An investigation into supervised machine learning algorithms for predicting crop yields is being conducted
Author(s): Laxman Garje1, Prof.B.A. Shinde2, Amruta Gavde3, Pratiksha Devkate4 , Snehal Shinde5
Affiliation: 1,2,3,4,5Shree Ramchandra College of Engineering
Page No: 18-21-
Volume issue & Publishing Year: Volume 1 Issue 1,June- 2024
Journal: International Journal of Modern Engineering and Management | IJMEM
ISSN NO: 3048-8230
DOI:
Abstract:
In many developing nations, agriculture remains the principal source of livelihood. Modern agricultural practices are continuously evolving to address the challenges posed by a rapidly changing environment. Farmers face obstacles, such as adapting to climate variations stemming from soil degradation and industrial pollution. The lack of essential nutrients, including potassium, nitrogen, and phosphorus, in the soil can result in reduced crop yields, making it difficult for farmers to satisfy the increasing demands of buyers and consumers. To tackle these challenges, innovative strategies are essential. This research paper investigates the use of machine learning methods, particularly focusing on the Support Vector Machine (SVM) and Random Forest algorithms, for forecasting crop yields. This predictive modeling helps farmers optimize resource utilization and make data-driven decisions about crop management. The importance of precise crop yield predictions is emphasized as vital for promoting sustainable and efficient agricultural practices. The paper also points out the limitations of traditional forecasting methods and presents machine learning as a practical alternative. A detailed examination of the SVM and Random Forest algorithms is provided, clarifying their fundamental concepts and appropriateness for yield prediction
Keywords:
crop prediction, machine learning, support vector machine, random forest, decision tree
Reference:
[1] “Suitable Crop Prediction based on affecting Parameter using Naïve Bayes Classification Machine Learning Technique [2023]” A Review by Dr. Latha Bandha, Aarushi Rai, Ankit Kansal - This paper provides an overview of various machine learning techniques used for crop yield prediction.
[2] "Automated Rice crop Yield Prediction using sine Cosine Algorithm with weighted Regularized Extreme learning Machine" [2023]by - Mr. .S .Thirumal, Dr. R. Latha This paper explores the application of machine learning algorithms such as Cosine Algorithm, Artificial Neural Networks (ANN) for rice yield prediction.
[3] “Analysis of Machine Learning Technique for Crop Selection and Prediction of Crop Cultivation” Proceedings of the International Conference on Inventive Computation Technologies (ICICT 2023) IEEE Xplore Part Number: CFP23F70- ART; ISBN: 979-8-3503-9849-6 [2023] by Tanvi Deshmukh , Anand Rajawat , S.B. Goyal , Jugnesh Kumar, Amol Potgantwar prediction of suitable crop and its growth monitoring is dependent on parameters like soil, water, temperature, rainfall, humidity and weather conditions that affect crop production
[4] “Machine Learning-Based Crop Recommendations for Precision Farming to Maximize Crop Yields” International Conference on Computer Communication and Informatics (ICCCI ), Jan. 23 – 25, 2023, Coimbatore, [2022] by C. Sagana, M. M. Sangeetha, S. Savitha , K .Devendran , T. Kavin , K. Kavinsri.
[5] “Effects of Satellite Revisit Rate and Time-Series Smoothing Method on Throughout-Season Maize Yield Correlation Accuracy” [2023] A Review by Emily Myers , Graduate Student Member, IEEE, John Kerekes , Senior Member, IEEE, Craig Daughtry, and Andrew Russ - This paper explored the effects of time-series end date and imaging frequency on our ability to correlate VI with maize yield, using daily, high-resolution (3-m GSD) multispectral satellite