BASF Agro Trademarks GmbH

The present invention relates to the planning and implementation of agricultural measures using remote sensing data and local field data. Using remote sensors, the total required amount and partial-area-specific required amounts of plant protection agents and/or nutrients and/or seeds and/or the like can be determined, and based on this information, the use of an application device can be planned. Using local field sensors, the current local required amounts in the field are determined so that the application device can apply the corresponding amounts as required.

Computer-implemented method and system ( 100 ) for enhancing a plant image database ( 230 ) for improved damage identification on plants. The system receives a real-world image ( 91 ) of a plant ( 11 ), recorded at a particular geographic location ( 2 ), together with image metadata comprising location data (LD 1 ) indicating the particular geographic location ( 2 ), and a time stamp (TS 1 ) indicating the point in time ( 3 ) when the real-world image ( 91 ) was recorded. A damage identifier ( 110 ), trained for identifying damage classes associated with damage symptoms present on plants of particular plant species, generates, from the real-world image ( 91 ), an output including a damage class (DC 1 ) for the damage symptoms on the real-world image. A similarity checker ( 120 ) determines feature similarities of the real-world image with selected images ( 232, 233, 234, 235 ) in a plant image database ( 230 ), and further identifies at least a subset ( 230 s ) of the selected images having a feature similarity with the real-world image exceeding a minimum similarity value ( 124 ). The generated damage class (DC 1 ) and the images of the subset ( 230 s ) with respective damage classes and plant species identifier are provided to a user ( 9 ). In response, the system receives from the user ( 9 ) a confirmed damage class (CDC 1 ) for the real-world image ( 91 ). A database updater ( 140 ) of the system updates the plant image database ( 230 ) by storing the received real-world image ( 91 ) together with its plant species identifier, its location data, its time stamp and the confirmed damage class.

The present invention relates to a method for forecasting of a parameter value of a cultivation area, the method comprising: generating (S 1 ), by an ensemble modelling structure, at least one first-model output parameter related to the cultivation area using ensemble modelling based on at least one first-model input parameter; generating (S 2 ), by an machine learning structure, at least one second-model output parameter related to the cultivation area using machine learning based on at least one second-model input parameter; and merging (S 3 ), by a model merging structure, the at least one first-model output parameter and the at least one first-model output parameter to calculate the parameter value of the cultivation area.

The present invention relates to digital farming. In order to reduce residual amounts of a treatment device. There is provided a method for treatment management on an agricultural area applying a treatment product to the agricultural area via a treatment device, the method comprising the following steps: providing ( 40 ) a field identifier and optionally a treatment specifier; determining ( 42 ) a treatment map based on the field identifier and the optional treatment specifier; determining ( 44 ) a field path for applying the treatment product to the field via the treatment device based on the treatment map, wherein the field path comprises at least a first section and a second section; generating ( 46 ) a control file for the treatment device, wherein the control file includes a recording mode for the first section of the field path and a first application mode for the second section of the field path; and providing ( 48 ) the control file, which is usable for controlling the treatment device.

A computer-implemented method for applying a product on an agricultural field, comprising the steps: receiving a control signal to start an adaptation of a product rate and/or of a frequency during a current application of the product on the agricultural field (S 10 ); continuously determining a current amount of the product in a tank of an application device for applying the product (S 20 ); continuously determining a current position of the application device in a route through the agricultural field (S 30 ); continuously adapting the product rate and/or the frequency based on the current position of the application device in the route through the agricultural field and the current amount of the product in the tank of the application device such that at the end of the route of the application device through the agricultural field a predetermined amount of the product is in the tank (S 40 ).

A computer-implemented method for applying a product on an agricultural field, comprising the steps: receiving a control signal to start an adaptation of a product rate and/or of a frequency during a current application of the product on the agricultural field (S 10 ); continuously determining a current amount of the product in a tank of an application device for applying the product based on a treatment savings parameter (S 20 ); continuously determining a current position of the application device in a route through the agricultural field (S 30 ); continuously adapting the product rate and/or the frequency based on the current position of the application device in the route through the agricultural field and the current amount of the product in the tank of the application device such that at the end of the route of the application device through the agricultural field a predetermined amount of the product is in the tank (S 40 ).

Method for providing control data for an application vehicle ( 12 ) when selectively applying pesticides, comprising the following steps: providing (S 10 ) location data of sub-areas ( 13, 14 ) of a field ( 10 ) to which at least one first pesticide has been applied in a first application; determining (S 20 ) transition areas ( 20 ) associated with the sub-areas ( 13, 14 ) to which the at least one first pesticide has been applied and the adjacent areas to which the at least one first pesticide has not been applied, based on the provided sub-area location data; providing (S 30 ) control data for controlling an application vehicle ( 12 ) for applying at least one second pesticide to the determined transition areas ( 20 ) in a second application.

The present application relates to the cultivation of crop plants using plant protection agents. Certain embodiments relate to methods, a system, and a computer program product for determining partial-area-specific requirements of a crop plant for plant protection agents.

The present invention relates to a system and a method for operating a treatment device ( 120 ) applying a treatment product to an agricultural area, the method comprising: obtaining (S 210 ) at least one dataset of an area of interest within the agricultural area ( 110 ) to a control system ( 12.10 ); determining (S 220 ), by the control system ( 12.10 ), from the at least one dataset a plant indicator, wherein a basic threshold for triggering application of the treatment product is dynamically adjustable in relation to the plant indicator; and providing a control signal (S 230 ), by the control system, to control the treatment device ( 120 ) based on the determined plant indicator and the threshold for triggering application of the treatment product.

The present invention relates to the planning and implementation of agricultural measures using remote sensing data and local field data. Using remote sensors, the total required amount and partial-area-specific required amounts of plant protection agents and/or nutrients and/or seeds and/or the like can be determined, and based on this information, the use of an application device can be planned. Using local field sensors, the current local required amounts in the field are determined so that the application device can apply the corresponding amounts as required.