicide, insecticide, acaricide, molluscicide, nematicide, avicide, piscicide, rodenticide, repellant, bactericide, biocide, safener, plant growth regulator, urease inhibitor, nitrification inhibitor, denitrification inhibitor, or any combination thereof; biological products such as microorganisms useful as fungicide (biofungicide), herbicide (bioherbicide), insecticide (bioinsecticide), acaricide (bioacaricide), molluscicide (biomolluscicide), nematicide (bionematicide), avicide, piscicide, rodenticide, repellant, bactericide, biocide, safener, plant growth regulator, urease inhibitor, nitrification inhibitor, denitrification inhibitor, or any combination thereof; fertilizers and / or nutrients; seeds and seedlings. The agricultural field may include any area, i.e. surface and subsurface, of a soil to be treated by e.g. seeding, planting and / or fertilizing. The agricultural field may be any plant or crop cultivation area, such as a farming field, a greenhouse, or the like. A plant may be a crop, a weed, a volunteer plant, a crop from a previous growing season, a beneficial plant or any other plant present on the agricultural field. The agricultural field may be identified through its geographical location or geo-referenced location data. A reference coordinate, a size and / or a shape may be used to further specify the agricultural field.

[0016] According to an exemplary embodiment of the present invention, the computer- implemented method further comprises providing historical savings data of the one or more agricultural fields comprising information on an amount of the agrilcutrual product saved when the agricultural product is appled at at least two different trigger values. The generation includes a balanced trigger value determined based on the historical savings data. When the agricultural product is applied at the balanced trigger value, a predefined balanced relationship between savings of the agricultural product and efficacy of the agricultural product is achieved.

[0017] Accordingly, in addition to the minimum trigger value and the maximum trigger value, a balanced trigger value may be provided to balance cost savings and efficacy. Therefore, the farmer may be given a further opportunity to select a mode to balance two targets of targeting the minimal required amount of agricultural product, and targetting maximum efficacy.

[0018] According to an exemplary embodiment of the present invention, the balanced trigger value comprises a trigger value at which the savings have a highest growth rate.

[0019] Accordingly, the balanced trigger value signals the beginning of a decline in the growth rate of the savings with the increase of trigger values. In other words, the increase of the savings slows down with the increase of trigger value. Thus, this balanced trigger value may provide a better balance between the two targets.

[0020] According to an exemplary embodiment of the present invention, the generation includes a balanced trigger value determined based on the minimum trigger value and the maximum trigger value. Accordingly, the balanced trigger value may be determined in a more efficient way without the need of the historical saving data on the day the user retrieves the threshold. However, in some implementations historical data collected from field trials or even from the given field may help to refine the functions for more specific conditions (e.g. a specific soil in a given country).

[0021] According to an exemplary embodiment of the present invention, the savings of the balanced trigger value are an average of the savings of the maximum trigger value and the savings of the minimum trigger value.

[0022] According to an exemplary embodiment of the present invention, the method further comprises providing historical condition data of the one or more agricultural fields. The generation includes at least two maximum trigger values for at least two different conditions determined based on a defined minimal efficacy of the agricultural product according to the historical efficacy data and the historical condition data.

[0023] Accordingly, the condition data may be used to further refine the at least two trigger values. The farmer may be given an opportunity to select between the modes according to a condition of the agricultural field to be treated.

[0024] According to an exemplary embodiment of the present invention, the generation includes at least two balanced trigger values for the at least two different conditions determined based on the historical savings data and the historical condition data or based on the minimum trigger values and the at least two maximum trigger values.

[0025] Examples of the condition data may include, but are not limited to, soil data indicative of a soil condition on the one or more agricultural fields, machine data indicative of a machine for applying the agricultural product on the one or more agricultural fields, environmental data indicative of an environmental condition on the one or more agricultural fields, crop management data indicative of an application history of an agricultural product for the one or more agricultural fields, field data of the one or more agricultural fields, harmful organism data on the one or more agricultural fields, and crop variety data relating to a crop grown or to be grown on the one or more agricultural fields. According to an exemplary embodiment of the present invention, the a minimal efficacy of the agricultural product comprises a user-defined minimal efficacy for generating the maximum trigger value.

[0026] According to an exemplary embodiment of the present invention, the at least one harmful organism comprises a plurality of harmful organisms of different predefined levels of harm. The minimal efficacy comprises an initial minimal efficacy of the agricultural product against one or more of the plurlatiy of harmful organism of a specified level of harm.

[0027] The harmful organisms may be predefined with respect to their level of harm. Level of harm may relate to the likelihood of successful treatment, such as the elimination of the harmful organism. Level of harm may relate to the amount or type of crop protection product required to control the organism. Level of harm may relate to the mechanisms to control the organism such as chemical, mechanical, electromagnetically, etc.

[0028] For example, with mixed harmful organisms of different levels of harm (e.g., one easy to control and one hard to control weed), the trigger value may be set to the hard-to-control harmful organism in order to control all harmful organisms.

[0029] According to an exemplary embodiment of the present invention, the method further comprises modifying the initial minimal efficacy based on an input received from a user interface and / or condition data of the agricultural field to be treated.

[0030] In this way, an initial minimal efficacy is first defined and may be further refined based on a user’s feedback loop and / or according to the condition(s) on the agricultural field.

[0031] According to an exemplary embodiment of the present invention, the method further comprises providing a user interface allowing a user to select a control and / or monitoring mode of at least one application device configured to apply an agricultural product to an agricultural field. According to an exemplary embodiment of the present invention, the method further comprises providing control data for controlling application means of at least one application device, wherein the control data comprises the at least one trigger value for applying the agricultural product on the agricultural field.

[0032] According to a second aspect of the present invention, there is provided a data processing apparatus comprising a processor adapted to perform the steps of the method of the first aspect and any associated example.

[0033] The provided apparatus may allow the use of a more optimal dose of the agricultural product avoiding unnecessary treating and / or over treatment of the agricultural field, and saving money and amounts of agricultural products.

[0034] Accoridng to a third aspect of the present invention, there is provided a harmful organism management system. The harmful organism management system comprises the data processing apparatus according to the second aspect and any associated example configured to provide at least two trigger values for at least two control and / or monitoring modes, wherein each control and / or monitoring mode has a respective trigger value for monitoring and / or controlling at least one application device for an application of an agricultural product, and an application device configured to apply the agricultural product to the agricultural field according to a control and / or monitoring mode selected from the at least two control and / or monitoring modes.

[0035] According to a further aspect of the present invention, there is provided a computer- readable storage medium comprising instructions which, when executed by a processor, cause the processor to carry out the steps of the method according to the first aspect and any associated example.

[0036] These and other objects, which become apparent upon reading the following description, are solved by the subject matters of the independent claims. The dependent claims refer to preferred embodiments of the invention.

