FIELD OF THE INVENTION

[0001] The present disclosure generally relates to a screening and a monitoring system, and more particularly, to a system for screening and monitoring behaviour of soil-crop-atmosphere and an associated method thereof.
BACKGROUND
[0002] The history of agriculture dates back thousands of years and the development has been driven by different climates, cultures, and technologies. Generally, agriculture is referred to as the production, processing, promotion, and distribution of agricultural products which may be broadly classified into foods, fibres, and raw materials. Agriculture is the backbone of the economic system of many countries and plays a critical role in its entire economy. In addition to providing food, agriculture is a source of livelihood for many. Agricultural products like sugar, tea, rice, spices, tobacco, coffee, for example, constitute the major items of exports of countries that rely on agriculture.
[0003] The process of agriculture includes farming by labours, with or without the help of machinery, in an area primarily devoted to agricultural processes. Irrespective of the different types of crops and methodologies of farming, the farmer's typical objective is to increase yield, maximize the crop quality and hence maximize the returns. In order to make the farmers to achieve said objectives, with the development of communication and technology over the last decade, many government organizations and companies have rushed into mobile based advisory platforms for providing expert advice to the farmers. However, such platforms are intended to solve farmers' problems based on questions sent by the farmers or pre¬set instructions, and farmers needs to understand their requirements in order to

achieve the desired objectives. Further, 40-60% loss in yield and crop quality is due to diseases and infestation in crops, for example in vegetables and fruits crops. The reasons for the same may be changing weather conditions, poor quality seeds, improper soil preparation, insects, and the like.
[0004] Conventionally, the disease and the infestation in the crops (i.e. the vegetables and in the fruit crops) are identified by visual means (i.e. using a camera, and the like), provided the symptoms associated with the crops are visible to a farmer. But as a matter of fact, by the time when the symptoms are visible to the farmer, till then the disease and the infestation have already spread through the field and a major portion of the crop (i.e. the vegetables and the fruit crops) is already being damaged, hence resulting into a loss to the farmer.
[0005] In addition, the crop being under stress is also one of the reasons for the loss in the yield and the crop quality. Generally, when the crop is under stress, the crop's behaviour changes which can be identified using different processes or techniques such as measuring different amounts and types of VOCs (Volatile Organic Compounds) /GLVs (Green Leaf Volatiles) emitted by the crop. Conventionally, the measurements of different amounts and the types of VOCs are done at large laboratories which require elaborate setups and costs large amounts of money. The use of VOCs for plant disease detection is limited to laboratory only as the direct molecular methods such as polymerase chain reaction (PCR), illumination fluo- rescence (IF), fluorescence in-situ hybridization (FISH) and enzyme linked immunosorbent assay (ELISA) requires elaborate setups and are prohibitively expensive. Moreover, the conventional solutions available in the market are focussed only on the environmental conditions to predict the stress to the plant.

[0006] Further, the conventional solutions are expensive and are centred around large farms. Hence, there is a need for an enhanced system for screening and monitoring behaviour of soil-crop-atmosphere.
SUMMARY
[0007] This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention. This summary is neither intended to identify key or essential inventive concepts of the invention and nor is it intended for determining the scope of the invention.
[0008] According to one embodiment of the present disclosure, an Internet of Things (IoT) system to determine health of a plant at a farm is disclosed. The system comprises an integrated sensor unit comprising a thin film sensor, deployed in a farm, configured to detect a change in an electrical property of a thin film in response to exposure of the thin film to a volatile organic compound (VOC) emitted from the plant, and comprises an ionization sensor, deployed in the farm, configured to ionize another VOC emitted from the plant and detect current associated with the flow rate of the ionized VOC. Further, the system comprises a controller in communication with the sensor unit and configured to receive, via a gateway, data related to the change in electrical property of the thin film and the current associated with the flow rate of the ionized VOC, and determine a type of stress or disease in the plant based on the received data.
[0009] To further clarify the advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention

and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.
BRIEF DESCRIPTION OF THE FIGURES;
[0010] These and other features, aspects, and advantages of the exemplary embodiments can be better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:
[0011] FIG. 1 illustrates a block diagram of a system including a sensor unit, a gateway, a cloud interface, and a mobile computing device for screening and monitoring behaviour of soil-crop-atmosphere to determine health of a plant, in accordance with an embodiment of the present disclosure;
[0012] FIG. 2 illustrates a detailed block diagram of the plurality of types of sensors to be deployed in a farm for screening and monitoring behaviour of soil-crop-atmosphere in accordance with an embodiment of FIG. 1 of the present disclosure;
[0013] FIG. 3 A illustrates a systematic diagram of an architecture of a system illustrating plurality of examples of communication network to be used for communication in between the gateway and the plurality of sensors via a BLE (Bluetooth Low Energy) / Wi-Fi / LoRa / ZigBee, for example, and the gateway and the main server via an internet / MQTT (Message Queuing Telemetry Transport) / cellular 3G/4G, respectively in accordance with an embodiment of the present disclosure;

