We are conducting a large-scale study analyzing brain tissues from mice and humans with different APOE genotypes, using both single-nucleus sequencing and spatial transcriptomics to assess RNA expression differences caused by APOE genotype. We are working with an expert bioinformatics core, but would like a data science student to help perform the analyses and act as an in-lab lead for the bioinformatics analysis. Prior experience analyzing RNA-sequencing data is preferred, but not required.
The main goal of this work is to assess if storms have increased in frequency over Antarctica. It is theorized that climate change will increase the intensity of the winds and frequency of the storms. With ICESat 2 satellite laser altimetry, we can count the number of storms and blowing snow events. ICESat 2 is a photon counting laser and generates terrabytes of data each day. Innovative data science techniques are needed to handle the data and analyze it. This project is, therefore, a suitable topic for a masters student that combines an important problem in Geophysics and climate science with a great Data Science application.
Until today there is no comprehensive theory for formation of tropical cyclones (hurricanes, typhoons). Therefore, it is common to use statistical methods to derive empirical indices as proxies for the probability for genesis. There are also different types of genesis pathways that have been explored in ad-hoc manner. I would like to explore the possibility of using machine learning to explore tropical cyclone genesis, in particular the different pathways in a more comprehensive manner.
We need someone with strong data wrangling capabilities, to be able to determine quick ways to clean and merge data. The format of the data is spatial (GIS) but it could also be manipulated in tabular format. GRID3 is a program within CIESIN which is a research center located at the Lamont-Doherty Campus (with office space on the morningside campus) and is part of Columbia’s Earth Institute. Candidates can learn more about the program at the GRID3 website.
In this project we’ll be expanding on the existing family of supervised topic models. These models extend LDA to document collections where, for each document, we observe additional labels or values of interest. More specifically, one of the goals of this project is to use additional document level data, such as author information, to develop better exploratory data tools.
Targeted phishing is one of the most common and damaging cybersecurity attacks, incurring tens of billions of dollars in losses a year. In order to increase the success of the phishing emails, attackers often craft emails that impersonate real people or legitimate online services, and send them from networks and hosting sites that have a high reputation. This leads major email security services, including Outlook and Gmail, to often misclassify these emails as legitimate.
Humanity thrives along major rivers – this is as true now as it was ages ago. Our dependence on rivers for agriculture and electricity, as well as the need to control its flow because of our proximity, has resulted in dramatic changes to the nature of the rivers. What were once great perennial rivers are now mere trickles during the summer months. This puts the livelihood of many people, especially poor farmers, in jeopardy. How can we monitor and document changes to the flow through rivers over time? Since river gauge measurements are rare or non-existent, any way in which we can use freely available satellite imagery (Landsat, Sentinel) to determine the changes in flow patterns of rivers over time would be extremely useful. One such tool is Rivamap – it uses OpenCV to analyze satellite imagery to extract information about rivers, especially for large rivers. What about smaller ones – it does not seem to work as well. In this project, the student(s) will have to develop machine-learning based methods (or extend the capabilities of Rivamap) to study satellite images to extract information about the path and dimensions of rivers of different flow rates and flow patterns. Comparison with ground-truth data will be needed.
