Maqola

Random Forests for Global and Regional Crop Yield Predictions

Jig Han JeongSchool of Environmental and Forest Sciences, College of the Environment, University of Washington, Box 354115, Seattle, WA 98195, United States of AmericaJonathan P. ResopCrop Systems and Global Change Laboratory, USDA-ARS, Beltsville, MD 20705, United States of AmericaNathaniel D. MuellerDepartment of Earth and Planetary Sciences, Harvard University, Cambridge, MA 02138, United States of AmericaDavid H. FleisherCrop Systems and Global Change Laboratory, USDA-ARS, Beltsville, MD 20705, United States of AmericaKyungdahm YunSchool of Environmental and Forest Sciences, College of the Environment, University of Washington, Box 354115, Seattle, WA 98195, United States of AmericaEthan E. ButlerDepartment of Forest Resources, University of Minnesota, St. Paul, MN 55108, United States of AmericaDennis TimlinCrop Systems and Global Change Laboratory, USDA-ARS, Beltsville, MD 20705, United States of AmericaKyo-Moon ShimClimate Change & Agroecology Division, National Institute of Agricultural Science, RDA, Suwon, KoreaJames GerberInstitute on the Environment, University of Minnesota, St. Paul, MN 55108, United States of AmericaVangimalla R. ReddyCrop Systems and Global Change Laboratory, USDA-ARS, Beltsville, MD 20705, United States of AmericaSoo‐Hyung KimSchool of Environmental and Forest Sciences, College of the Environment, University of Washington, Box 354115, Seattle, WA 98195, United States of America

2016en

ABI

Annotatsiya

Accurate predictions of crop yield are critical for developing effective agricultural and food policies at the regional and global scales. We evaluated a machine-learning method, Random Forests (RF), for its ability to predict crop yield responses to climate and biophysical variables at global and regional scales in wheat, maize, and potato in comparison with multiple linear regressions (MLR) serving as a benchmark. We used crop yield data from various sources and regions for model training and testing: 1) gridded global wheat grain yield, 2) maize grain yield from US counties over thirty years, and 3) potato tuber and maize silage yield from the northeastern seaboard region. RF was found highly capable of predicting crop yields and outperformed MLR benchmarks in all performance statistics that were compared. For example, the root mean square errors (RMSE) ranged between 6 and 14% of the average observed yield with RF models in all test cases whereas these values ranged from 14% to 49% for MLR models. Our results show that RF is an effective and versatile machine-learning method for crop yield predictions at regional and global scales for its high accuracy and precision, ease of use, and utility in data analysis. RF may result in a loss of accuracy when predicting the extreme ends or responses beyond the boundaries of the training data.

Hali tarjima qilinmagan

Identifikatorlar

DOI: 10.1371/journal.pone.0156571

Iqtiboslar va manbalar

2 ta iqtibos0 ta foydalanilgan manba

Koʻrsatkichlar — AkademScholar