Method for pollinating an agricultural area and pollination mix for pollinating an agricultural area

Abstract

The invention relates to a method for pollinating an agricultural area, comprising the method steps of: providing first pollination insects; providing second pollination insects which are a different species from the first pollination insects; and pollinating the plants of the agricultural area using the first and second pollination insects. The invention relates to a pollination mix for pollinating an agricultural area, the mix comprising first pollination insects and second pollination insects, the first and the second pollination insects being from different genera, and an agricultural area using first pollination insects which are assigned and / or provided to the agricultural area and second pollination insects which are assigned and / or provided to the agricultural area, the first and the second pollination insects being from different genera.

Description

[0001] METHOD FOR POLLINATION OF AGRICULTURAL AREA AND POLLINATION MIXTURE FOR POLLINATION OF AGRICULTURAL AREA

[0002] The invention relates to a method for pollinating an agricultural area, comprising the steps of providing first pollinating insects, providing second pollinating insects of a different species than the first pollinating insects, and pollinating the plants of the agricultural area with the first and second pollinating insects. The invention relates to a pollinator mix for pollinating an agricultural area with first pollinating insects and second pollinating insects, wherein the first and second pollinating insects are from different genera, as well as to an agricultural area with first pollinating insects assigned to and / or provided to the agricultural area and second pollinating insects assigned to and / or provided to the agricultural area, wherein the first and second pollinating insects are from different genera.

[0003] State of the art

[0004] The decline in insect populations, largely caused by intensive agriculture, poses a massive threat to agriculture itself: The decrease in pollinators leads to lower yields of fruits, vegetables, and oilseeds, while insects also play a vital role in soil fertility and pest control. Causes include monocultures, the use of pesticides (herbicides, insecticides) and fertilizers, which deplete habitats and food sources, as well as the lack of hedges and wildflowers. The consequences are a decline in biodiversity, more unstable ecosystems, and rising food prices. Impacts on agriculture:

[0005] Pollination: Many crops (over 84% in Germany) depend on insects to form fruits and seeds; without them, yields drop dramatically.

[0006] Soil fertility: Insects promote nutrient cycles and humus formation, which directly influences soil quality.

[0007] Natural pest control: Beneficial insects such as parasitic wasps reduce the need for chemical pesticides.

[0008] Quality and variety: Good pollination increases the quality and shelf life of fruit.

[0009] Declining yields lead to higher food prices and reduced availability of certain products.

[0010] Many plant species depend on specialized pollinating insects that have evolved alongside them. And the genetic diversity of plants safeguards agriculture and thus the food supply against future climate change and other challenges, such as pests.

[0011] Pollinating insects such as honeybees, mason bees, and bumblebees have different temperature ranges in which they are active. Rain or artificial irrigation restricts their ability to fly, while moist soil is necessary for their nesting sites. Physiological processes in the flower, such as the growth of pollen tubes, are also influenced by the weather.

[0012] Honeybees, bumblebees, and solitary bees differ fundamentally in their foraging ecology. Honeybees live in large colonies and, as a coordinated workforce, utilize floral resources up to 5 km from their hive. In contrast, solitary bees such as Osmia spp. forage individually to provide for their offspring, typically venturing within a radius of 100 to 600 m from their nesting site. All bee species modify their foraging strategies to balance the intake of nutrients such as sugars, lipids, microbial substances, micronutrients, and amino acids. However, species may have different nutritional requirements, and these differences can determine foraging preferences in landscapes where there is competition between target and non-target crops.

[0013] Improved pollination practices in agriculture can have significant positive effects on beekeepers, growers, and their associations. Since pollinators play a crucial role in the reproduction of many crops, better pollination practices can increase overall crop yields and quality. This, in turn, benefits beekeepers, as it provides them with richer and more diverse food sources for their bees. A diverse and abundant food supply not only contributes to the health and well-being of bees but also increases the potential for reliable honey production and reproduction rates.

[0014] It is therefore an object of the invention to provide a method for pollinating an agricultural area, with which an agricultural area is pollinated in such a way that the agricultural area achieves a higher yield.

[0015] It is further an object of the invention to provide a pollinator mix for the anesthetization of an agricultural area, with which an agricultural area can be pollinated in such a way that the agricultural area achieves a higher yield.

[0016] It is also an object of the invention to provide agricultural land for the cultivation of an agricultural product that has a pollinator mix such that the agricultural land achieves a higher yield. Description of the invention

[0017] The problem is solved by means of the inventive method for pollinating an agricultural area according to claim 1. Advantageous embodiments of the invention are set out in the dependent claims.

[0018] The inventive method for pollinating an agricultural area comprises three process steps: In the first process step, the first pollinating insects are provided. This provision includes loading, transporting, and / or setting up an insect colony such that the first pollinating insects can pollinate the agricultural area.

[0019] The second step of the process involves providing a second set of pollinating insects, which are a different species than the first. This provision includes loading, transporting, and / or setting up an insect colony in such a way that the second set of pollinating insects can pollinate the agricultural area.

[0020] The various pollinating insects differ fundamentally in their ecology and behavior, which influences their suitability for pollinating specific crops. One of the most fundamental differences lies in their social structure and foraging range. Honeybees, for example, live in large colonies and act as a coordinated team, capable of utilizing food resources up to 5 km from their hive. In contrast, solitary bees, such as mason bees (Osmia spp.), are solitary individuals that forage individually to provide for their offspring. Such solitary bees typically fly only within a maximum radius of 100 to 600 meters from their nesting site.

[0021] Furthermore, there are fundamental differences in pollination efficiency and food preferences among honeybees, bumblebees, and solitary bees. While all bee species adapt their foraging strategies to meet their nutritional needs (e.g., sugars and lipids), the species can have different nutritional requirements. A crucial difference also lies in environmental sensitivity and activity: honeybees, bumblebees, and mason bees exhibit different temperature ranges in which they are active. Generally, rain or artificial irrigation restricts the flight ability of all these insects.

