edouardelasalles/stnn
Code for the paper "Spatio-Temporal Neural Networks for Space-Time Series Modeling and Relations Discovery"
This project helps researchers and scientists forecast complex changes across many interacting locations over time, such as temperature variations or environmental pollutants. It takes in historical measurements from different spatial points over time, along with information on how these points are physically connected. The output is a prediction of future values and an understanding of the underlying relationships driving these changes. This tool is ideal for scientists, environmental modelers, or urban planners dealing with interconnected sensor data.
121 stars. No commits in the last 6 months.
Use this if you need to predict future values for interconnected spatial locations and also want to uncover the hidden influences between these locations.
Not ideal if your data points are completely independent of each other, or if you only need simple time series forecasting without considering spatial interactions.
Stars
121
Forks
43
Language
Jupyter Notebook
License
BSD-2-Clause
Category
Last pushed
Aug 31, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/edouardelasalles/stnn"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
zeiss-microscopy/OAD
Collection of tools and scripts useful to automate microscopy workflows in ZEN Blue using Python...
median-research-group/LibMTL
A PyTorch Library for Multi-Task Learning
qdrant/quaterion
Blazing fast framework for fine-tuning similarity learning models
lucidrains/PoPE-pytorch
Efficient implementation (and explorations) into polar coordinate positional embedding (PoPE) -...
MR-HosseinzadehTaher/BenchmarkTransferLearning
Official PyTorch Implementation and Pre-trained Models for Benchmarking Transfer Learning for...