It is crucial that this information is available so research can continue to build and improve recovery efforts. Therefore, we have made available process documentation and ample background through the white paper section. Additionally, there is value in opening up the capabilities of the digit tools to local communities. The addition of training tutorials and GitHub repositories aimed at making our research accessible and reproducible in the field.
An overview of the local context and geospatial nature of early recovery as it relates to improving emergency response.
This paper offers an overview of how to control bias in machine learning especially as it relates to damage assessment.
This paper investigates the use of low-code machine learning tools for determining the severity of structural damage following natural disasters.
This paper focuses on the application of deep learning approaches for damage assessment.
This paper aims to provide an understanding of how networks between community organizations and households influence disaster recovery.
A combined report of all white papers and working papers.