This Project Grant from the National Science Foundation's Computer and Information Science and Engineering program totaling $600,000 will fund the development of learning-driven models and methodologies for next-generation cellular network internet measurements from October 1, 2022 to September 30, 2025. The Regents of the University of Minnesota, doing business as the Office of Sponsored Projects Administration, will utilize novel ensembles of Gaussian processes to model rich cross-layer features and dynamics. Innovative Bayesian active sampling techniques will also guide the measurement process. Path-breaking tools will be developed to de-bias, de-noise and integrate crowd-sourced measurements that may be missing data, biased, conflicting or adversarial. Outcomes will be integrated into an existing measurement platform to improve sampling, data curation and analytics. The project aims to broadly impact next-generation network measurement, design, deployment and operation.