Artificial neural networks estimate evapotranspiration for Miscanthus × giganteus as effectively as empirical model but with fewer inputs

Aslan-Sungur, Guler Rojda; Moore, Caitlin E.; Bernacchi, Carl J.; Heaton, Emily; VanLoocke, Andy

doi:10.1007/s00704-025-05812-5

Artificial neural networks estimate evapotranspiration for Miscanthus × giganteus as effectively as empirical model but with fewer inputs

Journal Article · Mon Oct 13 00:00:00 EDT 2025 · Theoretical and Applied Climatology

DOI:https://doi.org/10.1007/s00704-025-05812-5· OSTI ID:3000097

Aslan-Sungur, Guler Rojda ^[1]; Moore, Caitlin E. ^[2]; Bernacchi, Carl J. ^[3]; Heaton, Emily ^[4]; VanLoocke, Andy ^[1]

Iowa State Univ., Ames, IA (United States)
Univ. of Illinois at Urbana-Champaign, IL (United States); Univ. of Western Australia, Crawley, WA (Australia)
Univ. of Illinois at Urbana-Champaign, IL (United States)
Iowa State Univ., Ames, IA (United States); Univ. of Illinois at Urbana-Champaign, IL (United States)

Estimating actual evapotranspiration (ET) is particularly crucial for addressing how vegetation affects the water balance of ecosystems. ET estimation can be complex with empirical models due to their many parameters and reliance on aridity. In contrast, artificial neural networks (ANNs) could potentially estimate ET with fewer and more common meteorological parameters. In this study, we trained two ANNs, one using a feed-forward approach (FFN) and the other a nonlinear auto-regressive network (NARX), to predict ET and compared them to the commonly used empirical model Granger and Gray (GG). We trained our models on a nine-year eddy covariance (EC) dataset for Miscanthus × giganteus (M. × giganteus) from Illinois (UIEF), then tested them using out-of-sample data from both UIEF and a different location in Iowa (SABR) to compare the accuracy of FFN, NARX, and GG models in estimating daily ET. A combination of air temperature (T_a) and solar radiation (R_s) was chosen as inputs due to the highest R² for FFN (R² = 0.79, 0.81, and 0.79 for training, testing, and validation, respectively) and only T_a for NARX (R² = 0.70 for out-of-sample validation). The predictive power of the FFN model was superior to the NARX and GG models at the UIEF site (R² = 0.84, 0.70, and 0.83 for out-of-sample validation, respectively). Our analysis showed that ANN approaches are as accurate as empirical approaches for estimating ET but use fewer inputs.

View Accepted Manuscript (DOE)

Research Organization:: Univ. of Illinois at Urbana-Champaign, IL (United States)

Sponsoring Organization:: USDOE Office of Science (SC), Biological and Environmental Research (BER)

Grant/Contract Number:: SC0018420

OSTI ID:: 3000097

Journal Information:: Theoretical and Applied Climatology, Journal Name: Theoretical and Applied Climatology Journal Issue: 11 Vol. 156; ISSN 0177-798X; ISSN 1434-4483

Publisher:: Springer Science and Business Media LLCCopyright Statement

Country of Publication:: United States

Language:: English

References (48)

