Laura Greenstreet

Aquaculture, or the farming or cultivation of aquatic organisms including fish and shellfish, has the potential to create economic growth with lower land-use, freshwater use, and carbon emissions than traditional livestock. Aquaculture is growing rapidly in the Amazon. However, the location, extent, and life-cycle of operations are poorly understood. Working with Dr. Carla Gomes, I helped develop deep learning methods to detect aquaculture ponds from medium resolution satellite data, using temporal information, attention, and contrastive learning to deal with issues including label imbalance, label bias, and generalization to new regions.

Large mammals often require more space than a single protected area and having connected protected areas is key for gene dispersal. It is important to understand which protected areas are isolated or at risk of isolation. I worked with Dr. Claire Kremen on the first global study of resistance-based connectivity, which takes into account the many possible paths across a landscape. Our results identified areas that are critical for connectivity but remain unprotected and we compared the overlap of these areas with existing conservation prioritization schemes.

Single-cell RNA-sequencing has allowed researchers to get snapshots of gene expression in individual cells. However, as the sequencing process is destructive and disassociates cells within a tissue, there is a need for methods to understand how development occurs in both space in time. I worked with Dr. Geoffrey Schiebinger on projects applying optimal transport to understand developmental trajectories and helped develop GPS-Seq, a manifold-learning approach to spatial transcriptomics that allows cellular positions to be reconstructed without the use of imaging.