A novel spatiotemporal convolutional long short-term neural network for air pollution prediction

Wen, Congcong; Liu, Shufu; Yao, Xiaojing; Peng, Ling; Li, Xiang; Hu, Yuan; Chi, Tianhe

doi:10.1016/j.scitotenv.2018.11.086

Cited by 329 publications

(155 citation statements)

References 52 publications

Supporting

Mentioning

146

Contrasting

Unclassified

Order By: Relevance

“…In recent years, one of the most prevalent types of artificial intelligence algorithms (i.e., deep learning methods) has achieved great success in various real-world applications, including image classification, speech recognition, time series prediction, natural language processing and so on (LeCun et al, 2015;Chan et al, 2015;Hinton et al, 2012;Wen et al, 2019;Collobert and Weston, 2008;Li et al, 2016Li et al, , 2018. Following this trend, researchers have shifted their focus towards learning-based approaches and, more specifically, to deep neural networks (Qi et al, 2016;Su et al, 2015;Qi et al, 2017a,b) for learning 3D local descriptors.…”

Section: Introductionmentioning

confidence: 99%

Directionally constrained fully convolutional neural network for airborne LiDAR point cloud classification

Wen

Yang

et al. 2020

ISPRS Journal of Photogrammetry and Remote Sensing

Self Cite

102

View full text Add to dashboard Cite

Point cloud classification plays an important role in a wide range of airborne light detection and ranging (LiDAR) applications, such as topographic mapping, forest monitoring, power line detection, and road detection. However, due to the sensor noise, high redundancy, incompleteness, and complexity of airborne LiDAR systems, point cloud classification is challenging. Traditional point cloud classification methods mostly focus on the development of handcrafted point geometry features and employ machine learning-based classification models to conduct point classification. In recent years, the advances of deep learning models have caused researchers to shift their focus towards machine learning-based models, specifically deep neural networks, to classify airborne LiDAR point clouds. These learning-based methods start by transforming the unstructured 3D point sets to regular 2D representations, such as collections of feature images, and then employ a 2D CNN for point classification. Moreover, these methods usually need to calculate additional local geometry features, such as planarity, sphericity and roughness, to make use of the local structural information in the original 3D space. Nonetheless, the 3D to 2D conversion results in information loss. In this paper, we proposed a directionally constrained fully convolutional neural network (D-FCN) that can take the original 3D coordinates and LiDAR intensity as input; thus, it can directly apply to unstructured 3D point clouds for semantic labeling. Specifically, we first introduce a novel directionally constrained point convolution (D-Conv) module to extract locally representative features of 3D point sets from the projected 2D receptive fields. To make full use of the orientation information of neighborhood points, the proposed D-Conv module performs convolution in an orientation-aware manner by using a directionally constrained nearest neighborhood search. Then, we designed a multiscale fully convolutional neural network with downsampling and upsampling blocks to enable multiscale point feature learning. The proposed D-FCN model can therefore process input point cloud with arbitrary sizes and directly predict the semantic labels for all the input points in an end-to-end manner. Without involving additional geometry features as input, the proposed method has demonstrated superior performance on the International Society for Photogrammetry and Remote Sensing (ISPRS) 3D labeling benchmark dataset. The results show that our model has achieved a new state-of-the-art level of performance with an average F1 score of 70.7%, and it has improved the performance by a large margin on categories with a small number of points (such as powerline, car, and facade).

show abstract

Section: Introductionmentioning

confidence: 99%

Directionally constrained fully convolutional neural network for airborne LiDAR point cloud classification

Wen

Yang

et al. 2020

ISPRS Journal of Photogrammetry and Remote Sensing

Self Cite

102

View full text Add to dashboard Cite

show abstract

“…Bunların yanında finans piyasalarında hisse senetlerinin fiyat tahminleri LSTM algoritmasının performansı incelenmiştir [16,17]. Son yıllarda literatürde, hava kirliliği tahmini, su kalitesinin tahmini ve ozon gazları yoğunluğunun tahmini gibi çevresel zaman serisi problemlerinde tahmin doğrululuğun yüksekliğinden dolayı LSTM yaklaşımı tercih edilmiştir [3,18]. Qing ve Niu [19] yaptıkları çalışmada, saatlik güneş ışınımı değerlerinin tahmini LSTM yöntemi kullanmışlar ve girdi verileri olarak aynı zaman dilimine ait hava tahmin değerleri kullanılmıştır.…”

Section: İlgi̇li̇ çAlişmalar (Related Work)unclassified

“…Yapay zekâ alanında son yıllarda üzerinde durulan yeni bir makine öğrenme yöntemi olan derin öğrenme, büyük miktarda verilerden etkili özellik temsillerinin öğrenilmesine katkı sağlayan etkin algoritmalar sunmaktadır [3]. Derin öğrenme modelleri, özellikle hisse senedi fiyat tahmini, hava kirliliği tahmini ve enerji fiyatları tahmini gibi zaman serileri tahmini problemlerinde yoğun bir şekilde kullanılmaktadır.…”

