Updated November 2024: This story has been updated with the new availability of Stardew's 1.6 update. The popular farming sim and ultimate cozy game Stardew Valley dropped a major update on Tuesday after months of anticipation. Stardew's 1.6 update has an insane amount of new content that touches every area of the game, from new menus and DIYs, to a new farm layout, new crops, and the ability to have multiple pets and play with seven friends at once. It's enough updates to make the game feel fresh, but it isn't so new that you can't ease back into a beloved farm and toil away. As of November 4, 2024, the free update is available for players on all platforms.

The popular farming sim and ultimate cozy game, Stardew Valley, dropped a major update on Tuesday after months of anticipation. Stardew's 1.6 update has an insane amount of new content that touches every area of the game, from new menus and DIYs, to a new farm layout, new crops, and the ability to have multiple pets and play with seven friends at once. It's enough updates to make the game feel fresh, but isn't so new that you can't ease back into a beloved farm and toil away. It's important to note here that the free update is currently only available for PC players. The update will come to mobile and consoles like the Nintendo Switch later on.

This work proposes a novel data-driven model capable of providing accurate predictions for the power generation of all wind turbines in wind farms of arbitrary layout, yaw angle configurations and wind conditions. The proposed model functions by encoding a wind farm into a fully-connected graph and processing the graph representation through a graph transformer. The graph transformer surrogate is shown to generalise well and is able to uncover latent structural patterns within the graph representation of wind farms. It is demonstrated how the resulting surrogate model can be used to optimise yaw angle configurations using genetic algorithms, achieving similar levels of accuracy to industrially-standard wind farm simulation tools while only taking a fraction of the computational cost.