[0014] FIG. 3B illustrates a schematic diagram of an architecture of an Internet of Things (IoT) system 100 deployed in a farm using the various system components, in accordance with an embodiment of the present invention.
[0015] FIG. 4A, FIG. 4B, FIG. 4C, and FIG. 4D illustrate a systematic diagram of a thin film sensor, an ionisation-based sensor, a current sensing showing amplification and conversion to an output voltage, and a block diagram showing integrated sensor unit, respectively in accordance with an embodiment of the present disclosure; and
[0016] FIG. 5 illustrates an exemplary process flow for screening and monitoring behaviour of soil-crop-atmosphere to determine health of a plant, in accordance with an embodiment of the present disclosure.
[0017] Further, skilled artisans will appreciate that elements in the figures are illustrated for simplicity and may not have necessarily been drawn to scale. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the figures by conventional symbols, and the figures may show only those specific details that are pertinent to understanding the embodiments of the present invention so as not to obscure the figures with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.
DETAILED DESCRIPTION
[0018] For the purpose of promoting an understanding of the principles of the disclosure, reference will now be made to the embodiment illustrated in the figures and specific language will be used to describe them. It will nevertheless be understood that no limitation of the scope of the disclosure is thereby intended.

Such alterations and further modifications to the disclosure, and such further applications of the principles of the disclosure as described herein being contemplated as would normally occur to one skilled in the art to which the disclosure relates are deemed to be a part of this disclosure.
[0019] It will be understood by those skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the disclosure and are not intended to be restrictive thereof.
[0020] The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such a process or a method. Similarly, one or more devices or sub-systems or elements or structures or components preceded by "comprises... a" does not, without more constraints, preclude the existence of other devices, other sub-systems, other elements, other structures, other components, additional devices, additional sub-systems, additional elements, additional structures, or additional components. Appearances of the phrase "in an embodiment", "in another embodiment" and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment.
[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. The system, methods, and examples provided herein are illustrative only and not intended to be limiting.
[0022] In addition to the illustrative aspects, exemplary embodiments, and features described above, further aspects, exemplary embodiments of the present

disclosure will become apparent by reference to the drawings and the following detailed description.
[0023] In accordance with embodiments of the present disclosure, a system for screening and monitoring behaviour of soil-crop-atmosphere in real time to determine health of a plant at a farm, is disclosed. The screening and monitoring system includes a plurality of sensors to be deployed in the farm, a gateway (i.e. a local server), a cloud interface (i.e. a main server), and a mobile computing device having an application. The mobile computing device is associated with a user (i.e., a farmer). The gateway is operatively connected with the plurality of sensors and the main server via a BLE (Bluetooth Low Energy), or Wi-Fi, or cellular (3G/4G), or Zigbee router or other known wired or wireless communication technologies.
[0024] The plurality of sensors includes such as, but not limited to, a soil sensor, a plant sensor, and an atmospheric sensor. The soil sensor may include, but not limited to, an optical sensor, and an electrochemical sensor, configured for sensing and measuring data related to various parameters such as, but not limited to, electrical conductivity, impedance rate of the soil, soil moisture, water retention, pH, soil physic-chemical properties, important primary, secondary and micro-nutrients like nitrogen, phosphorus, potassium, calcium, magnesium, sulfur, boron, and the like. The plant sensor may include, but not limited to, a sap-flow sensor, and a bio-volatiles/VOCs/GLVs detection sensors, configured for sensing and measuring data related to various parameters such as, but not limited to, volatile organic compounds, and green leaf volatiles emissions. The atmospheric sensor is configured for sensing and measuring data related to various parameters such as, but not limited to, weather conditions, ambient temperature, humidity, dew point, rainfall, and micro-climatic parameters within the farm demography. The above said sensed data associated with the various parameters is transmitted to the gateway via the BLE/Wi-Fi. The gateway further transmits the sensed data to the

main server. The main server processes the sensed data and compares the sensed data with the pre-stored data of a healthy plant, the best soil, and environmental conditions for its growth using AI (Artificial Intelligence) based analytics. Based on the comparison, the main server detects an abnormal behavior related to a crop stressor, and alerts the farmer by sending a real time notification in a form of messages/notifications to the mobile computing device, for example, stating the abnormal behavior of the plant, what kind of diseases the plant can result in and what can be done to protect the plant.
[0025] Thus, the present disclosure provides technical advantages by mapping classes of horticulture crop volatiles with classes of diseases, occurrence, stage of the crop and other micro-climatic parameters for different crop biotic and abiotic stressors. Further, the present disclosure provides for a low cost, small, and portable VOC detection platform for identification of early distress/disease in horticulture crops. Additionally, the use of AI analytics for precision agriculture and detecting deviations from normal behaviour facilitates in creating alerts for nutrient deficiencies and infestations much before any visual symptoms appear from large amounts of collected heterogeneous data.
[0026] FIG. 1 illustrates a block diagram of an Internet of Things (IoT) system 100 including a sensor unit, a gateway, a cloud interface, and a mobile computing device for screening and monitoring behaviour of soil-crop-atmosphere to determine health of a plant, in accordance with an embodiment of the present disclosure. The screening and monitoring system 100 may include a plurality of sensors 105-1, 105-2, and 105-3, the gateway 110 (i.e., a local server), the cloud interface 115 (i.e., a main server), and the mobile computing device 120. The mobile computing device 120 may include a software application and may be associated with a user (e.g., a farmer). By way of example, the mobile computing device 120 may include, but not limited to, a tablet or a smartphone, having