[0037] BRIEF DESCRIPTION OF THE DRAWINGS In the following, the present disclosure is further described with reference to the enclosed figures:

[0038] Figure 1 illustrates an exemplary simplified block diagram of a harmful organism management system;

[0039] Figure 2 illustrates an exemplary simplified block diagram of a data processing apparatus for providing a trigger value for applying an agricultural product on an agricultural field;

[0040] Figure 3 illustrates a flowchart describing a computer-implemented method for providing at least one trigger value for applying an agricultural product on an agricultural field;

[0041] Figure 4 illustrates an exemplary diagram describing the relation between the efficacy and the trigger values;

[0042] Figure 5 illustrates an exemplary diagram describing the relation between the product savings and the trigger value obtained from trial data in sugar beet fields;

[0043] Figure 6 illustrates an example of adapting the trigger value to at least one condition on the agricultural field based on historical data;

[0044] Figure 7 illustrates an exemplary trigger value Adaption table; and

[0045] Figure 8 illustrates exemplary savings as influenced by trigger value settings for sugar beet and com fields.

[0046] DETAILED DESCRIPTION OF EMBODIMENT

[0047] The following embodiments are mere examples for implementing the method, the system, the apparatus, or application device disclosed herein and shall not be considered limiting. Figure 1 illustrates an exemplary simplified block diagram of a harmful organism management system 200. The exemplary harmful organism management system 200 may comprise a data processing apparatus 10 for generating a trigger value for monitoring and / or controlling at least one application device configured to apply an agricultural product to an agricultural field 100, a data management system 110, a field management system 120, an electronic communication device 130, a network 140, and at least one application device 150.

[0048] An example of the data processing apparatus apparatus 10 is shown in Figure 2. The exemplary apparatus 10 of the illustrated example may comprise an input unit 12, a processing unit 14, and an output unit 16.

[0049] In general, the data processing apparatus 10 may comprise various physical and / or logical components for communicating and manipulating information, which may be implemented as hardware components (e.g., computing devices, processors, logic devices), executable computer program instructions (e.g., firmware, software) to be executed by various hardware components, or any combination thereof, as desired for a given set of design parameters or performance constraints.

[0050] In some implementations, the exemplary apparatus 10 may be embodied as, or in, a device or apparatus, such as a server, a workstation, or mobile device. The data processing apparatus 10 may comprise one or more microprocessors or computer processors, which execute appropriate software. The processing unit of the exemplary apparatus 10 may be embodied by one or more of these processors. The software may have been downloaded and / or stored in a corresponding memory, e.g., a volatile memory such as RAM or a non-volatile memory such as flash. The software may comprise instructions configuring the one or more processors to perform the functions as described herein.

[0051] It is noted that the data processing apparatus 10 may be implemented with or without employing a processor, and also may be implemented as a combination of dedicated hardware to perform some functions and a processor (e.g., one or more programmed microprocessors and associated circuitry) to perform other functions. For example, the functional units of the data processing apparatus 10, e.g., the input unit 12, the processing unit 14, and the output unit 16 may be implemented in the device or apparatus in the form of programmable logic, e.g., as a Field-Programmable Gate Array (FPGA). In general, each functional unit of the data processing apparatus may be implemented in the form of a circuit.

[0052] In some implementations, the exemplary apparatus 10 may also be implemented in a distributed manner, such as the distributed computing environment 40. For example, some or all units of the exemplary apparatus 10 may be arranged as separate modules in a distributed architecture and connected in a suitable communication network, such as a 3rd Generation Partnership Project (3GPP) network, a Long Term Evolution (LTE) network, Internet, LAN (Local Area Network), Wireless LAN (Local Area Network), WAN (Wide Area Network), and the like.

[0053] In this example, the data processing apparatus 10 is embodied as, or in, the field management system 120, e.g., residing in the field management system 120 as a software.

[0054] Turning back to Figure 1 , The data management system 110 of the illustrated example may store databases, applications, local files, or any combination thereof. The data management system 110 may comprise data obtained from one or more data sources. In some examples, the data management system 110 may include data obtained from a user device, which may be a computer, a smartphone, a tablet, a smartwatch, a monitor, a data storage device, or any other device, by which a user, including humans and robots, can input or transfer data to the data management system 110. In some examples, the data management system 110 may comprise data obtained from one or more sensors. The term “sensor” is understood to be any kind of physical or virtual device, module or machine capable of detecting or receiving real-world information and sending this real- world information to another system, which may include temperature sensor, humidity sensor, moisture sensor, pH sensor, pressure sensor, soil sensor, crop sensor, water sensor, cameras, or any combination thereof. In some examples, the data management system 110 may store one or more databases, which may be any organized collection of data, which can be stored and accessed electronically from a computer system, and from which data can be inputted or transferred to the data management system 110. In some examples, the data management system 110 may store historical data, such as historical efficacy data, historical savings data, historical condition data, collected from one or more agricultural fields. The historical data may comprise trial data. Depending the trial design, various trail data may be collected. For example, a plurality of on-farm and / or industry-based field trials may be carried out to create a grid over one or more agricultural fields in order to combine areas of different trigger values, which, if exceeded, an application of the agricultural product takes place. The differences in the agricultural product savings in the different areas of the one or more agricultural fields may be used to determine the relationship between agricultural product savings and trigger values. The differences in yield data in the different areas of the field may be used to determine the relationship between efficacies and trigger values.

[0055] In some examples, the data manage system 110 may comprise condition data of the agricultural field 100 to be treated. The condtion data may comprise one or more conditions.

[0056] In some implementations, the at least one condition may comprise information on historical and / or current presence of one or more harmful organisms on the agricultural field to be treated. The information on historical and / or current presence of one or more harmful organism on each agricultural field may comprise one or more of the following information: distribution of the harmful organism by locality, level of infestation (e.g., 0%- 100%), sources of infestation (e.g., pest species, weed specifies, fungal disease specifies), and resistance of the harmful organism to the agricultural product.

[0057] In some implementations, the at least one condition may comprise field data of the agricultural field to be treated. The field data may include georeferenced data of different agricultural areas and the associated treatment map(s). The field data may comprise information about one or more of the following information: crop present on the field (e.g. indicated with crop ID), the crop rotation, the location of the field, previous treatments on the field, sowing time, etc.

[0058] In some implementations, the at least one condition may comprise environmental data obtained from e.g., sensors deployed in the field and / or from a weather forecasting service. The environmental data is indicative of an environmental condition for the agricultural field. Exemplary environmental data may include, but is not limited to, air temperature, cloud cover, dew point, short wave radiation, long wave radiation, ice accumulation period, liquid accumulation period, relative humidity, precipitation accumulation period adjusted, snow accumulation period, wind speed. In some examples, the environmental data may be collected by sensors deployed on the agricultural field. In some examples, the environmental data may be received from a weather forecasting service.

[0059] In some implementations, the at least one condition may comprise crop management data. The crop management data indicative of application history of agricultural product(s) for the agricultural field. The crop management data may be obtained from a data management system that stores the history of applications of agricultural products for the agricultural field.

[0060] In some implementations, the at least one condition may comprise location data or geographical data of the agricultural field, which may include latitude and longitude data (e.g., decimal degrees, negative values for south or west) of the agricultural field, which may be obtained from the field data of the agricultural field.

[0061] In some implementations, the at least one condition may comprise any combination of the above-described examples.

