Sustainability and Data science
Development of a near-present, global human footprint index. Using existing data on global HFI, cloud-free satellite data from Landsat, and deep learning (with a convolutional neural network), we have developed the most up-to-date map of the human footprint index. The manuscript is Accepted at Environmental Research Letters, and be sure to checkout the preprint publication here at bioRxiv.
Revealing (potential) blindspots in the thematic content of scenarios research. Using latent Dirichlet analysis (LDA) to identify the latent themes and keywords across a corpus of texts, we aim to augment the human ability to distill thematic content from natural language. We explore this idea in the context of the pan-Arctic region, using a corpus of >1,500 web-based news articles about the future of the region.