Cambios
En el instante 10 de octubre de 2025, 7:19:46 UTC,
-
Añadido recurso Parameter Calibration of the Patch Growing Algorithm for Urban Land Change Simulations a Parameter Calibration of the Patch Growing Algorithm for Urban Land Change Simulations
f | 1 | { | f | 1 | { |
2 | "author": "R Lopez-Farias, SI Valdez, A Garcia-Robledo", | 2 | "author": "R Lopez-Farias, SI Valdez, A Garcia-Robledo", | ||
3 | "author_email": null, | 3 | "author_email": null, | ||
4 | "creator_user_id": "a3da3ec9-3fd4-47a4-8d04-0a90b09614e0", | 4 | "creator_user_id": "a3da3ec9-3fd4-47a4-8d04-0a90b09614e0", | ||
5 | "extras": [ | 5 | "extras": [ | ||
6 | { | 6 | { | ||
7 | "key": "Publicaci\u00f3n", | 7 | "key": "Publicaci\u00f3n", | ||
8 | "value": "Conferencia" | 8 | "value": "Conferencia" | ||
9 | }, | 9 | }, | ||
10 | { | 10 | { | ||
11 | "key": "Tipo", | 11 | "key": "Tipo", | ||
12 | "value": "Publicaci\u00f3n" | 12 | "value": "Publicaci\u00f3n" | ||
13 | } | 13 | } | ||
14 | ], | 14 | ], | ||
15 | "groups": [ | 15 | "groups": [ | ||
16 | { | 16 | { | ||
17 | "description": "Este grupo integra las publicaciones | 17 | "description": "Este grupo integra las publicaciones | ||
18 | acad\u00e9micas derivadas de los proyectos de investigaci\u00f3n del | 18 | acad\u00e9micas derivadas de los proyectos de investigaci\u00f3n del | ||
19 | Observatorio Metropolitano CentroGeo. Incluye art\u00edculos | 19 | Observatorio Metropolitano CentroGeo. Incluye art\u00edculos | ||
20 | presentados en congresos nacionales e internacionales, manuscritos en | 20 | presentados en congresos nacionales e internacionales, manuscritos en | ||
21 | formato preprint, cap\u00edtulos de libro y trabajos publicados en | 21 | formato preprint, cap\u00edtulos de libro y trabajos publicados en | ||
22 | revistas cient\u00edficas especializadas. Estos materiales reflejan la | 22 | revistas cient\u00edficas especializadas. Estos materiales reflejan la | ||
23 | labor de investigaci\u00f3n, desarrollo metodol\u00f3gico y | 23 | labor de investigaci\u00f3n, desarrollo metodol\u00f3gico y | ||
24 | an\u00e1lisis territorial del observatorio, contribuyendo al avance | 24 | an\u00e1lisis territorial del observatorio, contribuyendo al avance | ||
25 | del conocimiento en temas urbanos, metropolitanos y geoespaciales.", | 25 | del conocimiento en temas urbanos, metropolitanos y geoespaciales.", | ||
26 | "display_name": "Publicaciones", | 26 | "display_name": "Publicaciones", | ||
27 | "id": "a15a6b77-ddf5-4594-acab-7e772938a5b0", | 27 | "id": "a15a6b77-ddf5-4594-acab-7e772938a5b0", | ||
28 | "image_display_url": "", | 28 | "image_display_url": "", | ||
29 | "name": "publicaciones", | 29 | "name": "publicaciones", | ||
30 | "title": "Publicaciones" | 30 | "title": "Publicaciones" | ||
31 | } | 31 | } | ||
32 | ], | 32 | ], | ||
33 | "id": "f0f209f9-5807-4ca8-b763-5c273cc53cf5", | 33 | "id": "f0f209f9-5807-4ca8-b763-5c273cc53cf5", | ||
34 | "isopen": false, | 34 | "isopen": false, | ||
35 | "license_id": null, | 35 | "license_id": null, | ||
36 | "license_title": null, | 36 | "license_title": null, | ||
37 | "maintainer": null, | 37 | "maintainer": null, | ||
38 | "maintainer_email": null, | 38 | "maintainer_email": null, | ||
39 | "metadata_created": "2025-10-10T07:19:46.268413", | 39 | "metadata_created": "2025-10-10T07:19:46.268413", | ||
n | 40 | "metadata_modified": "2025-10-10T07:19:46.268420", | n | 40 | "metadata_modified": "2025-10-10T07:19:46.725953", |
41 | "name": | 41 | "name": | ||
42 | tch-growing-algorithm-for-urban-land-change-simulations-adc9e415743b", | 42 | tch-growing-algorithm-for-urban-land-change-simulations-adc9e415743b", | ||
