System and method for monitoring pollination of plants

Abstract

A system for monitoring pollination of plants with one or more flowers is disclosed. The system includes multiple microphones for monitoring an area including the one or more flowers. Each of the multiple microphones is configured to monitor a sub-region of the monitored area. Furthermore, each microphone is adapted to record sounds produced by pollinators (such as bumblebees) present in the sub-region of the microphone and is configured to output one or more signals indicating the recorded sounds. The system further includes a data processing system configured to receive the one or more signals indicating the recorded sounds from each of the multiple microphones. The data processing system is further configured to determine values ​​of pollination quality parameters indicating the degree of pollination of the one or more flowers in the monitored area based on the signals received from the multiple microphones.

Description

Technical Field

[0001] This disclosure relates to a system for monitoring the pollination of plants with one or more flowers, and more particularly to such a system comprising a plurality of microphones for monitoring an area including one or more flowers. This disclosure further relates to a corresponding method for monitoring plant pollination, and a data processing system, a computer-readable storage medium, and a computer program for performing this method. Background Technology

[0002] Fertilization in plants is a sexual reproductive process that occurs after pollination and germination. It is defined as the fusion of the male gamete (pollen) and the female gamete (egg) to form a diploid zygote. Fertilization is a physicochemical process that occurs after pollination of the carpels. The complete sequence of this process occurs in the development of the zygote into a seed.

[0003] Flowers play a crucial role in fertilization because they are the reproductive structures of angiosperms (flowering plants). Fertilization in plants occurs when gametes fuse under haploid conditions to produce a diploid zygote.

[0004] Pollination (the process during which pollen is transferred from the male parts of a plant to the female parts) is essential for fertilization and the production of seeds and the fruit from which they are attached. Therefore, pollination is very important in horticulture. If a batch of plants is not effectively pollinated, the yield of that batch will decrease significantly. Pollination can occur via passive (e.g., wind) or active mechanisms. Pollinators (such as bumblebees, bees, birds, bats, butterflies, flower beetles, etc.) are active contributors to pollination. Pollinators can be understood as animals that transport pollen from the male anthers of a flower to the female stigma. For example, bumblebees are commonly used to pollinate plants in greenhouses. Growers can purchase bees in boxes and place the boxes in appropriate locations within the greenhouse. The bees will then fly from flower to flower and perform their pollination function. The advantage of this natural pollination technique is that it provides efficient pollination, at least more efficient than techniques using manual labor.

[0005] The drawback of this natural pollination process is that greenhouse operators have only limited control over it, specifically limited control over the behavior of pollinators. Pollinators (such as bumblebees) may avoid areas of the greenhouse where conditions are less attractive to them. If, in a certain area of ​​the greenhouse, the temperature is relatively low and / or there is undesirable airflow and / or suboptimal lighting, pollinators may avoid that area, meaning that flowers in that area will not be pollinated well. The result could be that plants in that area will have very low fruit yields.

[0006] Therefore, it is crucial that greenhouse operators can monitor the extent to which pollinators pollinate flowers throughout the greenhouse. Only in this way can greenhouse operators take appropriate action if pollination occurs unsatisfactorily in any part of the greenhouse. Therefore, a system and method for monitoring plant pollination is needed in the art. Summary of the Invention

[0007] To this end, a system for monitoring pollination of plants with one or more flowers is disclosed. The system includes a plurality of microphones for monitoring an area including the one or more flowers. Each of the plurality of microphones is configured to monitor a sub-region of the monitored area. Furthermore, each microphone is adapted to record sounds produced by pollinators (such as bumblebees) present in the sub-region of the microphone and is configured to output one or more signals indicating the recorded sounds. The system further includes a data processing system configured to receive the one or more signals indicating the recorded sounds from each of the plurality of microphones. The data processing system is further configured to determine, based on the signals received from the plurality of microphones, a value of a pollination quality parameter indicating the degree to which the one or more flowers in the monitored area are pollinated.

[0008] This system allows for effective monitoring of plant pollination. It is easy to install and requires no substantial adjustments to other equipment within the greenhouse. Microphones simply need to be appropriately placed within the greenhouse, preferably so that they collectively cover a considerable portion of the greenhouse. Microphones can be installed, for example, in existing and / or nearby lighting fixtures within the greenhouse. The data processing system can reside outside the greenhouse. In one example, the data processing system is a desktop computer (with appropriate computer programs already installed) in the greenhouse operator's office. Advantageously, the microphones are relatively simple devices that can still monitor a relatively large sub-area, especially because they can record sounds from pollinators, for example, those behind some leaves, as seen from the microphone's position. This contrasts with, for example, imaging systems, which do not record pollinators if they are not in sight. In cases where pollinators are used to pollinate flowers in the greenhouse, the recorded sounds will also indicate sounds associated with the pollinator pollinating the flowers. Therefore, based on the recorded sounds, the data processing system can determine one or more pollination quality parameters described herein. In principle, the more pollination-related sounds indicated by one or more signals received from the microphone, the higher the value of the pollination quality parameter (assuming that a higher value of the pollination quality parameter corresponds to better pollination).

[0009] One or more signals can indicate the recorded sound because they indicate one or more waveforms representing the recorded sound. A waveform can be understood as the spectrum of sound, that is, the spectrum indicating the intensity (e.g., in dB) per frequency or per frequency bandwidth.

[0010] In principle, the better the pollination of flowers in the monitored area, the higher the yield. One batch of flowers may be pollinated better than another batch, in the sense that the flowers in one batch are pollinated more times on average than the flowers in another batch, i.e., the pollinators visit more frequently on average, and / or in the sense that the flowers in one batch are pollinated more effectively during the pollination event than the flowers in another batch.

[0011] Any kind of plant can be monitored using the publicly available system, such as: fruit plants, such as grapevines, blueberry plants, strawberry plants, raspberry plants, blackberry plants, apple trees, cherry trees, peach trees, etc.; and vegetable plants, such as cucumber plants, tomato plants, eggplants, pepper plants, etc.

[0012] Some or all of the microphones can be configured to record sounds produced by pollinators within a sub-region completely surrounding the microphone; that is, the microphone can be a 360-degree microphone. Additionally or alternatively, the microphones can be directional, as they are configured to monitor only a specific portion of their surrounding environment. A microphone can be configured to monitor a portion of at least one plant, such as a portion of a first plant and a portion of a second plant. In this case, the sub-region of the microphone includes only a portion of at least one plant. For illustration, the microphone can be configured to monitor the top portion of a high-wire tomato plant. Alternatively, the microphone can be configured to monitor multiple plants, typically, in the case of a strawberry plant. In this case, the sub-region of the microphone includes several plants. The sub-regions of the individual microphones may overlap or may not overlap. Examples of pollinators are bumblebees, bees, birds (such as hummingbirds), bats, butterflies, flower beetles, etc.

[0013] Each microphone is configured to output one or more signals that can be referred to as sound signals because they indicate recorded sound. Preferably, the one or more sound signals include an identifier of the microphone from which they were sent, enabling the data processing system to determine which microphone the signal originated from. Furthermore, the data processing system preferably has stored corresponding identifiers of microphones associated with their respective sub-areas within the greenhouse they monitor. This allows the data processing system to determine which sub-areas within the greenhouse, as indicated by the one or more signals from the microphones, are producing sound.

