0% found this document useful (0 votes)
53 views11 pages

Performance Analysis and Evaluation of Machine Learning Algorithms in Rainfall Prediction

This document analyzes and compares machine learning algorithms for rainfall prediction, including Lasso regression, ridge regression, elastic net regression, random forest, gradient boosting, and decision tree regressor. It finds that Lasso regression performs best with an R^2 score of 99.21%, MAE of 13.68, MSE of 6432.41 and RMSE of 80.20. The study aims to accurately predict rainfall to help prevent natural disasters and losses for farmers. Machine learning methods can potentially improve upon traditional statistical approaches for rainfall forecasting.

Uploaded by

shivasantosh004
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
53 views11 pages

Performance Analysis and Evaluation of Machine Learning Algorithms in Rainfall Prediction

This document analyzes and compares machine learning algorithms for rainfall prediction, including Lasso regression, ridge regression, elastic net regression, random forest, gradient boosting, and decision tree regressor. It finds that Lasso regression performs best with an R^2 score of 99.21%, MAE of 13.68, MSE of 6432.41 and RMSE of 80.20. The study aims to accurately predict rainfall to help prevent natural disasters and losses for farmers. Machine learning methods can potentially improve upon traditional statistical approaches for rainfall forecasting.

Uploaded by

shivasantosh004
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 11

SRM Institute of Science and Technology, kattankulatur, Chennai.

PERFORMANCE ANALYSIS AND


EVALUATION OF MACHINE LEARNING
ALGORITHMS IN RAINFALL PREDICTION
Done By:
V.Yashwanth Reddy: RA2111026010445
M.Rohan Reddy: RA2111026010445
M.Surya: RA2111026010461
Agenda:

 Abstract
 Introduction
 Scope of the project
 Objective
 Literature survey
 Reference
Abstract

 Massive rainfall forecast is a significant problem for the meteorological


department. This paper investigates the performance of the various Machine
Learning (ML) models, namely Lasso regression, ridge regression, elastic net
regression, random forest, gradient boosting and decision tree regressor.
 Those models performances have been calculated through the evaluation
metrics such as R ^ 2 score, Mean Absolute Error (MAE), Mean Square Error
(MSE), and Root Mean Square Error (RMSE).
 The objective of this study is to compare different machine learning regression
algorithms in rainfall dataset. In this analysis, we conclude that the Lasso
regression of the linear model is the best model among six ML models. Lasso
model given more R ^ 2 score is 99.21%, MAE is 13.68, MSE is 6432.41 and
RMSE is 80.20 at 80 % training data set and 20% at test dataset
Scope of the Project

 In the hydrological study, the main problem is accurately predicting the rainfall. Due to natural hazards
and storm, farmers will lose and destroy their crops.
 To avoid these problems, accurately and timely predict the rainfall prediction earlier and give caution
more first to farmers.
 The rainfall prediction is more required as it is concerned with the maximum association with other
factors like landslides, flooding, avalanches, earthquakes, and so on. Such disasters affect the public
severely for many decades.
 Hence, developing effective model to predict the rainfall helps to prevent the natural disaster to the
limited extent. We applied different regression techniques of machine learning algorithms to build the ML
models to make accurate and timely predictions. Machine learning is used to study and develop the
system behavior model.
 Machine learning modeling techniques used to design models which can be further predicted vital system
parameters with regards to Indian panther ecosystem.
 This article aims to deliver end to end machine learning life cycle right from Data acquisition to
evaluating the models. For evaluation metrics of regress or is R2, Mean Absolute Error (MAE), Mean
Square Error (MSE) and Root Mean Square (RMSE).
Introduction

•Problem: Accurate rainfall prediction is essential for a variety of applications, such as


drought monitoring, flood forecasting, and agricultural planning.
•Traditional methods for rainfall prediction, such as statistical methods, have limitations
in terms of accuracy and robustness.
•Artificial neural networks (ANNs) are a type of machine learning algorithm that can be
used to learn complex relationships between input and output variables.
•ANNs have been shown to be effective in rainfall prediction, and they have the
potential to improve the accuracy and robustness of rainfall forecasts.
Objective

 The rainfall prediction is more required as it is concerned with the


maximum association with other factors like landslides, flooding,
avalanches, earthquakes, and so on. Such disasters affect the
public severely for many decades. Hence, developing effective
model to predict the rainfall helps to prevent the natural disaster
to the limited extent.
LITERATURE REVIEW
Authors Techniques Accuracy Measure Description
Y.Jeevan nagendra SVR(support vector MSE The main idea behind
SVR is to find a
Kumar(2023) Regression hyperplane in a high-
dimensional feature
space that best
represents the
relationship between
the input features and
the corresponding
target values. This
hyperplane is
determined in such a
way that it maximizes
the margin between the
predicted data points
and the hyperplane,
while also allowing
some tolerance for
errors (known as
epsilon) on either side
of the hyperplane.
LITERATURE REVIEW

Authors Techniques Accuracy Measure Description

Chalachew Muluken MLR(multivariate Mean rainfall This paper presented


the multivariate linear
Liyew(2022) linear regression) regression because
multiple environmental
variables or features
were used to predict
the dependent variable
called daily rainfall
amount. Linear
regression is a
supervised
machine learning
technique used to
predict the unknown
daily rainfall amount
using the
known environmental
variables.
Literature Review
Authors Technique Accuracy Measure Descriptiion
Zaharaddeen SVM RMSE The key idea behind
SVM is to transform the
Karami(2021) input data into a higher-
dimensional space (by
using a kernel function)
and then find the
hyperplane that
maximizes the margin
between the classes.
The margin is the
distance between the
hyperplane and the
closest data points from
each class, known as
support vectors. SVM is
considered a "maximum
margin classifier"
because it seeks to find
the hyperplane with the
largest margin to
improve generalization
and reduce overfitting.
Conclusion

•Conclusion: The results of this study suggest that ANNs can


be used to develop accurate and robust rainfall prediction
systems. Further research is needed to improve the
performance of ANN models and to develop more efficient
training algorithms.
REFERENCE

 https://www.geeksforgeeks.org/ml-rainfall-prediction-using-linear-
regression/
 https://journalofbigdata.springeropen.com/articles/10.1186/s40537-021-
00545-4
 https://www.ijraset.com/research-paper/rainfall-prediction-using-ml

You might also like