Inspiration
The current surge in flooding in South Asia vicinity due to multiple reasons such as global warming needed prompt attention which led us to design a model that helped to identify affected area so that the rescue operations can be performed in an optimized way.
What it does
It identifies low-lying areas affected by the floods using a machine learning model and satellite images.
How we built it
Gathering a dataset, and training the model using mobilenet_v3_large.
Challenges we ran into
The required dateset were humongous and we had limited resources.
Accomplishments that we're proud of
We were able to complete it in time, that's all.
What we learned
We can address and solve more problems using machine learning, which can potentially save us from other natural disasters or at least we can mitigate the casualties that may be caused.
What's next for aws-disaster-response-folio3-teamB
Finding more required datasets of particular areas that we are interested and train other models on those datasets.
Built With
- machine-learning
- python
- pytoch
- sagemaker
- torch-vision
Log in or sign up for Devpost to join the conversation.