Published October 31, 2026 | Version v1

Dataset and code for: Sentinel-2 active-fire detection over complex reflective backgrounds using candidate-based spatial–spectral classification

  • 1. ROR icon Southwest University
  • 2. ROR icon Nanjing University
  • 3. ROR icon Nanjing University of Information Science and Technology
  • 4. ROR icon Anqing Normal University
  • 5. Information Engineering University
  • 6. ROR icon Vrije Universiteit Amsterdam
  • 7. ROR icon University of East Anglia

Description

This repository contains the dataset, source code, and pre-trained model supporting the findings of the study "Sentinel-2 active-fire detection over complex reflective backgrounds using candidate-based spatial–spectral classification".

1. Dataset (Dataset.zip)
This archive contains the datasets used for model training and performance evaluation in the study:
- model_training: Contains the datasets used for model training in this study.
- test: Contains multi-scenario datasets used for testing and evaluating the model's performance, where each subfolder represents data from a different type of land surface.

2. Code and Model (Code_and_Model.zip)
This archive contains the source code for the candidate-based spatial–spectral classification algorithm and the final trained model used in the manuscript.

Files

Code_and_Model.zip

Files (80.5 MB)

Name Size
md5:8fd422f3e8a366551fe4ed07212c67a4
1.8 MB Preview Download
md5:06cb815b01c5f3470e7176ed08f0ae27
78.8 MB Preview Download