https://jpas.in/index.php/home/issue/feed Journal Punjab Academy of Sciences 2024-12-29T05:24:01+00:00 Prof. Tarlok Singh jpasciences@gmail.com Open Journal Systems <p>The Journal Punjab Academy of Sciences (JPAS) is being published by Punjab Academy of Sciences (PAS) since 2004. It is a <strong>Peer Reviewed, Indexed, Refereed, Open Acess Scientific Research Journal</strong>. The all-inclusive approach of the Journal enables communication between scholars, scientists and academicians. It forms the basis for the development of further ideas and tracks emerging ideas in the field of science. Original research articles, reviews and short communications in all areas of physical, chemical and biological sciences, as well as related disciplines including engineering sciences are accepted for publication. The JPAS (Print ISSN 2229-7014) is widely circulated journal and helps to increase the visibility and creditability of the researchers and further in their career opportunities.</p> <p><strong>Print ISSN 2229-7014</strong></p> <p><strong>Year of Start (Print Journal): 2004</strong></p> <p><strong>Year of Start (Online Journal): 2020</strong></p> <p><strong>Frequency: Annual</strong></p> <p><strong>Published by: Punjab Academy of Sciences (India)</strong></p> <p><a title="28th PUNJAB SCIENCE CONGRESS NATIONAL CONFERENCE ON “Current Trends in SCIENCE AND TECHNOLOGY”" href="https://jpas.in/jpas2024.pdf"><strong>28th PUNJAB SCIENCE CONGRESS NATIONAL CONFERENCE ON “Current Trends in SCIENCE AND TECHNOLOGY”</strong></a></p> <p><a title="UGC Notification" href="https://jpas.in/UGCNotification.pdf"><strong><u>UGC Notification</u></strong></a></p> <p><a title="Membership Form" href="https://jpas.in/Membership%20Form.pdf"><strong>Membership Form</strong></a></p> <p><strong><a title="3rd Annual National Seminar on ROLE OF ARTIFICIAL INTELLIGENCE &amp; AUTOMATION IN MODERN AGE AGRICULTURE 13th NOVEMBER 2024" href="https://jpas.in/Announcement%20Brochure-2.pdf">3rd Annual National Seminar on ROLE OF ARTIFICIAL INTELLIGENCE &amp; AUTOMATION IN MODERN AGE AGRICULTURE 13th NOVEMBER 2024</a></strong></p> <p><a href="https://jpas.in/World%20Punjabi Diaspora Conference.pdf"><strong>World Punjabi Diaspora Conference</strong></a></p> <p><strong><a title="27th PUNJAB SCIENCE CONGRESS NATIONAL CONFERENCE ON “SCIENCE, BIODIVERSITY AND TECHNOLOGY: TOOLS FOR SUSTAINABLE DEVELOPMENT GOALS" href="https://jpas.in/PUNJAB%20SCIENCE%20CONGRESS bROCHURE fINAL 111.pdf">27th PUNJAB SCIENCE CONGRESS NATIONAL CONFERENCE ON “SCIENCE, BIODIVERSITY AND TECHNOLOGY: TOOLS FOR SUSTAINABLE DEVELOPMENT GOALS”</a></strong></p> https://jpas.in/index.php/home/article/view/95 SECURING SOIL HEALTH: LEVERAGING BLOCKCHAIN TECHNOLOGY FOR RELIABLE SOIL SAMPLING & TESTING 2024-12-28T18:38:52+00:00 Ramanpreet Singh ramanindagation@gmail.com Sukhwinder Singh Sran sukhwinder.ucoe@gmail.com Meenakshi Bansal ermeenu10@gmail.com <p>For efficient land management and harvesting, reliable soil testing and sampling is an essential component of agricultural techniques. The accuracy of soil data is at risk, though, due to problems like farmers using the same names and the frequency of inaccurate test results. Soil sampling and testing procedures may be made more secure and trustworthy with the use of blockchain technology, which is discussed in this study. Our proposed decentralized solution makes use of blockchain technology to avoid mistakes associated with shared names while also guaranteeing transparent record-keeping, immutable data verification, and safe farmer identification. Not only does our method ensure that soil test findings are genuine, but it also helps to build confidence among those involved in agriculture. Our case study illustrates how this technology may be put into reality and how it could transform soil management techniques. This, in turn, can lead to more sustainable agricultural results.</p> 2024-12-29T00:00:00+00:00 Copyright (c) 2024 https://jpas.in/index.php/home/article/view/96 CYBERSECURITY THREATS AND MITIGATION STRATEGIES IN AGRICULTURE 4.0 AND 5.0: CHALLENGES AND SOLUTIONS IN THE DIGITAL TRANSFORMATION OF AGRICULTURE 2024-12-29T03:34:45+00:00 Bhagwant Singh bhagwantsinghresearch@gmail.com Sikander Singh Cheema sikander@pbi.ac.in <p>Agriculture's digital evolution through Agriculture 4.0 and 5.0 brings unprecedented technological advancements, notably through IoT, AI, and Blockchain integration, which boost productivity, precision, and sustainability. However, this rapid adoption of connected and intelligent systems also presents a wide range of cybersecurity vulnerabilities that threaten data integrity, operational continuity, and privacy. This review identifies and categorizes key cybersecurity threats in Agriculture 4.0 and 5.0, examining specific risks associated with IoT devices, data privacy, AI models, and Blockchain applications in agriculture. It further explores mitigation