Rapid Prototype Design with Machine Learning Visualization for Disaster Prediction

Abstract

The goal of the study is to use machine learning to anticipate floods from weather data and to calculate the relief budget for flood-affected farmers.the web framework provides us with information about past and current floods India, as well as their date and location. We then used the Visual Crossing weather API to obtain historic weather data such as precipitation, humidity, temperature, cloud cover, and windspeed in those areas and during those times. We also performed several data augmentation techniques on this data set, which enabled us to significantly increase the diversity of data available for our training model, without actually collecting new data.Our machine learning model is based on the python sci-kit learn library. We used pandas to generate a data-frame for the dataset, and then tried various machine learning models from Logistic Regression to K-Nearest Neighbors to Random Forest Classification. After experimenting heavily with all of these models, the Random Forest Classifier gave us the highest accuracy of 99.61% on the test set. We proceeded to save our model in a pickle file.Our web app is based on the Flask python framework. We rendered HTML templates – with CSS for styling and JavaScript for added functionality – and integrated it with our machine learning models and datasets via the flask back-end.