The objective of this study is to investigate how changing configurations in temperature and precipitation are transmitted to productivity growth in the U.S. agricultural sector. In doing so, we account for farm heterogeneity in production possibilities and the considerable variations in weather and other physical characteristics of the environment. In contrast, the received literature on productivity growth assumes that firms share the same production possibilities and only differ with respect to their level of inefficiency. We do this by implementing a Random Parameters approach in a Stochastic Production Frontier framework. The resulting parameter estimates are used to decompose a multiplicative TFP index that yields measures of technological progress, technical efficiency change, environmental, and scale-mix efficiency. Our results indicate that even after accounting for knowledge stocks generated from investments in research and development there are significant reductions in productivity growth, primarily driven by weather anomalies. Acknowledgement : This study was partially funded by U.S. Department of Agriculture, National Institute of Food and Agriculture grant number 2016-67012-24678 and 2016-67024-24760.