The use of convolutional neural networks to forecast the dynamics of spreading forest fires in real time

Stankevich, Tatiana S.

doi:10.17323/1998-0663.2018.4.17.27

Cited by 4 publications

(1 citation statement)

References 1 publication

(4 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Convolutional neural networks (CNN) based on deep learning can extract features from data. Some scholars have attempted to use CNN for forest fire spread prediction [40,41]. Yang et al used CNN to verify forest fire spread prediction, and the results showed that CNN can extract relevant data features effectively [42].…”

Section: Introductionmentioning

confidence: 99%

AutoST-Net: A Spatiotemporal Feature-Driven Approach for Accurate Forest Fire Spread Prediction from Remote Sensing Data

Chen,

Tian,

Zheng

et al. 2024

Forests

View full text Add to dashboard Cite

Forest fires, as severe natural disasters, pose significant threats to ecosystems and human societies, and their spread is characterized by constant evolution over time and space. This complexity presents an immense challenge in predicting the course of forest fire spread. Traditional methods of forest fire spread prediction are constrained by their ability to process multidimensional fire-related data, particularly in the integration of spatiotemporal information. To address these limitations and enhance the accuracy of forest fire spread prediction, we proposed the AutoST-Net model. This innovative encoder–decoder architecture combines a three-dimensional Convolutional Neural Network (3DCNN) with a transformer to effectively capture the dynamic local and global spatiotemporal features of forest fire spread. The model also features a specially designed attention mechanism that works to increase predictive precision. Additionally, to effectively guide the firefighting work in the southwestern forest regions of China, we constructed a forest fire spread dataset, including forest fire status, weather conditions, terrain features, and vegetation status based on Google Earth Engine (GEE) and Himawari-8 satellite. On this dataset, compared to the CNN-LSTM combined model, AutoST-Net exhibits performance improvements of 5.06% in MIou and 6.29% in F1-score. These results demonstrate the superior performance of AutoST-Net in the task of forest fire spread prediction from remote sensing images.

show abstract

Section: Introductionmentioning

confidence: 99%

AutoST-Net: A Spatiotemporal Feature-Driven Approach for Accurate Forest Fire Spread Prediction from Remote Sensing Data

Chen,

Tian,

Zheng

et al. 2024

Forests

View full text Add to dashboard Cite

show abstract

Methods, models and algorithms in security systems: machine learning, robotics, insurance, risks, control

Topolsky

Vilisov

2021

View full text Add to dashboard Cite

The monograph examines topical issues of decision support and management in safety systems for fire and emergency situations through the use of innovative approaches and tools for operations research, artificial intelligence, robotics and management methods in organizational systems. The monograph is intended for faculty, researchers, graduate students (adjuncts) and doctoral students, as well as for undergraduates, students and listeners of educational organizations, all those who are interested in the problems of decision support and management in security systems.

show abstract

Regional Digital Economy: Assessment of Development Levels

Sidorov

Senchenko

2020

Mathematics

View full text Add to dashboard Cite

A model of a composite index of the development level digital economy of regions in various sizes is proposed. It is based on a functional network as a kind of directed graph, structured by levels based on the principles of hierarchy, modularity and balance, as well as the availability of data on the development of the digital economy. The scalar value of the required quantity was determined by means of additive convolution. The influence of the subjective factor was excluded by moving away from the expert determination of weighing measures of particular indicators (which are included in the composite index) and using a calculation based on the standard deviation. The proposed approach was tested in the framework of identifying the differentiation of the development level digital economy of regions in Russia, as well as comparing European and Russian practices.

show abstract

The use of convolutional neural networks to forecast the dynamics of spreading forest fires in real time

Cited by 4 publications

References 1 publication

AutoST-Net: A Spatiotemporal Feature-Driven Approach for Accurate Forest Fire Spread Prediction from Remote Sensing Data

AutoST-Net: A Spatiotemporal Feature-Driven Approach for Accurate Forest Fire Spread Prediction from Remote Sensing Data

Methods, models and algorithms in security systems: machine learning, robotics, insurance, risks, control

Regional Digital Economy: Assessment of Development Levels

Contact Info

Product

Resources

About