[0022] In the third step of the process, the crops on the agricultural land are pollinated by the first and second pollinating insects. The selection of these insects is optional, ensuring that ideally all flowers on the crops are pollinated to achieve optimal yield.

[0023] In a further embodiment of the invention, the second pollinating insects are of a different genus than the first pollinating insects. In particular, bumblebees belong to the genus Bombus, honeybees to the genus Apis, and mason bees to the genus Osmia. The flight activity of the different genera of pollinating insects differs under the same weather conditions, and they also exhibit different foraging behaviors. By diversifying the pollinating insects into different genera, the pollination efficiency of an agricultural area is increased.

[0024] In another embodiment of the invention, the second pollinating insects are a subfamily distinct from the first pollinating insects. The family Apidae (true bees) belongs to the order Hymenoptera and comprises over 6,000 species, including the well-known honeybees and bumblebees (subfamily Apinae), carpenter bees (Xylocopinae), and cuckoo bees (Nomadinae). They are closely related to digger wasps and feed on pollen and nectar, with most species being solitary, while bumblebees and honeybees are social. Diversifying the pollinating insects into different subfamilies increases the pollination efficiency of an agricultural area.

[0025] In a further embodiment of the invention, the number of first pollinating insects provided differs from the number of second pollinating insects. The foraging behavior and flight activity of the first pollinating insects typically vary under different weather conditions. To compensate for these differences, varying numbers of first and second pollinating insects are used to increase the pollination efficiency of an agricultural area.

[0026] In a further embodiment of the invention, pollination by the first pollinating insects occurs at a different time than pollination by the second pollinating insects. The foraging behavior and flight activity of the first pollinating insects typically differ under varying weather conditions. Therefore, pollination by the first and second pollinating insects usually also occurs at different times. For example, bumblebees maintain flight activity even in cooler temperatures and cloudy weather, while honeybee flight activity is severely restricted at temperatures below 12°C. Bumblebees can therefore pollinate, for example, as early as the morning of a day, while honeybees develop pollination activity at a later time.

[0027] In a further development of the invention, the first and second pollinating insects are provided at different locations. The provision of the first and second pollinating insects is carried out in such a way that their foraging areas overlap as little as possible while simultaneously enabling pollination of the entire agricultural area.

[0028] In a further embodiment of the invention, the first and second pollinating insects are provided in addition to the natural occurrence of pollinating insects. However, the natural occurrence of pollinating insects can vary considerably or be limited depending on the region and may not be sufficient, especially for intensive farming.

[0029] In a further embodiment of the invention, the first and second pollinating insects are provided from different locations. In another embodiment of the invention, providing the insects involves loading, transporting, and / or setting up an insect hive. Pollinating insects are typically kept by beekeepers and breeders away from the agricultural area to be pollinated. After pollination, they are optionally transported back to the breeder / beekeeper.

[0030] In a further embodiment of the invention, parameters of the agricultural area are recorded before the pollinating insects are provided. The recorded parameters include, in particular, data on the crops and their characteristics:

[0031] • Crop traits: Specifically for the target crops apple, cherry, and almond, detailed crop traits are recorded. These include flower morphology (size and shape), nectar and pollen content (including sugar concentration), flowering duration, and flowering phenology (time sequence of flowering).

[0032] • Success metrics: Measurements such as fruit set, yield, and the quality of pollinated fruit are recorded.

[0033] The merging of these extensive and diverse datasets enables advanced AI algorithms to generate precise suggestions for pollinator mixes tailored to specific crops and dynamic environmental conditions.

[0034] In a further development of the invention, the parameters of the agricultural area include influencing factors from the agricultural area's environment. In particular, these are parameters relating to field and soil conditions: These parameters include soil composition and quality, soil moisture, and leaf wetness. Agricultural practice: The AI / ML algorithm takes into account field parameters such as the cropping pattern, pest control, and the location of competing crops in the vicinity.

[0035] In a further embodiment of the invention, one or more parameters from the group include: data of the pollinating insects and the beehive / nest:

[0036] Sensors and activity: The algorithms collect sensor data from beehives, bumblebee nests, and mason bee nests. This includes temperature (including brood chamber temperature), humidity, air pressure, nest weight, and rain detection.

[0037] Health and behavior: Information is collected on the number, health, pollination efficiency, and condition of the beehive / nest. This is made possible by technologies such as cameras (for bee activity), GPS tracking, acoustic monitoring (using frequencies / sounds), and the analysis of volatile organic compounds (VOCs).

[0038] Biological variables: Bee species, their pollination habits and their temperature sensitivity are recorded.

[0039] Foraging strategy: To determine the impact of competing crops, the composition of pollen collected by bees is analyzed using metabarcoding, and the length of the foraging flight can be monitored using RFID tags.

[0040] Environmental, weather and landscape data:

[0041] Weather and climate: Current and historical weather and climate data are recorded, including temperature, wind, air and soil humidity, precipitation, and ground-level ozone. Secondary data: In addition to the primary data collection, secondary data are integrated, including satellite imagery (to identify competing crops) and data from scientific publications.

[0042] In a further embodiment of the invention, the type and number of the first and second pollinating insects are determined from the acquired parameters. The selection process for the type and number of pollinating insects is carried out using AI-based data models that generate pollinator mix proposals.

[0043] In a further embodiment of the invention, the number of first and second pollinating insects is determined using an AI / ML algorithm. The AI / ML algorithm processes a comprehensive mix of primary and secondary data to analyze pollination processes, the health of the pollinating insects, and their interactions with crops.

[0044] The selection of pollinating insects is based on a complex analysis and modeling of extensive data:

[0045] Goal definition (Optimal Mix): The main goal is to define the optimal mixtures of pollinating insects to maximize pollination while minimizing the impact on biodiversity and the population of wild pollinating insects.

[0046] Modeling approach: To determine these optimal mixtures, two main methodologies are used: Mechanistic models: These simulate the preferences of pollinating insects, focusing on their foraging flight and reproductive behavior. Data-driven models: These establish correlations between georeferenced variables and empirical observations of pollinating insect activity and crop interactions.

