Online citations, reference lists, and bibliographies.
← Back to Search

Predicting Spatial And Temporal Variability In Crop Yields: An Inter-comparison Of Machine Learning, Regression And Process-based Models.

G. Leng, J. Hall
Published 2020 · Economics, Medicine

Cite This
Download PDF
Analyze on Scholarcy
Share
Pervious assessments of crop yield response to climate change are mainly aided with either process-based models or statistical models, with a focus on predicting the changes in average yields, whilst there is growing interest in yield variability and extremes. In this study, we simulate US maize yield using process-based models, traditional regression model and a machine-learning algorithm, and importantly, identify the weakness and strength of each method in simulating the average, variability and extremes of maize yield across the country. We show that both regression and machine learning models can well reproduce the observed pattern of yield averages, while large bias is found for process-based crop models even fed with harmonized parameters. As for the probability distribution of yields, machine learning shows the best skill, followed by regression model and process-based models. For the country as a whole, machine learning can explain 93% of observed yield variability, followed by regression model (51%) and process-based models (42%). Based on the improved capability of the machine learning algorithm, we estimate that US maize yield is projected to decrease by 13.5% under the 2°C global warming scenario (by ~2050s). Yields less than or equal to the 10th percentile in the yield distribution for the baseline period are predicted to occur in 19% and 25% of years in 1.5°C (by ~2040s) and 2°C global warming scenarios, with potentially significant implications for food supply, prices and trade. The machine learning and regression methods are computationally much more efficient than process-based models, making it feasible to do probabilistic risk analysis of climate impacts on crop production for a wide range of future scenarios.
This paper references
10.1016/j.compag.2018.05.012
Machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture: A review
Anna Chlingaryan (2018)
10.1023/A:1010933404324
Random Forests
L. Breiman (2004)
10.1073/pnas.1312330110
The Inter-Sectoral Impact Model Intercomparison Project (ISI–MIP): Project framework
Lila Warszawski (2013)
10.1016/J.AGRFORMET.2011.02.010
Crop management and phenology trends in the U.S. Corn Belt: Impacts on yields, evapotranspiration and energy balance
W. J. Sacks (2011)
10.1175/BAMS-D-11-00094.1
An overview of CMIP5 and the experiment design
K. Taylor (2012)
10.1023/B:CLIM.0000013685.99609.9E
Hydrologic Implications of Dynamical and Statistical Approaches to Downscaling Climate Model Outputs
A. Wood (2004)
10.1016/J.AGRFORMET.2006.03.014
Climate changes and trends in phenology and yields of field crops in China, 1981-2000
F. Tao (2006)
10.1126/science.1239402
Climate Change Impacts on Global Food Security
T. Wheeler (2013)
10.1007/S10584-006-9122-6
Assessing the impacts of climate change on rice yields in the main rice areas of China
Fengmei Yao (2007)
10.1016/j.scitotenv.2018.10.434
Crop yield sensitivity of global major agricultural countries to droughts and the projected changes in the future
G. Leng (2019)
10.5194/ESD-7-327-2016
Differential climate impacts for policy-relevant limits to global warming: the case of 1.5 °C and 2 °C
C. Schleussner (2015)
10.1088/1748-9326/10/5/054013
The impact of climate extremes and irrigation on US crop yields
T. J. Troy (2015)
10.1073/pnas.1701762114
Temperature increase reduces global yields of major crops in four independent estimates
C. Zhao (2017)
10.1073/pnas.1222474110
Constraints and potentials of future irrigation water availability on agricultural production under climate change
J. Elliott (2013)
10.1088/1748-9326/11/11/114003
Emergence of new hydrologic regimes of surface water resources in the conterminous United States under future warming
G. Leng (2016)
10.1088/1748-9326/AA723B
Wheat yield loss attributable to heat waves, drought and water excess at the global, national and subnational scales
M. Zampieri (2017)
10.1038/ncomms13931
Consistent negative response of US crops to high temperatures in observations and crop models
Bernhard Schauberger (2017)
10.1016/j.scitotenv.2017.06.211
Evidence for a weakening strength of temperature-corn yield relation in the United States during 1980-2010.
G. Leng (2017)
10.1073/pnas.0701728104
Crop and pasture response to climate change
F. Tubiello (2007)
10.1007/s10584-012-0428-2
Projected temperature changes indicate significant increase in interannual variability of U.S. maize yields
D. Urbán (2012)
10.1016/J.GLOENVCHA.2003.10.008
Effects of climate change on global food production under SRES emissions and socio-economic scenarios
M. Parry (2004)
10.1007/s10584-018-2170-x
Impacts of rainfall extremes on wheat yield in semi-arid cropping systems in eastern Australia
Puyu Feng (2018)
10.1002/2017EF000690
Understanding the Changes in Global Crop Yields Through Changes in Climate and Technology
E. Najafi (2018)
10.1007/S10113-010-0173-X
The responses of agriculture in Europe to climate change
M. Bindi (2011)
10.1016/J.AGRFORMET.2015.11.003
Crop yield forecasting on the Canadian Prairies by remotely sensed vegetation indices and machine learning methods
M. Johnson (2016)
10.1088/1748-9326/8/1/014054
Regional disparities in the CO 2 fertilization effect and implications for crop yields
J. McGrath (2013)
10.1038/NCLIMATE3115
