A type of Artificial Intelligence that mimics the functioning of the human brain could represent a powerful solution in automatically detecting wildfires, plummeting the time needed to mitigate their devastating effects, a new study finds.
The new technology uses an ‘Artificial Neural Networks’ model that combines satellite imaging technology with deep learning (a subset of Artificial Intelligence (AI) and machine learning).
Findings, published in the peer-reviewed International Journal of Remote Sensing , report a 93% success rate when training the model via a dataset of images of Amazon rainforest with, and without, wildfires.
The technology, it is stated, could be used in a complementary nature with existing AI systems to enhance early warning systems and improve wildfire response strategies.
“The ability to detect and respond to wildfires is crucial for preserving the delicate ecological balance of these vital ecosystems, and the future of this Amazon region depends on decisive rapid action,” explains lead author Professor Cíntia Eleutério of the Universidade Federal do Amazonas, in Manaus.
“Our study’s findings could improve wildfire detection in the Amazonian ecosystem and elsewhere in the world, significantly assisting authorities in combating and managing such incidents.”
In 2023 there were 98,639 wildfires in the Amazon alone. The Amazon rainforest, too, accounts for a significant portion (51.94%) of wildfires in the Brazilian biomes. In recent years this area has experienced a notable increase in such incidents.
Currently, monitoring in the Amazon is provided with near, real-time data – however, it has moderate resolutions and the ability to detect details in remote areas or smaller fire outbreaks is limited.
This new technology uses a type of artificial neural network (a machine learning algorithm that uses a network of interconnected nodes to process data in a way that mimics the human brain) called a Convolutional Neural Network (CNN) to classify areas of the rainforest affected by wildfires and improve the issue. The algorithms developed enhance their performance over time through exposure to increasing volumes of data.
The research team, who are all based at the Universidade Federal do Amazonas, used images sourced from the Landsat 8 and 9 satellites to train the CNN. These satellites are fitted with near-infrared and shortwave infrared, which together are critical for detecting vegetation changes, as well as surface temperature alterations.
First, the CNN was trained on a dataset of 200 images of wildfires and an equal number of images without wildfires to ensure a balanced learning approach. Although small, this number of images proved sufficient for the CNN to achieve 93% accuracy during the training phase.
The CNN’s ability to distinguish between images with and without wildfires was then tested using 40 images not included in the training dataset. The model correctly classified 23 of the 24 images with wildfires and all 16 of the images without wildfires, thus underscoring its robustness and capability for generalisation, and showcasing its potential as a tool for effective wildfire detection.
“The CNN model could serve as a valuable addition, enabling more detailed analyses in specific regions. By combining the wide temporal coverage of the current sensors with the spatial precision of our model, we can significantly enhance wildfire monitoring in critical environmental preservation zones,” states co-author Professor Carlos Mendes, who has a PhD in physics.
“The model has the potential to significantly assist competent authorities in combating and managing such incidents, providing an advanced and more localized approach to wildfire detection.
“It serves as a complement to well-established large-scale monitoring systems, such as the satellite-based Moderate Resolution Imaging Spectroradiometer (MODIS) and Visible Infrared Imaging Radiometer Suite (VIIRS) which are widely used for continuous wildfire detection.”
Going forward, the authors recommend increasing the number of training images for CNN to work on, which “will undoubtedly lead to a more robust model”.
Other applications, they suggest, for the CNN could also be explored – such as monitoring and controlling deforestation.
/Public Release. This material from the originating organization/author(s) might be of the point-in-time nature, and edited for clarity, style and length. Mirage.News does not take institutional positions or sides, and all views, positions, and conclusions expressed herein are solely those of the author(s).View in full here.
Source: https://www.miragenews.com/
