| Title: | Drone-based community assessment, planning, and disaster risk management for sustainable development |
| Authors: | Whitehurst, D., B. Friedman, K. Kochersberger, V. Sridhar and J. Weeks |
| Year: | 2021 |
| Journal: | Remote Sensing |
| Volume (Issue): | 13(9) |
| Pages: | |
| Article ID: | 1739 |
| DOI: | 10.3390/rs13091739 |
| URL (non-DOI journals): | |
| Model: | SWAT |
| Broad Application Category: | hydrologic only |
| Primary Application Category: | flood impacts or conveyances |
| Secondary Application Category: | urban stormwater and/or BMP assessment |
| Watershed Description: | 4.6 km^2 Dzaleka Refugee Camp, located in Dowa Malawi (other examples are discussed for sites in Afghanistan and Virginia, U.S.). |
| Calibration Summary: | |
| Validation Summary: | |
| General Comments: | More information about the refugee camp is provided at https://www.unhcr.org/en-us/. |
| Abstract: | Accessible, low-cost technologies and tools are needed in the developing world to support community planning, disaster risk assessment, and land tenure. Enterprise-scale geographic information system (GIS) software and high-resolution aerial or satellite imagery are tools which are typically not available to or affordable for resource-limited communities. In this paper, we present a concept of aerial data collection, 3D cadastre modeling, and disaster risk assessment using low-cost drones and adapted open-source software. Computer vision/machine learning methods are used to create a classified 3D cadastre that contextualizes and quantifies potential natural disaster risk to existing or planned infrastructure. Building type and integrity are determined from aerial imagery. Potential flood damage risk to a building is evaluated as a function of three mechanisms: undermining (erosion) of the foundation, hydraulic pressure damage, and building collapse due to water load. Use of Soil and Water Assessment Tool (SWAT) provides water runoff estimates that are improved using classified land features (urban ecology, erosion marks) to improve flow direction estimates. A convolutional neural network (CNN) is trained to find these flood-induced erosion marks from high-resolution drone imagery. A flood damage potential metric scaled by property value estimates results in individual and community property risk assessments. |
| Language: | English |
| Keywords: | drone; aerial imagery; disaster risk management; classification; 3D modeling |