Description:Form 2

THE PATENTS ACT, 1970
COMPLETE SPECIFICATION
(See section 10 and rule 13)

Dew Enabled Intelligent Precision system for Crop Monitoring

APPLICANT NAME: INSTITUTE OF ENGINEERING & MANAGEMENT

ADDRESS: INSTITUTE OF ENGINEERING & MANAGEMENT, SALT
LAKE ELECTRONICS COMPLEX SECTOR – V, SALT
LAKE, KOLKATA, PIN – 700091.

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

Field of the invention:
This present invention discloses a precision agriculture and remote monitoring systems. It encompasses integrating sensor networks, IoT communication protocols, data analytics, and machine learning algorithms to enhance crop cultivation practices and soil health management in agricultural settings.

Background/Prior Art:

Conventional agricultural practices rely on manual observation and generalized management strategies, leading to suboptimal resource utilization and variable crop yields. Modern technological advancements have introduced sensor-based monitoring systems and data-driven decision-making tools, revolutionizing farming practices. However, existing solutions may need more scalability, complex infrastructure, and high maintenance requirements. Thus, an intelligent precision agriculture monitoring system is required to seamlessly collect, transmit, and analyze real-time data from dispersed sensor nodes across agricultural fields. Such an ecosystem would empower farmers with actionable insights to optimize crop selection, irrigation scheduling, and nutrient management, thereby enhancing productivity, sustainability, and resource efficiency in agriculture.

CN113743832B :Rice Disaster Monitoring System and Method discloses a comprehensive system for monitoring rice disasters, comprising several key modules. These include a rice ecological data module, encompassing aspects such as rice variety examination, zoning, and climate zoning indexes for rice planting. Additionally, there's a weather monitoring module to gather relevant weather information, a rice growing period module for determining the current growth stage of rice based on standard indices and meteorological data, a disaster judgment module to assess the type and severity of disasters during the rice growing phase, and a disaster processing module to devise appropriate response measures based on the identified disaster type and severity. The system is designed to be interfaced with a terminal for displaying pertinent disaster information and treatment measures.
This patent focuses solely on disaster monitoring in rice cultivation while it integrates meteorological and ecological data, it does not provide continuous real-time monitoring of soil health, crop conditions, or precision agriculture insights. The system primarily reacts to disasters rather than offering proactive farming recommendations. Whereas the present invention enables real-time soil and environmental monitoring using dew-enabled sensor nodes. Instead of just assessing disasters, our system predicts potential issues like soil nutrient depletion, moisture imbalance, and environmental stressors. With machine learning-based analytics, farmers receive personalized recommendations for crop selection, irrigation scheduling, and nutrient management, ensuring proactive rather than reactive farming.

US20230039763A1: Selective Crop Management System Using Biosensor Plants discloses a novel real-time selective crop management method utilizing biosensor plants. These biosensor plants are engineered with specific genetic modifications to encode visual biomarkers. These biomarkers are linked to reporter genes, which exhibit detectable phenotypes. Additionally, the regulatory regions of these genes are connected to specific plant or environmental parameters. Consequently, the reporter gene-phenotype's expression indicates the status of these parameters in the biosensor plant or its surroundings.

Whereas the method relies on genetically modified biosensor plants with visual biomarkers linked to specific environmental conditions. This approach limits its applicability to genetically engineered crops and may not be feasible for many regions due to regulatory constraints on genetically modified organisms (GMOs). Additionally, it primarily focuses on selective monitoring rather than offering an integrated precision farming solution. Whereas our system does not rely on genetically modified crops. Instead, it utilizes a network of non-invasive dew-enabled sensor nodes to monitor soil moisture, pH levels, NPK concentrations, and environmental parameters. This ensures that the solution is widely applicable to any crop type while still providing real-time precision farming insights.