Section: Gi̇ri̇ş (Introduction)unclassified

Uzun-Kısa Süreli Bellek Ağı Kullanarak Global Güneş Işınımı Zaman Serileri Tahmini

Kara

2019

Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım Ve Teknoloji

View full text Add to dashboard Cite

In this study, it is proposed a deep neural network approach, which has the capability to extract superior features on complex and nonlinear time series data, for forecasting global solar irradiance more accurately. This approach has also been used to expose both the relationship between input data and output data, as well as the contribution of input data to the output data. Figure A. The box plot of solar irradiance (a) Year (b) Quarter. Purpose: In this study, it is aimed to develop an accurate and effective prediction model using the LSTM neural network due to a rapidly growing interest in solar power generation. It is aimed to reveal that the proposed model based on a deep learning approach outperforms compared to machine learning models and statistical models. Theory and Methods: To overcome the complexity and nonlinearity issues in time series forecasting, the LSTM neural network that is a variation of the recurrent neural network is used to predict daily global solar irradiance. The effectiveness of the suggested method is compared with the state of the art machine learning algorithms such as Decision Tree Regression, Random Forest Regression, Gradient Boosting, and K-Nearest Neighbor. Results: To evaluate the performance of the proposed model for daily global solar irradiance, it is compared by four metrics comprising MAE, RMSE, MAPE, and r2. The results have shown that the proposed LSTM model is more effective and superior according to the other benchmark models. Conclusion: In this study, it has been suggested a deep LSTM model based on deep learning for forecasting daily global solar irradiance more accurately. The presented LSTM model can extract quality features that represent sophisticated and nonlinear characteristics of time series data. Also, it has been indicated that the proposed model is a robust and useful model compared with stateof-the-art machine learning models.

show abstract

“…In recent years, LSTM algorithms have achieved good research results in the field of simulation and prediction of the evolution process of air pollutant particle concentration, and the representative algorithms include: LSTM method and evaluation algorithm [18], ensemble-LSTM algorithm [19], CNN-LSTM algorithm [20], LSTM-FC algorithm [21]; LSTM algorithms based on air pollutant particle concentration characteristics: GC-LSTM algorithm [22], spatiotemporal convolutional LSTM algorithm [23]; LSTM algorithm based on deep learning: DL-LSTM algorithm [24], Multi-output DL-LSTM algorithm [25]; Deep DL-LSTM algorithm [26]. Algorithms of this type took the LSTM algorithm as the core, starting from the structural characteristics of the research object, they improved the LSTM algorithm to effectively simulate the evolution process of the concentration of atmospheric pollutant particles and improve the prediction performance of the algorithm, moreover, based on data analysis, they introduced CNN, FC, GC, DL, and other algorithms to optimize the input data and preliminarily explored the spatial correlation of the evolution process of particle concentration.…”

Section: Introductionmentioning

confidence: 99%

Spatial-Temporal Correlation-Based LSTM Algorithm and Its Application in PM2.5 Prediction

Zhao¹

2020

RIA

View full text Add to dashboard Cite

In existing researches, the algorithms for simulating and predicting the evolution process of air pollutant particle concentration have neither explored the spatial correlation of particle concentration in depth, nor achieved the fusion of the time dependence and the spatial correlation of the particle concentration. To this end, this paper proposes the longshort term memory network (LSTM) algorithm based on spatiotemporal fusion. First, the spatial correlation, the relevant factors and the calculation methods are proposed; then, the local spatial correlation factors are combined with the forget gate and the remember gate of the LSTM algorithm to construct a LSTM algorithm based on local spatial information and spatial-temporal correlation, namely the LTS-LSTM; after that, the learning result of LTS-LSTM is combined with the global spatial correlation factors to construct a LSTM algorithm based on global spatial information and spatial-temporal correlation, namely the GTS-LSTM; at last, the proposed algorithm is adopted to simulate the global and local air pollution particle concentration evolution process, and predict the particle concentration. On the global and local observation dataset, the proposed algorithm is compared with the regression algorithm, support vector machine (SVM), fuzzy neural network (FNN), LSTM neural network, GC-LSTM neural network, and DL-LSTM neural network. The comparison results show that: in terms of air particle concentration prediction, the performance of the proposed algorithm outperforms other traditional prediction algorithms, and its performance is close to the deep LSTM algorithms.

show abstract

A novel spatiotemporal convolutional long short-term neural network for air pollution prediction

Cited by 329 publications

References 52 publications

Directionally constrained fully convolutional neural network for airborne LiDAR point cloud classification

Directionally constrained fully convolutional neural network for airborne LiDAR point cloud classification

Uzun-Kısa Süreli Bellek Ağı Kullanarak Global Güneş Işınımı Zaman Serileri Tahmini

Spatial-Temporal Correlation-Based LSTM Algorithm and Its Application in PM2.5 Prediction

Contact Info

Product

Resources

About