Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 8 min ago
Peer-reviewedCC BYEarth system science data

CY-Bench: a comprehensive benchmark dataset for sub-national crop yield forecasting

  • Michiel Kallenberg1
  • Dilli Paudel2
  • Stella Ofori-Ampofo3
  • Hilmy Baja2
  • Ron van Bree2
  • Aike Potze2
  • Pratishtha Poudel4
  • Abdelrahman Saleh5
  • Weston Anderson6
  • Malte von Bloh3
  • Andres Castellano7
  • Oumnia Ennaji8
21 more authors
  • Raed Hamed9
  • Rahel Laudien10
  • Donghoon Lee11
  • Inti Luna12
  • Dainius Masiliū̄nas13
  • Michele Meroni14
  • Janet Mumo Mutuku15
  • Siyabusa Mkuhlani16
  • Jonathan Richetti17
  • Alex C. Ruane7
  • Ritvik Sahajpal6
  • Guanyuan Shuai6
  • Vasileios Sitokonstantinou2
  • Rogério de Souza Nóia Júnior
  • Amit Kumar Srivastava18
  • Robert Strong19
  • Lily‐belle Sweet20
  • Petar Vojnović21
  • Allard J. W. de Wit22
  • Maximilian Zachow23
  • Ioannis N. Athanasiadis2
23 affiliations
  1. 1Wageningen University & Research (Wageningen, Netherlands)
  2. 2Artificial Intelligence Group, Wageningen University and Research, P.O. Box 16, Wageningen, 6700 AA, the Netherlands
  3. 3Chair of Data Science in Earth Observation, Technical University of Munich, Arcisstraße 21, Munich, 80333, Germany
  4. 4Department of Agronomy, Purdue University, 915 Mitch Daniels Blvd, West Lafayette, IN 47907, United States
  5. 5Department of Soil Science, University of Manitoba, 13 Freedman Crescent, Winnipeg, MB R3T 2N2, Canada
  6. 6Department of Geographical Sciences, University of Maryland, 7251 Preinkert Drive, Collega Park, MD 20742, United States
  7. 7GISS Impacts Group, NASA Goddard Institute for Space Studies, 535 West 116th Street, Mail Code 4312, New York, NY 10027, United States
  8. 8College of Computing, Mohammed VI Polytechnic University, Lot 660, Benguerir, 43150, Morocco
  9. 9Institute for Environmental Studies, Vrije Universiteit Amsterdam, De Boelelaan 1105, Amsterdam, 1081 HV, the Netherlands
  10. 10Department of Climate Resilience, Potsdam Institute for Climate Impact Research, P.O. Box 60 12 03, Potsdam, 4412, Germany
  11. 11Department of Civil Engineering, University of Manitoba, 15 Gillson Street, Winnipeg, MB R3T 5V6, Canada
  12. 12Image Processing Laboratory, Universitat de València, C/Catedràtic Agustín Escardino Benlloch, 9, València, 46980, Spain
  13. 13Laboratory of Geo-Information Science and Remote Sensing, Wageningen University and Research, P.O. Box 47, Wageningen, 6700 AA, the Netherlands
  14. 14Seidor Consulting, Carrer dels Provençals 44, Barcelona, 08019, Spain
  15. 15West and Central Africa Region Hub, International Crops Research Institute for the Semi-Arid Tropics, P.O. Box 320, Bamako, Mali
  16. 16Natural Resources Management, International Institute of Tropical Agriculture, P.O. Box 30677, Nairobi, 00100, Kenya
  17. 17Agriculture and Food, Commonwealth Scientific and Industrial Research Organisation (CSIRO), 147 Underwood Av, Perth, WA 6014, Australia
  18. 18Simulation and Data Science- Multiscale modelling and Forecasting, Leibniz Centre for Agricultural Landscape Research, Eberswalder Straße 84, Müncheberg, 15374, Germany
  19. 19Agricultural Leadership, Education, and Communications, Texas A&M University, 600 John Kimbrough Blvd, College Station, TX 77843-2116, United States
  20. 20Department of Computational Hydrosystems, Helmholtz Centre for Environmental Research, Permoserstraße 15, Leipzig, 04318, Germany
  21. 21Fincons s.p.a, Via Torri Bianche 10, Vimercate, 20871, Italy
  22. 22Earth Observation and Environmental Informatics, Wageningen University and Research, P.O. Box 47, Wageningen, 6700 AA, the Netherlands
  23. 23Chair of Digital Agriculture, Technical University of Munich, Liesel-Beckmann-Straße 2, Freising, 85354, Germany
Open at sourcePDFDOICite

