AU2020103563A4

AU2020103563A4 - Machine learning based plant growth moderator

Info

Publication number: AU2020103563A4
Application number: AU2020103563A
Authority: AU
Inventors: Akash Kumar Bhoi; Priya Bhoi; Samarjeet Borah; Arshad Mohammed; Pradeep Kumar Mallick; Sushruta Mishra; Neeraj Priyadarshi; Mahaboob Shaik; Amarjeet Kumar Sharma; Piyush Kumar Shukla; Hrudaya Kumar Tripathy
Original assignee: Bhoi Priya Dr; Borah Samarjeet Dr; Mishra Sushruta Dr; Mohammed Arshad Dr; Sharma Amarjeet Kumar Dr; Tripathy Hrudaya Kumar Dr
Current assignee: Bhoi Priya Dr; Borah Samarjeet Dr; Mishra Sushruta Dr; Mohammed Arshad Dr; Sharma Amarjeet Kumar Dr; Tripathy Hrudaya Kumar Dr
Priority date: 2020-11-19
Filing date: 2020-11-19
Publication date: 2021-02-04
Anticipated expiration: 2028-11-19

Abstract

"MACHINE LEARNING BASED PLANT GROWTH MODERATOR" Exemplary aspects of the present disclosure are directed towards MACHINE LEARNING BASED PLANT GROWTH MODERATOR. It consists of a plurality of Remote Moderator Terminal (RMT) 101 comprising Humidity/Temperature sensor 101c-1, soil-moisture sensor 101c-2, Light-intensity sensor 101c-3, CO 2 Sensor 101c-4 and camera 101c-5, communicates with the Central Moderator Terminal (CMT) 103 through WiFi mesh-network 102. The relevant machine learning algorithms fed with collected data pertaing to factors affecting the growth of crop/plant and demand from various web portals. Based on the collected data and also by the images collected by Camera 101c-5, CMT predicts the best harvest date from the date of seeding. This harvesting date is converted to the number of days to harvest and fed to CMT 103 through GPRS connection. CMT 103 updates the routine in RMTs 101 based on the number of days remaining to harvest. RMTs run the routine and controls the temperature/humidity, moisture, water, light intensity, and CO 2 supplying to plant/crop. 1 101 106 USER TTGO-ESP37GSMPC/Mobil R 4 Wi-Fi/RF433 Mesh Connected FIG 1 100 PLANT GROWTH MANAGEMENT SYSTEM

Description

101

106

USER

TTGO-ESP37GSMPC/Mobil

R 4

Wi-Fi/RF433 Mesh Connected

FIG 1 100 PLANT GROWTH MANAGEMENT SYSTEM

1. TITLE OF THE INVENTION:

"MACHINE LEARNING BASED PLANT GROWTH MANAGEMENT SYSTEM"

2. PREAMBLE TO THE DESCRIPTION

The following specification particularly describes the invention and the manner in which it is to be performed

3. DESCRIPTION

TECHNICAL FIELD

[0001] The present disclosure generally relates to the field of agriculture, where electronic instruments, together with Machine Learning, are used for effective cultivation.

BACKGROUND

[0002] Agricultural automation is a farmer's dream wherefrom the plantation to harvesting is intended to be fully automatic. Though several inventions and disclosers have made a significant effort in automating agriculture in fragments, full pledge automation is yet a dream. Moreover, the plant/crop growth is predictable but not the market demand. When the plant/crop is harvested, the market demand, which is volatile, may decrease the Return on Investment (ROI) of the farmer.

[0003] Numerous prior arts have made attempts to automate the farming process in fragment way rather than a complete system. Automation of crop/plant watering system, pesticide spraying system, fertilizer system, are few.

[0004] Similarly, several prior art disclosures have ascertained computer-based algorithms based on several mitigation techniques for predicting the market price to give the best Return on Investment (ROI) to the farmer.

[0005] Articles in the prior art have proved that plant/crop growth can be manipulated by altering the water levels, humidity, moisture, temperature, light intensity from grow light.

[0006] If properly designed and fabricated the artificial intelligence-based market prediction system with a plant growth altering system, then the farmer can sell the plant/crop at the maximum Return on Investment (ROI).

