Assessing the impact of natural or man-made disasters on supply chain operations is vital, as elaborated in this workflow on monitoring risk to property insurers from cyclonic activity. The impact of disruption in operations due to an unforeseen situation at a particular node tends to have a ripple effect across the supply chain, often amplifying the negative impact - the Thailand Floods of 2011 is routinely cited as a real-life example - where Automotive, Electronics among several other industries were heavily affected globally. I recollect that it was difficult for me to procure a new computer hard drive in Mumbai in the aftermath of this incident - the product was facing a supply crunch and the prices of existing stock was soaring. Therefore, in order to mitigate the impact from unforeseen circumstances (refer my Oil Spill, Forest Fire, Landslide detection posts), one is compelled to lay in place a rapid response system which could help reduce the extent of damage, provide relief, initiate backup and ensure business continuity.
In this post, I will highlight two workflows involving the Assessment of Damage from Imagery-
The former was done by processing Satellite Imagery while the latter involved the deployment of a Deep Learning algorithm on the footage acquired by vehicle dashcam.
Workflow 1 : Assessing Damage from the Explosion in Beirut in 2020
The Beirut explosion was one of the largest non-nuclear explosions till date. While heavy casualties were restricted to the vicinity of the explosion site, the loss to infrastructure and property occurred even tens of kilometers away. The intensity of the explosion was such that the shockwaves travelled as far as neighbouring country Cyprus located more than 250 kilometers away! As a result, the already fledgling economy of Lebanon braces for a period of turmoil.
While you can see the video demonstration of the Satellite Imagery Analytics involved here, let me summarize it. Initially, I obtained two Synthetic Aperture Radar (SAR) Satellite Imagery datasets both acquired prior to the explosion and estimated its Coherence (in simple terms, this is an expression of how similar are the surface features across both the datasets) - the technical term for this entire procedure leading upto Coherence estimation is known as Interferometric SAR (InSAR).
Subsequently, I proceeded to estimate the Coherence between another two datasets - acquired prior and after the explosion respectively. The comparison of these two Coherence outputs helps reveal the damage to the buildings and other urban infrastructure - this can be inferred from those pixels where there has been a noticeable change in Coherence values, indicative of the fact that the underlying surface has been significantly altered. While a drastic shift in Coherence can be due to other factors such as agriculture harvesting for example, one can systematically rule them out through general understanding of the terrain (Beirut being an urban centre) and if needed, through ground-truthing.
Figure 1 also depicts the damage extent derived from the analysis of two Multispectral Satellite Imagery datasets acquired prior and post the explosion respectively - the process entailed change-detection between near infrared reflectances (while Sentinel-1 SAR Imagery is acquired through an active sensor onboard the satellite which sends pulses of microwaves towards the earth, Sentinel-2 Multispectral Imagery is acquired passively - by capturing reflected Solar radiation from earth). However, that output (as depicted in Figure 2 below) is mostly obscured by the InSAR output as the latter is more adept at detecting structural/geometric changes to the surface features - an aspect that is particularly applicable for this workflow.
Workflow Credits: ESA & RUS Copernicus
Do read this post if you'd like to understand Satellite Imagery Analytics in more detail.
Workflow 2 : Detecting and Classifying Road Cracks
I was exposed to the demonstration on Automated Road Surface Investigation using Deep Learning by my firm's GIS partner - Esri - at its Developer Conference in Kolkata in 2019 (it was presented by Divyansh Jha - data scientist at the company). The algorithm was applied on Vehicle Dashcam footage acquired on the Delhi-Faridabad highway. Divyansh indicated that the entire assessment process lasted a month - right from capturing the footage to analyzing it and validating the results.
Let me share with you the video footage of a similar demonstration from another User Confefrence-
As you'd concur, these types of studies and its potential impact on road safety is invaluable!
From both, time and cost perspective, geospatial analysis aided by Artificial Intelligence, Machine Learning and Internet-of-Things can be of high utility. With the advent of 5G telecommunications, the usage of such algorithms is anticipated to become more mainstream.
I have personally used Esri's ready-to-use Deep Learning Model to detect and classify Building Footprint and Swimming Pools from Aerial Imagery previously. The prowess of the algorithm is very impressive - its output left me mesmerized. Here is another video walkthrough entailing the usage of Esri's Deep Learning algorithm to identify and classify Powerlines.
ABOUT US
Intelloc Mapping Services, Kolkata | Mapmyops.com offers Mapping services that can be integrated with Operations Planning, Design and Audit workflows. These include but are not limited to Drone Services, Subsurface Mapping Services, Location Analytics & App Development, Supply Chain Services, Remote Sensing Services and Wastewater Treatment. The services can be rendered pan-India and will aid your organization to meet its stated objectives pertaining to Operational Excellence, Sustainability and Growth.
Broadly, the firm's area of expertise can be split into two categories - Geographic Mapping and Operations Mapping. The Infographic below highlights our capabilities-
Our Mapping for Operations-themed workflow demonstrations can be accessed from the firm's Website / YouTube Channel and an overview can be obtained from this brochure. Happy to address queries and respond to documented requirements. Custom Demonstration, Training & Trials are facilitated only on a paid-basis. Looking forward to being of service.
Regards,