Abstract

In-season, pre-harvest crop yield forecasts are essential for enhancing transparency in commodity markets and improving food security. They play a key role in increasing resilience to climate change and extreme events and thus contribute to the United Nations’ Sustainable Development Goal 2 of zero hunger. Pre-harvest crop yield forecasting is a complex task, as several interacting factors contribute to yield formation, including in-season weather variability, extreme events, long-term climate change, soil, pests, diseases and farm management decisions. Several modeling approaches have been employed to capture complex interactions among such predictors and crop yields. Prior research for in-season, pre-harvest crop yield forecasting has primarily been case-study based, which makes it difficult to compare modeling approaches and measure progress systematically. To address this gap, we introduce CY-Bench (Crop Yield Benchmark), a comprehensive dataset and benchmark to forecast maize and wheat yields at a global scale. CY-Bench was conceptualized and developed within the Machine Learning team of the Agricultural Model Intercomparison and Improvement Project (AgML) in collaboration with agronomists, climate scientists, and machine learning researchers. It features publicly available sub-national yield statistics and relevant predictors—such as weather data, soil characteristics, and remote sensing indicators—that have been pre-processed, standardized, and harmonized across spatio-temporal scales. With CY-Bench, we aim to: (i) establish a standardized framework for developing and evaluating data-driven models across diverse farming systems in more than 25 countries across six continents; (ii) enable robust and reproducible model comparisons that address real-world operational challenges; (iii) provide an openly accessible dataset to the earth system science and machine learning communities, facilitating research on time series forecasting, domain adaptation, and online learning. The dataset (https://doi.org/10.5281/zenodo.11502142, (Paudel et al., 2025a)) and accompanying code (https://github.com/WUR-AI/AgML-CY-Bench, (Paudel et al., 2025b))) are openly available to support the continuous development of advanced data driven models for crop yield forecasting to enhance decision-making on food security.

Related

  1. Brazilian bryophytes: a national-scale comprehensive dataset of species richness and geographic distribution
    J. V. Silva, J. Marmo, K. j. Tavares +2
    bioRxivPreprintCC BY-NC-NDFull textPlant biologybioRxiv
  2. OmniEEG-Bench: A Standardized Evaluation Benchmark for EEG Foundation Models
    Ziling Lu, Zongsheng Li, Xinke Shen +11
    arXiv (Cornell University)PreprintLicence not statedFull text11 citedNeuroscienceOpenAlex
  3. From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery?
    P. Llompart, L. Guner, H. Lai +2
    bioRxivPreprintCC BYFull textBioinformatics & computational biologybioRxiv
  4. RNA3D-Decoy: A Large-Scale Benchmark Dataset of AI-Generated RNA Structure Models for Quality Assessment
    X. Chen, H. Yadi, R. Cao +1
    bioRxivPreprintCC BYFull textBioinformatics & computational biologybioRxiv
  5. The first OpenBind release: An open experimental structure-affinity dataset and benchmark for structure-based AI
    J. Nelen, O. Khan, E. Adams +13
    bioRxivPreprintCC BYFull text1 citedBioinformatics & computational biologybioRxiv