[0062] The field management system 120 of the illustrated example may be a server that provides a web service to facilitate management of data. The field management system 120 may comprise a data extraction module (not shown) configured to identify data in the data management system 110 that is to be extracted, retrieve the data from the data management system 110, and provide the retrieved data to the data processing apparatus 10, which processes the extracted data according to the method as described herein. The processed data and the final outputs of the data processing apparatus 10 may be provided to a user output device (e.g., the electronic communication device 130), in an output database (e.g., in the data management system 110), and / or as a control file (e.g., for controlling the application device 150). The term “user output device” is understood to be a computer, a smartphone, a tablet, a smartwatch, a monitor, a data storage device, or any other device, by which a user, including humans and robots, can receive data from the field management system, such as the electronic communication device 130.

[0063] The term “output database” is understood to be any organized collection of data, which can be stored and accessed electronically from a computer system, and which can receive data, which is outputted or transferred from the field management system 120. For example, the output database may be provided to the data management system 110.

[0064] The term “control file”, also referred to as configuration file, is understood to be any binary file, data, signal, identifier, code, image, or any other machine-readable or machine- detectable element useful for controlling a machine or device, for example the application device 150. In some examples, the data processing apparatus 10 may provide an application scheme, which may be provided to the electronic communication device 130 to allow the farmer to configure the application device 150 according to the application scheme. In some examples, the data processing apparatus 10 may provide a configuration profile, which may be loaded to the application device 150 to configure the application device 150 to apply an agricultural product according to the determined trigger value.

[0065] The electronic communication device 130 of the illustrated example may be a desktop, a notebook, a laptop, a mobile phone, a smart phone and / or a PDA. The electronic communication device 130 may comprise a data analysis application, which may be a software application that enables a user to manipulate data extracted from the data management system 110 by the field management system 120 and to select and specify actions to be performed on the individual data. For example, the data analysis application may be a desktop application, a mobile application, or a web-based application. The data analysis application may comprise a user interface, such as an interactive interface including, but not limited to, a GUI, a character user interface, and a touch screen interface. Via the software application, the user may access the field management system 120 using e.g., Username and Password Authentication to obtain an application scheme and / or configuration file usable for configuring the at least one application device 150. The at least one application device 150 is configured to implement a sequence of crop protection measures.

[0066] Although Figure 1 may show a limited number of application devices, it will be appreciated that two or more application devices 150 may be implemented for some applications. In some examples, the at least one application device 150 may comprise an application device configured to implement a chemical measure to eliminate a target by using an agricultural product, such as herbicides, insecticides, fungicides, etc. Exemplary application devices for implementing a chemical measure may include e.g., ground robots with variable-rate applicators, aerial sprayers, or other variable-rate applicators for applying a chemical protection product to the agricultural area. In the example of Figure 5, the at least one application device 150 may be smart farming machinery. The smart farming machinery may be a smart sprayer and includes a connectivity system 152. The connectivity system 152 may be configured to communicatively couple the smart farming machinery 150 to the computing environment.

[0067] It is also possible that such application device comprises sensors (e.g. optical sensors, cameras, infrared sensors, soil sensors, etc.) to provide, for example, a weed distribution map.

[0068] The network 140 of the illustrated example communicatively couples the data management system 110, the field management system 120, the electronic communication device 130, and the at least one application device 150. In some examples, the network 140 may be the internet. Alternatively, the network 140 may be any other type and number of networks. For example, the network 140 may be implemented by several local area networks connected to a wide area network. For example, the data management system 110 may be associated with a first local area network, the field management system 120 may be associated with a second local area network, and the electronic communication device 130 may be associated with a third local area network. The first, second, and third local area networks may be connected to a wide area network. Of course, any other configuration and topology may be utilized to implement the network 140, including any combination of wired network, wireless networks, wide area networks, local area networks, etc. Figure 3 illustrates a flowchart describing a computer-implemented method 300 for providing at least one trigger value for applying an agricultural product on an agricultural field. The at least one trigger value is indicative of an amount of at least one harmful organism per surface unit, which, if exceeded, triggers an application of the agricultural product. The computer-implemented method 200 will be described in connection with the system shown in Figure 1 .

[0069] At block 310, the method 300 comprises the step of providing historical efficacy data of one or more agricultural fields comprising information on efficacies against at least one harmful organism when the agricultural product is appled at at least two different trigger values.

[0070] The historical efficacy data comprises information indicative of an efficacy of the agricultural product against the at least one harmful organism in relation to different trigger values for applying the agricultural product to the one or more agricultural fields.

[0071] The historical efficacy data may come from controlling the success of the application of the agricultural product in the field. This may be done by 1 ) a user providing feedback, 2) data collected in the field trials; and / or 3) a SmartSprayer driving over the same location again after a plurality of days after treatment, such as ~10-14 days after treatment, and recording the weed pressure as compared to the weed pressure at the day of spraying. For example, the efficacy may be calculated using the following equation: . 100 (1 )

[0072] It will be appreciated that the efficacy assessment may be at a different time in days (e.g., ~4 weeks), i.e. with a timely distance, after treatment. The timely difference may depend on a detailed protocol e.g., regarding the weed and the herbicide. The protocol may provide guidelines for efficacy assessments in registrations trials. Different authorities around the world may have different protocols. In some examples, the assessment time after treatment may depend on the type of application. For example, for pre-sowing and pre-emergence applications, 4 weeks after treatment may be the assessment time after treatment. For post-emergence applications, 2 weeks after treatment may be the assessment time after treatment. In some examples, different regions e.g., in different countries may have different protocols for registration trials, differing in how the efficacy is assessed in detail. In some examples, efficacy may be evaluated not only by area as stated, but also by area for the given weed species. For example, herbicide efficacy may need to be assessed for the given weed species.

[0073] The percentual value of the efficacy is determined by deducting the quotient of the detected weed area after the timely distance and the weed area at the day of the treatment. The result is multiplied by 100.

[0074] In an example, the efficacy data may be provided by an evaluation device used for field triels which may detect the the different input values such as “weed area after a plurality of days treatment”, “weed area at day of treatment”, “area sprayed” or “total area”. Such evaluation device may comprise a camera in order to detect the correxpondin areas. In another example efficacy data and the savings data may be provided by a user via a user interface.

[0075] For example, the electronic communication device 130 shown in Figure 1 may comprise a web browser application or other customized programs, applications, or modules configured to interface with the web service provided by field management system 120. Via the web browser application or other customized programs, applications, or modules, the evaluation device and / or user may upload the efficacy data to the field management system 120 using e.g., Username and Password Authentication.

[0076] In another example, the efficacy data may be stored in the data management system 110. The field management system 120 may retrieve the efficacy data from the data management system 110 and then transfer the retrieved data to the data processing apparatus 10 for further processing.

[0077] At block 320, the method 300 further comprises generating at least two trigger values. The generation includes a maximum trigger value determined based on a minimal efficacy of the agricultural product according to the efficacy data and a minimum trigger value determined based on a smallest amount of the at least one harmful organism per surface unit that is detectable by a sensor of the at least one application device. Figure 4 illustrates an exemplary diagram showing efficacy data describing the relation between the efficacy and the trigger values. In the diagram shown, the trigger value as percentage value is shown on the abscissa or X-axis and the efficacy is shown as percentage value on the ordinate or Y-axis.

