Long-Distance Wildfire & Smoke Detection is a computer vision dataset designed for early warning and environmental monitoring of forest fires. It aims to improve the model's ability to detect smoke and wildfires in long-distance forest monitoring scenarios and is widely used in research areas such as forest fire prevention, drone inspection, and intelligent monitoring. This dataset was generated using a fully synthetic approach, simulating high-view, long-distance monitoring scenarios such as forest fire towers and ridge surveillance cameras. It focuses on wildfire smoke column detection, which is more easily observed in the early stages of a fire. The dataset includes high-resolution synthetic images and a metadata.json file with annotations, including natural language descriptions and attribute fields such as category, monitoring distance, ecological region, and target visibility. Data categories include Smoke (approximately 901 TP3T) and Wildfire (approximately 101 TP3T), covering diverse ecological environments such as Mediterranean forests, North American woodlands, and tropical Asia.

Citation

@dataset{simuletic_wildfire_smoke_2026,
author = {Simuletic Team},
title = {Long-Range Wildfire & Smoke Detection Dataset},
year = {2026},
publisher = {Kaggle},
url = {https://simuletic.com/datasets}
}