scholarly journals ST-PCNN: Spatio-Temporal Physics-Coupled Neural Networks for Dynamics Forecasting

2021 ◽  
Author(s):  
Yu Huang ◽  
James Li ◽  
Min Shi ◽  
Hanqi Zhuang ◽  
Yufei Tang ◽  
...  
Keyword(s):  
Neural Network ◽  
Temporal Dynamics ◽  
Temporal Correlation ◽  
Current Data ◽  
Ocean Current ◽  
Coupled Neural Networks ◽  
Proposed Model ◽  
Essential Components ◽  
Spatio Temporal ◽  
Learn Physics

Abstract Ocean current, fluid mechanics, and many other physical systems with spatio-temporal dynamics are essential components of the universe. One key characteristic of such systems is that they can be represented by certain physics laws, such as ordinary/partial differential equations (ODEs/PDEs), irrespective of time or location. Physics-informed machine learning has recently emerged to learn physics from data for accurate prediction, but they often lack a mechanism to leverage localized spatial and temporal correlation or rely on hard-coded physics parameters. In this paper, we advocate a physics-coupled neural network model to learn parameters governing the physics of the system, and further couple the learned physics to assist the learning of recurring dynamics. Here a spatio-temporal physics-coupled neural network (ST-PCNN) model is proposed to achieve three goals: (1) learning the underlying physics parameters, (2) transition of local information between spatio-temporal regions, and (3) forecasting future values for the dynamical system. The physics-coupled learning ensures that the proposed model can be tremendously improved by using learned physics parameters, and can achieve useful long-range forecasting (e.g., more than two weeks). Experiments using simulated wave propagation and field-collected ocean current data validate that ST-PCNN outperforms typical deep learning models and existing physics-informed models.

scholarly journals Application of Convolutional Neural Network for Spatiotemporal Bias Correction of Daily Satellite-Based Precipitation

2020 ◽  
Vol 12 (17) ◽  
pp. 2731
Author(s):  
Xuan-Hien Le ◽  
Giha Lee ◽  
Kwansue Jung ◽  
Hyun-uk An ◽  
Seungsoo Lee ◽  
...  
Keyword(s):  
Neural Network ◽  
Standard Deviation ◽  
Convolutional Neural Network ◽  
Bias Correction ◽  
Temporal Correlation ◽  
Precipitation Data ◽  
Climate Data ◽  
Extreme Rainfall Events ◽  
Essential Components ◽  
Deviation Method

Spatiotemporal precipitation data is one of the essential components in modeling hydrological problems. Although the estimation of these data has achieved remarkable accuracy owning to the recent advances in remote-sensing technology, gaps remain between satellite-based precipitation and observed data due to the dependence of precipitation on the spatiotemporal distribution and the specific characteristics of the area. This paper presents an efficient approach based on a combination of the convolutional neural network and the autoencoder architecture, called the convolutional autoencoder (ConvAE) neural network, to correct the pixel-by-pixel bias for satellite-based products. The two daily gridded precipitation datasets with a spatial resolution of 0.25° employed are Asian Precipitation-Highly Resolved Observational Data Integration towards Evaluation (APHRODITE) as the observed data and Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks-Climate Data Record (PERSIANN-CDR) as the satellite-based data. Furthermore, the Mekong River basin was selected as a case study, because it is one of the largest river basins, spanning six countries, most of which are developing countries. In addition to the ConvAE model, another bias correction method based on the standard deviation method was also introduced. The performance of the bias correction methods was evaluated in terms of the probability distribution, temporal correlation, and spatial correlation of precipitation. Compared with the standard deviation method, the ConvAE model demonstrated superior and stable performance in most comparisons conducted. Additionally, the ConvAE model also exhibited impressive performance in capturing extreme rainfall events, distribution trends, and described spatial relationships between adjacent grid cells well. The findings of this study highlight the potential of the ConvAE model to resolve the precipitation bias correction problem. Thus, the ConvAE model could be applied to other satellite-based products, higher-resolution precipitation data, or other issues related to gridded data.

