Scribd
Upload
82 views10 pages

BCS01T1002 AI Fundamentals: Prepared By: Group No. 32, Yash Kumar, 20SCSE1180135 Yash Saxena, 20SCSE1180120

This document discusses using artificial intelligence for weather forecasting. It summarizes the old complicated techniques for weather prediction and existing systems that have limitations like overprediction and high costs. It then proposes two new models - a multi-target regression model that uses multivariate regression to predict multiple weather variables simultaneously, and a recurrent neural network model using LSTM to make predictions based on current and historical weather data. The importance of accurate weather forecasting is also highlighted.

Uploaded by

Yash Kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
82 views10 pages

BCS01T1002 AI Fundamentals: Prepared By: Group No. 32, Yash Kumar, 20SCSE1180135 Yash Saxena, 20SCSE1180120

This document discusses using artificial intelligence for weather forecasting. It summarizes the old complicated techniques for weather prediction and existing systems that have limitations like overprediction and high costs. It then proposes two new models - a multi-target regression model that uses multivariate regression to predict multiple weather variables simultaneously, and a recurrent neural network model using LSTM to make predictions based on current and historical weather data. The importance of accurate weather forecasting is also highlighted.

Uploaded by

Yash Kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 10

CAT-III

BCS01T1002
AI Fundamentals

Prepared by:
Group No. 32, Yash Kumar ,20SCSE1180135
Yash Saxena , 20SCSE1180120

Semester: I Section:13

Session 2020-2021

03/07/2021 1
School of Computing Science & Engineering
Course Code : BCS01T1002 Course Name: AI Fundamentals

Basic Terminologies
Course Code : XXXXXX Course Name: Data structures using C
• Weather - Condition of the air on earth at a given time.
• Climate - Average weather conditions in a place over many years.
• Weather Forecasting is the application of science and technology to predict the condition of the atmosphere based on previously
collected data.

Group No: 32 Program Name: B.Tech SCSE Sem: I 2


School of Computing Science & Engineering
Course Code : BCS01T1002 Course Name: AI Fundamentals

Ways to Predict Weather


Course Code : XXXXXX Course Name: Data structures using C
 The old complicated techniques.
1. Complicated Formulae, Complex Calculations
2. Less Accuracy.
3. Very Costly.

 Forecasting using Artificial Intelligence.


1. Instant Results.
2. More Accuracy.
3. Less Costly.

Group No: 32 Program Name: B.Tech SCSE Sem: I 3


School of Computing Science & Engineering
Course Code : BCS01T1002 Course Name: AI Fundamentals

The old complicated technique


Course Code : XXXXXX Course Name: Data structures using C
• Involves very complicated mathematical calculations.
• Time consuming.
• Requires huge amount of Data.
• Quite inaccurate results.

Ancient Barometer
ENIAC

Group No: 32 Program Name: B.Tech SCSE Sem: I 4


School of Computing Science & Engineering
Course Code : BCS01T1002 Course Name: AI Fundamentals

Existing Systems
Course Code : XXXXXX Course Name: Data structures using C
• Uses Machine Learning algorithms like Linear Regression etc.
• Some existing models make use of surrounding data of the target site which makes them less efficient.
• Over Prediction in many existing models.
• Gets very costly when made use of Satellites to gather data to make more precise predictions.

Group No: Program Name: Sem: I 5


School of Computing Science & Engineering
Course Code : BCS01T1002 Course Name: AI Fundamentals

New Models to overcome existing drawbacks


Course Code : XXXXXX Course Name: Data structures using C
 In order to overcome the drawbacks of the existing weather forecasting models, two new models have been proposed:-
1. MULTI-TARGET REGRESSION MODEL
2. RECURRENT NEURAL NETWORK (RNN) MODEL

 MULTI-TARGET REGRESSION MODEL:


• In comparison to the older method which uses Linear Regression for predicting future weather conditions, Multi-Target
Regression uses Multivariate Regression for predicting future weather conditions.
• In this model, the input variables are mapped to the multiple outputs that we want to predict that is humidity level,
precipitation rate, pressure.
• This particular model is based on Supervised Learning as this model uses regression technique which uses labeled dataset.

Group No: 32 Program Name: B.Tech SCSE Sem: I 6


School of Computing Science & Engineering
Course Code : BCS01T1002 Course Name: AI Fundamentals

MULTI-TARGET REGRESSION MODEL

Course Code : XXXXXX Course Name: Data structures using C

Multivariate Regression Plot

Group No: 32 Program Name: B.Tech SCSE Sem: I 7


School of Computing Science & Engineering
Course Code : BCS01T1002 Course Name: AI Fundamentals

RECURRENT NEURAL NETWORK (RNN) MODEL

• Recurrent neural network is a deep learning model which has an internal memory which can be used to store the
Course Code : XXXXXX Course Name: Data structures using C
information of the previously calculated output.
• Since RNN has short term memory, Long Short-Term Memory (LSTM) is used along with it.
• As we know that Neural Networks have fundamental components known as Neuron, so in this case; temperature,
humidity, pressure, dew point, wind speed, precipitation and visibility are considered as Neurons.
• Weather forecasting is done by collecting information related today weather in regards to the previous and the present
condition of the weather and utilizing this information to train LSTM model.

Group No: 32 Program Name: B.Tech SCSE Sem: I 8


School of Computing Science & Engineering
Course Code : BCS01T1002 Course Name: AI Fundamentals

Data flow and Importance of Accurate Weather Forecasting

• Since data is the key component in machine learning models, it is very important to clean the raw data and extract only the
Course Code : XXXXXX Course Name: Data structures using C
required data and feed the data to the model in a specific format.
• Weather forecasting is important to each and everyone, whether it is a student who decides to carry an umbrella or not by
knowing the weather, or a government organization which helps people to vacate a location by knowing that it is going to
rain heavily in that region.
• Accurate Weather Forecasting is really important to farmers .

Group No: 32 Program Name: B.Tech SCSE Sem: I 9


School of Computing Science & Engineering
Course Code : BCS01T1002 Course Name: AI Fundamentals

The End
Course Code : XXXXXX Course Name: Data structures using C

Thank You

Group No: 32 Program Name: B.Tech SCSE Sem: I 10

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy