Machine learning to predict biomass sorghum yields under future climate scenarios
Abstract
Abstract Crop yield modeling is critical in the design of national strategies for agricultural production, particularly in the context of a changing climate. Forecasting yields of bioenergy crops at fine spatial resolutions can help to evaluate near‐term and long‐term pathways for scaling up bio‐based fuel and chemical production, and for understanding the impacts of abiotic stressors such as severe droughts and temperature extremes on potential biomass supply. We used a large dataset of 28,364 Sorghum bicolor yield samples (uniquely identified by county and year of observation), environmental variables, and multiple approaches to analyze historical trends in sorghum productivity across the USA. We selected the most accurate machine learning approach (a variation of the random forest approach) to predict future trends in sorghum yields under four greenhouse gas (GHG) emission scenarios and two irrigation regimes. We identified irrigation practices, vapor pressure deficit, and time (a proxy for technological improvement) as the most important predictors of sorghum productivity. Our results showed a decreasing trend of sorghum yields over future years (on average 2.7% from 2018 to 2099), with greater decline under a high GHG emissions scenario (3.8%) and in the absence of irrigation (4.6%). Geographically, we observed the steepest predicted declines inmore »
- Authors:
-
[1];
[4]
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Joint BioEnergy Inst. (JBEI), Emeryville, CA (United States)
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Joint BioEnergy Inst. (JBEI), Emeryville, CA (United States); Huazhong Univ. of Science and Technology, Wuhan (China)
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Joint BioEnergy Inst. (JBEI), Emeryville, CA (United States); Argonne National Lab. (ANL), Argonne, IL (United States)
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Joint BioEnergy Inst. (JBEI), Emeryville, CA (United States); Univ. of California, Berkeley, CA (United States)
- Publication Date:
- Research Org.:
- Argonne National Laboratory (ANL), Argonne, IL (United States); Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC), Biological and Environmental Research (BER)
- OSTI Identifier:
- 1631977
- Alternate Identifier(s):
- OSTI ID: 1597542
- Grant/Contract Number:
- AC02-06CH11357; AC02-05CH11231
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Biofuels, Bioproducts & Biorefining
- Additional Journal Information:
- Journal Volume: 14; Journal Issue: 3; Journal ID: ISSN 1932-104X
- Publisher:
- Wiley
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 09 BIOMASS FUELS; Bioenergy; Biofuels; Climate Change; Machine Learning; Sorghum; Yield Modeling
Citation Formats
Huntington, Tyler, Cui, Xinguang, Mishra, Umakant, and Scown, Corinne D. Machine learning to predict biomass sorghum yields under future climate scenarios. United States: N. p., 2020.
Web. doi:10.1002/bbb.2087.
Huntington, Tyler, Cui, Xinguang, Mishra, Umakant, & Scown, Corinne D. Machine learning to predict biomass sorghum yields under future climate scenarios. United States. https://doi.org/10.1002/bbb.2087
Huntington, Tyler, Cui, Xinguang, Mishra, Umakant, and Scown, Corinne D. Wed .
"Machine learning to predict biomass sorghum yields under future climate scenarios". United States. https://doi.org/10.1002/bbb.2087. https://www.osti.gov/servlets/purl/1631977.
@article{osti_1631977,
title = {Machine learning to predict biomass sorghum yields under future climate scenarios},
author = {Huntington, Tyler and Cui, Xinguang and Mishra, Umakant and Scown, Corinne D.},
abstractNote = {Abstract Crop yield modeling is critical in the design of national strategies for agricultural production, particularly in the context of a changing climate. Forecasting yields of bioenergy crops at fine spatial resolutions can help to evaluate near‐term and long‐term pathways for scaling up bio‐based fuel and chemical production, and for understanding the impacts of abiotic stressors such as severe droughts and temperature extremes on potential biomass supply. We used a large dataset of 28,364 Sorghum bicolor yield samples (uniquely identified by county and year of observation), environmental variables, and multiple approaches to analyze historical trends in sorghum productivity across the USA. We selected the most accurate machine learning approach (a variation of the random forest approach) to predict future trends in sorghum yields under four greenhouse gas (GHG) emission scenarios and two irrigation regimes. We identified irrigation practices, vapor pressure deficit, and time (a proxy for technological improvement) as the most important predictors of sorghum productivity. Our results showed a decreasing trend of sorghum yields over future years (on average 2.7% from 2018 to 2099), with greater decline under a high GHG emissions scenario (3.8%) and in the absence of irrigation (4.6%). Geographically, we observed the steepest predicted declines in the Great Lakes (8.2%), Upper Midwest (7.5%), and Heartland (6.7%) regions. Our study demonstrates the use of machine learning to identify environmental controllers of sorghum biomass yield and predict yields with reasonable accuracy. These results can inform the development of more realistic biomass supply projections for bioenergy if sorghum production is scaled up. © 2020 Society of Chemical Industry and John Wiley & Sons, Ltd},
doi = {10.1002/bbb.2087},
journal = {Biofuels, Bioproducts & Biorefining},
number = 3,
volume = 14,
place = {United States},
year = {Wed Feb 05 00:00:00 EST 2020},
month = {Wed Feb 05 00:00:00 EST 2020}
}
Free Publicly Available Full Text
Publisher's Version of Record
Other availability
Search WorldCat to find libraries that may hold this journal
Cited by: 25 works
Citation information provided by
Web of Science
Web of Science
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
Effects of climate change on global food production under SRES emissions and socio-economic scenarios
journal, April 2004
- Parry, M. L.; Rosenzweig, C.; Iglesias, A.