US2023177330A1 provides herein the methods, systems, and media that implement machine learning algorithms to determine a cultivar regimen recommendation for a crop based on crop yield and cultivar condition data. a) Agricultural Data Integration and Analysis Platform discloses a computer-implemented method) solar-powered cultivar conditions from an internet of things sensor; b) applying a first machine learning algorithm to at least a portion of the current cultivar conditions to determine the cultivar regimen recommendation; c) receiving a verified crop yield after the cultivar regimen recommendation has been performed on the crop; d) feeding back the verified crop yield to improve the first machine learning algorithm's calculation over time; ande) transmitting the cultivar regimen recommendation of determining a cultivar regimen recommendation for a crop.
Whereas the present invention uses dew-enabled sensor nodes for soil monitoring and machine learning for crop selection, soil health, and irrigation. A real-time feedback loop integrates data from sensors and drones to refine recommendations. ESP32 microcontrollers ensure on-site processing, offering farmer-friendly, real-time decision support, unlike the US patent’s general IoT sensors. With this, the patent leverages real-time data from sensor-equipped dew nodes, measuring soil temperature, and moisture, pH, and NPK levels for immediate analysis. It focuses on current environmental conditions rather than past crop yields, using machine learning to generate personalized crop and soil management recommendations. Unlike the staged training process in Claim 31, our system provides continuous, real-time insights and delivers actionable recommendations via an intuitive farmer interface, enabling informed decision-making on the spot. The other invention does not specifically mention a neural network but instead uses machine learning algorithms more broadly to analyze real-time soil data from sensor-equipped dew nodes for crop selection and soil management recommendations. The focus is on practical, field-specific insights rather than complex neural network-based modelling.
The present invention is based on real-time soil data from dew nodes for crop selection and soil management, rather than historical regimens. Uses machine learning to analyse soil conditions, not historical crop yield or cultivar instructions. Does not incorporate verified categorical crop yield for training. Focuses on real-time recommendations, rather than refining algorithms based on past yield data. The present system focuses on real-time soil data collected from sensor-equipped dew nodes, which includes soil temperature, moisture, pH levels, and concentrations of Nitrogen, Phosphorus, and Potassium. No mention of wind speed, gust measurements, aerial imagery, or other environmental parameters like chemical composition, fruit growth measurement, or satellite imagery as part of the input features for machine learning or crop recommendation.
The present invention addresses field-level monitoring and does not specify single-plant conditions as a primary focus, but it does involve sensor data which could potentially support single-plant insights indirectly. Present invention includes GPS-enabled drones and sensors for location-aware monitoring but focuses on aggregated field data rather than precise single-plant conditions. The present invention involves drone and node-based data collection which supports high-resolution GPS for field-level applications. Present invention focuses on optimizing crop management via recommendations but does not specifically outline adjustments by category such as pruning or fertilizer types. It leverages sensor-driven insights to refine resource utilization broadly. It does not discuss reflective properties but leverages sensors and data for environmental monitoring and actionable insights. It is based on real-time environmental monitoring for recommendations. Present invention uniquely incorporates drones and dew nodes for sustainability and precision in field management.
Therefore, to the best of our knowledge, none of the above-mentioned prior art attempts, individually or collectively propose the system and embodiments indicated and disclosed by the present invention

Object of the invention:

The objective of the present invention is to develop an intelligent precision agriculture monitoring system that leverages modern technology to improve crop cultivation practices and soil health management.

Further the objective of the present invention is to establish a robust data collection and transmission infrastructure
Another objective of the present invention is to integrate machine learning algorithms into the server infrastructure to analyze collected data and provide personalized recommendations to farmers.
Yet another objective of the present invention is to utilize the MQTT protocol for communication between dew-enabled sensor nodes and a central server, the invention aims and this infrastructure will enable real-time monitoring of soil conditions, nutrient levels, and environmental parameters across extensive agricultural areas.
Yet another objective of the present invention is to integrate irrigation scheduling, and nutrient supplementation by offering actionable insights for crop selection wherein the invention aims to enhance agricultural productivity, sustainability, and profitability while minimizing resource waste and environmental impact.

