arXiv 2106.152812021-07-28cs.CVcs.LGeess.IV

On Board Volcanic Eruption Detection through CNNs and Satellite Multispectral Imagery

University of Sannio（桑尼奥大学）；Italian Space Agency（意大利空间局）

Maria Pia Del Rosso, Alessandro Sebastianelli, Dario Spiller, Pierre Philippe Mathieu, Silvia Liberata Ullo

英文摘要：

In recent years, the growth of Machine Learning (ML) algorithms has raised the number of studies including their applicability in a variety of different scenarios. Among all, one of the hardest ones is the aerospace, due to its peculiar physical requirements. In this context, a feasibility study and a first prototype for an Artificial Intelligence (AI) model to be deployed on board satellites are presented in this work. As a case study, the detection of volcanic eruptions has been investigated as a method to swiftly produce alerts and allow immediate interventions. Two Convolutional Neural Networks (CNNs) have been proposed and designed, showing how to efficiently implement them for identifying the eruptions and at the same time adapting their complexity in order to fit on board requirements.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

基于QCNN与静止卫星多光谱影像的火山云检测

Volcanic Clouds Detection through QCNN and Geostationary Satellite Multispectral Imagery

Istituto Nazionale di Geofisica e Vulcanologia (INGV)（国家地球物理与火山学研究所）；Thales Alenia Space Italia（泰雷兹阿莱尼亚空间意大利公司）；Euro-Mediterranean Center on Climate Change（欧亚地中海气候变化中心）；Università di Catania（卡塔尼亚大学）；INFN（国家核物理研究所）

本研究探讨混合量子卷积神经网络（QCNN）对含火山云的卫星图像分类的潜力，对比不同量子比特数QCNN与纯经典架构的性能，以解决火山云检测难题。

2026-08-04cs.CV

一种新的数据划分方法在火山喷发数据上的基准测试

Benchmarking of a new data splitting method on volcanic eruption data

University of Sannio（萨尼奥大学）；European Space Agency（欧洲空间局）；University of Pavia（帕维亚大学）

该研究提出基于累积直方图相异度（CHD）指数的迭代式数据划分方法，在火山喷发数据集上测试，相比随机划分、K-means划分实现更优性能，且未出现过拟合，验证了划分质量对模型学习的提升作用。

2024-10-08cs.CV

Self-supervised Contrastive Learning for Volcanic Unrest Detection

National Observatory of Athens（雅典国家天文台）；Harokopio University of Athens（雅典哈洛克皮奥大学）；University of Bristol（布里斯托大学）

Ground deformation measured from Interferometric Synthetic Aperture Radar (InSAR) data is considered a sign of volcanic unrest, statistically linked to a volcanic eruption. Recent studies have shown the potential of using Sentinel-1 InSAR data and supervised deep learning (DL) methods for the detection of volcanic deformation signals, towards global volcanic hazard mitigation. However, detection accuracy is compromised from the lack of labelled data and class imbalance. To overcome this, synthetic data are typically used for finetuning DL models pre-trained on the ImageNet dataset. This approa…

2022-02-08cs.CVeess.IV

用于在卫星图像中识别火山动荡的异常检测

Anomaly detection for the identification of volcanic unrest in satellite imagery

University of Bristol（布里斯托尔大学）；School of Earth Sciences（地球科学学院）

本文提出基于PaDiM的无监督深度学习框架，通过加权距离和预处理方法在卫星图像中识别火山形变异常，并在五座火山上验证了其优于监督学习的性能。

2024-05-28cs.CVeess.IV

Learning from Synthetic InSAR with Vision Transformers: The case of volcanic unrest detection

Institute of Astronomy, Astrophysics, Space Applications & Remote Sensing, National Observatory of Athens（雅典国家天文台天文、天体物理、空间应用与遥感研究所）；Harokopio University of Athens（雅典哈罗科皮奥大学）

The detection of early signs of volcanic unrest preceding an eruption, in the form of ground deformation in Interferometric Synthetic Aperture Radar (InSAR) data is critical for assessing volcanic hazard. In this work we treat this as a binary classification problem of InSAR images, and propose a novel deep learning methodology that exploits a rich source of synthetically generated interferograms to train quality classifiers that perform equally well in real interferograms. The imbalanced nature of the problem, with orders of magnitude fewer positive samples, coupled with the lack of a curated…

2022-06-16cs.CVeess.IV

基于Pix2Pix的人工智能火山灰圈定方法

Volcanic ash delimitation using Artificial Intelligence based on Pix2Pix

Universidad Central del Ecuador（厄瓜多尔中央大学）

针对传统火山灰云圈定方法依赖专家、效率低的问题，本研究提出用Pix2Pix生成对抗网络实现多光谱卫星图像到火山灰云图像的自动转换，经评估效果良好，可用于全球范围的灾害风险管理。

2023-07-24cs.CV

更多相关论文收起更多论文

A deep learning approach to detecting volcano deformation from satellite imagery using synthetic datasets

University of Bristol（布里斯托尔大学）

Satellites enable widespread, regional or global surveillance of volcanoes and can provide the first indication of volcanic unrest or eruption. Here we consider Interferometric Synthetic Aperture Radar (InSAR), which can be employed to detect surface deformation with a strong statistical link to eruption. The ability of machine learning to automatically identify signals of interest in these large InSAR datasets has already been demonstrated, but data-driven techniques, such as convolutional neutral networks (CNN) require balanced training datasets of positive and negative signals to effectivel…

2019-05-17cs.CVeess.IV

Synergistic Integration of Techniques of VC, Communication Technologies and Unities of Calculation Transportable for Generate a System Embedded That Monitors Pyroclastic Flows in Real Time

Universidad de las Fuerzas Armadas ESPE（武装部队大学ESPE）

At the end of an extensive investigation of the volcanic eruptions in the world, we determined patterns that coincide in this process, this data can be analyzed by artificial vision, obtaining the largest amount of information from images in an embedded system, using monitoring algorithms for compare continuous matrices, control camera positioning and link this information with mass communication technologies. The present work shows the development of a viable early warning technology solution that allows to analyze the behavior of volcanic flows automatically in a rash in real time, with a ve…

2022-08-15cs.CVcs.SYeess.IV