[0078] The diagram shown in Figure 4 represents, for example, a trigger value for an agricultural product used to control at least one harmful organism, such as herbicides used to control weeds. The trigger value and / or threshold value on the X-axis is indicative of an amount of the at least one harmful organism per surface unit (e.g., 2% weed coverage per square meter), which, if exceeded, triggers an application of the agricultural product, e.g. by opening a valve or nozzle.

[0079] Taking weeds as an example of the at least one harmful organism, the trigger value of 0% may indicate that any weed coverage per square meter that exceeds 0% weed coverage per square meter may trigger an application of the agricultural product. For example, smart sprayers may have camera sensors as sensor configured to detect green plants by differentiating biomass versus soil. This enables them to apply herbicides only where biomass, i.e. weeds, is detected. To do this, the smart sprayer may shutting on and off single nozzles when it is moving across the field. If the trigger value of an application is set to 0% weed coverage per square meter, an application is carried as soon as the detected weed coverage per square meter exceeds 0% weed coverage per square meter. Hence, a trigger value of 0 % may generate savings when exactly no weed is detected in the region of interest of the camera. In the illustrated example, a trigger value indicated with “flat” is shown in Figure 4. The “flat” trigger value means a flat application of the agricultural product. During the flat application of the agricultural product, nozzles of the smart sprayer are always open while driving. The “flat” trigger value is larger than 0%, which may be set to be 0,05%, 0.1 %, 0.15%, or any other trigger value. As the agricultural product will be applied to the entire agricultural field, the highest efficacy will be achieved at the “flat” trigger value. As shown in Figure 4, the efficacy decreases with an increased trigger value. This is because setting low trigger values will maximize efficacy, since all or most harmful organisms will be controlled. In some examples, the minimal efficacy may be defined by a user, e.g., via the electronic communication device 130 shown in Figure 1. In some examples, the minimal efficacy may be obtained from a database or look-up table filled by experts, which may be stored in the field management system 120. In some examples, this value may vary by region or even by grower.

[0080] In some further examples, the at least one harmful organism may comrpise a plurality of harmful organisms of different predefined levels of harm. The minimal efficacy comprises an initial minimal efficacy of the agricultural product against one or more of the plurlatiy of harmful organism of a specified level of harm. The harmful organisms may be predefined with respect to their level of harm. Level of harm may relate to the likelihood of successful treatment, such as the elimination of the harmful organism. Level of harm may relate to the amount or type of crop protection product required to control the organism. Level of harm may relate to the mechanisms to control the organism such as chemical, mechanical, electromagnetically, etc. For example, the initial minimal efficacy may be firstly determined according to a priority harmful organism, which is a harmful organsm of the hishest level of harm. The priority harmful organism is harder to control compared to the standard harmful organism. The priority harmful organisms (e.g., priority weeds) are the ones causing issues. Usually they are 1 ) hard to control and 2) having a negative impact. If they are hard to control (e.g., herbicides don’t work well on them), but don’t have a significant growth, seed production, hazardous effect on the crop growth or harvest process, they may not be priority harmful organisms (e.g., priority weeds). The initial minimal efficacy may be modified based on a user’s feedback and / or at least one condition on the agricultural field. In this way, an initial minimal efficacy is first defined and may be further refined based on a user’s feedback loop and / or according to the condition(s) on the agricultural field.

[0081] Once the minimal efficacy is set (shown as symbol C in Figure 4), the corresponding trigger value can be determined from the diagram shown in Figure 4. For example, if the minimal efficacy of 83 is set, the corresponding trigger value is 0.05%, which is set to be the maximum trigger value for applying the agricultural product.

[0082] The minimum trigger value is determined based on a smallest amount of the at least one harmful organism per surface unit that is detectable by a sensor of the at least one application device. The sensor may comprise an optical sensor providing an image of the field. Suitable optical sensors are multispectral cameras, stereo cameras, IR cameras, CCD cameras, hyperspectral cameras, ultrasonic or LIDAR (light detection and ranging system) cameras, or any combination thereof. The sensor may also include one or more sensors for remote sensing, such as satellite remote sensing, UVA (unmanned aerial vehicle) remote sensing, etc.

[0083] The smallest amount of the at least one harmful organism per surface unit that is detectable by a sensor of the at least one application device is related to the sensitivity of the sensor, such as the sensitivity of an optical camera. As will be explained with respect to the example shown in Figure 5, the smallest amount of the at least one harmful organism per surface unit that is detectable by a sensor of the at least one application device is 0.001 %, and the corresponding savings are 60%. In this example, the value of 0.001 % may be the minimum trigger value for applying the agricultural product.

[0084] Turning back to Figure 3, at block 330, the method 300 further comprise providing the at least two trigger values at least two control and / or monitoring modes, wherein each control and / or monitoring mode has a respective trigger value for monitoring and / or controlling the at least one application device for the application of the agricultural product

[0085] For example, the data processing apparatus 10 shown in Figure 1 may provide the at least two trigger values to one or more of a user output device (e.g., the electronic communication device 130), in an output database (e.g., in the data management system 110), and / or as a control file (e.g., for controlling the application device 150).

[0086] With the Smart Sprayer, the farmers may be given the opportunity to select between Savings mode (focusing on cost efficiency), and Efficacy mode (focusing on weed control). For example, a user interface, e.g., graphfical user interface (GUI), may be provided on the electronic communication device 130 allowing the user to select one trigger value from the two or more trigger values for applying the agricultural product on the agricultural field. Optionally, as shown in Figure 3, at block 310, the method 300 may further comprise providing historical savings data of the one or more agricultural fields comprising information on an amount of the agrilcutrual product saved when the agricultural product is appled at at least two different trigger values. The generation includes a balanced trigger value determined based on the historical savings data.

[0087] The savings data comprises data indicative of agricultural product savings in relation to different trigger values for applying the agricultural product.

[0088] Savings data may come from the application device, e.g. a SmartSprayer or a nozzle. When driving over the field, the as-applied-map is collected and from this map, the total sprayed area can be derived. The savings in area measured for example in ha, then is: 100 (2) ' '

[0089] In other words, the savings in area may be a percentage of the unsprayed area in the total area.

[0090] Figure 5 illustrates an exemplary diagram showing historical savings data describing the relation between the product savings and the trigger value. The historical savings data comprises data obtained from sugar beet fields. In the diagram shown, the trigger value is shown on the X-axis and the product savings compared to the flat application, i.e., trigger value is 0%, are shown on the Y-axis. Compared to Figure 4, which shows the trigger value on the X-axis ranging from 0% to 2%, the trigger value on the X-axis shown in Figure 5 ranges from 0% to 5% in order to show the curve fitting result over a broader range of trigger values.