Summary of the Invention:
The invention relates to an intelligent precision agriculture monitoring system that addresses the limitations of existing solutions by providing a comprehensive and integrated approach to precision farming. Key components of the system include dew-enabled nodes equipped with soil sensors, a drone-enabled data collection mechanism, and a centralized server infrastructure with machine learning capabilities. MQTT protocol ensures efficient communication between dew-enabled nodes and the central server, enabling seamless data transmission even in remote or low-bandwidth environments.
In an aspect of the invention, the system collects real-time data on soil temperature, NPK levels, soil moisture, and pH, allowing for precise soil health and environmental conditions monitoring. Machine learning algorithms analyze the collected data to generate personalized recommendations for crop selection, irrigation scheduling, and nutrient supplementation based on historical trends and environmental factors. In accordance with the invention, the invention aims to optimize resource utilization, minimize input waste, predicting diseases and improve agricultural productivity, sustainability, and profitability by empowering farmers with actionable insights.

Brief Description of the Drawing:
The following figures can be used to gain a thorough grasp of the system and methodology of the current invention:

Figure 100: Pictorial Representation of the UAV System for Precision Agriculture

101- Sensor layer or data collection layer
102-Data aggregation layer or edge layer
103- Cloud layer
104-Collecting Data from Field
105- Sending data through wireless network
106- UAV acting as a broker
107- Storing data in cloud or servers as well as sending data to the user
Figure 200- Diagram of the Dew Node, 201-Dew Node, 202-Charging Port, 203-NPK Sensor, 204- Capacitive Soil Moisture Sensor, 205-pH Sensor, 206-Soil Temperature Sensor
Figure 300: Schematic of the On-Board Electronics Circuit of the UAV System
301-Power Distribution Board, 302- Electronic Speed Controller, 303-Brushless DC Motor
304-Flight Controller, 305-Telemetry, 306-Receiver, 307-Power Module, 308-Battery
GPS, 309-Gimbal, 310-Camera
Figure 400: Strategic Calibrated and Accurate Placement of Sensors in Dew Node
Sensors are placed strategically, calibrated for accuracy, and tested for connectivity. Electronic boards ensure reliable data transmission with protocols and error handling. Microcomputers manage IoT and ML tasks with optimized resources and security. MQTT and Node-RED enable real-time data transfer, with continuous network monitoring.
Figure 500, 600, 700 are used for the experiment, a comprehensive dataset was utilized to support the analysis and modeling process. The dataset includes a variety of features that are critical for the task at hand, ensuring a robust foundation for training and evaluation. Each feature was carefully selected to capture relevant information and patterns needed for accurate predictions.
Figure 800: Comparative Analysis of Nitrogen (N), Phosphorus (P), and Potassium (K) Levels Across Various Crops from Field Data
The IoT dashboard provides a user-friendly interface for analyzing agricultural data, helping farmers make informed decisions on temperature, humidity, air quality, and soil conditions. It enhances farming efficiency with real-time insights and alerts. Future improvements may focus on scalability, usability, and technology integration.
Figure 900 A: Correlation Between Rainfall, Temperature, pH, and Essential Soil Nutrients (N, P, K)
Figure 900 B: Flowchart of Dew Enabled Intelligent Precision Agriculture Ecosystem for Crop Monitoring

The relationship between temperature, rainfall, pH, phosphorus (P), potassium (K), nitrogen (N), and rainfall is essential to comprehending and maximizing soil health and agricultural productivity, as shown in above figure.

Detailed description of the embodiment
The following provides a detailed description of the embodiments of the disclosure as illustrated in the accompanying drawings. These embodiments are presented with sufficient detail to clearly convey the disclosure while encompassing all potential modifications, equivalents, and alternatives that fall within the scope of the appended claims. The accompanying drawings, which form an integral part of this specification, illustrate an embodiment of the invention and, together with the description, serve to explain its underlying principles. The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate an embodiment of the invention, and together with the description, serve to explain the principles of the invention. As used in the description herein and throughout the claims that follow, the meaning of “a,” “an,” and “the” includes plural reference unless the context dictates otherwise.