[0007] Fredrick Awuor et al. (2013) have emphasized The development of ICT in various domains has driven substantial interest in rising investments by private sectors towards the growth of ICT in Agricultural research. Xiangyu Hu et al. (2011)developed the IoT application, which embedded IOT-Radio Frequency identification, GPS, and smart sensors used to transfer information from the field. The information was recorded using RFID, and sensors are used to monitor the field. Richard K (2014) developed a system with IoT, and Cloud Computing emphasizes reliable architectures to provide farmers with timely information from the field over 3G or WiFi.

[0008] CN106228325A discloses an invention which is an agricultural product supply chain management system based on the internet of things. However, this invention fails to disclose that only WiFi communication can be enabled and only related to monitoring the supply chain monitor of the agricultural product.

[0009] US7085777B2 discloses a method and a system for tracing the identity of an agricultural product. The system uses tracing software, and the information is sent to the local cloud server through wireless communication. To operate this system, it requires a skilled person.

[0010] CN104166924A discloses an invention in which the agricultural product electronic transaction management system, where the system consists of a peer to peer communication, and the information obtained is transmitted to store in the cloud server.

[0011] An prior art document, US20120005105A1, discloses an invention is a method through for supply chain management using mobile devices with the local database cloud server. The system uses a digital signature to access the data stored in the cloud server.

[0012] Another prior art document by J. Elizabeth et al., has testified that in Soybean plantation, grown in controlled environment cabinets under light intensities of 220 w/m2 or 90 w/m2 (400-700 nm) and day to night temperatures of 27.5-22.5 C or 20.0-12.5 C in all combinations, exhibited differences in growth rate, leaf anatomy, chloroplast ultrastructure, and leaf starch, chlorophyll, and chloroplast lipid contents.

[0013] Another prior art document by N. Yan et al., in their findings named Interactive effects of temperature and light intensity on photosynthesis and antioxidant enzyme activity in Zizania latifolia Turcz. Plants have disclosed that The results indicated that greenhouse-grown plants (GGP) had significantly higher plant height, leaf length, and leaf width, but lower leaf thickness and total shoot mass per cluster compared with field-grown plants (FGP).

[0014] Referring to another document, Constraints by water stress on plant growth presented by FI Pugnaire el at, discussed that water is among the most limiting factors for plant productivity and growth rates are proportional to water availability. Because of its essential role in plant metabolism, at both the cellular and whole-plant levels, any decrease in water availability imminently affects the growth rate of the plant.

[0015] Andrew Crane-Droesch in his document titled Machine learning methods for crop yield prediction and climate change impact assessment in agriculture has revealed and described an approach to yield modelling that uses a semiparametric variant of a deep neural network, which can simultaneously account for complex nonlinear relationships in high-dimensional datasets, as well as the known parametric structure and unobserved cross-sectional heterogeneity. Their predictive model approach is less pessimistic than others concerning the warmest regions and the warmest scenarios.

[0016] The present invention provides an Al-assisted agricultural device to assist the farmers in automation and supply chain management using the IoT platform.

[0017] The present invention addresses the shortcomings mentioned above of the prior art.

[0018] All publications herein are incorporated by reference to the same extent as if each publication or patent application were specifically and individually indicated to be incorporated by reference. Where a definition or use of a term in an incorporated reference is inconsistent or contrary to the definition of that term provided herein, the definition of that term provided herein applies, and the definition of that term in the reference does not apply.

SUMMARY

[0019] The following presents a simplified summary of the disclosure in order to provide a basic understanding of the reader. This summary is not an extensive overview of the disclosure, and it does not identify key/critical elements of the invention or delineate the scope of the invention. Its sole purpose is to present some concepts disclosed herein in a simplified form as a prelude to the more detailed description that is presented later.

[0020] Exemplary embodiments of the present disclosure are directed towards the MACHINE LEARNING BASED PLANT GROWTH MANAGEMENT SYSTEM 100.

[0021] An exemplary object of the present disclosure is directed towards a system that tracks the market demand, present plant growth and predict the exact date at which the harvesting of crop/plant to be done for maximum yield and return.

[0022] An exemplary object of the present disclosure is directed towards the machine learning based system to predict the date at which goods to be sold based on iterated significant market demand and supply data. The date estimated is based on, 1) The seedling germination and plant variant; 2) The data from various authenticated web pages like agricultural-ministry, Rythu Bazar, e-commerce stats, e-nam portal, and others. 3) Data from the metrological department and 4) Plant Health Management Division of NIPHM. And compare years of data and estimate the best price date at which crop/plant has to be harvested and sold at high prices.

