Apparatus for generating an application scheme for controlling a harmful organism on an agricultural field

Abstract

The present invention relates to digital farming. In order to support seasonal recommendations and planning, an apparatus (10) for generating an application scheme for controlling a harmful organism on an agricultural field. The apparatus comprises an input unit (12), a processing unit (14), and an output unit (16). The input unit (12) is configured to receive information on an expected presence of the harmful organism for an upcoming period. The processing unit (14) is configured to determine a rough control schedule comprising a plurality of control time periods for controlling the harmful organism, based on the information about an expected presence of the harmful organism for the upcoming period; determine, based on product data that comprises information on a plurality of agricultural products, at least one program of control measures to be sequentially applied to the agricultural field to control the harmful organism at the plurality of control time periods, wherein each control time period is associated with at least one respective control measure selected from a chemical measure or a mechanical measure; and generate the application scheme that comprises the determined rough control schedule with the plurality of control time periods and / or the at least one program of control measures. The output unit (16) is configured to provide the generated application scheme.

Description

[0001] APPARATUS FOR GENERATING AN APPLICATION SCHEME FOR CONTROLLING A HARMFUL ORGANISM ON AN AGRICULTURAL FIELD

[0002] FIELD OF THE INVENTION

[0003] The present invention relates to digital farming. In particular, the present invention relates to a computer-implemented method and an apparatus for determining a sequence of crop protection measures to be implemented across a season on an agricultural field, a target management system, a computer program product, and a computer-readable storage.

[0004] BACKGROUND OF THE INVENTION

[0005] In crop protection, products, active ingredients, and mode of actions are suitable to control a limited number of targets, such as weeds, diseases, pests, etc. at specific conditions. During season, the presence or the expected presence of targets is determined and suitable crop protection products may be selected to control the target in an ad hoc manner. However, continuous ad hoc section of crop protection products may not reach the best control across the season, since the added and / or combined usage of products, active ingredients, and / or mode of actions across multiple applications may provide better control. In addition, the continuous ad hoc selection of crop protection products may apply larger doses than necessary.

[0006] SUMMARY OF THE INVENTION

[0007] There may be a need to provide a recommendation method and system, which support seasonal recommendations and planning.

[0008] The objective of the present invention is solved by the subject-matter of the independent claims, wherein further embodiments are incorporated in the dependent claims.

[0009] According to a first aspect of the present invention, there is provided an apparatus for generating an application scheme for controlling a harmful organism on an agricultural field. The apparatus comprises an input unit, a processing unit, and an output unit. The input unit is configured to receive information on an expected presence of the harmful organism for an upcoming period. The processing unit is configured to determine a rough control schedule comprising a plurality of control time periods for controlling the harmful organism, based on the information about an expected presence of the harmful organism for the upcoming period. The processing unit is further configured to determine, based on product data that comprises information on a plurality of agricultural products, at least one program of control measures to be sequentially applied to the agricultural field to control the harmful organism at the plurality of control time periods. Each control time period is associated with at least one respective control measure selected from a chemical measure or a mechanical measure. In other words each control time period may be associated with a respective chemical measure or a mechanical measure. The processing unit is further configured to generate the application scheme that comprises the determined rough control schedule and / or the at least one program of control measures. The output unit is configured to provide the generated application scheme.

[0010] In some implementations, the application scheme may be generated before season start or before starting the crop protection program.

[0011] Accordingly, one or more harmful organisms (e.g., weeds, diseases, pests) to be expected on the agricultural field are estimated e.g., before season start or starting the crop protection program. The one or more expected harmful organisms can determine a rough control schedule, which comprises a sequence of control time periods for controlling the one or more harmful organisms. Then, the rough control schedule is further detailed out in a program (e.g., herbicide program, fungicide program, pesticide program, etc.) comprising a detailed sequence of mechanical measures and / or chemical applications to be applied at these control time periods. An application scheme can thus be generated based on the program. The generation of the application scheme may be carried out at any point in time and may be for example done due to agronomical, logistical, and / or commercial reasons before the season start. In an example a time period covered by the rough control schedule substantially may correspond to a season. Thus, the application scheme may be provided before a start time of the rough control schedule.

[0012] An exemplary apparatus for generating an application scheme for controlling a harmful organism is shown in FIG. 1.

[0013] In some examples, the processing unit is configured to determine a result of controlling the harmful organism with the at least one program of control measures, and generate the application scheme if the result of controlling the harmful organism meets a predefined management goal for the upcoming period.

[0014] Accordingly, the apparatus may consider the overall expected program-product performance for the entire upcoming period, and can pair different mechanical measures and / or chemical applications across different control time periods to achieve the predefined management goal after the program of control measures is implemented. The management goal may be a predefined growing goal of the agricultural crop plant on the agricultural field under prediction of environmental conditions. The predefined growing goal may be defined as a predefined amount of a crop grown. Alternatively or additionally, the management goal may be a predefined level of infestation to be achieved after application of the at least one program of control measures for the upcoming period. In some examples, the input unit is configured to receive one or more of the following information on the agricultural field: soil data indicative of a soil condition of the agricultural field, crop variety data relating to a crop grown or to be grown on an agricultural field for the upcoming period, environmental data indicative of an environmental condition on the agricultural field for the upcoming period, crop management data indicative of agricultural product application history on the agricultural field, and location data of the agricultural field. The processing unit is configured to determine a detailed control schedule with the plurality of control time periods determined based on the information on the expected presence of the harmful organism and the information on the agricultural field. The generated application scheme comprises the determined detailed control schedule with the plurality of control time periods and / or the at least one program of control measures.

[0015] With one or more of the above information on the agricultural field, the control time periods may be tailored to a specific agricultural field to achieve a more efficient control of the harmful organism.

[0016] In some examples, each of the plurality of time periods is a portion of a defined crop growing season.

[0017] In some examples, at least one chemical measure comprises a list of agricultural products suitable for controlling the harmful organism at one or more control time periods. The processing unit is configured to select an agricultural product from the list based on at least one predefined criterion.

[0018] Accordingly, when detailing out the exact application scheme, the apparatus may need to account for various criteria to improve the control of the harmful organism.

[0019] For example, agricultural products, active ingredient, and / or mode of action that have been used earlier already may not be repeatedly used for the upcoming period for a better resistance management.

[0020] For example, if the farmer has a large stock of a particular agricultural product suitable for controlling the harmful organism at one or more control time periods, the particular agricultural product may be selected. In some examples, the at least one predefined criterion comprises one or more of: information about agricultural product rotation, information about resistance prevention, and information about a type and / or a quantity of an agricultural product on stock.

[0021] In an example the at least one program of control measures may be selected based on the available agricultural product on stock and an alternative substantially comparable program of control measures may be dismissed. In other words, in a case where a program of control measures is suggested that may not match the available type and / or quantity of an agricultural product on stock, this suggested program of control measures may be replaced by a program that matches the available type and / or quantity of an agricultural product on stock.

[0022] In some examples, at least one chemical measure comprises a list of agricultural products suitable for controlling the harmful organism at one or more control time periods. The processing unit is configured to rank the agricultural products based on associated control efficacies on the harmful organism.

[0023] In some examples, the at least one program of control measures comprises a plurality of different programs of control measures suitable for controlling the harmful organism at the plurality of control time periods. The processing unit is configured to rank the plurality of different programs of control measures based on a predefined ranking criterion and to select one program of control measures for the application scheme based on the ranking.

[0024] Accordingly, the apparatus may also account for interdependencies of applications and determine suitable application sequence, the agricultural product(s) for each application, and rank suitable programs.

[0025] In some examples, the predefined ranking criterion comprises one or more of: a crop yield, a level of resistance of the harmful organism to the at least one program of control measures, information about a type and / or a quantity of an agricultural product on stock, and information about a machine on stock.

