Changes
On April 10, 2022 at 8:53:19 AM UTC, seanh:
-
Added field
Country
with valueUSA
to ARCTIC INFRASTRUCTURE INVENTORY
f | 1 | { | f | 1 | { |
2 | "author": "", | 2 | "author": "", | ||
3 | "author_email": "", | 3 | "author_email": "", | ||
4 | "creator_user_id": "2e9fa41b-0394-4070-98d0-205f79d5738b", | 4 | "creator_user_id": "2e9fa41b-0394-4070-98d0-205f79d5738b", | ||
5 | "extras": [ | 5 | "extras": [ | ||
n | n | 6 | { | ||
7 | "key": "Country", | ||||
8 | "value": "USA" | ||||
9 | }, | ||||
6 | { | 10 | { | ||
7 | "key": "Data Management ", | 11 | "key": "Data Management ", | ||
8 | "value": "\"Data in its raw form may contain errors or be | 12 | "value": "\"Data in its raw form may contain errors or be | ||
9 | incompatible with the structure of AII, so it must be processed before | 13 | incompatible with the structure of AII, so it must be processed before | ||
10 | integration. AII data is processed in 3 interconnected stages: | 14 | integration. AII data is processed in 3 interconnected stages: | ||
11 | cleaning, transformation, and validation. Cleaning and Transformation | 15 | cleaning, transformation, and validation. Cleaning and Transformation | ||
12 | Though they are two distinct stages, cleaning and transformation often | 16 | Though they are two distinct stages, cleaning and transformation often | ||
13 | occur at the same time. Cleaning refers to dealing with erroneous | 17 | occur at the same time. Cleaning refers to dealing with erroneous | ||
14 | records (those that are incomplete, inaccurate, irrelevant, or | 18 | records (those that are incomplete, inaccurate, irrelevant, or | ||
15 | duplicated). Transformation, in contrast, converts raw data into a | 19 | duplicated). Transformation, in contrast, converts raw data into a | ||
16 | desired format. Because AII is ultimately intended for public use, | 20 | desired format. Because AII is ultimately intended for public use, | ||
17 | Wilson Center staff aim to convert raw data into formats more easily | 21 | Wilson Center staff aim to convert raw data into formats more easily | ||
18 | understood by human users. Given that each AII data source contains | 22 | understood by human users. Given that each AII data source contains | ||
19 | unique records and encoding methods, cleaning and transformation was | 23 | unique records and encoding methods, cleaning and transformation was | ||
20 | tailored to each source. Validation Data validation ensures the | 24 | tailored to each source. Validation Data validation ensures the | ||
21 | quality of records that have undergone cleaning and transformation. | 25 | quality of records that have undergone cleaning and transformation. | ||
22 | Whenever possible, AII records were cross-referenced with data from | 26 | Whenever possible, AII records were cross-referenced with data from | ||
23 | multiple sources to confirm their validity.\"" | 27 | multiple sources to confirm their validity.\"" | ||
24 | }, | 28 | }, | ||
25 | { | 29 | { | ||
26 | "key": "Data Policy", | 30 | "key": "Data Policy", | ||
27 | "value": "\"The Wilson Center developed a list of potential data | 31 | "value": "\"The Wilson Center developed a list of potential data | ||
28 | sources and prioritized the inclusion of web pages that maximize the | 32 | sources and prioritized the inclusion of web pages that maximize the | ||
29 | volume, relevance, and accuracy of records. Priority was given to the | 33 | volume, relevance, and accuracy of records. Priority was given to the | ||
30 | datasets of government bodies, independent research organizations, and | 34 | datasets of government bodies, independent research organizations, and | ||
31 | NGOs, due to their role as aggregators of publicly available data and | 35 | NGOs, due to their role as aggregators of publicly available data and | ||
32 | transparency in methods. Additionally, as the owners of public | 36 | transparency in methods. Additionally, as the owners of public | ||
33 | infrastructure, governments can be assumed to have the most | 37 | infrastructure, governments can be assumed to have the most | ||
34 | authoritative dataset on public projects. For the current release of | 38 | authoritative dataset on public projects. For the current release of | ||
35 | AII (December 2020), the largest sources of data were: the United | 39 | AII (December 2020), the largest sources of data were: the United | ||