The future of evapotranspiration: Global requirements for ecosystem functioning, carbon and climate feedbacks, agricultural management, and water resources: THE FUTURE OF EVAPOTRANSPIRATION Fisher, Joshua B.; Melton, Forrest; Middleton, Elizabeth Water Resources Research, Vol. 53, Issue 4 https://doi.org/10.1002/2016WR020175	journal	April 2017
Evaporation from natural nonsaturated surfaces Granger, R. J.; Gray, D. M. Journal of Hydrology, Vol. 111, Issue 1-4 https://doi.org/10.1016/0022-1694(89)90249-7	journal	January 1989
Spurious regressions in econometrics Granger, C. W. J.; Newbold, P. Journal of Econometrics, Vol. 2, Issue 2 https://doi.org/10.1016/0304-4076(74)90034-7	journal	July 1974
Miscanthus: A Promising Biomass Crop Heaton, Emily A.; Dohleman, Frank G.; Miguez, A. Fernando Advances in Botanical Research https://doi.org/10.1016/B978-0-12-381518-7.00003-0	book	January 2010
Illuminating the “black box”: a randomization approach for understanding variable contributions in artificial neural networks Olden, Julian D.; Jackson, Donald A. Ecological Modelling, Vol. 154, Issue 1-2 https://doi.org/10.1016/S0304-3800(02)00064-9	journal	August 2002
A regional comparison of water use efficiency for miscanthus, switchgrass and maize VanLoocke, Andy; Twine, Tracy E.; Zeri, Marcelo Agricultural and Forest Meteorology, Vol. 164 https://doi.org/10.1016/j.agrformet.2012.05.016	journal	October 2012
Drought assessment and monitoring through blending of multi-sensor indices using machine learning approaches for different climate regions Park, Seonyoung; Im, Jungho; Jang, Eunna Agricultural and Forest Meteorology, Vol. 216 https://doi.org/10.1016/j.agrformet.2015.10.011	journal	January 2016
Modelling reference evapotranspiration using a new wavelet conjunction heuristic method: Wavelet extreme learning machine vs wavelet neural networks Kisi, Ozgur; Alizamir, Meysam Agricultural and Forest Meteorology, Vol. 263 https://doi.org/10.1016/j.agrformet.2018.08.007	journal	December 2018
Evaluation of SVM, ELM and four tree-based ensemble models for predicting daily reference evapotranspiration using limited meteorological data in different climates of China Fan, Junliang; Yue, Wenjun; Wu, Lifeng Agricultural and Forest Meteorology, Vol. 263 https://doi.org/10.1016/j.agrformet.2018.08.019	journal	December 2018
Deployment of artificial neural network for short-term forecasting of evapotranspiration using public weather forecast restricted messages Traore, Seydou; Luo, Yufeng; Fipps, Guy Agricultural Water Management, Vol. 163 https://doi.org/10.1016/j.agwat.2015.10.009	journal	January 2016
Evapotranspiration evaluation models based on machine learning algorithms—A comparative study Granata, Francesco Agricultural Water Management, Vol. 217 https://doi.org/10.1016/j.agwat.2019.03.015	journal	May 2019
Forecasting evapotranspiration in different climates using ensembles of recurrent neural networks Granata, Francesco; Di Nunno, Fabio Agricultural Water Management, Vol. 255 https://doi.org/10.1016/j.agwat.2021.107040	journal	September 2021
The biophysical link between climate, water, and vegetation in bioenergy agro-ecosystems Bagley, Justin E.; Davis, Sarah C.; Georgescu, Matei Biomass and Bioenergy, Vol. 71 https://doi.org/10.1016/j.biombioe.2014.10.007	journal	December 2014
Evapotranspiration estimation using four different machine learning approaches in different terrestrial ecosystems Dou, Xianming; Yang, Yongguo Computers and Electronics in Agriculture, Vol. 148 https://doi.org/10.1016/j.compag.2018.03.010	journal	May 2018
Sustainable Land Management for Bioenergy Crops Uludere Aragon, Nazli; Wagner, Melissa; Wang, Meng Energy Procedia, Vol. 125 https://doi.org/10.1016/j.egypro.2017.08.063	journal	September 2017
Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions Maier, Holger R.; Jain, Ashu; Dandy, Graeme C. Environmental Modelling & Software, Vol. 25, Issue 8 https://doi.org/10.1016/j.envsoft.2010.02.003	journal	August 2010
Forecasting groundwater levels using nonlinear autoregressive networks with exogenous input (NARX) Wunsch, Andreas; Liesch, Tanja; Broda, Stefan Journal of Hydrology, Vol. 567 https://doi.org/10.1016/j.jhydrol.2018.01.045	journal	December 2018
