This opportunity does not have a specified deadline.
In the tropics, forest loss has exceeded forest gain, leading to a net greenhouse gas emission that impacts global climate change. One of the simplest natural solutions to address climate change is, therefore, to protect and expand forests. However, stopping deforestation and forest degradation enough to limit warming to 2 degrees Celsius, the threshold beyond which massive and destabilizing climate events will be inevitable, requires biomonitoring of the carbon in remote rainforests, which can be expensive or impossible due to difficulty with access and poverty of indigenous people (which live near and/or manage more than 40% of all remaining protected lands). In this project, the Engineer Fellow will combine remote sensing data (multi-spectral satellite imagery, radar imagery, and LiDAR) with deep learning and computer vision algorithms to establish a fast, automatic, and cost-efficient generalized AI framework to accurately estimate aboveground carbon density (ACD), at fine-grained resolution, in remote tropical forests. The study area to be focused first is forested areas in Borneo Indonesia. We have obtained satellite imagery (100 GB) for the study region from the LANDSAT (2001-2018), DigitalGlobe Foundation and Planet (2014); attributes include 16-bit raw pixel values and labels, as well as LiDAR data (20 GB) for Borneo taken in 2014 by NASA CMS. A robust AI system would allow transparency in monitoring carbon stocks and deforestation in real-time, which could enhance access to carbon markets for small indigenous communities performing climate mitigation projects that reduce deforestation. Additionally, because we aim to make this tool easy to use for non-experts, the Engineer Fellow will have opportunity to deploy the model to web application in an easy to understand open-source format.
What you will do
work in cross-disciplinary teams to tackle a real world problem
attend weekly meetings to share insights
apply deep learning to advance poverty alleviation and forest conservation
contribute to co-authored publications
networking and resume building
Eligibility and Requirements:
Experience and proficiency with deep learning and computer vision programming. Enthusiasm to apply skills to a real world problem.