[0047] Data Basis and Adaptation: The AI-ML algorithm merges extensive datasets ranging from historical studies and sensor readings (such as temperature, humidity, bee activity, volatile organic compounds (VOCs), and acoustics) to detailed crop traits and weather data. Integrating these rich datasets (including those from IoT beehives and farm technology) significantly enhances the capacity to monitor and interpret pollinating insect behavior.

[0048] Proposal generation: The results of these models are transmitted to users via an interface. The underlying knowledge base (knowledge graph) maps the interplay of various entities such as bee species, weather patterns, flower characteristics, and crop varieties. This analysis can, for example, show that certain species, such as mason bees, exhibit superior pollination efficiency for a specific variety (e.g., 'Pink Lady' apples), possibly due to the optimal availability of nectar or pollen, or better alignment with flowering times and surrounding environmental conditions.

[0049] The suggestions of the AI ​​algorithm are thus generated by weighing the preferences, behavior and efficiency of specific pollinating insect species against the specific characteristics of the crop and the prevailing environmental conditions, with the aim of achieving both an increase in crop yield and quality as well as an improvement in indicators of the health of pollinating insect populations by at least 10%.

[0050] In a further embodiment of the invention, third pollinating insects are provided, which are a different species, genus, and / or subfamily from the first and second pollinating insects, wherein the plants of the agricultural area are pollinated by the first, second, and third pollinating insects. By diversifying the pollinating insects to include the first, second, and third pollinating insects, the pollination efficiency of an agricultural area is increased.

[0051] In a further embodiment of the invention, the first, second, and third pollinating insects are bees, mason bees, and / or bumblebees. These pollinating insects are particularly widespread and established in Central Europe, easy to breed and maintain, and differ fundamentally in their ecology and behavior, which influences their suitability for pollinating specific crops. Used as a pollinator mix, they increase the pollination efficiency of an agricultural area.

[0052] The problem is also solved by the pollinator mix according to the invention for the pollination of an agricultural area. Further advantageous embodiments are also set out in the dependent claims.

[0053] The pollinator mix according to the invention for pollinating an agricultural area comprises first pollinating insects and second pollinating insects.

[0054] According to the invention, the first and second pollinating insects are from different genera. These insects differ fundamentally in their ecology and behavior, which influences their suitability for pollinating specific crops. One of the most fundamental differences lies in their social structure and foraging range. Honeybees, for example, live in large colonies and act as a coordinated team, capable of utilizing food resources up to 5 km from their hive. In contrast, solitary bees, such as mason bees (Osmia spp.), are solitary individuals that forage individually to provide for their offspring. Such solitary bees typically fly only within a maximum radius of 100 to 600 meters from their nesting site.Furthermore, there are fundamental differences in pollination efficiency and food preferences among honeybees, bumblebees, and solitary bees. While all bee species adapt their foraging strategies to meet their nutritional needs (e.g., sugars and lipids), the species can have different nutritional requirements. A crucial difference also lies in environmental sensitivity and activity: honeybees, bumblebees, and mason bees exhibit different temperature ranges in which they are active. Generally, rain or artificial irrigation restricts the flight ability of all these insects.

[0055] In a further development of the invention, the second pollinating insects are a different species than the first pollinating insects. There are over 20,000 bee species worldwide, including the well-known honeybee and over 600 wild bee species in Germany, such as bumblebees, mason bees (e.g., horned mason bee), mining bees (e.g., common mining bee), silk bees (e.g., ivy silk bee), and carpenter bees (e.g., blue-black carpenter bee). While honeybees live in large colonies, most wild bees are solitary, building nests in the ground or in wood, and vary considerably in lifestyle and appearance. Different species of pollinating insects exhibit differences in their ecology and behavior, which influences their suitability for pollinating specific crops, as well as differences in pollination efficiency and food preferences.

[0056] In a further embodiment of the invention, the second pollinating insects are a subfamily distinct from the first pollinating insects. The family Apidae (true bees) belongs to the order Hymenoptera and comprises over 6,000 species, including the well-known honeybees and bumblebees (subfamily Apinae), carpenter bees (Xylocopinae), and cuckoo bees (Nomadinae). They are closely related to digger wasps and feed on pollen and nectar, with most species being solitary, while bumblebees and honeybees are social. Diversifying the pollinating insects into different subfamilies increases the pollination efficiency of an agricultural area.

[0057] In a further embodiment of the invention, the number of first pollinating insects provided differs from the number of second pollinating insects. The foraging behavior and flight activity of the first pollinating insects typically vary under different weather conditions. To compensate for these differences, varying numbers of first and second pollinating insects are used to increase the pollination efficiency of an agricultural area.

[0058] In a further embodiment of the invention, the type and / or number of the first and second pollinating insects are predetermined by an algorithm. The algorithm processes a comprehensive mix of primary and secondary data to analyze pollination processes, the health of the pollinating insects, and their interactions with crop plants.

[0059] In a further embodiment of the invention, the algorithm determines the type and / or number of first and second pollinating insects from parameters of the agricultural area. The selection process for the type and number of pollinating insects is carried out using AI-based data models that generate pollinator mix proposals.

[0060] In a further development of the invention, the algorithm uses one or more parameters from the group:

[0061] The algorithm processes a comprehensive mix of primary and secondary data to analyze pollination processes, the health of pollinating insects, and their interactions with crops. The selection of pollinating insects is based on a complex analysis and modeling of extensive data.

[0062] Goal definition (Optimal Mix): The main goal is to define the optimal mixtures of pollinating insects to maximize pollination while minimizing the impact on biodiversity and the population of wild pollinating insects.

[0063] Modeling approach: To determine these optimal mixtures, two main methodologies are used: Mechanistic models: These simulate the preferences of pollinating insects, focusing on their foraging flight and reproductive behavior.

[0064] Data-driven models: These establish correlations between georeferenced variables and empirical observations of pollinating insect activity and crop interactions.

