Earth and environmental science data encompass temporal scales of seconds to hundreds of years, and spatial scales of microns to tens of thousands of kilometers. Because of rapid technological advances in sensor development, computational capacity, and data storage density, the volume, velocity, complexity, and resolution of these data are rapidly increasing. Machine learning (ML), data mining, and other approaches often referred to collectively as artificial intelligence (AI) offer the promise for improved prediction and mechanistic understanding, and the path for fusing data from multiple sources into data-driven and hybrid models comprising both process-based and deep learning elements. For example, an AI framework could be used to integrate the wealth of leaf-level fluorescence and gas exchange measurements (e.g., Leafweb), AmeriFlux and FLUXNET ecosystem fluxes, and Free Air Carbon Dioxide Enrichment (FACE) and Spruce and Peatland Responses Under Changing Environments (SPRUCE) data to develop a unified treatment of stomatal responses, carbon assimilation, and acclimation to changes in hydrology and soil moisture. ML-based models of stomatal conductance and plant hydraulics can be employed to produce a hybrid process-based/ML-based land model for the US Department of Energy’s Energy Exascale Earth System Model (E3SM) with the aim of reducing uncertainties in predictions of soil moisture and carbon assimilation. Such hybrid ecohydrology models could also inform watershed models to deliver dynamic ecological process representations often absent in such models. A variety of environmental characterization, uncertainty quantification, and model prediction approaches will be described, and strategies for applying a new generation of ML methods on high performance computing platforms to Earth and environmental system science will be presented.