[0091] The diagram represents, for example, different savings for different trigger values for an agricultural product used to at least one harmful organism. Such agricultural product may be herbicides used to control weeds as harmful organism. With mixed harmful organisms of different levels of harm (e.g., one easy to control and one hard to control weed), the trigger value may be set to the hard-to-control harmful organism in order to control all harmful organisms). A low trigger value is equivalent to a small area of the harmful organisms per surface unit. A low trigger value therefore means that a small area of harmful organisms will exceed the trigger and the nozzle will be turned on. For example, if the trigger value of an application is set to be a low trigger value, e.g., 0.02% weed coverage per square meter, an application is carried as soon as the detected weed coverage per square meter exceeds 0.02% weed coverage per square meter. On the other hand, if the trigger value of an application is set to be a high trigger value, e.g., 0.2% weed coverage per square meter, an application is carried as soon as the detected weed coverage per square meter exceeds 0.2% weed coverage per square meter. Therefore, setting a low trigger value for the application of the agricultural product effectively means a high weed control to be applied to a lot of areas whereas easy to control weeds will have a high trigger value. Accordingly, depending on the level of the trigger value, the agricultural product is applied at low coverage of the at least harmful organism, i.e. having a high trigger value, or at higher coverage of the at least one harmful organism, i.e., having a low trigger value. As shown in Figure 5, the savings increase with an increased trigger value. This is because setting larger trigger values will maximize savings, since less weeds and thus area will be sprayed and consequently less agricultural product may be used.

[0092] In the diagram shown in Figure 5, the area 50 represents the range of the observed data, within which the observed data points (not shown) are located. In order to better reflect the relation between the observed savings data and the trigger value, a function is provided to fit a curve to the savings data to obtain a fitted function.

[0093] An example of the function used to be fitted in the range of observed data is a segmented quadratic function. In some examples, the segmented quadratic function may be a sigmoid function.

[0094] In some examples, the segmented quadratic function may be a four-parameter log- logistic function: f(x)' = c + - (3);

[0095] Jl+exp (fc(log(x)-log (e)))

[0096] In some examples, the segmented quadratic function may be a Weibull function (1 ): (%) = c + (d - c)(l - exp(— exp (b(log(x) - log (e))))) (4)

[0097] In some examples, the segmented quadratic function may be a Weibull model (2) (%) = c + (d - c)(l - exp(— exp (b(log(x) - log (e))))) (5)

[0098] In the above functions, y is the spraying savings, x is the trigger value, b is the slope at the infection point, c is the lower limit of the model, d is the upper limit, and e is the infection point.

[0099] In the diagram shown in Figure 5, a four-parameter log-logistic function according to equation (3) is provided to fit a curve to the savings data. Of course, other segmented quadratic functions, such as equations (4) and (5) may also be used to fit the curve to the savings data. In some examples, the user may select one of the above-described segmented quadratic functions to fit the curve. In some examples, one of the abovedescribed segmented quadratic functionsmay be a default equation in the system.

[0100] It will be appreciated that other segmented quadratic functions, such as the abovedescribed Weibull functions may also be used to fit the savings data.

[0101] The generation includes a balanced trigger value determined based on the historical savings data. When the agricultural product is applied at the balanced trigger value, a predefined balanced relationship between savings of the agricultural product and efficacy of the agricultural product is achieved.

[0102] As an example, the balanced trigger value comprises a trigger value at which the savings have a highest growth rate. In this illustrated example, the balanced trigger value corresponds to an inflection point on the curve where a curvature changes direction, slope or signs, and the balanced trigger value may be determined as follows.

[0103] Further referring to the example shown in Figure 5, by fitting the four-parameter log- logistic function to the savings data, in particular to the savings trial data, the parameters b, c, d and e of the four-parameter log-logistic function can be determined.

[0104] The parameter e is the trigger value belonging to infection point. In the diagram shown, the balanced trigger value is equal to the inflection point, i.e. parameter e, of the four- parameter log-logistic function, which is 0.05% shown in Figure 5 and corresponding to savings of 65.9%. In other words, if x of the four-parameter log-logistic function is equal to 0.05%, f(x) is equal to 65.9%. In Figure 5, the balanced trigger value is indicated with the symbol B on the savings curve.

[0105] As shown in Figure 5, the trigger value of 0.0016% is the minimum trigger value, which corresponds to the savings of 48.8%.

[0106] It is noted that the balanced trigger value may be generated differently in a different way compared to the above described detmining of the inflection point. This way of determining the balanced trigger value will be explained in Figure 6.

[0107] For example, the generation may include determining a balanced trigger value based on the minimum trigger value and the maximum trigger value. For example, the savings for the balanced trigger value are determined by taking an average of the savings for the minimum trigger value and the savings for the maximum trigger value. In other words, the balanced trigger value may be set to have the following agricultural product savings:

[0108] In the above equation, savings_balanced represents the agricultural product savings at the balanced trigger value, savings_minimum represents the agricultural product savings at the minimum trigger value, and savings_maximum represents the agricultural product savings at the maximum accepted efficacy . Based on the savings for the balanced trigger value, the balanced trigger value may be determined by intersecting the savings for the balanced trigger value with the savings curve. This will be described in detail hereinafter and in particular with respect to Figure 6.

[0109] In some implementations, the at least two trigger values may differ between different agricultural fields. To this end the method 300 shown in Figure 6 may comprise an optional step of providing historical condition data of the one or more agricultural fields. Historical condition data may relate to different conditions of the filed as will be described below. The generation includes maximum trigger values for at least two different conditions determined based on a defined minimal efficacy of the agricultural product according to the historical efficacy data and the historical condition data. The generation may further include balanced trigger values for the at least two different conditions determined based on the historical savings data and the historical condition data or based on the minimum trigger values and the at least two maximum trigger values. The optional steps will be explained in connection to Figure 6.

[0110] Figure 6 illustrates an example of adapting the trigger value to at least one condition on the agricultural field based on historical data. In a first step, historical efficacy data, and historical savings data are provided. As shown in Figure 6, the savings increase with an increased trigger value. This is because setting larger trigger values, i.e. absolute trigger values that lay higher then the flat rate application rate, will maximize savings, since less weeds and thus less area will be sprayed leading to less agricultural product consumption. On the other hand, the efficacy decreases with an increased trigger value. It is assumed that the efficacy curve 602 is a permanently decreasing curve along the abscissa. The efficacy decreases with an increased trigger value because setting higher trigger values will decrease the amount of application product, and may prevent that all or most weeds will be sprayed. In other words, higher trigger value spray less weed and thus more weed may grow.

[0111] The first step shown in Figure 6 corresponds to step 310 shown in Figure 6. In the first step, efficacy data 602 and savings data 601 are provided. These data may comprise trial data collected from one or more country-crop specific trials on one or more agricultural fields. As shown in the first figure in Figure 6, the savings data 601 and efficacy data 602 are plotted in the same diagram to bring it to the same scale, i.e. trigger values on the X- axis. In this way a normalization to the trigger values of the data may be achieved.

