Deep learning of Sentinel-1 SAR for burnt peatland detection in Ireland

Abstract

Peatlands represent vital carbon reserves; however, once ignited, they release stored carbon, inflicting lasting environmental harm and necessitating prolonged recovery periods. An innovative method merging Sentinel-1 satellite imagery and deep learning (DL) is proposed to monitor burnt peat across diverse regions of Ireland, regardless of weather conditions or time of day. Sentinel-2 images and field measurements were used to train deep neural networks (DNN) and the accuracy in detecting burnt peat areas reached 80 %. This was achieved by combining the VV (vertical transmit, vertical receive) and VH (vertical transmit, horizontal receive) from Sentinel-1. Time-series analysis of Sentinel-1 VV backscatter change for Wicklow Mountains in 2018 highlights the Sentinel-1's capacity to detect various phenomena, including snowfall and burnt peat, evident prior to the peat fire event. Furthermore, an examination of peat fire occurrences in Wicklow Mountains from 2018 to 2023 through time series and mapping shows a significant escalation, with the largest burnt areas detected in 2023 spanning over 40 km².