[0026] In some examples, the plurality of different programs of control measures comprise at least two programs of control measures generated for different harmful organism management scenarios, each harmful organism management scenario corresponding to a respective predefined harmful organism infestation condition. For example, the predefined harmful organism infestation condition may be defined using one or more of the following parameters: distribution of the harmful organism by locality, level of infestation (e.g., 0%-100% or abundance per area, e.g. plants / m2, or development stage of infestation, e.g. weed size or growth stages), sources of infestation (e.g., pest species, weed specifies, fungal disease specifies), and resistance of the harmful organism to the agricultural product. Different harmful organism management scenario correspond to different harmful organism infestation conditions with at least one predefined different parameter ranges. As an example, exemplary weed management scenarios may include one or more of: a heavy weed infestation scenario, a standard weed composition scenario, a scenario for a high pressure of resistant weed plus some broadleaf weeds, and a critical grass weed scenario.

[0027] The plurality of control time periods of different programs of control measures may be concatenated and / or at least partially overlapped. In this way, it is possible to switch to a different program of control measures to update the application scheme, if needed.

[0028] In some examples, the input unit is configured to receive data indicative of an occurrence of an event during an execution of the selected program of control measures or after an execution of the selected program of control measures. The processing unit is configured to determine whether the event has caused or is expected to cause a change of a planned result of controlling the harmful organism. The processing unit is configured to determine whether the change of the planned result of controlling the harmful organism has resulted in or is expected to result in a change of harmful organism infestation condition. In response to determining that the change of the planned result of controlling the harmful organism has resulted in or is expected to result in a change of harmful organism infestation situation, the processing unit is configured to select another program of control measures with the harmful organism management scenario corresponding to the changed harmful organism infestation condition. The output unit is configured to provide the another selected program of control measures as an updated application scheme.

[0029] The event may be an event that has caused or is expected to cause a change of an expected or planned result of controlling the harmful organism. In some examples, the event may include an application error. For example, one crop protection measure did not take place as planned in the application scheme. For example, one crop protection measure was carried out differently than planned in the application scheme. In some examples, the event may include in-season changes. For example, the environmental condition, e.g., weather condition, changes and is different from the predicted environmental condition. For example, dry weather and spotty rains may impact both herbicide effectiveness. The change of environmental condition may cause that weed emergence risk surpassing or exceeding threshold. E.g., within a given control time period the emergence model detects a strong weed emergence. For example, the change of environmental condition may cause that weed growth stage surpassing or exceeding threshold. For example, within a given control time period a weed growth model detects that weeds are most likely in a suitable growth stage.

[0030] In some examples, the data indicative of the one or more events may be provided by a user (e.g., farmer) via a user interface. In some examples, the data indicative of the one or more events may be retrieved from a database, such as a database storing the field records (e.g., records of herbicide application history). In some examples, the data indicative of the one or more events (e.g., a change of environmental condition) may be retrieved from e.g., a third party, e.g. a service provider, or by on-site sensors.

[0031] In some examples, the data indicative of one or more events may be received any time, such as during control time periods as well as between two control time periods. For example, environmental data may be received from e.g., a service provider, or on-site sensors continuously. In some examples, the data indicative of one or more events may be received at the end of one control time periods, or at the end of two or more control time periods. For example, camera data indicative of a weed infestation condition may be received at the end of each control time period to determine a result of control of the corresponding control measure. For example, in-season scouting data may be received when in-season scouting by a famer or contractor happens around 10 days after the application of a spray program.

[0032] Accordingly, the apparatus may review the execution of the application program and to account for previous applications and in-season changes. For example, one crop protection measure did not take place as planned in the application scheme. For example, one crop protection measure was carried out differently than planned in the application scheme. For example, the weather condition changes and is different than the data stored in the information of the agricultural field. In such cases, the apparatus may select a different program of control measures to better match the current harmful organism management scenario. The review may be triggered by a user via a user interface or automatically triggered by the detection of an occurrence of an event. Alternatively or additionally, the review process may be triggered when the farmer wants to execute the next program. Usually, one program runs for one season. Reviewing after the season for the next one may manage the next season successfully.

[0033] In some examples, each program of control measures may be provided with a label comprising one or more predefined conditions for selecting the respective program of control measures. The label may also comprise information on the harmful organism management scenario, such as a heavy weed infestation scenario, a standard weed composition scenario, a scenario for a high pressure of resistant weed plus some broadleaf weeds, and a critical grass weed scenario. The selection of a particular program of control measures may be performed by determining whether the changed harmful organism infestation condition matches information in a label of one program of control measures.

[0034] In some examples, the processing unit is configured to generate a control file comprising control parameters to control at least one application device control the harmful organism in accordance with the application scheme.

[0035] In some examples, the processing unit is configured to generate a filling guidance including the required agricultural products and their ratios to be filled into one or more tanks of at least one application device.

[0036] In some examples, the harmful organism comprises one or more of: a weed, a fungal disease, and a pest.

[0037] In some examples, the agricultural product comprises a crop protection product, preferably a herbicide product, a fungicide product, and / or a pesticide product.

[0038] According to a second aspect of the present invention, there is provided a harmful organism management system, which comprises an apparatus according to the first aspect and any associated example configured to generate an application scheme for controlling a harmful organism on an agricultural field, and at least one application device configured to control the harmful organism in accordance with the application scheme.

[0039] This will be explained in detail hereinafter and in particular with respect to the flow chart shown in FIG. 3.

[0040] According to a third aspect of the present invention, there is provided a computer-implemented method for generating an application scheme for controlling a harmful organism on an agricultural field, the method comprising: a) receiving information on an expected presence of the harmful organism for an upcoming period; b) determining a rough control schedule comprising a plurality of control time periods for controlling the harmful organism, based on the information about an expected presence of the harmful organism for the upcoming period; c) determining, based on product data that comprises information on a plurality of agricultural products, at least one program of control measures to be sequentially applied to the agricultural field to control the harmful organism at the plurality of control time periods, wherein each control time period is associated with at least one respective control measure selected from a chemical measure or a mechanical measure; d) generating the application scheme that comprises the determined rough control schedule with the plurality of control time periods and / or the at least one program of control measures; and e) providing the generated application scheme.

[0041] This will be explained in detail hereinafter and in particular with respect to the flow chart shown in FIG. 3.

[0042] According to a further aspect of the present invention, there is provided a computer product comprising instructions which, when the program is executed by a processing unit, cause the processing unit to carry out the steps of method according to the third aspect and any associated example.

[0043] In an embodiment, agricultural field may be any area in which organisms, particularly crop plants, are produced, grown, sown, and / or planned to be produced, grown or sown. The term "agricultural field" also includes horticultural fields, silvicultural fields and fields for the production and / or growth of aquatic organisms.

[0044] In an embodiment, agricultural product may comprise any product / object / material which may be applied on an agricultural field using threshold values. 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; water.

[0045] In an embodiment, control data may include any data being configured to operate and control an application device. The control data are provided by a control unit and may be configured to control one or more technical means of the application device, e.g. the drive control but is not limited thereto. In an embodiment, application map may be a map indicating a two-dimensional spatial distribution of the amounts, or dose rates, or types, or forms of products, which should be applied on different locations or zones within an agricultural field.

[0046] In an embodiment, harmful organism may be any organism that has a negative impact to the growth or to the health of the agricultural crop plant. Examples of the target may include, but are not limited to, weeds, diseases, pests, etc.

