Title of the Paper: A Survey on Machine Learning and Deep Learning Techniques for Crop Assessment, Yield Prediction, and Disease Detection
Authors: D. Lalitha; B. Kranthi Kiran
Abstract:
Agriculture plays a vital role in GDP of INDIA. Advanced technologies like ML/DL Machine Learning / Deep Learning portraying a vital role for precision farming with limited resources [1]. There is a significant increase of ML/DL models for analyzing agricultural data. This survey reviews many significant research papers focusing on ML and DL applications for crop assessment, yield prediction, and disease detection. The advantages and limitations of each approach are discussed in details in this paper. Rice is a staple food in India and is particularly significant in the state of Telangana. The study area is of Nalgonda District of Telangana and current year Paddy was cultivated in 66.77 lakh acres, yielding 1.53 crore metric tons, where it plays a crucial role in the agricultural economy. Nalgonda district, known for its rich agricultural heritage, has emerged as a notable producer of rice in the region. In the context of rapidly shifting climatic patterns and a continuously growing global population, ensuring food security has become a critical priority [2]. Biotic stresses significantly threaten crop productivity, identifying them at the initial stage is must to avoid loss in yield. Traditional ways for disease detection heavily depend on human expertise, which can be hand operated, slow moving and tedious, and susceptible to errors. Nevertheless, the evolution of machine learning (ML) [2] has introduced highly efficient and precise automated solutions for disease detection. This study thoroughly explores A range of ML approaches, The study explores Convolutional Neural Networks (CNNs) [10], Recurrent Neural Networks (RNNs), Support Vector Machines (SVMs) [15], Random Forests (RF) [18], and cutting-edge deep learning frameworks like ResNet and Inception. It delves into their core methodologies, the datasets employed, and the metrics used for evaluating performance and practical approaches. By text mining recent literature from the past five years, this review provides an extensive overview of suggested frameworks, methods, precision metrics, Attribute selection and extraction techniques, datasets, and their sources. Our findings highlight the substantial promise of ML-based approaches [5] in improving crop disease management. However, there is an urgent requirement to build more durable, scalable, and versatile systems, to address the broad range of factors and complexities of crop diseases. This review offers valuable insights for designing and deploying ML-driven solutions for plant illness detection, in turn promoting green farming and contributing to the worldwide food protection.
Keywords: Machine Learning /Deep Learning Techniques, Convolutional/ Recurrent Neural Networks, Support Vector Machines
ISSN (Online): 2456-9852 | Year: 2024 | Volume: 9, Issue: 1 | Journal Article | Publisher: IJECRT
Title of the Paper: Harnessing Artificial Intelligence for Sustainable Space Colonization
Authors: Kukka Chaitna Sree Varshith; Yashas Nallathambi; Sanka Santhosh; Kiranmai
Abstract:
As the world faces significant issues, including overpopulation and depletion of resources, space colonization, which is now becoming highly feasible, thanks to recent developments in Artificial Intelligence, has emerged as a hopeful solution. This research paper discusses the revolutionary role AI can play in tackling the various challenges associated with sustainable human settlement on celestial bodies, primarily the Moon and Mars. This study aims to optimize the required conditions for human survival out of Earth by developing solutions for habitat design, management of resources, and monitoring health through AI-driven automation. It investigates the concept of adaptive, energy efficient habitats, automates extractive processes for resources and implements health systems that curb the psychological and physiological results of living in space. The ethical, economic, and governance dimensions of AI deployment in extraterrestrial environments are critically assessed. The findings emphasize that AI not only enhances the sustainability of space colonies but also fosters economic opportunities and international collaboration in space exploration efforts. Finally, it contributes a comprehensive framework for making AI technologies available for the assurance of a prosperous human extension into the cosmos, bridging both immediate existential needs and long-term aspirations for human future.
Keywords: Artificial Intelligence (AI), Resource management, Sustainability
ISSN (Online): 2456-9852 | Year: 2024 | Volume: 9, Issue: 1 | Journal Article | Publisher: IJECRT