Tokyo Kion-On: Query-Based Generative Sonification of Atmospheric Data
This work addresses the need for more engaging climate data visualization tools for researchers and the public, though it is incremental in applying existing sonification methods to a specific dataset.
The paper tackles the problem of making climate data more accessible by developing Tokyo kion-on, a query-based sonification model that converts Tokyo's air temperature data from 1876 to 2021 into music using an LSTM with attention architecture trained on Japanese melodies, resulting in a system that enables interactive exploration of the data through adjustable hyper-parameters.
Amid growing environmental concerns, interactive displays of data constitute an important tool for exploring and understanding the impact of climate change on the planet's ecosystemic integrity. This paper presents Tokyo kion-on, a query-based sonification model of Tokyo's air temperature from 1876 to 2021. The system uses a recurrent neural network architecture known as LSTM with attention trained on a small dataset of Japanese melodies and conditioned upon said atmospheric data. After describing the model's implementation, a brief comparative illustration of the musical results is presented, along with a discussion on how the exposed hyper-parameters can promote active and non-linear exploration of the data.