Environmental Monitoring of Spatio-Temporal Changes in Northern Istanbul using Remote Sensing and GIS

Abstract

This study aims to evaluate the landscape transformation and the effect of the third Bosphorus Bridge construction works on the natural ecosystem over seven years' time in two districts, Beykoz and Sarıyer, located at the northern part of Asian and European Istanbul. The study applied supervised classificationmaximum likelihood algorithm to monitor land cover changes using multi-temporal satellite data of Landsat covering study area for the years of 2009 and 2016. The overall classification accuracies are 92.36% with Kappa statistic of 0.89 for 2009 and 91.25% with Kappa statistic of 0.89 for the year 2016. The current study resulted with a rapid land cover change at the study area with approximately 4% and %1 decrease in forest and green area, 2% increase in both agricultural and urban/build up areas. Additionally, the destroyed area increased with approximately 1% of the study area in the 7 years period. .

Remote sensing for monitoring tropical dryland forests: a review of current research, knowledge gaps and future directions for Southern Africa

“…EO has been applied to mapping the distribution, changes in cover, and condition including deforestation, desertification, fire damage, and climate impact (Smith et al 2019, Dogru et al 2020. Additionally, these data have been used to estimate biophysical characteristics such as total above ground biomass (AGB), leaf area index (LAI), woody area index, tree diameter, and canopy height which are key inputs into a variety of ecological models, as well as calculations of carbon balance and primary production (Donoghue 2000, Göksel et al 2018, Barbosa et al 2014. The continuous forest metrics obtained using EO data can be extracted at leaf and crown level to evaluate spectral elements of leaf or species properties and at standlevel and plot-level, or beyond to understand the variation between and among species, and through time (Muraoka and Koizumi 2009).…”

Prediction of construction accident outcomes based on an imbalanced dataset through integrated resampling techniques and machine learning methods

“…A dataset consisting of 395,777 construction accidents (2011-October 2020) acquired from the Republic of Turkey, Social Security Institution (SSI) showed that nearly 31% of all nation-wide construction accidents took place in Istanbul, which is the most populated industrial, economical and cultural center of Turkey (Ekmekcio glu et al, 2021). Huge construction projects, including several industrial and residential developments, took place in Istanbul over the last two decades (G€ oksel et al, 2018;Sarı, 2017), which brought a significant amount of employment opportunities to thousands of workers. As a result, 121,002 construction accidents were recorded in the city (120,277 nonfatal and 725 fatal) between 2011 and 2020.…”

Temporal monitoring of land use/land cover change in Kahramanmaraş city

“…Monitoring of temporal LULC in urban areas is possible by temporal analysis of satellite images (Hegazy and Kaloop 2015; Leichtle et al 135 2017;Jimoh et al 2018;Göksel and Doğru 2019;Orhan et al 2019). Different classification algorithms such as can be used in the supervised classification of images for selected periods (Otukei and Blaschke 2010;Karakuş et al 2017;Göksel et al 2018). The Support Vector Machines (SVMs), one of these algorithms, uses optimization algorithms to find the optimal boundaries between classes.…”