communication capabilities. The mobile computing device 120 and the gateway 110 may communicate with the main server 115 through the communication network (not shown in Figure 1) in one or more ways such as wired, wireless connections or a combination thereof. It may be noted that the system 100 disclosed herein may be configured for screening and monitoring behaviour of the soil-crop-atmosphere in real time. On the basis of detection, the system 100 detects an abnormal behaviour of the soil-crop-atmosphere and may alert the user (i.e., the farmer) through a dashboard (not shown) indicating the abnormal behaviour of the crop (i.e., a plant), type of diseases the plant can result in, and one or more steps to protect the plant. The dashboard may be accessible to the user (i.e., the farmer) via a software mobile application on the mobile computing device 120. Further, the dashboard may be maintained at a cloud-based web service for storing data related to the monitored data via the sensor unit 105, and may be shared on the mobile computing device 120, as requested or required by the user. Also, it is to be noted that the plurality of sensors 105-1, 105-2, and 105-3 configured for sensing and measuring plurality of parameters associated with the soil-crop-atmosphere are suitably deployed in the farm. The system 100 may be configured for monitoring the behavior of the plant by typically considering three factors such as the soil parameters, the type of plant and plant related parameters, and the atmospheric parameters (i.e., physical conditions required for growth of the plant.)
[0027] The main server 115 may include, for example, a mainframe computer, a computer server or a network of computers or a virtual server which provides functionalities or services for other programs or devices. In one implementation, the main server 115 may be a cloud server comprising one or more processors, controllers 125, associated processing modules, interfaces and storage devices communicatively interconnected to one another through one or more communication means for communicating information. The storage associated with the main server 115 may include volatile and non-volatile memory /database 135

for storing information and instructions to be executed by the one or more processors and for storing temporary variables or other intermediate information during processing. In one embodiment of the present disclosure, the main server 115 stores data of a healthy plant, the best soil, and environmental conditions required for growth of a healthy plant. This stored data may be used for comparison with the real-time data detected by the sensor unit 105 and to thereby determine health of the plant/crop.
[0028] In one embodiment of the present disclosure, the plurality of sensors 105-1,105-2, and 105-3 may include, but not limited to, a soil sensor, a plant sensor, and an atmospheric sensor. The soil parameter sensor unit 105-1, may include, but not limited to, a soil sensor, temperature and humidity sensor, soil water retention flow sensor, pH sensor, an optical sensor and an electrochemical sensor, configured for sensing and measuring data related to various parameters such as, but not limited to, electrical conductivity, impedance rate of the soil, soil moisture, water retention, pH, soil physic-chemical properties, important primary, secondary and micro-nutrients like nitrogen, phosphorus, potassium, calcium, magnesium, sulfur, boron, and the like. The plant parameter sensor unit 105-2, may include, but not limited to, a sap-flow sensor and abio-volatiles/VOCs/GLVs detection sensors, configured for sensing and measuring data related to various parameters such as, but not limited to, volatile organic compounds, and green leaf volatiles emissions. The atmospheric condition parameter sensor unit 105-3 is configured for sensing and measuring data related to various parameters, such as, but not limited to, weather conditions, ambient temperature, humidity, dew point, rainfall, and micro-climatic parameters within the farm demography. The above said sensed data associated with the various parameters is transmitted to the gateway via the BLE/Wi-Fi.
[0029] The different sensors of the sensor units may be located at different locations around the plant. In one embodiment of the present invention, the soil

parameter sensor unit 105-1 may be located in the ground. The sap flow sensor of the plant parameter sensor unit 105-2 may be attached to the stem of the plant. The bio-volatiles/VOC detection sensors of the plant parameter sensor unit 105-2 may be latched on or above the leaves of the plant.
[0030] In the same embodiment of the present disclosure, the gateway 110 is operatively connected with the plurality of sensors 105-1, 105-2, and 105-3 via a BLE (Bluetooth Low Energy) / Wi-Fi / LoRa / ZigBee. Further, in the same embodiment, the gateway 110 is operatively connected with the main server 115 via the internet / MQTT (Message Queuing Telemetry Transport) / cellular 3G/4G. In yet another embodiment, a Zigbee router is used in place of the gateway 110. It is to be noted herein that the Zigbee router is operatively connected with the plurality of sensors 105-1, 105-2, and 105-3, and the main server via a Zigbee and cellular/ Wi-Fi/ ethernet, respectively.
[0031] In the same embodiment, the gateway 110 further transmits the sensed data to the main server 115. The main server 115 processes the sensed data and compares the sensed data with the prestored data of a healthy plant, the best soil, and environmental conditions for its growth using AI (Artificial Intelligence) based analytics. Based on the comparison, the main server 115 detects an abnormal behavior and predict various types of crop stressors and the associated possible reasons, and alerts the farmer by sending a real time notification in a form of messages/notifications to the mobile computing device, for example, stating the abnormal behavior of the plant, types of crop stressors, type of diseases the plant can result in and what can be done to protect the plant. In one embodiment, the main server 115 may include a transceiver 130 (shown in Fig. 3) to transmit the alerts. Such alerts may be useful for preventive measures to safeguard crop loss.

