The DOI matches its Crossref record; 57 of the 58 references it cites were found in a registry or an index.
Spatio-temporal downscaling of gridded crop model yield estimates based on machine learning
Open accessAbstract
Global gridded crop models (GGCMs) are essential tools for estimating agricultural crop yields and externalities at large scales, typically at coarse spatial resolutions. Higher resolution estimates are required for robust agricultural assessments at regional and local scales, where the applicability of GGCMs is often limited by low data availability and high computational demand. An approach to bridge this gap is the application of meta-models trained on GGCM output data to covariates of high spatial resolution. In this study, we explore two machine learning approaches – extreme gradient boosting and random forests - to develop meta-models for the prediction of crop model outputs at fine spatial resolutions. Machine learning algorithms are trained on global scale maize simulations of a GGCM and exemplary applied to the extent of Mexico at a finer spatial resolution. Results show very high accuracy with R²>0.96 for predictions of maize yields as well as the hydrologic externalities evapotranspiration and crop available water with also low mean bias in all cases. While limited sets of covariates such as annual climate data alone provide satisfactory results already, a comprehensive set of predictors covering annual, growing season, and monthly climate data is required to obtain high performance in reproducing climate-driven inter-annual crop yield variability. The findings presented herein provide a first proof of concept that machine learning methods are highly suitable for building crop meta-models for spatio-temporal downscaling and indicate potential for further developments towards scalable crop model emulators.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Outputs with high resolution may be aggregated via clustering methods to provide insights [183], while at coarser resolution, statistical downscaling can help to disaggregate data to an appropriate spatial resolution, as seen in applications such as crop yield [249], wind speed [479] or surface temperature [481].”
From Tackling climate change with machine learning (2023) · cites this paper as [249]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
R: A Language and Environment for Statistical Computing
R Core Team (2000) · doi:10.32614/r.manuals · Cited by 355,893
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 2×
“Random forests (Breiman, 2001) employ not only bagging (row 295 sub-sampling) but also column sub-sampling, i.”
BackgroundXGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569 · cited 3×
“Two of the presently most flexible and in recent competitions best performing 131 (Fernández-Delgado, 2014; Chen and Guestrin, 2016) machine learning approaches for numeric 132 predictions, extreme gradient boosting and random forests, are tested and compared against crop 133 model simulations…”
BackgroundMethodInfluentialData Mining: Practical Machine Learning Tools and Techniques
Witten, I. H., Frank, E., & Hall, M. A. (2011) · Elsevier eBooks · doi:10.1016/c2009-0-19715-5 · Cited by 25,543
River flow forecasting through conceptual models part I — A discussion of principles
Nash, J. E., & Sutcliffe, J. V. (1970) · Journal of Hydrology · doi:10.1016/0022-1694(70)90255-6 · Cited by 24,401 · cited 1×
“386 NSE is a common metric for model performance over time, used especially in hydrology 387 (Nash and Sutcliffe, 1970).”
BackgroundWorldClim 2: new 1‐km spatial resolution climate surfaces for global land areas
Fick, S. E., & Hijmans, R. J. (2017) · International Journal of Climatology · doi:10.1002/joc.5086 · Cited by 16,088 · cited 2×
“with a monthly time step, however, are available at very fine 83 resolutions up to <1 km (e.g. Wang et al., 2016; Fick and Hijmans, 2017).”
Backgroundggplot2: Elegant Graphics for Data Analysis
Wickham, H. (2009) · doi:10.1007/978-0-387-98141-3 · Cited by 14,447
Updated world map of the Köppen-Geiger climate classification
(2007) · doi:10.5194/hess-11-1633-2007 · Cited by 13,640 · cited 1×
“397 Evaluations were partly carried out at the level of major Koeppen-Geiger climate regions 398 (Figure S2) following the rules of Peel et al. (2007).”