[0014] As described, the data processing system is configured to determine the value of a pollination quality parameter indicating the degree of pollination of one or more flowers in a monitored area. It should be understood that this can be implemented as the data processing system being configured to determine a pollination quality parameter indicating the degree of pollination of one or more flowers in a specific area of ​​the monitored area. The data processing system can be configured to determine several pollination quality parameters that respectively indicate the degree of pollination of one or more flowers in several areas of the monitored area. The data processing system being configured to determine the value of the pollination quality parameter indicating the degree of pollination of one or more flowers in the monitored area can additionally or alternatively be implemented as the data processing system being configured to determine a combined pollination quality parameter based on several pollination quality parameters associated with several areas of the monitored area.

[0015] In one embodiment, the data processing system is configured to: determine the number of pollination events in a monitored area or an area within a monitored area based on one or more signals received from multiple microphones, and / or determine the duration of each pollination event in the monitored area or an area within a monitored area, wherein each pollination event includes a pollinator visiting a flower. Pollination quality parameters can then be determined based on the number and / or duration of the pollination events. In such an embodiment, the value of the pollination quality parameter can be determined based on the number of pollination events and / or based on the duration of each pollination event. This embodiment provides a convenient way to determine pollination quality parameters. The number of pollination events and their corresponding durations are positively correlated with the degree to which the flower is pollinated.

[0016] In one embodiment, the data processing system is configured to determine pollination events by: determining the probability of a pollination event occurring, and counting it as a pollination event if the determined probability is higher than a threshold probability (e.g., higher than 50%).

[0017] It should be understood that a pollinator's visit to a flower does not necessarily mean that a pollination event has occurred, for example, when the flower requires sonication to release pollen, and the sonication sound or pattern proves ineffective or insufficient in terms of energy or duration (provided to the flower by the pollinator). In such cases, the data processing system may determine that a pollinator has visited the flower, but the system has not identified the sound and / or sound pattern associated with a pollination event.

[0018] In one embodiment, the data processing system is configured to determine the species or insect type of the pollinator for one or more specific pollination events. This is advantageous because it allows for tracking the diversity and other characteristics of the pollinator population. For example, if much of the pollination is done by wild bees that "accidentally" enter the greenhouse, there may be no need to add an additional bumblebee hive.

[0019] In one embodiment, the data processing system is configured to determine, for each of a plurality of areas within a monitored area, a pollination quality parameter indicating the extent to which one or more flowers in that area are pollinated, based on one or more signals received from a plurality of microphones. This embodiment advantageously allows monitoring of the pollination quality of each area within a total area, such as that monitored by a plurality of microphones, and thus enables greenhouse operators to see which locations have relatively low pollination quality.

[0020] The values ​​of pollination quality parameters, especially if they are continuously determined for the same area, can be used to predict when plants in that area are ready for harvest. Therefore, in one embodiment, the data processing system is configured to determine the harvest time for agricultural products based on the determined values ​​of the pollination quality parameters. More specifically, since the data processing system can be configured to determine the values ​​of the pollination quality parameters for each area within a monitored area, the data processing system can also be configured to determine this harvest time for each area within the monitored area.

[0021] In one embodiment, the data processing system is configured to, for each of a plurality of areas within a monitored area, determine the number of pollination events in that area and / or the duration of each pollination event in that area based on one or more signals received from a plurality of microphones, wherein each pollination event includes a pollinator visiting a flower. In this embodiment, the data processing is further configured to, for each area, determine a value for a pollination quality parameter indicating the extent to which one or more flowers in that area have been pollinated, based on the determined number of pollination events in that area and / or based on the determined duration of the pollination events in that area. This embodiment enables the pollination quality of each area to be determined conveniently.

[0022] The monitored area comprises several regions. These regions can be the same as sub-regions. In this case, a pollination quality parameter is determined for each sub-region, thus effectively determining a pollination quality parameter for each microphone. However, this is not necessary. The region for which the pollination quality parameter is determined can be different from the sub-region. For illustration, it is possible that only a few pollination events specifically occur in the overlapping area of ​​two sub-regions of two corresponding adjacent microphones. Then, a low pollination quality parameter can be determined for that specific area, while a higher pollination quality parameter can be determined for other areas within the two sub-regions of the two corresponding microphones.

[0023] The data processing system can be configured to determine the number of pollination events; in this sense, it is configured to determine the number of pollination events per unit of time (e.g., per week, per day, per hour, per minute, etc.).

[0024] In one embodiment, the data processing system is configured to determine a pollination event by identifying sounds and / or sound patterns associated with the pollination event from one or more signals from multiple microphones. This embodiment enables the precise determination of pollination events and potentially their corresponding durations.

[0025] Sound can be identifiable because it has a certain frequency. Sound patterns can be time-delayed sound patterns and / or frequency patterns, such as Fast Fourier Transform (FFT) patterns.

[0026] Preferably, the data processing system has stored one or more reference sounds and / or reference sound patterns associated with corresponding pollination events. Reference sounds can be obtained by recording the sounds produced when a pollinator actually pollinates a flower. In any case, it should be confirmed that pollination occurred when the reference sound was recorded. This can be easily done by a human observer who can indicate when the pollination event has occurred and is valid. Reference time-delay sound patterns can be obtained similarly. Reference frequency patterns can be obtained by performing a Fourier transform on the recorded reference sounds.

[0027] For this embodiment, in principle, any sound classification technique (also known as an audio classification technique) known in the art can be used to identify sounds and / or sound patterns associated with pollination events. For example, neural networks, such as those described in Xi Shao et al., Applying Neural Network on the Content-Based Audio Classification, Fourth International Conference on Information, Communications and Signal Processing, 2003 and the Fourth Pacific Rim Conference on Multimedia, Proceedings of the 2003 Joint, December 15-18, 2003, can be used. The training dataset cited in that publication can then be formed from recorded reference sounds and / or reference sound patterns.

[0028] The article "Predicting species identity of bumblebees through analysis offlight buzzing sounds" by [Authors' Name], *The International Journal of Animal Sound and its Recording*, Volume 26, 2017-Issue 1, pages 63-76, May 2016, discloses example spectrographs for different types of buzzing sounds, including ultrasonic processing for B. hyporum worker bees, and sound classification techniques that can be used to identify sounds associated with pollination events.

[0029] In one embodiment, the sound pattern is a time-delayed sound pattern and includes a first time period containing sounds associated with the pollinator's flight, a subsequent second time period substantially without sounds associated with the pollinator's flight, and a subsequent third time period containing sounds associated with the pollinator's flight.

[0030] Typically, pollinators do not fly during pollination. Therefore, the non-flying period between two flying periods can indicate pollination events.

[0031] The sounds or sound patterns should be identifiable in a noisy environment. It is highly likely that the recorded sounds included those of other pollinators flying during the second time period. However, for the purpose of identifying this pollination event, such flying sounds from other pollinators should be considered noise.

