In a recent interview on the Sirasa Pathikada programme, Professor Rohan Samarajiva, Chair of LIRNEasia, shed light on the potential of Artificial Intelligence (AI) in addressing various challenges and emphasised the need for mindful use of this technology for public benefit. He began by explaining the basic concepts of AI, distinguishing between general AI and narrow AI using simple examples. Prof. Samarajiva then highlighted the application of AI in disaster management, specifically in predicting floods. Drawing attention to Google’s flood forecasting system for the Ganga River in India, he described how AI utilises data from rainfall forecasts, river levels, and historical flood data to generate flood risk maps. 
In a recent interview on the Sirasa Pathikada programme, Professor Rohan Samarajiva, Chair of LIRNEasia, shed light on the potential of Artificial Intelligence (AI) in addressing various challenges and emphasised the need for mindful use of this technology for public benefit. He began by explaining the basic concepts of AI, distinguishing between general AI and narrow AI using simple examples. Prof. Samarajiva then highlighted the application of AI in disaster management, specifically in predicting floods. Drawing attention to Google’s flood forecasting system for the Ganga River in India, he described how AI utilises data from rainfall forecasts, river levels, and historical flood data to generate flood risk maps.
I was invited to speak at the launch of the UNDP-funded DataSmart initiative of the Ministry of Disaster Management, where some work is being done by Sarvodaya Fusion. I talked about the need not only to collect data, but also to ensure that it produced the right kind of information that could be translated by the beneficiaries into action that saved lives and protected assets and livelihoods. We need to think beyond generalized disaster warnings to provide people in particular locations with specific, actionable information that they could use, such as the river will crest in this particular location at x meters at this specific time. I went on to talk about the need to have more granular rainfall data that could be fed into models that could yield the kinds of actionable information people living in our river valleys could use. The attenuation of microwave transmissions caused by rainfall is built into the operation of the ubiquitous mobile networks.
The two-day workshop (Oct 17 & 18, 2016) in Moratuwa, invited Sarvodaya members from Batticaloa, Colombo, Gampaha, and Kegalle Districts. These participants have first-hand experience responding to the 2016 Western floods & landslide and the 2015 Northeast floods, in Sri Lanka. The objective was to share their tacit knowledge on taking a holistic and practical approach to responding to crises. Then give them the tools to analyze the experience to develop the Standard Operating Procedures (SOPs) themselves. To that end, we applied community engagement social practices methods for analyzing the knowledge to realize the design parameters for developing the Sarvodaya Disaster Response SOP.
LIRNEasia has worked with Sarvodaya, one of Sri Lanka’s well-established community-based organizations, since the 2004 Indian Ocean tsunami. As part of our HazInfo project, they established a disaster response unit and embedded resilience as part of their work plans and training. They had come to think that the government would take the lead in providing immediate assistance in the aftermath of a disaster because a Ministry focused on disaster management had been established and the various entities under it active. The urban flood disaster that hit the lower reaches of the Kelani river made them rethink their stance. The government response was seen as slow and ineffective.
We have been kicking around the idea of giving insurance a greater role in disaster risk reduction and response since 2005. Just a few months back I raised the issue at a workshop at UN ESCAP. In an interview with a Sinhala newspaper last week, I said it was a pity we were not anchoring compensation for flood damage on insurance principles and just giving out money. But here is good news. Too often, we criticize governments for sins of omission and commission.
Our disaster-relief partner Sarvodaya organized a small event at the community center at Pahala Bomiriya to hand over the remainder of the relief supplies to affected families. I was invited to say a few words. I talked about the need to build more resilient communities so that we could respond to hazards better in the future. The science of being able to forewarn people of floods exists. What we need to do is to implement the available solutions.
Sahana was developed by volunteer software engineers under the aegis of the Lanka Software Foundation in the months and years after the 2004 Indian Ocean Tsunami. It was handed over to an international foundation when I served as Chair of LSF. Nuwan Waidyanatha who cut his teeth on disaster research as part of the Hazinfo project, is now a leading trainer and part of the team guiding development of Sahana. Despite my best efforts to get those involved in the early development of the software interviewed for this story (triggered by one of my tweets), we are the only sources for information on Sahana in this Sunday Times story. There are allegations that the authorities could have utilised locally-available systems that could have helped to better coordinate disaster relief efforts.
Smith Dharmasaroja is on the ball, again. He was right in telling Thais to get ready for a tsunami, and he’s right in telling them they have caused the conditions for the floods. Floods are the biggest problem for most Asian countries. Attention must be paid. As some of Thailand’s worst flooding in half a century bears down on Bangkok — submerging cities, industrial parks and ancient temples as it comes — experts in water management are blaming human activity for turning an unusually heavy monsoon season into a disaster.
It’s been some time since we carried anything on dam safety. This California story is scary. People tend to underestimate the power of floods: six inches of fast-moving water can knock you down; two feet of water can float most cars away. Floods kill an average of 127 Americans a year — more than tornadoes or hurricanes — and cause more than $2 billion of property damage annually, according to the National Oceanic and Atmospheric Administration (corrected). This spring, the nation was riveted by images of blown levees and submerged towns in the Midwest along the Mississippi River.
National Early Warning System: Sri Lanka (NEWS:SL): A Participatory Concept Paper for the Design of an Effective All-Hazard Public Warning System (Version 2.1) Annexes: A Participatory Concept Paper for the Design of an Effective All-Hazard Public Warning System (Version 2.1) *Executive Summary*# *The 2004 Indian Ocean tsunami that claimed the lives of one in 500 of Sri Lanka�s people and displaced one in twenty has highlighted the critical importance of an effective National Early Warning System for Sri Lanka (NEWS:SL)*. Meeting this need, which has been discussed (and forgotten) after each of our too frequent disasters such as the cyclones of 1978 and the floods of 2003, can no longer be postponed. # *Public warning is a system, not a technology*.