InfluentialMERRA: NASA’s Modern-Era Retrospective Analysis for Research and Applications
Rienecker, M. M., Suárez, M. J., Gelaro, R., Todling, R., Bacmeister, J. T., Liu, E., Bosilovich, M. G., Schubert, S. D., Takacs, L. L., Kim, G.-K., et al. (2011) · Journal of Climate · doi:10.1175/jcli-d-11-00015.1 · Cited by 4,856 · cited 1×
“AgMERRA covers the period 185 1980-2010 and combines data from the Modern-Era Retrospective Analysis for Research and 186 Applications (MERRA; Rienecker et al., 2011), station data, and remotely sensed datasets and 187 has been bias corrected using stations from agricultural land only.”
MethodSoilGrids250m: Global gridded soil information based on machine learning
Hengl, T., Mendes de Jesus, J., Heuvelink, G. B. M., Ruiperez Gonzalez, M., Kilibarda, M., Blagotić, A., Shangguan, W., Wright, M. N., Geng, X., Bauer-Marschallinger, B., et al. (2017) · PLOS ONE · doi:10.1371/journal.pone.0169748 · Cited by 4,733
Computer Models of Watershed Hydrology
Singh, V. P. (1995) · Medical Entomology and Zoology · Cited by 3,273
Closing yield gaps through nutrient and water management
Mueller, N. D., Gerber, J., Johnston, M., Ray, D. K., Ramankutty, N., & Foley, J. A. (2012) · Nature · doi:10.1038/nature11420 · Cited by 2,942
Haylock, M. R., Hofstra, N., Tank, A. K., Klok, E. J., Jones, P. D., & New, M. G. (2008) · Journal of Geophysical Research Atmospheres · doi:10.1029/2008jd010201 · Cited by 2,439
Rosenzweig, C., Elliott, J., Deryng, D., Ruane, A. C., Müller, C., Arneth, A., Boote, K. J., Folberth, C., Glotter, M., Khabarov, N., et al. (2014) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1222463110 · Cited by 2,319 · cited 1×
“Besides the direct provision and interpretation of model outputs for crop 54 yields alone (e.g. Rosenzweig et al., 2014) or their joint evaluation with externalities such as 55 crop water use (Liu et al., 2013; Elliott et al., 2014), GGCMs provide base layers of input data 56 for agro-economic or…”
BackgroundSelf-citationGraph-based approach for airborne light detection and ranging segmentation
Vilarino, D. L., Cabaleiro, J. C., Sánchez, J. M., Rivera, F. F., & Pena, T. F. (2017) · Journal of Applied Remote Sensing · doi:10.1117/1.jrs.11.015020 · Cited by 1,760
Crop Yield Gaps: Their Importance, Magnitudes, and Causes
Lobell, D. B., Cassman, K. G., & Field, C. B. (2009) · Annual Review of Environment and Resources · doi:10.1146/annurev.environ.041008.093740 · Cited by 1,606
Portmann, F. T., Siebert, S., & Döll, P. (2010) · Global Biogeochemical Cycles · doi:10.1029/2008gb003435 · Cited by 1,586
Meinshausen, N. (2006) · Cited by 1,522
Wang, T., Hamann, A., Spittlehouse, D., & Carroll, C. (2016) · PLoS ONE · doi:10.1371/journal.pone.0156720 · Cited by 1,110
Duro, D. C., Franklin, S. E., & Dubé, M. G. (2011) · Remote Sensing of Environment · doi:10.1016/j.rse.2011.11.020 · Cited by 1,020 · cited 1×
“Within agricultural sciences, applications are to date mostly limited to processing 114 and analyzes of remote sensing data (e.g. Duro et al., 2012; Ali et al., 2015).”
BackgroundCrop planting dates: an analysis of global patterns
Sacks, W. J., Deryng, D., Foley, J. A., & Ramankutty, N. (2010) · Global Ecology and Biogeography · doi:10.1111/j.1466-8238.2010.00551.x · Cited by 963 · cited 2×
“The 62 latter two are available at increasingly fine resolutions well below 1 km (Hengl et al., 2017a, 63 Jarvis et al., 2008), while management is typically reported at national or subnational 64 administrative levels (e.g. Sacks et al., 2010; Mueller et al., 2012).”
