Transformers

Timeseries forecasting with Transformers

Table

⚠️ ❌ means not yet begun

Model	Description	Link	Status
Informer2020	Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting (AAAI'21 Best Paper)	zhouhaoyi/Informer2020: The GitHub repository for the paper "Informer" accepted by AAAI 2021.	❌
Transformer from darts		Transformer Model — darts documentation (unit8co.github.io)	✔️
Temporal Fusion Transformer	Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting	mattsherar/Temporal_Fusion_Transform: Pytorch Implementation of Google's TFT (github.com)	❌
Temporal Fusion Transformer from darts	Temporal Fusion Transformer — darts documentation (unit8co.github.io)	foo	❌
Temporal Fusion Transformer from neuralforecast	neuralforecast - Temporal Fusion Transformers (nixtla.github.io)	foo	❌
Transformers in Time Series	A professionally curated list of awesome resources (paper, code, data, etc.) on Transformers in Time Series, which is first work to comprehensively and systematically summarize the recent advances of Transformers for modeling time series data to the best of our knowledge.	qingsongedu/time-series-transformers-review: A professionally curated list of awesome resources (paper, code, data, etc.) on transformers in time series. (github.com)	❌

The latest notebook can be found over here: Link

1. Darts Transformer
   1. Forecasting using influent data itself
   2. Forcasting using influent as input, effluent as output
2. BSM1 Transformer model
   1. With all covariates (using influent as input, effluent as output)
   2. With only varying covariates (using influent as input, effluent as output)
3. BSM2 Model
   1. With all covariates (using influent as input, effluent as output)