Remote sensing‐based neural network mapping of tsunami damage in Aceh, Indonesia

Aitkenhead, Matthew; Lumsdon, Parivash; Miller, David R.

doi:10.1111/j.1467-7717.2007.01005.x

Cited by 14 publications

(5 citation statements)

References 15 publications

(13 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous recent studies on post‐tsunami reconstruction and recovery focus on these severe impacts, ranging from monitoring to prevention studies and addressing, for instance, fisheries and coastal livelihood (de Silva and Yamao, 2007), landscape (Aitkenhead et al , 2007), environmental issues (Shaw, 2007), and vulnerability (Birkmann and Fernando, 2008). However, the “process” side of recovery is equally important as it mediates all content.…”

Section: Introductionmentioning

confidence: 99%

Challenges of sustainable recovery processes in tsunami affected communities

Wiek

Ries

Thabrew

et al. 2010

Disaster Prevention and Management: An International Journal

View full text Add to dashboard Cite

PurposeSustainable housing and community recovery processes in the aftermath of tsunamis have to cope with direct impacts, such as fatalities, destroyed buildings, and loss of economic assets, as well as indirect impacts caused by shortcomings in recovery management. Recent studies on post‐tsunami recovery tend to focus on direct impacts, ranging from monitoring to prevention studies. Less attention is paid to recovery as a complex bundle of multi‐agent processes causing subsequent problems.Design/methodology/approachThe paper presents results from field studies evaluating post‐tsunami recovery processes in Sri Lanka against the concept of sustainable housing and community recovery. Semi‐structured observations and interviews were conducted on eight sites in the south‐western part of Sri Lanka during field visits 2005‐2006. The research involved beneficiaries and other citizens, representatives from government and administration, field workers (non‐governmental organizations), and scientists.FindingsEmpirical findings identify subsequent problems for specific capital forms, across different capital forms, and across different administrative levels. Moreover, critical issues refer to conceptualizing temporal horizons, comprehensive planning and decision making, stakeholders' involvement, and institutional embedding of recovery processes.Originality/valueAgainst this empirical background, the paper indicates improvement potentials referring to literature on comprehensive and adaptive planning to address the sustainable recovery challenges identified. The paper provides guidance for researchers, decision makers, planners, and field workers engaged in post‐disaster sustainable development.

show abstract

Section: Introductionmentioning

confidence: 99%

Challenges of sustainable recovery processes in tsunami affected communities

Wiek

Ries

Thabrew

et al. 2010

Disaster Prevention and Management: An International Journal

View full text Add to dashboard Cite

show abstract

“…Previously, neural networks have been used to predict the occurrence of tornadoes from radar data [16,17], the occurrence of damaging winds [18], and the trajectories of hurricanes [69]. Conditional on the occurrence of a natural disaster, neural networks have proved useful for assessing damages, for instance after the December 2004 tsunami in Aceh, Sumatra [19]. The application of machine learning to the prediction of potential tornado damages appears promising, though nascent in the current literature despite their increasing popularity and repeated calls for state of the art methods in the field of natural hazards [44,45] -with very recent calls for deep learning in the field of earth science [46].…”