[0047] In an embodiment, crop may refer to a plant such as a grain, fruit, or vegetable grown in large amounts. Preferred crops are: Allium cepa, Ananas comosus, Arachis hypogaea, Asparagus officinalis, Avena sativa, Beta vulgaris spec, altissima, Beta vulgaris spec, rapa, Brassica napus var. napus, Brassica napus var. napobrassica, Brassica rapa var. silvestris, Brassica oleracea, Brassica nigra, Camellia sinensis, Carthamus tinctorius, Carya illinoinensis, Citrus limon, Citrus sinensis, Coffea arabica (Coffea canephora, Coffea liberica), Cucumis sativus, Cynodon dactylon, Daucus carota, Elaeis guineensis, Fragaria vesca, Glycine max, Gossypium hirsutum, (Gossypium arboreum, Gossypium herbaceum, Gossypium vitifolium), Melianthus annuus, Hevea brasiliensis, Hordeum vulgare, Humulus lupulus, Ipomoea batatas, Juglans regia, Lens culinaris, Linum usitatissimum, Lycopersicon lycopersicum, Malus spec., Manihot esculenta, Medicago sativa, Musa spec., Nicotiana tabacum (N.rustica), Olea europaea, Oryza sativa, Phaseolus lunatus, Phaseolus vulgaris, Picea abies, Pinus spec., Pistacia vera, Pisum sativum, Prunus avium, Prunus persica, Pyrus communis, Prunus armeniaca, Prunus cerasus, Prunus dulcis and Prunus domestica, Ribes sylvestre, Ricinus communis, Saccharum officinarum, Secale cereale, Sinapis alba, Solanum tuberosum, Sorghum bicolor (s. vulgare), Theobroma cacao, Trifolium pratense, Triticum aestivum, Triticale, Triticum durum, Vicia faba, Vitis vinifera and Zea may. Most preferred crops are: Arachis hypogaea, Beta vulgaris spec, altissima, Brassica napus var. napus, Brassica oleracea, Citrus limon, Citrus sinensis, Coffea arabica (Coffea canephora, Coffea liberica), Cynodon dactylon, Glycine max, Gossypium hirsutum, (Gossypium arboreum, Gossypium herbaceum, Gossypium vitifolium), Melianthus annuus, Hordeum vulgare, Juglans regia, Lens culinaris, Linum usitatissimum, Lycopersicon lycopersicum, Malus spec., Medicago sativa, Nicotiana tabacum (N.rustica), Olea europaea, Oryza sativa , Phaseolus lunatus, Phaseolus vulgaris, Pistacia vera, Pisum sativum, Prunus dulcis, Saccharum officinarum, Secale cereale, Solanum tuberosum, Sorghum bicolor (s. vulgare), Triticale, Triticum aestivum, Triticum durum, Vicia faba, Vitis vinifera and Zea mays. Especially preferred crops are crops of cereals, corn, soybeans, rice, oilseed rape, cotton, potatoes, peanuts or permanent crops. In an embodiment, season may also be referred to crop's growing season, which is that portion of the year in which local conditions (i.e., rainfall, temperature, daylight, etc.) permit normal plant growth.

[0048] In an embodiment, season-long program may also be referred to as an application scheme to be applied on an agricultural field for an entire crop's growing season or a part of the entire crop's growing season. The application scheme comprises a control schedule with a plurality of control time periods for controlling the harmful organism and / or at least one program of control measures to be applied on an agricultural field. In an example, a time period covered by the control schedule substantially may correspond to a season. Thus, the application scheme may be provided before a start time of the control schedule.

[0049] BRIEF DESCRIPTION OF THE DRAWINGS

[0050] These and other aspects of the invention will be apparent from and elucidated further with reference to the embodiments described by way of examples in the following description and with reference to the accompanying drawings, in which

[0051] FIG. 1 illustrates a block diagram of an exemplary apparatus for generating an application scheme for controlling a harmful organism on an agricultural field.

[0052] FIG. 2 shows an exemplary harmful organism management system.

[0053] FIG. 3 shows a flow chart illustrating a computer-implemented method for generating an application scheme for controlling a harmful organism on an agricultural field.

[0054] FIG. 4 shows an exemplary expected infestation map for the agricultural field.

[0055] FIG. 5 shows an exemplary list of weeds as examples of harmful organism with recommended control time periods.

[0056] FIG. 6 shows an exemplary list of herbicides as examples of agricultural products.

[0057] FIG. 7 illustrates three exemplary application schemes by paring different chemistries / modes of action in the crop protection plan.

[0058] FIG. 8 illustrates an example of a program of control measures.

[0059] FIG. 9 illustrates an example of multiple programs of control measures.

[0060] FIG. 10 illustrates an exemplary updated application scheme. FIG. 11 shows an exemplary application device 400 configured to implement the application scheme.

[0061] It should be noted that the figures are purely diagrammatic and not drawn to scale. In the figures, elements which correspond to elements already described may have the same reference numerals. Examples, embodiments or optional features, whether indicated as non-limiting or not, are not to be understood as limiting the invention as claimed.

[0062] DETAILED DESCRIPTION OF EMBODIMENTS

[0063] In the following, the approach is described in relation with the application of an herbicide product for the purposes of illustration. However, anyone of ordinary skill in the art will appreciate that the method and apparatus described above and below can be adapted to other agricultural products, such as fungicides, pesticides, etc. Accordingly, the following described examples are set forth without any loss of generality to, and without imposing limitations upon, the claimed invention.

[0064] FIG. 1 shows a block diagram of an exemplary apparatus 10 for generating an application scheme for controlling a harmful organism on an agricultural field. The exemplary apparatus 10 may comprise an input unit 12, a processing unit 14, and an output unit 16.

[0065] In general, the 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.

[0066] In some implementations, the exemplary apparatus 10 may be embodied as, or in, a device or apparatus, such as a server, workstation, or mobile device. The apparatus 10 may comprise one or more microprocessors or computer processors, which execute appropriate software. The processing unit 14 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.

[0067] It is noted that the 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 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 apparatus may be implemented in the form of a circuit.

[0068] In some implementations, the exemplary apparatus 10 may also be implemented in a distributed manner. 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 3rdGeneration 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.

[0069] Although FIG. 1 may show a limited number of components by way of example, it can be appreciated that a greater or a fewer number of components may be employed for a given implementation. Furthermore, the functions provided by one or more components of the apparatus 10 may be combined or separated. Moreover, the functionality of any one or more components of the apparatus 10 may be implemented by any appropriate computing environment, such as personal computing environment, time-sharing computing environment, distributed computing environment, cloud-computing environment, and cluster computing environment. An exemplary cloud-computing environment is shown in FIG. 2.

[0070] FIG. 2 shows an exemplary simplified block diagram of a harmful organism management system 200, in which the apparatus 10 may be implemented. The exemplary harmful organism management system 200 may comprise 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. In this example, the apparatus 10 is embodied as, or in, the field management system 120, e.g., residing in the field management system 120 as a software.

[0071] 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 comprise information about one or more agricultural fields.

[0072] In some implementations, the information about one or more agricultural fields may comprise information on historical and / or current presence of one or more harmful organisms on the agricultural field. 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.

[0073] In some implementations, the information about one or more agricultural fields may comprise field data of different agricultural fields. 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.

[0074] In some implementations, the information about one or more agricultural fields 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.

[0075] In some implementations, the information about one or more agricultural fields 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.

[0076] In some implementations, the information about one or more agricultural fields 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.

[0077] In some implementations, the information about one or more agricultural fields may comprise any combination of the above-described examples. In some examples, the data management system 110 may comprise agricultural product data, which may comprise information about a plurality of agricultural products, such as crop protection products including, but not limited to, herbicides, pesticides, and fungicides. For example, the information may include product specifiers (e.g., product IDs, such as herbicide IDs, pesticide IDs, etc.), targeted harmful organism specifiers (e.g., harmful organism IDs, such as weed IDs, pest IDs, etc.), and any additional information. As an example, the herbicide data may provide information on weeds controlled, crop types on which the herbicide may be applied, mixing procedures, recommended application timing, application rates, active ingredients, mode of action, classification (such as preplant incorporated herbicide, pre- or post-emergent herbicide, Post Harvest Product), and proper safety apparel required during mixing and application. In some examples, the data management system 110 may comprise an agricultural product database, which may cover all or most of the common agricultural products. In some examples, the agricultural product database may be limited agricultural products of a certain provider. Moreover, it is also possible to limit the agricultural product database to agricultural products allowed in a respective jurisdiction. The agricultural product database might be provided by a third party. However, it is also possible that a user creates an agricultural product database by scanning the labels of each agricultural product he / she has in stock and by acquiring the respective information about each agricultural product from supplier databases. By means of the latter, it is also possible that a user supplements an agricultural product database adding information about further agricultural products.

[0078] 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 apparatus 10, which processes the extracted data according to the method as described herein. The processed data and the final outputs of the 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. 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. 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 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 apparatus 10 may provide a configuration profile, which may be loaded to the application device 150 to configure the application device 150 to apply a chemical measure or a mechanical measure according to the determined application timing.

[0079] 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 application scheme and / or the configuration file may comprise a sequence of control time periods with associated agricultural product IDs.