36 | Nations Code for Trade and Transport Locations the Global Power Plant | 40 | Nations Code for Trade and Transport Locations the Global Power Plant | ||
37 | Database (World Resources Institute) the Arctic Marine and Aviation | 41 | Database (World Resources Institute) the Arctic Marine and Aviation | ||
38 | Transportation Infrastructure Initiative (Arctic Council, under an | 42 | Transportation Infrastructure Initiative (Arctic Council, under an | ||
39 | initiative of the Governments of the United States and Iceland) the | 43 | initiative of the Governments of the United States and Iceland) the | ||
40 | Interagency Electronic Reporting System for Commercial Fishery | 44 | Interagency Electronic Reporting System for Commercial Fishery | ||
41 | Landings (State of Alaska) the Federal Agency of Sea and River | 45 | Landings (State of Alaska) the Federal Agency of Sea and River | ||
42 | Transport (Government of the Russian Federation) Because coverage is | 46 | Transport (Government of the Russian Federation) Because coverage is | ||
43 | currently limited to publicly available data, this list is not | 47 | currently limited to publicly available data, this list is not | ||
44 | exhaustive. When possible, the websites of private owners of | 48 | exhaustive. When possible, the websites of private owners of | ||
45 | infrastructure were also consulted as the most authoritative | 49 | infrastructure were also consulted as the most authoritative | ||
46 | source.\"" | 50 | source.\"" | ||
47 | }, | 51 | }, | ||
48 | { | 52 | { | ||
49 | "key": "Data Sharing Principle", | 53 | "key": "Data Sharing Principle", | ||
50 | "value": "\"Extracting Data Once a data source has been | 54 | "value": "\"Extracting Data Once a data source has been | ||
51 | earmarked for inclusion in AII, its data must be extracted. The method | 55 | earmarked for inclusion in AII, its data must be extracted. The method | ||
52 | chosen for data extraction depends on the format in which a web page | 56 | chosen for data extraction depends on the format in which a web page | ||
53 | stores data. Data used to build AII is stored in a variety of formats, | 57 | stores data. Data used to build AII is stored in a variety of formats, | ||
54 | ranging from .csv and .doc files to raw html. Where files are publicly | 58 | ranging from .csv and .doc files to raw html. Where files are publicly | ||
55 | available, they are downloaded in their raw form for further | 59 | available, they are downloaded in their raw form for further | ||
56 | processing. Where data is stored in html, web scraping is employed. | 60 | processing. Where data is stored in html, web scraping is employed. | ||
57 | Web scraping, a normal part of internet operations, allows users to | 61 | Web scraping, a normal part of internet operations, allows users to | ||
58 | grab the portions of a web page\u2019s html that contain the raw form | 62 | grab the portions of a web page\u2019s html that contain the raw form | ||
59 | of desired data. Web scraping can be performed in multiple coding | 63 | of desired data. Web scraping can be performed in multiple coding | ||
60 | languages, but for the purposes of AII, scraping was performed in | 64 | languages, but for the purposes of AII, scraping was performed in | ||
61 | Python. In accordance with industry standards, all data extraction | 65 | Python. In accordance with industry standards, all data extraction | ||
62 | and web scraping followed hypertext transfer protocol (HTTP) and | 66 | and web scraping followed hypertext transfer protocol (HTTP) and | ||
63 | proceeded with scraping only when issued a status code of 200 by the | 67 | proceeded with scraping only when issued a status code of 200 by the | ||
64 | requested server of the data source. Users also followed the scraping | 68 | requested server of the data source. Users also followed the scraping | ||
65 | protocols outlined by a server\u2019s Robots.txt file, being careful | 69 | protocols outlined by a server\u2019s Robots.txt file, being careful | ||
66 | not to exceed a server\u2019s request limits. There are several | 70 | not to exceed a server\u2019s request limits. There are several | ||
67 | limitations to using the methodology described in this document. It is | 71 | limitations to using the methodology described in this document. It is | ||
68 | unlikely that all data will be captured by this methodology due to the | 72 | unlikely that all data will be captured by this methodology due to the | ||