Similar estimates of temperature impacts on global wheat yield by three independent methods
B. Liu (2016)
10.1073/pnas.1015078108
Climate change risks for African agriculture
C. Müller (2011)
10.1038/srep16210
Soil mulching significantly enhances yields and water and nitrogen use efficiencies of maize and wheat: a meta-analysis
W. Qin (2015)
10.1088/1748-9326/AA518A
Comparing estimates of climate change impacts from process-based and statistical crop models
D. Lobell (2017)
10.1073/pnas.1222463110
Assessing agricultural risks of climate change in the 21st century in a global gridded crop model intercomparison
C. Rosenzweig (2013)
10.1088/1748-9326/2/1/014002
Global scale climate–crop yieldrelationships and the impacts of recentwarming
D. Lobell (2007)
10.1038/NCLIMATE2995
Regional disparities in the beneficial effects of rising CO2 concentrations on crop water productivity
D. Deryng (2016)
10.1038/ncomms6989
Climate variation explains a third of global crop yield variability
D. Ray (2015)
10.1038/NCLIMATE1585
Adaptation of US maize to temperature variations
Ethan E. Butler (2013)
10.1038/nature08823
The next generation of scenarios for climate change research and assessment
R. Moss (2010)
10.1088/1748-9326/10/2/024002
Response of double cropping suitability to climate change in the United States
Christopher A. Seifert (2015)
10.1038/NCLIMATE1916
Uncertainty in Simulating Wheat Yields Under Climate Change
S. Asseng (2013)
10.1038/nplants.2017.102
The uncertainty of crop yield projections is reduced by improved temperature response functions
E. Wang (2017)
10.1016/S1161-0301(02)00004-7
Consequences of climate change for European agricultural productivity, land use and policy
J. E. Olesen (2002)
10.1111/gcb.13901
Analysis of climate signals in the crop yield record of sub‐Saharan Africa
A. L. Hoffman (2018)
10.1088/1748-9326/5/1/014010
Robust negative impacts of climate change on African agriculture
W. Schlenker (2010)
10.1073/PNAS.0403720101
Rice yields decline with higher night temperature from global warming.
S. Peng (2004)
10.1016/J.AGRFORMET.2019.05.018
Incorporating machine learning with biophysical model can improve the evaluation of climate extremes impacts on wheat yield in south-eastern Australia
Puyu Feng (2019)
10.1029/2008GL033423
Towards probabilistic projections of climate change impacts on global crop yields
C. Tebaldi (2008)
10.1093/BIOINFORMATICS/BTQ134
Predicción y selección de variables con bosques aleatorios en presencia de variables correlacionadas
C. Alzate (2020)
10.1016/j.scitotenv.2017.07.017
Recent changes in county-level corn yield variability in the United States from observations and crop models.
G. Leng (2017)
10.1126/science.1204531
Climate Trends and Global Crop Production Since 1980
D. Lobell (2011)
10.1007/s10584-016-1773-3
A comparison of changes in river runoff from multiple global and catchment-scale hydrological models under global warming scenarios of 1 °C, 2 °C and 3 °C
S. Gosling (2016)
10.1126/SCIENCE.1078475
Climate and Management Contributions to Recent Trends in U.S. Agricultural Yields
D. Lobell (2003)
10.1073/pnas.1222460110
Multimodel assessment of water scarcity under climate change
J. Schewe (2013)
10.1016/J.STILL.2013.02.003
Thirty-year tillage effects on crop yield and soil fertility indicators
D. Karlen (2013)
10.1038/NCLIMATE2572
Energy system transformations for limiting end-of-century warming to below 1.5 °C
J. Rogelj (2015)
10.1371/journal.pone.0156571
Random Forests for Global and Regional Crop Yield Predictions
Jig Han Jeong (2016)
10.1038/nplants.2016.202
Plausible rice yield losses under future climate warming
Chuang Zhao (2016)
10.1088/1748-9326/AB154B
The effects of climate extremes on global agricultural yields
E. Vogel (2019)
10.1038/NCLIMATE2153
A meta-analysis of crop yield under climate change and adaptation
A. Challinor (2014)
10.5194/GMD-10-1403-2017
Global Gridded Crop Model evaluation: benchmarking, skills, deficiencies and implications
C. Müller (2016)
10.1016/S0959-3780(02)00090-0
The potential impacts of climate change on maize production in Africa and Latin America in 2055
P. G. Jones (2003)
10.1007/s10584-015-1576-y
Extreme hot summers in China in the CMIP5 climate models
Guoyong Leng (2015)
10.1088/1748-9326/10/2/024017
How model and input uncertainty impact maize yield simulations in West Africa
K. Waha (2015)
10.1088/1748-9326/AA7F33
Comparing and combining process-based crop models and statistical models with some implications for climate change
M. Roberts (2017)
10.1073/pnas.0906865106
Nonlinear temperature effects indicate severe damages to U.S. crop yields under climate change
W. Schlenker (2009)
10.1038/NCLIMATE1832
The critical role of extreme heat for maize production in the United States
D. Lobell (2013)
10.1016/J.AGRFORMET.2019.03.010
Integrating satellite and climate data to predict wheat yield in Australia using machine learning approaches
Yaping Cai (2019)
10.1016/J.EJA.2009.06.003
Adaptation to climate change and climate variability in European agriculture: The importance of farm level responses
P. Reidsma (2010)
10.1038/NCLIMATE2470
Rising Temperatures Reduce Global Wheat Production
S. Asseng (2015)
10.5194/GMD-8-261-2015
The Global Gridded Crop Model Intercomparison: data and modeling protocols for Phase 1 (v1.0)
J. Elliott (2014)
10.1016/J.AGSY.2019.05.010
Increasing risks of multiple breadbasket failure under 1.5 and 2 °C global warming
F. Gaupp (2019)
10.1016/J.AGRFORMET.2012.09.011
The Agricultural Model Intercomparison and Improvement Project (AgMIP): Protocols and Pilot Studies
C. Rosenzweig (2012)



Semantic Scholar Logo Some data provided by SemanticScholar