ARTIFICIAL POLLINATION METHODS AND APPARATUS FOR CARRYING IT OUT

Abstract

Novel, universal, well-controlled, scalable, easy-to-use, and cost-effective field / orchard management methods and systems are provided for the artificial pollination of agricultural areas, such as orchards and fields.

Description

ARTIFICIAL POLLINATION METHODS AND DEVICES FOR CARRYING IT OUT Technical Field of the Invention The invention relates to the field of artificial pollination. More specifically, the invention relates to novel systems and methods for managing pollination and to methods for increasing crop yield. Background of the Invention Pollination is a process that involves the transfer of pollen grains from the male part of a plant to the female part (stigma). This process is carried out naturally by the wind, small birds, insects (especially bees), and others. This process is crucial for subsequent fertilization, seed production, and the formation of fruits and vegetables. The disappearance of various natural pollinators is a phenomenon that, if it worsens, will undoubtedly cause great harm to the production of various crops that depend almost exclusively on insect pollination. Furthermore, the process of globalization has displaced the production of various crops from their natural habitat to different geographical areas, where the natural pollinators that evolved alongside the crop are no longer present.Their absence has a crucial impact on pollination quality, as local pollinators may be unable to pollinate efficiently due to inefficient pollen extraction, either due to inadequate body geometry and size or a lack of attraction to crop nectar and pollen; these factors combined affect crop yield and quality. Furthermore, the insect-based pollination process depends on insect behavior, which could be altered by weather conditions, temperatures, and other conditions beyond human control. Artificial pollination is a solution that helps overcome the aforementioned difficulties in a controlled and efficient manner, thus providing an increase in crop yield and quality. Currently available solutions suffer from several shortcomings. For example, manual pollination is the simplest and most economical method. Using different tools, such as brushes, pollen grains can be gently collected from a male flower and applied directly to the stigma of the female flower. Another manual pollination method is rubbing the male organs of cut flowers onto the female organs of pollinated flowers. These methods are useful on a small scale; however, they require skilled human labor for large-scale application. Other solutions offer mass collection and processing of flowers to extract the pollen grains.The collected pollen powder is then applied to the flowers using various techniques. This complicated process is costly and time-consuming, and could not be performed in the field or orchard. This method is suitable for certain types of crops that have a short mass flowering period and a large number of pollen grains per flower. Scalable, field / orchard-based, cost-effective, well-controlled, and easy-to-use systems and methods for artificial pollination, yield enhancement, and field / orchard management remain a long-standing unmet need. Brief Summary of Invention Accordingly, it is a primary objective of the present invention to provide universal, in-field / orchard, well-controlled, scalable, easy-to-use, and cost-effective methods and management systems for the artificial pollination of agricultural areas such as orchards and fields. The invention provides a pollination management system for an agricultural area comprising: a. a pollination module, wherein said module comprises a pollen collecting element configured to collect pollen; and a pollen applying element configured to release the pollen; b. a data acquisition module operatively coupled to the pollination module, wherein said data acquisition module comprises at least one sensor; c. a server in communication with the pollination module and the data acquisition module, wherein the server is configured to process the data acquired by the data acquisition module; d. an operations module comprising a controller in communication with the server and the pollination module, wherein said controller is configured to provide instructions to the pollination module; and, 70C7 I η / 77Π7 / Ε / ΥΙ e. a user interface; where said system is configured to artificially pollinate the agricultural area or a part thereof. The invention further provides a method of artificial pollination of an agricultural area in need of pollination or a part thereof, comprising: a. providing the pollination management system according to the embodiments of the invention; b. data acquisition by the data acquisition module of the pollination management system; c. transmission of the acquired data to the pollination management system server; d. processing of the data from step b) by the server to generate an output; e. transmitting the output of step d) to the operations module controller; and f. pollination of the agricultural area using the pollination module, wherein the step of pollinating the agricultural area is carried out according to instructions provided by the controller, and where the instructions provided by the controller are based on the result of step d). The invention further provides a method for increasing crop yield comprising providing an artificial pollination management system, wherein said pollination management system comprises a pollination module; and wherein said pollination module comprises at least one pollen collecting element; and wherein said pollen collecting element is configured to apply electrostatic forces to pollen grains, thereby attracting the pollen grains to the pollen collecting element. The invention further provides a pollen collecting element comprising a high voltage power supply, an electrode, a pollen collecting surface and, optionally, a container, wherein said high voltage power supply supplies high voltage to the electrode; and wherein said 70C7 I η / 77Π7 / Ε / YI electrode is configured to generate electric fields that apply electrostatic forces on the pollen grains; and wherein said pollen grains are attracted towards the pollen collection surface of the element. The invention further provides a computer-implemented method for artificially pollinating an agricultural area or a part thereof comprising a crop, the process comprising: a. providing the artificial pollination system according to the embodiments of the invention; b. data collection through the data acquisition module; c. Data processing and assessment of the crop status based on a set of parameters, extracted from the data, that indicate the crop status; d. provide instructions to the controller based on the crop status; and e. pollination of the agricultural area or part thereof. Additional features and advantages of the invention will become apparent from the following description and accompanying drawings. Brief Description of the Drawings A block diagram of an illustrative embodiment of a pollination management system is presented in FIG: 1; A flow diagram of an illustrative embodiment of the pollination method is presented in FIG: 2; A flow diagram of an illustrative embodiment of the computer-implemented pollination method is presented in FIGS. 3A-C; A graphic representation of the results of pollination in avocado trees is presented in FIG. 4A-B; A schematic representation of an illustrative embodiment of a pollen collecting element is presented in FIG. 5; and 70C7 I η / 77Π7 / Ε / ΥΙ A graphic representation of the results of pollination in avocado trees is presented in FIG: 6A-B. Detailed Description of the Invention Before explaining in detail at least one embodiment of the invention, we wish to make it clear that the application of the invention is not limited to the details of construction and arrangement of components presented in the following description or illustrated in the accompanying drawings. The invention is applicable to other embodiments or can be practiced or embodied in various ways. Furthermore, it should be understood that the phraseology and terminology employed herein are for descriptive purposes only and should not be considered as limiting. According to some embodiments, the invention provides a pollination management system for an agricultural area comprising: a) a pollination module, wherein said module comprises a pollen collecting element configured to collect pollen; and a pollen application element configured to release the pollen; b) a data acquisition module operatively coupled with the pollination module, wherein said data acquisition module comprises at least one sensor; c) a server in communication with the pollination module and the data acquisition module, where the server is configured to process the data acquired by the data acquisition module; d) an operations module comprising a controller in communication with the server and the pollination module, wherein said controller is configured to provide instructions to the pollination module; and, e) a user interface; wherein said system is configured to artificially pollinate the agricultural area or a desired portion of said agricultural area. In one embodiment, the agricultural area is a field. In another embodiment, the agricultural area is an orchard. As used herein, the term "field" is understood to mean an enclosed, cleared area of ​​land used for growing crops. The list of crops of the invention includes, but is not limited to, crops such as corn, soybeans, wheat, rice, oilseeds, cotton, grapes, sugarcane, fruits, and vegetables. As used herein, the term "orchard" means an area of ​​land where crop trees are grown, while "crop tree" refers to, but is not limited to, trees that produce or have the potential to produce the desired product. A non-limiting list of tree crops of the invention includes apple, avocado, walnut, cocoa, kiwi, peach, pear, citrus fruits such as orange, lemon, grapefruit, and tangerine; cherry, plum, apricot, mango, lychee; or any