69 | following factors: not all infrastructure data is publicly available | 73 | following factors: not all infrastructure data is publicly available | ||
70 | search engines may return incomplete data due to deficiencies and | 74 | search engines may return incomplete data due to deficiencies and | ||
71 | biases in algorithms, indices, and/or queries data collected from | 75 | biases in algorithms, indices, and/or queries data collected from | ||
72 | third-parties may be erroneous The Wilson Center will make efforts to | 76 | third-parties may be erroneous The Wilson Center will make efforts to | ||
73 | counter these limitations by: consulting governmental and | 77 | counter these limitations by: consulting governmental and | ||
74 | nongovernmental entities directly to gain access to data that may not | 78 | nongovernmental entities directly to gain access to data that may not | ||
75 | have appeared in search results or public web pages using multiple | 79 | have appeared in search results or public web pages using multiple | ||
76 | data sources to \u201cplug\u201d each other\u2019s gaps cleaning and | 80 | data sources to \u201cplug\u201d each other\u2019s gaps cleaning and | ||
77 | validating third-party data\"" | 81 | validating third-party data\"" | ||
78 | } | 82 | } | ||
79 | ], | 83 | ], | ||
n | 80 | "groups": [], | n | 84 | "groups": [ |
85 | { | ||||
86 | "description": "Inventory of Database for Earth Three Poles", | ||||
87 | "display_name": "An Inventory of Database for Earth Three | ||||
88 | Poles", | ||||
89 | "id": "543d60c4-2ba5-4474-b3d2-47a5cd109ce8", | ||||
90 | "image_display_url": | ||||
91 | .142.79/uploads/group/2021-05-18-053212.318529inventurydatabase1.jpg", | ||||
92 | "name": "inventury-of-database-for-earth-three-poles", | ||||
93 | "title": "An Inventory of Database for Earth Three Poles" | ||||
94 | } | ||||
95 | ], | ||||
81 | "id": "2f2eb6a0-6683-4de5-99e9-7311ab55b7d5", | 96 | "id": "2f2eb6a0-6683-4de5-99e9-7311ab55b7d5", | ||
82 | "isopen": false, | 97 | "isopen": false, | ||
83 | "license_id": "", | 98 | "license_id": "", | ||
84 | "license_title": "", | 99 | "license_title": "", | ||
85 | "maintainer": "", | 100 | "maintainer": "", | ||
86 | "maintainer_email": "", | 101 | "maintainer_email": "", | ||
87 | "metadata_created": "2022-04-05T07:50:27.000177", | 102 | "metadata_created": "2022-04-05T07:50:27.000177", | ||
t | 88 | "metadata_modified": "2022-04-05T07:52:00.716409", | t | 103 | "metadata_modified": "2022-04-10T08:53:19.568331", |
89 | "name": "arctic-infrastructure-inventory", | 104 | "name": "arctic-infrastructure-inventory", | ||
90 | "notes": "The Arctic Infrastructure Inventory (AII) | 105 | "notes": "The Arctic Infrastructure Inventory (AII) | ||
91 | tracks\u00a0infrastructure projects in the Arctic. With nearly 8,000 | 106 | tracks\u00a0infrastructure projects in the Arctic. With nearly 8,000 | ||
92 | projects listed, and thousands more that will be added as it grows, | 107 | projects listed, and thousands more that will be added as it grows, | ||
93 | AII\u00a0aims to be a tool and resource for all stakeholders in Arctic | 108 | AII\u00a0aims to be a tool and resource for all stakeholders in Arctic | ||
94 | infrastructure\u2014including policymakers, industry, researchers, | 109 | infrastructure\u2014including policymakers, industry, researchers, | ||
95 | community leaders, and more.\u00a0\r\n", | 110 | community leaders, and more.\u00a0\r\n", | ||
96 | "num_resources": 1, | 111 | "num_resources": 1, | ||
97 | "num_tags": 0, | 112 | "num_tags": 0, | ||
98 | "organization": { | 113 | "organization": { | ||
99 | "approval_status": "approved", | 114 | "approval_status": "approved", | ||
100 | "created": "2020-04-30T11:11:08.802657", | 115 | "created": "2020-04-30T11:11:08.802657", | ||
101 | "description": "Aerospace Information Research Institute (AIR) | 116 | "description": "Aerospace Information Research Institute (AIR) | ||
102 | under the Chinese Academy of Sciences (CAS) was established in July | 117 | under the Chinese Academy of Sciences (CAS) was established in July | ||
103 | 2017, following the approval for consolidation of three CAS | 118 | 2017, following the approval for consolidation of three CAS | ||
104 | institutes: the Institute of Electronics (IECAS), the Institute of | 119 | institutes: the Institute of Electronics (IECAS), the Institute of | ||