[0032] In one embodiment, the data processing system is configured to determine the duration of the pollination event based on the duration of a second time period, such as the duration of a pattern identified in the recorded sound.

[0033] In one embodiment, the pollinator is a bee (such as a bumblebee), and the sound associated with the pollination event is an ultrasonically processed sound and / or the sound pattern associated with the pollination event is an ultrasonically processed sound pattern. Bees are known to use vibrations to collect pollen from anthers. This is called ultrasonication, and is also known as buzz pollination. During ultrasonication, bees produce ultrasonically processed sounds. The characteristics of ultrasonically processed sounds are described in detail in Paul De Luca and Mario Vallejo-Marín's *What's the 'buzz' about? The ecology and evolutionary significance of buzz-pollination*, *Current Opinion in Plant Biology*, 2013, 16:429–435.

[0034] Ultrasonic processing sound can be understood as the sound produced by bees undergoing ultrasonic processing, and ultrasonic processing sound pattern can be understood as the frequency sound pattern produced by bees undergoing ultrasonic processing.

[0035] In one embodiment, the data processing system is configured to determine the duration of a pollination event based on the duration of the ultrasonically processed sound.

[0036] In one embodiment, a plurality of microphones includes a first microphone configured to monitor a first sub-region of a monitored area and a second microphone configured to monitor a second sub-region of the monitored area. The first and second sub-regions at least partially overlap, and a data processing system is configured to: receive from the first microphone one or more signals indicating sound recorded in the first sub-region, and from the second microphone one or more signals indicating sound recorded in the second sub-region; and, based on the first or more signals and the second or more signals, determine a value of a pollination quality parameter indicating the degree to which one or more flowers in one region of the monitored area are pollinated, said region including the at least partial overlap between the first and second sub-regions.

[0037] In one embodiment, the data processing system may be configured to determine, based on a first or more signals and a second or more signals, the duration of a specific pollination event in the overlap between the first and second sub-regions and / or the duration of the specific pollination event in the overlap between the first and second sub-regions. In this embodiment, the specific pollination event leaves a footprint in both the first or more signals and the second or more signals; that is, the sound associated with the specific pollination event is recorded by both the first and second microphones.

[0038] These embodiments enable the accurate determination of pollination quality parameters in areas near the boundaries of sub-regions monitored by microphones. Sound generated near the boundary of a particular microphone's sub-region is naturally less clear than sound generated near that particular microphone and recorded by that particular microphone. In this embodiment, the sub-regions of the first and second microphones overlap, meaning the overlapping area is monitored by both the first and second microphones. Sound generated in the overlapping area is recorded by both the first and second microphones. As a result, the sound generated in the overlapping area (e.g., the ultrasonically processed sound described above) is indicated by both a first or more signals and a second or more signals. Therefore, the sound will have a footprint in both the first or more signals and the second or more signals, although it may be a weak footprint. The data processing system can be configured to correlate the two footprints with each other based on their occurrence time, and based on this correlation, determine that the sound was generated in the overlapping area of ​​the first and second sub-regions. In particular, the data processing system is configured to determine, based on this correlation, that a pollination event has occurred in the overlapping area.

[0039] In one embodiment, where the first and second sub-regions at least partially overlap, the data processing system is configured to receive one or more first signals from a first microphone and one or more second signals from a second microphone, the first or more first signals indicating a first sound and / or a first sound pattern associated with a first pollination event, and the second or more second signals indicating a second sound and / or a second sound pattern associated with a second pollination event. In this embodiment, the data processing system is configured to determine that the first and second sounds are associated with the same pollination event and / or the first and second sound patterns are associated with the same pollination event based on the similarity between the first and second sounds and / or based on the similarity between the first and second sound patterns.

[0040] This embodiment allows for precise monitoring of pollination events in overlapping sub-regions. In particular, this embodiment prevents the same pollination event from being counted more than once.

[0041] Similarity can involve the similarity of the time of occurrence, such as the degree to which the first and second sounds and / or the first and second sound patterns are recorded simultaneously, and / or the similarity of the spectra, such as the degree to which the first and second sounds and / or the first and second sound patterns have the same spectra.

[0042] In one embodiment, the data processing system is configured to estimate the percentage of fertilized flowers based on the values ​​of one or more defined pollination quality parameters.

[0043] In one embodiment, the data processing system is further configured to execute a machine learning algorithm to improve its ability to determine values ​​of pollination quality parameters. Executing the machine learning algorithm includes receiving training data comprising multiple sets of recorded sounds for each batch of plants of a specific pollinator type. Each set of recorded sounds is associated in the training data with an actual value of a pollination quality parameter indicating the degree of pollination of the flowers in the associated batch. Executing the machine learning algorithm further includes building a pollination quality parameter estimation model based on the training data. This can be performed using methods known in the art.

[0044] For example, a pollination quality parameter for a batch could be the percentage of fertilized flowers in that batch, measured in actual measurements. Therefore, training data can be obtained by counting the number of pollination events in a quantified batch of flowers, using one or more microphones to monitor the area where the batch of flowers is located, and then counting the number of flowers that have been correctly pollinated at appropriate times. This allows for the calculation of the percentage of fertilized flowers in the batch. It should be understood that the actual yield of a batch (e.g., the number of fruits ultimately harvested) can be considered a pollination quality parameter, or at least understood as the input that determines the pollination quality parameter. It is important to understand that the actual final yield is related to the quality of pollination. The training data can then be analyzed by storing the recorded sounds and the actual measurements of the pollination quality parameter for each set of data.

[0045] Constructing a pollination quality parameter estimation model based on training data preferably involves correlating the recorded sounds with the actual values ​​of the pollination quality parameters.

[0046] In one example, the embodiment includes:

[0047] - Receive training data comprising multiple sets of recorded sounds, where each set of recorded sounds is associated with an area monitored by a microphone during a training period. This area includes the batches mentioned above.

[0048] -Analyze the recorded audio,

[0049] - Receive reports / measurements of pollination quality parameters for the region during the training period, and

[0050] - Correlate the analyzed data with the values ​​of pollination quality parameters.

[0051] In one embodiment, the data processing system is configured to determine one or more regions of interest among a plurality of regions, each determined region of interest having an associated pollination quality parameter value below a threshold, based on the value of a determined pollination quality parameter for each of the plurality of regions.

[0052] It should be understood that the higher the value of the pollination quality parameter, the better the pollination of the flower. Therefore, this embodiment makes it possible to identify areas in the greenhouse where pollination is not progressing well for some reason. The greenhouse operator can inspect these areas to see if the situation is as expected and what he or she can change (e.g., change the temperature, airflow, lighting) to promote pollination.

