Description:FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
&
The Patent Rules, 2003
COMPLETE SPECIFICATION
(See sections 10 & rule 13)
1. TITLE OF THE INVENTION
DIGITAL TWIN EMPOWERED DRONES TO ASSIST THE FARMERS TO OPTIMIZE THE AGRICULTURAL FIELD YARD
2. APPLICANT (S)
NAME NATIONALITY ADDRESS
DIVYASAMPARK IHUB ROORKEE FOR DEVICES MATERIALS AND TECHNOLOGY FOUNDATION IN Indian Institute of Technology Roorkee, Roorkee-247667, Uttarakhand, India.
3. PREAMBLE TO THE DESCRIPTION
COMPLETE SPECIFICATION

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

FIELD OF INVENTION:
[001] The present invention relates to the field of unmanned aerial vehicles. The present invention in particular relates to the digital twin empowered drones to assist the farmers to optimize the agricultural field yard.
DESCRIPTION OF THE RELATED ART:
[002] Modern farming continues to make significant strides in the industry's ability to produce larger and more robust foods in response to demand and increasing populations. For example, advances in chemical engineering, fertilization, irrigation, soil analysis and equipment (hardware and software) have revolutionized crop production and associated systems. In this evolution of farming techniques, modern farming has increasingly turned to technological advances in the full stream of farming such as planting, tending and harvesting of crops which requires a wide range of tools, equipment, machinery, chemicals and other materials.
[003] Reference may be made to the following:
[004] Patent No. US9745060 relates to a method and system utilizing one or more agricultural drones in combination with agricultural equipment, e.g., an agricultural boom sprayer, to evaluate the crops being farmed, and to improve the real-time delivery and dispensing of liquid from the sprayer including monitoring and verifying that the liquid is being dispensed correctly and/or in accordance with a desired distribution pattern or level.
[005] Patent No. US12092625 relates to a sensing tool. By profiling each of a number of first locations that have a ground truth classification, using a deployed sensing tool, digital soil properties of new locations without ground truth classifications can be obtained to determine corresponding classifications for the new locations. This allows information related to classifications to be utilized for optimal use of the new locations.
[006] Publication No. US2022172467 relates to a web server based distributed cellular system to provide 21st century total digital precision agriculture to small and uneducated poor farmers is proposed. A service model is used to avoid farmers owning any equipment and a system's provided service agent becomes on ground mentor of the farmer.
[007] Publication No. RO138437 relates to an online monitoring system for agricultural and horticultural crops. According to the invention, the system comprises a module for data collection (I.) from fixed stations provided with soil and air sensors (I.1.), motion sensors and video cameras (I.2.) placed on an irrigation pivot, pest-traps (I.3.) and satellite application Field View (I.4.), a data transmission module (II.) having a data centralization platform with subscription service (II.1.) and with data encryption service (II.2.), a data processing module (III.) comprising the following elements: analysis of data sampled in real time (III.1.), evolutive data analysis (III.2.), drone flight alert (III.3.), orthophoto planes (III.4.) and personalized recommendations (III.5.), a module for personalized recommendations to the farmer (IV.) and a module (V.) for alerts, reports, live images.
[008] Publication No. WO2024236091 relates to a drone monitoring method for observing and monitoring agricultural testing fields, comprising the steps of: (a) dividing the testing fields in a set of plots, each of the plots defined in a geographic information system, the plots being defined by coordinate information of 5 boundaries of 2D polygons, (b) defining at least one 2D sampling point in each plot for acquiring drone data, thereby obtaining a set of 2D sampling points, (c) overlaying the set of 2D sampling points with a digital elevation model, thereby obtaining an altitude reference height for each of the 2D sampling points, (d) for each 2D sampling point: determining an altitude coordinate corresponding to said 2D sampling point on the basis of the altitude reference height for said 2D sampling point, 10 and (e) for each 2D sampling point: determining a 3D sampling point by combining said 2D sampling point with the altitude coordinate corresponding to said 2D sampling point, wherein the altitude coordinate is determined by taking into account a canopy height at the 2D sampling point.
[009] Patent No. US12108697 relates to an agricultural management system includes an array of IoT sensors located across an area, and a set of wireless portal devices located across the area. The wireless portal devices are in communication with the IoT sensors. A drone, which includes an imaging device, is in communication with the wireless portal devices.
