Improving air quality prediction accuracy at larger temporal resolutions using deep learning and transfer learning techniques

2019 ◽  
Vol 214 ◽  
pp. 116885 ◽  
Author(s):  
Jun Ma ◽  
Jack C.P. Cheng ◽  
Changqing Lin ◽  
Yi Tan ◽  
Jingcheng Zhang
Keyword(s):  
Deep Learning ◽  
Air Quality ◽  
Transfer Learning ◽  
Prediction Accuracy ◽  
Quality Prediction ◽  
Air Quality Prediction ◽  
Learning Techniques

scholarly journals A DBN-Based Deep Neural Network Model with Multitask Learning for Online Air Quality Prediction

2019 ◽  
Vol 2019 ◽  
pp. 1-9 ◽  
Author(s):  
Jiangeng Li ◽  
Xingyang Shao ◽  
Rihui Sun
Keyword(s):  
Neural Network ◽  
Air Quality ◽  
Network Model ◽  
Neural Network Model ◽  
Prediction Accuracy ◽  
Deep Neural Network ◽  
Multitask Learning ◽  
Air Pollutant ◽  
Quality Prediction ◽  
Air Quality Prediction

To avoid the adverse effects of severe air pollution on human health, we need accurate real-time air quality prediction. In this paper, for the purpose of improve prediction accuracy of air pollutant concentration, a deep neural network model with multitask learning (MTL-DBN-DNN), pretrained by a deep belief network (DBN), is proposed for forecasting of nonlinear systems and tested on the forecast of air quality time series. MTL-DBN-DNN model can solve several related prediction tasks at the same time by using shared information contained in the training data of different tasks. In the model, DBN is used to learn feature representations. Each unit in the output layer is connected to only a subset of units in the last hidden layer of DBN. Such connection effectively avoids the problem that fully connected networks need to juggle the learning of each task while being trained, so that the trained networks cannot get optimal prediction accuracy for each task. The sliding window is used to take the recent data to dynamically adjust the parameters of the MTL-DBN-DNN model. The MTL-DBN-DNN model is evaluated with a dataset from Microsoft Research. Comparison with multiple baseline models shows that the proposed MTL-DBN-DNN achieve state-of-art performance on air pollutant concentration forecasting.

scholarly journals Prediction of Ambient PM2.5 Concentrations Using a Correlation Filtered Spatial-Temporal Long Short-Term Memory Model

2019 ◽  
Vol 10 (1) ◽  
pp. 14 ◽  
Author(s):  
Yuexiong Ding ◽  
Zheng Li ◽  
Chengdian Zhang ◽  
Jun Ma
Keyword(s):  
Air Pollution ◽  
Air Quality ◽  
Prediction Accuracy ◽  
Short Term Memory ◽  
Quality Prediction ◽  
Short Term ◽  
Concentration Data ◽  
Term Memory ◽  
Air Quality Prediction ◽  
Long Short Term Memory

Due to the increasingly serious air pollution problem, air quality prediction has been an important approach for air pollution control and prevention. Many prediction methods have been proposed in recent years to improve the prediction accuracy. However, most of the existing methods either did not consider the spatial relationships between monitoring stations or overlooked the strength of the correlation. Excluding the spatial correlation or including too much weak spatial inputs could influence the modeling and reduce the prediction accuracy. To overcome the limitation, this paper proposes a correlation filtered spatial-temporal long short-term memory (CFST-LSTM) model for air quality prediction. The model is designed based on the original LSTM model and is equipped with a spatial-temporal filter (STF) layer. This layer not only takes into account the spatial influence between stations, but also can extract highly correlated sequential data and drop weaker ones. To evaluate the proposed CFST-LSTM model, hourly PM2.5 concentration data of California are collected and preprocessed. Several experiments are conducted. The experimental results show that the CFST-LSTM model can effectively improve the prediction accuracy and has great generalization.

scholarly journals Blockchain-Enabled Federated Learning on Kubernetes for Air Quality Prediction Applications

2021 ◽  
Vol 3 (3) ◽  
pp. 196-217
Author(s):  
Shajulin Benedict ◽  
Deepumon Saji ◽  
Rajesh P. Sukumaran ◽  
Bhagyalakshmi M
Keyword(s):  
Air Quality ◽  
Quality Parameters ◽  
Model Parameters ◽  
Quality Prediction ◽  
Learning Models ◽  
Recent Past ◽  
Air Quality Prediction ◽  
Learning Techniques ◽  
Frame Work ◽  
Distributed Cluster

The biggest realization of the Machine Learning (ML) in societal applications, including air quality prediction, has been the inclusion of novel learning techniques with the focus on solving privacy and scalability issues which capture the inventiveness of tens of thousands of data scientists. Transferring learning models across multi-regions or locations has been a considerable challenge as sufficient technologies were not adopted in the recent past. This paper proposes a Blockchain- enabled Federated Learning Air Quality Prediction (BFL-AQP) framework on Kubernetes cluster which transfers the learning model parameters of ML algorithms across distributed cluster nodes and predicts the air quality parameters of different locations. Experiments were carried out to explore the frame- work and transfer learning models of air quality prediction parameters. Besides, the performance aspects of increasing the Kubernetes cluster nodes of blockchains in the federated learning environment were studied; the time taken to establish seven blockchain organizations on top of the Kubernetes cluster while investigating into the federated learning algorithms namely Federated Random Forests (FRF) and Federated Linear Regression (FLR) for air quality predictions, were revealed in the paper.

scholarly journals Uncertainty-Aware Deep Learning Architectures for Highly Dynamic Air Quality Prediction

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 14765-14778
Author(s):  
Ichrak Mokhtari ◽  
Walid Bechkit ◽  
Herve Rivano ◽  
Mouloud Riadh Yaici
Keyword(s):  
Deep Learning ◽  
Air Quality ◽  
Quality Prediction ◽  
Air Quality Prediction ◽  
Learning Architectures

scholarly journals Deep Learning Model for Air Quality Prediction Based on Big Data

2021 ◽  
pp. 170-175
Author(s):  
P. Parkavi ◽  
S. Rathi
Keyword(s):  
Air Pollution ◽  
Deep Learning ◽  
Air Quality ◽  
Internet Of Things ◽  
Learning Algorithm ◽  
Pollution Monitoring ◽  
The Internet ◽  
Quality Prediction ◽  
Air Quality Prediction ◽  
The Internet Of Things

Air pollution and its harm to human health has become a serious problem in many cities around the world. In recent years, research interests in measuring and predicting the quality of air around people has spiked. Since the Internet of things has been widely used in different domains to improve the quality for people by connecting multiple sensors. In this work an IOT based air pollution monitoring with prediction system is proposed. The internet of Things is a action interrelated computing devices that are given unique identifiers and the capability of exchange information over a system without anticipating that human to human or human to machine communication. The deep learning algorithm approach is to evaluate the accuracy for the prediction of air pollution. The main objective of the project is used to predict the air Quality. The large dataset works with LSTM for better air quality prediction. The prediction accuracy of air quality with LSTM, the evaluation indicator Root means square error is chosen to measure performance.

Sign in / Sign up

Export Citation Format

Share Document