Estimation of reference evapotranspiration in Brazil with limited meteorological data using ANN and SVM – A new approach Ferreira, Lucas Borges; da Cunha, Fernando França; de Oliveira, Rubens Alves Journal of Hydrology, Vol. 572 https://doi.org/10.1016/j.jhydrol.2019.03.028	journal	May 2019
Long-term time series prediction with the NARX network: An empirical evaluation Menezes, José Maria P.; Barreto, Guilherme A. Neurocomputing, Vol. 71, Issue 16-18 https://doi.org/10.1016/j.neucom.2008.01.030	journal	October 2008
Evaluating Different Machine Learning Methods for Upscaling Evapotranspiration from Flux Towers to the Regional Scale Xu, Tongren; Guo, Zhixia; Liu, Shaomin Journal of Geophysical Research: Atmospheres, Vol. 123, Issue 16 https://doi.org/10.1029/2018JD028447	journal	August 2018
Parameterizing Perennial Bioenergy Crops in Version 5 of the Community Land Model Based on Site‐Level Observations in the Central Midwestern United States Cheng, Yanyan; Huang, Maoyi; Chen, Min Journal of Advances in Modeling Earth Systems, Vol. 12, Issue 1 https://doi.org/10.1029/2019MS001719	journal	January 2020
On the Use of the Term “Evapotranspiration” Miralles, D. G.; Brutsaert, W.; Dolman, A. J. Water Resources Research, Vol. 56, Issue 11 https://doi.org/10.1029/2020WR028055	journal	October 2020
Cooling of US Midwest summer temperature extremes from cropland intensification Mueller, Nathaniel D.; Butler, Ethan E.; McKinnon, Karen A. Nature Climate Change, Vol. 6, Issue 3 https://doi.org/10.1038/nclimate2825	journal	October 2015
A critique of pure learning and what artificial neural networks can learn from animal brains Zador, Anthony M. Nature Communications, Vol. 10, Issue 1 https://doi.org/10.1038/s41467-019-11786-6	journal	August 2019
The FLUXNET2015 dataset and the ONEFlux processing pipeline for eddy covariance data Pastorello, Gilberto; Trotta, Carlo; Canfora, Eleonora Scientific Data, Vol. 7, Issue 1 https://doi.org/10.1038/s41597-020-0534-3	journal	July 2020
Avoiding overfitting in the analysis of high-dimensional data with artificial neural networks (ANNs) Defernez, Marianne; Kemsley, E. Katherine The Analyst, Vol. 124, Issue 11 https://doi.org/10.1039/A905556H	journal	January 1999
Direct climate effects of perennial bioenergy crops in the United States Georgescu, M.; Lobell, D. B.; Field, C. B. Proceedings of the National Academy of Sciences, Vol. 108, Issue 11 https://doi.org/10.1073/pnas.1008779108	journal	February 2011
Implications for the hydrologic cycle under climate change due to the expansion of bioenergy crops in the Midwestern United States Le, P. V. V.; Kumar, P.; Drewry, D. T. Proceedings of the National Academy of Sciences, Vol. 108, Issue 37 https://doi.org/10.1073/pnas.1107177108	journal	August 2011
Biofuel, land and water: maize, switchgrass or Miscanthus ? Zhuang, Qianlai; Qin, Zhangcai; Chen, Min Environmental Research Letters, Vol. 8, Issue 1 https://doi.org/10.1088/1748-9326/8/1/015020	journal	February 2013
Carbon debt of field-scale conservation reserve program grasslands converted to annual and perennial bioenergy crops Abraha, Michael; Gelfand, Ilya; Hamilton, Stephen K. Environmental Research Letters, Vol. 14, Issue 2 https://doi.org/10.1088/1748-9326/aafc10	journal	February 2019
Nitrous oxide fluxes over establishing biofuel crops: Characterization of temporal variability using the cross‐wavelet analysis Zeri, Marcelo; Yang, Wendy H.; Cunha‐Zeri, Gisleine GCB Bioenergy, Vol. 12, Issue 9 https://doi.org/10.1111/gcbb.12728	journal	July 2020
The carbon and nitrogen cycle impacts of reverting perennial bioenergy switchgrass to an annual maize crop rotation Moore, Caitlin E.; Berardi, Danielle M.; Blanc‐Betes, Elena GCB Bioenergy, Vol. 12, Issue 11 https://doi.org/10.1111/gcbb.12743	journal	September 2020
Ecosystem‐scale biogeochemical fluxes from three bioenergy crop candidates: How energy sorghum compares to maize and miscanthus Moore, Caitlin E.; Haden, Adam C.; Burnham, Mark B. GCB Bioenergy, Vol. 13, Issue 3 https://doi.org/10.1111/gcbb.12788	journal	December 2020
Long‐term yields in annual and perennial bioenergy crops in the Midwestern United States Kantola, Ilsa B.; Masters, Michael D.; Blanc‐Betes, Elena GCB Bioenergy https://doi.org/10.1111/gcbb.12940	journal	April 2022
