Assess the vulnerability of Indian coastal regions to cyclones. What lessons can be learnt from National Cyclone Risk Mitigation Program (NCRMP) in disaster management?

Demand of the Question:
Introduction: Briefly define cyclones
Body: Discuss the vulnerability of East and west coast of India to cyclones
Briefly introduce NCRMP and its success
Conclusion: As per context
Cyclones are well-developed low-pressure systems into which violent winds blow. With a coastline of 7516 km, India is exposed to nearly 10% of the world’s tropical cyclones and close to 5,700 km of coastline is prone to cyclones and tsunamis. There are 13 coastal states/UTs and 40% of the total population living within 100 km of the coastline – thus aggravating the challenge of rehabilitation in case of disasters.
Cyclones occur in the month of May-June and October-November, with primary peak in November and secondary peak in May (pre-monsoon). These cause large-scale destruction of lives, livelihood opportunities, and physical infrastructure and impacts country’s GDP adversely.

The East coast, especially the areas of AP, Odisha, Tamil Nadu, West Bengal and Puducherry, is more affected than the West coast of India. More than 80% of the cyclones witnessed by India have affected the eastern coast only. Over 58% of cyclones that develop in the Bay of Bengal approach and cross the East Coast in October-November and nearly 30% in the pre-monsoon season. One reason for higher vulnerability of the East coast is the sea-surface temperature which is higher for the Bay of Bengal than the Arabian Sea, leading to the formation of more cyclonic systems. High density of this coast hinders quick evacuation and leads to high losses.
Gujarat is the most vulnerable on the West Coast. Nearly 25% of the cyclones that develop over the Arabian Sea approach the West Coast in October-November as well as in the pre-monsoon season

A Saviour against Cyclones: In 2010, the Government of India has initiated the National Cyclone Risk Mitigation Project (NCRMP) to address cyclone risks in the country. The overall objective is to undertake suitable structural and non-structural measures to mitigate the effects of cyclones and improve preparedness in the coastal regions of India. The NCRMP has identified 13 cyclone-prone States and Union Territories (UTs), with varying levels of vulnerability based on the frequency of occurrence of cyclone, size of population and the existing institutional mechanism for disaster management. It focuses on following dimensions:

  1. Improved early warning dissemination systems
  2. Enhanced response capacity of local communities
  3. Improved access to emergency multi-purpose cyclone shelter, construction of roads and bridges for speedy evacuation etc.
  4. Strengthening the Disaster Risk Mitigation capacity at central, state and local levels in order to enable mainstreaming of risk mitigation measures into the overall development agenda.
    The results were visible when loss suffered in terms of human and animal lives during cyclone ‘Phailin’ 2013 and cyclone ‘Hudhud’ in 2014 was minimal as compared to 10000 casualties during Great Orissa Cyclone of 1999. As IMD forecasted and alerted the citizens of Odisha at an early stage, necessary evacuation and preparedness measures were taken on time, which led to a minimal loss of life and infrastructure. The continuous improvement in the NCRMP in order to minimise losses to infrastructure, coastal agriculture and horticulture also offers a valuable lesson in disaster preparedness and risk reduction through community engagement.
Comment on the life-saving potential of Artificial Intelligence in Disaster Management.

Demand of the Question:
Introduction: Define Artificial Intelligence
Body: Highlight role of AI in various stages of disaster management and provide examples of its use
Conclusion: Way forward on how to integrate AI in disaster management lifecycle
Artificial Intelligence (AI) is a term used for simulated intelligence in machines, which are programmed to mimic humans in a rational manner to achieve specific goals like visual perception, speech recognition, decision-making, and translation between languages. Due to its diversified application, .AI can be leveraged to save lives and infrastructure in disaster situations. AI can Help in addressing the information needs covering all the phases of disaster management such as, preparedness, early warning, response, relief, rehabilitation, recovery and mitigation. It is useful in integrating natural hazard assessments into development planning studies.