[0023] Another exemplary object of the present disclosure is directed towards the integration of ESP32 Microcontroller as Remote Moderator Terminal (RMT) 101 which aggregates the data received from the sensor and transmit the data through WiFi mesh network 102 to central station CMT 103 to save the data on SD card 103e.

[0024] An exemplary aspect of the present subject matter is directed towards communication between RMT 101 and CMT 103. The communication is based on mesh network 102, where the devices communicate through WiFi, and each device act as a node that is a transceiver-thereby removing the necessity of the WiFi modem.

[0025] An exemplary aspect of the present subject matter is directed towards the use of Camera 101c-5 for capturing the plant/crop and determine the growth rate with help on the relevant machine learning algorithm.

[0026] An exemplary aspect of the present subject matter is directed towards the implementation of carbon dioxide management system 203. CO2 Sensor 101c-4 monitors the levels and based on routine initialized; it regulates the carbon dioxide levels through CO2 Burner 203.

[0027] Another exemplary aspect of the present disclosure is directed towards the communication between CMT 103 and user interface 106, which is through GPRS data packet transmission.

[0028] Another exemplary aspect of the present disclosure is directed towards the control of plant growth parameters based on the predicted harvest date.

BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In the following, numerous specific details are set forth to provide a thorough description of various embodiments. Certain embodiments may be practiced without these specific details or with some variations in detail. In some instances, certain features are described in less detail so as not to obscure other aspects. The level of detail associated with each of the elements or features should not be construed to qualify the novelty or importance of one feature over the others.

[0030] FIG.1 is a diagram depicting the MACHINE LEARNING BASED PLANT GROWTH MANAGEMENT SYSTEM, according to an exemplary embodiment of the present disclosure.

[0031] FIG. 2 is a Block diagram for the deployment of Remote Moderator Terminal components in a closed environment.

[0032] FIG. 3 is a Block diagram representation of Remote Moderator Terminal (RMT) 101 and its plurality, according to an exemplary embodiment of the present disclosure.

[0033] FIG. 4 is a diagram depicting the structure and actual image of the Machine Learning based central console CMT 103, according to an exemplary embodiment of the present disclosure.

[0034] FIG. 5 is a flow chart 104-a representing a process carried in CMT, according to an exemplary embodiment of the present disclosure.

[0035] FIG. 6 diagram depicting 104-b Process carried in central moderator terminal (CMT) for predicting plant growth rate (MLA-1) 103, according to an exemplary embodiment of the present disclosure.

[0036] FIG.7 diagram depicting the flow chart 103-a for the process of execution of the command in CMT.

[0037] FIG. 8 diagram depicting the flow chart 108 Process of execution of the command in RMT (Routine)

DETAILED DESCRIPTION OF EXAMPLE EMBODIMENTS

[0038] It is to be understood that the present disclosure is not limited in its application to the details of construction and the arrangement of components outlined in the following description or illustrated in the drawings. The present disclosure is capable of other embodiments and of being practiced or of being carried out in various ways. Also, it is to be understood that the phraseology and terminology used herein is for the purpose of description and should not be regarded as limiting.

[0039] The use of "including", "comprising" or "having" and variations thereof herein is meant to encompass the items listed thereafter and equivalents thereof as well as additional items. The terms "a" and "an" herein do not denote a limitation of quantity, but rather denote the presence of at least one of the referenced item. Further, the use of terms "first", "second", and "third", and the like, herein do not denote any order, quantity, or importance, but rather are used to distinguish one element from another.

[0040] Referring to FIG. 1 is a diagram depicting a M L - B A S E D PLANT GROWTH MANAGEMENT SYSTEM whose function is to monitor and control the plant growth through the plurality of remote moderator terminal RMT. These RMTs monitor the growth rate through camera 101c-5 and sense growth parameters through various sensors. Further, RMTs are responsible for controlling the plant growth parameters, especially temperature, humidity, carbon dioxide, moisture, light, and water. All these parameters are carefully monitored and sent to Machine Learning based Moderator Terminal (CMT) 103 through a WiFi mesh network 102. The plurality of RMTs acts as a node in a mesh and works as transceivers. This indicates they act as access points (AP) and repeaters, thereby removing the dependency of the WiFi modem and extends the range of the WiFi for kilometres. The data received thus stored on to the in build store device 103e. This data is further sent to the user interface 106 GPRS 107 as data packets for further processing.