[010] Publication No. AU2021100538 relates to crop health monitoring system using loT and machine learning due to the inherent agrarian aspect of the economy, the agricultural sector holds paramount importance in many countries. Some countries have their GDP dependent on agriculture, but they rely on manual crop monitoring, which is a system that is labor intensive and ineffective. In comparison to this, in developing countries, many cutting-edge technology based technologies are being used to increase crop yield with optimum resource utilization. To this end, this invention suggested an integrated approach using IoT, machine learning and drone technology for monitoring crop health. The incorporation of these sensing modalities produces heterogeneous data which is not only differing in absorbed parameter also in the temporal fidelity. The spatial resolution of these approaches is also different, so the proposed scheme suggests the optimum integration of these sensing modalities and their implementation in practice.
[011] Publication No. AU2021107439 relates to due to the inherent agrarian aspect of the economy, the agricultural sector holds paramount importance in many countries. Some countries have their GDP dependent on agriculture, but they rely on manual crop monitoring, which is a system that is labor intensive and ineffective. In comparison to this, in developing countries, many cutting-edge technology based technologies are being used to increase crop yield with optimum resource utilization.
[012] Publication No. EP4483706 relates to a system for growing plants for modelling a farming environment, the system comprising: an enclosed device for growing the plants for modelling the farming environment; sensors placed in the farming environment for acquiring plant growth parameters data from the farming environment; computer configured for simulating the farming environment with the acquired plant growth parameters data to obtain simulated plant growth parameters; the computer further configured for mapping the simulated plant growth parameters to plant growth parameters of the enclosed device; the computer further configured for applying the mapped parameters to the enclosed device.
[013] Publication No. KR20200112342 relates to a digital twin-based smart remote farm system and a method thereof, which are based on smart twin technology to experience crop cultivation and harvest. According to one embodiment of the present invention, the digital twin-based smart farm management method generates virtual farmland linked to farmland based on a photographed image for the farmland, generates a virtual object for a crop selected by a client terminal to display the virtual object on the virtual farmland, transmits a farming activity request signal to a farmer terminal based on an input signal for a virtual farming activity performed on the virtual farmland, periodically collects a photographed image for a crop in accordance with the farming activity to change the shape of the virtual object in real-time according to the growth state of the crop, and generates guide information including information on a farming activity required for the virtual object based on a simulation result for the virtual farmland.
[014] Publication No. KR20200064364 relates to a drone kit for small cargo trucks, and for controlling pesticides of a farming drone, which is capable of allowing one skilled professional drone worker to simultaneously operate two drones.
[015] Publication No. KR20230090772 relates to a drone system for collecting crop growth information, for predicting a crop production, comprising: a drone which takes off at a set time and while travelling along a set altitude and course, takes an image of crops and measures temperature, humidity, and illumination around the crops; a drone station which provides a landing space for the drone to take off and land, has a door at an upper part of the landing space for opening and closing upon takeoff, landing, or movement of the drone, and charges the drone when the drone lands on the landing space; and a control server which sets the takeoff and landing time, altitude and course of the drone, analyzes the image of the crops transmitted from the drone to determine the growth status of the crops and the presence of a pest, if the pest is present, provides the presence of the pest and the location of the pest to an operator who manages the crop to conduct a control operation for eliminating the pest, and stores data transmitted from the drone and drone station.
[016] Publication No. WO2025063403 relates to an agriculture cultivation system using a digital twin, the system comprising: a real space part for the growth of a real specific plant; and a virtual space part which is the realization of a virtual identical model of the real space.
[017] Publication No. KR20220090817 relates to the system for analyzing and managing forage crop growth information using drone images of the present invention is characterized by including a boundary management step of generating parcel information and providing parcel information; an image analysis step of analyzing parcel images; and a pasture management step of generating parcel list information and parcel production information.
[018] Publication No. AU2020101843 relates to a system for monitoring and controlling farming using drone technology comprising a drone system for monitoring the farm and transmitting information and a ground control system for controlling the drone system and receiving the information. A camera is provided in the drone system for capturing images and video, a GPS module is provided in the drone system for locating image and video captured by the camera, a sensor module is provided in the drone system for measuring parameters of temperature, humidity, gas and pH.
[019] Publication No. IN202141061691 relates to drones are extremely significant in smart agriculture. Drone sensors can provide information about agricultural areas from an aerial view. Our idea is an automated drone-based smart agricultural system. An agricultural drone is an unmanned aerial vehicle (UAV) used primarily for smart and efficient farming. It is also used to monitor and boost crop production.
