How can machine learning help in understanding the impact of climate change on crop yields
Bibliographic Data
| ID | 15545264 |
|---|---|
| Authors | Balsher Singh Sidhu (0000-0002-4141-0028, University of British Columbia, corresponding author), Zia Mehrabi (0000-0001-9574-0420, University of Colorado Boulder), Navin Ramankutty (0000-0002-3737-5717, University of British Columbia), Milind Kandlikar (0000-0001-7368-371X, University of British Columbia) |
| Year | 2023 |
| Volume | 18 |
| Issue | 2 |
| Pages | 024008-024008 |
| Publication date | 2023-01-09 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Environmental Research Letters (JOURNAL) |
| Journal identifiers | ISSN: 1748-9326 • E-ISSN: 1748-9326 |
| Publisher | IOP Publishing (PUBLISHER • GB) |
| DOI | 10.1088/1748-9326/acb164 |
| OpenAlex | W4313855034 |
| Language | EN |
| Citations received | 2 |
| References cited | 35 |
Ordinary least squares linear regression (LR) has long been a popular choice among researchers interested in using historical data for estimating crop yield response to climate change. Today, the rapidly growing field of machine learning (ML) offers a wide range of advanced statistical tools that are increasingly being used for more accurate estimates of this relationship. This study compares LR to a popular ML technique called boosted regression trees (BRTs). We find that BRTs provide a significantly better prediction accuracy compared to various LR specifications, including those fitting quadratic and piece-wise linear functions. BRTs are also able to identify break points where the relationship between climate and yield undergoes significant shifts (for example, increasing yields with precipitation followed by a plateauing of the relationship beyond a certain point). Tests we performed with synthetically simulated climate and crop yield data showed that BRTs can automatically account for not only spatial variation in climate–yield relationships, but also interactions between different variables that affect crop yields. We then used both statistical techniques to estimate the influence of historical climate change on rice, wheat, and pearl millet in India. BRTs predicted a considerably smaller negative impact compared to LR. This may be an artifact of BRTs conflating time and climate variables, signaling a potential weakness of models with excessively flexible functional forms for inferring climate impacts on agriculture. Our findings thus suggest caution while interpreting the results from single-model analyses, especially in regions with highly varied climate and agricultural practices
Agricultural engineering · Agriculture · Climate change · Econometrics · Geography · Machine learning · Meteorology · Ordinary least squares · Precipitation · Range (aeronautics · Regression · Statistics · Yield (engineering · Climate change impacts on agriculture · Climate variability and models · Computer Science · Environmental Science · Hydrology and Drought Analysis · Mathematics · Ecology
Statistics versus machine learning
Relative Importance for Linear Regression in R
Nonlinear temperature effects indicate severe damages to U.S. crop yields under climate change
Statistical Modeling
Greater Sensitivity to Drought Accompanies Maize Yield Increase in the U.S. Midwest
Multivariate Adaptive Regression Splines
Climate Trends and Global Crop Production Since 1980
A working guide to boosted regression trees
Placing bounds on extreme temperature response of maize
Disentangling the separate and confounding effects of temperature and precipitation on global maize yield using machine learning, statistical and process crop models
Machine learning methods for crop yield prediction and climate change impact assessment in agriculture
Global scale climate–crop yield relationships and the impacts of recent warming
The response of maize, sorghum, and soybean yield to growing-phase climate revealed with machine learning
The effects of climate extremes on global agricultural yields
Stochastically modeling the projected impacts of climate change on rainfed and irrigated US crop yields
More uneven distributions overturn benefits of higher precipitation for crop yields
Comparing estimates of climate change impacts from process-based and statistical crop models
Sensitivity of grain yields to historical climate variability in India
Unpacking the climatic drivers of US agricultural yields
Wide adaptation of Green Revolution wheat
Power tariffs for groundwater irrigation in India
| Unique citing works | 2 |
|---|---|
| Citations per year | 1 |
| Citation span | 2024 - 2024 (1) |
| Citation velocity | recent |
| Highly cited | No |
| Citation types | Neutral: 2 |