Skip to content

This notebook demonstrates timeseries classification for crop identification on a subset of the MiniTimeMatch dataset by training an LSTM model.

Notifications You must be signed in to change notification settings

rajesvariparasa/timeseries-classification-lstm

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 

Repository files navigation

Timeseries Classification using LSTM

Open In Colab

This notebook demonstrates timeseries classification for crop identification on a subset of the MiniTimeMatch dataset by training an LSTM model.

The first two sections of this notebook are dedicated to data exploration and setting up a data preparation pipeline using a custom dataset class. The rest of the notebook deals with the set up and finetuning of the model architecture and the training loop.

Briefly about the data: Each observation in the data consists of a time sequence of 52 observations taken across 10 spectral bands of Sentinel-2. Each observation corresponds to spectral measurements aggregated over a land parcel. The observations are labelled with crop found in the parcel.

Data source: TimeMatch Dataset

About

This notebook demonstrates timeseries classification for crop identification on a subset of the MiniTimeMatch dataset by training an LSTM model.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published