The datasets obtained from IoT devices, sensors and satellites could be analyzed by the AI-powered systems to understand the magnitude and the patterns of natural disasters such as floods, earthquakes and tsunamis, which can help in better planning of infrastructure in disaster-prone areas.
a. Early warning in various disasters:
• Earthquakes: Artificial intelligence can use the enormous amount of seismic data to analyze the magnitude and patterns of earthquakes. For example, Google and Harvard are developing an AI system that can predict the aftershocks of an earthquake. Scientists have studied more than 131,000 earthquakes and aftershocks to build a neural network.
• Floods: Google is building an AI platform to predict floods in India and warn users via Google Maps and Google Search. The data for training the AI system is collected with the help of rainfall records and flood simulations. Alternatively, AI can also be used to monitor urban flooding.
• Volcanoes: training AI to recognize tiny ash particles from volcanoes. The shape of the ash particles can be used to identify the type of volcano. IBM is developing Watson that will predict volcanic eruptions using seismic sensors and geological data
b. Identifying at-risk communities, vulnerable systems and location of impact – can be used to improve decision-making about the issuing of building permits and insurance
c. Translating message to various languages through AI and Location Based Alert System (LBAS). based on threat status to a particular area
d. Identifying structural damages in dams, bridges, nuclear plants etc
e. AI could help develop new models by incorporating population growth and climate change to study likely disasters

    AI could be used to scrape information from millions of social media posts and clue rescue workers in to the hardest hit areas and people in the most need.
    After a disaster, insurance providers are inundated with claims. AI could help sift through claims data, and help insurance companies identify high-priority claims, streamlining the process for everyone involved. AI could further enhance recovery efforts by:
    ● Analyzing data from Drone and satellite imagery and IoT infrastructure data
    ● Use of AI-powered chatbots
    ● Data analysis from 911 and reverse 911 systems
    ● Social media data and Online heat maps
    Despite its immense potential in the field of disaster management, there is low intensity of AI research, lack of enabling data ecosystem, and unattractive Intellectual property regime to incentivise private sector to invest in AI based disaster management tools.
    Following steps should be taken to mainstream AI in disaster management:
    ● Collaboration between government agencies such as IMD, Ministry of earth sciences etc with Private players and universities
    ● A national AI database to create enabling environment for innovation
  3. ● Re-skilling and up-skilling to create AI ready workforce
  4. For furthering the Disaster resilience through AI, it should be a critical component of programmes like Make in India, Skill India and Digital India
  6. The pilot project done by Google in collaboration with the Central Water Commission, to estimate the flood level situation in Patna. Google claims that its AI based model was used to send a map-based alert to people who lived within thousand square kilometers around Patna. The accuracy of its model was over 90 per cent.
  7. Odhisa launched web and smartphone-based platform called “SATARK” to provide real time watch, alert and warning information for different hazards like heatwave, lightning, agriculture risk (drought), flood monitoring, ocean state information and tsunami risk, earthquake monitoring, cyclone/storm surge for improved disaster management. The system utilises a “machine learning algorithm” to self-learn from each seasonal cycle of operation, and improving on its own advisory generation process, over season. The system translates generic weather forecast products into user-friendly actionable advisories.
  8. Recently, students from IIT Madras developed an AI-enabled drone that can help authorities provide vital information on people trapped in disaster-hit areas.
  9. Kerala State IT Mission developed a crisis management system following the crowdsourcing method where text-based rescue requests posted were enhanced to capture geo-coordinates automatically and the geo-tagged information provided by the people in this portal. The flood of requests received in the portal were subjected to artificial intelligence-based algorithms to prioritise on the basis of key words such as elderly, urgent, pregnant, sick, ladies only, etc. Based on the prioritisation chart, the geo tags attached to the request were subjected to analysis utilising geo intelligence framework to generate cluster maps and heat maps which were handed over to the naval and disaster management authorities.


No comments yet. Why don’t you start the discussion?

Leave a Reply

Your email address will not be published. Required fields are marked *