other tree crop that may benefit from the management system of the invention.As used herein, the term "part" refers, without limitation, to a distinct portion or section of the whole, while "total" refers to the entire agricultural area. The part can be of any size, shape, or geometry. It can be a large portion of the area or a small portion of the area. The size of the portion of the area can be predetermined or chosen sporadically. According to some embodiments, the data acquisition module is configured to transmit the acquired data to the server. According to some embodiments, the instructions provided by the controller to the pollination module are based on the data processed by the server. In the context of the invention, the term “acquired data” should be understood as data acquired by the data acquisition module by means of the at least one sensor and / or data received and / or collected and / or transferred to and / or collected from an external source. Typically, the data acquired by the data acquisition module is a combination of the data obtained by the at least one sensor and data from an external source. The non-limiting list of data received from the external source includes field-related metadata, weather measurements and weather forecast data, and visual field data.The limited list of field metadata may include plant types, planting maps, plant ages, natural pollinators corresponding to hives, and weather data. According to some embodiments, the weather data may be obtained by any of the following: a third-party service, from the client's weather station, or using at least one sensor of the data acquisition module. According to some embodiments, the visual data may be obtained using a third-party provider, collected by image sensors of the data acquisition unit and / or drones, and / or by third parties, such as, but not limited to, satellite imaging companies. In one embodiment, the pollination module controller provides instructions based on the data processed by the server.As used herein, the term “sensor” refers, without limitation, to a device that detects and responds to some type of input from the physical environment. The specific input could be, but is not limited to, light, heat, motion, humidity, pressure, or any other environmental input. The non-limiting list of sensors of the invention includes one or more IR cameras, temperature sensors, humidity sensors, LiDAR sensors, sound recorders, GNSS, 4D imaging sensors, hyperspectral imaging, IMUs, light sensors, or any other applicable sensors, or a combination thereof. In one embodiment, the data acquisition module comprises a plurality of sensors. In one embodiment, the data acquisition module comprises a plurality of sensors of the same type. In another embodiment, the data acquisition module comprises a plurality of different sensors.In one embodiment, the data acquisition module comprises a set of sensors that are activated as required. In one embodiment, the user defines the combination of different sensors. In one embodiment, the data acquisition module comprises a predefined combination of sensors. According to some embodiments, the invention provides a pollen-collecting element of the pollination module comprising a high-voltage power supply, an electrode, a pollen-collecting surface, and, optionally, a container. According to some embodiments, the pollen-collecting element is configured to generate electric fields that apply electrostatic forces to the pollen grains, thereby attracting the pollen grains toward the pollen-collecting surface. In one embodiment, the pollen-collecting element further comprises at least one internal control unit, a vibration motor, or a suction unit. According to some embodiments, the server is configured to receive the acquired data, store the acquired data, generate a pollination heat map based on the acquired data, or any combination thereof. In one embodiment, the server is further configured to transmit the pollination heat map to the operations module. In the context of the invention, the term “heat map” should be understood, without limitation, as a holistic view of the field and / or orchard, with regard to pollination, including one or more of the following: identification of the flowering index in different parts of the fields, evaluation of the pollination efficiency in the areas based on environmental data, marking the areas to be pollinated based on their needs and previous pollination activities and based on other environmental factors (weather, bee activity, etc.). According to some embodiments, the data is indicative of the state of the crop, such as the morphological and phenological stages of flowering, plant health, and environmental suitability for pollination. In one embodiment, the data comprises data that is indicative of pollination efficiency. As used herein, the term "data" refers, without limitation, to any information and / or input related to the state of the environment and ecosystem impacts. The data may be acquired by the sensors of the data acquisition module and / or may be obtained from external sources, such as, but not limited to, weather forecasts, insect activity, or any other information that may be relevant. Data acquired by the sensors may include, but are not limited to, health / disease status, yield estimates, flowering stage, and others. According to some embodiments, the pollination management system of the invention is further configured to process real-time data acquired from the agricultural area and pollinate the agricultural area based on said real-time data. In one embodiment, the real-time data is selected from data acquired by at least one sensor of the data acquisition module, data received by the data acquisition module from an external source, or a combination thereof. As used herein, the term “real-time” refers, without limitation, to a configuration in which input data is processed within milliseconds so that it is substantially immediately available as feedback. In one embodiment, the real-time data is selected from data acquired from the plurality of sensors, data collected from an external source, or a combination thereof. According to some embodiments, the server is further configured to control at least one of: the area to be pollinated, the pollination time, the frequency of the pollination episodes, the number of pollination episodes, the duration of each pollination episode, or any combination thereof. In one embodiment, the pollination of the agricultural area comprises more than one pollination episode. In one embodiment, the pollination of the agricultural area comprises a predefined number of pollination episodes with predefined time intervals. In one embodiment, each pollination episode is performed based on real-time data acquired by the data acquisition module. In one embodiment, the location of the area to be pollinated is determined based on the data and / or real-time data acquired by the data acquisition unit. According to some embodiments of the invention, the pollen collecting element and the pollen applying element form a single unit configured to collect and release pollen. According to one embodiment, pollen is collected using electrostatic forces applied to the pollen grains by the pollen collecting element, optionally, the pollen is stored in a container of a type that is applicable for the storage of pollen grains and, at the desired time, the pollen is released by the pollen application element directly and / or indirectly attached to the pollen collecting element, such that the pollen collecting element and the pollen application element together constitute a single assembly designed to both collect and release the pollen grains. According to some embodiments, the pollen collecting element and the pollen applying element of the pollination module are separate elements.According to one embodiment, the pollen collecting element and the pollen applying element of the pollination module are not connected, either directly or indirectly, to each other, i.e., pollen grains are collected using electrostatic forces by the pollen collecting element, and then stored and / or transferred to the pollen applying element of the pollination module. Referring now to FIG. 1 which illustrates a schematic diagram of an exemplary embodiment of a system 100 containing the electrostatic pollination element 8 as part of the pollination module and other components to optimize and improve the overall pollination process. The pollination module receives a pollination heat map from the central server in the field and / or orchard where the operator is located and instructs the operator to go towards the relevant plants to be pollinated. The pollination element includes a power supply 1, the control unit 2 with the processing unit 4 used to process data in real time and combine the inputs from the server in the control of the pollination element and data storage 3 to store all data received from the sensors 6.The function of the sensors is to collect environmental data (such as, but not limited to, temperature, humidity, visible / non-visible light, and / or sound) about the status of the plant. The navigation system 9 with GNSS, MEMs, and other navigation sensors can provide data about the current location and inertial position of the worker in the tree. The user interface 5 includes a display or instruction lights to guide the operator where to perform pollination. A wireless connection 7 is used to send and receive data from the remote server(s). According to some embodiments, the pollen collecting element further comprises at least one of the units selected from: an internal control unit, a vibration motor, and a suction unit. According to some embodiments, the invention provides a method of artificially pollinating an agricultural area in need of pollination. Referring now to FIG: 2, a flowchart of an illustrative embodiment of the method of the invention is presented. The method comprises: providing the pollination management system according to embodiments of the invention