Agroecosystem model simulations reveal spatial variability in relative productivity in biomass sorghum and maize in Iowa, USA Bendorf, Josh; Heaton, Emily; Hartman, Theodore GCB Bioenergy, Vol. 14, Issue 12, p. 1336-1360 https://doi.org/10.1111/gcbb.13004	journal	October 2022
A comparison of canopy evapotranspiration for maize and two perennial grasses identified as potential bioenergy crops: COMPARISON OF CANOPY EVAPOTRANSPIRATION Hickman, George C.; Vanloocke, Andy; Dohleman, Frank G. GCB Bioenergy https://doi.org/10.1111/j.1757-1707.2010.01050.x	journal	June 2010
The impacts of Miscanthus×giganteus production on the Midwest US hydrologic cycle: IMPACTS OF MISCANTHUS ON US HYDROLOGIC CYCLE Vanloocke, Andy; Bernacchi, Carl J.; Twine, Tracy E. GCB Bioenergy https://doi.org/10.1111/j.1757-1707.2010.01053.x	journal	June 2010
Modeling the Exchanges of Energy, Water, and Carbon Between Continents and the Atmosphere Sellers, P. J. Science, Vol. 275, Issue 5299 https://doi.org/10.1126/science.275.5299.502	journal	January 1997
FLUXNET: A New Tool to Study the Temporal and Spatial Variability of Ecosystem–Scale Carbon Dioxide, Water Vapor, and Energy Flux Densities Baldocchi, Dennis; Falge, Eva; Gu, Lianhong Bulletin of the American Meteorological Society, Vol. 82, Issue 11 https://doi.org/10.1175/1520-0477(2001)082<2415:FANTTS>2.3.CO;2	journal	November 2001
and Switchgrass Production in Central Illinois: Impacts on Hydrology and Inorganic Nitrogen Leaching McIsaac, Gregory F.; David, Mark B.; Illinois, Corey A. Mitchell University of Journal of Environment Quality, Vol. 39, Issue 5 https://doi.org/10.2134/jeq2009.0497	journal	January 2010
Estimating evapotranspiration using the complementary relationship and the Budyko framework Kim, Homin; Kaluarachchi, Jagath J. Journal of Water and Climate Change, Vol. 8, Issue 4 https://doi.org/10.2166/wcc.2017.148	journal	June 2017
A Review of the Artificial Neural Network Models for Water Quality Prediction Chen, Yingyi; Song, Lihua; Liu, Yeqi Applied Sciences, Vol. 10, Issue 17 https://doi.org/10.3390/app10175776	journal	August 2020
A Nonlinear Autoregressive Exogenous (NARX) Neural Network Model for the Prediction of the Daily Direct Solar Radiation Boussaada, Zina; Curea, Octavian; Remaci, Ahmed Energies, Vol. 11, Issue 3 https://doi.org/10.3390/en11030620	journal	March 2018
Modeling and Predicting Carbon and Water Fluxes Using Data-Driven Techniques in a Forest Ecosystem Dou, Xianming; Yang, Yongguo Forests, Vol. 8, Issue 12 https://doi.org/10.3390/f8120498	journal	December 2017
MODIS-Based Estimation of Terrestrial Latent Heat Flux over North America Using Three Machine Learning Algorithms Wang, Xuanyu; Yao, Yunjun; Zhao, Shaohua Remote Sensing, Vol. 9, Issue 12 https://doi.org/10.3390/rs9121326	journal	December 2017
Water, Energy, and Carbon with Artificial Neural Networks (WECANN): a statistically based estimate of global surface turbulent fluxes and gross primary productivity using solar-induced fluorescence Alemohammad, Seyed Hamed; Fang, Bin; Konings, Alexandra G. Biogeosciences, Vol. 14, Issue 18 https://doi.org/10.5194/bg-14-4101-2017	journal	January 2017
Improving the complementary methods to estimate evapotranspiration under diverse climatic and physical conditions Anayah, F. M.; Kaluarachchi, J. J. Hydrology and Earth System Sciences, Vol. 18, Issue 6 https://doi.org/10.5194/hess-18-2049-2014	journal	January 2014
Sensitivity of potential evapotranspiration to changes in climate variables for different Australian climatic zones Guo, Danlu; Westra, Seth; Maier, Holger R. Hydrology and Earth System Sciences, Vol. 21, Issue 4 https://doi.org/10.5194/hess-21-2107-2017	journal	January 2017

Similar Records

Pretreatment of Miscanthus giganteus with Lime and Oxidants for Biofuels

Journal Article · Mon Feb 09 23:00:00 EST 2015 · Energy and Fuels · OSTI ID:1571030

Surface daytime net radiation estimation using artificial neural networks

Journal Article · Mon Nov 10 23:00:00 EST 2014 · Remote Sensing · OSTI ID:1222969

Artificial neural networks estimate evapotranspiration for Miscanthus × giganteus as effectively as empirical model but with fewer inputs

Citation Formats

References (48)

Similar Records

Related Subjects