Special Issue "Machine Learning of Remote Sensing Data for Urban Growth Analysis and Modeling"

A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Urban Remote Sensing".

Deadline for manuscript submissions: closed (30 November 2019).

Special Issue Editors

Dr. Rajesh Bahadur Thapa
Website SciProfiles
Guest Editor
International Centre for Integrated Mountain Development, Khumaltar, Lalitpur, GPO Box 3226, Kathmandu, Nepal
Interests: spatial analysis; spatial modeling; satellite-image processing; urbanization; urban growth; urban geography; land-cover change and forest ecosystems; GIS
Dr. Manjula Ranagalage
Website SciProfiles
Guest Editor
Department of Environmental Management, Faculty of Social Sciences and Humanities, Rajarata University of Sri Lanka, Mihintale, 50300, Sri Lanka
Interests: urban studies; remote sensing; GIS; spatial analysis; urban sustainability; urban heat island; urban climate; urban geography; green volume
Special Issues and Collections in MDPI journals

Special Issue Information

Dear Colleagues,

Urbanization has become a major trend worldwide in recent years. Globally, 55% of the world’s population lives in urban areas. The urban population is expected to be 6 billion, an increase of 1.5 times, by 2050. This increase is most dominant in developing countries. As the urban landscape grows, the increasing concentration of population and economic activities demands more resources for public infrastructures, housing, and industrial and commercial uses. These processes are often driven by the development plans and policies of a particular country and the region. Migration, urban sprawl, agriculture, and forest patterns also contribute to the growth process. Understanding the urban-growth process in the past and present and preparing for the future are fundamental to increasing the effectiveness of managing environmental sustainability. Growth processes are multi-dimensional, and problems are becoming multi-folds and more complicated than ever. However, at the same time, with the development of a highly capable cloud-computing infrastructure and automated machine-learning techniques, we are benefitting from the availability of unprecedented amounts of finer spatial scale data on aspects of the Earth’s environment from remote-sensing, demographic, social, and economic sources.

Although several attempts on the development of spatial analysis techniques for a better understanding of real-world phenomena were made by leading researchers in the past, the urban-growth modeling field has become even more challenging and thrilling than in before. Spatial and space–time inquires at higher spatial resolutions are becoming very important to understanding the daily growing complexities created by human–Earth interactions. It is true that our abilities to extract meaning and make useful decisions have not yet kept pace. We must become better equipped to unleash the power of new technology for testing and developing theories, identifying important processes, finding meaningful patterns, creating more effective visualizations of data, and making important societal decisions, which are possible through improving spatial analysis and modeling techniques and providing more empirical studies and geographical experiences. Remote-sensing data provide not only 2D information but also 3D information to understand the vertical development of cities. The combination of the 2D and 3D approaches helps to capture complex urban development. In this context, this Special Issue aims to document current developments in the state-of-the-art technology of machine learning of remote-sensing data and GIS for urban-growth modeling with multiple case studies.

This Special Issue, " Machine Learning for Urban Growth Analysis and Modeling”, will call for papers that demonstrate original research. It will help to overcome current gaps in urban-growth analysis using machine-learning algorithms and satellite remote-sensing data. Review articles are also welcome.

Contributions include as the following:

  1. The classification method to capture urban-landscape changes using machine learning

(e.g., the artificial neural network, the support-vector machine, random forest, Bayes, decision tree, etc.)

  1. The machine learning method to capture building footprints in urban areas
  2. Developing new, robust methods and machine-learning algorithms
  3. Remote-sensing data for urban growth analysis
  4. Urban population modeling
  5. 3D analysis of urban landscape

(e.g., urban built-up volume, urban-green volume)

  1. The urban-growth modeling application of high-resolution optical/radar sensors
  2. Future urban-growth modeling
  3. The visualization of urban-growth patterns
  4. Spatial analysis of urban-landscape changes
Prof. Dr. Yuji Murayama
Dr. Rajesh Bahadur Thapa
Mr. Manjula Ranagalage
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2200 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Machine learning
  • Urban growth
  • Visualization of urbanization pattern
  • Remote-sensing data
  • Landscape prediction and scenarios

Published Papers (6 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Open AccessArticle
Spatiotemporal Analysis of Land Use/Cover Patterns and Their Relationship with Land Surface Temperature in Nanjing, China
Remote Sens. 2020, 12(3), 440; https://doi.org/10.3390/rs12030440 - 31 Jan 2020
Abstract
Rapid urbanization is one of the most concerning issues in the 21st century because of its significant impacts on various fields, including agriculture, forestry, ecology, and climate. The urban heat island (UHI) phenomenon, highly related to the rapid urbanization, has attracted considerable attention [...] Read more.
Rapid urbanization is one of the most concerning issues in the 21st century because of its significant impacts on various fields, including agriculture, forestry, ecology, and climate. The urban heat island (UHI) phenomenon, highly related to the rapid urbanization, has attracted considerable attention from both academic scholars and governmental policymakers because of its direct influence on citizens’ daily life. Land surface temperature (LST) is a widely used indicator to assess the intensity of UHI significantly affected by the local land use/cover (LULC). In this study, we used the Landsat time-series data to derive the LULC composition and LST distribution maps of Nanjing in 2000, 2014, and 2018. A correlation analysis was carried out to check the relationship between LST and the density of each class of LULC. We found out that cropland and forest in Nanjing are helping to cool the city with different degrees of cooling effects depending on the location and LULC composition. Then, a Cellar Automata (CA)-Markov model was applied to predict the LULC conditions of Nanjing in 2030 and 2050. Based on the simulated LULC maps and the relationship between LST and LULC, we delineated high- and moderate-LST related risk areas in the city of Nanjing. Our findings are valuable for the local government to reorganize the future development zones in a way to control the urban climate environment and to keep a healthy social life within the city. Full article
Show Figures

