This project presents a comprehensive system integrating full-stack development with machine learning capabilities to forecast PM2.5 levels in the air. Leveraging the MEAN stack for robust full-stack development and the Prophet algorithm for machine learning, the system facilitates efficient prediction and visualization of PM2.5 concentrations. Upon accessing the system, users encounter an authentication page to ensure secure access. Following successful login, users are directed to the home page, which serves as the central interface for interaction. The home page features a user-friendly interface, including a dedicated section for data input. Users upload a CSV file containing the dataset and specify the prediction timeframe, choosing from options such as day, week, month, or year, along with entering the numerical duration. Subsequently, the machine learning algorithm processes the input data, generating predictions for the specified time-period. The system visualizes the forecasted PM2.5 levels through an interactive graph, providing users with intuitive insights into air quality trends. This visualization empowers users to make informed decisions and take proactive measures based on predicted PM2.5 concentrations. By seamlessly integrating full-stack development with machine learning, this project offers a practical solution for forecasting PM2.5 levels.

1.
Brown
,
D.
(
2018
). “
Air quality forecasting using machine learning techniques: a review
."
Journal of Computational Science
,
28
,
1
18
.
2.
Taylor
,
S. J.
, &
Letham
,
B.
(
2018
). “
Forecasting at scale
."
The American Statistician
,
72
(
1
),
37
45
.
3.
Taylor
,
J. W.
, &
Ljung
,
G. M.
(
2017
). “
Forecasting using big data: A review
."
Statistica Sinica
,
27
(
1
),
71
96
.
4.
Lewis
,
J.
,
Ebel
,
B.
, &
Engle
,
S.
(
2019
). “
Leveraging machine learning for PM2.5 forecasting: Insights and challenges
."
Environmental Modelling & Software
,
119
,
345
356
.
5.
Kordjamshidi
,
A.
,
Abbasi
,
M.
, &
Roushan
,
G.
(
2020
). “
A comprehensive review on PM2.5 prediction using machine learning and deep learning techniques.
Atmospheric Environment
,
227
,
117400
.
6.
Liu
,
Y.
,
Sui
,
B.
,
Wang
,
J.
,
Wang
,
X.
, &
Hu
,
Y.
(
2021
). “
PM2.5 concentration prediction based on machine learning algorithms: A review
."
Atmospheric Environment
,
247
,
118118
.
7.
Rangaswamy
,
M.
,
Saravanan
,
M.
, &
Priya
,
R.
(
2020
). “
Prediction of PM2.5 concentration using machine learning techniques.
Environmental Monitoring and Assessment
,
192
(
11
),
708
.
8.
Li
,
X.
,
Peng
,
L.
, &
Hu
,
H.
(
2019
). “
Machine learning models for predicting PM2.5 in real time in China
."
Journal of Cleaner Production
,
226
,
1036
1047
.
9.
Zhou
,
H.
,
Zhao
,
Q.
,
Wang
,
W.
,
Wang
,
L.
, &
Wu
,
Q.
(
2020
). “
An ensemble machine learning approach for PM2.5 concentration prediction in smart cities.
Environmental Pollution
,
256
,
113402
.
10.
Herrera
,
J.
, &
Sánchez-Lorenzo
,
A.
(
2019
). “
Predictive modeling of PM2.5 air pollution in a megacity using support vector regression based on synoptic patterns
."
Science of the Total Environment
,
693
,
133462
.
This content is only available via PDF.
You do not currently have access to this content.