43 | "notes": "Urban growth modelling is a current trend in | 43 | "notes": "Urban growth modelling is a current trend in | ||
44 | geo-computation due to its impact on the local living environment and | 44 | geo-computation due to its impact on the local living environment and | ||
45 | the quality of life. The FUTure Urban-Regional Environment Simulation | 45 | the quality of life. The FUTure Urban-Regional Environment Simulation | ||
46 | (FUTURES) model produces projections of landscape patterns by coupling | 46 | (FUTURES) model produces projections of landscape patterns by coupling | ||
47 | land suitability, per-capita demand, and patch growing algorithm (PGA) | 47 | land suitability, per-capita demand, and patch growing algorithm (PGA) | ||
48 | sub-models. In particular, the PGA is the urban growing simulator | 48 | sub-models. In particular, the PGA is the urban growing simulator | ||
49 | component that takes into account the stochastic nature of urban | 49 | component that takes into account the stochastic nature of urban | ||
50 | development. It requires a set of parameters, namely compactness mean, | 50 | development. It requires a set of parameters, namely compactness mean, | ||
51 | compactness range, and discount factor to approximate the general | 51 | compactness range, and discount factor to approximate the general | ||
52 | characteristics of the urban development structure. The fitness of the | 52 | characteristics of the urban development structure. The fitness of the | ||
53 | parameters is measured by computing the difference between the area | 53 | parameters is measured by computing the difference between the area | ||
54 | and compactness histograms of the observed and simulated urban | 54 | and compactness histograms of the observed and simulated urban | ||
55 | growths. On the one hand, the authors find these parameters via an | 55 | growths. On the one hand, the authors find these parameters via an | ||
56 | exhaustive grid search; nevertheless, this requires evaluating all the | 56 | exhaustive grid search; nevertheless, this requires evaluating all the | ||
57 | points in the grid, which implies a high computational cost because | 57 | points in the grid, which implies a high computational cost because | ||
58 | each point is associated with several PGA simulations. In addition, | 58 | each point is associated with several PGA simulations. In addition, | ||
59 | the approximation is limited to be one of the points in the grid. | 59 | the approximation is limited to be one of the points in the grid. | ||
60 | Thus, the better the precision is, the higher the required | 60 | Thus, the better the precision is, the higher the required | ||
61 | computational cost. On the other hand, evolutionary algorithms have | 61 | computational cost. On the other hand, evolutionary algorithms have | ||
62 | been widely used for the automatic calibration of parameters but, in | 62 | been widely used for the automatic calibration of parameters but, in | ||
63 | general, they are not designed to use a low number of evaluations, | 63 | general, they are not designed to use a low number of evaluations, | ||
64 | require expert tuning, and to define the stop criteria. Therefore, we | 64 | require expert tuning, and to define the stop criteria. Therefore, we | ||
65 | propose an algorithm to find the adequate parameters, with minimum | 65 | propose an algorithm to find the adequate parameters, with minimum | ||