[0112] In a second step, at least two trigger values are generated, such as a minimum trigger value 604 for applying the agricultural product on the agricultural field, and a maximum trigger value 609 for applying the agricultural product on the agricultural field shown in Figure 6. Additionally, in the illustrated example a balanced trigger value 608 is generated. Each trigger value is indicative of an amount of at least one harmful organism per surface unit (e.g., 2% weed coverage per square meter). The three trigger values on the X-axis or abscissa are indicated with respective arrows terminated with symbols A, B, and C. Accordingly, the three trigger values may also be referred to trigger value A, trigger value B, and trigger value C in the following. The symbols A and B are located on the savings curve 601 , showing the corresponding savings of trigger value A and B. The symbol C is located on the efficacy curve 602, showing the corresponding efficacy.

[0113] As will be discussed below, the efficacy corresponding to the trigger value C is the minimal efficacy accepted by a user.

[0114] The minimum trigger value may also be referred to as trigger value for max efficacy, shown as trigger value A in Figure 6. The minimum trigger value A is determined based on a smallest amount of the at least one harmful organism per surface unit that is detectable by a sensor of the at least one application device. As the sensor, such as an optical camera or other detection unit, may be manufactured by different Original Equipment Manufacturers (OEM), the sensor may have a lowest detection trigger value setting that is dependent on the OEM. In Figure 6, the minimum trigger value may also be referred to OEM trigger value, which may be the smallest quantity of at least one harmful organism per surface unit that can be detected by the sensor, e.g., an optical camera. In other words, this trigger value may be set by the dimensions of the agricultural device used for applying the application product.

[0115] As described above, the balanced trigger value B may be determined based on the historical savings data. The balanced trigger value may be a trigger value at which the savings have a highest growth rate. Alternatively (not shown in Figure 5), the savings of the balanced trigger value may be an average of the savings of the maximum trigger value and the savings of the minimum trigger value. In the illustrated example, the balanced trigger value is indicated by the symbol B on the savings curve.

[0116] In one example where the savings curve may have an inflection point the balanced value B may be set as the trigger value that may correspond to the infection point B of the savings curve. A savings curve may have an inflection point if a better fitting may be reached than with a curve without an inflection point. It is noted that the example of a saving curve fitted with a curve having an inflection point is not shown in Figure 6.

[0117] In a further example the trigger value of the minimal accepted efficacy may be determined, in order to ensure that the trigger value of the balanced point B does not exceed the trigger value of the minimal accepted efficacy C. In this way the minimum and maximum trigger values A and C, respectively are used for limiting the allowed trigger values and / or the value range for the balanced setup. Within this range a user may vary a suggested trigger value B setting wherein the suggested trigger value may be based on the balanced setup.

[0118] In this way the example as shown in Figure 6, where the savings curve does not have an inflection point or is inflection point free, as shown with savings curve 601 , an alternative method compared to the method as described in Figure 5 may be used for determining the balanced trigger value B. In that case savings curve 601 and efficacy curve 602 are drawn in the same diagram 603. Both the saving values and the efficacy values are scaled to the same ordinate in percentatge. The efficacy values may be a percentage of the weed pressure after a plurality of days after treatment, such as ~10-14 days after treatment, in relation to the weed pressure at the day of spraying. As an example, the efficacy values may be determined using equation (1 ) above. The savings in area may be a percentage of the unsprayed area in the total area. For example, the savings values may be determined using equation (2) above.

[0119] The minimum trigger value A, 604 is determined at the OEM trigger value and a correpsoninding minimum savings value 605 is determined based on the savings curve 601. Thus, the minimum trigger value A, 604 may substantially be defined by the dimension and / or configuration of the application device 130. The maximum allowable trigger value is set by the user at the minimum acceptable efficacy value C on the efficacy curve 602. This value C may be projected to the savings curve 601 at the same trigger value 609 as shown at maximum reachable savings value C’. C’ corresponds to the savings at the maximum allowable threshold value. In other words, C and C’ are located at the same trigger values 609. The savings value for C’ is determined and the savings

[0120] 606 for the balanced point is determined on the savings scale on the ordinate by determining the savings value 605 of A, the savings value 606 of C’ and forming the average or medium savings value 607. Based on the average saving value 607 the trigger value 608 for the balanced mode is determined by intersecting the average savings value

[0121] 607 with the savings curve 601 . The medium savings value may substantially correspond to the half distance d. In an example, it is verified that the corresponding trigger value 608 does not exceeed the maximum acceptable triggervalue 609.

[0122] The maximum trigger value C, 609 may be referred to as trigger value for max savings, shown as trigger value 609 in Figure 6. Accordingly, trigger value A 604 is the lowest trigger value and may be set in order to achieve max efficacy in Figure 6, and trigger value C, 609 is the maximum trigger value to achieve the minimal accepted efficacy C in Figure 6.

[0123] It will be appreciated that the minimal efficacy may be modified based on a user’s feedback loop and / or according to the condition(s) on each individual agricultural field. Therefore, the trigger value C may be adapted to be higher or lower than the trigger value C shown in Figure 6.

[0124] The second step shown in Figure 6 may be performed based on the description with respect to step 320 shown in Figure 3. For example, a maximum trigger value for applying the agricultural product on the agricultural field is determined based on the efficacy data and a minimal efficacy of the agricultural product. A function is provided to fit a curve to the savings data to obtain a fitted function without inflection point to better reflect the relation between the observed savings data and the trigger value. A minimum trigger value for applying the agricultural product on the agricultural field is determined based on the fitted function and a smallest detectable unit provided by a sensor configured to detect the at least one harmful organism in the agricultural field. A balanced trigger value is set for applying the agricultural product on the agricultural field between the minimum trigger value and the maximum trigger value.

[0125] In third and fourth steps, the user of one or more agricultural fields may select a trigger value from the minimum trigger value, the balanced trigger value, and a maximum trigger value for each of the one or more agricultural fields. The selected trigger value may be applied to on a single agricultural field. This corresponds to step 330 shown in Figure 6, which provides the at least two trigger values for selecting a control and / or monitoring mode of at least one application device configured to apply an agricultural product to an agricultural field according to the selected a control and / or monitoring mode.

[0126] In a fifth step, the third and fourth steps may be repeated to collect appropriate amount of data. In addition, the user’s feedback may be collected to adjust one or more trigger values.

[0127] In a sixth step, historical condition data of the one or more agricultural fields is provided. The generation includes at least two maximum trigger values for at least two different conditions determined based on a defined minimal efficacy of the agricultural product according to the historical efficacy data and the historical condition data.

[0128] For example, as shown in Figure 6, the historicial condition data may comprise data obtained in substantially each crop-country may be used to further differentiate conditions and / or parameters according to condition and management parameters, which may be obtained from one or more of the following data: soil data, machine data, environmental data, crop management data, field data, harmful organism data on the agricultural field, and crop variety data relating to a crop grown or to be grown on the agricultural field. As will be discussed below, for a given agricultural field, the most applicable set of trigger values (A, B, and C) may be further refined by the one or more of the above data obtained from that single agricultural field.