[020] Publication No. IN202331003879 relates to agricultural drones or unmanned aerial vehicles (UAVs) help optimize farm operations and crop production and monitor crop growth. In addition, drones are used in precision agriculture for a variety of tasks such as soil and field analysis, crop and pesticide application, and more. By using different imaging technologies such as multispectral, hyper spectral, and thermal imaging, farmers can better understand their farms and fields. Agricultural drone data and the resulting applications of its analysis help improve crop yields and farm efficiency.
[021] Publication No. IN202241000275 relates to agriculture is the main source of food supply. In farming the farmers uses powerful fuel based IC engines for heavy machineries. These machineries require skilled technician to operate and it causes environmental pollution. To overcome all the disadvantages in traditional approach, drones were introduced in smart farming.
[022] Publication No. IN202241004015 relates to unmanned aerial vehicles (UAV), which is exactly what they are (UAVs). Networked robotic technologies are devices that can be remotely configured and controlled via a ground station or a remote control. Regrettably, drones had little impact on how farmers performed their duties until recently.
[023] Publication No. IN201921015727 relates to an intelligent agriculture system comprising of pH, moisture, temperature, humidity, water flow, and ultrasonic sensors.
[024] Publication No. KR20240039730 relates to a drone for collecting data necessary for creating a digital twin, and to this end, the drone comprises a lidar sensor for collecting three-dimensional point cloud data of an object through a stationary flight at an arbitrary point, a camera module for collecting an image of the object in the stationary flight state, a data generation unit for generating matching data by matching position information of the drone at the arbitrary point, the three-dimensional point cloud data, and the image, and storing the matching data in a memory, and a flight controller for monitoring the position information of the drone in real time and then controlling the flight of the drone so that it can perform a stationary flight at the arbitrary point, and a method for providing a drone for collecting data for creating a digital twin of the object can be provided by using the matching data generated by the data generation unit at at least two points.
[025] Patent No. US11263707 relates to a crop prediction system performs various machine learning operations to predict crop production and to identify a set of farming operations that, if performed, optimize crop production. The crop prediction system uses crop prediction models trained using various machine learning operations based on geographic and agronomic information. Responsive to receiving a request from a grower, the crop prediction system can access information representation of a portion of land corresponding to the request, such as the location of the land and corresponding weather conditions and soil composition.
[026] Publication No. US2017161560 relates to a system and method for predicting harvest yield. The method includes receiving monitoring data related to at least one crop, wherein the monitoring data includes at least one multimedia content element showing the at least one crop; analyzing, via machine vision, the at least one multimedia content element; extracting, based on the analysis, a plurality of features related to development of the at least one crop; and generating a harvest yield prediction for the at least one crop based on the extracted features and a prediction model, wherein the prediction model is based on a training set including at least one training input and at least one training output, wherein each training output corresponds to a training input.
[027] Publication No. US2005234691 relates to crop yield may be assessed and predicted using a piecewise linear regression method with break point and various weather and agricultural parameters, such as NDVI, surface parameters (soil moisture and surface temperature) and rainfall data. These parameters may help aid in estimating and predicting crop conditions. The overall crop production environment can include inherent sources of heterogeneity and their nonlinear behavior.
[028] Publication No. KR20230146731 relates to a digital twin-based metaverse platform, which includes the steps of: surveying such as aerial photography, 3D drone mapping, and Lidar mapping; implementing real places, buildings, etc., through twin motion using Unreal Engine 4 based on the precise survey data; implementing virtual reality (VR)/augmented reality (AR)/extended reality (XR) using the realized twin-type real places, buildings, etc.; and constructing a metaverse platform using the implemented virtual reality (VR)/augmented reality (AR)/extended reality (XR).
[029] Publication No. WO2023028302 relates to a drone system for collecting structural condition data about a structure having an array of sensors disposed at various locations on the structure and methods of using such a drone system are disclosed herein.
[030] Publication No. US2024180062 relates to an agricultural assistance system includes a sensor in or on an unmanned aerial vehicle to perform sensing of a shape of an agricultural field when the unmanned aerial vehicle flies over the agricultural field, and a line creator configured or programmed to create a planned travel line for automatic operation of an agricultural machine. The line creator is configured or programmed to acquire the shape of the agricultural field obtained by the sensing before the automatic operation of the agricultural machine, and create the planned travel line on a virtual field representing the acquired shape of the agricultural field.
[031] Publication No. US2024161209 relates to a method for controlling application of agrichemical products, comprises acquiring remotely sensed digital image data; developing a prescription to apply at least one agrichemical product in a variable manner based on at least the digital image data, wherein the prescription describes a plurality of passes of a particular autonomous vehicle over a field to apply the at least one agrichemical product; applying the at least one agrichemical product to a crop in the variable manner by the particular autonomous vehicle according to the prescription.