BackgroundMethodGlobal land-use implications of first and second generation biofuel targets
Havlík, P., Schneider, U. A., Schmid, E., Böttcher, H., Fritz, S., Skalský, R., Aoki, K., de Cara, S., Kindermann, G., Kraxner, F., et al. (2010) · Energy Policy · doi:10.1016/j.enpol.2010.03.030 · Cited by 875
Self-citationWilliams, J. R., & Singh, V. P. (1995) · Cited by 650
Consistent negative response of US crops to high temperatures in observations and crop models
Schauberger, B., Archontoulis, S. V., Arneth, A., Balkovič, J., Ciais, P., Deryng, D., Elliott, J. W., Folberth, C., Khabarov, N., Müller, C., et al. (2017) · Nature Communications · doi:10.1038/ncomms13931 · Cited by 547 · cited 1×
“…of phenologic development in the EPIC model (see section 2.1), which 670 is driven by HU accumulation, while very high and very low temperatures cause stresses to the 671 crop, which is over large areas typically of minor importance compared to water deficits (e.g. 672 Schauberger et al., 2017).”
BackgroundInfluentialSelf-citationAli, I., Greifeneder, F., Stamenković, J., Neumann, M., & Notarnicola, C. (2015) · Remote Sensing · doi:10.3390/rs71215841 · Cited by 510
Simulating soil C dynamics with EPIC: Model description and testing against long-term data
Izaurralde, R. C., Williams, J. R., McGill, W. B., Rosenberg, N. J., & Jakas, M. C. Q. (2005) · Ecological Modelling · doi:10.1016/j.ecolmodel.2005.07.010 · Cited by 507
Bases and limits to using ‘degree.day’ units
Bonhomme, R. (2000) · European Journal of Agronomy · doi:10.1016/s1161-0301(00)00058-7 · Cited by 497 · cited 1×
“This can 652 be expected as crop growth processes are typically non-linear (Bonhomme, 2000) and crops’ 653 sensitivity to temperature and water supply can shift throughout the growing season.”
BackgroundClassification with correlated features: unreliability of feature ranking and solutions
Toloşi, L., & Lengauer, T. (2011) · Bioinformatics · doi:10.1093/bioinformatics/btr300 · Cited by 478
Ruane, A., Goldberg, R., & Chryssanthacopoulos, J. (2015) · Agricultural and Forest Meteorology · doi:10.1016/j.agrformet.2014.09.016 · Cited by 396
Global Gridded Crop Model evaluation: benchmarking, skills, deficiencies and implications
Müller, C., Elliott, J., Chryssanthacopoulos, J., Arneth, A., Balkovič, J., Ciais, P., Deryng, D., Folberth, C., Glotter, M., Hoek, S., et al. (2016) · Geoscientific model development · doi:10.5194/gmd-10-1403-2017 · Cited by 344 · cited 7×
“While the results are highly comparable among the two 612 methods, extreme gradient boosting shows moderately better results especially for inter-annual 613 yield variability (cf. Tables S6-9), which is of ample importance for climate impact studies (e.g. 614 Müller et al., 2017).”
