The DownLinQ
Published in

The DownLinQ

Puerto Rico: Electrical & Infrastructure recovery post-Maria

Puerto Rico suffered severe damage from the category 5 hurricane (Maria) in September 2017. Total monetary damages are estimated to be ~92 billion USD, the third most costly tropical cyclone in US history. The response to this damage has been tempered and slow moving, and the blackout as a result of Maria has been identified as the largest in US history and the second largest in world history.

Consequently, we developed a unique data-fusion mapping approach and the first independent remote sensing assessment of the recovery of electricity and infrastructure in Puerto Rico. Our approach incorporates a combination of time series visualizations and change detection mapping to create depictions of power or infrastructure loss and identify areas that are still struggling to recover. For this workflow, our approach leverages CometTS and combines VIIRS nighttime imagery, multispectral imagery from two Landsat satellites, US Census data, and crowd-sourced building footprint labels.

Based upon our analysis, we successfully identify and evaluate: 1) the recovery of electrical power compared to pre-storm levels, 2) the location of potentially damaged infrastructure that has yet to recover from the storm, and 3) the number of persons without power over time. As of May 31, 2018, declined levels of observed brightness across the island indicate that 13.9% +/- ~5.6% of persons still lack power and/or that 13.2% +/- ~5.3% of infrastructure has been lost. In comparison, the Puerto Rico Electric Power Authority states that less than 1% of their customers still are without power, which appears to be a substantial underestimation based upon our findings.

In this blog we are pleased to showcase some of the results of this analysis and to release a paper :

The following figures, videos, and methods are described in depth in the paper. A full presentation on this research will occur at the SPIE Remote Sensing Conference in Berlin, Germany (September 10-13, 2018).

Video 1. This video depicts a visualization of the percentage difference between observed brightness and expected brightness derived from an autoregressive integrated moving average (ARIMA) forecast model from April 2017 — May 2018 for all census tracts in Puerto Rico.
Figure 1. A visualization of the estimated persons without power across all of Puerto Rico. Puerto Rico Power Authority (PREPA) estimates are in red, and VIIRS derived estimates are in black. Any gaps between PREPA estimates are interpolated. The mean absolute deviation from the ARIMA derived seasonal trend line before the storm is visualized around the VIIRS derived estimates in gray. Our findings showed that as of May 31, 2018, declines in brightness levels across the island indicate that 13.9% +/- ~5.6% of persons still lack power and/or that 13.2% +/- ~5.3% of infrastructure has been lost. The PREPA states that less than 1% of their customers still are without power, which appears to be a substantial underestimation. Note that the two spikes in April are sudden (≤24 hours) power outages that affected large portions of the island. Our VIIRS estimates operate on a monthly scale, and are not sensitive enough to detect these sudden spikes.
Video 2. This video depicts a visualization of change in the Urban Development Index (UDI) (percent impervious multiplied by nighttime brightness) from April 2017 — May 2018 for San Juan and Caguas, Puerto Rico. Areas that have a UDI value of zero are made transparent.
Video 3. This video depicts a visualization of changes over time for via subtracting a pre-storm composite UDI (percent impervious multiplied by nighttime brightness) from monthly UDIs for San Juan and Caguas, Puerto Rico. Areas that have a UDI change value of zero are made transparent.
Video 4. This video depicts a visualization of change in the Urban Development Index (UDI) (percent impervious multiplied by nighttime brightness) from April 2017 — May 2018 for Humacao, Puerto Rico and the surrounding rural communities. Areas that have a UDI value of zero are made transparent. Note the lack of recovery and electrification in the western rural communities.
Video 5. This video depicts a visualization of the percent difference of monthly UDIs versus a pre-storm composite UDI (percent impervious multiplied by nighttime brightness) for Humacao, Puerto Rico and the surrounding rural communities. Areas that have a UDI change value of zero are made transparent. Recovery occurs fastest at resorts, the industrial park, and university.

--

--

--

As of March 2021, CosmiQ Works has been folded into IQT Labs. An archive will remain here to showcase historical work from CosmiQ Works that took place July 2016 — March 2021.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Jake Shermeyer

Jake Shermeyer

Data Scientist at Capella Space. Formerly CosmiQ Works.

More from Medium

Actors, security, and privacy: should you be concerned?

Sparking Collaborations with pyQuARC

Processing MicaSense Multispectral Imagery with DroneMapper

Predictive Modelling in Archaeology- Introduction