[0080] The at least one application device 150 is configured to implement a sequence of crop protection measures, such as mechanical measures and / or chemical measures, across a season on an agricultural field 100 that is determined by the exemplary apparatus 10. Although FIG.2 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 mechanical measure to eliminate a target (e.g., weeds) physically. Taking mechanical weed control as an example, there are several forms of mechanical weed control, such as finger weeders, brush weeders, torsion weeders, mini ridgers, and computer-vision-guided hoes that provide excellent control of weeds. 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 a chemical protection 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 FIG. 2, 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. A further exemplary application device for implementing a chemical measure is shown in FIG. 11.

[0081] 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.

[0082] FIG. 3 illustrates a flow chart illustrating a computer-implemented method 300 for generating an application scheme for controlling a harmful organism on an agricultural field. The method may be understood to underline operation of the above-mentioned exemplary apparatus 10 for generating an application scheme shown in FIGS. 1 and 2. The apparatus may be a computing device or a computing system, regardless of the platform, being suitable for executing program code related to the proposed method. As a further example, the apparatus may be embodied as, or in, a computer system. The apparatus may be embodied as, or in, a remote server that provides a web service to facilitate harmful organism management of a field e.g. by a farmer of the agricultural field. The remote server may have a more powerful computing power to provide the service to multiple users to manage many different agricultural fields. The remote server may include an interface through which a user can authenticate (e.g. by providing a username and password); and an interface for creating, modifying, and deleting configuration information of the at least one application devices of the user. For example, the configuration information may comprise geographical information of the target area, an application scheme for harmful organism treatment, etc. The configuration information may be loaded onto the at least one application devices to enable the at least one application devices to perform harmful organism treatment.

[0083] However, it will be also understood that the method steps explained in FIG. 3 are not necessarily tied to the architecture of the apparatus 10 as described above in relation to FIG. 1. More particularly, the method described below may be understood as teachings in their own right.

[0084] Beginning at block 310, i.e., step a), the method 300 comprises the step of receiving information on an expected presence of the harmful organism for an upcoming period.

[0085] The upcoming period may be a time window, within which the user plans to treat the harmful organism of the agricultural field. The upcoming period may be e.g., the upcoming days, week, month, or season.

[0086] The information about an expected presence of the harmful organism 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. In some examples, the information on an expected presence of the harmful organism may be provided by a user, such as a farmer, via the electronic communication device 130 shown in FIG. 2.

[0087] In some examples, the information about the expected presence of the harmful organism may be determined based on the information on historical and / or current presence of one or more harmful organisms on the agricultural field, which may be retrieved from the data management system 110. The information about historic presence of the harmful organism may be provided by an infestation map indicating details of the distribution of the harmful organism by locality in the past days, weeks, months, seasons, and / or years. Season and sources of infestation may also be provided in the infestation map, or in a json file or csv table. Alternatively or additionally, the harmful organism population data may comprise information about current presence of the harmful organism.

[0088] In some examples, the information about the expected presence of the harmful organism may be determined by analysing an agricultural field image, which may be captured by a drone, a satellite, etc. An object detection algorithm may be applied to identify the harmful organism on the agricultural field.

[0089] FIG. 4 illustrates an exemplary expected infestation map for the agricultural field 100. In the example of FIG. 4, the expected infestation map shows distribution of the harmful organism by locality and sources of infestation. The expected infestation map comprises two types of harmful organisms with IDs "A" and "B". In particular, the patch 100a of the field is associated with harmful organism ID "A". In other words, there is a likelihood of presence of harmful organism "A" in the patch 100a for the upcoming period. The patch 100b of the field is associated with harmful organism IDs "A" and "B". The expected infestation map may further comprise information about a level of infestation (not shown), which may be useful for determining an amount of agricultural product(s) to be applied.

[0090] At block 320, i.e. step b), the method further comprises the step of determining a rough control schedule comprising a plurality of control time periods for controlling the harmful organism, based on the information about an expected presence of the harmful organism for the upcoming period. The control time periods may include a plurality of dates and / or time windows (e.g., between 8 May to 11 May). In the rough control schedule, only suitable time periods are provided. The appropriate control measure at each control period will be determined at block 330.

[0091] In this step, the harmful organism (e.g., weeds) of concern can be identified based on the information about an expected presence of a harmful organism for an upcoming period. Taking weeds for example, there is a recommended time frame to apply an herbicide to each weed, because herbicides may be almost completely ineffective if applied at the wrong time of year. In most cases, this time is early in the weed's life cycle, but in some cases, herbicide should be applied during a different growth stage. The control timing for sequential applications of at least one control measure selected from a chemical measure or a mechanical measure for controlling weeds may be determined based on weed information retrieved from a weed database.

[0092] For example, the weeds "A" and "B" can be identified based on the expected infestation map for the agricultural field 100 shown in FIG. 4. The apparatus 10 may retrieve weed data of weeds "A" and "B" from e.g., a weed database in the data management system 110 shown in FIG. 2. The weed data may comprise information on recommended time frame(s) when the weeds "A" and "B" may be most effectively controlled. FIG. 5 shows an exemplary list of weeds "A" and "B" to be expected on the field with recommended time frame when the weeds "A" and "B" may be most effectively controlled. It is also indicated application time ranges for post-emergent herbicide, i.e., herbicides applied after the weed has emerged and is actively growing. An exemplary application time range for post-emergent herbicide is between mid-May and mid¬

[0093] October for weed "A". It is also indicated application time ranges for pre-emergent herbicides, such as between March and mid-April for weed "A". If the recommended control time periods for several weeds overlap, an application time may be selected that will offer good control all of those weeds, provided the herbicide selected is effective in controlling them. The recommended time frames for controlling the weeds "A" and "B" may be used to determine the rough control schedule. As an example, the rough control schedule for controlling the weed "A" may comprises a plurality of control time periods. One or more control time periods may be arranged between March and mid-April with the use of pre-emergent herbicides, and one or more control time periods may be arranged between mid-May and mid-October with the use of post-emergent herbicides.

[0094] However, on a particular agricultural field, the development of the harmful organism may be affected by many factors. Therefore, it may be beneficial to consider one or more of the following information on the agricultural field for determining a detailed control schedule for a particular agricultural field.

[0095] In some examples, environmental data for the field region 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. Moreover, depending on the remaining time until the control time(s), it is possible to add the weather data at a later point in time and / or to include / update the weather data at a predetermined time interval before the control time(s). 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.

[0096] In some examples, field data of the agricultural field may be retrieved from e.g., the data management system shown in FIG. 2. For example, the field data may comprise crop rotation information. Rotating crops may help to reduce build-up of certain harmful organisms, especially of those in the soil, such as root-feeding insects and fungi. In some examples, soil data relating to soil conditions of the field may be provided. This may include soil fertility or soil pH, soil compaction, excessive thatch, and water content, which may affect the development of e.g., weeds.

[0097] In some examples, crop variety data relating to a crop grown or to be grown on an agricultural field. 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. The crop variety data may be obtained from the field data of the agricultural field. For example, weed growth may be suppressed by increased crop density and spatial uniformity.

[0098] In some examples, machinery data indicative of available machinery to be used for the upcoming period may be provided. Exemplary machinery may include, but not limited to, drone, sprayer with a single tank, and sprayer with multiple tanks. For example, a sprayer with two tanks may apply two agricultural products at a single control time, while a sprayer with one tank may have to apply two agricultural products at two separate control time periods.

[0099] With one or more of the above information on the agricultural field, the control time periods may be tailored to a specific agricultural field to achieve a more efficient control of the harmful organism.

[0100] At block 330, i.e., step c), the method further comprises determining, based on product data that comprises information on a plurality of agricultural products, at least one program of control measures to be sequentially applied to the agricultural field to control the harmful organism at the plurality of control time periods. Each control time period is associated with at least one respective control measure selected from a chemical measure or a mechanical measure.

[0101] The step of determining at least one program of control measures may further comprise determining a result of controlling the harmful organism with the at least one program of control measures and generating the application scheme if the result of controlling the harmful organism meets a predefined management goal for the upcoming period. The management goal may be a predefined growing goal of the agricultural crop plant on the agricultural field under prediction of environmental conditions. The predefined growing goal may be defined as a predefined amount of a crop grown. Alternatively, or additionally, the management goal may be a predefined level of infestation to be achieved after application of the at least one program of control measures for the upcoming period.

