Identification of typical synoptic patterns causing heavy rainfall in the rainy season in Japan by a Self-Organizing Map

Nishiyama, Koji; Endo, Shinichi; Jinno, Kenji; Uvo, Cíntia Bertacchi; Olsson, Jonas; Berndtsson, Ronny

doi:10.1016/j.atmosres.2005.10.015

Cited by 80 publications

(65 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It is recommended that the capability of the SOM to "convert complex non-linear features into simple two-dimensional relationships" (Nishiyama et al 2007) is investigated to use the soundings and derived parameters in an SOM as an objective rainfall-forecasting tool.…”

Section: Summary and Discussionmentioning

confidence: 99%

A heavy rainfall sounding climatology over Gauteng, South Africa, using self-organising maps

Dyson

2015

Clim Dyn

View full text Add to dashboard Cite

The daily weather at a particular place is largely influenced by the synoptic circulation and thermodynamic profile of the atmosphere. Heavy rainfall occurs from a particular subset of synoptic and thermodynamic states. Baseline climatologies provide objective information on heavy rainfall-producing circulation patterns and thermodynamic variables. This is how climatologically large or extreme values associated with heavy rainfall are identified. The aim of this research is to provide a heavy rainfall sounding climatology in austral summer over Gauteng, South Africa, using self-organising maps (SOMs).The results show that the SOM captures the intra-seasonal variability of heavy rainfall soundings by clearly distinguishing between the atmospheric conditions on early summer (October to December) and late summer (January to March) heavy rainfall days. Conditions associated with heavy early summer rainfall are large vertical wind shear and conditional instability, while the atmosphere is drier and cooler than when heavy rainfall occurs in late summer. Late summer heavy rainfall conditions are higher convective instability and small vertical wind shear values. The SOM climatology shows that some heavy rainfall days occur in both early and late summer when large-scale synoptic weather systems cause strong near-surface moisture flux and large values of wind shear. On these days, both the conditional and convective instability of the atmosphere are low and heavy rainfall results from the strong synoptic forcing. In contrast, heavy rainfall also occurs on days when synoptic circulation is not very favourable and the air is relatively dry, but the atmosphere is unstable with warm surface conditions and heavy 2 rainfall develops from local favourable conditions. The SOM climatology provides guidelines to critical values of sounding-derived parameters for all these scenarios.

show abstract

Section: Summary and Discussionmentioning

confidence: 99%

A heavy rainfall sounding climatology over Gauteng, South Africa, using self-organising maps

Dyson

2015

Clim Dyn

View full text Add to dashboard Cite

show abstract

“…The SOM approach is, therefore, suited for the analysis of often complex and disparate geoscientific data (Fraser and Dickson 2007). The potential of the technique for hydrologic system analysis has been reviewed and concluded upon by Kalteh et al (2008), with recent examples including, e.g., investigations of heavy rainfall patterns (Nishiyama et al 2007) and groundwater exploration (Friedel et al 2012).…”

Section: Self-organizing Mapsmentioning

confidence: 99%

On the scope and management of pesticide pollution of Swedish groundwater resources: The Scanian example

Åkesson

Sparrenbom

Dahlqvist

et al. 2014

AMBIO

View full text Add to dashboard Cite

Twenty-three south-Swedish public supply wells were studied to assess pesticide pollution of regional groundwater resources. Relations between pesticide occurrence, hydrogeology, and land use were analyzed using Kohonen's Self-Organizing Maps approach. Pesticides are demonstrated to be substantially present in regional groundwater, with detections in 18 wells. Concentrations above the drinking water threshold are confirmed for nine wells. Observations indicate considerable urban influence, and lagged effects of past, less restricted use. Modern, oxic waters from shallow, unconfined, unconsolidated or fracture-type bedrock aquifers appear particularly vulnerable. Least affected waters appear primarily associated with deeper wells, anoxic conditions, and more confined sediment aquifers lacking urban influence. Comprehensive, standardized monitoring of pesticides in groundwater need to be implemented nationwide to enable sound assessments of pollution status and trends, and to develop sound groundwater management plans in accordance with the Water Framework Directive. Further, existing water protection areas and associated regulations need to be reassessed.