66 | expert intervention, using an Estimation of Distribution Algorithm | 66 | expert intervention, using an Estimation of Distribution Algorithm | ||
67 | designed to use a low number of function evaluations (EDALNFE) when | 67 | designed to use a low number of function evaluations (EDALNFE) when | ||
68 | compared to the grid search. EDALNFE provides several assets: it | 68 | compared to the grid search. EDALNFE provides several assets: it | ||
69 | delivers competitive results, it requires a low number of function | 69 | delivers competitive results, it requires a low number of function | ||
70 | evaluations, it does not require expert settings, and it is equipped | 70 | evaluations, it does not require expert settings, and it is equipped | ||
71 | with an automatic stop criterion. The proposed algorithm is compared | 71 | with an automatic stop criterion. The proposed algorithm is compared | ||
72 | to exhaustive grid search (the only method readily available in the | 72 | to exhaustive grid search (the only method readily available in the | ||
73 | FUTURES package) and differential evolution to demonstrate its | 73 | FUTURES package) and differential evolution to demonstrate its | ||
74 | superior performance.", | 74 | superior performance.", | ||
n | 75 | "num_resources": 0, | n | 75 | "num_resources": 1, |
76 | "num_tags": 9, | 76 | "num_tags": 9, | ||
77 | "organization": { | 77 | "organization": { | ||
78 | "approval_status": "approved", | 78 | "approval_status": "approved", | ||
79 | "created": "2022-05-19T00:10:30.480393", | 79 | "created": "2022-05-19T00:10:30.480393", | ||
80 | "description": "Observatorio Metropolitano CentroGeo", | 80 | "description": "Observatorio Metropolitano CentroGeo", | ||
81 | "id": "b3b3a79d-748a-4464-9471-732b6c74ec53", | 81 | "id": "b3b3a79d-748a-4464-9471-732b6c74ec53", | ||
82 | "image_url": | 82 | "image_url": | ||
83 | "2022-05-19-001030.456616FullColor1280x1024LogoOnly.png", | 83 | "2022-05-19-001030.456616FullColor1280x1024LogoOnly.png", | ||
84 | "is_organization": true, | 84 | "is_organization": true, | ||
85 | "name": "observatorio-metropolitano-centrogeo", | 85 | "name": "observatorio-metropolitano-centrogeo", | ||
86 | "state": "active", | 86 | "state": "active", | ||
87 | "title": "Observatorio Metropolitano CentroGeo", | 87 | "title": "Observatorio Metropolitano CentroGeo", | ||
88 | "type": "organization" | 88 | "type": "organization" | ||
89 | }, | 89 | }, | ||
90 | "owner_org": "b3b3a79d-748a-4464-9471-732b6c74ec53", | 90 | "owner_org": "b3b3a79d-748a-4464-9471-732b6c74ec53", | ||
91 | "private": false, | 91 | "private": false, | ||
92 | "relationships_as_object": [], | 92 | "relationships_as_object": [], | ||
93 | "relationships_as_subject": [], | 93 | "relationships_as_subject": [], | ||
t | 94 | "resources": [], | t | 94 | "resources": [ |
95 | { | ||||
96 | "cache_last_updated": null, | ||||
97 | "cache_url": null, | ||||
98 | "created": "2025-10-10T07:19:46.754344", | ||||
99 | "datastore_active": false, | ||||
100 | "description": "Urban growth modelling is a current trend in | ||||
101 | geo-computation due to its impact on the local living environment and | ||||
102 | the quality of life. The FUTure Urban-Regional Environment Simulation | ||||
103 | (FUTURES) model produces projections of landscape patterns by coupling | ||||
104 | land suitability, per-capita demand, and patch growing algorithm (PGA) | ||||
105 | sub-models. In particular, the PGA is the urban growing simulator | ||||
106 | component that takes into account the stochastic nature of urban | ||||