The envisioned agriculture monitoring invention presents a solution leveraging cutting-edge technology to revolutionize farming practices.
In the preferred embodiment, the intelligent precision agriculture monitoring system that addresses the limitations of existing solutions by providing a comprehensive and integrated approach for precision farming. The UAV system framework enhances precision agriculture by integrating dew nodes, drones, and advanced data analytics, as illustrated in the architecture diagram. This system aims to optimize data collection, crop health monitoring, and decision-making for sustainable farming practices.
Sensor Layer or Data Collection Layer:
The sensor layer in UAV system framework consists of a network of sensor-equipped dew nodes strategically deployed at 45-50 meter intervals across agricultural fields to ensure continuous monitoring of soil health. Each dew node is equipped with multiple sensors, including a soil temperature sensor to monitor temperature variations affecting seed germination and root development, a soil moisture sensor to measure water content for efficient irrigation, a soil pH sensor to determine soil acidity or alkalinity for crop suitability, and an NPK sensor to analyze the concentrations of Nitrogen (N), Phosphorus (P), and Potassium (K) key nutrients for plant growth. These dew nodes are powered by ESP32 microcontrollers, enabling real-time data processing and wireless transmission. The UAV, integrated with an ESP32 module and Raspberry Pi, collects sensor data from the dew nodes using a peer-to-peer (P2P) network with a transmission range of up to 450 meters. Once collected, the data is pre-processed and transmitted to a central IoT server hosting Node-RED, where machine learning algorithms analyze soil conditions and generate predictive models and personalized recommendations for crop selection and soil management. This sensor layer forms the backbone of UAV system, ensuring accurate, real-time monitoring for data-driven precision agriculture.
Data Aggregation Layer or Edge Layer:
The data aggregation layer is responsible for gathering environmental and soil data from the dew nodes deployed at 45-50 meter intervals across the farmland to ensure comprehensive coverage. Each dew node is equipped with sensors to monitor critical soil parameters, including soil humidity, temperature, pH, and nutrient levels (NPK). The collected data is continuously recorded in the dew node’s microcontroller (NodeMCU) and stored in a linked list for efficient processing.
When a drone equipped with a Raspberry Pi approaches a dew node, it scans for signals from dew nodes within its range. Upon detecting a dew node, it receives the sensor data via an MQTT-based communication protocol. The MQTT model ensures efficient and reliable data transmission between the dew nodes and the drone. This communication occurs without requiring an internet connection, allowing the system to function even in remote areas with limited connectivity.
In the UAV system framework, the MQTT protocol facilitates efficient communication between dew nodes and the UAV. When the UAV enters a dew node’s signal range, it receives sensor data via MQTT, where the dew nodes act as publishers sending the data, and the UAV acts as a subscriber collecting the information. MQTT is a lightweight, publish/subscribe messaging protocol designed for low-bandwidth and unreliable networks, ensuring reliable data transmission with minimal bandwidth consumption and low latency. This makes it ideal for real-time sensor data collection, enabling efficient monitoring and analysis for precision agriculture.
Cloud Layer:
The cloud layer is responsible for storing, processing, and analyzing the collected data. Once the drone collects the data from the dew nodes, it uploads the information to an IoT application platform hosted on a cloud server. This cloud-based system is capable of performing real-time analysis and providing insights into soil and crop health. The cloud layer processes the data for further decision-making, ensuring optimized farming practices such as irrigation, fertilization, and pest control.