[0041] In accordance with a non-limiting exemplary embodiment of the present subject matter, FIG. 2 is a representation of sensor insertion and control unit placement. As depicted in the drawings of FIG 2, the plants are grown in a suitable pot and placed precisely under the grow light 201. As per the prior arts, there is a significant enhancement in plant growth if they are subjected to constant light intensity. The watering system 202 consists of water springing system 202a and controlled by plurality of water flow monitoring and controller valves 202b for creating the mist and raising the humidity of the environment. Further drip system 202c controlled by water flow monitoring and controller valves 202b to further assist the system in maintaining the moisture content in the soil. As per necessity to add nutrients to the water, an extra attachment NUTRIENT INFUSER 204 is connected to the watering system 202 through the valve 202b. The CO 2 Burner 203 is activated to aid the photosynthesis process in the plant.

[0042] Referring to FIG 3 is a diagram depicting the internal schema of a Remote Moderator Terminal RMT 101. The internal schema collaborated around an ESP32 microcontroller setup 101a, which consists of battery 101a-2 and LCD 101a-3 along with ESP32 chip 101a. The RMT further consists of Relay group 101b and sensor group 101c. Six relays deployed to control the Lights, CO 2 Burner, watering system. Sensors group 101c consists of comprising Humidity/Temperature sensor 1Oc-1, soil-moisture sensor 101c-2, Light-intensity sensor lOc-3, CO2 Sensor 1Oc-4 and camera 101c5. The ESP32 microcontroller can display the sensor values on the LCD Display 101a-3 and sends the data to CMT 103 through mesh network 102. This sensor data encompasses RMT unique ID and time stamping. Further, all RMTs use in-build WiFi functionality of ESP32 101a-lwhich allows them to acts as transceivers, thereby removes the necessity of WiFi Modems. Any RMT can act as a bridge between individual RMTs 101 to CMT 103.

[0043] Referring to FIG. 4 is a diagram 103 depicting a system for Central Moderator Terminal (CMT) 103, which bridges the connection between RMTs 101 and user interface. RMTs 101 can connect to CMT 103 with no dependency on the internet and WiFi routers. The CMT 103 has an onboard LoRa based ESP32 103a, an OLED display103d, 2.4GHz antenna, onboard SD Card Holder 103e, ceramic antenna for GSM signal trans receiver 103f, LiPo battery, and GSM700 module 103b. Initially, ESP32 103a receives data through antenna 103c transmitted by RMTs 101. The sensor data then send to OLED display along with time and ID of RMTs and as well as User interface. The transmission of data from CMT 103 takes place in the form of GPRS data packets forming internet connectivity 107. The sensor data is then stored to SD memory card 103e.

[0044] In accordance with a non-limiting exemplary embodiment of the present subject matter, FIG. 5 is a flow chart 104-a depicting the process in CMT for predicting the market demand according to an exemplary embodiment of the present disclosure, which starts with the step 501 where past and present price of the plant/crop is collected and stored. Later in step 502, data of plant/crop growth rate, factors effecting, and yield are accumulated and stored. During step 503, monsoon and other historical climate data are retrieved from the metrological department IMD and stored. In the proceeding step 504, Using Machine learning algorithm MLA-1 predict present growth rate, which gives data pertain to present plant growth and estimated harvest date. The date of seeding the crop/plant is fed as input during step 505. Once the data stored, the next step proceeds to 506, where data is cleansed and classified with respect to time stampings and grouped into their respective domains, which are type of plant and its properties, market price history, weather conditions and present and predicted plant growth rate. The data is formatted and fed to the trained Machine learning module. During step 507, Relevant MLA forecast demand of the crop/plant at harvest time, and visualizes the data and also best date at which crop has to be harvested. Also, forecast analyses the data and generates the forecast with respect to demand of the crop/plant visualizes the data and also the best date at which crop has to be harvested during step 508. This process completes once the data generated is transmitted to the user interface 106 for further process.

[0045] According to a non-limiting exemplary embodiment of the present disclosure, FIG.6 is a representation 104-b depicting the process for measuring plant/crop growth rate according to an exemplary embodiment of the present disclosure. The method 104-b starts with step 601, where the camera 101c-5 Captures the live images and fed relevant machine learning algorithm. Images from seeding to presiding and present are compared with respect to height and width of the plant/crop in step 602 to get information in step 603. In this step, a precise comparison results in determining the exact plant/crop growth rate. This process gives the exact date at which the plant/crop becomes harvestable to yield maximum benefit to farmers. The proceeding step 604 estimation of harvest time based on the present growth rate is done. The same data is stored and made available for usage by other modules and transmitted to the user interface 106.

