time seriesfamily
TimesNet
General time series model for forecasting, imputation, classification and anomaly detection that models variation within and across periods in 2D. Paper by Wu et al. (2022).
Levelfamily
Classtime series
Parametersnot in the notes
Contextnot in the notes
Released5 Oct 2022
Opennessopen source
Runs onnot in the notes
Statusactive
R&D Topics
Identity
- Developer
- Tsinghua University
- Family
- not in the notes
- Released
- 5 Oct 2022 sourcesannouncement page
- Weights published
- –
- Record checked
- 12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- CNN Reshapes 1D series into 2D by period and applies 2D convolution
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- time series
- Output
- time series
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open source
- Licence
- MIT License sources
- Access routes
- not in the notes
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- Licence is that of thuml/Time-Series-Library (MIT).
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
DeveloperTsinghua Universityuniversity, China
Tsinghua Universityuniversity, ChinaModelTimesNetTsinghua University, time series
TimesNetTsinghua University, time seriesR&D TopicsDeep Learning Architectures for Time-Series Forecasting and ClassificationAnomaly Detection and Predictive Maintenance on Sensor Data
Use CasesAnomaly Detection on Sensor, SCADA and Historian DataIndustrialIndustrial Forecasting (Load, Throughput, Demand)IndustrialDemand ForecastingRetail and LogisticsPharma Manufacturing and GMPHealthcare+1 moreUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs It
PT Kalbe Farma TbkProof of concept, 20 Jul 2026
PT Pertamina Hulu Rokan (PHR)In production, 17 Oct 2025
PT Kilang Pertamina InternasionalIn production, 17 Oct 2025PT Pertamina International Shipping with Pertamina Marine EngineeringPlanned, 9 Dec 2024+10 moreDeployments of these use cases; none names this model.
PT Kalbe Farma TbkProof of concept, 20 Jul 2026PT Pertamina Hulu Rokan (PHR)In production, 17 Oct 2025PT Kilang Pertamina InternasionalIn production, 17 Oct 2025PT Pertamina International Shipping with Pertamina Marine EngineeringPlanned, 9 Dec 2024+10 moreDeployments of these use cases; none names this model.Organisations 1
R&D topics 2
Deep Learning Architectures for Time-Series Forecasting and ClassificationDesigning neural architectures, from transformers to simple linear and MLP models, for fo…produced byAnomaly Detection and Predictive Maintenance on Sensor DataDetecting abnormal behaviour in machine and process sensor time series to warn of faults…produced by
Sources
- arxiv.org/abs/2210.02186 https://arxiv.org/abs/2210.02186
- github.com/thuml/Time-Series-Library https://github.com/thuml/Time-Series-Library
- nixtlaverse.nixtla.io/neuralforecast/docs/capabilities/overview.html https://nixtlaverse.nixtla.io/neuralforecast/docs/capabilities/overview.html
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "TimesNet", https://aurion.semai.id/models/timesnet/, records of October 2026.