Smart Farming System Research Articles

Empowering Farmers with IoT, UAVs, and Deep Learning in Smart Agriculture

This review article explores the transformative influence of Internet of Things (IoT), Unmanned Aerial Vehicles (UAVs), and Deep Learning (DL) in modern agriculture, outlining their applications and impact on Smart Agriculture Systems (SAS). Examining various wireless communication technologies within IoT, including LoRa, Zigbee, and cellular networks like 5G, the study delineates their roles in enabling real-time monitoring and data transmission across expansive agricultural landscapes. Moving to UAVs, the review highlights their pivotal role in precision agriculture, elucidating how these aerial platforms equipped with diverse sensing technologies and cameras facilitate crop monitoring, disease detection, and targeted pesticide spraying. The integration of Deep Learning techniques, particularly Convolutional Neural Networks (CNNs), is discussed to emphasise their significance in disease detection, pest management, soil parameter estimation, and weed identification. The synthesis of these technologies reshapes traditional agricultural methodologies, empowering farmers with data-driven decision-making tools for optimized yield, sustainable practices, and efficient resource utilization. This comprehensive exploration aims to provide insights into the synergy of IoT, UAVs, and DL, laying the groundwork for the evolution of agricultural practices worldwide towards increased productivity and sustainability.

Corrections to “Evaluation of Machine Learning Approaches for Precision Farming in Smart Agriculture System: A Comprehensive Review”

Corrections to “Evaluation of Machine Learning Approaches for Precision Farming in Smart Agriculture System: A Comprehensive Review”

Forecasting of soil moisture using machine learning in smart agriculture systems

Growing crops in modern conditions is a complex task and practically combines the practices of experience and the latest methods, including information technology, which has become part of the concept of "smart farming". An important factor in the stable predicted yield is the level of soil moisture, which is the result of changes in climatic factors such as air temperature, soil temperature, intensity of solar radiation, rainfall, wind speed, etc. A methodology for processing real historical indicators of climate change in a certain geographical area with subsequent training and application of machine learning models to predict soil moisture is proposed. To build a machine learning model, the following algorithms were selected and studied: the algorithm of regression trees, random forest, linear regression, M5P algorithms and the K* algorithm. The data source for training the models is the open information resource International Soil Moisture Network (ISMN) from ismn.earth/en. , which provides data on soil moisture and temperature, air temperature, and rainfall. Other data was used from the Open Meteo information service, which provides a free API and allows you to get historical data and weather forecast in specified coordinates during specified days. A data structure was developed to train the model for further prediction of soil moisture. An architecture has been developed and a software system for predicting soil moisture based on machine learning algorithms has been created using the Spring Framework, the WEKA library and Java FX with the ability to select and study the appropriate algorithms. Experiments have been carried out and the results of the duration of model training have been presented, while the algorithms of regression trees and linear regression require the least training time. A comparison of algorithms is made according to the following criteria: learning speed, cross-testing speed, prediction speed, testing performance indicators for real historical data. Based on the results of the study, conclusions are drawn about individual algorithms, the feasibility of using them to predict soil moisture based on climatic indicators. The obtained results will make it possible to evaluate and select the best models of machine learning in the design of the information and analytical system "smart agriculture" for forecasting soil moisture.

Automated Fruit Sorting in Smart Agriculture System: Analysis of Deep Learning-based Algorithms

Automated Fruit Sorting in Smart Agriculture System: Analysis of Deep Learning-based Algorithms

Evaluation of Machine Learning Approaches for Precision Farming in Smart Agriculture System: A Comprehensive Review

Evaluation of Machine Learning Approaches for Precision Farming in Smart Agriculture System: A Comprehensive Review

Revolutionizing Automated Agriculture: A Brief Overview of an Advanced Smart Agriculture System Using Arduino UNO

This project presents a Smart Agriculture System that uses sensor technologies to improve crop monitoring and automate irrigation procedures. A variety of sensors are integrated into the system, such as a temperature sensor, a gas sensor, a photodiode for ambient light sensing, and a soil moisture sensor. When taken as a whole, these sensors offer real-time information on the concentrations of gases, ambient light levels, temperature fluctuations, and soil conditions in agricultural environments. The system’s primary function is to continuously monitor soil moisture levels in order to determine when irrigation is necessary. A water pump is activated when a predetermined moisture threshold is reached, guaranteeing timely and precise irrigation for the best possible crop growth. By monitoring the climate, the temperature sensor helps determine the environmental factors that affect crop health. Farmers can monitor important parameters with ease thanks to the convenient and user-friendly interface that the real-time display of sensor data on an LCD screen provides. Furthermore, by measuring the amount of natural light present, the ambient light sensor helps the system to optimize planting schedules and comprehend the impact of sunlight on crop development. The addition of a gas sensor expands the capabilities of the system by identifying possible environmental risks or variations in gas concentrations that could have an impact on crop quality. In addition to providing farmers with useful information about the health of their crops, this integrated smart agriculture system makes irrigation automation easier, saving water and increasing overall agricultural productivity. Due to its flexibility and scalability, the system is an invaluable resource for contemporary precision agriculture, contributing to sustainable farming practices and increased crop yields.