[0102] In order to generate an application scheme with the result of controlling the harmful organism meeting a predefined management goal for the upcoming period, the method may further comprise the steps as described hereinafter. First, based on the product data that comprises information on a plurality of agricultural products, a respective control measure is determined for each control time period to generate a first set of control measures to be sequentially applied at the plurality of control time periods. The selection of a chemical measure or a mechanical measure for a particular control time may depend on several factors. This will be described in detail hereinafter.

[0103] Second, a result of controlling the harmful organism is determined when the first set of control measures are sequentially applied to the agricultural field at the plurality of control time periods. In other words, the method considers whether pairing various crop protection products within the first set of control measures across multiple applications can achieve a desired result. The desired result may be a desired crop yield or a level of resistance e.g., across a season after sequentially applying the first set of control measures across different control time periods.

[0104] Third, it is determined whether the result of controlling the harmful organism meets the predefined management goal for the upcoming period. For example, the predefined management goal for the upcoming period may comprise a preset range of a crop yield . The preset range may be a threshold. For example, the result of controlling the harmful organism meets the management goal for the upcoming period, if a predicted amount of a crop grown is within the preset range. The result of controlling the harmful organism does not meet the predefined management goal for the upcoming period, if the predicted amount of a crop grown is outside the preset range.

[0105] Fourth, in response to determining that the result of controlling the harmful organism does not meet the predefined management goal for the upcoming period, a different control measure may be determined for at least one of the control time periods to generate a second set of control measures to be sequentially applied at the plurality of control time periods. For example, the apparatus may select a different herbicide to be applied at one control time period. For example, the apparatus may use a mechanical measure instead of a chemical measure for at least one control time period.

[0106] Fifth, the above steps may be repeatedly performed until the result of controlling the harmful organism meets the predefined management goal for the upcoming period.

[0107] Finally, in response to determining that the result of controlling the harmful organism meets the predefined management goal for the upcoming period, the at least one program of control measures is generated that comprises a set of control measures with the result of controlling the harmful organism meeting the predefined management goal for the upcoming period. Accordingly, the method may allow for better weed control results, e.g., including overlapping residual herbicides across the season. For example, the knowledge about which herbicides may be applied on the crops and the use of different chemistries / modes of action in the crop protection plan can provide an efficient weed control and supports the fight against resistance. Therefore, the method may use the product data to determine a detailed sequence of mechanical measures and / or chemical applications to be applied at these control time periods. The method may determine whether pairing various crop protection measures across multiple applications can achieve a desired result. In this way, the added and / or combined usage of products, active ingredients, and / or mode of actions across multiple applications may provide better control. Additionally, less doses may be applied to the agricultural field.

[0108] The selection of a chemical measure or a mechanical measure for a particular control time may depend on several factors, such as economic (e.g., cost), regulatory (law), logistic (machinery, weather and soil conditions), agronomic (e.g., weed effectiveness, crop growth stage, availability and effectiveness of herbicides at that time and on that soil, conventional vs. organic farm, weeds and weed resistances, etc.). In some implementations, the selection of a chemical measure or a mechanical measure for a particular control time may be determined based on pre-defined criteria defined by one or more of the above-described factors.

[0109] For example, the product data may be determined by performing a database search in an agricultural product database, which may be stored in e.g., the data management system 110 shown in Fig. 2. For example, the product data may include product specifiers (e.g., product IDs), targeted harmful organism specifiers (e.g., harmful organism IDs, such as weed IDs, pest IDs, etc.), and any additional information. As an example, the product data may comprise herbicide data, which may provide information on weeds controlled, crop types on which the herbicide may be applied, mixing procedures, application timing, application rates, active ingredients, mode of action, classification (such as preplant incorporated herbicide, pre- or post-emergent herbicide, Post Harvest Product), and proper safety apparel required during mixing and application.

[0110] If it is determined that a plurality of harmful organisms is present or expected in the field, it is preferred to determine, for each harmful organism, a respective agricultural product capable of targeting the respective harmful organism.

[0111] Fig. 6 shows an exemplary list of herbicides "A", "B", and "C" found in the agricultural product database capable of targeting the weed IDs "A" and "B" shown in Fig. 5. Herbicide "A", which targets weed "A", may be applied between March and mid-April, because it is a pre-emergent herbicide, while herbicide "C", which is a post-emergent herbicide, may be applied between midMay and mid-October for controlling weed "A". As shown in FIG. 6, the provided information may comprise information about a mode of action of an agricultural product. The mode of action of an agricultural product is the way in which the agricultural product controls susceptible harmful organisms. For example, the mode of action of an herbicide usually describes the biological process or enzyme in the plant that the herbicide interrupts, affecting normal plant growth and development. In other cases, the mode of action may be a general description of the injury symptoms seen on susceptible plants. Information regarding each product's mode of action may be found on the front of the label of the agricultural product. Further taking the herbicide as an example, the herbicide is often described as being a member of a particular numbered group. These numbers refer to a specific mode of action and were developed to consistently organize herbicides based on their mode of action. For example, "Group 1" herbicides are ACCase (acetyl-CoA carboxylase) inhibitors and "Group 2" herbicides are ALS (acetolactate synthase) inhibitors.

[0112] In some examples, as shown in FIG. 6, the provided information may comprise the information about an active ingredient (e.g., quizalofop, diclofop, fenoxaprop, etc.) in an agricultural product.

[0113] In the example shown in FIG. 6, the agricultural products "A" and "C" may have the same active ingredient "X", but differ in the mode of actions. In particular, the agricultural product "A" belongs to "Group 1" herbicides, while the agricultural product "C" belongs to "Group 2" herbicides. The agricultural product "B" may have an active ingredient "Y", and belongs to "Group 2" herbicides.

[0114] Although FIG. 6 may show a limited number of information by way of example, it can be appreciated that a greater or a fewer number of information about the available agricultural products may be employed for a given implementation.

[0115] In some examples, at least one chemical measure may comprise a list of agricultural products suitable for controlling the harmful organism at one or more control time periods. In such case, an agricultural product may be selected from the list based on at least one predefined criterion.

[0116] In one example, some herbicides may be categorized as pre- and post-emergent herbicides, and therefore may be applied at two or more control points across the season. For example, herbicide "A" is classified as a pre-emergent herbicide and a post-emergent herbicide. Therefore, herbicide "A" may be applied at the time frame between March and mid-April as a pre-emergent herbicide, as well as at the time frame between mid-May and mid-October as post-emergent herbicide. Therefore, in these cases, it may be beneficial to determine at which control time herbicide "A" should be applied before generating the application scheme.

[0117] In one example, the apparatus 10 may receive information on at least one agricultural product that has already been applied to the agricultural field within the crop growing season. The information may be provided by a user (e.g., farmer) via the electronic communication device 130 shown in FIG.2. The information may alternatively or additionally be retrieved from the data management system 110 shown in FIG.2. The processing unit 14 of the apparatus 10 may generate the application scheme that comprises rotational sequential applications of the at least one applied agricultural product and the chemical measures to be applied for the upcoming period. For example, if herbicide "A" shown in FIG. 6 has been applied between March and midApril as pre-emergent herbicide, the apparatus 10 may recommend herbicide "C" to be applied between mid-May and mid-October as post-emergent herbicide, instead of herbicide "A". In other words, the apparatus 10 may determine all products which has already been applied in the first parts / steps within the season-long program, and the apparatus 10 may recommend other products for the last parts / steps of the season-long program, e.g. in order to avoid the emergence of resistance.

[0118] In one example, if the farmer has a large stock of herbicide suitable for controlling the harmful organism at one or more control time periods, the herbicide may be selected.