The UAV system framework is designed to function without internet connectivity by utilizing an ad-hoc network for communication between the UAV and dew nodes, and a mesh network for communication between the dew nodes themselves. The UAV, equipped with a Raspberry Pi, directly connects to dew nodes within its range, allowing for seamless data transmission using the MQTT protocol, all without the need for external network infrastructure like Wi-Fi or cellular data. The dew nodes are linked in a mesh network, enabling data to be relayed through neighboring nodes if one is out of range. This setup ensures continuous data collection in remote areas, and once the UAV returns to an area with internet access, it uploads the collected data to the cloud for further analysis. This approach enables the system to operate efficiently in off-grid environments, providing real-time data collection and communication without relying on constant internet connectivity.
The designed network of dew nodes strategically dispersed throughout agricultural landscapes. Each of these nodes is meticulously equipped with an array of sensors, encompassing vital parameters crucial for soil health assessment, including temperature, moisture content, pH levels, and concentrations of essential nutrients such as Nitrogen, Phosphorus, and Potassium. These sensor-equipped dew nodes are further enhanced with ESP32 microcontrollers, affording them the capability for real-time data processing and transmission. An integral element of the system is the incorporation of drones, each outfitted with an ESP32 module, effectively extending the network's reach and enabling seamless data collection from the deployed dew nodes via a robust peer-to-peer (P2P) network with an expansive operational range of up to 400- 450 meters. Upon retrieval of the gathered data, the drones promptly relay this invaluable information to an on board Raspberry Pi, acting as a central hub for data aggregation and pre-processing. From there, the data journey continues to a central server, which serves as the nerve centre of the entire system, housing IoT application platform NodeRED—an advanced, user-friendly tool for visual programming. Harnessing the power of sophisticated machine learning algorithms, the server meticulously analyzes the aggregated soil data, unveiling nuanced insights and predictive models tailored to the specific needs of individual agricultural plots. These insights range from optimized crop selection recommendations to tailored soil management strategies, all aimed at empowering farmers with actionable intelligence to drive informed decision-making processes. The culmination of this intricate data analysis endeavour manifests in the generation of comprehensive reports, accessible to farmers through intuitive interfaces. Armed with these actionable insights, farmers are empowered to make data-driven decisions, optimize crop yields, mitigate risks, and foster sustainable agricultural practices that are not only environmentally conscious but also economically viable in the long term. Thus, the proposed agriculture monitoring project stands poised to redefine farming paradigms, ushering in an era of precision agriculture, sustainability, and agricultural prosperity.
The Agri IoDT framework enhances precision agriculture by integrating dew nodes, drones, and advanced data analytics, as illustrated in the architecture diagram. This system aims to optimize data collection, crop health monitoring, and decision-making for sustainable farming practices.
The AgriIoDT framework is designed to function without internet connectivity by utilizing an ad-hoc network for communication between the UAV and dew nodes, and a mesh network for communication between the dew nodes themselves. The UAV, equipped with a Raspberry Pi, directly connects to dew nodes within its range, allowing for seamless data transmission using the MQTT protocol, all without the need for external network infrastructure like Wi-Fi or cellular data. The dew nodes are linked in a mesh network, enabling data to be relayed through neighboring nodes if one is out of range. This setup ensures continuous data collection in remote areas, and once the UAV returns to an area with internet access, it uploads the collected data to the cloud for further analysis. This approach enables the system to operate efficiently in off-grid environments, providing real-time data collection and communication without relying on constant internet connectivity.