[0129] In other words, the more parameter and / or conditions are known for a field the more precisely the appropriated curve 60T, 602’, 601 ”, 602”, 60T”, and 602’” from the set of curves may be selected. In an example the curve pairs savings curve 60T and efficacy curve 602’ may belong to a different soil type than savings curve 601 ” and efficacy curve 602”. The different data may be taken from different trial fields and / or plots. In other words, different parameter and / or condition combinations may lead to different selctions of curve pairs. Each curve pair may correspond to a different parameter and / or condition and therefore may have different condition specific and / or parameter specific minimum, maximum and / or balanced trigger values. In an example the parmeter may be detected by remote sensing, by a database request and / or a user input. A field management system may be able to determine an appropriate balanced trigger for a combinaton of a specific agricultural device and a location, a condition and / or state of a field or a combination of fields.

[0130] The soil data is indicative of a soil condition on the agricultural field. This may include soil fertility or soil pH, soil compaction, excessive thatch, and water content, which may affect the development of e.g., weeds.

[0131] The machine data is indicative of a machine for applying the agricultural product on the agricultural field may be provided. Exemplary machinery may include, but not limited to, drone, sprayer with a single tank, and sprayer with multiple tanks.

[0132] The environmental data is indicative of an environmental condition on the agricultural field may be provided. Environmental data, like weather conditions, may have an influence on the development of certain harmful organisms. For example, warm and humid weather may favour the development of some weeds. The weather data can be provided by a third party, e.g. a service provider, or by on-site sensors. Other data about the crop environment may also be obtained e.g. from on-site sensors like moisture sensor, pH sensor, pressure sensor, soil sensor, water sensor, cameras, or any combination thereof.

[0133] The crop management data is indicative of an application history of an agricultural product for the agricultural field may be provided. The crop management data indicative of application history of agricultural product(s) for the agricultural field. The crop management data may be obtained from a data management system that stores the history of applications of agricultural products for the agricultural field.

[0134] In an example, field data of the agricultural field may be provided. The field data may include georeferenced data of different agricultural areas and the associated treatment map(s). The field data may comprise information about one or more of the following information: crop present on the field (e.g. indicated with crop ID), the crop rotation, the location of the field, previous treatments on the field, sowing time, etc.

[0135] In an example, harmful organism data on the agricultural field may be provided. The harmful organism data may comprise one or more of the following information: distribution of the harmful organism by locality, level of infestation (e.g., 0%-100%), sources of infestation (e.g., weed species, pest species), and life stages.

[0136] In an example, crop variety data relating to a crop grown or to be grown on the agricultural field may be provided. Exemplary crop variety data may include, but is not limited to, growth stage at a specific time point, crop density (i.e. number of crops present per unit area of the field), and days after plantation.

[0137] In this way, one or more agronomical factors, such as crop, crop rotation, weed species, herbicide resistant weeds, weed infestation pressure, herbicide spraying program, herbicide used, crop growth stage, weed growth stage, application timing, crop row spacing, soil texture, tillage practices, crop residue amount, precipitation, soil moisture, crop herbicide tolerant traits, region, and / or other agronomical factors, may be obtained. The one or more agronomical factors may have an influence on one or more trigger values, and therefore the one or more trigger values may differ between different agricultural fields.

[0138] For example, as shown in Figure 6 more refined trigger values belonging to the points “B” and “C” may be obtained for different conditions of e.g. soil, weeds, weather, location, row width and / or other conditions. In the example shown in Figure 6, more refined trigger values “B” and “C” are shown for different soil conditions, such as trigger values “B1” and “C1” for sandy soil, trigger values “B2”, “C2” for loamy soil, and trigger values “B3” and “C3” for clay soil.

[0139] In a seventh step, for a given agricultural field, the most applicable set of trigger values (Bi, Ci) from the sixth step may be further refined by data from that single agricultural field. For this, functions Bi and Ci are re-adjusted to fit to single field observations or a user’s feedback. For example, the minimal efficacy may come from the user’s feedback loop. An initial minimal efficacy can be set according to basic classification of weeds into priority weeds (e.g., hard-to-control weeds) and standard weeds, and may be refined based on the user’s feedback.

[0140] In one example, a data-driven model may be applied to adapt the trigger value to the at least one condition on the agricultural field. The data-driven model may be a machine learning algorithm. The machine learning algorithm may be a deep learning algorithm, such as deep neural networks, convolutional deep neural networks, deep belief networks, etc. The data-driven model may have been trained using the historical data e.g., obtained from the above-described first to fifth step. In order to train the data-driven model, a training dataset is collected, which comprises historical data describing at least one condition on one or more agricultural fields and the at least one trigger value for applying an agricultural product on the one or more agricultural fields. As noted above, the at least one condition may include one or more of (i) historical soil data indicative of a soil condition on the one or more agricultural fields, (ii) historical machine data indicative of a machine for applying the agricultural product on the one or more agricultural fields, (iii) historical environmental data indicative of an environmental condition on the one or more agricultural fields, (iv) historical crop management data indicative of an application history of an agricultural product for the one or more agricultural fields, (v) field data of the one or more agricultural fields, (vi) historical harmful organism data on the one or more agricultural fields, and (vii) historical crop variety data relating to a crop grown or to be grown on the one or more agricultural fields. The at least one trigger value comprises one or more of a minimum trigger value for applying an agricultural product on the one or more agricultural fields, a maximum trigger value for applying the agricultural product on the one or more agricultural fields, and a trigger value used for applying the agricultural product on the one or more agricultural fields. The training dataset is thus {condition(s), trigger value(s)} with the number of agricultural fields as N. The data-driven model, such as neural networks, is then established, with condition(s) on each agricultural field as input and trigger values (s) on the respective agricultural field as target labels to train the data-driven model, so that for a new agricultural field k, the condition(s)_k indicative of at least one condition on the agricultural field k can be used to determine at least one trigger value, such as trigger values “A”, “B”, and / or “C” for the agricultural field k through the data-driven model. The data-driven model is then established, with condition(s) as input and trigger value(s) as target labels to train data-driven model. In another example, instead of applying a data-driven model, a trigger value Adaption table may be provided to reflect the agronomic factor’s influence on the trigger values. For example, Figure 7 illustrates an exemplary trigger value Adaption table, which comprises the following data: key weed species, crop, crop growth stage, crop herbicide traits, tillage, and cover crop / residue, and their influences on the trigger value “B”. As shown in Figure 7, concerning the key weed species, if any one of palmer amaranth, waterhemp, common ragweed, and giant ragweed is selected, a value of 0.25 will be reduced from the determined balanced trigger value “B”, 608. If a com is grown or to be grown on the agricultural field, a value of 0.1 will be added to the trigger value “B”, while if a soybean is grown or to be grown on the agricultural field, no change is made. The trigger value “B” also increases with the number of crop herbicide traits. In particular, a value of 0.25 will reduced from the trigger value “B” with no traits, while a value of 0.1 will be added to the trigger value “B” with three traits. As shown, the trigger value “B” may also be adapted to different tillages and different residues. For example, it is possible to obtain an applicable set of trigger values (A, B, and C) based on the above-described method. Then, the condition of a particular agricultural field may be considered to refine the applicable set of trigger values. For example, based on the information such as key weed species, crop, crop growth stage, crop herbicide traits, tillage, and cover crop / residue of that said agricultural field, the farmer may look for a correction value in the trigger value Adaption table shown in Figure 7 to refine one or more of the trigger values.