105 | Remote Sensing and Digital Earth (RADI), and the Academy of | 120 | Remote Sensing and Digital Earth (RADI), and the Academy of | ||
106 | Opto-Electronics (AOE) at CAS President Board Meeting. The merger is | 121 | Opto-Electronics (AOE) at CAS President Board Meeting. The merger is | ||
107 | the outcome of CAS efforts towards reformation of its R&D system to | 122 | the outcome of CAS efforts towards reformation of its R&D system to | ||
108 | meet future R&D challenges and to better meet the national demands.", | 123 | meet future R&D challenges and to better meet the national demands.", | ||
109 | "id": "c25dce84-97be-4153-8b90-d38f9ab73e5f", | 124 | "id": "c25dce84-97be-4153-8b90-d38f9ab73e5f", | ||
110 | "image_url": "2021-05-18-080509.992585AIRlogo.png", | 125 | "image_url": "2021-05-18-080509.992585AIRlogo.png", | ||
111 | "is_organization": true, | 126 | "is_organization": true, | ||
112 | "name": "air", | 127 | "name": "air", | ||
113 | "state": "active", | 128 | "state": "active", | ||
114 | "title": "Aerospace Information Research Institute, CAS", | 129 | "title": "Aerospace Information Research Institute, CAS", | ||
115 | "type": "organization" | 130 | "type": "organization" | ||
116 | }, | 131 | }, | ||
117 | "owner_org": "c25dce84-97be-4153-8b90-d38f9ab73e5f", | 132 | "owner_org": "c25dce84-97be-4153-8b90-d38f9ab73e5f", | ||
118 | "private": false, | 133 | "private": false, | ||
119 | "relationships_as_object": [], | 134 | "relationships_as_object": [], | ||
120 | "relationships_as_subject": [], | 135 | "relationships_as_subject": [], | ||
121 | "resources": [ | 136 | "resources": [ | ||
122 | { | 137 | { | ||
123 | "cache_last_updated": null, | 138 | "cache_last_updated": null, | ||
124 | "cache_url": null, | 139 | "cache_url": null, | ||
125 | "created": "2022-04-05T07:52:00.484037", | 140 | "created": "2022-04-05T07:52:00.484037", | ||
126 | "datastore_active": false, | 141 | "datastore_active": false, | ||
127 | "description": "The Arctic Infrastructure Inventory (AII) | 142 | "description": "The Arctic Infrastructure Inventory (AII) | ||
128 | tracks\u00a0infrastructure projects in the Arctic. With nearly 8,000 | 143 | tracks\u00a0infrastructure projects in the Arctic. With nearly 8,000 | ||
129 | projects listed, and thousands more that will be added as it grows, | 144 | projects listed, and thousands more that will be added as it grows, | ||
130 | AII\u00a0aims to be a tool and resource for all stakeholders in Arctic | 145 | AII\u00a0aims to be a tool and resource for all stakeholders in Arctic | ||
131 | infrastructure\u2014including policymakers, industry, researchers, | 146 | infrastructure\u2014including policymakers, industry, researchers, | ||
132 | community leaders, and more.\u00a0\r\n", | 147 | community leaders, and more.\u00a0\r\n", | ||
133 | "format": "", | 148 | "format": "", | ||
134 | "hash": "", | 149 | "hash": "", | ||
135 | "id": "647cd873-0a16-46ae-82b0-447ff00df001", | 150 | "id": "647cd873-0a16-46ae-82b0-447ff00df001", | ||
136 | "last_modified": null, | 151 | "last_modified": null, | ||
137 | "metadata_modified": "2022-04-05T07:52:00.721424", | 152 | "metadata_modified": "2022-04-05T07:52:00.721424", | ||
138 | "mimetype": null, | 153 | "mimetype": null, | ||
139 | "mimetype_inner": null, | 154 | "mimetype_inner": null, | ||
140 | "name": "ARCTIC INFRASTRUCTURE INVENTORY", | 155 | "name": "ARCTIC INFRASTRUCTURE INVENTORY", | ||
141 | "package_id": "2f2eb6a0-6683-4de5-99e9-7311ab55b7d5", | 156 | "package_id": "2f2eb6a0-6683-4de5-99e9-7311ab55b7d5", | ||
142 | "position": 0, | 157 | "position": 0, | ||
143 | "resource_type": null, | 158 | "resource_type": null, | ||
144 | "size": null, | 159 | "size": null, | ||
145 | "state": "active", | 160 | "state": "active", | ||
146 | "url": "https://arcticinfrastructure.wilsoncenter.org/", | 161 | "url": "https://arcticinfrastructure.wilsoncenter.org/", | ||
147 | "url_type": null | 162 | "url_type": null | ||
148 | } | 163 | } | ||
149 | ], | 164 | ], | ||
150 | "state": "active", | 165 | "state": "active", | ||
151 | "tags": [], | 166 | "tags": [], | ||
152 | "title": "ARCTIC INFRASTRUCTURE INVENTORY", | 167 | "title": "ARCTIC INFRASTRUCTURE INVENTORY", | ||
153 | "type": "dataset", | 168 | "type": "dataset", | ||
154 | "url": "https://arcticinfrastructure.wilsoncenter.org/", | 169 | "url": "https://arcticinfrastructure.wilsoncenter.org/", | ||
155 | "version": "" | 170 | "version": "" | ||
156 | } | 171 | } |