show abstract

“…These symptoms are part of the "curse of dimensionality". In similar studies (where SOMs were trained with many grid cells), only one to three variables were used (e.g., Hewitson and Crane 2002;Reusch et al 2005;Nishiyama et al 2007;Cassano 2009, 2010). In this study, we used two predictor variables, the aforementioned SLP and H500.…”

Section: Predictor Variablesmentioning

confidence: 99%

“…Self-organizing maps (SOMs), a type of neural network, are also well suited to handle high-dimensional data (e.g., gridded meteorological data). SOMs have been used successfully in many meteorological studies such as attribution of extreme events to synoptic patterns (Cavazos 2000;Nishiyama et al 2007;) and predicting changes in the occurrence of synoptic patterns under climate change Cassano 2009, 2010). In most of these cases, the predictors were synoptic pressure fields, because pressure is forecasted well by numerical weather prediction (NWP) models (Kanamitsu et al 2002;Colle et al 2003;Krishnamurti et al 2003;Hamill et al 2013).…”

Section: Introductionmentioning

confidence: 99%

Automated prediction of extreme fire weather from synoptic patterns in northern Alberta, Canada

et al. 2017

View full text Add to dashboard Cite

Abstract:Wildfires burn an average of 2 million hectares per year in Canada, most of which can be attributed to only a few days of severe fire weather. These "spread days" are often associated with large-scale weather systems. We used extreme threshold values of three Canadian Fire Weather Index System (CFWIS) variables -the fine fuel moisture code (FFMC), initial spread index (ISI), and fire weather index (FWI) -as a proxy for spread days. Then we used self-organizing maps (SOMs) to predict spread days, with sea-level pressure and 500 hPa geopotential height as predictors. SOMs require many input parameters, and we performed an experiment to optimize six key parameters. For each month of the fire season (May-August), we also tested whether SOMs performed better when trained with only one month or with neighbouring months as well. Good performance (AUC of 0.8) was achieved for FFMC and ISI, while nearly good performance was achieved for FWI. To our knowledge, this is the first study to develop a machine-learning model for extreme fire weather that could be deployed in real time.Key words: wildland fire, fire danger, fire regimes, SOM, weather.Résumé : Les feux, dont la plupart peuvent être imputés à seulement quelques jours durant lesquels les conditions météorologiques sont propices aux incendies forestiers sévères, détruisent en moyenne deux millions d'hectares de forêt par année au Canada. Ces jours propices à la propagation des feux sont souvent associés à de vastes systèmes météorologiques. Nous avons utilisé des valeurs seuils extrêmes pour trois variables de la méthode canadienne de l'indice forêt-météo (MCIFM) : l'indice du combustible léger (ICL), l'indice de propagation initiale (IPI) et l'indice forêt-météo (IFM) en tant que substituts pour les jours propices à la propagation des feux. Ensuite, nous avons utilisé des cartes autoorganisables (SOM) pour prédire les jours propices à la propagation des feux avec comme prédicteurs la pression au niveau de la mer et une hauteur du géopotentiel de 500 hPa. Les SOM exigent plusieurs paramètres d'entrée et nous avons effectué une expérience pour optimiser six paramètres clés. Pour chaque mois de la saison des feux (mai-août), nous avons aussi testé si les SOM étaient plus performantes lorsqu'elles étaient entraînées avec seulement un mois ou en incluant aussi les mois voisins. Une bonne performance (AUC de 0,8) a été obtenue pour ICL et IPI, alors qu'une performance satisfaisante a été obtenue pour IFM. À notre connaissance, il s'agit de la première étude qui élabore un modèle d'apprentissage automatique pour des conditions météorologiques extrêmes propices aux incendies forestiers qui peut être déployé en temps réel. [Traduit par la Rédaction] Mots-clés : feux de forêt, danger d'incendie, régime des feux, cartes autoorganisables (SOM), conditions météorologiques.

show abstract

Identification of typical synoptic patterns causing heavy rainfall in the rainy season in Japan by a Self-Organizing Map

Cited by 80 publications

References 13 publications

A heavy rainfall sounding climatology over Gauteng, South Africa, using self-organising maps

A heavy rainfall sounding climatology over Gauteng, South Africa, using self-organising maps

On the scope and management of pesticide pollution of Swedish groundwater resources: The Scanian example

Automated prediction of extreme fire weather from synoptic patterns in northern Alberta, Canada

Contact Info

Product

Resources

About