[032] Publication No. US2024116630 relates to methods for predicting a yield of fruit growing in an agricultural plot are provided.
[033] Patent No. US11944047 relates to a system and method for obtaining real-time data regarding the condition of a crop and planning and executing an irrigation cycle in response to the data. The invention uses an unmanned aerial vehicle to survey the conditions within an irrigated area.
[034] Patent No. US11952118 relates to an apparatus for biological control of agricultural pests and for reducing damage to crops. The apparatus includes a container for holding biological organisms or material.
[035] Publication No. IN202511002213 relates to a smart irrigation system designed to optimize water usage in agriculture using Internet of Things (IoT) sensors and machine learning. The system incorporates soil moisture sensors to monitor soil hydration, temperature sensors to track ambient temperature, and an Arduino board as the central controller. It utilizes a water pump, activated by signals from the Arduino board, to deliver water to crops when necessary.
[036] Publication No. IN202541016603 relates to an artificial intelligence-driven system generates real-time irrigation, fertilization, and pest control recommendations. The system includes processors and memory (204) storing instructions that, when executed, enable the system to receive real-time agricultural data from multi-spectral and hyper-spectral imaging units, sensors, and pest and disease-induced visual markers.
[037] Publication No. IN202421004089 relates to an integrated system for immersive water resource management, intertwining Digital Twin Networks, Non-Fungible Token (NFT) Systems, and a collaborative Village Metaverse. The Digital Twin Network dynamically creates virtual representations of physical water wells, incorporating real-time data from sensors, IoT devices, and historical records. Simultaneously, the Village Metaverse establishes a three-dimensional environment, providing stakeholders with a collaborative platform to interact, simulate scenarios, and make decisions. It uses an autonomous and hybrid smart well manager (SWM), smart well platform (SWP), and smart water and energy pump Platform (SWEPP) to automate the collection of data related to energy consumption, water volume, quality, and purpose of use, analysis, alerting and actuation.
[038] The article entitled “Enhancing smart agriculture by implementing digital twins: a comprehensive review” by Nikolaos Peladarinos; Dimitrios Piromalis; Vasileios Cheimaras; Efthymios Tserepas; Radu Adrian Munteanu and Panagiotis Papageorgas; Sensors 23 (16), 7128; 11 August 2023 talks about a comprehensive overview of the contemporary state of research on digital twins in smart farming, including crop modelling, precision agriculture, and associated technologies, while exploring their potential applications and their impact on agricultural practices, addressing the challenges and limitations such as data privacy concerns, the need for high-quality data for accurate simulations and predictions, and the complexity of integrating multiple data sources. Lastly, the paper explores the prospects of digital twins in agriculture, highlighting potential avenues for future research and advancement in this domain.
[039] The article entitled “Digital twin-based crop yield prediction in agriculture” by Rajeswari Devarajan; Athish Venkatachalam; Sivaram Ponnusamy; Research Gate; February 2024 talks about enhancing predictive capabilities, optimize resource utilization, monitor crop health, and provide data-driven decision support. Results indicate a remarkable prediction accuracy of 91.69%, showcasing the system's potential to revolutionize agriculture, empower farming communities, and contribute to global food security. The chapter concludes by outlining potential future enhancements and advancements, positioning the digital twin-based crop yield prediction system as a significant stride towards efficient and sustainable agricultural practices.
[040] The article entitled “Strategic integration of drone technology and digital twins for optimal construction project management” by Tareq Salem; Mihai Dragomir and Eric Chatelet; Appl. Sci. 14(11), 4787; 31 May 2024 talks about the integrated approach to construction project management by integrating digital technology into monitoring and surveillance operations. Through the use of drones and image processing software, data can be updated regularly and accurately about the progress at the construction site, allowing managers and decision makers to have a clear view of the current situation and make effective decisions based on accurate. In addition, this approach contributes to improving communication and coordination among project team members, as data and images can be easily and effectively shared, reducing opportunities for error and enhancing effective interaction among different parties. Using digital twin technologies, planning and forecasting processes can also be improved, as comprehensive analysis of digital data provides a deeper understanding of project dynamics, identifies potential risks, and enables appropriate preventive measures to be taken. In conclusion, the integration of digital twins and the use of drones in construction projects represent a significant step towards achieving smarter and more efficient management, and successfully achieving the defined goals with greater effectiveness.
