Presentation #402.01 in the session “Mining TESS Data with Machine Learning and Other Advanced Methods”.
All-sky photometric time-series missions have allowed for the monitoring of thousands of young to understand the evolution of stellar activity. Here we developed a convolutional neural network (CNN), stella, specifically trained to find flares in TESS short-cadence data. We applied the network to 3200 young stars to evaluate flare rates as a function of age and spectral type. We also measured rotation periods for 1500 of our targets and find that flares of all amplitudes are present across all spot phases, suggesting high spot coverage across the entire surface. Additionally, flare rates and amplitudes decrease for stars older than 50 Myr across all temperatures hotter than 4000 K, while cooler stars show no evolution across 800 Myr. Cooler stars also show higher flare rates and amplitudes across all ages. We investigate the effects of high flare rates on photoevaporative atmospheric mass loss for young planets and find planets lose 4-7% more atmosphere over the first 1 Gyr in the presence of flares.