Recently, many countries like Japan, China and the USA have been the victimized by natural disasters resulting in many deaths and damages in millions of dollars. However much precautionary measures had been taken by evacuating thousands of people and preparing for the disasters, the natural disasters still proved to be too strong. However, Roger Wang, Lecturer of Fluid Mechanics in Civil Engineering, University of Dundee thinks that Aritificial Intelligence could prove to have a great potential in mitigating the consequences of natural disasters.
Over the past years, AI has developped significantly. It has also caught up to human understanding as esearchers recently demonstrated that AI could help diagnose breast tumours from the medical imaging. Roger Wang demonstrated in his research paper that AI is able to help monitor floods and could deliver more accurate early warning messages in the near future.
In his research paper, he described how he used two of the most popular AI techniques to monitor tweets and photos streamed from Twitter and a mobile app called MyCoast. These AI-based algorithms can identify the location mentioned in a tweet about flooding and describe the content of the photos to recognise flood scenes through intensive training with “worked examples”, photos manually labelled by humans using keywords. After such training, the trained AI could make a prediction about whether a new photo is a flood scene or not. However, he also mentioned that AI is better than humans in terms of speed and volume, but not in terms of quality. This is especially true of flood monitoring. His research demonstrated that AI could make mistakes in recognising flood scenes. However, this situation might change in the future. Secondly, he mentioned that AI is still weak when it comes to prediction. Although these algorithms can make acceptable forecasts within the scope of the past, predictions become wild when they go beyond the parameters of the training data. In terms of flood-monitoring, then, it is difficult to predict long-term flood trends based on the past training datasets because climate change is fundamentally changing the trend of many hydrological factors. We have no acceptable training data in this case.
Anyway, the most significant difference between AI and humans is that we generate creative solutions, and AI is not capable of providing them. It is merely a tool to facilitate humand understanding and preditcion. It has therefore a long way to go before it catches up with human thinking, creativity and motivation according to Wang (2018).
Evidently it would be a major step towards the future if AI could help us predict natural disasters sooner and help mitigate them more effectively which could save thousands of lives and millions of dollars. With the development which AI is going through nowadays, I think that within 10 years this will be possible. Only time will tell us if this prediction is accurate.
References:
Wang, R., Mao, H., Wang, Y., Rae, C., & Shaw, W. (2018). Hyper-resolution monitoring of urban flooding with social media and crowdsourcing data. Computers & Geosciences,111, 139-147. doi:10.1016/j.cageo.2017.11.008
Wang, R. (2018, September 19). AI could help us manage natural disasters – but only to an extent. Retrieved September 19, 2018, from http://theconversation.com/ai-could-help-us-manage-natural-disasters-but-only-to-an-extent-90777
Hi Ali, thanks for catching up on this recent topic and how it could be influenced by AI. I think AI does play an important role in forecasting across various industries already today. The most popular thereby probably being resource planning in retail. Above that I read a really interesting article about how AI can be used to predict flue outbreaks significantly faster than other centers for disease control can just by checking Google searches and Twitter feeds. This is possible since what are all of us do before going to the doctor? Of course, we do google symptoms and treatments before taking on the hustle to actually wait for hours at the doctor to just get some medications which we could have gotten ourselves at the supermarket. These searches can then be used by AI to draw the conclusion of a flu outbreak. I am convinced that no human is capable of combining the amounts of data AI is able to process and that therefore AI forecasts also in the field of natural disasters will be more accurate than the ones given by humans.