[0065] Data Basis and Adaptation: The algorithm merges extensive datasets ranging from historical studies and sensor readings (such as temperature, humidity, bee activity, volatile organic compounds (VOCs), and acoustics) to detailed crop traits and weather data. Integrating these rich datasets (including those from IoT beehives and farm technology) significantly improves the capacity to monitor and interpret pollinating insect behavior.

[0066] Proposal generation: The results of these models are transmitted to users via an interface. The underlying knowledge base (knowledge graph) maps the interplay of various entities such as bee species, weather patterns, flower characteristics, and crop varieties. This analysis can, for example, show that certain species, such as mason bees, exhibit superior pollination efficiency for a specific variety (e.g., 'Pink Lady' apples), possibly due to the optimal availability of nectar or pollen, or better alignment with flowering times and surrounding environmental conditions.

[0067] The algorithm's suggestions are generated by weighing the preferences, behavior, and efficiency of specific pollinating insect species against the specific characteristics of the crop and the prevailing environmental conditions, with the aim of achieving both an increase in crop yield and quality and an improvement in indicators of pollinating insect population health by at least 10%.

[0068] In a further embodiment of the invention, the parameters are determined based on the agricultural area to be pollinated, wherein the agricultural area has vegetation, and the vegetation has an inflorescence. The parameters recorded include, in particular, data on the cultivated plants and their characteristics:

[0069] Plant traits: Specifically for the target crops apple, cherry, and almond, detailed characteristics of the cultivated plants (crop traits) are recorded. These include flower morphology (size and shape), nectar and pollen content (including sugar concentration), flowering duration, and flowering phenology (time sequence of flowering).

[0070] Success metrics: Measurements such as fruit set, yield, and the quality of pollinated fruit are recorded.

[0071] The merging of these extensive and diverse datasets enables the AI ​​algorithms to generate precise suggestions for pollinator mixes tailored to specific crops and dynamic environmental conditions.

[0072] In a further embodiment of the invention, the first and second pollinating insects are assigned to different insect colonies, the insect colonies being arranged at different locations. The arrangement of the first and second pollinating insects is such that their foraging areas overlap as little as possible while simultaneously enabling pollination of the entire agricultural area.

[0073] In a further embodiment of the invention, the pollinator mix includes third pollinating insects that are a different species, genus, and / or subfamily than the first and second pollinating insects. Diversifying the pollinating insects to include first, second, and third pollinating insects increases the pollination efficiency of an agricultural area.

[0074] In a further development of the invention, the first, second, and third pollinating insects are bees, mason bees, and / or bumblebees. These pollinating insects are particularly widespread and established in Central Europe, easy to breed and maintain, and differ fundamentally in their ecology and behavior, which influences their suitability for pollinating specific crops. Used as a pollinator mix, they increase the pollination efficiency of an agricultural area.

[0075] The problem is further solved by the agricultural area according to the invention for cultivating an agricultural product. Further advantageous embodiments are also set forth in the dependent claims.

[0076] The agricultural area according to the invention for cultivating an agricultural product has vegetation, wherein the vegetation has an inflorescence. The vegetation consists predominantly of crop plants and is suitable for producing agricultural products such as apples, cherries, and almonds. Such crop plants have an inflorescence and depend on pollination by pollinators, in particular pollinating insects. The agricultural area according to the invention for cultivating an agricultural product additionally has first pollinating insects assigned to and / or provided by the agricultural area and second pollinating insects assigned to and / or provided by the agricultural area, wherein the first and second pollinating insects are from different genera. By diversifying the pollinating insects to different genera, the pollination efficiency of an agricultural area is increased.

[0077] In a further development of the invention, the second pollinating insects are of a different genus than the first pollinating insects. In particular, bumblebees belong to the genus Bombus, honeybees to the genus Apis, and mason bees to the genus Osmia. The flight activity of the different genera of pollinating insects differs under the same weather conditions, and they also exhibit different foraging behaviors.

[0078] In a further embodiment of the invention, the second pollinating insects are a subfamily distinct from the first pollinating insects. The family Apidae (true bees) belongs to the order Hymenoptera and comprises over 6,000 species, including the well-known honeybees and bumblebees (subfamily Apinae), carpenter bees (Xylocopinae), and cuckoo bees (Nomadinae). They are closely related to digger wasps and feed on pollen and nectar, with most species being solitary, while bumblebees and honeybees are social. Diversifying the pollinating insects into different subfamilies increases the pollination efficiency of an agricultural area.

[0079] In a further embodiment of the invention, the number of first pollinating insects provided differs from the number of second pollinating insects. The foraging behavior and flight activity of the first pollinating insects typically vary under different weather conditions. To compensate for these differences, varying numbers of first and second pollinating insects are used to increase the pollination efficiency of an agricultural area.

[0080] In a further embodiment of the invention, the agricultural area, in addition to the provided first and second pollinating insects, also contains naturally occurring pollinating insects. However, the natural occurrence of pollinating insects can vary considerably or be limited depending on the region and may not be sufficient, especially for intensive farming.

[0081] In a further embodiment of the invention, the first and second pollinating insects belong to different insect colonies, the insect colonies being arranged in different locations. The arrangement of the first and second pollinating insects is such that their foraging areas overlap as little as possible while simultaneously enabling pollination of the entire agricultural area.

[0082] In a further embodiment of the invention, the agricultural area has third pollinating insects that are a different species, genus, and / or subfamily than the first and second pollinating insects. The bee family (Apidae) belongs to the order Hymenoptera and comprises over 6,000 species, including the well-known honeybees and bumblebees (subfamily Apinae). Most species are solitary, while bumblebees and honeybees are social.

[0083] In a further embodiment of the invention, the first, second, and third pollinating insects are bees, mason bees, and / or bumblebees. These pollinating insects are particularly widespread and established in Central Europe, easy to breed and maintain, and differ fundamentally in their ecology and behavior, which influences their suitability for pollinating specific crops. Used as a pollinator mix, they increase the pollination efficiency of an agricultural area. Description of exemplary embodiments

[0084] Exemplary embodiments of the inventive method for pollinating an agricultural area, the inventive pollinator mix and the inventive agricultural area are shown schematically simplified in the drawings and are explained in more detail in the following description.

