leizhang-geo/CNN-LSTM_for_DSM

Using CNN-LSTM deep learning model for digital soil mapping. This is the code for paper "Zhang et al. A CNN-LSTM model for soil organic carbon content prediction with long time series of MODIS-based phenological variables"

33
/ 100
Emerging

This project helps environmental scientists and agricultural researchers create detailed maps of soil organic carbon (SOC) content. By inputting static environmental data (like topography) and dynamic time-series data (like vegetation changes from MODIS satellites), it generates predictions of SOC values. This allows for better understanding of soil health across different regions.

No commits in the last 6 months.

Use this if you need to predict soil organic carbon content using a combination of static spatial environmental variables and dynamic, long-term satellite phenological data.

Not ideal if you do not have your own ground truth soil sample data for training, or if you are interested in predicting other soil properties besides soil organic carbon.

soil-mapping remote-sensing environmental-science agricultural-research land-management
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

89

Forks

15

Language

Python

License

Last pushed

Mar 07, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/leizhang-geo/CNN-LSTM_for_DSM"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.