Image Sensor Layer:
The image sensor layer is an integral part of the framework, where each dew node is equipped with a camera to capture real-time images of the crops. These images, along with sensor data, serve as inputs for crop health monitoring, helping to detect early signs of diseases, pest infestations, or other issues affecting crop growth. The image sensor provides critical visual data, which is transmitted to the drone for further processing and analysis.
Figure 100 illustrates the diagram depicts an aerial perspective of an agricultural field with a drone traversing the airspace above. The drone is illustrated as a quad copter outfitted with propulsion systems and an embedded ESP32 module. The agricultural landscape is divided into discrete zones, each demarcated to represent the placement of sensor-equipped dew nodes. Symbolic lines extend from the drone to the dew nodes, indicating the wireless data transmission occurring between them. In addition, contextual elements such as topographical features, vegetative cover, and agricultural infrastructure may be depicted to provide environmental context.
Figure 200 illustrates the diagram portrays a schematic representation of a sensor-equipped dew node, showcasing its structural design and constituent components. The main body of the node is depicted as a compact enclosure with apertures designated for the installation of various sensors, encompassing those for monitoring soil temperature, moisture content, pH levels, and concentrations of essential nutrients, including Nitrogen, Phosphorus, and Potassium. Each sensor is labelled correspondingly within the node. Furthermore, the diagram features additional elements such as an integrated ESP32 microcontroller, power supply unit, and wireless communication module. Visual indicators, such as directional arrows, delineate the flow of data between sensors and the microcontroller, as well as the wireless communication pathways, elucidating the operational functionality of the node.
Figure 300 illustrates the diagram provides an internal view of the drone's electronic circuitry and internal components. The primary focus is on the on board electronics responsible for facilitating data transmission and processing. Critical components, including the ESP32 module, wireless communication antennas, and interface connectors for external devices (such as sensors), are prominently featured. Additionally, the diagram may illustrate ancillary components such as power distribution circuits, voltage regulation mechanisms, and data storage modules. Schematic lines indicating signal pathways and interconnections between components aid in comprehending the architectural layout of the system. Accompanying annotations delineate the functionality of each component and its respective contribution to the overall operation of the drone system.
Algorithm 1 for Dew Enabled Intelligent Precision Agriculture Ecosystem for Crop Monitoring
Require: 𝑥: Belongs to the 𝑑 dimensional real space, represented as 𝑥 ∈ ℝ . This means 𝑥 is a vector with 𝑑 features.
Require: 𝑦: Represents the output or prediction made by the model.
Require: 𝑓: Represents the prediction model.
Step 1: Train the SVM model f_SVM (𝑥) to predict class labels.
Step 2: Train a Random Forest model f_RF (𝑥) with 𝑇 decision trees.
Step 3: Train a LightGBM model f_LGBM (𝑥) for class prediction.
Step 4: For an input data point 𝑥, obtain the predicted class label from each mode:
y_SVM = f_SVM (𝑥)
y_RF =f_RF (𝑥)
y_LGBM = f_LGBM (𝑥)
Step 5: Combine predictions from SVM, Random Forest, and LightGBM using a voting mechanism.
Step 6: Calculate the voting weights for each model: w_SVM = 1, w_RF = 1, w_LGBM = 1.
Step 7: Compute the weighted average of class probabilities:
P_x=(w_SVM.P_SVM^k+w_RF.P_RF^k+w_LGBM.P_LGBM^k)/(w_SVM+w_RF+w_LGBM )
Step 8: Identify the class category with the maximum likelihood as the ultimate forecast: y ̂= 〖argmax〗_x (P_x).
Step 9: The final predicted class label for the input data sample 𝑥 is y ̂ depending on the voting mechanism.

