{"dp_type": "Project", "free_text": "Feed-Forward Artificial Neural Networks"}
[{"awards": "1066348 Reusch, David", "bounds_geometry": null, "dataset_titles": null, "datasets": null, "date_created": "Thu, 29 Sep 2011 00:00:00 GMT", "description": "Reusch/0636618 This award supports a three-year effort to use nonlinear techniques to improve understanding of Antarctic climate through studies of observational and forecast model data sets; improve and extend reconstructions of past Antarctic climate from ice-core data; and reconstruct data missing from the observational records, potentially into the pre-instrumental era. The intellectual merit of the proposed activity arises from the opportunity to improve understanding of the past, present and future climate of the Antarctic, a key component in the global climate system. Self-organizing maps (SOMs), an emerging, powerful nonlinear tool, will be used to classify free-atmosphere reanalysis data into archetypal patterns (SOM states). Feed-forward artificial neural networks (FF-ANNs) will then be trained to predict the preferred SOM states from ice-core data covering the instrumental era. The trained FF-ANNs will extend the reconstructions of SOM states to the full length of the ice core data, leading to long-term reconstruction of climate. Histories of surface conditions will be improved by filling data gaps in observational records using FF-ANNs and free-atmosphere reanalysis data. These records may also be extended into the pre-instrumental era using the above ice-core based reconstructions of the atmospheric circulation. The broader impacts of the project relate to activities with the Earth and Mineral Sciences Museum (co-located in the Geosciences building) which will bring project results/tools to a wider audience through development of interactive graphical visualizations/presentations for the Museum\u0027s fixed and traveling GeoWall displays. One or more undergraduates from the College will be involved in the project with an option to also present project results at a national meeting/workshop. The work will also contribute to the continuing development of an \"early career\" investigator, including the opportunity to continue building (and refining) relevant and useful skills in teaching, outreach, collaboration, etc.", "east": null, "geometry": null, "instruments": null, "is_usap_dc": false, "keywords": "LABORATORY; Climate; Reanalyses; Model; Forecast Model; Model Output", "locations": null, "north": null, "nsf_funding_programs": "Antarctic Glaciology", "paleo_time": null, "persons": "Reusch, David", "platforms": "OTHER \u003e PHYSICAL MODELS \u003e LABORATORY", "repositories": null, "science_programs": null, "south": null, "title": "Observations, Reanalyses and Ice Cores: A Synthesis of West Antarctic Climate", "uid": "p0000098", "west": null}, {"awards": "0087380 Alley, Richard", "bounds_geometry": "POLYGON((-180 -60,-144 -60,-108 -60,-72 -60,-36 -60,0 -60,36 -60,72 -60,108 -60,144 -60,180 -60,180 -63,180 -66,180 -69,180 -72,180 -75,180 -78,180 -81,180 -84,180 -87,180 -90,144 -90,108 -90,72 -90,36 -90,0 -90,-36 -90,-72 -90,-108 -90,-144 -90,-180 -90,-180 -87,-180 -84,-180 -81,-180 -78,-180 -75,-180 -72,-180 -69,-180 -66,-180 -63,-180 -60))", "dataset_titles": null, "datasets": null, "date_created": "Thu, 01 Jul 2004 00:00:00 GMT", "description": "0087380\u003cbr/\u003eAlley\u003cbr/\u003e\u003cbr/\u003eThis award provides three years of support to use a broad, adaptable, multi-parameter approach, using a range of techniques including artificial neural networks to seek the relations between meteorological conditions and the snow pit and ice core records they produce. Multi-parameter, high resolution, ice core data already in hand or now being collected reflect snow accumulation, atmospheric chemistry, isotopic fractionation, and other processes, often with subannual resolution. The West Antarctic sites from which such data are available will be used as starting points for back-trajectory analyses in reanalysis data products to determine the meteorological conditions feeding the data stream. The artificial neural nets will then be used to look for optimal relations between these meteorological conditions and their products. Previous work has demonstrated the value of reanalysis products in determining snow accumulation, of back trajectory analyses in understanding glaciochemistry, and of artificial neural nets in linking meteorological conditions and their products. Preliminary work shows that neural nets are successful in downscaling from reanalysis products to automatic weather station data in West Antarctica, enabling interpolation of site-specific data to improve understanding of recent changes in West Antarctic climate.", "east": 180.0, "geometry": "POINT(0 -89.999)", "instruments": null, "is_usap_dc": false, "keywords": "Climate; Not provided; Feed-Forward Artificial Neural Networks; Ff-Anns", "locations": null, "north": -60.0, "nsf_funding_programs": "Antarctic Glaciology", "paleo_time": null, "persons": "Reusch, David", "platforms": "Not provided", "repositories": null, "science_programs": null, "south": -90.0, "title": "Relating West Antarctic Ice Cores to Climate with Artificial Neural Networks", "uid": "p0000747", "west": -180.0}]
X
X
Help on the Results MapX
This window can be dragged by its header, and can be resized from the bottom right corner.
Clicking the Layers button - the blue square in the top left of the Results Map - will display a list of map layers you can add or remove
from the currently displayed map view.
The Results Map and the Results Table
- The Results Map displays the centroids of the geographic bounds of all the results returned by the search.
- Results that are displayed in the current map view will be highlighted in blue and brought to the top of the Results Table.
