A neural network based approach to detecting urban land cover changes using Landsat TM and IKONOS imagery

Abstract Urban heat island (UHI) is a phenomenon which may have adverse effects on our environment and is stimulated as a result of urbanisation or land cover changes. Thermal remote sensing has been found beneficial to study the effect of urbanisation on UHI intensity. This paper analyses the variation in Land surface temperature (LST) with land cover changes in Varanasi city of India from 1989 to 2018 using Landsat satellite images. A new index named Urban Heat Intensity Ratio Index (UHIRI) was proposed to quantify the urban heat intensity from 1989 to 2018 which was found to increase from 0.36 in year 1989 to 0.87 in year 2018. Further, contribution of each land cover towards UHI was determined using Land cover contribution index (LCCI). The negative value of LCCI for water and vegetation indicates its negative contribution towards UHI whereas positive value of LCCI for bare soil and built-ups depicted its positive contribution towards UHI. The LCCI value for urban land cover shows significant increase in 29 years i.e. 0.49, 1.43, 3.40, 4.37 for years 1989, 1997, 2008 and 2018 respectively. The change in normalized LST from years 1989 to 2018 for the conversion of bare land to built-ups and vegetation to built-ups were found to be as -0.11 and 0.42 respectively. This led to conclusion that the replacement of vegetation with urban land cover has severe impact on increasing UHI intensity.

Download Full-text

Urban land cover changes assessment by satellite remote sensing imagery

10.1117/12.830198 ◽

2009 ◽

Author(s):

Maria A. Zoran

Keyword(s):

Remote Sensing ◽

Land Cover ◽

Satellite Remote Sensing ◽

Urban Land ◽

Land Cover Changes ◽

Remote Sensing Imagery ◽

Urban Land Cover

Download Full-text

Monitoring urban land cover changes at the urban fringe from SPOT HRV imagery in south-east England

International Journal of Remote Sensing ◽

10.1080/01431168908903937 ◽

1989 ◽

Vol 10 (6) ◽

pp. 953-963 ◽

Cited By ~ 48

Author(s):

N. A. QUARMBY ◽

J. L. CUSHNIE

Keyword(s):

Land Cover ◽

Urban Land ◽

Urban Fringe ◽

Land Cover Changes ◽

Urban Land Cover ◽

South East England

Download Full-text

Improving Urban Land Cover/Use Mapping by Integrating A Hybrid Convolutional Neural Network and An Automatic Training Sample Expanding Strategy

Remote Sensing ◽

10.3390/rs12142292 ◽

2020 ◽

Vol 12 (14) ◽

pp. 2292

Author(s):

Xin Luo ◽

Xiaohua Tong ◽

Zhongwen Hu ◽

Guofeng Wu

Keyword(s):

Neural Network ◽

Feature Extraction ◽

Land Cover ◽

Convolutional Neural Network ◽

Training Sample ◽

Urban Land ◽

Support Vector ◽

Land Cover Mapping ◽

Urban Regions ◽

Urban Land Cover

Moderate spatial resolution (MSR) satellite images, which hold a trade-off among radiometric, spectral, spatial and temporal characteristics, are extremely popular data for acquiring land cover information. However, the low accuracy of existing classification methods for MSR images is still a fundamental issue restricting their capability in urban land cover mapping. In this study, we proposed a hybrid convolutional neural network (H-ConvNet) for improving urban land cover mapping with MSR Sentinel-2 images. The H-ConvNet was structured with two streams: one lightweight 1D ConvNet for deep spectral feature extraction and one lightweight 2D ConvNet for deep context feature extraction. To obtain a well-trained 2D ConvNet, a training sample expansion strategy was introduced to assist context feature learning. The H-ConvNet was tested in six highly heterogeneous urban regions around the world, and it was compared with support vector machine (SVM), object-based image analysis (OBIA), Markov random field model (MRF) and a newly proposed patch-based ConvNet system. The results showed that the H-ConvNet performed best. We hope that the proposed H-ConvNet would benefit for the land cover mapping with MSR images in highly heterogeneous urban regions.

Download Full-text