[0046] According to a non-limiting exemplary embodiment of the present disclosure, FIG.8 is a flow chart 108 depicting the process of execution of commands, also called as routine in the RMTs according to an exemplary embodiment of the present disclosure. The RMTs routine is updated by CMT 103 as per the required growth rate. FIG 8 illustrates a routine adopted for increasing the growth rate of the plant/ crop for meeting the enhanced harvest date. The process starts at 801where the selection of routine is carried out in the CMT, which is based on the days required to harvest. In this step, it verifies Number of Days received is less than usual plant /crop growth. Proceeding step 802 Calculate the percentage of growth required. To meet this new growth rate, RMTs start to Increase the humidity, light intensity, Water quantity, CO 2 and maintain the temperature best situated

for that plant/crop growth, which equivalent to the percentage of growth required, which is carried out in step 803. The following step 804 initiates the camera 1Oc-5, which takes pictures of plant/crop and compares to calculate the present growth rate over two days. This comparison is fed to the next step 805, where a case scenario of increased growth rate. If the growth rate is more than required, then calculate the percentage of growth to be decreased. This percentage of growth rate to be decreased fed to RMTs microcontroller 101al. Step 806 initiate the process by decrease the temperature, humidity, light intensity, Water quantity, CO2 equivalent to the percentage of growth required. This routine carries on in a loop until the harvest is completed.

[0047] In an embodiment, the plant/ crop growth parameters controlled by the RMTs 101, whereas the growth rate, which is to be maintained by the RMTs, is updated periodically by CMT103 through WiFi Mesh Network 102. The growth rate, which is to be maintained, is communicated through the GPRS communication 107 established by the CMT 103. The data can be displayed on the user interface, which might be a mobile, PC/Laptop, or WiFi-enabled devices.

[0048] In an embodiment, the CO 2 burner 203, when activated, releases the carbon dioxide into the plant/crop space to assist the photosynthesis process, and the amount of CO 2 to be released is based on the routine which is being executed in RMTs. The growth rate drastically increase when CO 2 content is predominantly high. The levels are monitored by CO2 sensor 101c-4.

[0049] In an embodiment, grow lights 201 deployed over the plant/crop with a variable light intensity device. RMT monitors the light intensity through light intensity sensor 101c-3 and gives the command to vary it to the variable light intensity device. This device varies the intensity of the light by decreasing the power input to it. It was learned earlier from the prior art that light intensity variation affects plant growth.

[0050] In an embodiment, water sprinkling is accomplished through sprinklers 202a. Water is controlled in these sprinklers by control valves 202b. The valves 202b have a composition of the flow monitoring system and solenoid to obstruct the water flow. To increase the humidity, RMTs open the valves 202b and measure the water flow and record the humidity through humidity sensor 101c-1. The sprinkler system 202a not only increase the humidity but also decreases the ambient temperature around the plant/crop. It was learned earlier from the prior art that the misting process decreases the pests and increase the humidity. And also, the temperature variation affects the growth rate, and hence, the misting process also helps the temperature to be in control.

[0051] In an embodiment, soil moisture is monitored with the help of moisture sensor 101c-2. The RMT monitors the value and controls the valve 202b, which helps in distributing the water to plant/crop through drip points 202c. Further to this watering system, if the farmer wants to add fertilizer/nutrients/ amino acts to the water, then NUTRIENT INFUSER 204 allows the contents in it to be added to water flow through the mixer unit available in valve 202b. Based on the routine, RMT controls the valves to vary the water, nutrient and to mist. All these parameters help the plant grow faster, and if a decrease is there, then the growth rate become normal.

Claims

EDITORIAL NOTE 2020103563 There is one page of claims only STATEMENT OF CLAIMS We Claim:

1. The Machine Learning based plant growth moderator consisting of:

A Central Moderator Terminal (CMT) 103, with inbuilt TensorFlow Lite system, it is capable of executing machine learning algorithms and having capability of communicating with other devises over WiFi or GPRS system; and Where in Central Moderator Terminal (CMT) 103 co-ordination with plurality of Remote Moderating Terminal (RMT) collects plant growth data and control the parameters affecting the plant growth; and Remote Moderating Terminal (RMT) comprising of sensor DHT22, BH1750, KG003, and light intensity controller for regulating the parameter which amounts to plant growth; and Relevant machine learning algorithms uses, Data base Module, and image recognition modules for predicting market price, plant growth and pest detection.