107 | development. It requires a set of parameters, namely compactness mean, | ||||
108 | compactness range, and discount factor to approximate the general | ||||
109 | characteristics of the urban development structure. The fitness of the | ||||
110 | parameters is measured by computing the difference between the area | ||||
111 | and compactness histograms of the observed and simulated urban | ||||
112 | growths. On the one hand, the authors find these parameters via an | ||||
113 | exhaustive grid search; nevertheless, this requires evaluating all the | ||||
114 | points in the grid, which implies a high computational cost because | ||||
115 | each point is associated with several PGA simulations. In addition, | ||||
116 | the approximation is limited to be one of the points in the grid. | ||||
117 | Thus, the better the precision is, the higher the required | ||||
118 | computational cost. On the other hand, evolutionary algorithms have | ||||
119 | been widely used for the automatic calibration of parameters but, in | ||||
120 | general, they are not designed to use a low number of evaluations, | ||||
121 | require expert tuning, and to define the stop criteria. Therefore, we | ||||
122 | propose an algorithm to find the adequate parameters, with minimum | ||||
123 | expert intervention, using an Estimation of Distribution Algorithm | ||||
124 | designed to use a low number of function evaluations (EDALNFE) when | ||||
125 | compared to the grid search. EDALNFE provides several assets: it | ||||
126 | delivers competitive results, it requires a low number of function | ||||
127 | evaluations, it does not require expert settings, and it is equipped | ||||
128 | with an automatic stop criterion. The proposed algorithm is compared | ||||
129 | to exhaustive grid search (the only method readily available in the | ||||
130 | FUTURES package) and differential evolution to demonstrate its | ||||
131 | superior performance.", | ||||
132 | "format": "HTML", | ||||
133 | "hash": "", | ||||
134 | "id": "7484c0ce-962f-42c3-9a34-a281537819ba", | ||||
135 | "last_modified": null, | ||||
136 | "metadata_modified": "2025-10-10T07:19:46.729696", | ||||
137 | "mimetype": null, | ||||
138 | "mimetype_inner": null, | ||||
139 | "name": "Parameter Calibration of the Patch Growing Algorithm | ||||
140 | for Urban Land Change Simulations", | ||||
141 | "package_id": "f0f209f9-5807-4ca8-b763-5c273cc53cf5", | ||||
142 | "position": 0, | ||||
143 | "resource_type": null, | ||||
144 | "size": null, | ||||
145 | "state": "active", | ||||
146 | "url": "https://doi.org/10.1109/enc53357.2021.9534789", | ||||
147 | "url_type": null | ||||
148 | } | ||||
149 | ], | ||||
95 | "state": "active", | 150 | "state": "active", | ||
96 | "tags": [ | 151 | "tags": [ | ||
97 | { | 152 | { | ||
98 | "display_name": "algorithm", | 153 | "display_name": "algorithm", | ||
99 | "id": "da224d7c-d794-48c8-8316-05d6b5fdc51c", | 154 | "id": "da224d7c-d794-48c8-8316-05d6b5fdc51c", | ||
100 | "name": "algorithm", | 155 | "name": "algorithm", | ||
101 | "state": "active", | 156 | "state": "active", | ||
102 | "vocabulary_id": null | 157 | "vocabulary_id": null | ||
103 | }, | 158 | }, | ||
104 | { | 159 | { | ||
105 | "display_name": "calibration", | 160 | "display_name": "calibration", | ||
106 | "id": "57aaaf8e-b348-4b10-bb60-62ad1d2773c6", | 161 | "id": "57aaaf8e-b348-4b10-bb60-62ad1d2773c6", | ||
107 | "name": "calibration", | 162 | "name": "calibration", | ||
108 | "state": "active", | 163 | "state": "active", | ||
109 | "vocabulary_id": null | 164 | "vocabulary_id": null | ||
110 | }, | 165 | }, | ||