[0053] In one embodiment, the system includes a pollination control system configured to influence pollination in selected areas. In this embodiment, a data processing system is configured to control the pollination control system to improve pollination in one or more areas of interest based on the determination of those areas. The pollination control system is adapted to control environmental conditions in one or more monitored areas, where these environmental conditions affect pollination in those areas. These environmental conditions may include lighting conditions, sound, vibration, airflow, temperature, humidity, etc., in one or more areas. Systems for controlling lighting, sound, vibration, airflow, temperature, and humidity are known in the art. For example, near open windows or vents in a greenhouse, or at the location of air inlets in a ventilation system, airflow may discourage insects from flying there, and therefore pollination is unlikely to occur. This is because, generally, flying insects are disturbed by airflow and may even become disoriented. (Temporarily) adjusting airflow can therefore be used to control pollination in some areas of a greenhouse. Another example of areas where reduced pollination activity may occur could be areas near energy accumulation that causes disturbances such as noise and vibration. Furthermore, enhanced light, or light entering the greenhouse and directed directly at the plants (enhanced through reflections on greenhouse glass panels or reflective assets used in greenhouses), can lead to reduced pollination activity. Additionally, uneven temperature and CO2 concentrations throughout the greenhouse can also alter pollination uniformity, and therefore there may always be locations / areas within the greenhouse that provide less favorable climatic conditions for pollinators. Therefore, temperature and CO2 control can be used to influence pollination in certain locations / areas within the greenhouse.

[0054] This embodiment achieves uniform pollination of a batch of flowers throughout the greenhouse and prevents localized yield reductions due to poor pollination.

[0055] If a pollination control system is used to improve pollination, it can also be called a pollination promotion system. In particular, a pollination control system can be configured to improve and / or worsen pollination in a selected area.

[0056] The data processing system can be configured to control the pollination control system to degrade pollination in areas outside the areas of interest, based on the determination of one or more regions of interest. This can be beneficial because it allows for more uniform pollination. To illustrate, pollination can affect harvest time, and by suppressing pollination in selected areas, it can be ensured that fruits are ready for harvest at approximately the same time.

[0057] In one embodiment, the pollination control system includes a horticultural lighting system configured to generate pollination light suitable for influencing pollination. A data processing system is then configured to control the horticultural lighting system to provide pollination light in one or more areas of interest, based on the determination of such areas, to improve pollination in those areas. This embodiment provides a convenient way to promote pollination in selected areas. The pollination light, for example, can attract pollinators.

[0058] Horticultural lighting systems can therefore be configured to produce pollination light suitable for improving and / or worsening pollination. The techniques disclosed in WO2015 / 113818 A1 (particularly the spectrum) can be used to attract pollinators and / or direct them to areas where pollination should be improved. Typically, tunable spectra, polarization, intensity, and / or flicker patterns of light can be used to control the attraction or repulsion of pollinators into or out of a location. Blue light (e.g., wavelengths around 400-405 nm) or long UVA wavelengths attract bumblebees well. "Bee purple," a combination of yellow and ultraviolet light, also attracts bumblebees. Additionally or alternatively, the angle of illumination on the flower can be altered to make the petals more visible to bees. Some petals appear to change color depending on the angle of illumination and / or the viewing angle. This is called iridescence. The color changes are typically in the UV spectrum and are therefore visible to bees. They can see these shimmering petals and associate them with sugar. Thus, the flower becomes more attractive to bees and is pollinated.

[0059] In one embodiment, the pollination control system includes a sound generation system configured to generate acoustic signals suitable for influencing pollination. A data processing system is then configured to control the sound generation system to provide acoustic signals in one or more regions of interest, based on the determination of those regions, to improve pollination in those regions.

[0060] The sound generation system can therefore be configured to produce acoustic signals suitable for improving and / or worsening pollination. For example, pollinator sounds (such as the flight sound of bumblebees or ultrasonic processing sounds) can be used to attract additional pollinators. The sound generation system can also apply a self-learning process to listen to / record pollination sounds and reproduce sounds associated with successful pollination.

[0061] A unique aspect of this disclosure relates to a method for monitoring pollination of a plant with one or more flowers. The method includes receiving one or more signals from each of a plurality of microphones used for monitoring an area including said one or more flowers, indicative of recorded sound. Each of the plurality of microphones is configured to monitor a sub-region of the monitored area. Furthermore, each microphone is adapted to record sound produced by a pollinator (such as a bumblebee) present in the sub-region of the microphone. The method further includes determining a value of a pollination quality parameter, indicative of the degree to which one or more flowers in the monitored area are pollinated, based on the one or more signals received from the plurality of microphones. Optionally, the method is computer-implemented. Each step of any method described herein may or may not be computer-implemented.

[0062] Furthermore, this method for monitoring pollination can include any steps that the data processing system described in this disclosure is configured to perform. It should be understood that these steps are not necessarily performed by the data processing system. For illustration, the steps for controlling the pollination control system can be performed by both the data processing system and by human greenhouse operators.

[0063] In one embodiment, the method includes, for each of a plurality of regions in a monitored area, determining a pollination quality parameter indicating the degree to which one or more flowers in that region are pollinated, based on one or more signals received from a plurality of microphones. The embodiment further includes, based on the determined values ​​of the pollination quality parameters for each of the plurality of regions, determining one or more regions of interest, each region of interest having an associated pollination quality parameter value below a threshold. The embodiment further includes, based on the determination of the one or more regions of interest, controlling a pollination control system configured to influence pollination in the selected regions to improve pollination in the one or more regions of interest.

[0064] The latter step is performed, for example, by a greenhouse operator who controls the horticultural lighting system and / or sound generation system described herein. Alternatively, this step can be performed by a data processing system. In the latter case, the data processing system can perform this step autonomously, in the sense that no human intervention is required.

[0065] One aspect of this disclosure relates to a data processing system for use in any system described herein for monitoring plant pollination. This data processing system can be configured to perform any of the methods described herein for monitoring plant pollination.

[0066] One aspect of this disclosure relates to a computer program including instructions that, when executed by a data processing system, cause the data processing system to perform any of the methods described herein for monitoring plant pollination, including methods in which a pollination control system is controlled to influence pollination.

[0067] One aspect of this disclosure relates to a non-transitory computer-readable storage medium for storing any computer program described herein.

[0068] One aspect of this disclosure relates to a computer including a computer-readable storage medium having computer-readable program code embodied therein, and a processor (preferably a microprocessor) coupled to the computer-readable storage medium, wherein the processor is configured to perform any of the methods described herein in response to executing the computer-readable program code.

[0069] One aspect of this disclosure relates to a computer program or computer program suite comprising at least one software code portion or a computer program product storing at least one software code portion, the software code portion being configured to perform any of the methods described herein when run on a computer system.

[0070] As those skilled in the art will appreciate, aspects of the present invention can be embodied as systems, methods, or computer program products. Therefore, aspects of the present invention can take the form of entirely hardware embodiments, entirely software embodiments (including firmware, resident software, microcode, etc.), or embodiments combining software and hardware aspects, which are generally referred to herein as “circuit,” “module,” or “system.” The functionality described in this disclosure can be implemented as algorithms executed by a computer’s processor / microprocessor. Furthermore, aspects of the present invention can take the form of computer program products embodied in one or more computer-readable media having computer-readable program code embodied thereon (e.g., stored thereon).

[0071] Any combination of one or more computer-readable media can be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any suitable combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In the context of this invention, a computer-readable storage medium can be any tangible medium that can contain or store a program used by or in conjunction with an instruction execution system, apparatus, or device.