Smart Farming System Based on Cloud Computing Technologies

Smart farming is a new concept that can be described as applying different kinds of modern technology to make farming more efficient. One such technology is the Internet of Things, an extension of the Internet and other connections into mundane devices. This paper uses dedicated sensors and cloud computing technologies to model a smart farming system that helps farmers keep track of state of the crops and livestock. It also covers implementing and testing an Android tracker app that is supposed to become the first component of the mentioned system, a client application that communicates with the cloud computing services yet to be implemented. The end product provides its users with an easy way of keeping track of the state of their farms, simplifying the farmers’ work and enhancing productivity.

Farmers’ Toolkit: Deep Learning in Weed Detection and Precision Crop & Fertilizer Recommendations

Agriculture is widely recognized as a significant and indispensable occupation on a global scale. The current imperative is to optimize agricultural practices and progressively transition towards smart agriculture. The Internet of Things (IoT) technology has dramatically enhanced people’s daily lives via diverse applications across several domains. Previous studies have yet to effectively incorporate Artificial Intelligence (AI) with sensor technology to provide comprehensive guidance to agricultural practitioners, hindering their ability to achieve good outcomes. This research offers Farmers’ Toolkit with four layers: sensor, network, service, and application. This toolkit aims to facilitate the implementation of a smart farming system while effectively managing energy resources. With a specific emphasis on the application layer, the toolkit uses a deep learning methodology to construct a fertilizer recommendation system that aligns with the expert’s perspective. This study utilizes IoT devices and Wireless Sensor Network (WSN) methods to enhance the efficiency and speed of recommending appropriate crops to farmers. The recommendation process considers several criteria: temperature, yearly precipitation, land area, prior crop history, and available resources. The identification of undesirable vegetation on agricultural fields, namely the detection of weeds, is carried out using drone technology equipped with frame-capturing capabilities and advanced deep-learning algorithms. The findings demonstrate an accuracy rate of 94%, precision rate of 92%, recall rate of 96%, and F1 score of 94%. The toolkit for farmers alleviates physical labor and time expended on various agricultural tasks while enhancing overall land productivity, mitigating potential crop failures in specific soil conditions, and minimizing crop damage inflicted by weeds.

IoT performance analysis on water infrastructure to support optimization of catfish cultivation

In recent years, IoT has become a reliable technology in the agricultural sector to optimize cultivation results. In the Marsudi Luhur breeder group, the harvest results were not optimal because many catfish died and gave off a bad smell. According to several references, to ensure healthy growth of catfish, continuous irrigation of the pond is required even though the flow rate is low. The location of the catfish pond is quite far from residential areas so it is not practical to monitor irrigation performance by frequently visiting the pond area. Therefore, this project aims to create an IoT-based smart farming system using the Blynk application. The system has been successfully implemented to help monitor and control solenoid performance and water flow remotely. The results show that the IoT-based smart system has performed well and has the potential to increase efficiency, comfort and productivity in managing catfish ponds.

Towards Precise Agriculture: Integrating Machine Learning Techniques for Smart Farming Systems

Towards Precise Agriculture: Integrating Machine Learning Techniques for Smart Farming Systems

Smart Agriculture Solutions: Harnessing AI and IoT for Crop Management

This review article, “Smart Agriculture Solutions: Harnessing AI and IoT for Crop Management,” explores the transformative impact of digital technologies in agriculture. It focuses on the integration of the Internet of Things (IoT), Cloud Computing, and Artificial Intelligence (AI) in enhancing sustainable farming practices. IoT technologies enable real-time monitoring of agricultural conditions using sensors and drones, while Cloud Computing provides robust data processing capabilities. AI leverages this data for predictive analytics in crop yields, disease detection, and automation of farming processes, optimizing resource use and adapting to climate change. The paper also examines the synergy of renewable energy sources with AI to power smart farming systems, proposing innovative solutions for energy-efficient, AI-driven agriculture. It highlights AI’s extensive role in improving crop management, from seed selection to soil analysis and crop health monitoring, thereby increasing yield quality and fostering sustainability. Furthermore, the article discusses the significance of space technologies in smart agriculture, showcasing advancements like drones and big data analytics. These innovations are crucial in developing economies, addressing global challenges like food security and contributing to economic growth. This review underlines the necessity of AI and IoT in revolutionizing agricultural methodologies, ensuring efficiency and sustainability in the face of a rapidly growing global population.