[0032] In one embodiment of the present disclosure, the AI based analytics may be implemented using a plurality of neural network layers. Examples of neural networks include, but not limited to, convolutional neural network (CNN), deep neural network (DNN), recurrent neural network (RNN), or Restricted Boltzmann Machine (RBM). The learning technique is a method for training a AI module within the main server 115 using a plurality of learning data to cause, allow, or control the main server 115 to make a determination regarding health of plant/crop in a farm. Examples of learning techniques include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. At least one of a plurality of CNN, DNN, RNN, RMB models and the like may be implemented to thereby achieve execution of the present subject matter's mechanism through an AI model. A function associated with AI may be performed through the non-volatile memory, the volatile memory, and the processor. The processor may include one or a plurality of processors. At this time, one or a plurality of processors may be a general-purpose processor, such as a central processing unit (CPU), an application processor (AP), or the like, a graphics-only processing unit such as a graphics processing unit (GPU), a visual processing unit (VPU), and/or an Al-dedicated processor such as a neural processing unit (NPU). The one or a plurality of processors control the processing of the input data in accordance with a predefined operating rule or artificial intelligence (AI) model stored in the non-volatile memory and the volatile memory. The predefined operating rule or artificial intelligence model is provided through training or learning.
[0033] The training of the AI module may be performed by deploying the system sensor nodes 105 across one or more farms during training phase. Post deployment, data will be collected for an appropriate time period (e.g., 2-3 months) for different parameters and various crops. Iterations to models will be made further on the continuous stream of localised data captured from IoT system 100. The

collected data may be pruned and pre-processed and exploratory analysis will be performed to get insights. Further, based on the data captured from sensor nodes 105 deployed on the model farms, one or more AI models will be built to detect different kinds of attacks and stress happening in a plant based on which specific alerts may be given to the farmer in future during deployment/operation/real-time monitoring phase. The localised data will be further used to understand plant requirements such as plant growth factors, sunlight, water, etc. along with potential diseases and stressors. These models will be learned using advanced deep learning algorithms and time-series modelling.
[0034] FIG. 2 illustrates a detailed block diagram 200 of the plurality of types of sensors 105-1, 105-2, and 105-3 to be deployed in a farm for screening and monitoring behaviour of soil-crop-atmosphere in accordance with an embodiment of FIG. 1 of the present disclosure. Referring to FIG. 2, the plurality of types of sensors 105-1, 105-2, and 105-3 deployed in the farm may include, but not limited to, a soil parameter sensor unit 105-1, a plant parameter sensor unit 105-2, and an atmospheric/physical condition parameter sensor unit 105-3. In addition, a microcontroller unit 205, a communication network 210, and a power unit 215 may also be coupled to the sensor unit 105 for deployment in the farm. The microcontroller unit 205 is configured for processing data related to the plurality of types of sensors 105-1, 105-2, and 105-3. The communication network 210 enables communication between the plurality of the types of sensors 105-1, 105-2, and 105-3, the gateway 110, the main server 115, and the mobile computing device 120. The power unit 215 is configured for supplying power to the plurality of types of sensors 105-1, 105-2, and 105-3.
[0035] The communication network 210 may be a wireless network or a wired network or a combination thereof. Wireless network may include long range wireless radio, wireless personal area network (WPAN), wireless local area

network (WLAN), mobile data communications such as 3G, 4G or any other similar technologies. The communication network 210 may be implemented as one of the different types of networks, such as intranet, local area network (LAN), wide area network (WAN), the internet, and the like. The communication network 210 may either be a dedicated network or a shared network. The shared network represents an association of the different types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Internet Protocol (TCP/IP), Wireless Application Protocol (WAP), and the like. Further the communication network 210 may include a variety of network devices, including routers, bridges, servers, modems, computing devices, storage devices, and the like. In one implementation, the communication network 210 may be internet which enables communication between the plurality of the types of sensors 105-1, 105-2, and 105-3, the gateway 110, the main server 115, and the mobile computing device 120.
[0036] In one embodiment, the soil parameter sensor unit 105-1 may be configured for sensing and measuring plurality of parameters associated with the soil, for example data related to electrical conductivity of the soil, impedance rate of the soil, soil moisture, water retention by the soil, pH of the soil, physical-chemical properties of the soil, primary, secondary and micro-nutrients of the soil like nitrogen, phosphorus, potassium, calcium, magnesium, sulfur, boron, and the like. It may be noted that the above said parameters of the soil are measured and sensed by one or more types of sensors, for example, a soil sensor, an electrochemical sensor, a temperature and humidity sensor, a soil water retention flow sensor, an optical sensor, a pH sensor, and the like. Further, it is to be noted that the temperature and the moisture of the soil is measured at a frequency of every hour, pH is measured once in a month, primary nutrients (i.e. Nitrogen, Phosphorous, Potassium) are measured every day, secondary nutrients (i.e. Calcium, Magnesium, Sulphur) are measured every one-two weeks, and

