Patent Application
20240295494
Nutritional deficiencies in plants reduce the yield of grow operations by limiting the growth of the plants or in worst cases, killing the plants. In particular, the inability of plants to receive enough nitrogen (N), phosphorus (P) or potassium (K) affects the yield of grow operations. At the same time, in order to be efficient and ecologically sound, grow operations do not want to add excess amounts of Nitrogen, Phosphorous or Potassium to the plant bed.
The discussion above is merely provided for general background information and is not intended to be used as an aid in determining the scope of the claimed subject matter. The claimed subject matter is not limited to implementations that solve any or all disadvantages noted in the background.
A method of identifying NPK-deficiency includes measuring intensities of light reflected from a cannabis plant to produce intensities at a set of spectral bands, wherein the cannabis plant is one variety of a plurality of varieties of cannabis. The intensities are applied to a classifier so that the classifier provides one of an indication that the cannabis plant is NPK-deficient or an indication that the cannabis plant is NPK-sufficient, wherein the classifier has been trained using plants that include each of the plurality of varieties of cannabis.
In accordance with a further embodiment, a method includes placing a light sensor within a meter of a top of a plant and measuring intensities of each of a set of spectral bands of light reflected by the plant using the light sensor. The intensities are then used to classify the plant as NPK-deficient.
In accordance with a still further embodiment, a system includes a sensing system having a light sensor and a positioning system, wherein the light sensor measures intensities for light reflected from at least one cannabis plant at a plurality of spectral bands and the positioning system provides a position of the sensing system when the light sensor measured the intensities. A classifier receives the intensities and the position and provides a classification for the at least one cannabis plant at the position, wherein the classification indicates whether the at least one cannabis plant is NPK-deficient and the classification is based on the received intensities.
This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.
Early detection of nitrogen (N), phosphorus (P), and potassium (K) deficiencies (collectively NPK deficiencies) is important in maximizing yield of the plant. However, some plants, such as cannabis, appear green and healthy during early stages of growth even though they are not receiving enough NPK. As a result, growers have had to wait for the plants to show visible signs of NPK deficiency before being able to take action to correct the deficiencies.
The present inventors have discovered that NPK-deficient cannabis plants exhibit a change in the amount of light they reflect at near infrared wavelengths. This change occurs before the cannabis plants have any visible indications to a human grower of NPK-deficiency. The embodiments discussed below provide a system that uses the intensity of light reflected from cannabis plants at a collection of wavelengths, including near infrared wavelengths, to categorize cannabis plants as either being NPK-deficient or NPK-sufficient. Because the embodiments use near infrared wavelengths, NPK deficiencies are detected earlier than the prior art. The system can be used with multiple different varieties of cannabis plants even though NPK deficiencies cause different changes in light reflectance in different varieties of cannabis.
In accordance with one embodiment, the detection of the reflected light intensity is improved by placing the light sensors within a meter of the cannabis plant.
In step 100 of
At step 104, a hyper-spectral light sensor 204 in a sensing system 206 is moved to a position over plants 202. In accordance with one embodiment, sensor 204 is positioned within a meter of the top of plants 202. At step 106, sensor 204 obtains intensity levels of light reflected by plants 202 at a set of selected hyper-spectral bands. In accordance with one embodiment, the set of hyper-spectral bands include 2.1 nm wide bands centered at 725.57, 732.05, 992.83, 854.39, 792.9, and 712.62 nm, which are all in the near infrared range (700 nm-1400 nm). In one such embodiment, these hyper-spectral bands are used for multiple varieties of cannabis plants, even though the varieties have different morphologies. This provides a single system that can work with multiple different varieties of cannabis, thereby reducing the number of systems needed to implement the present embodiments.