MDTP

2021 ◽  
Vol 14 (8) ◽  
pp. 1289-1297
Author(s):  
Ziquan Fang ◽  
Lu Pan ◽  
Lu Chen ◽  
Yuntao Du ◽  
Yunjun Gao
Keyword(s):  
Neural Network ◽  
Short Term Memory ◽  
Temporal Dynamics ◽  
Real Life ◽  
Feature Modeling ◽  
Traffic Prediction ◽  
Interactive System ◽  
Trajectory Data ◽  
Spatio Temporal ◽  
Prediction Approach

Traffic prediction has drawn increasing attention for its ubiquitous real-life applications in traffic management, urban computing, public safety, and so on. Recently, the availability of massive trajectory data and the success of deep learning motivate a plethora of deep traffic prediction studies. However, the existing neural-network-based approaches tend to ignore the correlations between multiple types of moving objects located in the same spatio-temporal traffic area, which is suboptimal for traffic prediction analytics. In this paper, we propose a multi-source deep traffic prediction framework over spatio-temporal trajectory data, termed as MDTP. The framework includes two phases: spatio-temporal feature modeling and multi-source bridging. We present an enhanced graph convolutional network (GCN) model combined with long short-term memory network (LSTM) to capture the spatial dependencies and temporal dynamics of traffic in the feature modeling phase. In the multi-source bridging phase, we propose two methods, Sum and Concat, to connect the learned features from different trajectory data sources. Extensive experiments on two real-life datasets show that MDTP i) has superior efficiency, compared with classical time-series methods, machine learning methods, and state-of-the-art neural-network-based approaches; ii) offers a significant performance improvement over the single-source traffic prediction approach; and iii) performs traffic predictions in seconds even on tens of millions of trajectory data. we develop MDTP + , a user-friendly interactive system to demonstrate traffic prediction analysis.

Study on Wind Speed Forecasting Based on STC and BP Neural Network

2013 ◽  
Vol 724-725 ◽  
pp. 623-629
Author(s):  
Xing Jie Liu ◽  
Wen Shu Zheng ◽  
Tian Yun Cen
Keyword(s):  
Neural Network ◽  
Wind Speed ◽  
Bp Neural Network ◽  
Prediction Accuracy ◽  
Wind Farm ◽  
Target Prediction ◽  
Temporal Correlation ◽  
Economic Security ◽  
Wind Speed Forecasting ◽  
Spatio Temporal

Accurate wind speed forecasting of wind farm is of great significance in economic security and stability of the grid. In order to improve the prediction accuracy, the paper first proposed a spatio-temporal correlation predictor method. Based on physical characteristics of wind speed evolution, the method looked for the wind speed and direction information at sites close to the target prediction site, and established STCP model to forecast. And then we established the BP neural network to finish multi-step forecast with wind speed time series of target forecast site .Last, two methods were combined to form STCP-BP method. Simulation tests are conducted with operation data from certain wind farm group in China and results show that STCP-BP method can effectively improve the prediction accuracy compared with BP model.

scholarly journals HIERARCHICAL SPATIO-TEMPORAL DYNAMICS OF A CHAOTIC NEURAL NETWORK FOR MULTISTABLE BINOCULAR RIVALRY

2009 ◽  
Vol 05 (01) ◽  
pp. 123-134 ◽  
Author(s):  
YUTA KAKIMOTO ◽  
KAZUYUKI AIHARA
Keyword(s):  
Neural Network ◽  
Binocular Rivalry ◽  
Temporal Dynamics ◽  
Visual Images ◽  
Chaotic Neural Network ◽  
Perceptual Alternation ◽  
Spatio Temporal ◽  
Characteristic Features ◽  
The Brain ◽  
Special Case

Binocular rivalry is perceptual alternation that occurs when different visual images are presented to each eye. Despite the intensive studies, the mechanism of binocular rivalry still remains unclear. In multistable binocular rivalry, which is a special case of binocular rivalry, it is known that the perceptual alternation between paired patterns is more frequent than that between unpaired patterns. This result suggests that perceptual transition in binocular rivalry is not a simple random process, and the memories stored in the brain can play an important role in the perceptual transition. In this study, we propose a hierarchical chaotic neural network model for multistable binocular rivalry and show that our model reproduces some characteristic features observed in multistable binocular rivalry.