micronutrients (i.e. Fe, B, Cu, CI, Mn, Mo, Zn, Co, Ni) of the soil are measured every three months.
[0037] Similarly, the plant parameter sensor unit 105-2 is configured for sensing and measuring plurality of parameters associated with the plant, for example data related to volatile organic compounds, and green leaf volatiles emissions. The plant sensor may include, but not limited to, a sap-flow sensor, and a bio-volatiles/VOCs (Volatile Organic Compound) /GLVs (Green Leaf Volatile) detection sensors. The sap-flow sensor is configured for sensing and measuring flow of water in tracheary cells of a xylem tissue. By measuring the flow of the water in the tracheary cells of the xylem tissue, provides a most accurate real-time assessment of plants response to changes in environment, abiotic stress, and productivity. The changes in the sap-flow are also reflective of soil moisture, soil nutrient availability, and sunlight availability. Thus, sap-flow monitoring helps in developing an optimization models to enhance crop productivity through precision inputs.
[0038] The VOCs (Volatile Organic Compounds) detection sensor is configured to detect and sense the VOCs emitted by the plant when the plant is under stress. The word "stress" herein referred to as a biotic stress, an abiotic stress, and a mechanical stress. Examples of the biotic stress may include, but not limited to, infection caused by phytobacteria, fungi, and Phyto virus's infection, and the like. Similarly, examples of the mechanical stress may include, but not limited to, an herbivory attack, an insect attack, and the like. Examples of the abiotic stress may include, but not limited to, sunlight (i.e., high temperature, light density), drought conditions, oxidative stress, humidity, ozone, C02, temperature, nutrient availability, and the like, that results in the emission of VOCs through the parts of the plant body. In other words, VOCs are emitted instantly upon the mechanical injury/damage/stress, or the biotic stress, or the abiotic stress to the plant. Most

VOCs are organic compounds which act as proteinase inhibitors in the insects & pathogens. The detection of these compounds can help identification of infected plants at the onset of disease itself. Few VOCs emitted by plants under stress may include, but not limited to, (E)-2-hexenal, 1-hexenol, 1-octanol, l-penten-3-one, 1-tetradecanol, 3-hexen-l-ol propanoate, 3-methyl-3-pentanol, carbamate, p-ethylguaiacol, R-caryophyllene, and y-terpene. The above said biotic stress, or the abiotic stress all have some impact on the volatile emission dynamics, or on the ratios of compounds in a volatile blend. The abiotic stress may also impact the plant quality, which can affect herbivore performance, and the performance of predators and parasitoids. Hence, the abiotic stress/environment has enormous potential to interfere with multitrophic interactions, including those mediated by volatiles, blends of which may be altered in plants subjected to oxidative stress. So, by calculating VOC emission, the system predicts much about the plant health with more accuracy.
[0039] As a matter of fact, plants under stress emit some kind of VOCs through its body, however, these VOCs are very specific to type of the stress, even quantity of emission changes with the change in the stress amount. If multiple stresses occur at the same time, the VOCs emitted may be different from the VOCs emitted in the case of individual stress. So, by determining the amount and type of VOCs, the type of stress will be identified. The VOCs may be C4-C12 fatty alcohols, or cyclic alcohols, or phenol-derived compounds, or terpene-derived compounds, and derivatives and mixtures, and the like. In addition, most of the VOCs are organic compounds which act as proteinase inhibitors in the insects, and the pathogens. The detection of the organic compounds can help in identification of the infected plants at the onset of disease itself. Further, it is to be noted herein that the plant volatiles, for example ethylene, terpenes, phenols, jasmonates, isoprene, S-methyl methane thiosulfonate (MMTS), and dimethyl trisulfide (DMTS) are measured at a frequency of every five-fifteen minutes.

[0040] As discussed earlier, in the same embodiment, the atmospheric parameter sensor unit 105-3 is configured for sensing and measuring data associated with various parameters related to weather conditions, ambient temperature, humidity, dew point, rainfall, and micro-climatic parameters within the farm demography via one or more types of atmosphere sensors, for example, temperature sensor, dew point sensor, and the like. In another embodiment of the present disclosure, a local weather station is set-up inside the farm. The local weather station helps in analyzing the data regarding the weather conditions so that the farmer can protect the plant from any incoming stresses in future. Further, it is to be noted herein that the atmospheric parameters, for example, raindrops, the atmospheric temperature, and the atmospheric humidity are measured every hour. Below is a table indicating an exemplary list of parameters and frequency of monitoring is presented for a quick reference:

S.No Parameter Frequency
1 Soil Temperature Every Hour
2 Soil Moisture Every Hour
3 Soil pH Once a Month
4 Soil Nutrients (Primary) Nitrogen (N) Every Day
5
Phosphorus(P) Every Day
6
Potassium (K) Every Day
7 Soil Nutrients (Secondary) Calcium (Ca) Every 1-2 Weeks
8
Magnesium (Mg) Every 1-2 Weeks
9
Sulphur (S) Every 1-2 Weeks

10 Micronutrients Fe, B, Cu, CI, Mn,
Mo, Zn, Co, Ni Every Three Months
11 Raindrop Every Hour
12 Environment Temperature Every Hour
13 Humidity Every Hour
14 Plant Volatiles Ethylene Every 5-15 Minutes
15
Terpenes Every 5-15 Minutes
16
Phenols Every 5-15 Minutes
17
Jasmonates Every 5-15 Minutes
18
Isoprene Every 5-15 Minutes
19
S-methyl methane
thiosulfonate
(MMTS) Every 5-15 Minutes
20
dimethyl trisulfide (DMTS) Every 5-15 Minutes
Table 1
[0041] FIG. 3 A illustrates a schematic diagram of an architecture of an Internet of Things (IoT) system 100 illustrating plurality of examples of communication network to be used for communication among the various system components. As discussed earlier, the plurality of the types of the sensors 105-1, 105-2, and 105-3, the gateway 110, the cloud interface/main server 115, and the mobile computing device 120 are communicatively coupled with each other via one or more communication networks 210.