111 | { | 166 | { | ||
112 | "display_name": "computation", | 167 | "display_name": "computation", | ||
113 | "id": "7360e5e0-ae0d-4cd2-8974-a4f49ac17663", | 168 | "id": "7360e5e0-ae0d-4cd2-8974-a4f49ac17663", | ||
114 | "name": "computation", | 169 | "name": "computation", | ||
115 | "state": "active", | 170 | "state": "active", | ||
116 | "vocabulary_id": null | 171 | "vocabulary_id": null | ||
117 | }, | 172 | }, | ||
118 | { | 173 | { | ||
119 | "display_name": "computer-science", | 174 | "display_name": "computer-science", | ||
120 | "id": "29cae056-cd7e-43f7-be5b-b25869a3fbf2", | 175 | "id": "29cae056-cd7e-43f7-be5b-b25869a3fbf2", | ||
121 | "name": "computer-science", | 176 | "name": "computer-science", | ||
122 | "state": "active", | 177 | "state": "active", | ||
123 | "vocabulary_id": null | 178 | "vocabulary_id": null | ||
124 | }, | 179 | }, | ||
125 | { | 180 | { | ||
126 | "display_name": "grid", | 181 | "display_name": "grid", | ||
127 | "id": "ffb14913-8224-4760-8d62-ba7cfcdb4542", | 182 | "id": "ffb14913-8224-4760-8d62-ba7cfcdb4542", | ||
128 | "name": "grid", | 183 | "name": "grid", | ||
129 | "state": "active", | 184 | "state": "active", | ||
130 | "vocabulary_id": null | 185 | "vocabulary_id": null | ||
131 | }, | 186 | }, | ||
132 | { | 187 | { | ||
133 | "display_name": "histogram", | 188 | "display_name": "histogram", | ||
134 | "id": "933d7267-334e-4f94-b55e-e7a80b3da092", | 189 | "id": "933d7267-334e-4f94-b55e-e7a80b3da092", | ||
135 | "name": "histogram", | 190 | "name": "histogram", | ||
136 | "state": "active", | 191 | "state": "active", | ||
137 | "vocabulary_id": null | 192 | "vocabulary_id": null | ||
138 | }, | 193 | }, | ||
139 | { | 194 | { | ||
140 | "display_name": "mathematical-optimization", | 195 | "display_name": "mathematical-optimization", | ||
141 | "id": "b33a86ee-df39-4619-8165-c8d73afbf5a4", | 196 | "id": "b33a86ee-df39-4619-8165-c8d73afbf5a4", | ||
142 | "name": "mathematical-optimization", | 197 | "name": "mathematical-optimization", | ||
143 | "state": "active", | 198 | "state": "active", | ||
144 | "vocabulary_id": null | 199 | "vocabulary_id": null | ||
145 | }, | 200 | }, | ||
146 | { | 201 | { | ||
147 | "display_name": "range-aeronautics", | 202 | "display_name": "range-aeronautics", | ||
148 | "id": "631e97f4-5be6-4bf1-a707-33ebbb9778fa", | 203 | "id": "631e97f4-5be6-4bf1-a707-33ebbb9778fa", | ||
149 | "name": "range-aeronautics", | 204 | "name": "range-aeronautics", | ||
150 | "state": "active", | 205 | "state": "active", | ||
151 | "vocabulary_id": null | 206 | "vocabulary_id": null | ||
152 | }, | 207 | }, | ||
153 | { | 208 | { | ||
154 | "display_name": "set-abstract-data-type", | 209 | "display_name": "set-abstract-data-type", | ||
155 | "id": "b2cf6bcc-6aa2-4a45-9c63-4066f4e32845", | 210 | "id": "b2cf6bcc-6aa2-4a45-9c63-4066f4e32845", | ||
156 | "name": "set-abstract-data-type", | 211 | "name": "set-abstract-data-type", | ||
157 | "state": "active", | 212 | "state": "active", | ||
158 | "vocabulary_id": null | 213 | "vocabulary_id": null | ||
159 | } | 214 | } | ||
160 | ], | 215 | ], | ||
161 | "title": "Parameter Calibration of the Patch Growing Algorithm for | 216 | "title": "Parameter Calibration of the Patch Growing Algorithm for | ||
162 | Urban Land Change Simulations", | 217 | Urban Land Change Simulations", | ||
163 | "type": "dataset", | 218 | "type": "dataset", | ||
164 | "url": "https://doi.org/10.1109/enc53357.2021.9534789", | 219 | "url": "https://doi.org/10.1109/enc53357.2021.9534789", | ||
165 | "version": null | 220 | "version": null | ||
166 | } | 221 | } |