[1000] ; acquiring data by the data acquisition module of the pollination management system

[2000] ; transmitting the acquired data to the server of the pollination management system

[3000] ; transmitting the acquired data to the central server of the pollination management system

[3000] ; processing the data of step

[2000] by the server to generate an output

[4000] ; transmitting the output of step

[4000] to the controller of the operations module

[5000] , and pollinating the agricultural area by the pollination module

[6000] .In one embodiment, the step of pollinating the agricultural area is carried out according to instructions provided by the controller. In one embodiment, the instructions provided by the controller are based on the output of step

[4000] . According to some embodiments of the above method, the step of pollinating the agricultural area comprises the steps of collecting pollen by the pollen collecting element of the pollination module and releasing pollen by the pollen applying element of the pollination module. According to some embodiments of the above method, the step of collecting pollen by the pollen collecting element further comprises generating electric fields that apply electrostatic forces on the pollen grains thereby attracting the pollen grains towards the pollen collecting surface of the pollen collecting element. According to some embodiments of the above method, the step of acquiring data using data obtained from the acquisition module comprises at least one of acquiring data using the at least one sensor of the data acquisition module, receiving data from an external source, or a combination of both. In the context of the method of the invention, the term “acquiring data” or “data acquisition” is understood as at least one action or series of actions performed by one or more components of the data acquisition module, resulting in the collection of data. The data may be acquired by the at least one sensor of the data acquisition module and / or the data may be received from an external source. The data may also be obtained by any other means, provided that the data is in a format suitable for the configuration of the data acquisition module.According to embodiments of the system and methods of the invention, the data acquired by at least one sensor of the pollination module may include, but is not limited to, location data (GPS), IMU data, visual data (e.g., images of crop plants while being pollinated), weather-related data such as temperature, humidity, wind, etc. These data will serve as the basis for pollination effectiveness measurements (e.g., assessing climate suitability for pollination, evaluating flowering and flower receptivity, and operational needs for pollination: what was pollinated and when to schedule additional activities later). Depending on the modalities, data acquired from an external source may include field-related metadata, climate measurements and forecast data, and visual field data. Field metadata may include plant types, planting maps, plant age, natural pollinators that correspond to hives. Climate data may be obtained through a third-party service, from the client's weather station, or using the system's sensors. According to some modalities of the above method, the data is real-time data. According to some embodiments of the above method, the step of processing the data and generating results comprises the selected steps of establishing the number of pollination episodes, establishing the time of pollination, establishing the frequency of pollination, establishing the duration of the pollination episode, establishing the location of pollination, establishing the area to be pollinated, or any combination thereof. According to some embodiments of the above method, the time of pollination is established based on the acquired data. In one embodiment, the location of pollination is established based on the acquired data. In one embodiment, the method comprises more than one pollination event. In one embodiment, the method comprises 70C7 I η / 77Π7 / Ε / YI multiple pollination episodes. In one embodiment, the method comprises a preset number of pollination episodes. In one embodiment, the acquired data is real-time data and the pollination is a real-time pollination. In one embodiment, the number of pollination episodes is set in real-time based on the real-time data. In one embodiment, the pollination episodes are carried out at a preset frequency. In one embodiment, each pollination episode has a preset duration. According to some embodiments of the above method, the method further comprises repeating steps

