Impairing Land Registry: Social, Demographic, and Economic Determinants of Forest Classification Errors

被引:4
作者
Adamiak, Maciej [1 ]
Biczkowski, Miroslaw [2 ]
Lesniewska-Napierala, Katarzyna [3 ]
Nalej, Marta [3 ]
Napierala, Tomasz [3 ]
机构
[1] SoftwareMill, PL-02791 Warsaw, Poland
[2] Nicolaus Copernicus Univ Torun, Fac Earth Sci & Spatial Management, Lwowska 1, PL-87100 Torun, Poland
[3] Univ Lodz, Fac Geog Sci, Kopcinskiego31, PL-90142 Lodz, Poland
关键词
land cover; forest; convolutional neural networks; machine learning; land registry errors; GEOGRAPHICALLY WEIGHTED REGRESSION; SCALE-DEPENDENT RELATIONSHIPS; VARYING RELATIONSHIPS; LANDSCAPE PATTERNS; CIVIL-SOCIETY; COVER DATA; FRAGMENTATION; REGION; DEMOCRATIZATION; DEFORESTATION;
D O I
10.3390/rs12162628
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
This paper investigates the social, demographic, and economic factors determining differences between forest identification based on remote sensing techniques and land registry. The Database of Topographic Objects and Sentinel-2 satellite imagery data from 2018 were used to train a forest detection supervised machine learning model. Results aggregated to communes (NUTS-5 units) were compared to data from land registry delivered in Local Data Bank by Statistics Poland. The differences identified between above mentioned sources were defined as errors of land registry. Then, geographically weighted regression was applied to explain spatially varying impact of investigated errors' determinants: Urbanization processes, civic society development, education, land ownership, and culture and quality of spatial planning. The research area covers the entirety of Poland. It was confirmed that in less developed areas, local development policy stimulating urbanization processes does not respect land use planning principles, including the accuracy of land registry. A high education level of the society leads to protective measures before the further increase of the investigated forest cover's overestimation of the land registry in substantially urbanized areas. Finally, higher coverage by valid local spatial development plans stimulate protection against forest classification errors in the land registry.
引用
收藏
页数:25
相关论文
共 115 条
[1]  
[Anonymous], 2010, J RESOUR ENERGY DEV, DOI DOI 10.3233/RED-120068
[2]  
[Anonymous], 2018, ROCZNIK STATYSTYCZNY
[3]   Sustainability and social justice [J].
Balaceanu, Cristina ;
Apostol, Diana ;
Penu, Daniela .
WORLD CONFERENCE ON BUSINESS, ECONOMICS AND MANAGEMENT (BEM-2012), 2012, 62 :677-681
[4]  
Banks N., 2012, WORKING PAPER, P171
[5]   On the need for national land administration infrastructures [J].
Bennetta, Rohan ;
Rajabifard, Abbas ;
Williamson, Ian ;
Wallace, Jude .
LAND USE POLICY, 2012, 29 (01) :208-219
[7]   Tracking indigenous forest cover within an urban matrix through land use analysis: The case of a rapidly developing African city [J].
Bhugeloo, Astika ;
Peerbhay, Kabir ;
Ramdhani, Syd ;
Sershen .
REMOTE SENSING APPLICATIONS-SOCIETY AND ENVIRONMENT, 2019, 13 :328-336
[8]  
Borowska-Stefanska M, 2018, GEOGRAFIE-PRAGUE, V123, P63
[9]   Land use history (1840-2005) and physiography as determinants of southern boreal forests [J].
Boucher, Yan ;
Grondin, Pierre ;
Auger, Isabelle .
LANDSCAPE ECOLOGY, 2014, 29 (03) :437-450
[10]  
Brach M, 2015, SYLWAN, V159, P883