Multivariate Wave Climate Using Self-Organizing Maps

Abstract The visual description of wave climate is usually limited to two-dimensional conditional histograms. In this work, self-organizing maps (SOMs), because of their visualization properties, are used to characterize multivariate wave climate. The SOMs are applied to time series of sea-state parameters at a particular location provided by ocean reanalysis databases. Trivariate (significant wave height, mean period, and mean direction), pentavariate (the previous wave parameters and wind velocity and direction), and hexavariate (three wave parameters of the sea and swell components; or the wave, wind, and storm surge) classifications are explored. This clustering technique is also applied to wave and wind data at several locations to analyze their spatial relationship. Several processes are established in order to improve the results, the most relevant being a preselection of data by means a maximum dissimilarity algorithm (MDA). Results show that the SOM identifies the relevant multivariate sea-state types at a particular location spanning the historical variability, and provides an outstanding analysis of the dependency between the different parameters by visual inspection. In the case of wave climate characterizations for several locations the SOM is able to extract the qualitative spatial sea-state patterns, allowing the analysis of the spatial variability and the relationship between different locations. Moreover, the distribution of sea states over the reanalysis period defines a probability density function on the lattice, providing a visual interpretation of the seasonality and interannuality of the multivariate wave climate.

Download Full-text

The relationship between phonological awareness time and reading abilities: an assessment using self-organizing maps

International Journal on Disability and Human Development ◽

10.1515/ijdhd-2012-0112 ◽

2013 ◽

Vol 12 (3) ◽

Cited By ~ 1

Author(s):

Ana Sucena ◽

João Falcão Carneiro ◽

Ana Paula Vale ◽

Fernanda Leopoldina Viana

Keyword(s):

Response Time ◽

Phonological Awareness ◽

Word Reading ◽

Self Organizing Maps ◽

Nonword Reading ◽

Reading Abilities ◽

Task Time ◽

Good And Poor Readers ◽

The Relationship ◽

Self Organizing

AbstractClassically, the assessment of reading disabilities is based on the accuracy for word and nonword reading, as well as on the accuracy or sensibility measures (such as d′) for phonological awareness tasks. Recent studies indicate that in terms of phonological awareness results, the response time is a more accurate indicator than sensibility measures (such as d′), thus providing an important measure explaining some of the differences between good and poor readers. This article explores the discriminative capability of phonological awareness task time (PATT) in reading disability assessment.One hundred and eighty-six children were tested using conventional tasks, specifically word reading, nonword reading, and phonological awareness tasks. The word and nonword accuracy and PATT were used to train self-organizing maps (SOM) to classify children into three distinct groups.Phonological awareness response time provides a powerful discriminative measure.Our results indicate that the PATT constitutes a useful selective measure, particularly in the third and fourth grades when classical variables such as word and nonword reading accuracy lose their discriminative capabilities. Also, the use of SOM to classify children’s reading abilities can successfully categorize children and capture meaningful measures such as the lexicality effect.

Download Full-text

Analyzing the multidimensional wave climate with self organizing maps

OCEANS 2009-EUROPE ◽

10.1109/oceanse.2009.5278285 ◽

2009 ◽

Cited By ~ 2

Author(s):

Fernando J. Mendez ◽

Paula Camus ◽

Raul Medina ◽

Antonio Cofino

Keyword(s):

Wave Climate ◽

Self Organizing Maps ◽

Self Organizing

Download Full-text

Complex Drivers of Riparian Soil Oxygen Variability Revealed Using Self-Organizing Maps

10.21203/rs.3.rs-1108620/v1 ◽

2021 ◽

Author(s):

Brittany Victoria Lancellotti ◽

Kristen Underwood ◽

Julia Perdrial ◽

Carol Adair ◽

Andrew Schroth ◽

...

Keyword(s):