[0042] As depicted the main server 115 may include at least a controller 125 (or a processor), a transceiver 130, and a memory/database 135. In some embodiments, the memory /database 135 may be communicatively coupled to the controller 125. The memory 135 stores data, instructions executable by the controller 125. The memory 135 may include one or more modules/units and a database to store data. The one or more modules/units may be configured to perform the steps of the present disclosure using the data stored in the database to analyze soil-crop-atmospheric data in order to determine health of the plant, in accordance with various embodiment of the present invention. Additionally, the memory may be volatile or non-volatile memory and may be used for AI based analytics performed at the main server 115. Further, the transceiver 130 may be configured to transmit and receive data at the main server 115, such as receiving data via the gateway 110 and transmitting alerts to the mobile computing device 120, in accordance with various embodiments of the present invention.
[0043] In one embodiment of the present disclosure, the communication between the gateway 110 and the plurality of sensors in the sensor unit 105 may be performed via a wireless networking such as, but not limited to, BLE (Bluetooth Low Energy), Wi-Fi, Long Range Radio (LoRa), or ZigBee. Further, the the gateway 110 and the main server 115 may be configured to communicate via wireless communication networks such as, but not limited to, internet, MQTT (Message Queuing Telemetry Transport), or cellular network (e.g., 3G/4G) in accordance with an embodiment of the present disclosure.
[0044] In yet another embodiment, a Zigbee router is used in place of the gateway 110. It may be noted herein that the Zigbee router is operatively connected with the plurality of sensors 105-1, 105-2, and 105-3, and the main server 115 via a Zigbee and cellular/ Wi-Fi/ ethemet, respectively.

[0045] FIG. 3B illustrates a schematic diagram of an architecture of an Internet of Things (IoT) system 100 deployed in a farm using the various system components, in accordance with an embodiment of the present invention. For deployment in a farm, the sensor unit 105 comprising a plurality of sensors may be deployed as a sensor node in the IoT system 100. The farm may include a plurality of such sensor nodes 105 based on size of the farm. The plurality of sensor nodes 105 sense the targeted parameters on predetermined sensing durations. The sensor nodes 105 collect the data and send it to a gateway 110, which relays data to the cloud server 115 for storage and AI based analytics. The cloud server 115 processes the received data using the AI based analytics to determine health of the plant and identify any issues, such as a crop stressor. The localized soil-plant-atmosphere data is also used to learn various crops stressors models using advanced AI based models. These models help in detecting and alerting any kind of stressors in the crops at its onset, thus reducing the disease detection time from weeks to hours. This information is then disseminated to farmers using a web-based or mobile-based dashboard 120. The real-time alerts will further enable farmers with timely information and making wiser decisions.
[0046] Additionally, the system 100 may be used for precision monitoring of input requirements of specific crops. Also, the data detected by the sensor nodes 105 may be utilized for controlling usage of fertilizers, pesticides, insecticide, and early disease management. The sensor nodes based data may be further used for detecting optimal time to harvest a crop, thus maintaining the best quality of the produce. Moreover, the biofertilizer profiles based on soil chemistry may also be determined using the data detected by the sensor nodes. The localized crop data and real-time monitoring can also be used by organizations in improvement of farming.
[0047] FIG. 4A, FIG. 4B, FIG. 4C, and FIG. 4D illustrate a systematic diagram of a thin film sensor, an ionisation-based sensor, a current sensing showing

amplification and conversion to an output voltage, and a block diagram showing integrated sensor unit, respectively in accordance with an embodiment of the present disclosure.
[0048] In the present embodiment of the disclosure, two types of VOCs detection sensors may be used simultaneously in an integrated sensor unit 400D which are based on different detection techniques. For example, sensing via detecting change in an electrical property of a thin film as well as sensing via detecting flow rate of an ionized gas molecule. The above said two types of VOCs sensors can be integrated together and may address different classes of compounds and thereby increase the range of chemicals that the sensor can detect. It is to be noted herein that the two types of the VOCs sensors help in mapping multiple different types of VOCs emitted by the plant. Since, some compounds may not be ionized without fragmenting them, having a thin film method can be used for those molecules. Thus, while the thin film sensor may be used for detection of first class of VOCs, the ionization sensor may detect a different class of VOCs. In one embodiment of the present invention, the integrated sensor unit 400D may be latched on or above the leaves.
[0049] Thin film sensor for VOC sensing (referring to FIG. 4A): Herein, the conductive element is deposited on a silicon, a glass, or a flexible substrate that are exposed to the VOCs and the VOCs can get adsorbed on the element. The change in the conductivity will be detectable by observing the change in the current. A system 406 for reading the current and converting the current into an output is required (referring to FIG. 4C). The sensor has multiple types of thin film and can be scaled down to a desirable size during fabrication. Optimal size and detection sensitivity depend on an initial material characterisation and on the adsorption coefficient of the material and VOCs. Exemplary materials for thin film sensors may include, but not limited to, porous polymers, carbon nanotubes (CNTs),