Advantage of the present invention:
The advantage of the present invention is to develop an intelligent precision agriculture monitoring system that leverages modern technology to improve crop cultivation practices and soil health management.
Further advantage of the present invention is to establish a robust data collection and transmission infrastructure
Another advantage of the present invention is to integrate machine learning algorithms into the server infrastructure to analyze collected data and provide personalized recommendations to farmers.
Yet another advantage of the present invention is to utilize the MQTT protocol for communication between dew-enabled sensor nodes and a central server, the invention aims and this infrastructure will enable real-time monitoring of soil conditions, nutrient levels, and environmental parameters across extensive agricultural areas.
Yet another advantage of the present invention is to integrate irrigation scheduling, and nutrient supplementation by offering actionable insights for crop selection wherein the invention aims to enhance agricultural productivity, sustainability, and profitability while minimizing resource waste and environmental impact.
Yet the further advantage of the system is that the MQTT model ensures efficient and reliable data transmission between the DEW nodes and the drone. This communication operates without requiring an internet connection, enabling the system to function seamlessly in remote areas with limited connectivity. The system achieves this internet-free operation through an ad hoc network, which facilitates direct device-to-device communication. This setup ensures efficient data exchange between DEW nodes and the UAV, optimizing real-time monitoring and decision-making in agricultural environments.
It will be understood that the invention may be carried out into practice by skilled persons with many modifications, variations and adaptations without departing from its spirit or exceeding the scope of the claims in describing the invention for illustration.
Any inclusion to or deletion from the embodiment occurred, the specification is herein deemed as modified thus fulfilling the written description of all elements used in the claims so appended.
, Claims:We claim,
1. A Dew Enabled Intelligent Precision system (100-300) for Crop Monitoring characterizing
-Sensor Layer wherein the sensor layer in UAV system framework configured with network of sensor-equipped dew nodes strategically deployed at 45-50 meter intervals across agricultural fields to ensure continuous monitoring of soil health and the system is characterized with Unmanned Aerial Vehicle (UAV) integrated with an ESP32 module and Raspberry Pi and collects sensor data from the dew nodes using a peer-to-peer (P2P) network with a transmission range of up to 400-450 meters and wherein the collected data is pre-processed and transmitted to a central IoT server hosting Node-RED, where machine learning algorithms analyze soil conditions and generate predictive models and personalized recommendations for crop selection and soil management wherein the system is integrated with the image sensor layer where each dew node is configured with a camera to capture real-time images of the crops and these images, along with sensor data, serve as inputs for crop health monitoring, helping to detect early signs of diseases, pest infestations, or other issues affecting crop growth wherein the image sensor provides critical visual data, which is transmitted to the drone for further processing and analysis
-Data Aggregation Layer wherein the data aggregation layer is responsible for gathering environmental and soil data from the dew nodes deployed at 45-50 meter intervals across the farmland to ensure comprehensive coverage wherein each dew node is equipped with sensors to monitor critical soil parameters, including soil humidity, temperature, pH, and nutrient levels (NPK) and the collected data is continuously recorded in the dew node’s microcontroller (Node MCU) and stored in a linked list for efficient processing wherein the drone is configured with a Raspberry Pi and approaches a dew node, it scans for signals from dew nodes within its range and upon detecting a dew node, it receives the sensor data using MQTT-based communication protocol and the UAV system framework is designed to function without internet connectivity by utilizing an ad-hoc network for communication between the UAV and dew nodes and a mesh network for communication between the dew nodes themselves
-Cloud Layer wherein the cloud layer is used for storing, processing, and analyzing the collected data and the drone collects the data from the dew nodes and it uploads the information to IoT application platform hosted on a cloud server wherein this cloud-based system and is capable of performing real-time analysis and providing insights into soil and crop health
- The Agri IoDT framework to enhance precision agriculture by integrating dew nodes, drones, and advanced data analytics,
2. The dew Enabled Intelligent Precision system for Crop Monitoring as claimed in claim 1 wherein each dew node is configured with multiple sensors, including a soil temperature sensor to monitor temperature variations affecting seed germination and root development wherein a soil moisture sensor is used to measure water content and soil pH sensor to determine soil acidity or alkalinity for crop suitability, and an NPK sensor to analyze the concentrations of Nitrogen (N), Phosphorus (P), and Potassium (K) for plant growth and these dew nodes are powered by ESP32 microcontrollers, enabling real-time data processing and wireless transmission.
3. The dew Enabled Intelligent Precision system for crop monitoring as claimed in claim 1 wherein the MQTT ensures efficient and reliable data transmission between the dew nodes and the drone and this communication without internet connection facilitates the system to function even in remote areas with limited connectivity facilitates efficient communication between dew nodes and the UAV and wherein the UAV enters a dew node’s signal range, it receives sensor data via MQTT, where the dew nodes act as publishers sending the data, and the UAV acts as a subscriber collecting the information.
4. The dew Enabled Intelligent Precision system for crop monitoring as claimed in claim 1 wherein on board Raspberry Pi functions as a central data aggregation point for receiving and pre-processing data collected by the drone from the sensor-equipped dew nodes.
5. The dew Enabled Intelligent Precision system for crop monitoring as claimed in claim 1 wherein the AgriIoDT framework is configured to function without internet connectivity by utilizing an ad-hoc network for communication between the UAV and dew nodes, and a mesh network for communication between the dew nodes wherein the UAV is equipped with a Raspberry Pi, directly connects to dew nodes within its range and is used for seamless data transmission using the MQTT protocol and without the need for external network infrastructure and the dew nodes are linked in a mesh network to enable the data to be relayed through neighboring nodes placed in out of range and this setup ensures continuous data collection in remote areas, and once the UAV returns to an area with internet access, it uploads the collected data to the cloud for further analysis wherein this enables the system to operate efficiently in off-grid environmentally and is providing real-time data collection and communication without internet connectivity.
6. The dew Enabled Intelligent Precision system for crop monitoring as claimed in claim 1 wherein an integrated ESP32 microcontroller, power supply unit, and wireless communication module with visual indicators including directional arrows, delineate the flow of data between sensors and the microcontroller and wireless communication pathways using the dew node.

