Exploiting Polygon Metadata to Understand Raster Maps - Accurate Polygonal Feature Extraction

Exploiting Polygon Metadata to Understand Raster Maps - Accurate Polygonal Feature Extraction. Lin, F., Knoblock, C. A., Shbita, B., Vu, B., Li, Z., & Chiang, Y. In Proceedings of the 31st ACM International Conference on Advances in Geographic Information Systems, of SIGSPATIAL '23, New York, NY, USA, 2023. Association for Computing Machinery.

Paper doi abstract bibtex 4 downloads

Locating undiscovered deposits of critical minerals requires accurate geological data. However, most of the 100,000 historical geological maps of the United States Geological Survey (USGS) are in raster format. This hinders critical mineral assessment. We target the problem of extracting geological features represented as polygons from raster maps. We exploit the polygon metadata that provides information on the geological features, such as the map keys indicating how the polygon features are represented, to extract the features. We present a metadata-driven machine-learning approach that encodes the raster map and map key into a series of bitmaps and uses a convolutional model to learn to recognize the polygon features. We evaluated our approach on USGS geological maps; our approach achieves a median F1 score of 0.809 and outperforms state-of-the-art methods by 4.52%.

@inproceedings{10.1145/3589132.3625659,
author = {Lin, Fandel and Knoblock, Craig A. and Shbita, Basel and Vu, Binh and Li, Zekun and Chiang, Yao-Yi},
title = {Exploiting Polygon Metadata to Understand Raster Maps - Accurate Polygonal Feature Extraction},
year = {2023},
isbn = {9798400701689},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3589132.3625659},
doi = {10.1145/3589132.3625659},
abstract = {Locating undiscovered deposits of critical minerals requires accurate geological data. However, most of the 100,000 historical geological maps of the United States Geological Survey (USGS) are in raster format. This hinders critical mineral assessment. We target the problem of extracting geological features represented as polygons from raster maps. We exploit the polygon metadata that provides information on the geological features, such as the map keys indicating how the polygon features are represented, to extract the features. We present a metadata-driven machine-learning approach that encodes the raster map and map key into a series of bitmaps and uses a convolutional model to learn to recognize the polygon features. We evaluated our approach on USGS geological maps; our approach achieves a median F1 score of 0.809 and outperforms state-of-the-art methods by 4.52\%.},
booktitle = {Proceedings of the 31st ACM International Conference on Advances in Geographic Information Systems},
articleno = {109},
numpages = {12},
keywords = {raster map, polygon extraction, image processing},
location = {, Hamburg, Germany, },
series = {SIGSPATIAL '23}
}