[2000] to

[6000] a predefined number of times. According to some embodiments of the above method, the data is selected from data acquired by the plurality of sensors of the data acquisition unit, data collected from at least one external source, or a combination thereof. In some cases, the agricultural area is a crop field. In another case, the agricultural area is a vegetable garden. According to some embodiments of the above method, the crop is a tree crop. In one embodiment, the tree crop is selected from, among others, avocado, cocoa, walnuts, citrus, kiwi, peach, mango, lychee, pear, plum, cherry, apricot, or any other tree crop that can benefit from the pollination system and / or methods of the invention. According to some embodiments of the above method, the crop is a field crop. In one embodiment, the list of field crops of the invention includes, among others, crops such as corn, soybeans, wheat, rice, oilseeds, cereals, cotton, grapes, sugarcane, fruits, and vegetables. According to some embodiments, the invention provides a method for increasing crop yield comprising providing an artificial pollination management system, wherein said pollination management system comprises a pollination module; and wherein said pollination module comprises at least one pollen collecting element; and wherein said pollen collecting element is configured to apply electrostatic forces to pollen grains, thereby attracting the pollen grains to the pollen collecting element. In one embodiment, the pollination management system further comprises a data acquisition module; a server in communication with the data acquisition module; an operations module in communication with the server, the data acquisition module, and the pollination module; and a user interface.In one embodiment, pollen grains are attracted to the pollen collection surface of the pollen collecting element. In one embodiment, the agricultural area is an orchard. In another embodiment, the agricultural area is a field of a crop. As used herein, the term “yield” or “agricultural productivity” or “agricultural production” refers, without limitation, to the measurement of the yield of a crop per unit of crop area and / or the generation of seeds from the same plant. In the context of the invention, the increase in yield can be measured according to any suitable parameter or technique known in the art and / or in use by growers. For example, number of fruits and / or seeds per crop, fruit size, crop weight, and other parameters. According to some embodiments of the above method, the crop yield can increase between 5% and 500%. In one embodiment, the crop yield can increase between 10% and 500%.Crop yield can increase by 5%, 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, 100%, 110%, 120%, 130%, 140%, 150%, 160%, 170%, 180%, 190%, 200%, 210%, 220%, 230%, 240%, 250%, 260%, 270%, 280%, 290%, 300%, 310%, 320%, 330%, 340%, 350%, 360%, 370%, 3830%, 390%, 400%, 410%, 420%, 430%, 440%, 450%, 460%, 470% 480%, 490%, 500%. According to some embodiments, the invention provides a collecting element comprising a high voltage power supply, an electrode, a pollen collecting surface, and optionally a container, said high voltage power supply supplying high voltage to the electrode; and said electrode being configured to generate electric fields that apply electrostatic forces on the pollen grains; and said pollen grains being attracted towards the pollen collecting surface of the element. In one embodiment, the pollen collecting element further comprises at least one of an internal control unit, a vibration motor, a blower, or a suction unit. Referring now to FIG. 5 , which illustrates an exemplary embodiment of the inventive pollen collecting element 200.A high-voltage power supply 20 supplies high voltage to the electrode 30, which generates electric fields that apply electrostatic forces to the pollen grains. The pollen is then attracted to the pollen collection surface 40. According to some embodiments, the invention provides a computer-implemented method of artificially pollinating an agricultural area comprising a crop, or a portion thereof. Referring now to Fig. 3A, which presents a flowchart of an illustrative embodiment of the method comprising the steps of: providing the artificial pollination system according to embodiments of the invention

[10000] ; collecting data by the data acquisition module

[11000] ; processing the data in step

[11000] ,

[12000] ; evaluating the state of the crop based on a set of parameters, extracted from the data, indicative of the state of the crop

[13000] ; providing instructions to the controller based on the state of the crop

[14000] ; and, pollinating the agricultural area or a portion thereof

[15000] . According to some modalities of the above method, such data is image data. According to some embodiments of the above method, said crop condition assessment comprises using a trained neural network. In one embodiment, said processing step comprises computation steps of said image data using a computer-implemented algorithm trained to generate an output based on the image data. In another embodiment, the computer-implemented algorithm is trained to generate an output based on predefined attributes or feature vectors extracted from the image data.In one embodiment, said method comprises steps for implementing, with said algorithm, a training process according to a training data set comprising a plurality of training images of a plurality of crop plants captured by the at least one image sensor, wherein each respective training image, of the plurality of training images, is associated with the state of said crop plant represented in the respective training image. Referring now to Fig. 3B, which depicts an illustrative embodiment of the above process wherein said training process comprises steps of capturing images of the crop plants using an image sensor

[16000] ; classifying the images into desired categories by applying a label associated with parameters or attributes, extracted from the image data, indicative of the state of the crop

[17000] ; and applying a computer vision algorithm to determine a set of feature vectors associated with each desired category

[18000] , According to some embodiments, the above process further comprises the step of applying a machine learning process with the trained algorithm implemented by computer to determine the state of the imaged crop

