Hybrid Machine Learning based Crop Prediction Model
Main Article Content
Abstract
The manufacturing of agricultural goods has always been an essential component of economic growth, and it has had a significant influence on the economic well-being of our country. In addition, as a result of the quick development of science, the agricultural sector has emerged as one of the most important areas in which to address challenges associated with farming. These challenges include land, the flow of groundwater, catastrophic events, herbicides, and pesticides. It is essential to the growth of harvests in farming that an adequate quantity of precipitation be observed throughout all stages of yield development. Along with crop prediction, this paper provides clear information about the quantities of soil ingredients required and their associated costs by applying deep learning techniques to the suggested model. When compared to the current approach, it improves precision. By analyzing the data provided, it aids producers in making informed business decisions. The land's climate and dirt are factored in to estimate a reasonable harvest. The goal is to introduce a Python-based system that makes use of strategic thinking to foresee the most productive harvest under specific circumstances while minimizing associated costs. Machine Learning is handled by the Support Vector Machine (SVM) algorithm, while Deep Learning is represented by the LSTM and RNN algorithms.
Article Details

This work is licensed under a Creative Commons Attribution-NoDerivatives 4.0 International License.