graphene/graphene oxide, and nano gold rods. In a preferred embodiment, CNTs and graphene oxide surfaces may be used for thin film sensors, which show a considerable change in conductivity depending when gas compounds adsorb to the surface. Further, in one embodiment, the thin film sensor may have multiple types of thin films and can be scaled down to desirable size during fabrication.
[0050] Ionisation-based sensor (referring to FIG. 4B): The ionisation-based sensor ionises the incoming gaseous compound using UV (Ultraviolet) light and read the value of current generated by the flow of ionized charges. This is a more suitable method for smaller easily ionisable VOCs. The outer chamber is made of a light flexible polymer, incoming gas will be ionized and detected using the electrodes deposited in the inner tubing. The sensitivity of the ionisation-based sensor device can be tuned by optimising the ionisation energy as well as optimising the electrode area in the detection chamber. A system 406 for reading the current and converting the current into an output voltage is required (referring to FIG. 4C). Referring to FIG. 4C, includes a transimpedance amplifier configured for amplifying an input "I" current from sensing element, an analog output configured for outputting the current into the analog form, and an analog to digital converter configured for converting the analog current into a digital output.
[0051] Integrated sensor unit (referring to FIG. 4D): In the same embodiment of the present disclosure, an integrated sensor unit 400D is used. The integrated sensor unit 400D includes the thin film sensor 402, the ionisation-based sensor 404, and a highly compact sensing circuitry 406 and batteries 408. The integrated sensor unit 400D is fabricated as a separate sensor and having a compact size within 1cm x 1cm each. In one embodiment, the size of the integrated sensor unit 400D comprising the thin film sensor 402 and the ionization sensor 404 may be either one of 1 cm x 1 cm, 1 cm x 2 cm, 2 cm x 1 cm, and 2 cm x 2cm. Thus, the integrated sensor unit 400D is so compact that it may be easily stuck to or hung on a small

plant. The integrated sensor unit 400D is integrated along with a current amplifier and an analog to digital converter 406, and a RF (Radio Frequency) transmitter 410 on a small substrate like conventional PCB or a flexible substrate. The integrated sensor unit 400D also houses a small battery 408 to power the sensors and readout circuitry. Double sided soldering makes this system an extremely compact i.e., approximately 1-4 sq. cm. In addition, the integrated sensor unit 400D is sealed with water resistant epoxy polymer, and only an inlet/outlet for input air + VOC is available which is covered with a protective porous membrane.
[0052] Further, in real-world deployment, the present invention may be deployed in farms, with 15-20 nodes of sensors (as discussed herein) being deployed in an open field (e.g., 2 acres). Also, these different nodes can cooperate to improve the overall detection and estimation performance of different parameters, as one sensor may not be able to reliably pick up the VOCs reliably because of environmental factors.
[0053] FIG. 5 illustrates an exemplary process flow 500 for screening and monitoring behaviour of soil-crop-atmosphere to determine health of a plant, in accordance with an embodiment of the present disclosure.
[0054] At step 502, the method comprises measuring one or more parameters associated with the soil. In one embodiment, the parameters associated with the soil may be measured by various (first) sensors, such as, but not limited to, a soil sensor, temperature and humidity sensor, soil water retention flow sensor, pH sensor, an optical sensor and an electrochemical sensor. The measured one or more parameters may include, but not limited to, electrical conductivity, impedance rate of the soil, soil moisture, water retention, pH, soil physic-chemical properties, important primary, secondary and micro-nutrients like nitrogen, phosphorus, potassium, calcium, magnesium, sulfur, and boron.

[0055] At step 504, the method comprises measuring one or more atmospheric parameters. In one embodiment, the measured atmospheric parameters may include, but not limited to, weather conditions, ambient temperature, humidity, dew point, rainfall, and micro-climatic parameters within the farm demography. The atmospheric parameter related sensors may be standard well-known (second) sensors such as, but not limited to, temperature sensor, humidity sensor, and light sensor.
[0056] At step 506, the method comprises measuring one or more parameters related to plant condition. In one embodiment, the parameters associated with the plant condition may be measured by various sensors, such as, but not limited to, a sap-flow sensor and a bio-volatiles/VOCs/GLVs detection sensors. The one or more parameters related to plant condition may include, but not limited to, flow of water in tracheary cells of a xylem tissue of the plant, VOCs, and green leaf volatiles emissions. The bio-volatiles/VOC detection sensors of the plant parameter sensor unit may be latched on or above the leaves of the plant, while the sap flow sensor may be attached to stem of the plant.
[0057] In one embodiment, an integrated sensor unit comprising at least two types of VOC detection sensors may be employed for detecting bio-volatiles/VOCs. Examples of VOC detection sensors may include a thin film sensor and an ionization sensor. In the thin film sensor, upon exposure to some VOCs, the change in the conductivity of a conductive element will be detectable by observing the change in the current. In the ionization based sensor, another set of VOCs are ionized using UV light and a corresponding current generated by the flow of ionized charges may be measured. Since, some compounds may not be ionized without fragmenting them, the thin film sensor can be used for those molecules/VOCs. Thus, the thin film sensor may be configured to detect the change in electrical

