Mapping Urban Garden Destruction in Tehran Using Landsat Imagery and Machine Learning

Abstract. In recent decades, Tehran has experienced widespread migration and rapid development due to the concentration of commercial, financial, cultural, and educational activities, leading to changes in land use and disruptions. These issues are particularly significant in relation to private green spaces (gardens), which play a vital role in environmental services and urban quality of life. Urban management, through legal tools and effective policies, can play a key role in either preserving or demolishing these spaces. Examining the relationship between urban management laws and the status of these spaces can contribute to sustainable development and urban livability. In this study, the overall destruction of green spaces in Tehran was first examined. To this end, laws related to private urban green spaces were identified, and the most important ones were specified. Then, Landsat 2, 5, 7, and 8 satellite images for the years 1976 to 2016, with ten-year intervals and based on selected legal variables, were extracted for the summer season of Tehran. In the next step, supervised machine learning methods (Support Vector Machine, Random Forest, and Decision Tree) and unsupervised methods (K-Means) were employed to classify the images, and changes in land use were calculated by comparing these classified images. The results of the study show that from 1976 to 1986, 11.11%, from 1986 to 1996, 19.60%, from 1996 to 2006, 15.62% and from 2006 to 2016, 26.73% of Tehran green spaces were destroyed. These results indicate that the destruction of green spaces in Tehran has followed a continuous and increasing trend, particularly in Municipal Districts 1, 2, 3, and 5. After identifying the general destruction of green spaces, a case study was conducted in Tehran to examine the main objective of this paper, which is to analyze the destruction of gardens. In this context, the Kan gardens in District 5 were selected as a representative example of urban gardens, and the impact of urban management laws on the destruction of these gardens was examined using satellite images and ground-truth data. The results of the study show the significant impact of urban management laws and policies on the destruction of gardens.

Authors

Institutions

Publication Details

Journal
ISPRS annals of the photogrammetry, remote sensing and spatial information sciences
Published
2026-05-29
DOI
https://doi.org/10.5194/isprs-annals-x-4-w8-2025-533-2026
Primary Topic
Urban Green Space and Health
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Mapping Urban Garden Destruction in Tehran Using Landsat Imagery and Machine Learning

M. R. Delavar, Hamidreza Rabiei Dastjerdi, Maryam Mohammadzadeh
ISPRS annals of the photogrammetry, remote sensing and spatial information sciences
Urban Green Space and Health
article

Mapping Urban Garden Destruction in Tehran Using Landsat Imagery and Machine Learning

M. R. Delavar, Hamidreza Rabiei Dastjerdi, Maryam Mohammadzadeh
article en

Abstract

Abstract. In recent decades, Tehran has experienced widespread migration and rapid development due to the concentration of commercial, financial, cultural, and educational activities, leading to changes in land use and disruptions. These issues are particularly significant in relation to private green spaces (gardens), which play a vital role in environmental services and urban quality of life. Urban management, through legal tools and effective policies, can play a key role in either preserving or demolishing these spaces. Examining the relationship between urban management laws and the status of these spaces can contribute to sustainable development and urban livability. In this study, the overall destruction of green spaces in Tehran was first examined. To this end, laws related to private urban green spaces were identified, and the most important ones were specified. Then, Landsat 2, 5, 7, and 8 satellite images for the years 1976 to 2016, with ten-year intervals and based on selected legal variables, were extracted for the summer season of Tehran. In the next step, supervised machine learning methods (Support Vector Machine, Random Forest, and Decision Tree) and unsupervised methods (K-Means) were employed to classify the images, and changes in land use were calculated by comparing these classified images. The results of the study show that from 1976 to 1986, 11.11%, from 1986 to 1996, 19.60%, from 1996 to 2006, 15.62% and from 2006 to 2016, 26.73% of Tehran green spaces were destroyed. These results indicate that the destruction of green spaces in Tehran has followed a continuous and increasing trend, particularly in Municipal Districts 1, 2, 3, and 5. After identifying the general destruction of green spaces, a case study was conducted in Tehran to examine the main objective of this paper, which is to analyze the destruction of gardens. In this context, the Kan gardens in District 5 were selected as a representative example of urban gardens, and the impact of urban management laws on the destruction of these gardens was examined using satellite images and ground-truth data. The results of the study show the significant impact of urban management laws and policies on the destruction of gardens.

ISPRS annals of the photogrammetry, remote sensing and spatial information sciencesVol. X-4/W8-2025
University of Tehran (IR)
Sustainable cities and communities
Openalex Percentile: Top 7%
Urban Green Space and Health
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.