IoT Based Smart Agriculture / Gardening

Traditional agriculture rely heavily on manual monitoring and irrigation, leading to water waste, uneven crop growth, and increased labor costs. This paper proposes an Internet of Things (IoT)-based smart agriculture system for optimized irrigation. The system uses an ESP32 microcontroller to collect soil moisture data from sensors. User-defined thresholds trigger automated watering using a relay-controlled mechanism. The system offers on-site monitoring through an OLED display and remote monitoring capabilities via the Blynk platform. This paper details the system design, implementation, and testing, demonstrating its power for efficient water use and improved crop yield in agricultural and gardening applications.

Yield prediction models of organic oil rose farming with agricultural unmanned aerial vehicles (UAVs) images and machine learnaing algorithms

The alternative solution for predicting yields involves leveraging the latest technological advancements in unmanned aerial vehicles (UAVs) imagery. This approach aims to empower agricultural systems operating in nature-dependent conditions, enabling them to optimize the utilization of limited resources effectively. This study aimed to provide the agricultural data management needed for the adoption of sustainable agriculture systems and the transition of precision to smart agriculture systems by combining technology. The study was carried out in the 2019–2020 vegetation period to determine the effect of the parameters on the yield in the areas where organic farming is grown in Isparta oil rose (Rosa Damascena Mill.) and to develop yield prediction models by combining them with spectral measurements. In the study, the phenological, morphological, and biochemical changes of the Isparta oil rose were examined periodically, and the effects of biotic and abiotic stress factors during the vegetation period were determined in the study and testing area. For the early yield prediction of organic Isparta oil rose was chosen thirteen parameters as soil moisture, pH, electrical conductivity (EC), soil temperature, and nine vegetation indices were derived from UAV-acquired multispectral images. The parameters were functioned in machine learning algorithms, which were multiple linear regression (MLR), multivariate adaptive regression splines (MARS), decision trees (chi-squared automatic interaction detector (CHAID), exhaustive chi-squared automatic interaction detector (ExCHAID), classification and regression tree (CART)), random forest (RF)) and artificial neural network (ANN), to develop the prediction models. Early period (day 69) for organic rose yield prediction models were determined to be useable as MARS 1 (0.907 R2), ExCHAID 1 (0.888 R2), CART 1 (0.931 R2), and RF 1 (0.909 R2).As a result of the study, the models can be used integrated with UAV and soil data for the early prediction of Isparta oil rose yield under organic farming systems, especially during the Agriculture 4.0 transition phase in our country. It is such that models be developed and used in different ecologies for sustainable agricultural systems.

Prevention of soil erosion, prediction soil NPK and Moisture for protecting structural deformities in Mining area using fog assisted Smart agriculture system

A new idea called "smart agriculture" enables farms to be managed using cutting-edge technology like IoT, AI, robotics, drones, etc. The goal is to maximize the use of the resources at hand while producing more crops of higher quality and quantity. Crop output growth is mostly dependent on the fertility and moisture content of the soil. In the past, different fertilizers were added to the soil to boost its nutrients, but this process took time and labour from humans. Subsequently, as technology advanced, the data gathered from IoT devices was processed via cloud computing. Fog computing provides a solution to the significant latency associated with cloud server location that is remote. The main goal of this research is to create a fog-assisted recommendation model that can be applied to the future prediction of soil moisture content and NPK. When combined with agricultural systems, machine learning algorithms provide a proactive, data-driven method for maximizing resource management and soil health. It offers a succinct overview of how to forecast crop growth through the use of hybrid machine learning algorithms on the IFogsim platform to enhance soil quality and irrigation efficiency. Moreover, it lessens soil erosion and increases soil stability. In the mining sector, the suggested technique is helpful for protecting against structural deformities and stabilizing slopes.

Harvesting the Future: AI and IoT in Agriculture

This review article, “Harvesting the Future: AI and IoT in Agriculture,” presents a comprehensive analysis of the transformative impact of Artificial Intelligence (AI) and the Internet of Things (IoT) in modern agriculture. It synthesizes a range of studies to showcase how AI and Machine Learning (ML) algorithms are revolutionizing crop management, precision agriculture, and supply chain efficiency. Utilizing data from various sources like sensors, drones, and satellites, these technologies enable optimized resource use, enhanced crop yields, and better livestock health monitoring. The review highlights the role of IoT in agriculture, particularly its benefits in easy installation, reduced maintenance, and energy harvesting for device sustainability. It explores the integration of IoT with big data and knowledge-based systems, addressing key challenges in farm data management. Additionally, the paper delves into the growing adoption of smart agriculture techniques, driven by cost-effective IoT sensors and AI advancements. These technologies facilitate efficient resource management, predictive analytics, and autonomous farming, thereby modernizing traditional agricultural practices. The review also discusses the broader social implications and future trends in the adoption of smart agriculture systems, describing their significance in enhancing agricultural productivity, sustainability, and profitability.

