Lightning Talks - 02

13 Nov 2021, 17:00 UTC+8
10 minutes each (w/ Q&A)

video on YouTube

Back to schedule

Niccolo Dejito | Cyrus Nikko Pante | Chiara Ledesma | Neyzielle Cadiz

Detecting New Informal Settlements using Satellite Images, AI, and Mobile Apps
Niccolo Dejito
The talk will be about a project we did at Thinking Machines that combined AI, satellite images, and mobile apps to quickly and efficiently detect new informal settlements across Colombia. The purpose is to assist humanitarian organizations in locating communities in need of aid, especially in light of the recent Venezuelan economic crisis and ongoing COVID-19 pandemic.

Diwata QGIS Browser: A QGIS plugin for browsing and loading Diwata-2 SMI products
Cyrus Nikko Pante
It is a tutorial about using Diwata QGIS Browser. It is a QGIS plugin that enables user to browse and load Diwata-2 Spaceborne Multispectral Imager (SMI) products. It uses technologies Spatiotemporal Asset Catalog (STAC) to search for these image and loads a Cloud Optimized GeoTiFF (COG) product.

Interpretable Poverty Mapping using Social Media Data, Satellite Images, and Open Geospatial Data
Chiara Ledesma
Access to accurate, granular, and up-to-date poverty data is essential for humanitarian organizations to identify vulnerable areas for poverty alleviation efforts. Recent works have shown success in combining computer vision and satellite imagery for poverty estimation; however, the cost of acquiring high-resolution images coupled with black box models can be a barrier to adoption for many development organizations. In this study, we present an interpretable and cost-efficient approach to poverty estimation using machine learning and readily accessible data sources including social media data, low-resolution satellite images, and volunteered geographic information. Using our method, we achieve an R2 of 0.66 for wealth estimation in the Philippines, compared to 0.63 using computer vision. Finally, we use feature importance analysis to identify the highest contributing features both globally and locally to help decision makers gain deeper insights into poverty.

Message from DOST-ASTI
Neyzielle Cadiz

Creative Commons License
This work and its contents is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Other works (software, source code, etc.) referenced in this website are under their own respective licenses.
This site is powered by Jekyll and hosted on Github (view source)