Search

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.

Undergraduate hands‐on research can foster innovation and critical thinking among young scholars to delve into real‐world challenges. Specifically, exploring the critical nexus between water usage and agricultural yield, can foster academic growth and holds the key to addressing global food security in an era of increasing environmental constraints, where students can unlock insights crucial to enhancing crop yield and sustainability. Investigating the intricate relationship between water management and crop productivity through undergraduate research is exemplified in this article. Undergraduate students acquired hands‐on research experience by collecting, processing, and analyzing destructive (crop biomass samples) and non‐destructive (plant height, nodes, and leaf chlorophyll content) cropping system data on soybeans under irrigated and dryland production systems, where they worked closely with the farmer. Identifying the current research problem and study site selection, scientific decision‐making during the field study, developing critical thinking while ensuring research communication skills, and quality assurance and quality control through technology during data collection and analysis were learning outcomes. The research highlights the observed distinct performance between irrigated and non‐irrigated soybeans using non‐destructive plant health and growth indicators with plant biomass, following appropriate quality control and assurance steps. Statistically, irrigated soybeans outperformed non‐irrigated soybeans in terms of average plant height at maturity (irrigated: 97.0±1.7 cm vs. non‐irrigated: 37.4±0.6 cm; p<0.01) and number of nodes on the mainstem (irrigated: 19.5±1.2 vs. non‐irrigated: 12.6±0.8; p<0.01). Findings from this study can help ensure quality control and assurance in future cropping system projects. Through the agroecosystem study, we exhibit the importance and role of undergraduate research opportunities in developing the next generation of problem solvers. [ABSTRACT FROM AUTHOR]