Graphical abstract

Open AccessArticle
Quantification of Annual Settlement Growth in Rural Mining Areas Using Machine Learning
Remote Sens. 2020, 12(2), 235; https://doi.org/10.3390/rs12020235 - 09 Jan 2020
Cited by 1
Abstract
Studies on annual settlement growth have mainly focused on larger cities or incorporated data rarely available in, or applicable to, sparsely populated areas in sub-Saharan Africa, such as aerial photography or night-time light data. The aim of the present study is to quantify [...] Read more.
Studies on annual settlement growth have mainly focused on larger cities or incorporated data rarely available in, or applicable to, sparsely populated areas in sub-Saharan Africa, such as aerial photography or night-time light data. The aim of the present study is to quantify settlement growth in rural communities in Burkina Faso affected by industrial mining, which often experience substantial in-migration. A multi-annual training dataset was created using historic Google Earth imagery. Support vector machine classifiers were fitted on Landsat scenes to produce annual land use classification maps. Post-classification steps included visual quality assessments, majority voting of scenes of the same year and temporal consistency correction. Overall accuracy in the four studied scenes ranged between 58.5% and 95.1%. Arid conditions and limited availability of Google Earth imagery negatively affected classification accuracy. Humid study sites, where training data could be generated in proximity to the areas of interest, showed the highest classification accuracies. Overall, by relying solely on freely and globally available imagery, the proposed methodology is a promising approach for tracking fast-paced population dynamics in rural areas where population data is scarce. With the growing availability of longitudinal high-resolution imagery, including data from the Sentinel satellites, the potential applications of the methodology presented will further increase in the future. Full article
Show Figures

Graphical abstract

Open AccessArticle
Spatiotemporal Modeling of Urban Growth Using Machine Learning
Remote Sens. 2020, 12(1), 109; https://doi.org/10.3390/rs12010109 - 28 Dec 2019
Cited by 1
Abstract
This paper presents a general framework for modeling the growth of three important variables for cities: population distribution, binary urban footprint, and urban footprint in color. The framework models the population distribution as a spatiotemporal regression problem using machine learning, and it obtains [...] Read more.
This paper presents a general framework for modeling the growth of three important variables for cities: population distribution, binary urban footprint, and urban footprint in color. The framework models the population distribution as a spatiotemporal regression problem using machine learning, and it obtains the binary urban footprint from the population distribution through a binary classifier plus a temporal correction for existing urban regions. The framework estimates the urban footprint in color from its previous value, as well as from past and current values of the binary urban footprint using a semantic inpainting algorithm. By combining this framework with free data from the Landsat archive and the Global Human Settlement Layer framework, interested users can get approximate growth predictions of any city in the world. These predictions can be improved with the inclusion in the framework of additional spatially distributed input variables over time subject to availability. Unlike widely used growth models based on cellular automata, there are two main advantages of using the proposed machine learning-based framework. Firstly, it does not require to define rules a priori because the model learns the dynamics of growth directly from the historical data. Secondly, it is very easy to train new machine learning models using different explanatory input variables to assess their impact. As a proof of concept, we tested the framework in Valledupar and Rionegro, two Latin American cities located in Colombia with different geomorphological characteristics, and found that the model predictions were in close agreement with the ground-truth based on performance metrics, such as the root-mean-square error, zero-mean normalized cross-correlation, Pearson’s correlation coefficient for continuous variables, and a few others for discrete variables such as the intersection over union, accuracy, and the f 1 metric. In summary, our framework for modeling urban growth is flexible, allows sensitivity analyses, and can help policymakers worldwide to assess different what-if scenarios during the planning cycle of sustainable and resilient cities. Full article
Show Figures