[19000] . Referring now to Fig. 3C, which depicts an illustrative embodiment of the above process wherein said training process comprises the steps of capturing images of the crop plant using an image sensor [16000a]; classifying images into desired categories by marking certain objects in the images and labeling said objects with the desired classes [17000a]; and applying a computer vision algorithm to determine a set of feature vectors associated with each desired category [18000a]. According to some embodiments of the above method, the method comprises the steps of applying a machine learning process with the trained computer-implemented algorithm to determine the state of the flowering plant from which images have been obtained. In one embodiment, said algorithm is implemented with a machine learning process using a neural network with the processed data.In yet another embodiment, said machine learning process comprises calculating, by at least one neural network, a label of at least one desired category for at least one flowering plant, wherein the label of at least one classification category is calculated at least according to weights of at least one neural network, wherein the at least one neural network is trained according to a training data set comprising a plurality of training images of a plurality of crop plants captured by the at least one image sensor, wherein each respective training image, of the plurality of training images, is associated with said label of at least one desired category of at least one crop plant depicted in the respective training image; and generating, according to the label, of at least one classification category, instructions for execution by the controller.Alternatively, the machine learning process comprises calculating, by at least one neural network, a label of at least one desired class for at least one type of crop plant, wherein the label of at least one class is calculated at least according to weights of the at least one neural network, wherein the at least one neural network is trained according to a training data set comprising a plurality of training images of a plurality of crop plants captured by the at least one image sensor, wherein each respective training image, of the plurality of training images, is associated with said label of at least one desired class of at least one type of plant depicted in the respective training image; and generating, according to the label, of at least one class, instructions for execution by the controller. In the context of the invention, the terms "crop" and / or "crop plant" are interchangeable and should be understood as a complete plant and / or plant parts, including, but not limited to, leaves, fruits, seeds, stems, tree branches, tree trunks, flowers, or any other parts not explicitly mentioned herein. The crop plants of the invention are field crops and / or tree crops, so the term "crop plant" also includes trees or tree crops. According to some embodiments, the additional purpose of the invention is to disclose a holistic method for the field / orchard pollination process wherein: pollen collection is performed using the pollen collecting element configured to apply electrostatic forces to the pollen grains; pollen application is performed using different methods such as electrostatic spraying, air pumps, among others, or any other application method of the corresponding technical area; data collection is performed by the data acquisition module that is used to collect data that will then be sent to a remote server via wireless or other type of connection.Those skilled in the art will understand that a server can be a single computer, a network of computers, either in the cloud or on a local machine; the server will process the data and provide information to the producer; the server will provide recommendations on necessary future actions for the producer to take, using the device's "user interface" (for real-time actions) and using dashboards (for real-time and / or offline actions). Those skilled in the art will understand that the data service could be provided on different platforms, such as websites, mobile applications, tablet applications, and other platforms available on the market or under development.Insights and actions the server can provide include, but are not limited to, pollination efficiency; recommendations on areas to artificially repollinate due to inefficient pollination; reporting pests and physical damage in the orchard / field; water conditions; temperature and humidity near crops; and any other parameters that may influence the frequency, duration, and / or location of pollination. zncz in / zznz / E / Yi The terminology used herein is for the sole purpose of describing particular embodiments and is not intended to be limiting of the invention. According to some embodiments, the method of the present invention comprises the steps of applying a machine learning process to the trained algorithm implemented by computer to determine the state of the plant. Therefore, it is within the scope of the present invention that the algorithm (or computer-readable program) is implemented with a machine learning process using a neural network with the processed data. The term “training,” in the context of machine learning implemented within the system of the present invention, refers to the process of creating a machine learning algorithm. Training involves the use of a deep learning framework and a training data set. A training data source can be used to train machine learning models for a variety of use cases, from fault detection to consumer intelligence.The neural network may calculate a classification category, and / or embedding, and / or perform clustering, and / or detect objects belonging to the trained classes to identify the state of an individual plant in the context of pollination. As used herein, the term "class" refers, without limitation, to a set or category of things that have some property or attribute in common and are differentiated from others by kind, type, or quality. The computer-readable program instructions may also be loaded into 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 being executed on the computer, other programmable apparatus, or other device, implement the functions / acts. As used herein, the term “classify” or “classification” may sometimes be interchanged with the term clustering or labeling when, for example, multiple plant images are analyzed, each image may be classified according to its predefined feature vectors and used to create clusters, and / or the plant images may be embedded, and the embeddings may be clustered. The term “desired category” may sometimes be interchanged with the term embedding, for example, the output of a neural network trained in response to an image of a plant may correspond to one or more classification categories, or a vector that stores a computed embedding.It is worth noting that the classification category and the embedding can be generated by the same trained neural network, for example, the classification category is generated by the last layer of the neural network, and the embedding is generated by a hidden embedding layer of the neural network. The architecture of the one or more neural networks can be implemented, for example, as pooled, nonlinear, locally connected, fully connected convolutional layers, and / or combinations of the above. It should be noted that labeling and classification of plants in the images or plant condition trait targets can be entered manually or semi-manually by a user (e.g., via the GUI, e.g., selected from a list of available phenotypic trait targets), obtained as predefined values ​​stored on a data storage device, and / or automatically calculated. The term “feature vector” refers, from now on and in the context of machine learning, to a measurable property, characteristic, parameter, or individual attribute of an observed phenomenon, e.g., detected by a sensor. In this paper, it is evident that the choice of an informative, discriminatory, and independent feature is a crucial step in obtaining effective algorithms in pattern recognition, machine learning, classification, and regression. Algorithms that utilize feature vector classification include nearest neighbor classification, neural networks, and statistical techniques. In computer vision and image processing, a feature is information that is relevant to solving the computational task related to a given application. Features can be specific structures in the image, such as points, edges, or objects.Features can also be the result of a general neighborhood operation or feature detection applied to the image. When features are defined in terms of local neighborhood operations applied to an image, a procedure commonly known as feature extraction is performed. Example 1: Cross-pollination of avocado trees of the Ettinqer and Hass cultivars (one, three, six treatments) 70C7 I η / 77Π7 / Ε / ΥΙ Forty trees were cross-pollinated between the Ettinger and Hass cultivars. One, three, or six consecutive treatments were administered versus the control group, which had not received any artificial pollination treatment. The average number of fruits and yield increase were measured. The results are shown in Table 1: zncz in / zznz / E / Yi Treatment Average number of fruits Yield increase One treatment 219 52% Three treatments 318 121% Six treatments 250 73% Control 144 0 According to Table 1 and as represented in Fig. 4A, a significantly higher average number of fruits was observed compared to the control group, and a significant increase in yield was evident. Furthermore, as