[0119] Turning back to FIG. 3, at block 340, i.e., step d), the method further comprises generating the application scheme that comprises the determined rough control schedule with the plurality of control time periods and / or the at least one program of control measures . If a detailed control schedule is determined, the generated application scheme may comprise the detailed control schedule and the at least one program of control measures. Three exemplary application schemes are shown in FIG. 7. As will be explained in detail below, the control schedule shown in FIG. 7 comprises three control time periods, namely control time "a", control time "b", and control time "c". In some examples, the control schedule shown in FIG. 7 may be a rough control schedule, which is a control schedule that is determined based on the information about an expected presence of the harmful organism for the upcoming period. In some examples, the control schedule shown in FIG. 7 may be a detailed control schedule, which is a control schedule that is determined not only based on the information about an expected presence of the harmful organism for the upcoming period, but also based on the information on the agricultural field, such as soil data, crop variety data, environmental data, crop management data, and / or location data of the agricultural field. FIG. 7 also shows three program of control measures including a first program of control measures, namely program 1, a second program of control measures, namely, program 2, and a third program of control measures, namely program 3. This will be explained in detail with respect to FIG. 7 below.

[0120] In another example, the determined associated control measures associated to the plurality of control time periods may comprise two or more chemical measures using a plurality of agricultural products. The processing unit 14 of the apparatus 10 may generate the application scheme that comprises rotational sequential applications of the plurality of agricultural products. For example, if herbicide "A" shown in FIG. 5 has not yet been applied. Because of herbicide rotation, it is more recommendable to use herbicide "A" between March and mid-April as pre- emergent herbicide. Therefore, the apparatus 10 will recommend using herbicide "C" between mid-May and mid-October (which is similar to herbicide "A"). In this case, an "anticipatory" planning is needed. Therefore, the apparatus 10 may first create a preliminary season long program, which will then be optimized on this basis of different factors, e.g., resistance management, herbicide rotation, etc. In some implementations, at at least one control time, there may exist multiple agricultural products (e.g., herbicides) and / or combinations of agricultural products (e.g., herbicides) suitable for controlling the harmful organisms (e.g., weeds). The multiple agricultural products may also be referred to as candidate agricultural products. The plurality of candidate agricultural products may differ from each other at least in an active ingredient and / or a mode of action. In such case, the processing unit 14 may be configured rank the plurality of candidate agricultural products according to their control efficacies on the harmful organism and to select one or more candidate agricultural products to be used for the at least one control time based on their associated control efficacies. In other words, in order to select the agricultural products, these agricultural products may be ranked according to their efficacy against the harmful organism. Agricultural products (e.g., herbicides) with efficacy lower than e.g., a threshold may be filtered to reduce numbers. As an example, within each mode of action and / or within each active ingredient, the best agricultural products may be selected to reduce numbers.

[0121] For better weed control results, including overlapping residual herbicides across the season may be needed. The knowledge about which herbicides may be applied on the crops and the use of different chemistries / modes of action in the crop protection plan can provide an efficient weed control and supports the fight against resistance. Therefore, it may be beneficial to pair different herbicides across the season. To that end, it may be beneficial to rank the plurality of different programs of control measures based on a predefined ranking criterion, and select one program of control measures for the application scheme based on the ranking. The predefined ranking criterion comprises one or more of: a crop yield and a level of resistance of the harmful organism to the at least one program of control measures. For example, at at least one control time, the determined associated control measure comprises a plurality of candidate agricultural products suitable for controlling the harmful organism. The plurality of candidate agricultural products may differ from each other at least in an active ingredient and / or a mode of action. The processing unit 10 may be configured to generate a plurality of candidate application schemes that have different candidate agricultural products at the at least one control time, determine an application consequence of each candidate application scheme. The application consequence comprises one or more of: a crop yield and a level of resistance. The apparatus 10 may be configured to rank the plurality of candidate application schemes based on the associated application consequences to generate the application scheme.

[0122] For example, the weed data may comprise given resistances to certain mode of actions (MoA). When ranking the tank mixtures and when ranking the programs, the apparatus may consider the efficacy of the products (e.g., herbicide) against the weeds. Combinations where a weed is resistant against the herbicide will have lower efficacies (low efficacy of the herbicide) and will thus be downranked. As we recommend or show only the top choices in the frontend, the low- ranked herbicides may most likely not even be recommended at the end.

[0123] FIG. 7 illustrates three exemplary application schemes by paring different chemistries / modes of action in the crop protection plan. In FIG. 7, three control time periods "a", "b", and "c" are shown. As noted above, in some examples, the control schedule shown in FIG. 7 may be a rough control schedule, which is a control schedule that is determined based on the information about an expected presence of the harmful organism for the upcoming period. In some examples, the control schedule shown in FIG. 7 may be a detailed control schedule, which is a control schedule that is determined not only based on the information about an expected presence of the harmful organism for the upcoming period, but also based on the information on the agricultural field, such as soil data, crop variety data, environmental data, crop management data, and / or location data of the agricultural field. At control time "a", two herbicides "A" and "N" may be used for controlling a target weed. At control time "b", two herbicides "B" and "M" may be used for controlling the target weed. At control time "c", herbicide "C" may be used to control the target weed. Three exemplary weed control programs may be provided, each program comprising a different combination of herbicides at control time periods "a", "b", and "c". The three exemplary weed control programs are also referred to as three program of control measures. The consequence of each program may be also determined. For examples, as shown in FIG. 7, program 1 shows 90% control efficacy on the target weed, and the crop has a high crop yield. Program 2 shows 85% control efficacy on the target weed, and the crop has a medium crop yield. Program 3 shows 80% control efficacy on the target weed, and the crop has a low crop yield. These programs may be ranked according to their consequences, and the best ranked program may be selected. For example, program 1 may be selected, because it has a higher control efficacy on the target weed and a higher crop yield.

[0124] In some implementations, the rank of candidate application schemes may be further adjusted based on a product stock and an equipment stock of a farmer.

[0125] For example, the apparatus 10 may receive information about a product stock indicative of an amount of one or more available agricultural products that are ready to be used on the agricultural field. The information may be provided by a user (e.g., farmer) via the electronic communication device 130 shown in FIG.2. The information may alternatively or additionally be retrieved from the data management system 110 shown in FIG.2. The processing unit 14 of the apparatus 10 may select one or more candidate application schemes with the one or more available agricultural products in the product stock, and to rank the one or more selected candidate application schemes to generate the application scheme. For example, if the farmer has a large stock of herbicide "M", it would make sense that all season-long programs using a large / larger amount of herbicide "M" will be accordingly ranked higher. In such case, the apparatus 10 may recommend program 2. Optionally, the efficiency difference between the original season-long program, i.e., program 1, and the adjusted season-long program, i.e., program 2, may be displayed to the user.

[0126] For example, the apparatus 10 may receive information about an equipment stock indicative of one or more available machines that are ready to be used on the agricultural field. The information may be provided by a user (e.g., farmer) via the electronic communication device 130 shown in FIG.2. The information may alternatively or additionally be retrieved from the data management system 110 shown in FIG.2. The processing unit 14 of the apparatus may select one or more candidate application schemes to match a configuration of the one or more available machines, and to rank the one or more selected candidate application schemes to generate the application scheme. For example, if the farmer has a smart sprayer in his "machine / equipment stock", then a season-long program depending on the smart sprayer may be created. The smart sprayer may allow the farmer to perform some herbicide applications on a spot-spray basis, and other herbicide applications on a flat-spray basis. For example, heat as spot-spray may be combined with glyphosate flat-spray. In such case, the apparatus may rank the programs with regard to available machines or machine attributes. For example, herbicide "A" is a sport-spray, and herbicide "M" is a flat-spray. If it is determined that the farmer has a smart sprayer with two tanks, the apparatus may recommend program 2 as the application scheme.

[0127] Turning back to FIG. 3, at block 350, i.e., step e), the method further comprises the step of providing the generated application scheme.

[0128] FIG. 8 illustrates an example of a program of control measures. The illustrated program of control measures comprises four control time periods including burndown, pre-emergence, early postemergence, and late post-emergence. Each control time period may be associated with a list of agricultural products which may be found in the agricultural product database capable of targeting the harmful organism. As described above with respect to the example shown in FIG. 6, it is possible to select one agricultural product from the list for each control time period based on at least one predefined criterion to form the application scheme.

[0129] FIG. 9 illustrates an example of multiple programs of control measures. In the illustrated example, the multiple programs of control measures may be generated according to different harmful organism management scenarios. Each harmful organism management scenario corresponds to a respective predefined harmful organism infestation condition. For example, the predefined harmful organism infestation condition may be defined using one or more of the following parameters: 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. Different harmful organism management scenario correspond to different harmful organism infestation conditions with at least one predefined different parameter ranges. As an example, exemplary weed management scenarios may include one or more of: a heavy weed infestation scenario, a standard weed composition scenario, a scenario for a high pressure of resistant weed plus some broadleaf weeds, and a critical grass weed scenario.