[0072] Computer-readable signal media may include propagated data signals having computer-readable program code embodied therein (e.g., in baseband or as part of a carrier wave). Such propagated signals may take any of a variety of forms, including, but not limited to, electromagnetic, optical, or any suitable combination thereof. A computer-readable signal medium may be any computer-readable medium that is not a computer-readable storage medium and may convey, propagate, or deliver a program used by or in conjunction with an instruction execution system, apparatus, or device.

[0073] Program code embodied on a computer-readable medium can be transmitted using any suitable medium (including, but not limited to, wireless, wired, fiber optic, cable, RF, etc., or any suitable combination thereof). Computer program code for carrying out the operations of various aspects of the invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​(such as Java™, Smalltalk, or C++) and conventional procedural programming languages ​​(such as the "C" programming language or similar programming languages). The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)) or can be connected to an external computer (e.g., via the Internet provided by an Internet service provider).

[0074] Various aspects of the invention are described below with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, particularly a microprocessor or central processing unit (CPU), to produce a machine such that the instructions, executable via the processor of the computer, other programmable data processing apparatus, or other device, create means for implementing the functions / actions specified in the flowchart illustrations and / or one or more block diagram blocks.

[0075] These computer program instructions may also be stored in a computer-readable medium that can instruct a computer, other programmable data processing apparatus, or other device to operate in a particular manner, such that the instructions stored in the computer-readable medium produce an article of writing, which includes instructions that implement functions / actions specified in flowcharts and / or one or more block diagrams.

[0076] Computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus, or other device to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide for implementing the functions / actions specified in the flowchart and / or one or more block diagram boxes.

[0077] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code, which includes one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions described in the blocks may not appear in the order shown in the figures. For example, two blocks shown consecutively may actually be executed substantially simultaneously, or sometimes these blocks may be executed in reverse order, depending on the functions involved. It will also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a system based on dedicated hardware, or a combination of dedicated hardware and computer instructions, that performs the specified function or action.

[0078] In addition, a computer program for implementing the methods described herein is provided, as well as a non-transitory computer-readable storage medium for storing the computer program. The computer program may, for example, be downloaded (updated) to an existing data processing system, or stored during the manufacture of such systems.

[0079] Unless otherwise explicitly stated, elements and aspects discussed with respect to a particular embodiment or with respect to a particular embodiment may be suitably combined with elements and aspects of other embodiments. Embodiments of the invention will be further described with reference to the accompanying drawings, which schematically illustrate embodiments according to the invention. It will be understood that the invention is not limited in any way to these specific embodiments. Attached Figure Description

[0080] Various aspects of the invention will be explained in more detail with reference to exemplary embodiments shown in the accompanying drawings, in which:

[0081] Figure 1 An embodiment of a system for monitoring plant pollination is illustrated schematically;

[0082] Figure 2 A heatmap indicating the corresponding value for the corresponding area within the monitored area;

[0083] Figure 3 An embodiment of a system including a garden lighting system is illustrated schematically;

[0084] Figure 4 An embodiment of a system including a sound generation system is illustrated schematically;

[0085] Figure 5 This is a flowchart illustrating a method according to an embodiment;

[0086] Figure 6 This is a flowchart illustrating a machine learning algorithm used to construct a model for estimating pollination quality parameters;

[0087] Figure 7 A data processing system according to an embodiment is shown. Detailed Implementation

[0088] In the accompanying drawings, the same reference numerals indicate the same or similar elements.

[0089] Figure 1 This is a schematic representation of an embodiment of the system 1 for monitoring plants disclosed herein. Specifically, Figure 1 A greenhouse 10 is shown, containing several plants 6 with one or more flowers 8. The plants can be of any type, as long as they are pollinated. Examples of plants include: fruit plants such as grapevines, blueberry plants, strawberry plants, raspberry plants, blackberry plants, apple trees, cherry trees, peach trees, etc.; and vegetable plants such as cucumber plants, tomato plants, eggplants, pepper plants, etc.

[0090] The system includes multiple microphones 2a-2f for monitoring areas inside greenhouse 10. The microphones can be installed in existing lighting fixtures, or at least in the locations of existing lighting fixtures. The microphones can be suspended above the plants. Alternatively or additionally, the microphones can be located between the plants. Each microphone is configured to monitor a sub-area of ​​the monitored area. For illustration, microphone 2a is configured to monitor sub-area 4a, microphone 2b is configured to monitor sub-area 4b, and so on. Each microphone can record sounds produced by pollinators (such as bumblebees) present in the sub-area of ​​the microphone. Furthermore, each microphone can output one or more signals indicating the recorded sounds. These signals can be output to data processing system 100 via a corresponding communication connection between the microphone and data processing system 100. In the figures, solid lines to and from data processing system 100 indicate such communication connections. Each communication connection mentioned herein can be a wired connection, a wireless connection, or a connection that is partly wired and partly wireless. In one example, the microphones can be connected to a packet-switched network such as the Internet and communicate with data processing system 100 via the Internet. The data processing system is, for example, a remote server.

[0091] The data processing system 100 can be a distributed system, for example, some components such as memory elements may be located at one or more microphones, while other components such as microprocessors may be located far from the microphones (e.g., at a remote server).

[0092] In any case, the data processing system 100 is configured to receive one or more signals indicating recorded sound from each of a plurality of microphones via one or more input interfaces 112 of the data processing system. The data processing system 100 is further configured to determine, using at least one processor 102, a value of a pollination quality parameter indicating the extent to which one or more flowers in a monitored area are pollinated by pollinators present in the monitored area, based on the signals received from the plurality of microphones. The data processing system 100 may, for example, be configured to count the number of pollination events in the monitored area or an area within the monitored area and / or the duration of each pollination event in the monitored area or an area within the monitored area. As used herein, a pollination event can be understood to include a pollinator visiting a flower and pollinating it. The data processing system 100 may, for example, count the average number of pollination events per unit time (e.g., per day) per flower for a specific area within the monitored area and / or the entire monitored area as a whole. Based on the number of pollination events and / or based on their measured duration, the value of the pollination quality parameter can be determined.

[0093] Figure 1 The overlapping of sub-region 4 monitored by microphones is shown. However, this is not strictly necessary. Some sub-regions may overlap, while others may not overlap with any other sub-region. Furthermore, embodiments where no sub-region 4 overlaps with another sub-region 4 are envisioned. It should be understood that if two sub-regions at least partially overlap, their two associated microphones can record the sounds of pollinators present in the overlapping area. For illustration, sub-regions 4a and 4b at least partially overlap. This means that microphones 2a and 2b will record sounds as produced by pollinators present in the overlapping area. The data processing system 100 can then be configured to determine the value of a pollination quality parameter, indicating the degree of pollination of the flowers in the overlap between sub-regions 4a and 4b, based on both the signal from microphone 2a and the signal from microphone 2b. By having multiple microphones cover the same area, the accuracy of detecting pollination events in that area can be improved. Furthermore, this also allows for better localization of the measured pollination events. After all, if the same pollination event is recorded in both the sound recorded by microphone 2a and the sound recorded by microphone 2b, then the pollination event must have occurred in the overlap between sub-regions 2a and 2b. The overlap area between the two microphones may be relatively large.