At step 107, a current position of light sensor 204 and the intensities of the reflected light are stored in a memory 208 of sensing system 206 as position and spectral intensities 210. The current position is provided by a positioning system 212 in sensing system 206. In accordance with one embodiment, positioning system 212 comprises a motor controller that is able to determine the position of light sensor 204 based on the number of rotations of a drive motor that moves light sensor 204 over the plants. In other embodiments, positioning system 212 comprises a Global Positioning System (GPS) that provides the position of light sensor 204 using signals received from satellites. Position and spectral intensities 210 include a separate light intensity for each hyper-spectral band in the set of hyper-spectral bands obtained by light sensor 204.
At step 108, position and spectral intensities 210 are transmitted by a network interface 214 of sensing system 206 to a server 216 through a network 218. In accordance with one embodiment, network 218 includes a wide-area network such as the Internet. Position and spectral intensities 210 are stored in a memory 217 in server 216 and are provided to a classifier 220 executed by server 216.
At step 109, classifier 220 uses the spectral intensities in position and spectral intensities 210 to classify the position as either NPK-deficient or NPK-sufficient.
In accordance with one embodiment, classifier 220 is a Neural Network Multilayer Perceptron (MLP). MLP is an artificial neural network that is trained using supervised machine learning. It is a more complicated process than a simple linear classifier and can analyze a substantial amount of data. In other embodiments, classifier 220 is a Stepwise Discriminant Analysis (STDA), a Quadratic Discriminant Analysis, or a random forest classifier. Those skilled in the art will recognize that these are examples of possible classifiers and other classifiers may be used as classifier 220. In accordance with one embodiment, classifier 220 is trained using light intensities measured from a plurality of different varieties of cannabis plants. As a result, classifier 220 is able to classify multiple different varieties of cannabis as being either NPK-deficient or NPK-sufficient.
At step 112, the class provided by classifier 220 is stored with the position as position and NPK class 222.
At step 114, sensing system 206 determines if there are more plant positions to be evaluated. If there are more plant positions, sensing system 206 moves to a different position and steps 104-112 are repeated for the new position.
When sensing system 206 has collected spectral intensities at all desired plant positions and classifier 220 has produced an NPK class for each position at step 114, nutrient application values are set for each position at step 116. In particular, a nutrient calculator 224 uses the NPK class 222 and a date of planting 226 for the position to calculate an amount of nutrients that should be applied to the position. If the NPK class is NPK-sufficient, the nutrient application value is set to a minimum value, which in many cases will be zero. If the NPK class is NPK-deficient, the nutrient application value is set so as to overcome the NPK deficiency while ensuring that an excessive amount of nutrients is not applied to the position. Human growers are alerted to conditions that require intervention or changes to nutrient applications. In particular, date of planting 226 is used to estimate the date of harvest and the nutrient value is selected so that the plant has sufficient NPK to reach the harvest date but there is a minimum amount of NPK left at the position after the harvest date. The nutrient application value is stored with the position as an entry 228 in memory 217.
At step 118, the nutrient application values for each position are provided to a nutrient application system 230 through network 218 or some other network. In accordance with one embodiment, nutrient application system 230 is a nutrient feed line that is able to provide different amounts of nutrients to different positions in a grow operation. In other embodiments, nutrient application system 230 is a movable fertilization system equipped with a positioning system that is able to determine when the fertilization system is at a desired position and is able to apply a desired amount of nutrients at that position. Nutrient application system 230 uses the nutrient application values to provide the appropriate amount of nutrients to each position at some point during a multi-day period, such as four days for example. In accordance with one embodiment, the nutrients are provided as soon as possible during the multi-day period. In other embodiments, the nutrients are provided over the course of the multi-day period.
At the end of the multi-day period, sensing system 206 or server 216 determines if the harvest date has been reached for all plants in the grow operation at step 120. If at least one plant has not been harvested, the method returns to step 104 and steps 104-120 are repeated. Thus, at the end of each multi-day period, the plants are reclassified. This allows plants that had been classified as NPK-sufficient to be reclassified as NPK-deficient if the amount of NPK provided to the plants is no longer sufficient. In addition, it allows plants that were classified as NPK-deficient to be reclassified as NPK-sufficient if the nutrients applied in step 118 were effective in overcoming the NPK deficiency. By reclassifying the plants, the amount of nutrients applied to the plants can be minimized while ensuring that the plants are receiving enough NPK.