Downloads: 4

{"_id":"WdbuPr8xcrT4FQJEg","bibbaseid":"lin-knoblock-shbita-vu-li-chiang-exploitingpolygonmetadatatounderstandrastermapsaccuratepolygonalfeatureextraction-2023","author_short":["Lin, F.","Knoblock, C. A.","Shbita, B.","Vu, B.","Li, Z.","Chiang, Y."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Lin"],"firstnames":["Fandel"],"suffixes":[]},{"propositions":[],"lastnames":["Knoblock"],"firstnames":["Craig","A."],"suffixes":[]},{"propositions":[],"lastnames":["Shbita"],"firstnames":["Basel"],"suffixes":[]},{"propositions":[],"lastnames":["Vu"],"firstnames":["Binh"],"suffixes":[]},{"propositions":[],"lastnames":["Li"],"firstnames":["Zekun"],"suffixes":[]},{"propositions":[],"lastnames":["Chiang"],"firstnames":["Yao-Yi"],"suffixes":[]}],"title":"Exploiting Polygon Metadata to Understand Raster Maps - Accurate Polygonal Feature Extraction","year":"2023","isbn":"9798400701689","publisher":"Association for Computing Machinery","address":"New York, NY, USA","url":"https://doi.org/10.1145/3589132.3625659","doi":"10.1145/3589132.3625659","abstract":"Locating undiscovered deposits of critical minerals requires accurate geological data. However, most of the 100,000 historical geological maps of the United States Geological Survey (USGS) are in raster format. This hinders critical mineral assessment. We target the problem of extracting geological features represented as polygons from raster maps. We exploit the polygon metadata that provides information on the geological features, such as the map keys indicating how the polygon features are represented, to extract the features. We present a metadata-driven machine-learning approach that encodes the raster map and map key into a series of bitmaps and uses a convolutional model to learn to recognize the polygon features. We evaluated our approach on USGS geological maps; our approach achieves a median F1 score of 0.809 and outperforms state-of-the-art methods by 4.52%.","booktitle":"Proceedings of the 31st ACM International Conference on Advances in Geographic Information Systems","articleno":"109","numpages":"12","keywords":"raster map, polygon extraction, image processing","location":", Hamburg, Germany, ","series":"SIGSPATIAL '23","bibtex":"@inproceedings{10.1145/3589132.3625659,\nauthor = {Lin, Fandel and Knoblock, Craig A. and Shbita, Basel and Vu, Binh and Li, Zekun and Chiang, Yao-Yi},\ntitle = {Exploiting Polygon Metadata to Understand Raster Maps - Accurate Polygonal Feature Extraction},\nyear = {2023},\nisbn = {9798400701689},\npublisher = {Association for Computing Machinery},\naddress = {New York, NY, USA},\nurl = {https://doi.org/10.1145/3589132.3625659},\ndoi = {10.1145/3589132.3625659},\nabstract = {Locating undiscovered deposits of critical minerals requires accurate geological data. However, most of the 100,000 historical geological maps of the United States Geological Survey (USGS) are in raster format. This hinders critical mineral assessment. We target the problem of extracting geological features represented as polygons from raster maps. We exploit the polygon metadata that provides information on the geological features, such as the map keys indicating how the polygon features are represented, to extract the features. We present a metadata-driven machine-learning approach that encodes the raster map and map key into a series of bitmaps and uses a convolutional model to learn to recognize the polygon features. We evaluated our approach on USGS geological maps; our approach achieves a median F1 score of 0.809 and outperforms state-of-the-art methods by 4.52\\%.},\nbooktitle = {Proceedings of the 31st ACM International Conference on Advances in Geographic Information Systems},\narticleno = {109},\nnumpages = {12},\nkeywords = {raster map, polygon extraction, image processing},\nlocation = {, Hamburg, Germany, },\nseries = {SIGSPATIAL '23}\n}\n\n\n","author_short":["Lin, F.","Knoblock, C. A.","Shbita, B.","Vu, B.","Li, Z.","Chiang, Y."],"key":"10.1145/3589132.3625659","id":"10.1145/3589132.3625659","bibbaseid":"lin-knoblock-shbita-vu-li-chiang-exploitingpolygonmetadatatounderstandrastermapsaccuratepolygonalfeatureextraction-2023","role":"author","urls":{"Paper":"https://doi.org/10.1145/3589132.3625659"},"keyword":["raster map","polygon extraction","image processing"],"metadata":{"authorlinks":{}},"downloads":4},"bibtype":"inproceedings","biburl":"https://bibbase.org/network/files/3E8vjZ9tpMwaLo8Hx","dataSources":["8eQQPu5qWjk8KSph6","Qx7EhmagS9HmZqzQr","c3uZgDfvZw2qtJCbJ","qmripNokAKr9wM7ka","TuGnkB4aF3mWPcFnQ","LYRyuex4y2kvvDWRm","n4SD4EqQ5R79AWNE6"],"keywords":["raster map","polygon extraction","image processing"],"search_terms":["exploiting","polygon","metadata","understand","raster","maps","accurate","polygonal","feature","extraction","lin","knoblock","shbita","vu","li","chiang"],"title":"Exploiting Polygon Metadata to Understand Raster Maps - Accurate Polygonal Feature Extraction","year":2023,"downloads":4}