Agriculture’s global environmental impacts are widely expected to continue expanding, driven by population and economic growth and dietary changes. This Review highlights climate change as an additional amplifier of agriculture’s environmental impacts, by reducing agricultural productivity, reducing the efficacy of agrochemicals, increasing soil erosion, accelerating the growth and expanding the range of crop diseases and pests, and increasing land clearing. We identify multiple pathways through which climate change intensifies agricultural greenhouse gas emissions, creating a potentially powerful climate change–reinforcing feedback loop. The challenges raised by climate change underscore the urgent need to transition to sustainable, climate-resilient agricultural systems. This requires investments that both accelerate adoption of proven solutions that provide multiple benefits, and that discover and scale new beneficial processes and food products.

Accurate and cost-effective quantification of the carbon cycle for agroecosystems at decision-relevant scales is critical to mitigating climate change and ensuring sustainable food production. However, conventional process-based or data-driven modeling approaches alone have large prediction uncertainties due to the complex biogeochemical processes to model and the lack of observations to constrain many key state and flux variables. Here we propose a Knowledge-Guided Machine Learning (KGML) framework that addresses the above challenges by integrating knowledge embedded in a process-based model, high-resolution remote sensing observations, and machine learning (ML) techniques. Using the U.S. Corn Belt as a testbed, we demonstrate that KGML can outperform conventional process-based and black-box ML models in quantifying carbon cycle dynamics. Our high-resolution approach quantitatively reveals 86% more spatial detail of soil organic carbon changes than conventional coarse-resolution approaches. Moreover, we outline a protocol for improving KGML via various paths, which can be generalized to develop hybrid models to better predict complex earth system dynamics.