7. The method of Dew Enabled Intelligent Precision system comprises
- deploying sensor layer to collect sensor data from the dew nodes using a peer-to-peer (P2P) network with a transmission range of up to 400-450 meters
- Pre-processing and transmission to a central IoT server hosting Node-RED, where machine learning algorithms analyze soil conditions and generate predictive models and personalized recommendations for crop selection and soil management wherein the system is integrated with the image sensor layer where each dew node is configured with a camera to capture real-time images of the crops and these images, along with sensor data, serve as inputs for crop health monitoring, helping to detect early signs of diseases, pest infestations, or other issues affecting crop growth wherein the image sensor provides critical visual data, which is transmitted to the drone for further processing and analysis
-aggregating the data layer wherein the data aggregation is responsible for gathering environmental and soil data from the dew nodes deployed at 45-50 meter intervals across the farmland to ensure comprehensive coverage wherein each dew node is equipped with sensors to monitor critical soil parameters, including soil humidity, temperature, pH, and nutrient levels (NPK)
- recording the collected data in the dew node’s microcontroller (Node MCU) and stored in a linked list for efficient processing wherein the drone is configured with a Raspberry Pi and approaches a dew node, it scans for signals from dew nodes within its range and upon detecting a dew node, it receives the sensor data using MQTT-based communication protocol and the UAV system framework is designed to function without internet connectivity by utilizing an ad-hoc network for communication between the UAV and dew nodes and a mesh network for communication between the dew nodes themselves
- storing, processing and analyzing the collected data in the cloud layer and the drone collects the data from the dew nodes and it uploads the information to IoT application platform hosted on a cloud server wherein this cloud-based system is capable of performing real-time analysis and providing insights into soil and crop health
- Enhancing the precision system by the Agri IoDT framework by integrating dew nodes, drones, and advanced data analytics
-interpreting the data to provide actionable insights and recommendations for farmers, including crop selection, irrigation scheduling, and nutrient management strategies using the algorithms integrated into the server infrastructure interpret.

8. The method of Dew Enabled Intelligent Precision system as claimed in claim 7 wherein the UAV, equipped with a Raspberry Pi, directly connects to dew nodes within its range, allowing for seamless data transmission using the MQTT protocol without external network and the dew nodes are linked in a mesh network, enabling data to be relayed through neighboring nodes wherein one is out of range and this setup ensures continuous data collection in remote areas, and wherein the UAV returns to an area with internet access, it uploads the collected data to the cloud for further analysis.