strategies such as device encryption, Blockchain security protocols, Explainable AI (XAI) for transparency, and secure data-sharing practices to counteract these risks. By analyzing the interplay between Blockchain and AI, this study highlights synergies that enhance security, transparency, and trust within digital agriculture systems. In discussing ongoing challenges, including economic constraints and scalability issues, this review emphasizes the need for interdisciplinary research and tailored cybersecurity frameworks to safeguard agriculture’s digital transformation. Ultimately, securing Agriculture 4.0 and 5.0 is essential for strengthening global food systems, economic resilience, and the long-term sustainability of the agriculture sector.</p> <p>, , , , , .</p> <p>&nbsp;</p> 2024-12-29T00:00:00+00:00 Copyright (c) 2024 https://jpas.in/index.php/home/article/view/97 PRECISION AGRICULTURE USING ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING 2024-12-29T03:42:51+00:00 Parneet Kaur parkneet@gmail.com Dhavleesh Rattan parkneet@gmail.com Tejpal Sharma parkneet@gmail.com <p>Agriculture has seen a drastic evolution in the past few years. The usage of artificial intelligence technologies has made a significant impact on the respective field. Precision Agriculture (PA) practices have become very popular nowadays; these are the techniques which are focused on sensing and analyzing specific areas of the crops only such that the productivity of the entire crop field can increase. This article reviews the recent research done in the field of PA based on various machine learning and deep learning techniques. The usage of IoT technologies in supporting these techniques is also crucial. The research gaps in the current scenario of PA have also been discussed.</p> 2024-12-29T00:00:00+00:00 Copyright (c) 2024 https://jpas.in/index.php/home/article/view/98 FARMING 4.0: THE DIGITAL TRANSFORMATION OF AGRICULTURE 2024-12-29T03:51:21+00:00 Gurpreet Singh Gurpreet.1887@gmail.com <p>This is the transformative revolution sweeping across the agricultural sector commonly known as "Farming 4.0." It is led by advanced technologies such as Artificial Intelligence (AI), Machine Learning (ML), and the Internet of Things (IoT). They are changing the face of farming with data-driven, automated, and sustainable methods tailored to the required global food supply production. Agriculture will face challenges with the upsurge of a world population projected to reach 9.7 billion by 2050. Climate change, resource scarcity, and labor shortages are its significant challenges. Farming 4.0 addresses these issues through predictive analytics, automation, and real-time monitoring to optimize crop management, livestock monitoring, and supply chains. AI and ML analyze vast volumes of agricultural data that can lead to actionable insights that will improve decision-making. Precision farming aims to optimize planting schedules, water usage, and fertilizer application while increasing yields with minimal resources by using AI. The ML algorithms predict disease outbreaks and improve breeding cycles in livestock management, providing timely delivery with chain optimizations that avoid unnecessary waste and amplify market access for the farmers. Examples of Farming 4.0 in real life include the equipment John Deere is developing using AI, which consequently reduces chemical inputs such as herbicides, and Plantix, a mobile app for diagnosing plant diseases with high accuracy. Platforms such as IBM Watson Decision for Agriculture offer precise predictions about yield, and in this regard, assist the farmers in their planning. However, challenges concerning high costs, lack of technical expertise among smallholder farmers, and data quality issues hinder adoption. More important, ethical issues-auditing data protection, for instance, and job loss-will need to be addressed equally. The future promises much for all robotics, IoT, and AI will do to transform more agricultural. Realtime monitoring and even precision will improve with autonomous drones, robotic harvesters, and IoT-enabled sensors. Sustainability is going to be key, driven by AI to optimize the use of resources and minimize environmental footprint. End. Farming 4.0 marks a pivotal evolution in agriculture, harnessing AI and ML to create a more efficient, resilient, and sustainable farming ecosystem, addressing current challenges while meeting future demands.