2022
DOI: 10.1016/j.uclim.2022.101315
|View full text |Cite
|
Sign up to set email alerts
|

AI-based air quality PM2.5 forecasting models for developing countries: A case study of Ho Chi Minh City, Vietnam

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
2
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
6
2
1

Relationship

0
9

Authors

Journals

citations
Cited by 15 publications
(5 citation statements)
references
References 15 publications
0
2
0
Order By: Relevance
“…SGDRegressor is a regression algorithm that uses stochastic gradient descent (SGD) to minimize the loss function and is suitable for handling large-scale datasets. Compared with the traditional batch gradient descent, SGDRegressor approximates the E(w, b) true gradient by considering only one training sample per iteration, resulting in an efficient training process [45]. Due to the stochastic nature of the decline, SGDRegressor requires more iterations to reach the minimum, but it is still computationally inexpensive.…”
Section: Sgdregressor Algorithmmentioning
confidence: 99%
“…SGDRegressor is a regression algorithm that uses stochastic gradient descent (SGD) to minimize the loss function and is suitable for handling large-scale datasets. Compared with the traditional batch gradient descent, SGDRegressor approximates the E(w, b) true gradient by considering only one training sample per iteration, resulting in an efficient training process [45]. Due to the stochastic nature of the decline, SGDRegressor requires more iterations to reach the minimum, but it is still computationally inexpensive.…”
Section: Sgdregressor Algorithmmentioning
confidence: 99%
“…Artificial intelligence algorithms are playing an increasingly important role in environmental detection. For example, in hydrology, artificial intelligence, and climate detection, the use of corresponding algorithms can achieve good prediction results [9][10][11].…”
Section: Related Workmentioning
confidence: 99%
“…P M 2.5 (µg/m 3 ) DO (mg/L) Matrix GCN-GRU Rakholia et al [11] GCN-GRU Huan et al [ In this paper, we compare the performance of our implemented model with other studies, which can be observed in Table 2. For P M 2.5 , Rakholia's study [11] implemented a 1D CNN-LSTM model to predict P M 2.5 values after 24 hours and evaluated prediction accuracy using MAE and RMSE. Our GCN-GRU model shows a lower performance of around 0.9 in MAE and 0.87 in RMSE, indicating a higher prediction accuracy.…”
Section: Performance Comparisonmentioning
confidence: 99%