The use of a MLP neural network for analysis and aodeling of land use changes with variations variable of physical and economic social

Subiyanto, Sawitri; Sukmono, Abdi; Bashit, Nurhadi; Amarrohman, Fauzi Janu

doi:10.1088/1755-1315/389/1/012029

Cited by 3 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This agrees with Heider et al (2018) andHernández-Flores et al (2017) who reported among the main urban driving forces distance to urban areas, distance to roads and population growth rate. But they did not agree with the findings of Akintuyi et al (2021), Fathizad et al (2019 and Subiyanto et al (2019), perhaps because they analysed other land-use changes in addition to urbanisation in countries with very different conditions from the study area.…”

Section: Discussionmentioning

confidence: 59%

“…It ranges from 0 (no association) to 1 (perfect association). Values close to 0.4 show an association between variables, and values less than 0.15 indicate a low association (Akintuyi et al 2021;Fathizad et al 2019;Subiyanto et al 2019). The independent factors used were elevation, distance to previous urban land, distance to roads, population density, education years, occupants per dwelling, percentage of the dependent population, percentage of indigenous households and land use.…”

Section: Driving Socio-economic Factorsmentioning

confidence: 99%

See 1 more Smart Citation

Urban growth in peri-urban, rural and urban areas: Mexico City

Cruz-Bello

Galeana-Pizaña²,

Arellano

2023

Buildings and Cities

View full text Add to dashboard Cite

This remote sensing study compares growth occurring in three urban types between 2005 and 2014: peri-urban, rural and urban, in a fast-growing metropolitan region west of Mexico City. Future urban growth for the period 2014-24 is modelled using the land-use/cover change (LUCC) model Geomod. Urban expansion is correlated with some socio-territorial factors and the impacts are assessed for the loss of biomass. In both periods, the urban zone differed the most from the other two in terms of urban expansion. The Geomod predictions overestimate the urban expansion in the urban zone and underestimate it in the peri-urban and rural zones. Significant differences exist in the average urban expansion between zones. The main urban growth drivers were elevation, population density, distance to previous urban land and distance to roads. A substantial loss of biomass is due to urban growth, including expansion and infill. The research reveals significant differences in growth between peri-urban, rural and urban areas, and contributes spatial information for designing focused land-use policies in dynamic urban contexts. POLICY RELEVANCEThis article contributes to understanding the differentiated urban growth of urban, periurban and rural areas, which can translate into more precise and effective public policies. Urban expansion and infill patterns differ. For peri-urban and rural areas, the main growth is infill, so actions should be implemented to sustainably manage the vacant or undeveloped land within an existing human settlement to prevent further expansion, but also to avoid the loss of priority areas for the provision of ecosystem services. In urban areas where the main urban increment is expansion, sensible consolidation decisions need to be taken to avoid further urban expansion and the incorporation of urban green space.*Author affiliations can be found in the back matter of this article 2 Cruz-Bello et al.

show abstract

Section: Discussionmentioning

confidence: 59%

Section: Driving Socio-economic Factorsmentioning

confidence: 99%

Urban growth in peri-urban, rural and urban areas: Mexico City

Cruz-Bello

Galeana-Pizaña²,

Arellano

2023

Buildings and Cities

View full text Add to dashboard Cite

show abstract

“…The MLP is one of the most popular neural network models in remote sensing thematic mapping. It has been widely used in land-cover mapping (Jamali 2020), land-use classification (Subiyanto et al 2019), and change detection (Wang, Lu, and Qin 2020). The MLP has the advantage of data-driven and automatic learning, which is conducive to specific classification tasks.…”

Section: Comparison With Other Benchmark Methodsmentioning

confidence: 99%

Mapping and analyzing the local climate zones in China’s 32 major cities using Landsat imagery based on a novel convolutional neural network

Huang

Liu

2021

Geo-spatial Information Science

View full text Add to dashboard Cite

The Local Climate Zone (LCZ) scheme provides researchers with a standard method to monitor the Urban Heat Island (UHI) effect and conduct temperature studies. How to generate reliable LCZ maps has therefore become a research focus. In recent years, researchers have attempted to use Landsat imagery to delineate LCZs and generate maps worldwide based on the World Urban Database and Access Portal Tools (WUDAPT). However, the mapping results obtained by the WUDAPT method are not satisfactory. In this paper, to generate more accurate LCZ maps, we propose a novel Convolutional Neural Network (CNN) model (namely, LCZ-CNN), which is designed to cope with the issues of LCZ classification using Landsat imagery. Furthermore, in this study, we applied the LCZ-CNN model to generate LCZ mapping results for China's 32 major cities distributed in various climatic zones, achieving a significantly better accuracy than the traditional classification strategies and a satisfactory computational efficiency. The proposed LCZ-CNN model achieved satisfactory classification accuracies in all 32 cities, and the Overall Accuracies (OAs) of more than half of the cities were higher than 80%. We also designed a series of experiments to comprehensively analyze the proposed LCZ-CNN model, with regard to the transferability of the network and the effectiveness of multiseasonal information. It was found that the first convolutional stage, corresponding to low-level features, shows better transferability than the second and third convolutional stages, which extract high-level and more image-or task-oriented features. It was also confirmed that the multi-seasonal information can improve the accuracy of LCZ classification. The thermal characteristics of the different LCZ classes were also analyzed based on the mapping results for China's 32 major cities, and the experimental results confirmed the close relationship between the LCZ classes and the magnitude of the Land Surface Temperature (LST).

show abstract