Project AURIONAI Use-Cases Research & Innovation
Industrial

Industrial Forecasting (Load, Throughput, Demand)

Time-series foundation models, gradient boosting and classical statistics.

time series
7named models
62candidates
0deployments
0in Indonesia

Named Models

AmazonChronos-2AmazonReleasedOct 2025Runs onsingle datacentre GPU, CPU serverClasstime seriesAmazon (AWS AI) zero-shot forecasting model with covariate in-context learning; report 17 Oct 2025. Context is 8,192 time steps.Commercial use: allowed; Jakarta hosting: unknown; Indonesian support: not statedGoogleTimesFM 2.5GoogleReleasedSep 2025Runs onsingle datacentre GPU, CPU serverClasstime seriesTimesFM version behind BigQuery AI.FORECAST that 3.0 is planned to replace (implied).Commercial use: allowed; Jakarta hosting: unknown; Indonesian support: not statedGoogleTimesFM 3.0GoogleReleasedAug 2026Runs onsingle datacentre GPUClasstime seriesGoogle Research multivariate time-series foundation model; best single zero-shot model (rank 14 of 143) on the GIFT-Eval leaderboard rebuilt from its raw results. Code Apache, weights non-commercial.Commercial use: non-commercial; Jakarta hosting: unknown; Indonesian support: not statedHuawei (Huawei Cloud)Pangu Prediction ModelHuawei (Huawei Cloud)Releasednot in the notesRuns onnot in the notesClasstime seriesHuawei forecasting model used for Conch Cement clinker strength (3- and 28-day) and Shenzhen Energy wind and solar yield.Commercial use: proprietary terms; Jakarta hosting: unknown; Indonesian support: not statedIBMGranite FlowStateIBMReleasednot in the notesRuns onCPU serverClasstime seriesGranite FlowStateIBM forecasting model, #3 on GIFT-Eval as of 2 Oct 2025 per IBM docs. Licence unverified.Commercial use: not stated; Jakarta hosting: unknown; Indonesian support: not statedIBMGranite TinyTimeMixer (TTM) r2IBMReleased2024Runs onCPU server, laptopClasstime seriesGranite TinyTimeMixer (TTM) r2IBM tiny forecasting model for CPU-only machines; vendor claims to beat larger models, but GIFT-Eval ranks TTM-R2 140 of 143 with test leakage flagged.Commercial use: allowed; Jakarta hosting: unknown; Indonesian support: not statedSalesforceMoirai 2.0SalesforceReleasedAug 2025Runs onCPU server, embedded GPUClasstime seriesSalesforce AI Research time-series foundation model; report revised 3 Feb 2026. CC BY-NC per secondary source; not stated in paper.Commercial use: non-commercial; Jakarta hosting: unknown; Indonesian support: not stated
Where this comes from
Models the research names for this use case. Research, with sources on each model record.

Who Runs It

No deployment is recorded for this use case.

Where this comes from
Documented uses by named organisations. The evidence column says who made the claim.

Candidate Models

TSB-AD

A general benchmark for this model class, not a test on this use case. Time-series anomaly detection, 1,070 series from 40 datasets (VUS-PR); NeurIPS 2024; open to community submissions from 1 Apr 2026. Higher is better.

Sungkyunkwan UniversityPaAnoSungkyunkwan University vendor-reported0.53(Sub)-PCA independent0.42Carnegie Mellon UniversityMOMENT (MOMENT-1-large)Carnegie Mellon University independent0.39DeepAnT independent0.31OmniAnomaly maintainer-run0.31PCA independent0.31
00.51
DatadogToto 2.0 1BDatadog, time seriesReleasedJun 2026open weightshas scoreslast 18 monthsDatadogToto 2.0 2.5BDatadog, time seriesReleasedJun 2026open weightshas scoreslast 18 monthsDatadogToto 2.0 313MDatadog, time seriesReleasedJun 2026open weightshas scoreslast 18 monthsIBMGranite PatchTST-FM r1IBM, Rensselaer Polytechnic Institute, time seriesReleasedMar 2026open weightshas scoreslast 18 monthsSalesforceMoirai 2.0 smallSalesforce, time seriesReleasedNov 2025open weightshas scoreslast 18 monthsIBMFlowState r1.1IBM, time seriesReleasedSep 2025open weightshas scoreslast 18 monthsNX-AITiRexNX-AI, time seriesReleasedMay 2025open weightshas scoreslast 18 monthsIBMGranite TSPulseIBM, time seriesReleasedMay 2025open weightshas scoreslast 18 monthsNX-AITiRex-2NX-AI, time seriesReleasedJun 2026has scoreslast 18 monthsDatadogToto 2.0 22MDatadog, time seriesReleasedJun 2026open weightslast 18 months

Showing 10 of 62. All models of this class

Where this comes from
Derived, not researched: models in the directory whose class matches a class this use case uses, excluding family records and models shut down or deprecated. Ranked by how many fit facts they meet, then by release date. Each fit fact is read from the model record.

Sources

  1. Granite Time Series | IBM Granite ibm.com https://www.ibm.com/ae-ar/granite/docs/models/time-series/
  2. Introducing Chronos-2: From univariate to universal forecasting amazon.science https://www.amazon.science/blog/introducing-chronos-2-from-univariate-to-universal-forecasting
  3. google/timesfm-2.5-200m-pytorch , Hugging Face huggingface.co https://huggingface.co/google/timesfm-2.5-200m-pytorch
  4. Google TimesFM-3 voegt multivariate forecasting toe datanorth.ai https://datanorth.ai/nl/nieuws/google-lanceert-timesfm-3
  5. Introducing Moirai 2.0 salesforce.com https://www.salesforce.com/blog/moirai-2-0/
  6. aimagazine.com/articles/how-huawei-pangu-5-5-ai-models-trans... https://aimagazine.com/articles/how-huawei-pangu-5-5-ai-models-transform-industry-operations

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Industrial Forecasting (Load, Throughput, Demand)", https://aurion.semai.id/usecases/ind-forecasting/, records of October 2026.