2. The device of claim 1, wherein the Central Moderator Terminal (CMT) 103 can predict market price based on values acquired from E-commerce web market and other government websites such as Rhythm bazar portal.

3. The device of claim 1, wherein a Central Moderator Terminal (CMT) 103 in co ordination with RMTs and relevant machine learning algorithm can predict the present plant growth rate.

4. The device of claim 1, wherein a Central Moderator Terminal (CMT) 103 generates a routine for RMTs 101, which is further used to generate set commands to control Light, moisture, humidity and temperature in and around the plant.

5. The device of claim 1, wherein a camera module along with relevant machine learning algorithm detects the plant growth rate and makes RMTs to give appropriate command for plant growth modulation.

102 101

106 2020103563

RMT RMT 1 2

USER CMT Interface PC/Mobil TTGO-ESP32-700GSM e RMT 4

RMT n

Wi-Fi/RF433 Mesh Connected

FIG 1 100 PLANT GROWTH MANAGEMENT SYSTEM

GROW LIGHTS 202a 2020103563

202b

POT- POT- POT- 202c 1 2 n 202 202d 205

ML BASED WATER CO2 CONTROL TANK BOARD

204 203 FIG 2 FIG 2 SCHEMA FOR DEPLOYMENT OF RMT SYSYTEM

101a 101b 101a-3 101a-2 101a-1

Relay Group RELAY RELAY 1 6 101c 2020103563

101c-1 101c-2

101c-5 ESP32 WiFi/RF

101c-3

203 101c-4

101 REMOTE MODERATOR TERMINAL (RMT)

FIGURE 3

103c 2020103563

103b

103d 103a

103e 103f

FIG 4

103 CENTRAL MODERATOR TERMINAL (CMT)

Acquire the price tag of the desired plant/crop from e-NAM and 501 rythubazar web portals.

502 Acquire the plant/crop growth properties from NIPHM 2020103563

503 Acquire the weather conditions form the portal mausam.imd.gov.in of India Meteorological Department

504 Using Machine learning algorithm MLA-1 predict present growth rate.

505 Collect the date of seeding the plant/crop

Prepare a dataset for use with relevant MLA and feed the data 506 With Trained machine learning model.

507 Relevant MLA forecast demand of the crop/plant at harvest time, and visualizes the data and also best date at which crop has to be harvested

508 The data is presented to RMTs and other user interfaces

FIG 5

104-a Process carried out in CMT for predicting Market Demand

Acquire the image of the plant/crop 601 2020103563

Compare the acquired image with previous image. Image 602 comparison will be based on date after the seeding and preceding date Relevant MLA with image recognition model predicts the growth 603 rate

604 Estimates harvest date based on the predicted rate growth.

605 Send the data to user interface 106 and store the data for utilization by other process.

FIG 6

104-b Process for predicting plant growth rate (MLA1)

Acquire the no of days to harvest from the step 605 701

Decide the routine/classification to be loaded in to RMT based on 702 the days acquired (Routine may be for increase or decrease the critical levels of plant/crop growth factors ) 703 Based on date classification set the limits for, Grow Light 2020103563

intensity, CO2 Levels, Water, Humidity & fertilizer Mixer level

Verify The routine is updated in every RMT and they will follow 704 the classification and collect the data.

Send data to CMT by RMTs through WiFi mesh network and 705 stores the data on local storage.

706 For every two hours the CMT collects the data and sends it to user.

FIG 7

103-a Process of execution of command in CMT

Is No of Days received is less than normal plant /crop growth. 801 Calculate the percentage of growth required

802 Increase the temperature, humidity, light intensity, Water quantity 2020103563

equivalent to percentage of growth required

Take pictures of plant/crop through 101c-5 and compare to 803 calculate the growth rate

If the growth rate is more than required then calculate the 804 percentage of growth to be decreased.

Decrease the temperature, humidity, light intensity, Water quantity 805 equivalent to percentage of growth required

806 Store the sensor data and camera data on to CMT memory storage card 103e

807 Store the sensor data and camera data on to CMT memory storage card 103e

FIG 7 108 Process of execution of command in RMT(Routine)