Comparative Analysis of Prediction Model In Weather Forecasting System For Agricultural Development

J, Prakash and A, Bharathi and M, Priya Dharshini (2021) Comparative Analysis of Prediction Model In Weather Forecasting System For Agricultural Development. In: ICCAP 2021, 7-8 December 2021, Chennai, India.

[thumbnail of PDF]
Preview
Text (PDF)
eai.7-12-2021.2314971.pdf - Published Version

Download (2MB) | Preview

Abstract

Agriculture is the backbone of a country. If a country is able to yield very good food it can be one of the best countries in the world. Rainfall is playing a vital role in field of agriculture. Predicting weather conditions for agriculture is a challenging and most needed feature for agriculture for every country. In the recent years, Data Analytics has played a vital role in detecting the challenges and risks in certain factors. We use Learning algorithms to predict challenges and risk faced in each problem. By predicting them in prior we may take certain actions before itis leaving out of our hand. The learning and prediction algorithms help to classify, predict and to make changes if needed. This study aims in predicting weather (i.e., Rainfall) which helps every agriculturist to predict weather and to sow different types of plants based on the weather condition. This study not only helps for agriculture it also helps in various fields like fishing, sports, transportation, tourism, etc. Weather forecasting is based on the available historical data. The predictions are done using various algorithms like Artificial Neural Network (ANN), Support Vector Machine (SVM) and Linear Regression (LR). The results infer that the prediction model using Support Vector Machine gives the best accuracy when compared with Linear Regression and Artificial Neural Network. This prediction helps people in planting crops and helps to make decision based on the weather condition.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: weather prediction agriculture learning models support vector machine linear regression artificial neural network
Subjects: T Technology > T Technology (General)
Depositing User: EAI Editor IV
Date Deposited: 24 Feb 2022 14:20
Last Modified: 24 Feb 2022 14:20
URI: https://eprints.eudl.eu/id/eprint/9701

Actions (login required)

View Item
View Item