[0141] Figure 8 shows exemplary savings as influenced by trigger value settings for sugar beet and com. It can be seen from Figure 8 that the non-linear regression and their parameters are different between com and sugar beet fields. In these examples, fitting curves having an inflection point may be used. In particular, the minimum trigger value and the balanced trigger value for the sugar beet field have values of 0.0016% and 0.6%, respectively, and the balanced trigger value is 0.05%, which is indicated with the symbol B on the savings curve. On the other hand, the minimum trigger value and the maximum trigger value for the com field have values of 0.0016% and 1.5%, respectively, and the balanced trigger value is 0.6%, which is indicated with the symbol B on the savings curve. These differences reflect agronomic factor’s influence on the parameters of the trigger value And savings equation using e.g., machine learning approaches or trigger value Adaption table as described above. In this way, the trigger values “A”, “B”, and / or “C” may be determined, therefore defining the Efficacy, Balanced, and Savings mode for individual fields depending on their individual characteristics.

[0142] Aspects of the present disclosure relates to computer program elements configured to carry out steps of the methods described above. The computer program element might therefore be stored on a computing unit of a computing device, which might also be part of an embodiment. This computing unit may be configured to perform or induce performing of the steps of the method described above. Moreover, it may be configured to operate the components of the above described system. The computing unit can be configured to operate automatically and / or to execute the orders of a user. The computing unit may include a data processor. A computer program may be loaded into a working memory of a data processor. The data processor may thus be equipped to carry out the method according to one of the preceding embodiments. This exemplary embodiment of the present disclosure covers both, a computer program that right from the beginning uses the present disclosure and computer program that by means of an update turns an existing program into a program that uses the present disclosure. Moreover, the computer program element might be able to provide all necessary steps to fulfill the procedure of an exemplary embodiment of the method as described above. According to a further exemplary embodiment of the present disclosure, a computer readable medium, such as a CD-ROM, USB stick, a downloadable executable or the like, is presented wherein the computer readable medium has a computer program element stored on it which computer program element is described by the preceding section. A computer program may be stored and / or distributed on a suitable medium, such as an optical storage medium or a solid state medium 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. However, the computer program may also be presented over a network like the World Wide Web and can be downloaded into the working memory of a data processor from such a network. According to a further exemplary embodiment of the present disclosure, a medium for making a computer program element available for downloading is provided, which computer program element is arranged to perform a method according to one of the previously described embodiments of the present disclosure. The present disclosure has been described in conjunction with a preferred embodiment as examples as well. However, other variations can be understood and effected by those persons skilled in the art and practicing the claimed invention, from the studies of the drawings, this disclosure and the claims. Notably, in particular, the any steps presented can be performed in any order, i.e. the present invention is not limited to a specific order of these steps. Moreover, it is also not required that the different steps are performed at a certain place or at one node of a distributed system, i.e. each of the steps may be performed at a different nodes using different equipment / data processing units.

[0143] In the claims as well as in the description the word “comprising” does not exclude other elements or steps and the indefinite article “a” or “an” does not exclude a plurality. A single element or other unit may fulfill the functions of several entities or items recited in the claims. The mere fact that certain measures are recited in the mutual different dependent claims does not indicate that a combination of these measures cannot be used in an advantageous implementation.

Claims

Claims1. A computer-implemented method for generating a trigger value for monitoring and / or controlling at least one application device configured to apply an agricultural product to an agricultural field, wherein the trigger value relates to a field condition to be treated by the agricultural product, the method comprising: providing (310) historical efficacy data of one or more agricultural fields comprising information on efficacies against at least one harmful organism when the agricultural product is applied at at least two different trigger values; generating (320) at least two trigger values, wherein the generation includes a maximum trigger value determined based on a minimal efficacy of the agricultural product according to the historical efficacy data and a minimum trigger value determined based on a smallest amount of the at least one harmful organism per surface unit that is detectable by a sensor of the at least one application device; and providing (330) the at least two trigger values for at least two control and / or monitoring modes, wherein each control and / or monitoring mode has a respective trigger value for monitoring and / or controlling the at least one application device for the application of the agricultural product.

2. The computer-implemented method according to claim 1 , further comprising providing historical savings data of the one or more agricultural fields comprising information on an amount of the agrilcutrual product saved when the agricultural product is applied at at least two different trigger values, wherein the generation includes a balanced trigger value determined based on the historical savings data, wherein when the agricultural product is applied at the balanced trigger value, a predefined balanced relationship between savings of the agricultural product and efficacy of the agricultural product is achieved.

3. The computer-implemented method according to claim 2, wherein the balanced trigger value comprises a trigger value at which the savings have a highest growth rate.

4. The computer-implemented method according to claim 1 , wherein the generation includes a balanced trigger value determined based on the minimum trigger value and the maximum trigger value.

5. The computer-implemented method according to claim 4, wherein the savings of the balanced trigger value are an average of the savings of the maximum trigger value and the savings of the minimum trigger value.

6. The computer-implemented method according to any one of the preceding claims, further comprising: providing historical condition data of the one or more agricultural fields, wherein the generation includes at least two maximum trigger values for at least two different conditions determined based on a defined minimal efficacy of the agricultural product according to the historical efficacy data and the historical condition data.

7. The computer-implemented method according to claim 6, wherein the generation includes at least two balanced trigger values for the at least two different conditions determined based on the historical savings data and the historical condition data or based on the minimum trigger values and the at least two maximum trigger values.

8. The computer-implemented method according to any one fo the preceding claims, wherein the minimal efficacy of the agricultural product comprises a user- defined minimal efficacy for generating the maximum trigger value.

9. The computer-implemented method according to any one of the preceding claims, wherein the at least one harmful organism comprises a plurality of different harmful organisms; and wherein the minimal efficacy comprises an initial minimal efficacy of the agricultural product against one or more of the plurlatiy of harmful organism of a specified level of harm. .

10. The computer-implemented method according to claim 9, further comprising: modifying the initial minimal efficacy based on an input received from a user interface and / or condition data of the agricultural field to be treated.

11. The computer-implemented method according to any one of the preceding claims, further comprising: providing a user interface allowing a user to select a control and / or monitoring mode of at least one application device configured to apply an agricultural product to an agricultural field12. The computer-implemented method according to any one of the preceding claims, further comprising: providing control data for controlling application means of at least one application device, wherein the control data comprises the at least one trigger value for applying the agricultural product on the agricultural field.

13. A data processing apparatus (10) comprising a processor adapted to perform the steps of the method of any one of the preceding claims.

14. A harmful organism management system (200), comprising: the data processing apparatus according to claim 13 configured to provide at least two trigger values for at least two control and / or monitoring modes, wherein each control and / or monitoring mode has a respective trigger value for monitoring and / or controlling at least one application device for an application of an agricultural product; and an application device configured to apply the agricultural product to the agricultural field according to a control and / or monitoring mode selected from the at least two control and / or monitoring modes.

15. A computer-readable storage medium comprising instructions which, when executed by a processor, cause the processor to carry out the steps of the method according to any one of claims 1 to 12.

Images