</p> 2024-12-29T00:00:00+00:00 Copyright (c) 2024 https://jpas.in/index.php/home/article/view/99 ENHANCED IMAGE PREPROCESSING FOR AUTOMATED MAIZE GRAIN VARIETY IDENTIFICATION 2024-12-29T04:03:27+00:00 Pritpal Kaur sukhwinder.ucoe@gmail.com Sukhwinder Singh Sran sukhwinder.ucoe@gmail.com Manish Kapoor sukhwinder.ucoe@gmail.com <p>Image identification is based on identifying the basics of geometry and shapes of the objects. The implementation of computer technology for identifying agricultural products based on their visual characteristics has been increasing&nbsp;popularity in the last few years. Methods for image processing based on product visual characteristics are used in a variety of fields for identification and analysis purposes.For the development of hybrid model for automated identification of maize grain varieties, several processes involved including image preprocessing, segmentation, feature extraction and identification. This paper is about the preprocessing of maize grain images after capturing images. Image preprocessing was necessary to resize images, augment images, gray-scale conversion and eliminate the noise from images in order to obtain more accurate feature information.</p> 2024-12-29T00:00:00+00:00 Copyright (c) 2024 https://jpas.in/index.php/home/article/view/100 IDENTIFICATION OF CROP HEALTH USING AI-ENABLED REMOTE SENSING 2024-12-29T04:12:53+00:00 Jaspreet Kaur Jaspreetkaurpaul@gmail.com Navjot Kaur navjot@pbi.ac.in <p>The rapid advancement of remote sensing technology, combined with artificial intelligence (AI), has opened new avenues for precision agriculture, particularly in the identification of crop health. This paper explores the integration of AI algorithms with remote sensing techniques, enabling the accurate detection and diagnosis of crop health conditions in real-time. Remote sensing devices capture high-resolution data through satellite, UAV (unmanned aerial vehicle), and ground-based sensors, while AI processes this data to detect patterns associated with various crop health indicators, such as nutrient deficiencies, disease symptoms, water stress, and pest infestations. AI techniques, including machine learning (ML), deep learning, and computer vision, automate and enhance the interpretation of this extensive dataset. This approach reduces dependency on traditional, labour-intensive scouting methods and offers a cost-effective, scalable solution for monitoring crop health across large agricultural areas. The paper also discusses potential challenges while suggesting directions for future research.</p> 2024-12-29T00:00:00+00:00 Copyright (c) 2024 https://jpas.in/index.php/home/article/view/101 SUPPLY CHAIN OPTIMIZATION IN AGRICULTURE USING ARTIFICIAL INTELLIGENCE 2024-12-29T04:22:28+00:00 Saumya Rajvanshi deepgaurav48@pbi.ac.in Gurleen Kaur deepgaurav48@pbi.ac.in Gaurav Deep deepgaurav48@pbi.ac.in <p>Agriculture is vital to nation’s economy as it fulfills the food demand of increasing population .The demand for sustainable practices increases and supply chain optimization using Artificial Intelligence (AI) is the most promising technology in agriculture sector. This article reviews the recent research done in the field of supply chain based on various AI techniques. The process of supply chain in agriculture is discussed and various AI tools are discussed which helps in mitigating the problems of supply chain. The research gaps in the current scenario are also discussed.</p> <p>&nbsp;</p> 2024-12-29T00:00:00+00:00 Copyright (c) 2024 https://jpas.in/index.php/home/article/view/102 ADVANCEMENTS IN DEEP LEARNING TECHNIQUES FOR IMAGE-BASED DETECTION OF DISEASES IN LEAVES OF MAIZE: A REVIEW 2024-12-29T04:30:33+00:00 Bhavya sukhwinder.ucoe@gmail.com Sukhwinder Singh Sran sukhwinder.ucoe@gmail.com Rohit Sachdeva sukhwinder.ucoe@gmail.com <p>This review article explores the critical role of deep learning in the automated detection and classification of maize leaf diseases, which significantly threaten global agricultural productivity. Traditional methods of disease identification typically depend on manual inspections, which can be time-consuming and susceptible to human error, resulting in inconsistent outcomes. In contrast, the proposed deep learning framework employs convolutional neural networks (CNNs) and transfer learning techniques that enhance diagnostic accuracy while reducing computational requirements. By utilizing a comprehensive dataset of labeled maize leaf images, the model effectively distinguishes between healthy and diseased leaves, targeting common afflictions such as maize rust, northern leaf blight, and gray leaf spot. The study emphasizes the model's adaptability to varying environmental conditions and its superior performance compared to conventional machine learning approaches. Furthermore, the article addresses the challenges encountered in real-world agricultural settings, including issues related to variable lighting and complex backgrounds that can obscure disease symptoms. It underscores the necessity for high-resolution, meticulously labeled images and advanced technology-driven solutions to enable rapid and precise disease detection. Such advancements are crucial for improving crop management and enhancing food security. Ultimately, this review aims to democratize access to effective diagnostic tools, empowering farmers and stakeholders in the agricultural sector with the resources needed to combat maize leaf diseases effectively. By fostering the adoption of these innovative technologies, the study contributes to the ongoing efforts to enhance agricultural resilience and productivity in the face of pressing global challenges.