File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1080/17538947.2022.2155718
- Scopus: eid_2-s2.0-85146966622
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Article: A hybrid model for high spatial and temporal resolution population distribution prediction
Title | A hybrid model for high spatial and temporal resolution population distribution prediction |
---|---|
Authors | |
Keywords | big data Cellular automata long short-term memory population distribution spatial and temporal analysis |
Issue Date | 2022 |
Citation | International Journal of Digital Earth, 2022, v. 15, n. 1, p. 2268-2295 How to Cite? |
Abstract | The accurate prediction of population distribution is crucial for numerous applications, from urban planning to epidemiological modelling. Using one-week data collected from open and multiple sources, including telecommunication activity, weather, point of interest, buildings, roads, and land use in Milan, Italy, we develop a hybrid method combining cellular automata (CA) and long short-term memory (LSTM) to predict population distribution with fine temporal and spatial granularity. Specifically, the convolutional autoencoder and LightGBM are applied to identify missing building types based on the pedestrian shed. The LSTM learns the transition rules of CA and Shapley additive explanations value is used for variable importance analysis. Results demonstrate that the combination of convolutional autoencoder and LightGBM is effective in building type prediction. The proposed model for population distribution prediction outperforms LSTM, the combination of CA and neural network, and the combination of CA and LightGBM by at least 5–10%. A variable importance analysis reveals that temporal variables are the most significant for prediction, followed by spatial and natural variables. The order of hour, housing-related variables, and types of precipitation are the most important variables in each category. |
Persistent Identifier | http://hdl.handle.net/10722/329916 |
ISSN | 2021 Impact Factor: 4.606 2020 SCImago Journal Rankings: 0.813 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Zhang, Yuhang | - |
dc.contributor.author | Zhang, Yi | - |
dc.contributor.author | Huang, Bo | - |
dc.contributor.author | Liu, Xin | - |
dc.date.accessioned | 2023-08-09T03:36:25Z | - |
dc.date.available | 2023-08-09T03:36:25Z | - |
dc.date.issued | 2022 | - |
dc.identifier.citation | International Journal of Digital Earth, 2022, v. 15, n. 1, p. 2268-2295 | - |
dc.identifier.issn | 1753-8947 | - |
dc.identifier.uri | http://hdl.handle.net/10722/329916 | - |
dc.description.abstract | The accurate prediction of population distribution is crucial for numerous applications, from urban planning to epidemiological modelling. Using one-week data collected from open and multiple sources, including telecommunication activity, weather, point of interest, buildings, roads, and land use in Milan, Italy, we develop a hybrid method combining cellular automata (CA) and long short-term memory (LSTM) to predict population distribution with fine temporal and spatial granularity. Specifically, the convolutional autoencoder and LightGBM are applied to identify missing building types based on the pedestrian shed. The LSTM learns the transition rules of CA and Shapley additive explanations value is used for variable importance analysis. Results demonstrate that the combination of convolutional autoencoder and LightGBM is effective in building type prediction. The proposed model for population distribution prediction outperforms LSTM, the combination of CA and neural network, and the combination of CA and LightGBM by at least 5–10%. A variable importance analysis reveals that temporal variables are the most significant for prediction, followed by spatial and natural variables. The order of hour, housing-related variables, and types of precipitation are the most important variables in each category. | - |
dc.language | eng | - |
dc.relation.ispartof | International Journal of Digital Earth | - |
dc.subject | big data | - |
dc.subject | Cellular automata | - |
dc.subject | long short-term memory | - |
dc.subject | population distribution | - |
dc.subject | spatial and temporal analysis | - |
dc.title | A hybrid model for high spatial and temporal resolution population distribution prediction | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1080/17538947.2022.2155718 | - |
dc.identifier.scopus | eid_2-s2.0-85146966622 | - |
dc.identifier.volume | 15 | - |
dc.identifier.issue | 1 | - |
dc.identifier.spage | 2268 | - |
dc.identifier.epage | 2295 | - |
dc.identifier.eissn | 1753-8955 | - |