[0094] In one embodiment, the multiple microphones may comprise one or more microphone arrays known in the art, wherein each microphone in the array can monitor substantially the same area. This makes it possible to retrieve the direction of sound and thus determine the location of the recorded sound. The advantage of doing so is that a large area can be monitored and stationary position information can be determined from the recorded sound. The microphone array can also be used for beamforming to improve the signal-to-noise ratio by removing noise sources. Using a microphone array enables more precise localization of pollination events and also provides indication of the pollinator's flight path.

[0095] The data processing system 100 can be configured to determine corresponding pollination quality parameters for multiple regions. It should be understood that the region where the pollination quality parameter value is determined does not necessarily coincide with sub-region 4 of the microphone 2. However, in one embodiment, each region corresponds to a sub-region. The data processing system 100 then effectively determines the value of the pollination quality parameter for each sub-region, indicating the degree to which one or more flowers are pollinated in the sub-region in question.

[0096] The data processing system 100 can further be configured to display areas of corresponding pollination quality parameters and their corresponding values ​​on a display 16 via one or more output interfaces 114. This can be presented in the form of a heatmap.

[0097] Figure 2 An example of a display 16 presenting pollination quality parameters for each region is shown. Display 16 presents three regions, A, B, and C. Regions B and C have similar values ​​for their pollination quality parameters. In this example, it is assumed that the flowers in regions B and C are well pollinated. However, the pollination quality parameter for region A has a relatively low value, that is, relatively low compared to the values ​​in regions B and C. This lower value indicates that the flowers in region A are not as well pollinated as those in regions B and C. A greenhouse operator viewing this heatmap can then check region A to see if the conditions in region A are as they should be and to see if he or she can take steps to improve pollination in region A. Conditions can refer to environmental conditions such as light conditions, sound, vibration, airflow, temperature, humidity, etc., and therefore the greenhouse operator can take steps to change one or more of these environmental conditions to improve pollination.

[0098] Therefore, region A can be identified as the region of interest as described above, having pollination quality parameters below a threshold. Which threshold to use largely depends on the available resources (which plants, which pollinators, etc.); however, a suitable threshold can be determined for any situation.

[0099] Figure 3An embodiment is schematically illustrated, wherein the system includes a pollination control system configured to influence pollination in a selected area. In this embodiment, the system also includes multiple microphones; however, for clarity, these are not shown. Figure 2 As shown in the diagram. The data processing system 100 is configured to control the pollination control system to improve pollination in one or more regions of interest based on the determination of those regions. Figure 3 In this system, the pollination control system includes a horticultural lighting system 12 configured to generate pollination light suitable for influencing pollination. As explained above, the horticultural lighting system can be controlled to provide pollination light in one or more areas of interest to improve pollination in those areas.

[0100] Figure 4 An embodiment of the system is schematically illustrated, which also includes a pollination control system implemented as a sound generation system 14, configured to generate acoustic signals suitable for influencing pollination. This embodiment also includes multiple microphones. These are not shown for clarity. The sound generation system 14 preferably includes multiple microphones. These microphones can then be placed at different locations throughout the monitored area, allowing acoustic signals to be selectively provided in different areas, preferably the identified areas of interest. The data processing system 100 is configured to control the sound generation system to provide acoustic signals in one or more areas of interest, based on the determination of those areas, to improve pollination in those areas.

[0101] Figure 5 This is a flowchart illustrating an embodiment of a method for monitoring plant pollination. In steps 30-37, microphone 2... a -2 N Signals are sent to the data processing system 100. The data processing system 100 then receives one or more signals from each microphone. These signals indicate the sound recorded by the microphones.

[0102] In step 38, the data processing system 100 determines, based on one or more signals received in steps 30-37, a value for a pollination quality parameter indicating the degree of pollination of one or more flowers in the monitored area. This step can be implemented as the data processing system 100 determining a value for an overall pollination quality parameter indicating the degree of pollination of flowers in the entire area monitored by multiple microphones. Additionally or alternatively, this step can be implemented as the data processing system 100 determining a value for a specific area, or as the data processing system 100 determining a corresponding value for a corresponding area within the monitored area.

[0103] The data processing system can be configured to determine a pollination event by identifying sounds and / or sound patterns associated with a pollination event from one or more signals from multiple microphones. Predicting species identity of bumblebees through analysis offlightbuzzing sounds, The International Journal of Animal Sound and its Recording, Volume 26, 2017-Issue 1, pages 63-76, May 2016 (hereinafter referred to as )of Figure 1 The spectrograph shown illustrates the spectrum of an ultrasonically processed sound associated with a pollination event. The data processing system 100 can therefore be configured to identify the sound by recognizing its spectrum.

[0104] In one embodiment, the data processing system is configured to identify sound patterns, which can be understood as time-delayed sound patterns, and include a first time period containing sounds associated with pollinator flight, a subsequent second time period with substantially no sounds associated with pollinator flight, and a subsequent third time period containing sounds associated with pollinator flight. Note that... of Figure 1 The sound patterns associated with pollination events are also shown, as it shows the sounds between 0 and 10 seconds associated with bee flight, the sounds between 10 and 15.5 seconds with virtually no sounds associated with pollinator flight, and then the sounds associated with pollinator flight again starting from 15.5 seconds.

[0105] Bees (such as bumblebees) typically perform the following series of actions when pollinating flowers. Based on these actions and the sounds they are associated with, sound patterns can be identified in recorded sounds.

[0106] - Approaching the flower: The microphone (either located near the flower or pointed at it) captures the sound of the bumblebee in its flight mode (with a distinctive wing frequency). This approach can be inferred from the increase in the sound amplitude.

[0107] - Landing on the flower: Upon landing, the sound suddenly "disappears" (because the bumblebee fixes its wings). This is the starting point for "measuring" how long the bumblebee stays on the flower.

[0108] - Staying on flowers: The periods during which bumblebees stay on flowers (interacting, collecting nectar and pollen) are either quiet times for the bees (the time between landing and taking off), or times when the bees produce ultrasonic sounds or ultrasonic sound patterns. This time is important because a sufficiently long period means the bee has a "beneficial" interaction with the flower (enjoying the food it finds), and is therefore most likely to fertilize the flower, as there is a high probability of fertilization when deep inside the flower.

[0109] - Takeoff from the flower: Takeoff can be detected by the reactivation of the sound. This can be characterized not only by the start of the sound, but also by an increase in the sound frequency and amplitude.

[0110] -Flight Away: The flight away event is similar to the approach phase, but the opposite. Takeoff is detected first, and then Bumblebee enters a fixed wing frequency mode, and the amplitude decreases as the distance between Bumblebee and the microphone increases.

[0111] - Communication signals: When a bumblebee is generating sounds, such as to recruit other bees, the likelihood of pollination increases. One reason is that the bee indicates that the flower is a good food source it will visit. Furthermore, it recruits more pollinators, thus increasing the chances that more pollinators will visit the flower.

