Data Science and Deep Learning in Natural Sciences

We are producing and consuming more data than ever before. Massive data allow us to better understand the world around us, yet they bring a new set of challenges due to their inherent noise and sheer enormity in size. Without smart algorithms and infrastructures, big data problems will remain intractable, and the same is true in natural science research. The mission of data science as a research field is to develop and apply computational methods in support of and in the replacement of costly practices in handling data. In this talk, I will introduce how data science and deep learning has been used for solving various problems in natural sciences. In particular, I will present a case study of analyzing high-resolution satellite images to infer socioeconomic scales of developing countries.