Optimizing growing process in a hybrid growing environment using computer vision and artificial intelligence
A method for optimizing plant growth in a hybrid growing environment may implement artificial intelligence to measure and alter plant biometrics. Independent variables may be altered by a control unit by manipulating various control systems within the growing environment. Dependent variables may be measured, and the response of the dependent variables may be recorded in association with the alteration to the independent variables. A historical database may store data regarding the variables and may be referenced and updated by an exemplary embodiment. The control unit may optimize one or more variables or parameters based on a targeted value or outcome. An exemplary hybrid growing environment may include one or more vertical growing phases and a horizontal phase. The phases may implement various watering systems and may be hydroponic, be a complete CEA, use a mixture of natural, artificial, and/or supplemental lighting.
1 . A system for an agricultural environment, the system comprising:
a plurality of imaging sensors and weather sensors;
a plurality of environmental control systems, the environmental control systems configured to adjust a plurality of independent variables; and
a control unit configured to receive data from the imaging sensors and weather sensors to identify a plurality of dependent variables, wherein the control unit is configured to adjust the environmental control systems based on a data model, wherein the data model is autonomously updated in real time by the control unit,
wherein the plurality of independent variables comprise dry bulb temperature, wet bulb temperature, relative humidity, plant surface temperature, vapor pressure deficit (VPD), lighting intensity and/or period, light spectrum wavelengths, amount of nutrients applied or retained, C02 concentration, water temperature, water pH, water conductivity, amount of dissolved oxygen, amount or presence of pesticides, water usage, C02 assimilation, chlorophyll fluorescence, chlorophyll concentration, and microbial levels in nutrient solutions, and
wherein the control unit is configured to adjust the plurality of independent variables and is further configured to measure the plurality of dependent variables to identify a result or effect of the adjusted plurality of independent variables.
2 . The system of claim 1 , wherein the control unit is configured to receive data from the imaging sensors to identify plant health, plant quality, presence of pests and pathogens and instance of disease, rate of growth or biomass accumulation.
3 . The system of claim 1 , wherein the control unit is configured to compute a normalized difference vegetation index (NVDI), visible atmospherically resistant index (VARI), normalized difference water index (NDWI), light intensity (or photosynthetically available radiation, PAR), light spectrum, day-light index (DLI), or vapor pressure deficit (VPD) from data from the imaging sensors and/or weather sensors.
4 . The system of claim 1 , wherein the dependent variables comprise at least one of growing duration, plant weight, plant leaf growth, root growth, plant diameter, plant health, an identification of pests, mold, mildew, or rejected plants, growth cycle DLI, vapor pressure deficit (VPD), temperature, electricity usage, watering periodicity, time in an environment or phase, nutrient concentration, or soil moisture content.
5 . The system of claim 1 , wherein the result of the adjusted independent variables is used to update a data model.
6 . The system of claim 1 , wherein the control unit is configured to store a control data model in addition to the data model, and wherein adjustments to the data model are compared to adjustments to the control data model.
7 . The system of claim 1 , wherein the control unit is configured to adjust the independent variables to increase a rate of development.
8 . The system of claim 1 , wherein the control unit is configured to adjust the independent variables to decrease a rate of development based on a schedule or market demand.
9 . The system of claim 1 , wherein the independent variables are adjusted based on one or more target dependent variables to meet a target development stage based on one or more predicted conditions in a subsequent phase.
10 . The system of claim 1 , wherein the independent variables are adjusted based on a measured quality and presence of abiotic or biotic-induced abnormalities.
11 . The system of claim 1 , wherein the control unit is configured to identify and store a plurality of weather patterns from the weather sensors, and wherein the control unit is configured to adjust the independent variables based on a weather forecast predicted based on the weather patterns.
12 . The system of claim 1 , wherein the control unit is configured to implement a feedback loop, the feedback loop comprising adjusting one or more independent variables, measuring a change in one or more dependent variables due to the adjusted independent variables, and updating the data model based on the measured change.
13 . The system of claim 1 , wherein the control unit is configured to identify a plant density from the imaging sensors, and configured to identify an optimal time for transplanting to a subsequent phase based on the identified plant density.
14 . The system of claim 1 , wherein the control unit is configured to optimize and update the data model using one or more of a cluster analysis, bootstrap sampling, and/or extreme gradient boosting.