Water Quality Forecasting

Introduction

The task for this dataset is to forecast the spatio-temporal traffic volume based on the historical traffic volume and other features in neighboring locations. Specifically, the traffic volume is measured every 15 minutes at 36 sensor locations along two major highways in Northern Virginia/Washington D.C. capital region. The 47 features include: 1) the historical sequence of traffic volume sensed during the 10 most recent sample points (10 features), 2) week day (7 features), 3) hour of day (24 features), 4) road direction (4 features), 5) number of lanes (1 feature), and 6) name of the road (1 feature). The goal is to predict the traffic volume 15 minutes into the future for all sensor locations. With a given road network, we know the spatial connectivity between sensor locations.

Processsed Data

Download link: [Dataset]

Data format: *.mat (use Matlab to open)

Data description:

Variable Name
 Type Size

Description
tra_X_te array of matrices 1*840 test set input data: traffic indices for 840 contiguous quarter-hours
  • each element is a 36*48 matrix: 36 spatial locations by 48 features
tra_X_tr array of matrices 1*1261 training set input data: traffic indices for 1261 contiouous quarter-hours
  • each element is a 36*48 matrix: 36 spatial locations by 48 features
tra_Y_te array of matrices 36*840 test set output data: traffic flowfor 36 locations in 840 contiguous quarter-hours
from 2017-01-02 00:00
tra_Y_tr array of matrices 36*1261 training set output data: traffic flowfor 36 locations in 1261 contiouous quarter-hours
until 2017-02-01 00:15
tra_adj_mat squared matrix 36*36 adjacency matrix denoting the spatial connectivity of traffic network among 36 locations

Citation

To use these datasets, please cite the papers:

Liang Zhao, Olga Gkountouna, and Dieter Pfoser. 2019. Spatial Auto-regressive Dependency Interpretable Learning Based on Spatial Topological Constraints. ACM Trans. Spatial Algorithms Syst. 5, 3, Article 19 (August 2019), 28 pages. DOI:https://doi.org/10.1145/3339823

Acknowledgement

 

NSF 1755850 (sole-PI): "CRII: III: Interpretable Models for Spatio-Temporal Event Forecasting using Social Sensors", $174,990. 2018-2021, National Science Foundation.