Developing GeoAI Integrated Mass Valuation Model Based on LADM Valuation Information Great Britain Country Profile

被引:1
作者
Mete, Muhammed Oguzhan [1 ]
机构
[1] Istanbul Tech Univ, Dept Geomat Engn, Istanbul, Turkiye
关键词
GeoAI; GIS; LADM; machine learning; mass appraisal; valuation information;
D O I
10.1111/tgis.13273
中图分类号
P9 [自然地理学]; K9 [地理];
学科分类号
0705 ; 070501 ;
摘要
Access to information pertaining to land facilitates strategic planning for individuals, businesses, and governmental entities and allows them to anticipate and address contemporary challenges such as climate change, housing requirements, and economic prosperity. Improvements in information technologies contribute to data creation, analysis, and dissemination processes that enable gaining knowledge about land-related events. Greater use of location data within property technologies gives rise to an efficient and sustainable land administration system. GeoAI can contribute greatly to the solution of spatial problems by extracting information from complex data through geospatial intelligence. Property valuation requires a spatially explicit model to evaluate locational factors with spatial analyses. In this study, a Land Administration Domain Model (LADM)-based mass valuation model is developed for Great Britain by integrating GeoAI techniques. First, the LADM Valuation Information package is matched with the country's current organizational structure and it is extended according to the needs to create a country profile. After developing the conceptual model, a database schema is created and automatic conversion to the physical model is conducted. Loading different data sources into the database, a mass valuation application is carried out through spatial analysis and Random Forest regression analysis. As a result, a highly accurate and holistic valuation model is implemented based on the international land administration standards.
引用
收藏
页数:16
相关论文
共 74 条
[1]   Supporting land data integration and standardization through the LADM standard: Case of Morocco's country profile MA-LADM [J].
Abdeslam Adad, Moulay ;
Semlali, El Hassane ;
El-Ayachi, Moha ;
Ibannain, Fatiha .
LAND USE POLICY, 2020, 97
[2]  
ada V., 2017, FIG Working Week 2017
[3]  
Ali SD, 2022, 2022 IEEE INTERNATIONAL CONFERENCE ON AEROSPACE ELECTRONICS AND REMOTE SENSING TECHNOLOGY, ICARES, DOI 10.1109/ICARES56907.2022.9993515
[4]  
[Anonymous], 2024, [No title captured]
[5]   Developing an LADM Valuation Information Model for Mongolia [J].
Buuveibaatar, Munkhbaatar ;
Lee, Kangjae ;
Lee, Wonhee .
LAND, 2023, 12 (04)
[6]  
Cagdas, 2016, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, V4, P145, DOI [10.5194/isprs-annals-IV-2-W1-145-2016, DOI 10.5194/ISPRS-ANNALS-IV-2-W1-145-2016]
[7]   Semantic segmentation of high-resolution satellite images using deep learning [J].
Chaurasia, Kuldeep ;
Nandy, Rijul ;
Pawar, Omkar ;
Singh, Ravi Ranjan ;
Ahire, Meghana .
EARTH SCIENCE INFORMATICS, 2021, 14 (04) :2161-2170
[8]  
Chi B, 2021, UKDA, DOI 10.5255/UKDA-SN-854240
[9]   Geo-Aware Networks for Fine-Grained Recognition [J].
Chu, Grace ;
Potetz, Brian ;
Wang, Weijun ;
Howard, Andrew ;
Song, Yang ;
Brucher, Fernando ;
Leung, Thomas ;
Adam, Hartwig .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW), 2019, :247-254
[10]   GeoAI: A Model-Agnostic Meta-Ensemble Zero-Shot Learning Method for Hyperspectral Image Analysis and Classification [J].
Demertzis, Konstantinos ;
Iliadis, Lazaros .
ALGORITHMS, 2020, 13 (03)