Cite

BibTeXRIS
BibTeX
@article{kallenberg2026cybench,
  title = {{CY-Bench: a comprehensive benchmark dataset for sub-national crop yield forecasting}},
  author = {Michiel Kallenberg and Dilli Paudel and Stella Ofori-Ampofo and Hilmy Baja and Ron van Bree and Aike Potze and Pratishtha Poudel and Abdelrahman Saleh and Weston Anderson and Malte von Bloh and Andres Castellano and Oumnia Ennaji and Raed Hamed and Rahel Laudien and Donghoon Lee and Inti Luna and Dainius Masiliū̄nas and Michele Meroni and Janet Mumo Mutuku and Siyabusa Mkuhlani and Jonathan Richetti and Alex C. Ruane and Ritvik Sahajpal and Guanyuan Shuai and Vasileios Sitokonstantinou and Rogério de Souza Nóia Júnior and Amit Kumar Srivastava and Robert Strong and Lily‐belle Sweet and Petar Vojnović and Allard J. W. de Wit and Maximilian Zachow and Ioannis N. Athanasiadis},
  journal = {Earth system science data},
  year = {2026},
  month = jun,
  doi = {10.5194/essd-18-3997-2026},
  url = {https://doi.org/10.5194/essd-18-3997-2026},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - CY-Bench: a comprehensive benchmark dataset for sub-national crop yield forecasting
AU  - Michiel Kallenberg
AU  - Dilli Paudel
AU  - Stella Ofori-Ampofo
AU  - Hilmy Baja
AU  - Ron van Bree
AU  - Aike Potze
AU  - Pratishtha Poudel
AU  - Abdelrahman Saleh
AU  - Weston Anderson
AU  - Malte von Bloh
AU  - Andres Castellano
AU  - Oumnia Ennaji
AU  - Raed Hamed
AU  - Rahel Laudien
AU  - Donghoon Lee
AU  - Inti Luna
AU  - Dainius Masiliū̄nas
AU  - Michele Meroni
AU  - Janet Mumo Mutuku
AU  - Siyabusa Mkuhlani
AU  - Jonathan Richetti
AU  - Alex C. Ruane
AU  - Ritvik Sahajpal
AU  - Guanyuan Shuai
AU  - Vasileios Sitokonstantinou
AU  - Rogério de Souza Nóia Júnior
AU  - Amit Kumar Srivastava
AU  - Robert Strong
AU  - Lily‐belle Sweet
AU  - Petar Vojnović
AU  - Allard J. W. de Wit
AU  - Maximilian Zachow
AU  - Ioannis N. Athanasiadis
PY  - 2026
DA  - 2026/06/11
JO  - Earth system science data
DO  - 10.5194/essd-18-3997-2026
UR  - https://doi.org/10.5194/essd-18-3997-2026
AB  - In-season, pre-harvest crop yield forecasts are essential for enhancing transparency in commodity markets and improving food security. They play a key role in increasing resilience to climate change and extreme events and thus contribute to the United Nations’ Sustainable Development Goal 2 of zero hunger. Pre-harvest crop yield forecasting is a complex task, as several interacting factors contribute to yield formation, including in-season weather variability, extreme events, long-term climate change, soil, pests, diseases and farm management decisions. Several modeling approaches have been employed to capture complex interactions among such predictors and crop yields. Prior research for in-season, pre-harvest crop yield forecasting has primarily been case-study based, which makes it difficult to compare modeling approaches and measure progress systematically. To address this gap, we introduce CY-Bench (Crop Yield Benchmark), a comprehensive dataset and benchmark to forecast maize and wheat yields at a global scale. CY-Bench was conceptualized and developed within the Machine Learning team of the Agricultural Model Intercomparison and Improvement Project (AgML) in collaboration with agronomists, climate scientists, and machine learning researchers. It features publicly available sub-national yield statistics and relevant predictors—such as weather data, soil characteristics, and remote sensing indicators—that have been pre-processed, standardized, and harmonized across spatio-temporal scales. With CY-Bench, we aim to: (i) establish a standardized framework for developing and evaluating data-driven models across diverse farming systems in more than 25 countries across six continents; (ii) enable robust and reproducible model comparisons that address real-world operational challenges; (iii) provide an openly accessible dataset to the earth system science and machine learning communities, facilitating research on time series forecasting, domain adaptation, and online learning. The dataset (https://doi.org/10.5281/zenodo.11502142, (Paudel et al., 2025a)) and accompanying code (https://github.com/WUR-AI/AgML-CY-Bench, (Paudel et al., 2025b))) are openly available to support the continuous development of advanced data driven models for crop yield forecasting to enhance decision-making on food security.
SN  - 1866-3508
SN  - 1866-3516
ER  -