A Spatial–Temporal Causal Convolution Network Framework for Accurate and Fine-Grained PM2.5 Concentration Prediction
Shaofu Lin,Junjie Zhao,Jianqiang Li,Xiang Liu,Yumin Zhang,Shaohua Wang,Qiang Mei,Zhuodong Chen,Yuyao Gao +8 more
TL;DR: In this paper , a spatial-temporal causal convolutional network (ST-CCN-PM2.5) was proposed to predict fine-grained PM2-5 concentration in Haikou, China.
read more
Abstract: Accurate and fine-grained prediction of PM2.5 concentration is of great significance for air quality control and human physical and mental health. Traditional approaches, such as time series, recurrent neural networks (RNNs) or graph convolutional networks (GCNs), cannot effectively integrate spatial–temporal and meteorological factors and manage dynamic edge relationships among scattered monitoring stations. In this paper, a spatial–temporal causal convolution network framework, ST-CCN-PM2.5, is proposed. Both the spatial effects of multi-source air pollutants and meteorological factors are considered via spatial attention mechanism. Time-dependent features in causal convolution networks are extracted by stacked dilated convolution and time attention. All the hyper-parameters in ST-CCN-PM2.5 are tuned by Bayesian optimization. Haikou air monitoring station data are employed with a series of baselines (AR, MA, ARMA, ANN, SVR, GRU, LSTM and ST-GCN). Final results include the following points: (1) For a single station, the RMSE, MAE and R2 values of ST-CCN-PM2.5 decreased by 27.05%, 10.38% and 3.56% on average, respectively. (2) For all stations, ST-CCN-PM2.5 achieve the best performance in win–tie–loss experiments. The numbers of winning stations are 68, 63, and 64 out of 95 stations in RMSE (MSE), MAE, and R2, respectively. In addition, the mean MSE, RMSE and MAE of ST-CCN-PM2.5 are 4.94, 2.17 and 1.31, respectively, and the R2 value is 0.92. (3) Shapley analysis shows wind speed is the most influencing factor in fine-grained PM2.5 concentration prediction. The effects of CO and temperature on PM2.5 prediction are moderately significant. Friedman test under different resampling further confirms the advantage of ST-CCN-PM2.5. The ST-CCN-PM2.5 provides a promising direction for fine-grained PM2.5 prediction.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Methods used for handling and quantifying model uncertainty of artificial neural network models for air pollution forecasting
TL;DR: In this article , a review of the approaches for addressing model uncertainty according to the steps for building ANN models is presented, which recommends the development and application of approaches that can both handle and quantify uncertainty surrounding the development of ANN models.
22
Interpretable Machine Learning Approaches for Forecasting and Predicting Air Pollution: A Systematic Review
Anass Houdou,Imad El Badisy,Kenza Khomsi,Sammila Andrade Abdala,Fayez Abdulla,Houda Najmi,Majdouline Obtel,Lahcen Belyamani,Azeddine Ibrahimi,Mohamed Khalis +9 more
TL;DR: This systematic review will focus on reviewing studies that have utilized interpretable machine learning models to enhance interpretability while maintaining high accuracy for air pollution prediction.
Adaptive scalable spatio-temporal graph convolutional network for PM2.5 prediction
Qingjian Ni,Yuhui Wang,Jiayi Yuan +2 more
TL;DR: This paper proposes ASGCN, an adaptive scalable spatio-temporal graph convolutional network for PM2.5 prediction, combining time convolution and adaptive weighted multilayer graph convolution to capture temporal and spatial relationships, achieving state-of-the-art performance on two real PM2.5 datasets.
9
Simultaneous forecasting of wind speed for multiple stations based on attribute-augmented spatiotemporal graph convolutional network and tree-structured parzen estimator
Chu Zhang,Xiujie Qiao,Zhao Zhang,Yuhan Wang,Yongyan Fu,Muhammad Shahzad Nazir,Tian Peng +6 more
TL;DR: This study proposes an evolutionary algorithm-based deep learning model, IASTGCN-TPE, for simultaneous wind speed forecasting at multiple stations, leveraging spatiotemporal relationships and mutual information to improve accuracy and outperform baseline models.
9
Particulate Matter (PM1, 2.5, 10) Concentration Prediction in Ship Exhaust Gas Plume through an Artificial Neural Network
TL;DR: In this article , an Artificial Neural Network (ANN) was used to evaluate an individual ship's plume by combining several data sources such as AIS data, meteorological data, and measured the ship plume pollutants concentration.
References
Deep learning
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
67K
Learning Phrase Representations using RNN Encoder--Decoder for Statistical Machine Translation
Kyunghyun Cho,Bart van Merriënboer,Caglar Gulcehre,Dzmitry Bahdanau,Fethi Bougares,Holger Schwenk,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio +8 more
- 01 Jan 2014
TL;DR: In this paper, the encoder and decoder of the RNN Encoder-Decoder model are jointly trained to maximize the conditional probability of a target sequence given a source sequence.
•Proceedings Article
A unified approach to interpreting model predictions
Scott M. Lundberg,Su-In Lee +1 more
- 04 Dec 2017
TL;DR: In this article, a unified framework for interpreting predictions, SHAP (SHapley Additive exPlanations), is presented, which assigns each feature an importance value for a particular prediction.
A Computer Movie Simulating Urban Growth in the Detroit Region
TL;DR: A Computer Movie Simulating Urban Growth in the Detroit Region as discussed by the authors was made to simulate urban growth in the city of Detroit, Michigan, United States of America, 1970, 1970.
9.4K
Neurons with graded response have collective computational properties like those of two-state neurons.
TL;DR: A model for a large network of "neurons" with a graded response (or sigmoid input-output relation) is studied and collective properties in very close correspondence with the earlier stochastic model based on McCulloch - Pitts neurons are studied.
7.1K