- As the map is panned or zoomed, the highlighted rows in the table will update.
- If you click on a centroid on the map, it will turn yellow and display a popup with details for that project/dataset - including a link to the landing page. The bounds for the project(s)/dataset(s) selected will be displayed in red. The selected result(s) will be highlighted in red and brought to the top of the table.
- The default table sorting order is: Selected, Visible, Date (descending), but this can be changed by clicking on column headers in the table.
- Selecting Show on Map for an individual row will both display the geographic bounds for that result on a mini map, and also display the bounds and highlight the centroid on the Results Map.
- Clicking the 'Show boundaries' checkbox at the top of the Results Map will display all the bounds for the filtered results.
Defining a search area on the Results Map
- If you click on the Rectangle or Polygon icons in the top right of the Results Map, you can define a search area which will be added to any other search criteria already selected.
- After you have drawn a polygon, you can edit it using the Edit Geometry dropdown in the search form at the top.
- Clicking Clear in the map will clear any drawn polygon.
- Clicking Search in the map, or Search on the form will have the same effect.
- The returned results will be any projects/datasets with bounds that intersect the polygon.
- Use the Exclude project/datasets checkbox to exclude any projects/datasets that cover the whole Antarctic region.
Viewing map layers on the Results Map
Older retrieved projects from AMD. Warning: many have incomplete information.
To sort the table of search results, click the header of the column you wish to search by. To sort by multiple columns, hold down the shift key whilst selecting the sort columns in order.
| Project Title/Abstract/Map | NSF Award(s) | Date Created | PIs / Scientists | Dataset Links and Repositories | Abstract | Bounds Geometry | Geometry | Selected | Visible | |
|---|---|---|---|---|---|---|---|---|---|---|
|
Observations, Reanalyses and Ice Cores: A Synthesis of West Antarctic Climate
|
1066348 |
2011-09-29 | Reusch, David | No dataset link provided | Reusch/0636618 This award supports a three-year effort to use nonlinear techniques to improve understanding of Antarctic climate through studies of observational and forecast model data sets; improve and extend reconstructions of past Antarctic climate from ice-core data; and reconstruct data missing from the observational records, potentially into the pre-instrumental era. The intellectual merit of the proposed activity arises from the opportunity to improve understanding of the past, present and future climate of the Antarctic, a key component in the global climate system. Self-organizing maps (SOMs), an emerging, powerful nonlinear tool, will be used to classify free-atmosphere reanalysis data into archetypal patterns (SOM states). Feed-forward artificial neural networks (FF-ANNs) will then be trained to predict the preferred SOM states from ice-core data covering the instrumental era. The trained FF-ANNs will extend the reconstructions of SOM states to the full length of the ice core data, leading to long-term reconstruction of climate. Histories of surface conditions will be improved by filling data gaps in observational records using FF-ANNs and free-atmosphere reanalysis data. These records may also be extended into the pre-instrumental era using the above ice-core based reconstructions of the atmospheric circulation. The broader impacts of the project relate to activities with the Earth and Mineral Sciences Museum (co-located in the Geosciences building) which will bring project results/tools to a wider audience through development of interactive graphical visualizations/presentations for the Museum's fixed and traveling GeoWall displays. One or more undergraduates from the College will be involved in the project with an option to also present project results at a national meeting/workshop. The work will also contribute to the continuing development of an "early career" investigator, including the opportunity to continue building (and refining) relevant and useful skills in teaching, outreach, collaboration, etc. | None | None | false | false | |
|
Relating West Antarctic Ice Cores to Climate with Artificial Neural Networks
|
0087380 |
2004-07-01 | Reusch, David | No dataset link provided | 0087380<br/>Alley<br/><br/>This award provides three years of support to use a broad, adaptable, multi-parameter approach, using a range of techniques including artificial neural networks to seek the relations between meteorological conditions and the snow pit and ice core records they produce. Multi-parameter, high resolution, ice core data already in hand or now being collected reflect snow accumulation, atmospheric chemistry, isotopic fractionation, and other processes, often with subannual resolution. The West Antarctic sites from which such data are available will be used as starting points for back-trajectory analyses in reanalysis data products to determine the meteorological conditions feeding the data stream. The artificial neural nets will then be used to look for optimal relations between these meteorological conditions and their products. Previous work has demonstrated the value of reanalysis products in determining snow accumulation, of back trajectory analyses in understanding glaciochemistry, and of artificial neural nets in linking meteorological conditions and their products. Preliminary work shows that neural nets are successful in downscaling from reanalysis products to automatic weather station data in West Antarctica, enabling interpolation of site-specific data to improve understanding of recent changes in West Antarctic climate. | POLYGON((-180 -60,-144 -60,-108 -60,-72 -60,-36 -60,0 -60,36 -60,72 -60,108 -60,144 -60,180 -60,180 -63,180 -66,180 -69,180 -72,180 -75,180 -78,180 -81,180 -84,180 -87,180 -90,144 -90,108 -90,72 -90,36 -90,0 -90,-36 -90,-72 -90,-108 -90,-144 -90,-180 -90,-180 -87,-180 -84,-180 -81,-180 -78,-180 -75,-180 -72,-180 -69,-180 -66,-180 -63,-180 -60)) | POINT(0 -89.999) | false | false |