property of the thin film corresponding to detection of a first class of VOCs of a plurality of VOCs. Further, the ionization sensor may be configured to detect the flow rate of ionized gas molecule corresponding to detection of a second class of VOCs of the plurality of VOCs.
[0058] At step 508, the method comprises receiving data related to soil, atmospheric parameters, and VOC detection sensors. The data may be received at a main server via a gateway from the various sensor unit based system. One or more communication networks may be employed to receive the data at the main server. In one embodiment, for the VOC detection sensors, the method may include receiving data related to change in electrical property of the thin film (e.g., current) for one set/class of VOCs, and the current associated with the flow rate of the ionized VOCs for another set/class of VOCs. Similarly, the data related to various parameters measured for soil and atmosphere may also be received from the various sensor units.
[0059] At step 510, the method comprises analyzing the received data related to soil, atmospheric properties, and VOC detection sensors. In one embodiment, the data may be analyzed by a controller of the main server. For example, the received data related to change in electrical property of the thin film and the current associated with the flow rate of the ionized VOC may be analyzed by comparison with pre-stored data of a similar healthy plant at the server. In one embodiment, the analysis may be performed based on AI based analytics using a machine learning or deep learning or neural network models associated with plant health or soil-crop-atmosphere data. The machine/deep learning models may be trained based on extensive historical data related to soil/atmosphere/plants using well known mechanism.

[0060] At step 512, the method comprises determining a type of stress or disease in the plant based on the analysis at step 510 to alert a user (farmer). Specifically, the main server (or controller) detects an abnormal behavior related to a crop stressor. Generally, when the crop is under stress, the crop's behaviour changes which can be identified using different processes or techniques such as measuring different amounts and types of VOCs (Volatile Organic Compounds) /GLVs (Green Leaf Volatiles) emitted by the crop. Further, in one embodiment, the classes of horticulture crop volatiles (detected at previous steps) may be mapped with classes of diseases, occurrence, stage of the crop, and other micro-climatic parameters for identifying different crop biotic and abiotic stressors.
[0061] At step 514, the method comprises transmitting, to a user device, an alert related to the determined type of stress or disease in the plant. In one embodiment, the alert may be sent real-time via an SMS, mobile application push notification, or an automated call. The alert may be sent via a transceiver within the main server. The real-time alerts will further enable farmers with timely information and making wiser decisions. Further, the alerts shared based on analysis of sensor based data may identify nutrient deficiencies and infestations much before any visual symptoms appear from large amounts of collected heterogeneous data. Thereby, the present invention yields significant advantage over conventional solutions which rely on images based data of plants to identify any on-farm issues.
[0062] The figures and the foregoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, orders of processes described herein may be changed and are not limited

to the manner described herein. Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts necessarily need to be performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples. Numerous variations, whether explicitly given in the specification or not, such as differences in structure, dimension, and use of material, are possible.

We Claim;

1. An Internet of Things (IoT) system (100) to determine health of a plant at a
farm, the system (100) comprising:
an integrated sensor unit (400D) comprising:
a thin film sensor (402), deployed in the farm, configured to detect a change in an electrical property of a thin film in response to exposure of the thin film to a volatile organic compound (VOC) emitted from the plant, and
an ionization sensor (404), deployed in the farm, configured to ionize another VOC emitted from the plant and detect current associated with the flow rate of the ionized VOC; and
a controller (125) in communication with the integrated sensor unit (400D) and configured to:
receive, via a gateway (110), data related to the change in electrical property of the thin film and the current associated with the flow rate of the ionized VOC, and
determine a type of stress or disease in the plant based on the received data.
2. The system (100) as claimed in claim 1 comprising:
a soil parameter sensor unit (105-1) comprising at least a first sensor configured to measure one or more parameters associated with the soil; and
an atmospheric parameter sensor unit (105-3) comprising at least a second sensor configured to measure one or more atmospheric parameters.
3. The system (100) as claimed in claim 1 comprising a transceiver (130)
configured to transmit, to a user device (120), an alert related to the determined type
of stress or disease in the plant.

4. The system (100) as claimed in claim 1, wherein the thin film sensor (402) is configured to detect the change in electrical property of the thin film corresponding to detection of a first class of VOCs of a plurality of VOCs, and wherein the ionization sensor (404) is configured to detect the flow rate of ionized gas molecule corresponding to detection of a second class of VOCs of the plurality ofVOCs.
5. The system (100) as claimed in claim 1, wherein the thin film sensor (402) is made of one of carbon nanotubes and graphene oxide deposited on one of a silicon, glass, and a flexible substrate.
6. The system (100) as claimed in claim 1, wherein the thin film sensor (402) is configured to detect the change in conductivity of the thin film based on detection of a change in current, and wherein the ionization sensor (404) is configured to ionize the other VOC using ultraviolet light.
7. The system (100) as claimed in claim 1, wherein the determination of the type of stress or disease in the plant comprises a determination of biotic stress or a mechanical injury to the plant.
8. The system (100) as claimed in claim 1, wherein the integrated sensor unit (400D) is attached to the plant.
9. The system (100) as claimed in claim 1, wherein the controller (125) is configured to compare data related to the change in the electrical property of the thin film and the current associated with the flow rate of the ionized VOC with pre-stored data of a healthy plant.

10. A method (500) to determine health of a plant at a farm, the method (500) comprising:
detecting (506), by a thin film sensor deployed in the farm, a change in an electrical property of a thin film in response to exposure of the thin film to a volatile organic compound (VOC) emitted from the plant;
ionizing (506), by an ionization sensor deployed in the farm, another VOC and detect current associated with the flow rate of the ionized VOC;
analyzing (510) data related to the change in electrical property of the thin film and the current associated with the flow rate of the ionized VOC; and
determining (512) a type of stress or disease in the plant based on the analysis to alert a user.