[0085] They show:

[0086] Fig. 1: Method for pollinating an agricultural area

[0087] Fig. 2: Method for pollinating an agricultural area, recording of parameters of the

[0088] Pollinating insects

[0089] Fig. 3: Method for pollinating an agricultural area, recording of parameters of

[0090] Environmental, weather and landscape data

[0091] Fig. 4: Method for pollinating an agricultural area, recording of the parameters of the

[0092] agricultural land

[0093] Fig. 5a: Agricultural area, pollinator mix with honeybees and bumblebees

[0094] Fig. 5b: Agricultural area, pollinator mix with mason bees and bumblebees

[0095] Fig. 5c: Agricultural area, pollinator mix with honeybees and mason bees

[0096] Fig. 5d: Agricultural area, pollinator mix with mason bees, honey bees and bumblebees

[0097] Fig. 1 shows an embodiment of the method 1 according to the invention for pollinating an agricultural area 100. The entire data infrastructure is designed to collect primary data from IoT nodes and sensors in the field, as well as secondary data (e.g., from scientific publications and climate models such as WorldClim) and from the pollinating insects HB, BB, MB 10, 20, 30, and to fuse them using machine learning (ML). The data are processed in real time via APIs and stored in a data lake. Data acquisition 30 is carried out from the pollinating insects HB, BB, MB themselves and their nests / hives. Sensor values ​​from beehives, bumblebee nests, and mason bee nests 30 are collected, including temperature (including brood chamber temperature), humidity, air pressure, nest weight, and evidence of rainfall.Information on the number, health, pollination efficiency, and condition of hives is collected using technologies such as cameras (to record bee activity), GPS tracking, acoustic monitoring (using frequencies / sounds), and volatile organic compound (VOC) analysis. Key biological variables include bee species, their pollination habits, and their temperature sensitivity. To evaluate foraging strategies and understand the impact of competing crops, the composition of collected pollen is analyzed using metabarcoding, and foraging flight duration is monitored using RFID tags.

[0098] A second area involves the collection of detailed data on the crops and their specific characteristics (crop traits), particularly for the target crops apple, cherry, and almond. This includes flower morphology (size and shape), nectar and pollen content (including sugar concentration), flowering duration, and flowering phenology (the timing of flowering). Pollination success is measured using metrics such as fruit set, yield, and the quality of the pollinated fruit.

[0099] Third, the algorithm integrates comprehensive environmental, weather, and landscape data. This includes current and historical weather and climate data such as temperature, wind, air and soil humidity, precipitation, and ground-level ozone. Field and soil conditions are also considered, including soil composition and quality, soil moisture, and leaf wetness. Within the context of agricultural practice, field variables such as cropping patterns, pest control, and the location of competing crops in the vicinity are recorded.10 The datasets are supplemented with secondary data,20 such as satellite imagery (to identify competing crops) and data from scientific publications. The AI / ML algorithm ML processes a mixture of primary and secondary data to reduce and analyze the complexity of pollination processes, the health of pollinating insects, and their interactions with crops.The aim is to gain a deeper understanding of the relevant interactions between pollinating insects HB, BB, MB and crop plants. The combination of all these extensive and diverse datasets—from historical studies to sensor values ​​and crop traits to dynamic environmental information—enables the AI ​​algorithm ML to generate precise and tailored pollinator mix proposals 40 that are adapted to specific crops and changing environmental conditions. These pollinator mix proposals are then forwarded to users who provide the pollinator mix containing the first, second, and third pollinating insects HB, BB, MB 50. Provisioning 50 includes the loading, transport, and / or placement of one or more insect hives by the user.The first, second and third pollinating insects HB, BB, MB pollinate the agricultural area 100; at a later time, the agricultural area 100 is harvested.

[0100] Fig. 2 shows an embodiment of method 1, wherein 30 parameters are acquired from the pollinating insects HB, BB, and MB. The acquisition of these 30 parameters is achieved through an innovative combination of advanced sensor technology, established ecological field studies, and molecular analyses. Both the managed pollinating insects HB, BB, and MB, as well as wild bees, are monitored simultaneously.

[0101] To determine the health, behavior, and reproduction rate of pollinating insects HB, BB, and MB, specially adapted sensors are deployed in beehives, bumblebee nests, and mason bee nests. The 30 continuously recorded physical parameters include temperature (including brood chamber temperature), humidity, air pressure, and nest weight. Rainfall is also recorded. The activity and vitality of pollinating insects HB, BB, and MB are monitored using various methods. These include acoustic monitoring of frequencies / sounds that measure bee activity and the individual frequencies of pollinating insects HB, BB, and MB. Specialized bioacoustic loggers use machine learning to classify flying insects into broad taxonomic groups.In addition, cameras are used for monitoring to take photos of pollinating insects HB, BB, MB for non-lethal monitoring, with the computer enabling live detection, identification and documentation of pollinating insects HB, BB, MB at the level of the main crop pollinator groups.

[0102] For more detailed health and behavior analysis, GPS tracking and volatile organic compound (VOC) analysis are conducted. VOC analysis can provide information about bee health, the type of nectar collected (and thus the pollinated plant species), and flower characteristics. The sensors also serve to identify factors that support or limit reproduction, for example, by measuring ozone and insecticide concentrations near the hives. In addition to the sensors, established ecological field methods are used to validate the sensor results and obtain a more comprehensive picture of the pollinating insect communities.

[0103] The recording of foraging activity is done via:

[0104] 1. Metabarcoding: The composition of pollen collected by honeybees and bumblebees is analyzed at the molecular level to identify the effects of competing crops.

[0105] 2. Direct Observation: During transect walks on agricultural land, researchers identify pollinating insects HB, BB, MB, and naturally occurring pollinating insects and observe their visitation behavior on plants, enabling the creation of site-specific plant-pollinating insect networks. These walks are also repeated at night under red light to collect data on nocturnal pollinating insects. 3. Flower Insect Timed Counts: Focal observations are conducted on flowers to estimate the pollination rate by the entire pollinating insect community.

