Search for: All records

Animals frequently make adaptive decisions about what to prioritize when faced with multiple, competing demands simultaneously. However, the proximate mechanisms of decision-making in the face of competing demands are not well understood. We explored this question using brain transcriptomics in a classic model system: threespined sticklebacks, where males face conflict between courtship and territorial defence. We characterized the behaviour and brain gene expression profiles of males confronted by a trade-off between courtship and territorial defence by comparing them to males not confronted by this trade-off. When faced with the trade-off, males behaviourally prioritized defence over courtship, and this decision was reflected in their brain gene expression profiles. A distinct set of genes and biological processes was recruited in the brain when males faced a trade-off and these responses were largely non-overlapping across two brain regions. Combined, these results raise new questions about the interplay between the neural and molecular mechanisms involved in decision-making. 

Modern climate projections lack adequate spatial and temporal resolution due to computational constraints. A consequence is inaccurate and imprecise predictions of critical processes such as storms. Hybrid methods that combine physics with machine learning (ML) have introduced a new generation of higher fidelity climate simulators that can sidestep Moore's Law by outsourcing compute-hungry, short, high-resolution simulations to ML emulators. However, this hybrid ML-physics simulation approach requires domain-specific treatment and has been inaccessible to ML experts because of lack of training data and relevant, easy-to-use workflows. We present ClimSim, the largest-ever dataset designed for hybrid ML-physics research. It comprises multi-scale climate simulations, developed by a consortium of climate scientists and ML researchers. It consists of 5.7 billion pairs of multivariate input and output vectors that isolate the influence of locally-nested, high-resolution, high-fidelity physics on a host climate simulator's macro-scale physical state.The dataset is global in coverage, spans multiple years at high sampling frequency, and is designed such that resulting emulators are compatible with downstream coupling into operational climate simulators. We implement a range of deterministic and stochastic regression baselines to highlight the ML challenges and their scoring. The data (https://huggingface.co/datasets/LEAP/ClimSim_high-res) and code (https://leap-stc.github.io/ClimSim) are released openly to support the development of hybrid ML-physics and high-fidelity climate simulations for the benefit of science and society.