BackgroundResultInfluentialSelf-citationTomislav Hengl, A., Leenaars, J. G. B., Shepherd, K. D., Walsh, M., Heuvelink, G. B. M., Mamo, T., Tilahun, H., Berkhout, E., Cooper, M., Fegraus, E., et al. (2017) · Nutrient Cycling in Agroecosystems · doi:10.1007/s10705-017-9870-x · Cited by 336
The Global Gridded Crop Model Intercomparison: data and modeling protocols for Phase 1 (v1.0)
Elliott, J. W., Müller, C., Deryng, D., Chryssanthacopoulos, J. P., Boote, K. J., Büchner, M., Foster, I. T., Glotter, M. J., Heinke, J., Iizumi, T., et al. (2015) · Geoscientific model development · doi:10.5194/gmd-8-261-2015 · Cited by 311
Stöckle, C. O., Williams, J. R., Rosenberg, N. J., & Jones, C. (1992) · Agricultural Systems · doi:10.1016/0308-521x(92)90067-x · Cited by 256
Uncertainty in soil data can outweigh climate impact signals in global crop yield simulations
Folberth, C., Skalský, R., Moltchanova, E. V., Balkovič, J., Azevedo, L. B., Obersteiner, M. H., & van der Velde, M. (2016) · Nature Communications · doi:10.1038/ncomms11872 · Cited by 256
Self-citationProjecting future crop productivity for global economic modeling
Müller, C., & Robertson, R. (2013) · Agricultural Economics · doi:10.1111/agec.12088 · Cited by 247
Scale changes and model linking methods for integrated assessment of agri-environmental systems
Ewert, F. A., van Ittersum, M. K., Heckelei, T., Thérond, O., Bezlepkina, I., & Andersen, E. (2011) · Agriculture Ecosystems & Environment · doi:10.1016/j.agee.2011.05.016 · Cited by 192
Balkovič, J., van der Velde, M., Skalský, R., Xiong, W., Folberth, C., Khabarov, N., Смирнов, А. В., Mueller, N. D., & Obersteiner, M. H. (2014) · Global and Planetary Change · doi:10.1016/j.gloplacha.2014.08.010 · Cited by 174
Self-citationGlobal agro-ecological zone V4 – Model documentation
Fischer, G., Nachtergaele, F. O., van Velthuizen, H., Chiozza, F., Francheschini, G., Henry, Muchoney, D. M., & Tramberend, S. (2021) · FAO eBooks · doi:10.4060/cb4744en · Cited by 156
EPIC model parameters for cereal, oilseed, and forage crops in the northern Great Plains region
Kiniry, J. R., Williams, J. R., Major, D. J., Izaurralde, R. C., Gassman, P. W., Morrison, M. J., Bergentine, R., & Zentner, R. P. (1995) · Canadian Journal of Plant Science · doi:10.4141/cjps95-114 · Cited by 149
Understanding the weather signal in national crop‐yield variability
Frieler, K., Schauberger, B., Arneth, A., Balkovič, J., Chryssanthacopoulos, J. P., Deryng, D., Elliott, J. W., Folberth, C., Khabarov, N., Müller, C., et al. (2017) · Earth s Future · doi:10.1002/2016ef000525 · Cited by 147
Self-citationPugh, T. A. M., Müller, C., Elliott, J. W., Deryng, D., Folberth, C., Olin, S., Schmid, E., & Arneth, A. (2016) · Nature Communications · doi:10.1038/ncomms12608 · Cited by 141
Self-citationFolberth, C., Gaiser, T., Abbaspour, K. C., Schulin, R., & Yang, H. (2012) · Agriculture Ecosystems & Environment · doi:10.1016/j.agee.2012.01.026 · Cited by 121 · cited 1×
“…the impact of 738 uncertainties and spatial resolutions in climate, soil, management, and land use data as well as 739 crop model parameterization or meta-model error is as has been done before for single crop 740 models (Folberth et al., 2012a) and crop model ensembles (e.g. Angulo et al., 2014).”
