It has been widely recognized that tropical cyclone (TC) genesis requires favorable large-scale environmental conditions. Based on these linkages, numerous efforts have been made to establish an empirical relationship between seasonal TC activities and large-scale environmental favorabilities in a quantitative way, which lead to conceptual functions such as the TC genesis index. However, due to the limited amount of reliable TC observations and complexity of the climate system, a simple analytic function may not be an accurate portrait of the empirical relation between TCs and their ambiences. In this research, we use convolution neural networks (CNNs) to disentangle this complex relationship. To circumvent the limited amount of seasonal TC observation records, we implement transfer-learning technique to train ensembles of CNNs first on suites of high-resolution climate simulations with realistic seasonal TC activities and large-scale environmental conditions, and then subsequently on the state-of-the-art reanalysis from 1950 to 2019. Our CNNs can remarkably reproduce the historical TC records, and yields significant seasonal prediction skills when the large-scale environmental inputs are provided by operational climate forecasts. Furthermore, by forcing the ensemble CNNs with 20th century reanalysis products and phase 6 of the Coupled Model Intercomparison Project (CMIP6) experiments, we attempted to investigate TC variabilities and their changes in the past and future climates. Specifically, our ensemble CNNs project a decreasing trend of global mean TC activity in the future warming scenario, which is consistent with our dynamic projections using TC-permitting high-resolution coupled climate model.