[041] The article entitled “Digital twin of drone-based protection of agricultural areas” by Gergely Teschner; Csaba Hajdu; János Hollósi; Norbert Boros; Attila Kovács; Áron Ballagi; IEEE; 26 December 2022 talks about a complex vision-based intrusion detection system to overcome these problems and further proposes more extensive control and flexibility on the development process. The solution provides a workflow integrating Digital Reality methods into the system development by creating a digital twin of the drone and its surrounding environment in a general-purpose robotic simulator. With this simulation, the triggering events and environmental effects can be easily emulated, such as a wild animal entering the area of interest. The solution also focuses on incorporating new 5G info-communication networks on handling communication between the intrusion detection system and the base station in a distributed manner.
[042] The article entitled “Digital twins in agriculture: orchestration and applications” by Marc Escribà-Gelonch; Shu Liang; Pieter van Schalkwyk; Ian Fisk Nguyen Van Duc Long; Volker Hessel; J. Agric. Food Chem. 72, 10737−10752; May 6, 2024 talks about the digital twins have emerged as an outstanding opportunity for precision farming, digitally replicating in real-time the functionalities of objects and plants. A virtual replica of the crop, including key agronomic development aspects such as irrigation, optimal fertilization strategies, and pest management, can support decision-making and a step change in farm management, increasing overall sustainability and direct water, fertilizer, and pesticide savings. In this review, Digital Twin technology is critically reviewed and framed in the context of recent advances in precision agriculture and Agriculture 4.0. The review is organized for each step of agricultural lifecycle, edaphic, phytotechnologic, postharvest, and farm infrastructure, with supporting case studies demonstrating direct benefits for agriculture production and supply chain considering both benefits and limitations of such an approach. Challenges and limitations are disclosed regarding the complexity of managing such an amount of data and a multitude of (often) simultaneous operations and supports.
[043] The article entitled “Digital twins in smart farming” by Cor Verdouw; Bedir Tekinerdogan; Adrie Beulens; Sjaak Wolfert; Agricultural Systems Volume 189, 103046; April 2021 talks about how digital twins can advance smart farming. It defines the concept, develops a typology of different types of Digital Twins, and proposes a conceptual framework for designing and implementing Digital Twins. The framework comprises a control model based on a general systems approach and an implementation model for Digital Twin systems based on the Internet of Things—Architecture (IoT-A), a reference architecture for IoT systems. The framework is applied to and validated in five smart farming use cases of the European IoF2020 project, focusing on arable farming, dairy farming, greenhouse horticulture, organic vegetable farming and livestock farming.
[044] The article entitled “Digital twins in agriculture: a time machine for your farm” by Alina Piddubna, agritechtomorrow; 06/04/24 talks about the digital twins to agriculture is rapidly moving from concept to reality, with digital twin technology making its way to fields and barns. In doing so, it is transforming the day-to-day operations of agribusinesses, affecting how they manage their processes, systems, and facilities. On a global scale, this new technology is becoming the driving force for a sustainable future, removing uncertainties in crop cultivation, livestock farming, and climate change impacts. In agriculture, digital twin technology allows farmers to create a digital model of an entire agricultural ecosystem, including fields, facilities, crops, animals, and machinery. Digital counterparts of farm assets can be used to track the health of soil, crops, or livestock, analyze farm operations, act on real-time insights, and predict future outcomes.
[045] The article entitled “Introducing digital twins to agriculture” by Christos Pylianidis, Sjoukje Osinga, Ioannis N. Athanasiadis; Computers and Electronics in Agriculture, Volume 184, 105942; 15 July 2020 talks about a mixed-method approach to investigate the added-value of digital twins for agriculture. We examine the extent of digital twin adoption in agriculture, shed light on the concept and the benefits it brings, and provide an application-based roadmap for a more extended adoption. We report a literature review of digital twins in agriculture, covering years 2017-2020. We identify 28 use cases, and compare them with use cases in other disciplines. We compare reported benefits, service categories, and technology readiness levels to assess the level of digital twin adoption in agriculture. We distill the digital twin characteristics that can provide added-value to agriculture from the examined digital twin applications in agriculture and in other disciplines. Then, inspired by digital twin applications in other disciplines, we propose a roadmap for digital twins in agriculture, consisting of examples of growing complexity. We conclude this paper by identifying the distinctive characteristics of agricultural digital twins.
[046] The article entitled “Digital twin in agriculture” by Haribabu S; linkedin; Apr 2, 2025 talks about the digital twin in agriculture is a virtual replica of a physical farm, crop field, or agricultural supply chain that allows farmers to monitor, analyze, and optimize agricultural operations in real-time. This technology integrates IoT sensors, AI, machine learning, drones, and big data analytics to enhance crop productivity, resource efficiency, and sustainability.