Self-citationLiu, J., Folberth, C., Yang, H., Rockström, J., Abbaspour, K. C., & Zehnder, A. J. B. (2013) · PLoS ONE · doi:10.1371/journal.pone.0057750 · Cited by 112 · cited 1×
“…of model outputs for crop 54 yields alone (e.g. Rosenzweig et al., 2014) or their joint evaluation with externalities such as 55 crop water use (Liu et al., 2013; Elliott et al., 2014), GGCMs provide base layers of input data 56 for agro-economic or integrated assessment models (IAMs; Müller…”
BackgroundSelf-citationReidsma, P., Ewert, F. A., Boogaard, H., & van Diepen, K. (2009) · Agricultural Systems · doi:10.1016/j.agsy.2008.12.009 · Cited by 110
Assessing Weather-Yield Relationships in Rice at Local Scale Using Data Mining Approaches
Delerce, S., Dorado, H., Grillon, A., Rebolledo, M. C., Prager, S. D., Patiño, V. H., Garcés-Varón, G., & Jimenez, D. R. (2016) · PLoS ONE · doi:10.1371/journal.pone.0161620 · Cited by 98
Gaiser, T., de Barros, I., Sereke, F., & Lange, F.-M. (2009) · Agriculture Ecosystems & Environment · doi:10.1016/j.agee.2009.10.014 · Cited by 95
An AgMIP framework for improved agricultural representation in integrated assessment models
Ruane, A., Rosenzweig, C., Asseng, S., Boote, K., Elliott, J., Ewert, F., Jones, J. W., Martre, P., McDermid, S., Müller, C., et al. (2017) · Environmental Research Letters · doi:10.1088/1748-9326/aa8da6 · Cited by 94 · cited 2×
“…or the use of global crop model 93 simulations with artificial alterations of climate variables to retrieve estimates of climate change 94 impacts for assessment studies based on regressions along temperature, precipitation, and CO2 95 concentrations (Ruane et al., 2017; Rosenzweig et al., 2018).”
BackgroundMethodInfluentialFolberth, C., Yang, H., Gaiser, T., Abbaspour, K. C., & Schulin, R. (2013) · Agricultural Systems · doi:10.1016/j.agsy.2013.04.002 · Cited by 88
Self-citationStatistical emulators of maize, rice, soybean and wheat yields from global gridded crop models
Blanc, É. (2017) · Agricultural and Forest Meteorology · doi:10.1016/j.agrformet.2016.12.022 · Cited by 86 · cited 2×
“Within the closely related, recently emerging field of crop model emulators, Blanc 624 and Sultan (2015) and Blanc (2017) developed polynomial models to predict yields for various 625 crops under climate change using unique parameterizations for the statistical models at the grid 626 cell level.”
BackgroundCoordinating AgMIP data and models across global and regional scales for 1.5°C and 2.0°C assessments
Rosenzweig, C., Ruane, A. C., Antle, J. M., Elliott, J. W., Ashfaq, M., Chatta, A. A., Ewert, F. A., Folberth, C., Hathie, I., Havlík, P., et al. (2018) · Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences · doi:10.1098/rsta.2016.0455 · Cited by 79 · cited 2×
“In addition, they may omit farm-level 74 heterogeneity present at the sub-grid level (Ewert et al., 2011), which is essential for local to 75 regional decision-making and stakeholder information (Rosenzweig et al., 2018).”
BackgroundMethodSelf-citationIzaurralde, R. C., McGill, W. B., & Williams, J. R. (2012) · Elsevier eBooks · doi:10.1016/b978-0-12-386897-8.00017-6 · Cited by 58 · cited 1×
“…of elevated atmospheric CO2 concentration on plant growth (Stockle et 148 al., 1992), detailed soil organic matter cycling (Izaurralde et al., 2006, Izaurralde et al., 2012), 149 and an extended number of crop types and cultivars (e.g. Kiniry et al., 1995; Gaiser et al., 2010) 150 among others…”
BackgroundFolberth, C., Yang, H., Wang, X., & Abbaspour, K. C. (2012) · Ecological Modelling · doi:10.1016/j.ecolmodel.2012.03.035 · Cited by 51 · cited 1×
“…the impact of 738 uncertainties and spatial resolutions in climate, soil, management, and land use data as well as 739 crop model parameterization or meta-model error is as has been done before for single crop 740 models (Folberth et al., 2012a) and crop model ensembles (e.g. Angulo et al., 2014).”