shown in Fig. 4B, despite the increase in the average number of fruits, no change in fruit weight was observed. Example 2: Cross-pollination of avocado trees of the Ettinger and Hass cultivars (one, four, eight treatments) 40 trees were cross-pollinated between the Ettinger and Hass cultivars. One, four, or eight consecutive treatments were administered versus the control group, which had not received any artificial pollination treatment, and the average number of fruits and yield increase were measured. The results are shown in Table 2: Treatment Average number of fruits Yield increase One treatment 54.86 10.45% Four treatments 68.50 37.92 Eight treatments 79.25 59.56% Control 49.67 0 According to Table 2 and as represented in Fig. 6A, a higher average number of fruits was observed compared to the control group and a significant increase in yield was evident. Furthermore, as shown in Fig. 6B, despite the increase in the average number of fruits, no change was observed in the average weight of fruits per treatment. Example 3: Artificial pollination of lychee trees Litchi chinensis Forty lychee trees were cross-pollinated between the Floridan variety (pollinator) and the Mauritius variety (pollinated). Cross-pollination treatments were compared with the control group, which had not received any artificial pollination treatment, and the average number of fruits and yield increase were measured. Average fruit weight was also measured. Apart from the indicated treatments, the trees were grown under the same growing conditions. An increase in the average number of fruits and a significant increase in yield are observed. Example 4: Artificial pollination of mango trees Mangifera indica Forty mango trees of the Tali, Keitt & Kent varieties were pollinated by cross-pollination or self-pollination according to the treatments shown in Table 4: zncz in / zznz / E / Yi Tree ID Treatment 1 Control Tali x Tali Keitt x Tali Kent x Tali 2 Control Tali x Tali Keitt x Tali Kent x Tali 3 Control Tali x Tali Keitt x Tali Kent x Tali 4 Control Tali x Tali Keitt x Tali Kent x Tali 5 Control Tali x Tali Keitt x Tali Kent x Tali 6 Control Tali x Tali Keitt x Tali Kent x Tali 7 Control Tali x Tali Keitt x Tali Kent x Tali 8 Control Tali x Tali Keitt x Tali Kent x Tali 9 Control Tali x Tali Keitt x Tali Kent x Tali 10 Control Tali x Tali Keitt x Tali Kent x Tali The treatments are compared to the control group, which has not received any artificial pollination treatment, and the average number of fruits and yield increase are measured. Average fruit weight is also measured. Aside from the indicated treatments, the trees are grown under the same growing conditions. An increase in the average number of fruits and a significant increase in yield are observed. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the singular forms “a” and “the” also include plural forms unless the context clearly indicates otherwise. It is further understood that the terms “comprises” or “comprising,” when used herein, specify the presence of the indicated features, integers, steps, operations, components of elements and / or groups, or combinations thereof, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups, or combinations thereof. As used herein, the terms “comprise,” “comprising,” “include,” “including,” “having,” and their conjugates mean “including but not limited to.”The term “consisting of” means “including and limited to.” As used herein, the term “and / or” includes any and all possible combinations of one or more of the associated enumerated elements, as well as the lack of combinations when interpreted in the alternative (“or”). Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one skilled in the art to which this invention pertains. It is further understood that terms, as defined in commonly used dictionaries, are to be construed with a meaning consistent with their meaning in the context of the specification and claims and are not to be interpreted in an idealized or overly formal sense unless expressly defined herein. Known functions or constructs may not be described in detail for the sake of brevity and / or clarity. It will be understood that when an element is referred to as being “on”, “attached” to, “operatively coupled” to, “operatively joined” to, “operatively assembled” with, “connected” to, “coupled” with, “in contact”, etc., with another element, it may be directly on, attached, connected, operatively coupled, operatively assembled, coupled and / or in contact with the other element or intermediate elements may also be present. Conversely, when an element is said to be “in direct contact” with another element, no intermediate elements are present. Whenever the term “about” is used, it refers to a measurable value, such as a quantity, a time duration, and the like, and is intended to encompass variations of ±20%, ±10%, ±5%, ±1%, or ±0.1% from the specified value, as such variations are appropriate for performing the methods described. It will be understood that terms such as, for example, “process,” “compute,” “calculate,” “determine,” “establish,” “analyze,” “check,” or the like, may refer to operation(s) and / or process(es) of a computer, a computing platform, a computing system, or other electronic computing device, which manipulates and / or transforms data represented as physical (e.g., electronic) quantities within the computer's registers and / or memories, into other data similarly represented as physical quantities within the computer's registers and / or memories or other non-transitory information storage medium that can store instructions for performing operations and / or processes. It is understood that, although the terms "first," "second," etc., may be used herein to describe various elements, components, regions, layers, and / or sections, these elements, components, regions, layers, and / or sections are not to be limited by these terms. Rather, these terms are used only to distinguish one element, component, region, layer, and / or section from another element, component, region, layer, and / or section. Certain features of the invention, which are described, for clarity, in the context of separate embodiments, may also be provided in combination in a single embodiment. Conversely, various features of the invention, which are described, for brevity, in the context of a single embodiment, may also be provided separately or in any suitable subcombination, or as deemed appropriate, in any other described embodiment of the invention. Certain features described in the context of several embodiments should not be considered essential features of those embodiments, unless the embodiment would not function without those elements. znc? I η / 77Π7 / Ε / ΥΙ Throughout this application, various embodiments of this invention may be presented in a range format. It should be understood that the description in range format is merely for convenience and brevity and should not be construed as an inflexible limitation on the scope of the invention. Accordingly, the description of a range should be considered to specifically disclose all possible subranges, as well as individual numerical values ​​within that range. For example, the description of a range such as 1 to 6 should be considered to have subranges that are specifically disclosed as 1 to 3, 1 to 4, 1 to 5, 2 to 4, 2 to 6, 3 to 6, etc., as well as individual numbers within that range, e.g., 1, 2, 3, 4, 5, and 6. This applies regardless of the breadth of the range. Whenever a numerical range is indicated in this document, it is intended to include any number (fractional or whole) cited within the indicated range. The phrases “ranging from” a first indicated number to a second indicated number and “ranging from” a first indicated number to a second indicated number are used interchangeably in this document and are intended to include the first and second indicated numbers and all fractional and whole numbers between them. Whenever the terms “plurality” and “a plurality” are used, they are intended to include, for example, “multiple” or “two or more.” The terms “plurality” or “a plurality” may be used throughout the specification to describe two or more components, devices, elements, units, parameters, or the like. The term “set,” when used herein, may include one or more elements. Unless explicitly stated, the method embodiments described herein are not restricted to a particular order or sequence. Furthermore, some of the described method embodiments or elements thereof may occur or be performed simultaneously, at the same time, or concurrently. Regarding all publications, patent applications, patents, and other references mentioned. The descriptions of these publications in their entirety are incorporated by reference into this application to more fully describe the state of the art to which this invention pertains. In case of conflict, the patent specification, including definitions, shall prevail. Furthermore, the materials, methods, and examples are illustrative only and are not intended to be limiting. Throughout this application, reference is made to various publications, published patent applications, and published patents. zncz in / zznz / E / Yi Those skilled in the art will appreciate that the present invention is not limited to what has been particularly shown and described above. Rather, the scope of the present invention is defined by the appended claims and includes combinations and subcombinations of the various features described above, as well as variations and modifications thereof, which might come to mind to those skilled in the art upon reading the foregoing description.