[047] In order to overcome the above listed prior art, the present invention aims to provide a Digital Twin empowered drone to assist the farmers to optimize the agricultural field yield.
[048] The prior art predominantly uses drones to capture static data without the use of real-time technologies to enhance crop yield in the field. The proposed system uses Digital twin to capture and visualize the data to convert into a real-time virtual model. The existing models utilize older versions of object detection such as YOLOv3 to YOLOv7 whereas our system is trained on the latest version of YOLOv11 model. Most of the data used in prior art models are either pre-pared datasets or low resolution satellite images Our model utilizes real-time drone captured high resolution agricultural field images which are fed into the system for enhanced model output. The prior art systems use either IoT integrated sensor data or images whereas our system is integrated with IOT sensors placed in the agricultural field and drone images to provide exact locations in the field.
OBJECTS OF THE INVENTION:
[049] The principal object of the present invention is to provide a digital twin empowered drones to assist the farmers to optimize the agricultural field yard.
[050] Another object of the present invention is to enhance the precision farming approach, enabling more sustainable agricultural practices and contributing to the growth of the agricultural sector.
[051] Yet another object of the present invention is to reduce discrepancies between real-time agricultural field data and predicted outcomes from digital twin models.
[052] Still another object of the present invention is to provide a system to agriculture, empower farmers to make informed decisions and maximize productivity.
SUMMARY OF THE INVENTION:
[053] The present invention relates to a system and method for optimizing crop monitoring and yield prediction through a digital twin-empowered system, coupled with real-time data acquisition and predictive analytics. The system comprises IoT sensors to capture environmental parameters such as soil moisture, temperature, and humidity, while drones equipped with high-resolution cameras provide aerial images of the agricultural field. These images are processed by a control unit to classify and analyze crop health and growth patterns. Real-time data is synchronized with the digital twin model and processed in the cloud, enabling farmers to monitor field conditions virtually and make data-driven decisions. Additionally, reinforcement learning is utilized to dynamically optimize operations such as drone routing and resource management. The system offers predictive capabilities for crop yields, automates processes like irrigation and pest control, and provides actionable insights to enhance sustainability and productivity. By bridging the gap between physical and digital environments, this approach facilitates precision farming, ensuring optimal resource utilization and improved agricultural outcomes. This invention highlights the technological advancements, implementation methods, and potential impact of this integrated solution on modern agriculture.
[054] The system reduces discrepancies between real-time agricultural field data and predicted outcomes from digital twin models. This integrates machine learning methods for real-time crop behavior prediction and field condition analysis. This enhances farming decision-making by minimizing errors in crop management and resource allocation.
BRIEF DESCRIPTION OF THE INVENTION
[055] It is to be noted, however, that the appended drawings illustrate only typical embodiments of this invention and are therefore not to be considered for limiting its scope, for the invention may admit to other equally effective embodiments.
[056] Fig.1 shows an agricultural device for enhance crop monitoring and yield prediction.
[057] Fig.2 shows flow chart according to the present invention.
DETAILED DESCRIPTION OF THE INVENTION:
[058] The present invention provides an agricultural device that combines digital twin technology, IoT-based sensor networks, drone imaging, and AI based method to enhance crop monitoring and yield prediction. The system creates a virtual representation of an agricultural field by synchronizing real-time data from sensors deployed in the field, allowing for accurate predictions of crop growth, field conditions, and yield outcomes. Drones equipped with high-resolution cameras continuously capture images of the field, which are processed using the image detection method for classification and analysis. The data collected from sensors and drones is stored and processed in the cloud, enabling real-time monitoring and decision-making. By automating processes such as irrigation and pest control, the system provides farmers with valuable insights to optimize crop management, improve yields, and ensure sustainable agricultural practices. This invention provides, data-driven approach to agriculture that empowers farmers with the tools to make informed decisions and maximize productivity.
[059] Fig.1 shows an agricultural device for enhance crop monitoring and yield prediction. The invention provides digital twin systems, consisting of IoT-based sensor networks, drone imaging, and artificial intelligence (AI) driven analytics to significantly improve the monitoring and management of agricultural fields. The IoT sensors placed in the agricultural field capture environmental parameters such as soil moisture, temperature, and humidity, while the drones equipped with high-resolution cameras provide aerial images of the agricultural field. These images are sent to the digital twin and the AI model using the IoT gateway where stress is detected using the image classification model and highlighted in the digital twin.