Agricultural informatics: emphasising potentiality and proposed model on innovative and emerging Doctor of Education in Agricultural Informatics program for smart agricultural systems

Agricultural informatics: emphasising potentiality and proposed model on innovative and emerging Doctor of Education in Agricultural Informatics program for smart agricultural systems

Agricultural Informatics: Emphasising potentiality and proposed model on innovative and emerging Doctor of Education (Ed.D.) in Agricultural Informatics Program for Smart Agricultural Systems

Agricultural Informatics: Emphasising potentiality and proposed model on innovative and emerging Doctor of Education (Ed.D.) in Agricultural Informatics Program for Smart Agricultural Systems

Smart Agriculture using Ensemble Machine Learning Techniques in IoT Environment

Crop yield is a serious concern for farmers due to irregular irrigation, soil erosion, uncontrolled seed planting, severe weather conditions, peasants, and unpredicted locust infestations. The lack of current data and the intricacy of traditional agriculture leads to inefficiency and excessive operation costs. Smart farming with Artificial Intelligence techniques and the Internet of Things (IoT) in agriculture overcome these challenges by connecting all the accessible data sources into a single, fully effective functional unit. Smart agriculture helps in the sustainability of food production by using minimum resources such as water, fertilizer, and seeds. It provides a better understanding of the soil, crop, and changing weather. Furthermore, the sensors in the system assist in monitoring and controlling the resources. In this research, we present ensemble-based machine learning approaches in the IoT environment to predict crop yields and enable sustainable farming by guiding the farmers to grow the correct crop during the correct season to increase their yields. The proposed method uses a novel ensemble-based machine learning classification approach with two levels of predictions-level-0 prediction includes (Logistic Regression (LR), Classification and Regression Trees (CART), Support Vector Machines (SVM), and K-Nearest Neighbors (KNN)) classifiers are input as features to the level-1 meta classifier (Random Forest) to detect the distinct categories of different crops. Its predictions can be extremely close to the ground truth, which accurately predicts 22 categories of crops with 99% accuracy. Hence, the proposed Smart agriculture system can assist farmers in improved yield production and remote monitoring at low cost.

Smart Agriculture system based on IoT reference architecture and service choreography

This paper presents a monitoring, control, and management system that allows the interoperability of multiple smart gateways in a greenhouse to bolster automatic decision making on water supplied to the crops in real-time. The system consists of several sensor nodes interconnected by Zigbee to measure ambient and soil parameters to control the greenhouse irrigation process. In addition, a web service is included to help the system manager to visualize and operate the greenhouse on a web platform. The system also supports human decision making to cope with undesirable and unexpected environmental events. Smart gateways enable data reading, storage and edge computing using automatic rules to manage actions in the greenhouse, as well as data transmission for centralized processing in cloud services. The service communication system layer is supported by choreography middleware for messaging distribution, which enables agile scalability. This research proposes a hybrid scheme and compares to a centralized scheme. The latency times in the choreography system were analyzed to find a suitable solution adapted to infrastructure deployment features. Numerical results shows that such an adaptive deployment of the irrigation services among edge and fog layers can reduce the computational load on the gateways, improve system response times, and enhance device performance.

SUSTAINABLE DEVELOPMENT AND SMART AGRICULTURE SYSTEM

Modern farming is being transformed by smart agricultural systems, which use creative innovation for long-term sustainability. Examining the approaches of smart agriculture, this paper mostly focuses on precision farming, IoT integration, and data-driven decision-making procedures. Precision farming's toolkit consists of drones, sensors, and global positioning systems (GPS), meant to enhance crop management, efficiency, and quality of harvest. By means of IoT, agricultural processes may be automated and real-time monitored, thus improving water and energy efficiency, lowering environmental effect, and raising productivity. Using predictive insights made available by merging big data analytics with machine learning algorithms helps one better forecast and address issues like global warming, pest control, and soil health. This research examines case studies and pilot projects all over to better grasp what factors influence the scalability and acceptability of an implementation as well as what makes it successful. The paper contends that infrastructural development, farmer education, and supportive laws are vital if smart agriculture is to fully realize itself. It addresses the social and financial consequences as well as how it may improve food security, provide employment, and increase farmers' pay. Emphasizing the need of research and development expenditure, stakeholder involvement, and continuous innovation, the paper closes with a conversation about what the future holds. By the use of smart agriculture systems, which mix contemporary technology with time-honoured farming practices, sustainable agricultural development—including the protection of the environment and future generations' food supply—may be much strengthened.