Abstract
Lava flow mapping has direct relevance to volcanic hazards once an eruption has begun. Satellite remote sensing techniques are increasingly used to map newly erupted lava, thanks to their capability to survey large areas with frequent revisit time and accurate spatial resolution. Visible and infrared satellite data are routinely used to detect the distributions of volcanic deposits and monitor thermal features, even if clouds are a serious obstacle for optical sensors, since they cannot be penetrated by optical radiation. On the other hand, radar satellite data have been playing an important role in surface change detection and image classification, being able to operate in all weather conditions, although their use is hampered by the special imaging geometry, the complicated scattering process, and the presence of speckle noise. Thus, optical and radar data are complementary data sources that can be used to map lava flows effectively, in addition to alleviating cloud obstruction and improving change detection performance. Here, we propose a machine learning approach based on the Google Earth Engine (GEE) platform to analyze simultaneously the images acquired by the synthetic aperture radar (SAR) sensor, on board of Sentinel-1 mission, and by optical and multispectral sensors of Landsat-8 missions and Multi-Spectral Imager (MSI), on board of Sentinel-2 mission. Machine learning classifiers, including K-means algorithm (K-means) and support vector machine (SVM), are used to map lava flows automatically from a combination of optical and SAR images. We describe the operation of this approach by using a retrospective analysis of two recent lava flow-forming eruptions at Mount Etna (Italy) and Fogo Island (Cape Verde). We found that combining both radar and optical imagery improved the accuracy and reliability of lava flow mapping. The results highlight the need to fully exploit the extraordinary potential of complementary satellite sensors to provide time-critical hazard information during volcanic eruptions.
Highlights
Introduction nal affiliationsLava flows represent a significant natural hazard to communities living at the edge of an active volcano [1]
Each single classifier is able to reproduce good portions of the lava flow field ranging from ACC = 0.74 to ACC = 0.83 for the Etna lava flow and ACC = 0.70 for S1 for the Fogo lava flow, both the cases of study show that the fused and the combined mapping are more accurate than the single satellite data classifiers, confirming that using all the available information in our proposed machine learning framework allows to get a better knowledge of the lava flow extension
We have introduced a machine learning approach to rapidly map lava flows exploiting all the freely available information coming from Sentinel-1, Sentinel-2, and Landsat-8 satellite
Summary
Lava flows represent a significant natural hazard to communities living at the edge of an active volcano [1]. Properties, and services can be severely damaged by lava flows. When lava flows through inhabited areas, destruction is usually complete [2]. And accurate measurements of the areal coverage of newly erupted lava are a critical component of volcano monitoring [3]. Advancements in satellite remote sensing offer incomparable opportunities for detecting and tracking eruptive activity thanks to the massive amount of data with varying degrees of temporal and spatial resolution provided from a number of sensors operating in the visible, infrared, thermal, and microwave regions of the electromagnetic spectrum [4]. Once an eruption is in progress, the monitoring provided by satellite data allows an extraordinary view of active lava flows
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
