Welcome to Francis Academic Press

Academic Journal of Environment & Earth Science, 2021, 3(1); doi: 10.25236/AJEE.2021.030111.

A Research Based on Machine Learning of Satellite Data Modelling and Image Deep Convolution Learning Model


Zhan Shu

Corresponding Author:
Zhan Shu

Brooks School, North Andover, MA, United States


The issue of fires causing damage in the life of people has been especially prevalent in the past year around the world in larger events and through this project computer learning models are able to detect and recognize them with high accuracy and functions as a potential solution towards the reduction of damage caused by fires. During the first stage we use satellite imaging in order to detect the areas where a wildfire could be started and then after the areas are identified we move to stage 2 of the program where we would use closer monitors over the area in the form of images in order to identify whether or not there is a fire in the area or not. Once the it is confirmed that there the area the local fire department could then be contacted to resolve the issue.


wildfire detection, data preprocessing, machine learning, convolutional neural network, image classification, satellite real-time prediction

Cite This Paper

Zhan Shu. A Research Based on Machine Learning of Satellite Data Modelling and Image Deep Convolution Learning Model. Academic Journal of Environment & Earth Science (2021) Vol. 3 Issue 1: 52-58. https://doi.org/10.25236/AJEE.2021.030111.


[1] https://www.fire.ca.gov/incidents/2020/.

[2] Yu, B., et al. "Fire Risk Prediction Using Remote Sensed Products: A Case of Cambodia." Photogrammetric Engineering and Remote Sensing 83.1(2017):19-25.

[3] Wang, Y. B., and M. A. Xian-Min. "Image-based prediction and recognition method for exogenous-fire in coal mine." Journal of Xi’an University of Science and Technology (2012).

[4] Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "ImageNet classification with deep convolutional neural networks." Communications of the ACM 60.6 (2017): 84-90.

[5] http://proceedings.mlr.press/v97/tan19a.html Tan, M. & Le, Q.. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97: 6105-6114 Available from.