DEEP LEARNING ARCHITECTURES FOR FOREST FIRE DETECTION
Main Article Content
Abstract
The escalating frequency of catastrophic wildfires demands advanced computational solutions. This research presents a comprehensive evaluation of deep learning models for forest fire detection deployed on Anaconda Cloud infrastructure. Leveraging NVIDIA A100 GPUs and containerized environments, our optimized NAS-FireNet architecture achieves 98.7% lab accuracy with 0.6 ms per-image inference latency (27 ms per batch). The cloud-based framework processes 1,652 images/second, enabling real-time analysis of 2,300 km² terrain per server node. Field validation in Southeast Asia confirmed 94.3% operational accuracy (4.4% drop due to atmospheric interference), demonstrating 68.3% reduction in false negatives compared to conventional satellite systems. Extended analysis reveals carbon efficiency of 38 km²/kWh and 42.4% cost reduction versus commercial cloud platforms.
Downloads
Article Details
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.