Wildfire danger prediction optimization with transfer learning

arXiv:2403.12871v1 Announce Type: new
Abstract: Convolutional Neural Networks (CNNs) have proven instrumental across various computer science domains, enabling advancements in object detection, classification, and anomaly detection. This paper explores the application of CNNs to analyze geospatial data specifically for identifying wildfire-affected areas. Leveraging transfer learning techniques, we fine-tuned CNN hyperparameters and integrated the Canadian Fire Weather Index (FWI) to assess moisture conditions. The study establishes a methodology for computing wildfire risk levels on a scale of 0 to 5, dynamically …

abstract analyze anomaly anomaly detection application arxiv classification cnn cnns computer computer science convolutional neural networks cs.lg danger data detection domains enabling geospatial networks neural networks object optimization paper prediction science transfer transfer learning type wildfire