[0112] Optionally, as indicated by the dashed lines, the data processing system 100 controls the horticultural lighting system 12 to locally generate pollination light in order to improve pollination in a selected area (step 40); and / or controls the sound generation system 14 to locally provide sound signals in order to improve pollination in a selected area (step 42); and / or controls the display 16 to optionally present, in the form of a heat map, the values ​​of one or more determined pollination quality parameters of one or more corresponding areas in the monitored area on the display (step 44).

[0113] Figure 6 This is a flowchart illustrating an embodiment of the method, in which a machine learning algorithm is executed to improve the ability of a data processing system to determine the values ​​of pollination quality parameters based on recorded sounds.

[0114] Initially, training data 50 is obtained. This training data 50 includes multiple sets of recorded sounds 52 for each batch of plants, wherein each set of recorded sounds is associated in the training data 50 with an actual value 54 of a pollination quality parameter that indicates the degree of pollination of the flowers in the associated batch.

[0115] This training data 50 is then used in step 56 to correlate pollination quality values ​​with the recorded sounds. Step 56 therefore includes correlating pollination quality values ​​with the recorded sounds. The output of step 56 is a pollination quality parameter estimation model 58, which is used in step 62 to determine one or more values ​​64 of the pollination quality parameters based on the recorded sounds 60. The output of step 62 is a set 64 of one or more values ​​of the corresponding one or more pollination quality parameters.

[0116] Optionally, as indicated by the dashed line, step 68 is performed. In this step 68, the value of the pollination quality parameter as determined in step 62 is compared with the actual measured value 66 of the pollination quality parameter to see how accurate the determined pollination quality parameter 64 is. Of course, the value determined in step 62 and the actual measured value 66 used for comparison in step 68 are for the same batch of plants. The actual measured value 66 and the recorded sound 60 can then be used as training data to improve the correlation, i.e., to improve the pollination quality parameter estimation model used in step 62.

[0117] Figure 7 A block diagram illustrating a data processing system according to one embodiment is provided. Generally, a data processing system may also be referred to herein as a data processor, data processing unit, data processing server, or data processing computer.

[0118] like Figure 7 As shown, the data processing system 100 may include at least one processor 102 coupled to a memory element 104 via a system bus 106. Thus, the data processing system can store program code within the memory element 104. Furthermore, the processor 102 can execute program code accessed from the memory element 104 via the system bus 106. In one aspect, the data processing system may be implemented as a computer suitable for storing and / or executing program code. However, it should be understood that the data processing system 100 may be implemented in the form of any system including a processor and memory capable of performing the functions described herein.

[0119] Memory element 104 may include one or more physical memory devices, such as, for example, local memory 108 and one or more mass storage devices 110. Local memory may refer to random access memory or other non-persistent storage devices generally used during the actual execution of the program code. Mass storage devices may be implemented as hard disk drives or other persistent data storage devices. Processing system 100 may also include one or more cache memories (not shown) that provide temporary storage for at least some of the program code to reduce the number of times the program code must be retrieved from mass storage device 110 during execution.

[0120] Optionally, the input / output (I / O) devices depicted as input device 112 and output device 114 may be coupled to the data processing system. Examples of input devices may include, but are not limited to, multiple microphones, a keyboard, a pointing device such as a mouse, or a touch-sensitive display, as mentioned herein. Examples of output devices may include, but are not limited to, the display 16 mentioned herein, the pollination control system mentioned herein, such as the garden lighting system mentioned herein, and / or the sound generation system mentioned herein. Input and / or output devices may be coupled to the data processing system directly or through an intermediate I / O controller.

[0121] In embodiments, the input and output devices may be implemented as a combined input / output device (in... Figure 7 (Dashed lines are used to illustrate input device 112 and output device 114). An example of such a combined device is a touch-sensitive display, sometimes also called a "touchscreen display" or simply a "touchscreen". In such embodiments, input to the device can be provided by the movement of a physical object (such as, for example, a stylus or a user's finger) on or near the touchscreen display.

[0122] Network adapter 116 can also be coupled to the data processing system to enable it to couple to other systems, computer systems, remote network devices, and / or remote storage devices via an intermediate private or public network. The network adapter may include a data receiver for receiving data transmitted to the data processing system 100 from the systems, devices, and / or networks, and a data transmitter for transmitting data from the data processing system 100 to the systems, devices, and / or networks. Modems, cable modems, and Ethernet cards are examples of different types of network adapters that can be used with the data processing system 100.

[0123] like Figure 7 As illustrated, memory element 104 can store application program 118. In various embodiments, application program 118 may be stored in local memory 108, one or more mass storage devices 110, or isolated from both local memory and mass storage devices. It should be understood that data processing system 100 may further execute an operating system that facilitates the execution of application program 118. Figure 7 (Not shown in the image). The application 118, implemented as executable program code, can be executed by the data processing system 100 (e.g., by the processor 102). In response to executing the application, the data processing system 100 can be configured to perform one or more operational or method steps described herein.

[0124] In one aspect, the data processing system 100 may represent a server. For example, the data processing system may represent an (HTTP) server, in which case the application 118 may be configured to perform (HTTP) server operations when executed.

[0125] Various embodiments of the present invention can be implemented as a program product for use with a computer system, wherein the program(s) of the program product define the functionality of the embodiments (including the methods described herein). In one embodiment, the program(s) may be contained on a variety of non-transitory computer-readable storage media, wherein, as used herein, the expression “non-transitory computer-readable storage media” includes all computer-readable media, with the sole exception of transient propagation signals. In another embodiment, the program(s) may be contained on a variety of transient computer-readable storage media. Illustrative computer-readable storage media include, but are not limited to: (i) non-writable storage media on which information is permanently stored (e.g., read-only memory devices within a computer, such as CD-ROM discs readable by a CD-ROM drive, ROM chips, or any type of solid-state non-volatile semiconductor memory); and (ii) writable storage media on which changeable information is stored (e.g., flash memory, floppy disks within a floppy disk drive or hard disk drive, or any type of solid-state random access semiconductor memory). The computer program may run on the processor 102 described herein.

[0126] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used herein, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that, when used in this specification, the terms “comprising” and / or “including” specify the presence of the stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0127] All the means or steps plus functional elements in the following claims are intended to include any structure, material, action, and equivalent for performing a function in combination with other claimed elements as specifically claimed. Descriptions of embodiments of the invention have been shown for illustrative purposes, but are not intended to be exhaustive or limited to the implementations in the disclosed forms. Many modifications and variations will be apparent to those skilled in the art. Embodiments have been chosen and described in order to best explain the principles of the invention and some practical applications, and to enable others skilled in the art to understand the invention with respect to various embodiments with various modifications suitable for the particular intended use.