When all of the plants have been harvested, the method of
As shown in
In
As shown in
As shown in
As sensing systems 350, 352 move along their respective rails, they are positioned over different plants in their respective plant beds and under different sets of lights that are positioned over their plant beds. Since the sensing system is self-propelled, it controls its movement over the plants allowing it to control the linear density of sensor values collected over the plants. In addition, because the sensing system is able to move relative to the plants, when sensing is not being performed, the sensing system can move to a position where it is not between the lights and any particular plant. This ensures that each plant receives as much light as possible when sensing is not taking place.
As shown in
Guide wheels 516 and 616 include a central portion that extends into groove 520 of rail 366 and two side portions above and below the central portion that engage with a side of rail 366. Guide wheels 516 and 616 are free to spin along their respective central axis and in accordance with one embodiment are not driven by a motor.
Drive wheel 512 is driven by an electric motor 800 shown in
As shown in
As shown in
As shown in
As shown in
Infrared light emitted by the plants is also received by infrared sensor 1310 through aperture 600. The received infrared light can be used to estimate the temperature of the plants which in turn can be used to determine Vapor Pressure Deficiency, an important growing metric.
As shown in
Together, circuit board 900, motor 800, and drive wheel 512 form a movement subsystem configured to move the sensors and camera in boom 360 between the plants and the light sources.
Processor 1606 is also connected to a memory 1610 which contains a schedule 1612, a sensor collection routine 1614 and an image collection routine 1616. Schedule 1612 indicates when sensor collection routine 1614 should be executed and when image collection routine 1616 should be executed. Processor 1606 uses a time provided by a clock 1618 and scheduled times provided by schedule 1612 to determine when to execute sensor collection routine 1614 and image collection routine 1616.
Memory 1610 also includes images 1620 collected by camera 1306 and sensor data 1622 collected by range finder 1308, temperature sensor 1406, humidity sensor 1404, upward facing light sensors 1000, 1100, 1200, upward facing deep ultraviolet sensor 1202, downward facing light sensor 1300, downward facing infrared sensor 1310, downward facing deep ultraviolet sensor 1302, and CO2 sensor 1402 at different locations. In accordance with one embodiment, as images and sensor data are received from sensor interfaces 1604 they are stored in memory 1610 together with identifying information such as the time and date at which the images/sensor data were received and the position of the boom along the rail when the sensor data/images were received.
In accordance with one embodiment, memory 1610 also includes a collection of plant locations 1624 that indicate the position of plants within the plant bed. Plant locations 1624 may be entered by hand or may be determined from images collected by camera 1506.
Processor 1606 is in wireless communication with server 216 through a wireless interface 1652 and a router 1654, which form network interface 214 of
When the time for data collection arrives, processor 1606 instructs motor 800 to turn drive wheel 512 so as to place boom 360 at a desired position set in sensor collection routine 1614. When boom 360 arrives at the desired location, processor 1606 collects sensor data from range finder 1308, temperature sensor 1406, humidity sensor 1404, upward facing light sensors 1000, 1100, 1200, upward facing deep ultraviolet sensor 1202, downward facing light sensor 1300, downward facing infrared sensor 1310, downward facing deep ultraviolet sensor 1302, and CO2 sensor 1402.
At step 1706, processor 1606 stores the sensor data as sensor data 1622 in memory 1610 along with the position along the plant bed where the data was collected and the time and date at which the data was collected. At step 1708, processor 1606 determines if the sensing system has reached the end of the plant bed. If the sensing system has not reached the end of the plant bed, processor 1606 sends an instruction through motor interface 1608 to motor 800 to cause the motor to rotate the drive wheel so that the sensing system moves laterally along the rail. Steps 1704, 1706, and 1708 are then repeated at the new position along the rail.