Claims

1. A pollination management system for an agricultural area comprising: a) a pollination module, wherein said module comprises a pollen collection element configured to collect pollen; and a pollen application element configured to release pollen; b) a data acquisition module operatively coupled with the pollination module, wherein said data acquisition module comprises at least one sensor; c) a server communicating with the pollination module and the data acquisition module, wherein the server is configured to process the data acquired by the data acquisition module; d) an operations module comprising a controller communicating with the server and the pollination module, wherein said controller is configured to provide instructions to the pollination module; and e) a user interface;f) where said system is configured to artificially pollinate the agricultural area or a part thereof.; 2. The system of claim 1, wherein the data acquisition module is configured to transmit the acquired data to the server.

3. The system of claim 1 or 2, wherein the instructions provided to the pollination module by the controller are based on data processed by the server.

4. The system of any of claims 1 to 3, wherein at least one sensor is selected from the group consisting of IR camera, temperature sensor, humidity sensor, LiDAR, sound recorder, GNSS, 4D image sensor, hyperspectral imaging, IMU and a light sensor.

5. The system of any one of claims 1 to 4, wherein the data acquisition module comprises a plurality of sensors.

15. The system of any one of claims 12 to 14, wherein the real-time data is selected from location data (GPS), IMU data, visual data, and weather-related data.

16. The system of any one of claims 1 to 15, wherein the server is further configured to control at least one of: the area to be pollinated, the pollination time, the frequency of pollination events, the number of pollination events, the duration of each pollination event, or any combination thereof.

17. The system of any one of claims 1 to 16, wherein the pollen-collecting element and the pollen-applying element form a single unit configured to collect and release pollen. 18.The system of any one of claims 1 to 16, wherein the pollen collecting element and the pollen application element of the pollination module are separate elements.

19. The system of any one of claims 1 to 18, wherein the agricultural area is a cultivated field or an orchard. 20.A method of artificially pollinating an agricultural area requiring pollination, or a part thereof, comprising: a) providing the pollination management system of any one of claims 1 to 19; b) data acquisition by the data acquisition module of the pollination management system; c) transmission of the acquired data to the server of the pollination management system; d) processing of the data from step b) by the server to generate an output; e) transmission of the output from step d) to the controller of the operations module; and f) pollination of the agricultural area by the pollination module, wherein the pollination step of the agricultural area is carried out in accordance with instructions provided by the controller, and wherein the instructions provided by the controller are based on the result of step d). 21.The method of claim 20, wherein the step of pollinating the agricultural area comprises the steps of collecting the pollen by the pollen-collecting element of the pollination module and releasing the pollen by the pollen-applying element of the pollination module.

22. The method of claim 21, wherein the step of collecting the pollen by the pollen-collecting element further comprises generating electric fields that apply electrostatic forces to the pollen grains, thereby attracting the pollen grains to the pollen-collecting surface of the pollen-collecting element.

23. The method of any of claims 20 to 22, wherein the step of acquiring data by means of the acquisition module comprises at least one data acquisition step by means of at least one sensor of the data acquisition module, receiving data from an external source, or a combination thereof. 24.The method of claim 23, wherein the data acquisition step by the acquisition module comprises data acquisition by at least one sensor of the data acquisition module and data reception from an external source.