[0130] As shown in FIG. 9, the exemplary programs of control measures including program "A", program "B", and program "C", which may be preconfigured to different management scenarios. The program "A" may include four control time periods including burndown, pre-emergence, early post-emergence, and late post-emergence. The program "B" may comprise two control time periods including tillage and mid / late post-emergence. The program "C" may comprise three control time periods including early post-emergence, mid post-emergence, and late postemergence. Each program of control measures has a respective sequence of control time periods, which may be determined based on the predefined sequence of actions to take corresponding to the harmful organism management scenario. The sequence of control time periods for each program may be pre-defined settings by the agronomy experts, who determine that a certain harmful organism management scenario needs the control periods e.g. burn-down, pre-emergence, post-emergence, where burn-down is limited to e.g. 21 to 7 days before sowing, pre-emergence to sowing until 1 day before emergence, post-emergence e.g. growth stage e.g., V10-V11 growth stage. The exact settings may depend on country, crop, weeds, etc. A detailed sequence of herbicide tank mixture, such as herbicide tank mixtures "a" to "h" shown in FIG. 9, for a given weed strategy can then be determined for each control time period of the sequence of control time periods. For example, in the program "A" illustrated in FIG. 9, a tank mixture "a" is shown for the control time period "burndown". Another four alternative tank mixtures may be shown in the dropdown menu. In some examples, when selecting a certain tank mixture, the corresponding control time period may be further narrowed down. For example, the application, e.g. Mid-post-emergence, should be done in the window from V12-V18 growth stage. However, due to the legal requirement of e.g. two products in the tank mixture, the actual possible application window is V14-V16 growth stage. It will be appreciated that while the herbicide mixtures shown in FIG. 9 are indicated with different reference letters "a" to "h", some of the herbicide mixtures may be the same. For example, in program A, the herbicide mixture "c" could be the same as herbicide mixture "f" in program "C". Therefore, the letters "a" to "h" are used merely as labels for herbicide mixtures and should not be construed to indicate that these herbicide mixtures are different.

[0131] FIG. 10 illustrates a further example of multiple programs of control measures. During the execution of the application scheme, one or more events may happen which may trigger the selection of a different program of control measures to better match the harmful organism management scenario. In some examples, the data indicative of the one or more events may be provided by a user (e.g., farmer) via a user interface. In some examples, the data indicative of the one or more events may be retrieved from a database, such as a database storing the field records (e.g., records of herbicide application history). In some examples, the data indicative of the one or more events (e.g., a change of environmental condition) may be retrieved from e.g., a third party, e.g. a service provider, or by on-site sensors. For example, as shown in FIG. 10, the program "B" was selected and started as the application scheme. After application of the first control measure, i.e., tillage, data indicative of an occurrence of an event may be collected. In one example, the event may be that the effectiveness of tillage does not meet an expected result of controlling the harmful organism. In an example, the event may be that the presence of the harmful organism after the tillage exceeds an expected level of infestation. Then, the data may be analysed e.g., by the apparatus 10 shown in FIGS. 1 and 2 to determine whether the event has caused or is expected to cause a change of a planned result of controlling the harmful organism, and whether the change of the planned result of controlling the harmful organism has resulted in or is expected to result in a change of harmful organism infestation condition. For example, the program "B" may be generated for a scenario of a standard weed composition scenario. After application of the first control measure, the occurrence of the event indicates that the effectiveness of tillage does not meet an expected result of controlling the harmful organism. This is expected to result in a change of harmful organism infestation condition, e.g., harmful organism infestation condition requiring more intensive post-emergence treatment. As a result, if the program "B" continues to be executed, the management goal cannot be achieved. This event may trigger the selection of the program "C" as an updated application scheme, which is configured to provide an intensive post-emergence treatment of the weeds. As shown in FIG. 10, the program "C" has three control time periods, namely early post-emergence, mid postemergence, and late post-emergence. Therefore, if the tillage as a weed management strategy fails or does not meet an expect result of controlling the harmful organism, the program "C" can be selected to better control the emerging weeds to achieve the management goal. Accordingly, the method may review the execution of the application program and to account for previous applications and in-season changes. For example, one crop protection measure did not take place as planned in the application scheme. For example, one crop protection measure was carried out differently than planned in the application scheme. For example, the weather condition changes and is different than the data stored in the information of the agricultural field. In such cases, the method may select a different program of control measures to better match the current harmful organism management scenario. Alternatively or additionally, the review process may be triggered when the farmer wants to execute the next program. Usually, one program runs for one season. Reviewing after the season for the next one may manage the next season successfully.

[0132] In some examples, one event may trigger several alternative programs of control measures for the same issue. These alterative programs of control measures may be chosen based farm logistic preferences. For example, the apparatus may propose one management strategy, but the user may select another option from the alternatives. Also, the harmful organism management scenarios may be tailored towards specific weed conditions (e.g. "high infestation of grass weeds + select critical broadleaf weeds" vs. "critical grass weeds". In this case, some of the strategies may be suitable for a range of similar conditions of weeds and infestations, but depending on bad the infestation of grass weeds is and how critical the broadleaf weeds are. These alternative programs of control measures may be recommended to the user and the user may decide to go for one or the other scenario.

[0133] In some examples, each program of control measures may be provided with a label comprising one or more predefined conditions for selecting the respective program of control measures. The label may also comprise information on the harmful organism management scenario, such as a heavy weed infestation scenario, a standard weed composition scenario, a scenario for a high pressure of resistant weed plus some broadleaf weeds, and a critical grass weed scenario. The selection of a particular program of control measures may be performed by determining whether the changed harmful organism infestation condition matches information in a label of one program of control measures. In some examples, the generated application scheme or the updated application scheme may be provided as a recommendation by means of a user interface (e.g. a display) e.g., in the electronic communication device 130 shown in Fig. 2. The recommendation may comprise a filling guidance including the required agricultural products and their ratios to be filled into one or more tanks of a dispenser or any other mixing unit.

[0134] In case of an update application scheme, some information may be generated in case the updated program differs from the old one, e.g. "based on your input we have updated recommendations for you. Do you want to update your program?". This may allow a user to decide whether to switch to an updated application scheme. Alternatively, the updated program may be shown in addition to the old one. The updated program may be highlighted to allow a user to decide whether to switch to an updated application scheme. In some examples, some information may be generated in case the updated program does not differ from the old one "we have revised your spray program based on your input. Nothing changed - You're all good."

[0135] In some examples, control data may be generated based on the generated application scheme or the updated application scheme for controlling the at least one application device 150 shown in FIG. 2. The control data may include an agricultural product ID and a dose map. If two or more agricultural products will be used, the control data may include a plurality of agricultural product IDs and product ratio per product ID. The product ratio per product ID may be determined from the expected infestation map. In some examples, the dose rate may be determined for the mix in a single tank system. In some examples, the dose rate may be determined on a per-product ID basis for products in multi-tank system. The control data may be provided to the at least one application scheme configured to implement the application scheme.

[0136] FIG. 11 shows an exemplary application device 400 configured to implement the application scheme. The exemplary application device 400 may comprise a treatment unit 430, a monitoring unit 432, a mission controller 442, a communication interface 444, a GPS 446, an on-board memory 448, and a battery (BAT) 450. The application device 400 may be releasably attached or directly mounted to a ground platform (e.g. tractor) or an aerial platform (e.g., drone).

[0137] The treatment unit 430 may comprise an actuator(s) 434 and an actuator controller 436. The actuator(s) 434 is configured to regulate crop protection product release in response to a control signal provided by the actuator controller 436.

[0138] The monitoring unit 432 may comprise a sensor(s) 438 and a sensor controller 440 for controlling the sensor to sense one or more conditions on the field. The sensor(s) 438 may be 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. Alternatively, or additionally, the sensor(s) may include further sensors to measure humidity, light, temperature, wind or any other suitable condition on the field. The treatment unit 430 and the monitoring unit 432 are communicatively coupled to the mission controller 442 in a wired or wireless connection. The mission controller 442 is configured to control the treatment unit 430 and the monitoring unit 432 based on the application scheme generated according to the method disclosed therein.