[0106] The primary data obtained on the activity of pollinating insects HB, BB, and MB and their interactions with crops are combined with secondary data (e.g., scientific publications). By combining these manually and automatically collected data—from visual recording to molecular analysis—the pollination habits and temperature sensitivity of various pollinating insects HB, BB, and MB can be comprehensively analyzed.

[0107] Fig. 3 shows an embodiment of method 1, in which the acquisition 20 of parameters from environmental, weather, and landscape data is carried out. Secondary data are not directly acquired 20, as they are already existing data, but rather identified, evaluated, and integrated into the machine learning (ML) analysis to supplement the primary information collected in the field and to support the machine learning (ML) models. The aim is to collect secondary data from the micro to the global level 20 (from the farm through the local and regional levels to the national and international levels) in order to enrich the data, broaden the scope of the investigation, and increase the level of detail of the primary data.

[0108] The most important sources and their uses include:

[0109] 1. Weather and climate data: Data from historical studies and climate models such as WorldClim are integrated. These serve to analyze associations between past and current weather and climate data with harvest quantities, qualities, and phenological data.

[0110] 2. Remote sensing and landscape data: Satellite images from providers such as Copernicus and ESA are used. Using these images, the ML algorithm can identify competing crops in the foraging flight zones of the pollinating insects HB, BB, and MB, and assess landscape complexity.

[0111] 3. Scientific literature and research results: The secondary data basis is comprised of scientific publications and historical studies. In particular, a meta-analysis of existing literature is conducted to close knowledge gaps, define flower preferences and the pollination efficiency of the focus species, and thus fully parameterize the experimental analysis and the Kl model.

[0112] 4. Data on related projects and standards: Standards, results and methods from other relevant national or international research and innovation activities, such as the EU projects RestPoll, PoshBee and BeeHome, are integrated into and used in the project.

[0113] The secondary data are fused with the primary data (from IoT beehives, field sensors and ecological surveys) using machine learning to develop high-performance data models for AI.

[0114] Fig. 4 shows an embodiment of method 1, in which the parameters 10 of the agricultural area 100 are acquired. The acquisition 10 of the parameters of the agricultural area 100, the environment, and the crops is carried out by a comprehensive combination of modern IoT sensors, remote sensing, and detailed field studies. For the target crops apple, cherry, and almond, primarily detailed characteristics of the crops are acquired 10. These include flower morphology (size and shape), nectar sugar content, and pollen content. The flowering duration and flowering phenology (the temporal progression of flowering) are also determined precisely. The measurements 10 also include the leaf moisture of the plants. To evaluate the actual success of pollination, measured values ​​such as fruit set, yield, fruit quality, and the number of seeds serve as crucial control values.The origin of the collected pollen is investigated using molecular analysis to determine if it comes from the variety to be pollinated. AI-based data analysis tools process this wide range of data to identify patterns in flower structure and nectar content and to decipher the preferences of the pollinating insects HB, BB, and MB.

[0115] The agricultural areas (100) and the surrounding environment are monitored using various technical aids: Weather and climate: Weather stations and sensors are used to measure current and historical weather and climate data. Essential parameters such as temperature, wind speed, air and soil humidity, air pressure, and precipitation are recorded. The ozone concentration (ozone level) near the ground is also measured using appropriate sensors.

[0116] Soil and field: Soil moisture sensors provide data on moisture levels. In addition, soil composition and quality, as well as field variables such as planting patterns and pest control measures, are taken into account.

[0117] Landscape and competition: To map the foraging flight zones of pollinating insects, satellite data (from providers such as Copernicus and ESA) are used to identify competing crops in the vicinity. The impact of these competing crops on the pollination of the target crops is determined by metabarcoding machine learning (ML) analysis of pollen collected by pollinating insects.

[0118] Figure 5 shows different pollinator mixes for pollinating an agricultural area 100. The pollinator mix includes units (hives) of mason bees (Osmia bicornis / cornuta, MB), honeybees (Apis mellifera, HB), and bumblebees (Bombus terrestris, BB) in varying combinations and numbers. Almonds, cherries, and apples are of great economic importance; therefore, the agricultural area 100 contains apple trees, almond trees, and cherry trees in varying combinations. The natural occurrence of pollinating insects is assumed to be constant and negligibly low in these examples. The following initial values ​​and information on the foraging behavior of the individual species are assumed (source: Plant Fact Sheets - Association of Pollination Beekeepers Germany):

[0119] Honeybees HB: Flower visits per insect / day: 3,000; Number of insects per hive: 20,000; Number of foraging insects per hive: 4,000; Flower visit potential per hive / day: 12,000,000; Active from approx. 12°C, optimal at 20-30°C, flight activity severely restricted at temperatures below 12°C and during rain. Collect both nectar and pollen. Highly developed communication within the colony through a dance language. High fidelity to specific flower species (flower constancy). Foraging activity varies depending on the availability of nectar and the distance to the nectar source.

[0120] Mason bees (MB): Flower visits per insect / day: 5,000; Number of insects per hive: 500; Number of foragers per hive: 450; Flower visit potential per hive / day: 2,250,000; Active from approx. 4-10°C, optimal at 15-25°C. Less sensitive to cooler temperatures compared to honeybees (HB). Flight activity decreases during rain. Primarily collect pollen, also nectar. Solitary lifestyle; each mason bee builds its own brood cell. Low flower constancy within a foraging flight. High pollination efficiency, as pollen loss is facilitated by their body structure.

[0121] Bumblebees BB: Flower visits per insect / day: 4,000; Number of insects per hive: 500; Number of foraging insects per hive: 125; Flower visit potential per hive / day: 500,000; Active from approx. 5°C, optimal at 10-25°C, flight activity persists even at cooler temperatures and in cloudy weather. Bumblebees BB also fly in light rain. Collect both nectar and pollen. Visit a wide variety of flower species. Due to their size and strength, they can access deep flowers and those with complex flower mechanisms. Lower flower constancy compared to honeybees HB.

