Non-linear and heterogeneous processes have long challenged our ability to predict environmental systems. Here, we present a semi-autonomous and artificial intelligence (AI)-guided framework that iterates between predictive modeling and targeted in situ sampling to rapidly improve environmental predictions. We demonstrate our workflow by predicting oxygen consumption rates from streambed sediments across the contiguous United States (CONUS), a key process of stream metabolism. Our approach consisted of 18 iterative loops of measurements and models, combining distributed participatory field sampling, lab analysis, automated machine learning (ML) predictions, and error and distinctiveness analyses to autonomously guide the next sampling at optimal site locations. Through our approach, we increased the predictive power of sediment oxygen consumption across CONUS by over fifteenfold between the first and last iteration. Relative to our last sampling iteration, our first sampling missed sites with high rates and underestimated median oxygen consumption rates by 68%. In addition to identifying areas of high oxygen consumption rates, iterations enabled refinement of laboratory and data handling methods, and engagement with a broad community of field researchers. We conclude that AI-guided iterative loops between targeted sampling and predictive modeling are a powerful and efficient approach for improving predictions of heterogeneous environmental processes.
Neural manifolds that orchestrate walking and stopping
Walking, stopping and maintaining posture are essential motor behaviors, yet the underlying neural processes remain poorly understood. Here, we investigate neural activity behind locomotion and