</p> 2024-12-29T00:00:00+00:00 Copyright (c) 2024 https://jpas.in/index.php/home/article/view/103 INTEGRATING FUZZY LOGIC INTO SMART AGRICULTURE SYSTEMS FOR BETTER YIELD PREDICTIONS 2024-12-29T04:41:03+00:00 Sukhpreet Kaur Sidhu sukhpreetkaursran@gmail.com <p>Agricultural systems are inherently complex, with multiple factors affecting crop yield, pest management, irrigation, soil health, and climate conditions. Traditional decision-making tools often struggle to accommodate the uncertainty and vagueness associated with agricultural data. Fuzzy set theory and fuzzy logic provide a framework for managing imprecision, allowing farmers, agronomists, and decision-makers to make more informed and flexible decisions. This paper explores the application of fuzzy set theory in various aspects of agriculture, focusing on how it aids in irrigation management, crop disease detection, pest control and overall farm management, among other areas. The paper highlights case studies and research advancements that showcase the practical benefits of adopting fuzzy logic in agriculture.</p> 2024-12-29T00:00:00+00:00 Copyright (c) 2024 https://jpas.in/index.php/home/article/view/104 ARTIFICIAL INTELLIGENCE IN FARMING: ADVANCING CROP MANAGEMENT, PEST CONTROL, AND SUSTAINABLE PRACTICES 2024-12-29T04:45:21+00:00 Lal Chand Panwar Lc.panwar5876@gmail.com Himanshu Lc.panwar5876@gmail.com <p>The integration of Artificial Intelligence (AI) in farming has revolutionized the agricultural sector, transforming traditional practices into precision agriculture. This paper explores the current trends and future scope of AI in farming, highlighting its applications in crop monitoring, yield prediction, disease detection, and automation. Systems are being developed to assist agricultural experts in finding better solutions all over the world. The applications of AI techniques in several fields of agricultural research, industrial insights, and the obstacles to AI adoption in agriculture are the major topics of this study. This paper discusses the benefits of AI-powered farming, including increased efficiency, reduced labor costs, and enhanced decision-making. Additionally, this paper also explores the role of machine learning algorithms, computer vision in collecting and analyzing agricultural data. The paper also addresses the challenges and limitations of implementing AI in farming, such as data privacy, security concerns, and the need for standardization. The analysis reveals that AI has the potential to increase crop yields, reduce environmental impact, and promote sustainable agriculture practices. As the global population continues to grow, AI-powered farming will play a vital role in ensuring food security and meeting the increasing demand for food production.</p> 2024-12-29T00:00:00+00:00 Copyright (c) 2024 https://jpas.in/index.php/home/article/view/105 SOIL POLLUTION DETECTION USING MACHINE LEARNING: A REVIEW 2024-12-29T04:52:35+00:00 Nirvair Neeru info@jpas.in Navjot Kaur info@jpas.in <p>Soil pollution is a developing natural issue, which leads to extreme biological, horticultural, and general wellbeing issues. Conventional strategies for detection and to monitor soil pollution such as chemical analysis and manual sampling are very tedious, costly, and limited in scope. Machine learning (ML) presents a promising way to overcome these problems by automatic detection of pollutants, prediction of contamination trends, and optimization monitoring strategies. This paper reviews the present status, the difficulties and future capability of ML in the field of soil pollution detection and mitigation.</p> <p><strong>&nbsp;</strong></p> 2024-12-29T00:00:00+00:00 Copyright (c) 2024 https://jpas.in/index.php/home/article/view/106 A REVIEW ON METHODS FOR DETECTING STUBBLE RESIDUE BURNING USING SATELLITE REMOTE SENSING 2024-12-29T04:59:35+00:00 Jagbir Singh Gill gill.jagbir@gmail.com Dhavleesh Rattan dhavleesh@gmail.com Manvinder Sharma gill.jagbir@gmail.com Gaurav Goel gaurav.coecse@cgc.edu.in Gagan Singla gill.jagbir@gmail.com Tejpal Sharma gill.jagbir@gmail.com <p>Stubble residue burning is a significant environmental issue, contributing to air pollution, greenhouse gas emissions, and public health hazards. Satellite remote sensing has emerged as a vital tool for detecting and monitoring stubble burning events over large areas. This paper reviews the various methods used for detecting stubble residue burning through satellite remote sensing. Various methods discussed include thermal anomaly detection, smoke plume identification, spectral analysis and the role of machine learning. A comparative analysis of these methods is provided, focusing on their accuracy, resolution, computational requirements and ability to capture the spatial and temporal dynamics of stubble burning. Sentinel-2 MSI and MODIS data is used to detect and visualize the fire for state of Punjab region.