Claims

1. A system for monitoring pollination of a plant with one or more flowers, the system comprising: A plurality of microphones for monitoring an area including the one or more flowers, wherein each of the plurality of microphones is configured to monitor a sub-region of the monitored area, wherein each microphone is adapted to record sounds produced by pollinators present in the sub-region of the microphone, and is configured to output one or more signals indicating the recorded sounds, the system further comprising: A data processing system comprising at least one input interface and at least one processor, said at least one processor being configured to - Receive one or more signals indicating the recorded sound from each of the plurality of microphones via the at least one input interface, and - The at least one processor determines a value of a pollination quality parameter indicating the extent to which one or more flowers in a monitored area are pollinated based on one or more signals received from the plurality of microphones, wherein the value of the pollination quality parameter is determined based on the number of pollination events and / or the duration of each pollination event as determined by the data processing system based on one or more signals received from the plurality of microphones, wherein each pollination event includes a pollinator visiting the flower, and wherein the data processing system is configured to determine the pollination event by identifying sounds associated with the pollination event and / or sound patterns associated with the pollination event from one or more signals from the plurality of microphones.

2. The system of claim 1, wherein the data processing system is configured to - For each of multiple areas within the monitored area, determine the number of pollination events in that area and / or the duration of each pollination event in that area based on one or more signals received from the multiple microphones, each pollination event including pollinator visit to the flower, and - For each region, a pollination quality parameter indicating the extent to which one or more flowers in the region are pollinated is determined based on the number of pollination events identified in the region and / or the duration of the pollination events identified in the region.

3. The system according to claim 2, The sound pattern described is a time-delayed sound pattern, and includes a first time period containing sounds associated with the pollinator's flight, a subsequent second time period with substantially no sounds associated with the pollinator's flight, and a subsequent third time period containing sounds associated with the pollinator's flight; and The sounds associated with the pollination event are ultrasonically processed sounds and / or the sound patterns associated with the pollination event are ultrasonically processed sound patterns.

4. The system of claim 1, wherein the plurality of microphones includes a first microphone configured to monitor a first sub-region of the monitored area and a second microphone configured to monitor a second sub-region of the monitored area, wherein the first sub-region and the second sub-region at least partially overlap, and wherein the data processing system is configured to - Receive one or more signals from the first microphone indicating the sound recorded in the first sub-region, and receive one or more signals from the second microphone indicating the sound recorded in the second sub-region, and - Based on the first or more signals and the second or more signals, determine the value of a pollination quality parameter indicating the degree to which one or more flowers in a region of the monitored area are pollinated, the region including the at least partial overlap between the first sub-region and the second sub-region.

5. The system of claim 1, wherein the data processing system is further configured to execute a machine learning algorithm to improve the ability of the data processing system to determine the value of the pollination quality parameter, wherein executing the machine learning algorithm includes: - Receive training data, which includes multiple sets of recorded sounds from each batch of plants, wherein each set of recorded sounds is associated in the training data with an actual value of a pollination quality parameter indicating the degree of pollination of the perianth in the associated batch, and - Construct a pollination quality parameter estimation model based on the training data.

6. The system of claim 2, wherein the data processing system is configured to -Based on the values ​​of pollination quality parameters determined for each of the multiple regions, one or more regions of interest are identified among the multiple regions, each region of interest having an associated pollination quality parameter value below a threshold.

7. The system according to claim 6, further comprising: A pollination control system configured to influence pollination in a selected area by controlling one or more environmental conditions selected from lighting conditions, sound, vibration, airflow, temperature, and humidity, wherein the data processing system is configured to - Based on the determination of the one or more areas of interest, the pollination control system is controlled to improve pollination in the one or more areas of interest by controlling environmental conditions selected from lighting conditions, sound, vibration, airflow, temperature and humidity in one or more of the selected areas.

8. The system of claim 7, wherein the data processing system is configured to control the pollination control system to improve pollination in the one or more areas of interest by controlling environmental conditions in one or more of the selected areas other than the one or more areas of interest, based on the determination of the one or more areas of interest.

9. The system of claim 7 or 8, wherein the data processing system is configured to control the pollination control system to control pollination in the plurality of regions based on the determined value of a pollination quality parameter for each of the plurality of regions, so as to achieve substantially uniform pollination in the plurality of regions of the monitored region.

10. The system of claim 9, wherein the pollination control system includes a horticultural lighting system configured to generate pollination light suitable for influencing pollination, wherein The data processing system is configured to control the horticultural lighting system to provide pollination light in the one or more areas of interest, based on the determination of the one or more areas of interest, to improve pollination in the one or more areas of interest. The pollination light mentioned therein includes blue and / or long UVA wavelengths.

11. The system of claim 9, wherein the pollination control system includes a sound generation system configured to generate an acoustic signal suitable for influencing pollination, wherein The data processing system is configured to, based on the determination of the one or more regions of interest, control the sound generation system to provide acoustic signals in the one or more regions of interest to improve pollination in the one or more regions of interest. The acoustic signals mentioned include the sound of pollinators flying or ultrasonically processed sounds.

12. A method for monitoring pollination of a plant with one or more flowers, the method comprising: - Receive one or more signals from each of a plurality of microphones used for monitoring an area including the one or more flowers, indicating the recording of sound, wherein Each of the plurality of microphones is configured to monitor a sub-region of the monitored area, wherein each microphone is adapted to record sounds produced by pollinators present in the sub-region of the microphone, the method further comprising: - The number of pollination events and / or the duration of each pollination event are determined based on one or more signals received from the plurality of microphones, wherein each pollination event includes a pollinator visiting the flower, and the pollination event is determined by identifying sounds associated with the pollination event and / or sound patterns associated with the pollination event from one or more signals from the plurality of microphones. - Based on the number of pollination events and / or the duration of each pollination event, determine the value of a pollination quality parameter indicating the extent to which one or more flowers in the monitored area are pollinated.

13. The method of claim 12, further comprising: - For each of the multiple areas within the monitored area, a pollination quality parameter indicating the degree to which one or more flowers in that area have been pollinated is determined based on one or more signals received from the multiple microphones, and - Based on the determined pollination quality parameter values ​​for each of the multiple regions, one or more regions of interest are identified, each region of interest having an associated pollination quality parameter value below a threshold, and - Based on the determination of the one or more areas of interest, a pollination control system is controlled, the pollination control system being configured to influence pollination in the selected areas by controlling environmental conditions selected from lighting conditions, sound, vibration, airflow, temperature and humidity in the selected areas, in order to improve pollination in the one or more areas of interest.

14. A data processing system for use in a system for monitoring plant pollination according to any one of claims 1-11, the data processing system comprising: - At least one input interface, adapted to receive one or more signals indicating recorded sound from each of a plurality of microphones, and - At least one processor adapted to determine, based on one or more signals from the plurality of microphones, a value of a pollination quality parameter indicating the extent to which one or more flowers in a monitored area are pollinated, wherein the value of the pollination quality parameter is determined based on the number of pollination events and / or the duration of each pollination event as determined by the data processing system based on one or more signals received from the plurality of microphones, wherein each pollination event includes a pollinator visiting the flower, and wherein the data processing system is configured to determine the pollination event by identifying sounds associated with the pollination event and / or sound patterns associated with the pollination event from one or more signals from the plurality of microphones.

15. A computer program comprising instructions that, when executed by at least one processor of the data processing system according to claim 14, cause the data processing system to perform the method according to claim 12 or 13.

Images