[0122] In a first embodiment (Fig. 5a), agricultural area 100 has an equal number of almond and cherry trees. To generate a yield from agricultural area 100, pollination-relevant data from the area are recorded. Pollination-relevant data from the surrounding area are also recorded. The pollination parameters of pollinating insects HB, MB, and BB are also recorded. The AI ​​algorithm creates a pollinator mix tailored to specific crops and environmental conditions. This pollinator mix, comprising pollinating insects HB and BB, is transmitted to users 40, made available 50, and positioned at different locations within agricultural area 100 to utilize the foraging range of the individual trees. In this example, one hive of honeybees HB / ha agricultural area 100 and three hives of bumblebees BB / ha agricultural area 100 are used.The pollinator mix carries out the pollination of the inflorescence of the cultivated plants; the harvest takes place at the appropriate time.

[0123] In a second embodiment (Fig. 5b), agricultural area 100 is planted exclusively with apple trees. To generate a yield from agricultural area 100, pollination-relevant data from the area are recorded. Pollination-relevant data from the surrounding area are also recorded. The pollination parameters of pollinating insects HB, MB, and BB are also recorded. The AI ​​algorithm creates a pollinator mix tailored to specific crops and environmental conditions. This pollinator mix, comprising the second pollinating insects MB and the third pollinating insects BB, is transmitted to the users 40, made available 50, and positioned at different locations within agricultural area 100 to utilize the foraging range of the individual hives. In this embodiment, three mason bee hives MB per hectare of agricultural area 100 and three bumblebee hives BB per hectare of agricultural area 100 are used.The pollinator mix carries out the pollination of the inflorescence of the cultivated plants; the harvest takes place at the appropriate time.

[0124] Mason bees MB can exhibit superior efficiency over honey bees HB in pollinating certain apple varieties such as 'Pink Lady', as their activity is better aligned with the flowering time and prevailing environmental conditions (such as lower temperatures).

[0125] In a third embodiment (Fig. 5c), the agricultural area 100 has an equal number of cherry and apple trees. To generate a yield from the agricultural area 100, pollination-relevant data from the agricultural area 100 are recorded. Furthermore, pollination-relevant data from the surrounding area of ​​the agricultural area 100 are recorded. The pollination parameters of pollinating insects HB, MB, and BB are also recorded. The AI ​​algorithm creates a pollinator mix for machine learning that is tailored to the crops and the environmental conditions. The pollinator mix, comprising the first pollinating insects HB and the second pollinating insects MB, is transmitted to the users 40, made available 50, and positioned at different locations within the agricultural area 100 to utilize the foraging range of the individual trees. In this example, one hive of honeybees HB / ha agricultural area 100 and three hives of mason bees MB / ha agricultural area 100 are used.The pollinator mix carries out the pollination of the inflorescence of the cultivated plants; the harvest takes place at the appropriate time.

[0126] In a fourth embodiment (Fig. 5d), agricultural area 100 has an equal number of almond, cherry, and apple trees. To generate a yield from agricultural area 100, pollination-relevant data from the area are recorded. Pollination-relevant data from the surrounding area are also recorded. The pollination parameters of pollinating insects HB, MB, and BB are also recorded. The AI ​​algorithm creates a pollinator mix tailored to specific crops and environmental conditions. This pollinator mix, comprising pollinating insects HB, MB, and BB, is transmitted to users 40, made available 50, and positioned at different locations within agricultural area 100 to utilize the foraging range of the individual trees.In this example, one hive of honeybees (HB) per 100 hectares of agricultural land, three hives of mason bees (MB) per 100 hectares of agricultural land, and three hives of bumblebees (BB) per 100 hectares of agricultural land are used. This pollinator mix pollinates the inflorescences of the cultivated plants, and the harvest takes place at the appropriate time.

[0127] REFERENCE MARK LIST

[0128] 1. Method for pollinating an agricultural area

[0129] 10 Recording parameters of agricultural land

[0130] 20. Recording secondary parameters

[0131] 30 Recording parameters of pollinating insects

[0132] 40 Creating the pollinator mix for a user

[0133] 50. Preparing the pollinator mix

[0134] 100 agricultural land

[0135] ML AI / ML algorithm with database

[0136] HB First pollinating insects / honeybees

[0137] MB Second pollinating insects / mason bees

[0138] BB Third pollinating insects / bumblebees

Claims

PATENTA NSPRÜCHE 1. Method (1 ) for pollinating an agricultural area (100) comprising the following process steps: • Provision of initial pollinating insects (HB), • Providing secondary pollinating insects (MB) that are a different species from the primary pollinating insects (HB), and • Pollination of the plants of the agricultural area (100) with the first (HB) and second pollinating insects (MB).

2. Method (1) for pollinating an agricultural area (100) according to claim 1 , characterized in that the second pollinating insects (MB) are of a different genus than the first pollinating insects (HB).

3. Method (1) for pollinating an agricultural area (100) according to claim 1 or 2, characterized in that the second pollinating insects (MB) are a subfamily different from the first pollinating insects (HB).

4. Method (1) for pollinating an agricultural area (100) according to one or more of the preceding claims, characterized in that the number of first pollinating insects (HB) provided differs from the number of second pollinating insects (MB).

5. Method (1) for pollinating an agricultural area (100) according to one or more of the preceding claims, characterized in that Pollination with the first pollinating insects (HB) occurs at a different time than pollination with the second pollinating insects (MB).

6. Method (1) for pollinating an agricultural area (100) according to one or more of the preceding claims, characterized in that the first (HB) and the second pollinating insects (MB) are provided at different locations.

7. Method (1) for pollinating an agricultural area (100) according to one or more of the preceding claims, characterized in that the provision of the first (HB) and the second pollinating insects (MB) is carried out in addition to the natural occurrence of the pollinating insects.

8. Method (1) for pollinating an agricultural area (100) according to one or more of the preceding claims, characterized in that the provision of the first (HB) and the second pollinating insects (MB) is carried out from different locations.