- Global Environmental Change, Vol. 14, Issue 1
Comparison of Models for Describing; Corn Yield Response to Nitrogen Fertilizer
journal, January 1990
- Cerrato, M. E.; Blackmer, A. M.
- Agronomy Journal, Vol. 82, Issue 1
Effects on soil temperature, moisture, and maize yield of cultivation with ridge and furrow mulching in the rainfed area of the Loess Plateau, China
journal, January 2013
- Li, Rong; Hou, Xianqing; Jia, Zhikuan
- Agricultural Water Management, Vol. 116
EnviroAtlas: A new geospatial tool to foster ecosystem services science and resource management
journal, August 2015
- Pickard, Brian R.; Daniel, Jessica; Mehaffey, Megan
- Ecosystem Services, Vol. 14
Integrating environmental covariates and crop modeling into the genomic selection framework to predict genotype by environment interactions
journal, November 2013
- Heslot, Nicolas; Akdemir, Deniz; Sorrells, Mark E.
- Theoretical and Applied Genetics, Vol. 127, Issue 2
Comparing estimates of climate change impacts from process-based and statistical crop models
journal, January 2017
- Lobell, David B.; Asseng, Senthold
- Environmental Research Letters, Vol. 12, Issue 1
High density biomass estimation for wetland vegetation using WorldView-2 imagery and random forest regression algorithm
journal, August 2012
- Mutanga, Onisimo; Adam, Elhadi; Cho, Moses Azong
- International Journal of Applied Earth Observation and Geoinformation, Vol. 18
Climate and Management Contributions to Recent Trends in U.S. Agricultural Yields
journal, February 2003
- Lobell, D. B.
- Science, Vol. 299, Issue 5609
Nonlinear heat effects on African maize as evidenced by historical yield trials
journal, March 2011
- Lobell, David B.; Bänziger, Marianne; Magorokosho, Cosmos
- Nature Climate Change, Vol. 1, Issue 1
Breeding Technologies to Increase Crop Production in a Changing World
journal, February 2010
- Tester, M.; Langridge, P.
- Science, Vol. 327, Issue 5967
Nonlinear temperature effects indicate severe damages to U.S. crop yields under climate change
journal, August 2009
- Schlenker, Wolfram; Roberts, Michael J.
- Proceedings of the National Academy of Sciences, Vol. 106, Issue 37
Take a Closer Look: Biofuels Can Support Environmental, Economic and Social Goals
journal, June 2014
- Dale, Bruce E.; Anderson, James E.; Brown, Robert C.
- Environmental Science & Technology, Vol. 48, Issue 13
The U.S. drought of 2012
journal, December 2015
- Rippey, Bradley R.
- Weather and Climate Extremes, Vol. 10
Biomass production of herbaceous energy crops in the United States: field trial results and yield potential maps from the multiyear regional feedstock partnership
journal, January 2018
- Lee, Do Kyoung; Aberle, Ezra; Anderson, Eric K.
- GCB Bioenergy, Vol. 10, Issue 10
2016 Billion-Ton Report: Advancing Domestic Resources for a Thriving Bioeconomy
report, July 2016
- Langholtz, M. H.; Stokes, B. J.; Eaton, L. M.
- DOE/EE-1440
Global scale climate–crop yield relationships and the impacts of recent warming
journal, March 2007
- Lobell, David B.; Field, Christopher B.
- Environmental Research Letters, Vol. 2, Issue 1
Climate variation explains a third of global crop yield variability
journal, January 2015
- Ray, Deepak K.; Gerber, James S.; MacDonald, Graham K.
- Nature Communications, Vol. 6, Issue 1
Annual Irrigation Dynamics in the U.S. Northern High Plains Derived from Landsat Satellite Data: Satellite-Derived Irrigation Dynamics
journal, September 2017
- Deines, Jillian M.; Kendall, Anthony D.; Hyndman, David W.
- Geophysical Research Letters, Vol. 44, Issue 18
Strategies for near-term scale-up of cellulosic biofuel production using sorghum and crop residues in the US
journal, November 2018
- Cui, Xinguang; Kavvada, Olga; Huntington, Tyler
- Environmental Research Letters, Vol. 13, Issue 12
Random Forests for Global and Regional Crop Yield Predictions
journal, June 2016
- Jeong, Jig Han; Resop, Jonathan P.; Mueller, Nathaniel D.
- PLOS ONE, Vol. 11, Issue 6
Climate extremes indices in the CMIP5 multimodel ensemble: Part 2. Future climate projections: CMIP5 PROJECTIONS OF EXTREMES INDICES
journal, March 2013
- Sillmann, J.; Kharin, V. V.; Zwiers, F. W.
- Journal of Geophysical Research: Atmospheres, Vol. 118, Issue 6
Global crop yield response to extreme heat stress under multiple climate change futures
journal, March 2014
- Deryng, Delphine; Conway, Declan; Ramankutty, Navin
- Environmental Research Letters, Vol. 9, Issue 3
AquaCrop - The FAO Crop Model to Simulate Yield Response to Water: II. Main Algorithms and Software Description
journal, May 2009
- Raes, Dirk; Steduto, Pasquale; Hsiao, Theodore C.
- Agronomy Journal, Vol. 101, Issue 3
Do nonlinear temperature effects indicate severe damages to US crop yields under climate change?
journal, October 2009
- Meerburg, B. G.; Verhagen, A.; Jongschaap, R. E. E.
- Proceedings of the National Academy of Sciences, Vol. 106, Issue 43