Agriculture
Oil Palm Yield Prediction
Tree ensembles and biophysical crop models with satellite indices.
Named Models
PySawit (enhanced)EOS Data Analytics (EOSDA)Releasednot in the notesRuns onnot in the notesClassgeospatialEOSDA oil palm yield model; vendor claims accuracy raised from 78% to up to 90% on an unnamed Indonesian estate.Commercial use: proprietary terms; Jakarta hosting: unknown; Indonesian support: not statedExtra Trees oil palm yield model (JOPR 2025)not in the notesReleased2025Runs onnot in the notesClasstabularAcademic oil palm yield model on Pahang agromet data 1986 to 2020; R2 0.88 (ET) vs 0.79 RF, 0.78 GB, 0.41 LR (Khan, Kamaruddin, Sheikh, Rahman, Bakht, Malaysia).Commercial use: not stated; Jakarta hosting: unknown; Indonesian support: not statedWhere this comes from
Models the research names for this use case. Research, with sources on each model record.
Who Runs It
production, 2
PT Astra Agro Lestari TbkCountry: IndonesiaTIARA (TBS Prediksi Astra), AI application predicting fresh fruit bunch production (model not stated)Vendor: not statedproductionDate21 Sep 2026Named as an example in use by a GAPKI board member, not by Astra; no results statedEvidence: independent reportConfidence: highSource: selular.id, astra-agro.co.id
Unnamed Indonesian estate (15,000 to 17,000 ha)Country: IndonesiaPySawit (enhanced)Vendor: EOSDAproductionDate2024
Accuracy raised from 78% to up to 90% (vendor claim), season 2024 to 2025Evidence: company statementConfidence: lowSource: eos.com
Where this comes from
Documented uses by named organisations. The evidence column says who made the claim.
Candidate Models
TabArena: All Tasks, no imputation, snapshot 2026-05-06, 59 entries
A general benchmark for this model class, not a test on this use case. Elo across tabular tasks, anchored RandomForest default = 1000; TabPFN-lab researchers are involved. Higher is better. Elo has no zero, so the axis starts at 1,200. Showing 10 of 13.
AutoGluon 1.5Amazon maintainer-run1,700
TabPFN-2.6Prior Labs maintainer-run1,626RealTabPFN-2.5Prior Labs maintainer-run1,604
TabICL v2INRIA maintainer-run1,598RealMLPINRIA maintainer-run1,514
TabDPTLayer 6 AI maintainer-run1,460
TabMYandex maintainer-run1,448
LightGBMMicrosoft AI maintainer-run1,435CatBoostYandex maintainer-run1,418
XGBoostDMLC community maintainer-run1,3761,2001,5001,800
XGBoostDMLC community, tabularReleasedAug 2026open weightshas scoreslast 18 monthsLightGBMMicrosoft AI, tabularReleasedJul 2026open weightshas scoreslast 18 monthsTabPFN-2.6Prior Labs, tabularReleasedMar 2026open weightshas scoreslast 18 monthsCatBoostYandex, tabularReleasedFeb 2026open weightshas scoreslast 18 monthsAutoGluon 1.5Amazon, tabularReleased2026open weightshas scoreslast 18 monthsTabICL v2INRIA, tabularReleased2026open weightshas scoreslast 18 monthsRealTabPFN-2.5Prior Labs, tabularReleasedNov 2025open weightshas scoreslast 18 months
SAP-RPT-OSS (sap-rpt-1-oss)SAP, tabularReleasedJun 2025open weightshas scoreslast 18 months
DINOv3 SAT-493M ViT-7BMeta, geospatialReleasedAug 2025open weightslast 18 monthsDINOv3 SAT-493M ViT-L (distilled)Meta, geospatialReleasedAug 2025open weightslast 18 monthsShowing 10 of 64. 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.
Links
Models 2
Sources
- PREDICTION OF OIL PALM YIELD USING MACHINE LEARNING: COMPARISON OF LINEAR AND NON-LINEAR ALGORITHMS WITH MULTIVARIATE TIME SERIES DATA ̵ jopr.mpob.gov.my https://jopr.mpob.gov.my/prediction-of-oil-palm-yield-using-machine-learning-comparison-of-linear-and-non-linear-algorithms-with-multivariate-time-series-data/
- How EOSDA Enhanced PySawit Model To Help Oil Palm Industry eos.com https://eos.com/blog/eosda-enhanced-pysawit-model-to-improve-its-accuracy/
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Oil Palm Yield Prediction", https://aurion.semai.id/usecases/ag-yield-prediction/, records of October 2026.