Assessing the impact of natural or man-made disasters on operations is vital from a risk management point of view, as elaborated in this workflow related to Hurricane Risk for the Property Insurance sector. During unforeseen circumstances (see: Oil Spills, Forest Fires, Landslides posts), one is compelled to adopt a rapid response mechanism to reduce the extent of damage, provide rescue & relief, and to ensure business continuity. The impact of a halt in operations due to a disaster at a particular node tends to have a ripple effect across the Supply Chain, often magnifying the negative impact. The Thailand Floods of 2011 is often cited as an example - Automotive, Electronics among several other industries were heavily affected by the disruption of manufacturing operations in Thailand. I distinctly remember this phase - it was difficult to procure a new Computer Hard Drive in Mumbai, India in the aftermath of this incident - the product was facing a supply crunch and the prices had shot up through the roof!
In this post, I will highlight two workflows involving the assessment of Damage from Imagery-
gauging the impact from the horrific explosion in Beirut, Lebanon in 2020
automated detection and classification of Road Cracks for preventive maintenance
Both the damage assessment workflows involve the use of different methods - the former is done by analyzing Aerial Imagery while the latter involves the deployment of a GIS-based Deep Learning Framework on the footage captured by a vehicle's dashcam.
Workflow 1 : Assessing Damage from the Explosion in Beirut
I won't demonstrate the methodology of deriving this output, just sharing an overview - initially I obtained two Radar Satellite Imagery datasets prior to the date of explosion (4th August 2020) and estimated its Coherence i.e. the similarity / correlation between pixels at the same spot across both the sets of Imagery. Then, I estimated the Coherence of another two Imagery datasets - one prior to the date of explosion and another after. The difference between the two Coherence estimation outputs is what is depicted in Figure 1 above - the pixels where there is a noticeable change in Coherence values, it is implicative of a significant alteration of the underlying surface - in our case being damage to the buildings and other urban infrastructure.
Note: Figure 1 also contains the Damage extent information as determined by analyzing two Optical Satellite Imagery datasets - prior and post the explosion. However, that output is mostly masked by the Radar Imagery analysis output. This is due to the fact that the latter is more adept at detecting changes in surface features.
The Beirut explosion is one of the largest non-nuclear explosion 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 shockwaves from the explosion was felt even in adjacent countries (>250 kms away). The tragedy sunk the already fledgling economy of Lebanon in further turmoil.
Much thanks to ESA & RUS Copernicus for the training material and Imagery Analytics methodology.
Do read this post if you'd like to initiate your understanding of Satellite Imagery Analytics entails.
Workflow 2 : Detecting and Classifying Road Cracks
This demonstration (Video 1 below) was unveiled by my firm's GIS technology partner - Esri first at its Developer Conference in 2019. I had the good fortune of seeing this Demo later at Esri India User Conference in Kolkata in the same year. It was presented by Divyansh Jha - a Data Scientist at the company. The Deep Learning algorithm was applied on Vehicle Dashcam footage acquired on the Delhi - Faridabad highway. Divyansh indicated that the entire assessment process lasted a month - from capturing the footage to analyzing it and validating the results. The output is invaluable!
Video 1: Road Crack Detection using DL demo video. Methodology can be found here.
From both Time and Cost perspectives - GIS blended with Artificial Intelligence, Machine Learning & Internet-of-Things can be of high utility. With the advent of 5G telecommunications, the scope of modern geo-technology is likely to burgeon.
I have personally used Esri's ready-to-use Deep Learning Model to detect and classify Infrastructure objects - Buildings & Swimming Pools respectively - from Optical Satellite Imagery. The prowess of Deep Learning is impressive - the output left me mesmerized. Here is another video walkthrough involving the usage of Esri's Deep Learning Model to classify Power Lines.
ABOUT US
Intelloc Mapping Services | Mapmyops.com is based in Kolkata, India and engages in providing Mapping solutions 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, some even globally, and will aid an organization to meet its stated objectives especially pertaining to Operational Excellence, Cost Reduction, Sustainability and Growth.
Broadly, our 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 flyer. 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,