25. The method of any of claims 20 to 24, wherein the data is selected from location data (GPS), IMU data, visual data, and weather-related data.

26. The method of any of claims 20 to 25, wherein the data is real-time data. 27.The method of any one of claims 20 to 26, wherein the data processing and output generation step comprises selected steps from: establishing the number of pollination events, establishing the pollination time, establishing the pollination frequency, establishing the duration of the pollination event, establishing the pollination location, establishing the area to be pollinated, or any combination thereof.

28. The method of any one of claims 20 to 27, wherein the pollination step of the agricultural area comprises more than one pollination event.

29. The method of claim 28, comprising a predetermined number of pollination events.

30. The method of claim 29, wherein the pollination events are carried out at a predetermined frequency. 31.The method of any one of claims 28 to 30, wherein each pollination event has a predetermined duration.

32. The method of any one of claims 20 to 31, wherein the agricultural area or a part thereof is a field of a crop or an orchard.

33. The method of any one of claims 20 to 32, wherein the data acquired is real-time data and the pollination is real-time pollination.

34. A method for increasing the yield of a crop comprising providing an artificial pollination management system, wherein said pollination management system comprises a pollination module; and wherein said pollination module comprises at least one pollen-collecting element; and wherein said pollen-collecting element is configured to apply electrostatic forces to the pollen grains, thereby attracting the pollen grains towards the pollen-collecting element. 35.The method of claim 34, wherein the pollination management system further comprises a data acquisition module; a server communicating with the data acquisition module; an operations module communicating with the server, the data acquisition module, and the pollination module; and a user interface.

36. The method of claim 34 or 35, wherein the pollen collecting element comprises a high-voltage power supply, an electrode, a pollen collecting surface, and optionally a container, wherein said high-voltage power supply provides high voltage to the electrode; and wherein said electrode is configured to generate electric fields that apply electrostatic forces to the pollen grains.

37. The method of claim 36, wherein the pollen grains are attracted to the pollen collecting surface of the pollen collecting element. 38.The method of any one of claims 34 to 37, wherein the agricultural area is an orchard.

39. The method of any one of claims 34 to 37, wherein the agricultural area is a cultivated field.

40. The method of claim 39, wherein the crop is a tree crop or an extensive crop.

41. The method of claim 40, wherein the crop is a tree crop selected from the group consisting of avocado, cocoa, nuts, citrus, kiwi, peach, pear, plum, cherry, mango, lychee, and apricot. 42.A pollen-collecting element comprising a high-voltage power supply, an electrode, a pollen-collecting surface, and optionally a container, wherein said high-voltage power supply provides high voltage to the electrode; and wherein said electrode is configured to generate electric fields that apply electrostatic forces to the pollen grains; and wherein said pollen grains are attracted to the pollen-collecting surface of the element.

43. The pollen-collecting element of claim 42, further comprising at least one internal control unit, a vibration motor, a blower, or a suction unit. 44.A computer-implemented method for the artificial pollination of an agricultural area or a portion thereof comprising a crop, the process comprising: a) providing the artificial pollination system of any one of claims 1 to 19; b) data collection by the data acquisition module; c) processing the data and evaluating the crop status based on a set of parameters, extracted from the data, indicative of the crop status; d) providing instructions to the controller based on the crop status; and e) pollinating the agricultural area or a portion thereof.

45. The method of claim 44, wherein said data are image data.

46. The method of claim 45, wherein said evaluation of the agricultural area status comprises the use of a trained neural network. 47.The method of claim 46, wherein the processing step comprises the steps of calculating said image data using a computer-implemented algorithm trained to generate an output based on the image data.

48. The method of claim 47, wherein said computer-implemented algorithm is trained to generate an output based on pre-established feature vectors or attributes extracted from the image data.

49. The method of any of claims 45 to 48, wherein said method comprises the steps of implementing, with said algorithm, a training process according to a training dataset comprising a plurality of training images of the crop, wherein each respective training image of the plurality of training images is associated with the state of said crop depicted in the respective training image. 50.The method of claim 46, wherein said training process comprises the steps of: a) capturing images of the crop using an image sensor; b) classifying the images into desired categories by applying a label associated with parameters or attributes, extracted from the image data, indicative of the crop's condition; and c) applying a computer vision algorithm to determine a set of feature vectors associated with each desired category.

51. The method of claim 50, further comprising a step of applying a machine learning process with the computer-implemented trained algorithm to determine the condition of the crop from which the images were obtained.

52. The method of claim 51, wherein said algorithm is implemented with a machine learning process that uses a neural network with the processed data. 53.The method of claim 52, wherein said machine learning process comprises calculating, through at least one neural network, a label of at least one desired category for the at least one crop, wherein the label of at least one classification category is calculated at least according to the weights of the at least one neural network, wherein the at least one neural network is trained according to a training dataset comprising a plurality of training images of a plurality of crops captured by the at least one image sensor, wherein each respective training image of the plurality of training images is associated with said label of at least one desired category of at least one crop represented in the respective training image; and generating, according to the label, instructions for the execution of the at least one classification category by the controller. 54.The method of any one of claims 44 to 53, wherein the crop is an extensive crop.

55. The method of any one of claims 44 to 53, wherein the crop is a tree crop.

56. The method of claim 55, wherein the agricultural area is an orchard.

57. The method of claim 55 or 56, wherein the tree crop is selected from the group consisting of avocado, cocoa, nuts, citrus, kiwi, peach, pear, plum, cherry, mango, lychee, and apricot.

58. The method of claim 57, wherein the tree crop is selected from avocado, mango, and lychee.

Images