Scribd
Upload
3 views9 pages

RNN Weather Forecasting in Oromia

The document reviews existing weather forecasting methods, highlighting their limitations such as low resolution, data quality issues, and high computational costs. It proposes a Recurrent Neural Network (RNN) model as a solution, which automates forecasting, improves real-time data updates, and captures extreme weather patterns more effectively. The RNN model is presented as a scalable and cost-effective alternative that enhances prediction accuracy and reliability for weather forecasting in Oromia.

Uploaded by

hundaolteshome94
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
3 views9 pages

RNN Weather Forecasting in Oromia

The document reviews existing weather forecasting methods, highlighting their limitations such as low resolution, data quality issues, and high computational costs. It proposes a Recurrent Neural Network (RNN) model as a solution, which automates forecasting, improves real-time data updates, and captures extreme weather patterns more effectively. The RNN model is presented as a scalable and cost-effective alternative that enhances prediction accuracy and reliability for weather forecasting in Oromia.

Uploaded by

hundaolteshome94
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

Chapter 2: Literature Review

(Existing System)
Weather Forecasting Using RNN in
Oromia
Final Year Project
Introduction
• - Weather forecasting is crucial for agriculture,
disaster management, and planning.
• - Traditional forecasting relies on historical
data but lacks real-time adaptability.
• - The study evaluates existing methods and
their limitations.
Existing Weather Forecasting
Methods
• 1. **Surface Weather Observations** –
Collects temperature, humidity, wind speed,
precipitation.
• 2. **Satellite Imagery** – Provides cloud
patterns and atmospheric data.
• 3. **Numerical Weather Prediction (NWP)
Models** – Uses algorithms (GFS, ECMWF) for
forecasts.
Challenges in the Existing System
• - **Low Spatial & Temporal Resolution** –
Weather stations are far apart, affecting
accuracy.
• - **Data Quality Issues** – Limited historical
data, distorted satellite imagery.
• - **Computational Costs** – NWP models
require high processing power and expertise.
Users & Functions of the Existing
System
• 1. **Farmers** – Plan farming activities based
on forecasts.
• 2. **Transportation Companies** – Adjust
routes and schedules for safety.
• 3. **Disaster Management Teams** – Prepare
for extreme weather events.
• 4. **Government & Researchers** – Use data
for planning and policy-making.
Bottlenecks in the Existing System
• - **Limited Real-time Processing** –
Forecasts rely heavily on historical trends.
• - **Inconsistent Weather Patterns** – Hard to
predict extreme climate changes.
• - **High Cost & Complexity** – Requires
significant computational resources.
Performance Metrics for
Improvement
• - **Mean Absolute Error (MAE)** – Measures
average error between predicted & actual
values.
• - **Mean Squared Error (MSE) & Root Mean
Squared Error (RMSE)** – Evaluate accuracy.
• - **R-Squared Value** – Determines how well
the model explains variations.
Proposed Solution: RNN Model
• - **Automates Weather Forecasting** –
Reduces manual intervention.
• - **Real-time Data Updates** – Improves
accuracy & reliability.
• - **Captures Seasonal & Extreme Weather
Patterns** – Better than traditional methods.
• - **Scalable & Cost-Effective** – Handles large
datasets efficiently.
Conclusion
• - Traditional forecasting methods have
limitations in accuracy and real-time
processing.
• - The proposed **RNN-based model
significantly improves prediction accuracy.**
• - RNN enhances **efficiency, scalability, and
reliability** for weather forecasting in
Oromia.

You might also like