GUI Software consisting of flood prediction and disaster management
This project will consist of following parts:-
i) Flood prediction using machine learning or AI based models.
ii) Development of appropriate disaster management strategy based on the collected data from disasters in the past. (Text mining and sentiment analysis of tweets)
Flood:- It is an overflow of water that submerges land that is usually dry. In the sense of "flowing water", the word may also be applied to the inflow of the tide. Floods are an area of study of the discipline hydrology and are of significant concern in agriculture, civil engineering and public health.
The dataset will be analyzed and fed into machine learning algorithms to predict the occurence of flood based on many factors like precipitation, time-frames of previous occurrences.
Salient feature:-
- Prediction of next month rainfall using RNN with 12 timesteps.
- Logistic Regression to predict flood from rainfall value.
This module will consist of using text mining and sentiment analysis of tweets related to floods. The textual content of social media reflects people's sentiments. Sentiment analysis is a technique in text classification aimed to categorize texts based on conveyed opinions like positive, negative or neutral. This technique would enable us to understand the pros and cons of the current disaster management system and how it can be improved to reduce the loss caused by such disasters. It also shows the involvement of authority in successfully tackling the disaster.
Natural disasters like flood claim numerous lives and cause significant damage to property. There have been many efforts to predict the disasters based on various sources of data. Social Media and Internet have also been helpful important source of information in prediction of the disasters and they have contributed significantly to early detection and adoption for effective disaster management.