[060] The proposed model captures the live sensor-based parameters along with the image data collected through the drone. The drone operations are controlled through the drone routing algorithm. The drones deployed on the field continuously capture the images and send the data to the cloud-based repository (ex, Amazon cloud). The IoT based protocols along with the LoRaWAN Gateway provides an interface to exchange the sensor data from the agricultural field to Cloud based storage systems. The virtual twins along with the real time data analyzed on the twin dashboard to understand the status of the agricultural field and the crop behaviour. The data collected from the agricultural yard is given as an input for the YOLO v11 algorithm for further processing and decision-making activities (fig 2).
[061] The core of the invention is the use of digital twin technology, which creates a virtual replica of an agricultural field by synchronizing real-time data from IoT sensors deployed in the field. This invention predicts field conditions, crop health, and yield outcomes. Drones equipped with high-resolution cameras capture aerial images of the field, which are then analyzed using AI based methods, to identify specific crop behaviors, pests, and growth patterns. The system also employs cloud computing to store and process vast amounts of data, ensuring efficient access and real-time analysis. By automating tasks like irrigation or pest control and providing predictive insights, the system supports farmers in making informed decisions, improving productivity, and optimizing resource usage. This invention facilitates sustainable farming practices by merging physical and digital worlds to offer a comprehensive, data-driven approach to agricultural management.
[062] The invention is an agricultural monitoring and yield prediction system that integrates several cutting-edge technologies to optimize farming practices and improve crop management. At its core, this system combines digital twin technology, IoT-based sensor networks, drone imaging, cloud computing, and artificial intelligent (AI) driven analytics to create a comprehensive, real-time monitoring solution for agricultural fields.
[063] The digital twin is a virtual representation of the physical agricultural field, synchronized with real-time data collected through IoT sensors deployed across the field. These sensors measure various environmental parameters, such as soil moisture, temperature, humidity, and light levels, providing crucial insights into the health of the soil and crops. The virtual model of the field is continuously updated with this real-time data, allowing for accurate predictions about crop growth, pest infestations based on the surrounding plant images. The pest infested areas can be detected and highlighted in the digital twin by mapping the field geographical points in the digital twin. An example of such is mapping a 200*200 meter field as 10*10 units on the virtual entity. This allows us to pinpoint every location and also analyze the overall field condition.
[064] To gather additional visual data, drones equipped with high-resolution cameras are deployed to capture aerial images of the field. These images are processed using an artificial intelligence (AI) based image detection method, which classifies the images to identify key features like crop health, potential pests, and growth patterns. These classifications depend upon parameters such as dryness of the field in a particular area, abnormal plant growth, and the difference in the plant color in various parts of the field. This integration of visual data with sensor data further enhances the system’s ability to predict crop behavior and optimize field management by automating sprinklers in the field based on conditions such as low soil moisture, low ammonia content in the soil, low nitrogen for the plants, etc. These automations replenish the field and support plant growth. This level of automation is triggered by data-driven insights, allowing farmers to automate routine tasks based on real-time conditions, reducing manual labor and ensuring more efficient operations.
[065] The data collected from both the IoT sensors and drone imaging is transmitted to a cloud-based storage system for processing and analysis. Cloud computing enables efficient data storage, access, and real-time analytics, ensuring that the information is readily available for farmers to make timely decisions. The system uses machine learning models to analyze the data and provide actionable insights, such as recommending irrigation schedules, identifying pest outbreaks, or predicting crop yields. This predictive capability allows farmers to plan more effectively, reduce waste, and optimize resource usage.
[066] The invention utilizes reinforcement learning to dynamically optimize drone flight paths and sensor-based parameter collection providing high-quality, actionable insights for farmers which allows them to manage the field and crop growth optimally. Additionally, enhancing yield predictions and providing crop health monitoring helps the farmers to prepare for unforeseen circumstances that might hinder the plant growth. It offers a scalable and adaptable solution that can be implemented across various agricultural fields and crop types across various regions and their regional crops and facilitates continuous learning and improvement of predictive models using real-time sensor and image data.
[067] It complies with agricultural industry standards and regulations for environmental monitoring and farming technologies and promotes the broader adoption of AI, IoT, and digital twin technologies in modern agricultural practices.
[068] Thus this is a hybrid system that combines physical agricultural environments with digital simulations, creating a drone-twin device. The system’s integration of IoT sensors in the agricultural field, artificial intelligence (AI) for plant stress detection, drone technology for high resolution imaging and algorithmic routing, and cloud computing provides farmers with an advanced tool to monitor, manage, and predict agricultural outcomes more efficiently. By utilizing both historical and real-time data, it empowers farmers to make data-driven decisions, ultimately enhancing productivity, sustainability, and profitability in modern agriculture. This invention enhances the precision farming approach, enabling more sustainable agricultural practices and contributing to the growth of the agricultural sector.
