VincLee8188/Spatio-temporal-forecasting-PyTorch
Leverage on recent advances in graph convolution and sequence modeling to design neural networks for spatio-temporal forecasting, which including the use of graph convolutional neural networks, gated recurrent units and transformers.
This project helps operations engineers and urban planners predict how conditions will change across a network over time. For example, it can take historical traffic sensor data from different road segments and predict future traffic flows or speeds across those same segments. This allows for better resource allocation and proactive decision-making in complex, interconnected systems.
No commits in the last 6 months.
Use this if you need to forecast how a system's state, like traffic or environmental conditions, will evolve across various interconnected locations over time.
Not ideal if your data doesn't have a clear spatial relationship that can be represented as a network or graph.
Stars
26
Forks
3
Language
Python
License
—
Category
Last pushed
Oct 06, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/VincLee8188/Spatio-temporal-forecasting-PyTorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
amazon-science/chronos-forecasting
Chronos: Pretrained Models for Time Series Forecasting
SalesforceAIResearch/uni2ts
Unified Training of Universal Time Series Forecasting Transformers
moment-timeseries-foundation-model/moment
MOMENT: A Family of Open Time-series Foundation Models, ICML'24
ServiceNow/TACTiS
TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series, from...
yotambraun/APDTFlow
APDTFlow is a modern and extensible forecasting framework for time series data that leverages...