</p> 2024-12-29T00:00:00+00:00 Copyright (c) 2024 https://jpas.in/index.php/home/article/view/107 CROP PREDICTION FOR AGRICULTURE PRODUCTION OPTIMIZATION 2024-12-29T05:09:39+00:00 Navneet Kaur info@jpas.in Rashwinder Singh info@jpas.in <p>Crop prediction is a crucial aspect of modern agriculture, offering valuable insights into crop yields, growth patterns, and potential challenges that may arise. This study combines advanced data analysis methods with machine learning models to enhance the accuracy of crop predictions. By integrating these techniques, we are able to forecast crop outcomes with greater precision. In our approach, we focus on several key parameters that contribute to the development of robust predictive models. These include historical agricultural data, weather patterns, soil properties, and satellite imagery. By analyzing these factors, our models provide farmers with actionable insights that can help them optimize yield, while also supporting policymakers in making informed decisions regarding crop planning, resource management, and risk mitigation. This project also emphasizes the importance of sustainable agricultural practices, advocating for the efficient use of resources and environmental protection. A continuous data collection approach is explored, which is critical for adapting to the ever-changing conditions in agriculture. Furthermore, the study aligns the insights from agricultural experts with real-world practices and challenges, ensuring practical applicability. Looking ahead, future work could focus on improving the accuracy of the models by incorporating additional data, such as new crop types and diverse geographical areas. Additionally, exploring deep learning techniques and integrating sensor data through Internet of Things (IoT) technology could further enhance the predictive capabilities of the system.</p> 2024-12-29T00:00:00+00:00 Copyright (c) 2024 https://jpas.in/index.php/home/article/view/108 AI AND IOT-DRIVEN SOLUTIONS FOR SUSTAINABLE FARMING IN PUNJAB: OVERCOMING FINANCIAL BARRIERS AND ENHANCING RESOURCE EFFICIENCY 2024-12-29T05:14:42+00:00 Jairaj Sander info@jpas.in Sikander Singh info@jpas.in <p>One of the most important industries in the world today is agriculture, which is essential to environmental sustainability, food security, and economic growth. With a growing global population expected to reach nearly 10 billion by 2050, ensuring a steady and reliable food supply is essential for avoiding hunger and malnutrition. Once called as ‘granary of the country’ and ‘bread basket of the country’, the state of Punjab revolutionized the Agro needs and Agro economy of the country, after the green revolution, Punjab, Haryana, and western UP quenched the need for food security and got India independence from the humiliating PL480 scheme.&nbsp; Punjab contributes 10 - 12 % of rice and 13 - 15 % of wheat in India’s total rice and wheat production despite covering only 1.5 % of the geographical area of the country. After the Green Revolution. People employed in agriculture and agriculture-related fields have drastically come down from 60% to 35-36%, and that is not just because of modernization, urbanization, and diversification rather Many people have lost interest in farming as a result of Punjab's diminishing agricultural economic returns, soil deterioration, and the depletion of natural resources like groundwater. Traditional crops like rice and wheat have yielded stagnant income over time, and the rising labor, fertilizer, and water costs have made farming less profitable. Many farmers in the state suffer from poor and erratic profits as a result. The frequency of farmer suicides in Punjab has jumped since 2015. From nearly 70 suicides a year between 2000 and 2014, the number increased by nearly four times to 263 a year after 2015 (peaking at 323 in 2018).[The India Forum]. Many of the reasons farmers take these extreme steps can be improved with the use of AI and IoT-incorporated farming.&nbsp; The adoption of advanced technologies like agricultural sensors, drones, GPS, and other integrated devices has rapidly progressed in agriculture. However, in Punjab, most farmers have not embraced these precision agricultural practices. Key reasons include a lack of awareness about these technologies, financial constraints, and other practical barriers that limit farmers' ability to implement modern farming methods. In this paper, writers have addressed the major problems farmers across Punjab are facing and how many of these can be solved using modern technological approaches.</p> 2024-12-29T00:00:00+00:00 Copyright (c) 2024