Snap bean production has decreased by ~30% recently due to an increase in imports and changing consumer preferences towards more fresh and frozen products. A major production concern is weed species that escape control, since they cause yield losses and can contaminate harvest loads. Coupled with changing weather patterns, snap bean processors and growers will have to adjust to these and future challenges. Field surveys were conducted to identify associations among crop/weed management practices and environmental factors on snap bean yield and weed density. From 2019-2023, snap bean fields throughout the major U.S. production regions were surveyed for weeds at harvest. Management records for each field were obtained from growers. Information on soil and weather conditions of each surveyed field also was obtained. In total 358 production fields were surveyed in the Midwest (Illinois, Iowa, Minnesota, Wisconsin), Northeast (Delaware, Maryland, New York. Pennsylvania), and Northwest (Oregon, Washington) regions. To determine associations among management and environmental variables on crop yield and weed density, the machine learning algorithm random forest was utilized. The models had 24 and 22 predictor variables for crop yield and weed density, respectively, and both were trained on 80% of the data with the remainder used as a test set to determine model accuracy. Partial dependence plots were used to visualize the change in response variables based on the most important predictors. The crop yield model had pseudo-R2 values of 0.56 and an accuracy of 74%. Higher average temperatures during early season growth, higher soil organic matter content, and planting midseason (June-July) predicted an increase in average crop yield. Meanwhile, excessive precipitation early in the season, high sand content of the soil, high temperatures at crop flowering and row cultivation predicted a decrease in crop yield. The weed density model had pseudo-R2 values of 0.55 and an accuracy of 81%. While row cultivation was associated with lower snap bean yield, it corresponded to a decrease in weed density, suggesting row cultivation had less-than-ideal selectivity between the crop and weed. Moreover, multiple spring tillage operations prior to planting predicted an increase in average weed density, implying that excessive tillage may favor emergence of weeds in snap bean. Over the coming decades, climate change-driven weather variability is likely to influence snap bean production, both directly through crop growth and indirectly through weeds that escape control practices that also are influenced by the weather.