Graphical abstract

Open AccessArticle
Automatic Detection of Spatiotemporal Urban Expansion Patterns by Fusing OSM and Landsat Data in Kathmandu
Remote Sens. 2019, 11(19), 2296; https://doi.org/10.3390/rs11192296 - 02 Oct 2019
Cited by 9
Abstract
During the last few decades, a large number of people have migrated to Kathmandu city from all parts of Nepal, resulting in rapid expansion of the city. The unplanned and accelerated growth is causing many environmental and population management issues. To manage urban [...] Read more.
During the last few decades, a large number of people have migrated to Kathmandu city from all parts of Nepal, resulting in rapid expansion of the city. The unplanned and accelerated growth is causing many environmental and population management issues. To manage urban growth efficiently, the city authorities need a means to be able to monitor urban expansion regularly. In this study, we introduced a novel approach to automatically detect urban expansion by leveraging state-of-the-art cloud computing technologies using the Google Earth Engine (GEE) platform. We proposed a new index named Normalized Difference and Distance Built-up Index (NDDBI) for identifying built-up areas by combining the LandSat-derived vegetation index with distances from the nearest roads and buildings analysed from OpenStreetMap (OSM). We also focused on logical consistencies of land-cover change to remove unreasonable transitions supported by the repeat photography. Our analysis of the historical urban growth patterns between 2000 and 2018 shows that the settlement areas were increased from 63.68 sq km in 2000 to 148.53 sq km in 2018. The overall accuracy of mapping the newly-built areas of urban expansion was 94.33%. We have demonstrated that the methodology and data generated in the study can be replicated to easily map built-up areas and support quicker and more efficient land management and land-use planning in rapidly growing cities worldwide. Full article
Show Figures

Graphical abstract

Open AccessFeature PaperArticle
Spatial Forecasting of the Landscape in Rapidly Urbanizing Hill Stations of South Asia: A Case Study of Nuwara Eliya, Sri Lanka (1996–2037)
Remote Sens. 2019, 11(15), 1743; https://doi.org/10.3390/rs11151743 - 24 Jul 2019
Cited by 13
Abstract
Forecasting landscape changes is vital for developing and implementing sustainable urban planning. Presently, apart from lowland coastal cities, mountain cities (i.e., hill stations) are also facing the negative impacts of rapid urbanization due to their economic and social importance. However, few studies are [...] Read more.
Forecasting landscape changes is vital for developing and implementing sustainable urban planning. Presently, apart from lowland coastal cities, mountain cities (i.e., hill stations) are also facing the negative impacts of rapid urbanization due to their economic and social importance. However, few studies are addressing urban landscape changes in hill stations in Asia. This study aims to examine and forecast landscape changes in the rapidly urbanizing hill station of Nuwara Eliya, Sri Lanka. Landsat data and geospatial techniques including support vector machines, urban–rural gradient, and statistical analysis were used to map and examine the land use/land cover (LULC) change in Nuwara Eliya during the 1996–2006 and 2006–2017 periods. The multilayer perceptron neural network-Markov model was applied to simulate future LULC changes for 2027 and 2037. The results show that Nuwara Eliya has been directly affected by rapid urban development. During the past 21 years (1996–2017), built-up areas increased by 1791 ha while agricultural land declined by 1919 ha due to augmented urban development pressure. The pressure of urban development on forest land has been relatively low, mainly due to strict conservation government policies. The results further show that the observed landscape changes will continue in a similar pattern in the future, confirming a significant increase and decrease of built-up and agricultural land, respectively, from 2017 to 2037. The changes in agricultural land exhibit a strong negative relationship with the changes in built-up land along the urban–rural gradient (R2 were 0.86 in 1996–2006, and 0.93 in 2006–2017, respectively). The observed LULC changes could negatively affect the production of unique upcountry agricultural products such as exotic vegetables, fruits, cut flowers, and world-famous Ceylon tea. Further, unplanned development could cause several environmental issues. The study is important for understanding future LULC changes and suggesting necessary remedial measures to minimize possible undesirable environmental and socioeconomic impacts. Full article
Show Figures

Graphical abstract

Open AccessArticle
Newly Built Construction Detection in SAR Images Using Deep Learning
Remote Sens. 2019, 11(12), 1444; https://doi.org/10.3390/rs11121444 - 18 Jun 2019
Cited by 4
Abstract
Remote sensing data can be utilized to help developing countries monitor the use of land. However, the problem of constant cloud coverage prevents us from taking full advantage of satellite optical images. Therefore, we instead opt to use data from synthetic-aperture radar (SAR), [...] Read more.
Remote sensing data can be utilized to help developing countries monitor the use of land. However, the problem of constant cloud coverage prevents us from taking full advantage of satellite optical images. Therefore, we instead opt to use data from synthetic-aperture radar (SAR), which can capture images of the Earth’s surface regardless of the weather conditions. In this study, we use SAR data to identify newly built constructions. Most studies on change detection tend to detect all of the changes that have a similar temporal change characteristic occurring on two occasions, while we want to identify only the constructions and avoid detecting other changes such as the seasonal change of vegetation. To do so, we study various deep learning network techniques and have decided to propose the fully convolutional network with a skip connection. We train this network with pairs of SAR data acquired on two different occasions from Bangkok and the ground truth, which we manually create from optical images available from Google Earth for all of the SAR pairs. Experiments to assign the most suitable patch size, loss weighting, and epoch number to the network are discussed in this paper. The trained model can be used to generate a binary map that indicates the position of these newly built constructions precisely with the Bangkok dataset, as well as with the Hanoi and Xiamen datasets with acceptable results. The proposed model can even be used with SAR images of the same specific satellite from another orbit direction and still give promising results. Full article
Show Figures

Figure 1

Back to TopTop