[069] This is an agricultural device which allows the farmers to monitor the agricultural yard and its behaviour through Drone Twin (DT). An artificial intelligence based customized algorithm automates the process of event-based actions in the agricultural field. The hybrid drone combines the features of Digital Twin to enhance the quality of agricultural field Crop monitoring and growth prediction.
[070] This is a robust YOLOv11 model with 96.0% accuracy for detecting stress in the agricultural field. Successfully implemented IoT sensors for real-time monitoring of critical environmental factors and soil compositions. It demonstrated the effectiveness of the Drone powered Digital Twin in assessing real-time conditions of the field as well as stress detection in plants.
[071] Numerous modifications and adaptations of the system of the present invention will be apparent to those skilled in the art, and thus it is intended by the appended claims to cover all such modifications and adaptations which fall within the true spirit and scope of this invention.
REFERENCES
[1] Verdouw, C., Tekinerdogan, B., Beulens, A., & Wolfert, S. (2021). Digital twins in smart farming. Agricultural Systems, 189, 103046.
[2] Sreedevi, T.R., Santosh Kumar, M.B., 2020. Digital twin in smart farming: a categorical literature review and exploring possibilities in hydroponics. Advanced Computing and Communication Technologies for High Performance Applications (ACCTHPA), Cochin, India 2020, 120–124.
[3] Nie, J., Wang, Y., Li, Y., & Chao, X. (2022). Artificial intelligence and digital twins in sustainable agriculture and forestry: a survey. Turkish Journal of Agriculture and Forestry, 46(5), 642-661.
[4] Van Der Burg, S., Kloppenburg, S., Kok, E. J., & Van Der Voort, M. (2021). Digital twins in agri-food: Societal and ethical themes and questions for further research. NJAS: Impact in Agricultural and Life Sciences, 93(1), 98-125.
[5] Brunelli, M., Ditta, C. C., & Postorino, M. N. (2022). A Framework to Develop Urban Aerial Networks by Using a Digital Twin Approach. Drones, 6(12), 387.
[6] Hunt ER, Daughtry CST. What good are unmanned aircraft systems for agricultural remote sensing and precision agriculture? Int J Remote Sens 2018; 39:5345–76.
[7] El Bilali H, Allahyari MS. Transition towards sustainability in agriculture and food systems: Role of information and communication technologies. Inform Process Agric 2018; 5:456–64.
[8] Angin, P., Anisi, M. H., Göksel, F., Gürsoy, C., & Büyükgülcü, A. (2020). AgriLoRa: a digital twin framework for smart agriculture. J. Wirel. Mob. Networks Ubiquitous Comput. Dependable Appl., 11(4), 77-96.
[9] Kalyani, Y., Bermeo, N. V., & Collier, R. (2023). Digital twin deployment for smart agriculture in Cloud-Fog-Edge infrastructure. International Journal of Parallel, Emergent and Distributed Systems, 1-16.
[10] P. SP and P. Balamurugan, "Unmanned Aerial Vehicle in the Smart Farming Systems: Types, Applications and Cyber-Security Threats" 2022 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), Chennai, India, 2022, pp. 1-9, doi: 10.1109/ICSES55317.2022.9914070. , Claims:WE CLAIM:
1. The digital twin empowered drones to assist the farmers to optimize the agricultural field yard comprises-
a) IoT-based sensor networks (1),
b) Drones (2a, 2b…) equipped with high-resolution cameras (3a, 3b….) for drone imaging (2), and
c) Digital Twin integrated with sensor automation for real-time AI-driven analytics to significantly improve the monitoring and management of agricultural fields.
2. The digital twin empowered drones to assist the farmers to optimize the agricultural field yard, as claimed in claim 1, wherein the system dynamically optimize drone flight paths and sensor-based parameter collection providing high-accuracy and actionable insights for farmers, enhancing yield predictions and crop health monitoring.
3. The digital twin empowered drones to assist the farmers to optimize the agricultural field yard, as claimed in claim 1, wherein IoT sensors (1) captures environmental parameters such as soil moisture, temperature, and humidity, nitrogen levels, ammonia levels, oxygen levels in the soil and provides a real-time visualization of the agricultural field with sensor automation to improve the visibility of their agricultural land and instantly automate the actions need to be taken in the field.