Soil Moisture ◽

Sensor Data ◽

Soil Conditions ◽

Self Organizing Map ◽

Self Organizing Maps ◽

High Soil Moisture ◽

Dry Conditions ◽

Proxy Measurement ◽

The Relationship ◽

Self Organizing

Abstract Oxygen (O2) is a key regulator of soil reduction-oxidation processes and therefore modulates biogeochemical cycles. The difficulties associated with accurately characterizing soil O2 variability have prompted the use of soil moisture as a proxy for soil O2, based on the low solubility of O2 in water. Due to seasonal shifts in soil O2 depletion mechanisms, the use of soil moisture alone as a proxy measurement could result in inaccurate O2 estimations. For example, soil O2 may remain high during cool months when soil respiration rates are low. We analyzed high-frequency sensor data (e.g., soil moisture, temperature, CO2, O2) with a machine learning technique, the Self-Organizing Map, to pinpoint suites of soil conditions that are associated with contrasting O2 regimes. At two low-lying riparian sites in contrasting land use and topographic settings of northern Vermont, we found that soil O2 levels varied seasonally, and with soil moisture. For example, forty-seven percent of low O2 levels were associated with cool and wet soil conditions, whereas 32% were associated with warm and dry conditions. Contrastingly, the majority (62%) of high O2 conditions occurred under warm and dry conditions. High soil moisture levels did not always lead to low O2, however, as 38% of high O2 values occurred under cool and wet conditions. Our results highlight challenges associated with predicting soil O2 solely based on soil moisture, as variable combinations of soil and site-specific hydrologic conditions can complicate the relationship between soil water content and O2. This indicates that process-based ecosystem and denitrification models that rely solely on soil moisture to estimate O2 availability will, in some cases, need to incorporate other site and climate-specific drivers to accurately predict soil O2.

Download Full-text

Visual Interpretation of Self Organizing Maps

2010 Eleventh Brazilian Symposium on Neural Networks ◽

10.1109/sbrn.2010.15 ◽

2010 ◽

Cited By ~ 4

Author(s):

Edson Caoru Kitani ◽

Emilio Del Moral Hernandez ◽

Carlos Eduardo Thomaz ◽

Leandro Augusto da Silva

Keyword(s):

Visual Interpretation ◽

Self Organizing Maps ◽

Self Organizing

Download Full-text

Investigation of Unexpected Sea-States

23rd International Conference on Offshore Mechanics and Arctic Engineering, Volume 2 ◽

10.1115/omae2004-51181 ◽

2004 ◽

Author(s):

Alessandro Toffoli ◽

Jean Michel Lefe`vre ◽

Patrick Josse ◽

Jaak Monbaliu

Keyword(s):

Information Service ◽

Weather Forecast ◽

Wave Climate ◽

Sea State ◽

Wave Parameters ◽

Warning Criteria ◽

Bad Weather

It is assumed that dangerous and unexpected sea-states may occur if the sea conditions are fairly rough. It is therefore of concern to meteo centers to include sea-state related parameters in marine weather forecast when they exceed a certain threshold. To select appropriate parameters that can point at dangerous wave events, the sea-state at the time and location of shipping accidents reported as being due to bad weather by the Lloyd’s Marine Information Service (LMIS) were extracted from the ECMWF ERA-40 archive. The analysis of these wave parameters reveals the occurrence of apparently rather low sea-states (e.g. Hm0 < 4 m). To test the findings against the related oceanographic features, wave climatology was computed. The present study aims at finding a possible correlation between wave climate and shipping incidents to identify warning criteria.

Download Full-text

A Recommendation Model that Combines Self-Organizing Maps and Case-Based Reasoning: A Case of Online Community Recommender Systems

The e-Business Studies ◽

10.15719/geba.9.1.200803.309 ◽

2008 ◽

Vol 9 (1) ◽

pp. 309-327 ◽

Cited By ~ 1

Author(s):

Hyoung-yong Lee

Keyword(s):

Recommender Systems ◽

Online Community ◽

Case Based Reasoning ◽

Self Organizing Maps ◽

Case Based ◽

Self Organizing

Download Full-text

WAVE CLIMATE OF THE BLACK SEA’S COASTAL WATERS DURING THE LAST THREE DECADES

Proceedings of International Conference "Managinag risks to coastal regions and communities in a changinag world" (EMECS'11 - SeaCoasts XXVI) ◽

10.31519/conferencearticle_5b1b943584ab71.87772537 ◽

2017 ◽

Author(s):

Fedor Gippius ◽

Stanislav Myslenkov ◽

Elena Stoliarova ◽

...

Keyword(s):

Wind Speed ◽

Cell Size ◽

Coastal Waters ◽

Wind Wave ◽

Spatial Scales ◽

Wave Model ◽

Wave Climate ◽

Computational Grid ◽

Coastal Areas ◽

Wave Parameters

This study is focused on the alterations and typical features of the wind wave climate of the Black Sea’s coastal waters since 1979 till nowadays. Wind wave parameters were calculated by means of the 3rd-generation numerical spectral wind wave model SWAN, which is widely used on various spatial scales – both coastal waters and open seas. Data on wind speed and direction from the NCEP CFSR reanalysis were used as forcing. The computations were performed on an unstructured computational grid with cell size depending on the distance from the shoreline. Modeling results were applied to evaluate the main characteristics of the wind wave in various coastal areas of the sea.

Download Full-text