Agriculture Crop Yield Analysis and Prediction using Feature Selection based Machine Learning Techniques
T. V. Rajinikanth1, Burma Kavya2, Narameta Thanuja Sri3, Alley Yashwanth Saikrishna4
1Dr. T. V. Rajini Kanth, Professor & Head, Department of Computer Science Engineering- AI & ML, SNIST, Hyderabad (Telangana), India.
2Burma Kavya, B.Tech Students, Department of Computer Science and Engineering, Sreenidhi Institute of Science and Technology, Hyderabad (Telangana), India.
3Narameta Thanuja Sri, B.Tech Students, Department of Computer Science and Engineering, Sreenidhi Institute of Science and Technology, Hyderabad (Telangana), India.
4Alley Yashwanth Saikrishna, B.Tech Students, Department of Computer Science and Engineering, Sreenidhi Institute of Science and Technology, Hyderabad (Telangana), India.
Manuscript received on 28 November 2022 | Revised Manuscript received on 03 December 2022 | Manuscript Accepted on 15 December 2022 | Manuscript published on 30 December 2022. | PP: 99-108 | Volume-12 Issue-2, December 2022 | Retrieval Number: 100.1/ijeat.B39421212222 | DOI: 10.35940/ijeat.B3942.1212222
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Agriculture is being the world’s largest industry; it plays a major role in maintaining the economic stability of developing countries. Because of the responsibilities that this sector bears, it is critical to find the precision of production in making profitable decisions in agricultural sector. Machine learning is the most effective tool for making decisions. Machine learning techniques with correct optimizations have been utilized in conjunction with the use of multiple algorithms and create an accurate model for predicting production and also in guiding to improve crop cultivation for enhanced output. The elements like cost of cultivation, cost of production, and yield are utilized to predict the crop yield during the analysis. In this study, the necessary data was acquired, and the methodologies and features employed in agricultural yield analysis were studied. During the literature survey more than 50 articles were referred for analysis. Relevant topics were collected from electronic databases and found useful machine learning approaches with which desired model was developed. Along with Random Forest, Decision Trees, and Support Vector Machine, Gaussian Nave Bayes, and Ada Boost machine learning techniques, Carl Pearson Correlation, Mutual Information, and Chi Square Feature Selection techniques were applied. The accuracy percentage for different algorithms was calculated crop yield prediction with and without feature selection approaches. We also used time complexities to figure out which method is the most efficient and accurate.
Keywords: Yield Analysis, Decision Tree, Feature Selection, Random Forest, Crop Selection.
Scope of the Article: Agricultural Informatics and Communication