Section: Introductionmentioning

confidence: 99%

Predicting property damage from tornadoes with zero-inflated neural networks

Diaz

Joseph

2019

Weather and Climate Extremes

View full text Add to dashboard Cite

Tornadoes are the most violent of all atmospheric storms. In a typical year, the United States experiences hundreds of tornadoes with associated damages on the order of one billion dollars. Community preparation and resilience would benefit from accurate predictions of these economic losses, particularly as populations in tornado-prone areas increase in density and extent. Here, we use a zero-inflated modeling approach and artificial neural networks to predict tornado-induced property damage using publicly available data. We developed a neural network that predicts whether a tornado will cause property damage (out-of-sample accuracy = 0.821 and area under the receiver operating characteristic curve, AUROC, = 0.872). Conditional on a tornado causing damage, another neural network predicts the amount of damage (out-of-sample mean squared error = 0.0918 and R 2 = 0.432). When used together, these two models function as a zero-inflated log-normal regression with hidden layers. From the best-performing models, we provide static and interactive gridded maps of monthly predicted probabilities of damage and property damages for the year 2019. Two primary weaknesses include (1) model fitting requires log-scale data which leads to large natural-scale residuals and (2) beginning tornado coordinates were utilized rather than tornado paths. Ultimately, this is the first known study to directly model tornado-induced property damages, and all data, code, and tools are publicly available. The predictive capacity of this model along with an interactive interface may provide an opportunity for science-informed tornado disaster planning.

show abstract

“…Outputs from the vulnerability assessment process can be easily displayed via simple, clear thematic maps [Cutter et al, 2003;Williams and Alvarez, 2003]. At present, available methods for tsunami vulnerability assessment are designed to be applied mainly at high resolution [Papadopoulos and Dermentzopoulos, 1998;Aitkenhead et al, 2007;Dominey-Howes and Papathoma, 2007;Garcin et al, 2008;Taubenbock et al, 2008;Dall'Osso et al, 2009a;Dall'Osso et al, 2009b;Dominey-Howes, et al, 2010] using data at the scale of individual buildings or infrastructure units. Data are normally gathered through field surveys and direct census analysis.…”

Section: Introductionmentioning

confidence: 99%

A novel approach (the CRATER method) for assessing tsunami vulnerability at the regional scale using ASTER imagery

Osso¹,

Bovio²,

Cavalletti³

et al. 2010

ItJRS

View full text Add to dashboard Cite

We present here a novel method to assess coastal vulnerability to tsunami based on GIS (Geographical Information System), ASTER imagery (Advanced Spaceborn Thermal Emission and Reflection Radiometer) and SRTM-3 elevation model (Shuttle Radar Topography Mission-3). We developed this method within the CRATER project (Coastal Risk Analysis for Tsunamis and Environmental Remediation) and applied it on the whole western coast of Thailand. As result, we generated a set of vectorial vulnerability maps with a geometrical resolution of 90m (scale 1:450 000). This approach provides a low-cost and quick tool to analyse extended coastal tracts, and prioritize investments for prevention measures or for further high-resolution analysis. Un nuovo approccio (metodo CRATER) per la stima a scala regionale della vulnerabilità a tsunami mediante immagini ASTER Riassunto Il lavoro presentato introduce un nuovo metodo per la stima della vulnerabilità costiera a tsunami, basato sul GIS (Geographical Information System), sull'impiego di immagini ASTER (Advanced Spaceborn Thermal Emission and Reflection Radiometer) e modelli di elevazione SRTM-3 (Shuttle Radar Topography Mission-3). Il metodo è stato sviluppato nell'ambito del progetto CRATER (Coastal Risk Analysis for Tsunamis and EnvironmentalRemediation) ed applicato all'intera costa occidentale della Tailandia. I risultati consistono in un set di mappe vettoriali della vulnerabilità con risoluzione di 90m (scala 1:450 000). Tale approccio costituisce un mezzo relativamente economico e veloce per l'analisi di estesi tratti costieri e per la gestione di investimenti in misure di prevenzione o in ulteriori analisi ad alta risoluzione. Tsunami, Vulnerabilità costiera, ASTER, GIS, Uso Suolo. Dall'Osso et al. Tsunami vulnerability at the regional scale: the CRATER method Parole chiave:

show abstract

Remote sensing‐based neural network mapping of tsunami damage in Aceh, Indonesia

Abstract: In addition to the loss of human life, the tsunami event of 26

Cited by 14 publications

References 15 publications

Challenges of sustainable recovery processes in tsunami affected communities

Challenges of sustainable recovery processes in tsunami affected communities

Predicting property damage from tornadoes with zero-inflated neural networks

A novel approach (the CRATER method) for assessing tsunami vulnerability at the regional scale using ASTER imagery

Contact Info

Product

Resources

About