When the sensing system reaches the end of the plant bed, processor 1606 sends an instruction to motor 800 to return the sensing system to a docking station at step 1710. While motor 800 is turning drive wheel 512 to cause sensing system 350 to return to the docking station, processor 1606 transmits sensor data 1622 to server 216 through wireless interface 1652, router 1654, and internet 1656 at step 1712. Processor 1606 then waits until it is once again time for sensor data to be collected. In accordance with one embodiment, sensor data is collected once per hour over the entire length of the plant bed. In accordance with one embodiment, sensor data 1622 includes reflected light intensities measured by downward facing light sensor 1300 in spectral bands in the infrared region and the positions at which those light intensities were measured. In addition, the sensor data returned to server 218 includes an identifier for either sensing system 350 or the plant bed that sensing system 350 is positioned over so that server 218 has a complete indication of the position of sensor 1300 when the light intensities were measured.
In the embodiments shown in
Although the system above discusses NPK-deficiency, the system can also be used to detect overwatering and underwatering of plants.
Although the sensing system shown in
Embodiments of the present invention can be applied in the context of computer systems other than computing device 10. Other appropriate computer systems include handheld devices, multi-processor systems, various consumer electronic devices, and the like. Those skilled in the art will also appreciate that embodiments can also be applied within computer systems wherein tasks are performed by remote processing devices that are linked through a communications network (e.g., communication utilizing Internet or web-based software systems). For example, program modules may be located in either local or remote memory storage devices or simultaneously in both local and remote memory storage devices. Similarly, any storage of data associated with embodiments of the present invention may be accomplished utilizing either local or remote storage devices, or simultaneously utilizing both local and remote storage devices.
Computing device 10 further includes an optional hard disc drive 24, an optional external memory device 28, and an optional optical disc drive 30. External memory device 28 can include an external disc drive or solid state memory that may be attached to computing device 10 through an interface such as Universal Serial Bus interface 34, which is connected to system bus 16. Optical disc drive 30 can illustratively be utilized for reading data from (or writing data to) optical media, such as a CD-ROM disc 32. Hard disc drive 24 and optical disc drive 30 are connected to the system bus 16 by a hard disc drive interface 32 and an optical disc drive interface 36, respectively. The drives and external memory devices and their associated computer-readable media provide nonvolatile storage media for the computing device 10 on which computer-executable instructions and computer-readable data structures may be stored. Other types of media that are readable by a computer may also be used in the exemplary operation environment.
A number of program modules may be stored in the drives and RAM 20, including an operating system 38, one or more application programs 40, other program modules 42 and program data 44. In particular, application programs 40 can include programs for implementing any one of modules discussed above. Program data 44 may include any data used by the systems and methods discussed above.
Processing unit 12, also referred to as a processor, executes programs in system memory 14 and solid state memory 25 to perform the methods described above.
Input devices including a keyboard 63 and a mouse 65 are optionally connected to system bus 16 through an Input/Output interface 46 that is coupled to system bus 16. Monitor or display 48 is connected to the system bus 16 through a video adapter 50 and provides graphical images to users. Other peripheral output devices (e.g., speakers or printers) could also be included but have not been illustrated. In accordance with some embodiments, monitor 48 comprises a touch screen that both displays input and provides locations on the screen where the user is contacting the screen.
The computing device 10 may operate in a network environment utilizing connections to one or more remote computers, such as a remote computer 52. The remote computer 52 may be a server, a router, a peer device, or other common network node. Remote computer 52 may include many or all of the features and elements described in relation to computing device 10, although only a memory storage device 54 has been illustrated in
In a networked environment, program modules depicted relative to the computing device 10, or portions thereof, may be stored in the remote memory storage device 54. For example, application programs may be stored utilizing memory storage device 54. In addition, data associated with an application program may illustratively be stored within memory storage device 54. It will be appreciated that the network connections shown in
Although elements have been shown or described as separate embodiments above, portions of each embodiment may be combined with all or part of other embodiments described above.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms for implementing the claims.
