Projects
CC19 - Extract guidance and actions from Climate Change documents using Machine Learning
Project start and end dates:
2020-05-26 to 2020-08-14
We are in the design and planning phase of a new climate change impact planning software product that will recommend a set of actions that ordinary citizens can take to avoid, mitigate, adapt, or rebuild from climate change disasters.
Although there is a wealth of guidance information out there in PDFs or on websites, rather than go through those one by one, we want machine learning NLP and NLU techniques (and others?) to be applied that can automatically extract that kind of guidance from a PDF document or body of text.
A previous class successfully produced a working prototype, using Amazon Web Services and python libraries, that is able to extract actions from PDF files and textual content.
We would like you continue their work and extend their code to further improve the accuracy of this model, overcome some of the identified issues and challenges, explore some of the identified future enhancements, and also inject your own creativity and ideas.
The University at Albany, SUNY interns enhanced the results of a previous machine learning research project to investigate how machine learning techniques could be used to extract meaningful climate change actions from existing content.
They identified promising enhancements including: the possibility of extracting actional text from PDF images; sentiment analysis to identify guidance priority and risk; improved keywords and phrases extraction; sentence extraction rules; and use of KNN classification techniques.
They regularly asked for feedback to adjust and improve their algorithm and coding efforts and align them with our project goals and objectives. They also indicated many areas for future improvement or investigation.
Overall their result was very promising and the techniques they explored provide us with a lot of insight. We are grateful to them for enhancing our machine learning research project.
Thank
You!
We would like to thank Aakar Mathur, Kalpita Dapkekar, and the other interns and teaching staff of VI – Master’s Students: Data Science – Analysis, Business Intelligence, and Machine Learning course. *
* For privacy reasons, we only list people who gave us permission to do so. Did you contribute to this project? Contact us to be added!
Related Project
Software can help the world respond to climate change impacts and disasters.
In 2019 we set out to investigate if there is a need for a solution that gives citizens personalized help preparing for and recovering from climate change impacts and lets trusted authorities assist them and report on their results.
As part of this effort, a great deal of market and technical research was conducted over the last few years. Over 140 students have been involved so far, in dozens of academic institutions in Canada and internationally.
Our greatest finding is the willingness of citizens to take responsibility and help themselves, their neighbors and community plan for, mitigate and recover from climate change impacts and disasters. We also confirmed that a software solution can be built to help overcome the barriers they face when trying to do so.
Now we’re working on a prototype and sharing our findings and progress. Find out more on our OASIS project website!
The State University of New York at Albany, commonly referred to as University at Albany, SUNY Albany or UAlbany, is a public research university with campuses in the New York cities of Albany and Rensselaer and the Town of Guilderland, United States.
A Riipen Project
Riipen is your online platform for virtual project-based learning
Get hands-on support from our students through an in-class project or virtual internship.
- In-class projects allow you to connect with one of our educators to embed your project into the students’ curriculum. Become the real-life case study for students in the classroom!
- Virtual internships are similar to in-person internships, except they are project-based with a clear outcome and the engagement is primarily done online.