9. Method (100) for pollinating an agricultural area (100) according to one or more of the preceding claims, characterized in that the provision includes the loading, transport and / or setting up of an insect colony.

10. Method (1) for pollinating an agricultural area (100) according to one or more of the preceding claims, characterized in that The provision of the first (HB) and second pollination insects (MB) takes place from different locations.

11. Method (1) for pollinating an agricultural area (100) according to one or more of the preceding claims, characterized in that parameters of the agricultural area (100) are recorded (10) before the pollination insects (HB, MB) are provided.

12. Method (1) for pollinating an agricultural area (100) according to claim 11, characterized in that the parameters of the agricultural area include influencing factors from the environment of the agricultural area (100).

13. Method (1) for pollinating an agricultural area (100) according to claim 11 or 12, characterized in that one or more parameters from the group: type of crop, presence of natural pollinating insects, soil composition and quality, soil moisture and leaf wetness, cultivation patterns, pest control and / or the location of competing crops in the vicinity.

14. Method (1) for pollinating an agricultural area (100) according to one or more of claims 11 to 13, characterized in that the type and number of the first (HB) and second pollinating insects (MB) are determined from the recorded (10) parameters.

15. Method (1) for pollinating an agricultural area (100) according to one or more of claims 11 to 14, characterized in that The number of first (HB) and second pollination insects (MB) is determined using an AI / ML algorithm (ML).

16. Method (1) for pollinating an agricultural area (100) according to one or more of the preceding claims, characterized in that third pollinating insects (BB) are provided which are one of the first (HB) and second pollinating insects (MB) are of different species, genus and / or subfamily, with the plants of the agricultural area (100) being pollinated by the first (HB), second (MB) and third pollinating insects (BB).

17. Method (1) for pollinating an agricultural area (100) according to one or more of the preceding claims, characterized in that the first, second and third pollinating insects are bees, mason bees and / or bumblebees.

18. Pollinator mix for the pollination of an agricultural area (100) with • first pollinating insects (HB) and • second pollinating insects (MB), wherein the first (HB) and second pollinating insects (MB) are from different genera.

19. Pollinator mix for pollinating an agricultural area (100) according to claim 18, characterized in that the second pollinating insects (MB) are a different species from the first pollinating insects (MB).

20. Pollinator mix for pollinating an agricultural area (100) according to claim 18 or 19, characterized in that The second pollination insects (MB) are a subfamily distinct from the first pollination insects (HB).

21. Pollinator mix for pollinating an agricultural area (100) according to one or more of claims 18 to 20, characterized in that the number of first pollinating insects (HB) provided differs from the number of second pollinating insects (MB).

22. Pollinator mix for pollinating an agricultural area (100) according to one or more of claims 18 to 21, characterized in that the type and / or number of the first (HB) and the second pollinating insects (MB) are predetermined by an algorithm (ML).

23. Pollinator mix for pollinating an agricultural area (100) according to claim 22, characterized in that the algorithm (ML) determines the type and / or number of the first (HB) and second pollinating insects (MB) from parameters of the agricultural area (100).

24. Pollinator mix for pollinating an agricultural area (100) according to claim 23, characterized in that the algorithm (ML) uses one or more parameters from the group consisting of the type of crop, the occurrence of natural pollinating insects, soil condition and quality, soil moisture and leaf wetness, cultivation patterns, pest control and / or the location of competing crops in the vicinity.

25. Pollinator mix for pollinating an agricultural area (100) according to claim 23 or 24, characterized in that the parameters are determined based on the agricultural area (100) to be pollinated (10), wherein the agricultural area (100) has vegetation, wherein the vegetation has an inflorescence.

26. Pollinator mix for pollinating an agricultural area (100) according to one or more of claims 18 to 25, characterized in that the first (HB) and second pollinating insects (MB) are assigned to different insect hives, wherein the insect hives are arranged in different locations.

27. Pollinator mix for pollinating an agricultural area (100) according to one or more of claims 18 to 26, characterized in that the pollinator mix comprises third pollinating insects (BB) which are a species, genus and / or subfamily different from the first (HB) and second pollinating insects (MB).

28. Pollinator mix for pollinating an agricultural area (100) according to one or more of claims 18 to 27, characterized in that the first (HB), second (MB) and third pollinating insects (BB) are bees, mason bees and / or bumblebees.

29. Agricultural area (100) for the cultivation of an agricultural product with • a growth, wherein the growth has an inflorescence, • first pollination insects (HB) assigned and / or provided to the agricultural area (100) and • second pollination insects (MB) assigned and / or provided to the agricultural area (100), where the first (HB) and second pollinating insects (MB) are from different genera.

30. Agricultural area (100) for the cultivation of an agricultural product according to claim 29, characterized in that the second pollination insects (MB) are of a different genus than the first pollination insects (HB).

31. Agricultural area (100) for the cultivation of an agricultural product according to claim 29 or 30, characterized in that the second pollination insects (MB) are a subfamily different from the first pollination insects (HB).

32. Agricultural area (100) for the cultivation of an agricultural product according to one or more of claims 29 to 31, characterized in that the number of first pollinating insects (HB) provided differs from the number of second pollinating insects (MB).

33. Agricultural area (100) for the cultivation of an agricultural product according to one or more of claims 29 to 32, characterized in that the agricultural area (100) has naturally occurring pollinating insects in addition to the provided first (HB) and second pollinating insects (MB).

34. Agricultural area (100) for the cultivation of an agricultural product according to one or more of claims 29 to 33, characterized in that the first (HB) and second pollinating insects (MB) belong to different insect hives, wherein the insect hives are arranged in different locations.

35. Agricultural area (100) for the cultivation of an agricultural product according to one or more of claims 29 to 34, characterized in that the agricultural area (100) has third pollination insects (BB) which are a species, genus and / or subfamily different from the first (HB) and second pollination insects (MB).

36. Agricultural area (100) for the cultivation of an agricultural product according to one or more of claims 29 to 35, characterized in that the first (HB), second (MB) and third pollinating insects (BB) are bees (HB), mason bees (MB) and / or bumblebees (BB).

Images