Self-citationEmulating maize yields from global gridded crop models using statistical estimates
Blanc, É., & Sultan, B. (2015) · Agricultural and Forest Meteorology · doi:10.1016/j.agrformet.2015.08.256 · Cited by 49 · cited 2×
“630 However, the visual comparison of inter-annual yield variability for the Corn Belt during the 631 historic time period in Blanc and Sultan (2015) and the regional predictions presented in this 632 study suggest that the polynomial models may be suitable at the global scale and for longer term…”
BackgroundManaging Agricultural Greenhouse Gases
(2012) · Elsevier eBooks · doi:10.1016/c2010-0-66174-8 · Cited by 44
Emulating global climate change impacts on crop yields
Oyebamiji, O., Edwards, N. R., Holden, P. B., Garthwaite, P. H., Schaphoff, S., & Gerten, D. (2015) · Statistical Modelling · doi:10.1177/1471082x14568248 · Cited by 34
‘Fingerprints’ of four crop models as affected by soil input data aggregation
Angulo, C., Gaiser, T., Rötter, R. P., Børgesen, C. D., Hlavinka, P., Trnka, M., & Ewert, F. A. (2014) · European Journal of Agronomy · doi:10.1016/j.eja.2014.07.005 · Cited by 32
Cited by
Sorted by citations
Machine Learning in Agriculture: A Comprehensive Updated Review
Benos, L. T., Tagarakis, A. C., Dolias, G., Berruto, R., Katerıs, D., & Bochtis, D. (2021) · Sensors · doi:10.3390/s21113758 · Cited by 1,048
Sharma, R., Kamble, S., Gunasekaran, A., Kumar, P. V., & Kumar, A., V (2020) · Computers & Operations Research · doi:10.1016/j.cor.2020.104926 · Cited by 837
Cao, J., Zhang, Z., Tao, F., Zhang, L., Luo, Y., Zhang, J., Han, J., & Xie, J. (2020) · Agricultural and Forest Meteorology · doi:10.1016/j.agrformet.2020.108275 · Cited by 385
Ahmed, K., Sachindra, D. A., Shahid, S., Demirel, M. C., & Chung, . (2019) · Hydrology and earth system sciences · doi:10.5194/hess-23-4803-2019 · Cited by 311
“The RF algorithm is found to perform well with spatial datasets and is less prone to over-fitting (Folberth et al., 2019).”
BackgroundMethodIntegrated phenology and climate in rice yields prediction using machine learning methods
Guo, Y., Fu, Y. H., Hao, F., Zhang, X., Wu, W., Jin, X., Bryant, C. R., & Senthilnath, J. (2020) · Ecological Indicators · doi:10.1016/j.ecolind.2020.106935 · Cited by 315
Metadata
- Authors
- Folberth, C., Baklanov, A., Balkovič, J., Skalský, R., Khabarov, N., & Obersteiner, M.
- Affiliations
- International Institute for Applied Systems Analysis (AT)
- National Research University Higher School of Economics (RU)
- Corresponding author
- Folberth, C.
- Venue
- Agricultural and Forest Meteorology
- Publisher
- Elsevier BV
- Published
- 2019-01
- Volume
- 264
- Pages
- 1-15
- ISSN
- 0168-1923 (ISSN-L)
- OpenAlex
- W2895348292
- Cited by
- 161
- References
- 58
- Citations by year
- 2026: 10 · 2025: 24 · 2024: 24 · 2023: 19 · 2022: 29 · 2021: 29 · 2020: 14 · 2019: 12
- FWCI
- 11.60
- Type
- journal article
- Language
- en
- Open access
- green
- ddd.uab.cat
- Licence
- Locations
- Agricultural and Forest Meteorology (publishedVersion)
- Dipòsit Digital de Documents de la UAB (Universitat Autònoma de Barcelona) (submittedVersion, cc-by-nc-nd)
- IIASA PURE (International Institute of Applied Systems Analysis) (submittedVersion)
- LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) (submittedVersion, cc-by-nc-nd)
- Funders
- European Research Council (ERC-2013-SynG-610028 Imbalance-P)
- National Research University Higher School of Economics
- Topics
- Life Sciences › Agricultural and Biological Sciences › Agronomy and Crop Science › Climate change impacts on agriculture
- Life Sciences › Agricultural and Biological Sciences › Plant Science › Smart Agriculture and AI
- Physical Sciences › Environmental Science › Ecology › Remote Sensing in Agriculture
- Keywords
- gridded crop models, crop yield prediction, meta-model, maize yield, extreme gradient boosting, random forest, evapotranspiration, Mexico
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