[0139] The communication interface 444 may include hardware and / or software to enable the application device 400 to communicate with other devices and / or a network, via a wired or wireless connection. For example, the communication interface 444 may enable the application device 400 to communicate with an unmanned aerial vehicle (UAV), a robot, a ground station, a cloud environment, a remote controller, yield maps, or any combination thereof.

[0140] The on-board memory 448 may be a volatile memory such as RAM or a non-volatile memory such as flash. The software comprising instructions configuring the treatment unit 430 and the monitoring unit 432 to perform the functions according to the application scheme can be downloaded and stored in the on-board memory 448.

[0141] Accordingly, the apparatus, the harmful organism management system, and the computer- implemented method are provided for determining a sequence of crop protection measures to be implemented across a season on an agricultural field. In crop protection, before season start of starting the crop protection program, the most likely targets (e.g., weeds, diseases, pests, etc.) to be expected are estimated. The computer-implemented method and apparatus disclosed herein may use the targets to determine the crop protection strategy, which is most likely to be successfully to control the target. The strategy may comprise a sequence of crop protection measures, such as mechanical measures (e.g., tillage, mowing, weed pulling, etc.) chemical measures (e.g., herbicides, pesticides, fungicides, etc.) across the season. In addition, the strategy may be further detailed out in a program comprising a detailed sequence of mechanical measures and / or chemical applications and the corresponding mode of actions, active ingredients, and / or products. Such approach may be carried out at any point in time and may be done due to agronomical, logistical and commercial reasons before the season start. In some implementations, the computer-implemented method and apparatus disclosed herein may need to account for previous applications and in-season changes (e.g., applications did not take place, or crop protection measures were carried out differently than planned). In some implementations, the computer-implemented method and apparatus disclosed herein may account for interdependencies of applications, determine the most suitable application sequence and the products for each application, and rank suitable programs.

[0142] This exemplary embodiment of the invention covers both, a computer program that right from the beginning uses the invention and a computer program that by means of an up-date turns an existing program into a program that uses the invention.

[0143] Further on, the computer program element might be able to provide all necessary steps to fulfil the procedure of an exemplary embodiment of the method as described above. According to a further exemplary embodiment of the present invention, a computer readable medium, such as a CD-ROM, 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.

[0144] 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.

[0145] 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 invention, 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 invention.

Claims

Claims1. An apparatus (10) for generating an application scheme for controlling a harmful organism on an agricultural field, the apparatus comprising: an input unit (12); a processing unit (14); and an output unit (16); wherein the input unit (12) is configured to receive information on an expected presence of the harmful organism for an upcoming period; wherein the processing unit (14) is configured to: determine a rough control schedule comprising a plurality of control time periods for controlling the harmful organism, based on the information about an expected presence of the harmful organism for the upcoming period; determine, based on product data that comprises information on a plurality of agricultural products, at least one program of control measures to be sequentially applied to the agricultural field to control the harmful organism at the plurality of control time periods, wherein each control time period is associated with at least one respective control measure selected from a chemical measure or a mechanical measure; and generate the application scheme that comprises the determined rough control schedule with the plurality of control time periods and / or the at least one program of control measures; and wherein the output unit (16) is configured to provide the generated application scheme.

2. The apparatus according to claim 1, wherein the processing unit is configured to: determine a result of controlling the harmful organism with the at least one program of control measures; and generate the application scheme if the result of controlling the harmful organism meets a predefined management goal for the upcoming period.

3. The apparatus according to claim 1 or 2, wherein the input unit (12) is configured to receive one or more of the following information on the agricultural field: soil data indicative of a soil condition of the agricultural field;crop variety data relating to a crop grown or to be grown on an agricultural field for the upcoming period; environmental data indicative of an environmental condition on the agricultural field for the upcoming period; crop management data indicative of agricultural product application history on the agricultural field; and location data of the agricultural field; and wherein the processing unit (14) is configured to determine a detailed control schedule with the plurality of control time periods determined based on the information on the expected presence of the harmful organism and the information on the agricultural field; and wherein the generated application scheme comprises the determined detailed control schedule with the plurality of control time periods and / or the at least one program of control measures.

4. The apparatus according to any one of the preceding claims, wherein each of the plurality of time periods is a portion of a defined crop growing season.

5. The apparatus according to any one of the preceding claims, wherein at least one chemical measure comprises a list of agricultural products suitable for controlling the harmful organism at one or more control time periods; and wherein the processing unit (14) is configured to select an agricultural product from the list based on at least one predefined criterion.

6. The apparatus according to claim 5, wherein the at least one predefined criterion comprises one or more of: information about agricultural product rotation; information about resistance prevention; and information about a type and / or a quantity of an agricultural product on stock.

7. The apparatus according to any one of the preceding claims, wherein at least one chemical measure comprises a list of agricultural products suitable for controlling the harmful organism at one or more control time periods; and wherein the processing unit (14) is configured to rank the agricultural products based on associated control efficacies on the harmful organism.

8. The apparatus according to any one of the preceding claims,wherein the at least one program of control measures comprises a plurality of different programs of control measures suitable for controlling the harmful organism at the plurality of control time periods; and wherein the processing unit is configured to rank the plurality of different programs of control measures based on a predefined ranking criterion and to select one program of control measures for the application scheme based on the ranking.

9. The apparatus according to claim 8, wherein the predefined ranking criterion comprises one or more of: a crop yield; a level of resistance of the harmful organism to the at least one program of control measures; information about a type and / or a quantity of an agricultural product on stock; and information about a machine on stock.

10. The apparatus according to claim 8 or 9, wherein the plurality of different programs of control measures comprise at least two programs of control measures generated for different harmful organism management scenarios, each harmful organism management scenario corresponding to a respective predefined harmful organism infestation condition.

11. The apparatus according to claim 10, wherein the input unit is configured to receive data indicative of an occurrence of an event during an execution of the selected program of control measures or after an execution of the selected program of control measures; wherein the processing unit is configured to: determine whether the event has caused or is expected to cause a change of a planned result of controlling the harmful organism; determine whether the change of the planned result of controlling the harmful organism has resulted in or is expected to result in a change of harmful organism infestation condition; in response to determining that the change of the planned result of controlling the harmful organism has resulted in or is expected to result in a change of harmful organism infestation situation, select another program of control measures with the harmful organism management scenario corresponding to the changed harmful organism infestation condition; and wherein the output unit is configured to provide the another selected program of control measures as an updated application scheme.

12. The apparatus according to any one of the preceding claims, wherein the processing unit (14) is configured to generate a control file comprising control parameters to control at least one application device control the harmful organism in accordance with the application scheme; and / or to generate a filling guidance including the required agricultural products and their ratios to be filled into one or more tanks of at least one application device.

13. The apparatus according to any one of the preceding claims, wherein the harmful organism comprises one or more of: a weed, a fungal disease, and a pest; and / or wherein the agricultural product comprises a crop protection product, preferably a herbicide product, a fungicide product, and / or a pesticide product.

14. A harmful organism management system (200), comprising: an apparatus (10) according to any one of the preceding claims configured to generate an application scheme for controlling a harmful organism on an agricultural field; and at least one application device (150) configured to control the harmful organism in accordance with the application scheme.

15. A computer-implemented method (300) for generating an application scheme for controlling a harmful organism on an agricultural field, the method comprising: a) receiving (310) information on an expected presence of the harmful organism for an upcoming period; b) determining (320) a rough control schedule comprising a plurality of control time periods for controlling the harmful organism, based on the information about an expected presence of the harmful organism for the upcoming period; c) determining (330), based on product data that comprises information on a plurality of agricultural products, at least one program of control measures to be sequentially applied to the agricultural field to control the harmful organism at the plurality of control time periods, wherein each control time period is associated with at least one respective control measure selected from a chemical measure or a mechanical measure; d) generating (340) the application scheme that comprises the determined rough control schedule with the plurality of control time periods and the at least one program of control measures; and e) providing (350) the generated application scheme.

Images