scholarly journals A Generative Model for Dynamic Networks with Applications

2019 ◽  
Vol 33 ◽  
pp. 7842-7849
Author(s):  
Shubham Gupta ◽  
Gaurav Sharma ◽  
Ambedkar Dukkipati
Keyword(s):  
Neural Network ◽  
Social Networks ◽  
Real World ◽  
Link Prediction ◽  
Temporal Dynamics ◽  
Dynamic Networks ◽  
Collaboration Networks ◽  
Proposed Model ◽  
Latent Space ◽  
Over Time

Networks observed in real world like social networks, collaboration networks etc., exhibit temporal dynamics, i.e. nodes and edges appear and/or disappear over time. In this paper, we propose a generative, latent space based, statistical model for such networks (called dynamic networks). We consider the case where the number of nodes is fixed, but the presence of edges can vary over time. Our model allows the number of communities in the network to be different at different time steps. We use a neural network based methodology to perform approximate inference in the proposed model and its simplified version. Experiments done on synthetic and real world networks for the task of community detection and link prediction demonstrate the utility and effectiveness of our model as compared to other similar existing approaches.

scholarly journals Tracklet Pair Proposal and Context Reasoning for Video Scene Graph Generation

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3164
Author(s):  
Gayoung Jung ◽  
Jonghun Lee ◽  
Incheol Kim
Keyword(s):  
Neural Network ◽  
High Performance ◽  
Sliding Window ◽  
Temporal Context ◽  
Scene Graph ◽  
Context Reasoning ◽  
Proposed Model ◽  
Video Scene ◽  
Spatio Temporal ◽  
Graph Generation

Video scene graph generation (ViDSGG), the creation of video scene graphs that helps in deeper and better visual scene understanding, is a challenging task. Segment-based and sliding-window based methods have been proposed to perform this task. However, they all have certain limitations. This study proposes a novel deep neural network model called VSGG-Net for video scene graph generation. The model uses a sliding window scheme to detect object tracklets of various lengths throughout the entire video. In particular, the proposed model presents a new tracklet pair proposal method that evaluates the relatedness of object tracklet pairs using a pretrained neural network and statistical information. To effectively utilize the spatio-temporal context, low-level visual context reasoning is performed using a spatio-temporal context graph and a graph neural network as well as high-level semantic context reasoning. To improve the detection performance for sparse relationships, the proposed model applies a class weighting technique that adjusts the weight of sparse relationships to a higher level. This study demonstrates the positive effect and high performance of the proposed model through experiments using the benchmark dataset VidOR and VidVRD.

scholarly journals Spatiotemporal Multi-Graph Convolution Network for Ride-Hailing Demand Forecasting

2019 ◽  
Vol 33 ◽  
pp. 3656-3663 ◽  
Author(s):  
Xu Geng ◽  
Yaguang Li ◽  
Leye Wang ◽  
Lingyu Zhang ◽  
Qiang Yang ◽  
...  
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Traffic Congestion ◽  
Large Scale ◽  
Contextual Information ◽  
Demand Forecasting ◽  
Wait Time ◽  
Temporal Correlation ◽  
Gating Mechanism ◽  
Proposed Model

Region-level demand forecasting is an essential task in ridehailing services. Accurate ride-hailing demand forecasting can guide vehicle dispatching, improve vehicle utilization, reduce the wait-time, and mitigate traffic congestion. This task is challenging due to the complicated spatiotemporal dependencies among regions. Existing approaches mainly focus on modeling the Euclidean correlations among spatially adjacent regions while we observe that non-Euclidean pair-wise correlations among possibly distant regions are also critical for accurate forecasting. In this paper, we propose the spatiotemporal multi-graph convolution network (ST-MGCN), a novel deep learning model for ride-hailing demand forecasting. We first encode the non-Euclidean pair-wise correlations among regions into multiple graphs and then explicitly model these correlations using multi-graph convolution. To utilize the global contextual information in modeling the temporal correlation, we further propose contextual gated recurrent neural network which augments recurrent neural network with a contextual-aware gating mechanism to re-weights different historical observations. We evaluate the proposed model on two real-world large scale ride-hailing demand datasets and observe consistent improvement of more than 10% over stateof-the-art baselines.

Sign in / Sign up

Export Citation Format

Share Document