4.6 Article

Grey- and rough-set-based seasonal disaster predictions: an analysis of flood data in India

Journal

NATURAL HAZARDS
Volume 97, Issue 1, Pages 395-435

Publisher

SPRINGER
DOI: 10.1007/s11069-019-03651-y

Keywords

Seasonal disaster prediction; Grey theory; Rough set theory; Floods; Supply chains

Funding

  1. Indian Institute of Technology Madras, Chennai, India

Ask authors/readers for more resources

In a globally competitive market, companies attempt to foresee the occurrences of any catastrophe that may cause disruptions in their supply chains. Indian subcontinent is prone to frequent disasters related to floods and cyclones. It is essential for any supply chain operating in India to predict the occurrence of any such disasters. By doing so, the disaster management and the relief teams can prepare for the worst. This research makes use of a grey seasonal disaster prediction model to forecast the possible occurrence of any flood-related disasters in India. Flood data of major flood occurrences for a period of 10years (2007-2017) have been taken for analysis in this context. We have established a grey model of the first order and with one variable, GM (1, 1), for prediction; from the results, we observe there are high chances of occurrence of a flood-related disaster in India during the early monsoon period (June-August), in both 2018 and 2020. By observing the prediction sequences on fatalities, there is likelihood that the death toll may rise above 100 and the flood can result in disastrous consequences. Also, the results of prediction are compared using an enhanced rough-set-based prediction model. From the results of rough-set-based prediction model, there are chances of a severe flood in mid-2018 in India. The results will be useful for organizations, NGOs and State Governments to carefully plan their supply and logistics network in the event of disasters.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.6
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available