Monitoring statewide urban development using multitemporal multisensoral satellite data covering a 40-year time span in north Rhine-Westphalia (Germany)

Schoettker, Birte; Over, M.; Braun, Matthias; Menz, Gunter; Siegmund, Alexander

doi:10.1117/12.511087

Cited by 3 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to balance the spatial resolution and the spatial extent of the Ruhr, a grid resolution of 100 m was used. This classification procedure is described in detail in references [21,61]. For the calibration of SLEUTH, the 1984 data comprise the base year and the 2001 data constitute the reference year.…”

Section: Geosimulation -Using the Ai Of Cellsmentioning

confidence: 99%

“…Fundamentally, SVM is a linear binary classifier that labels a sample of empirical data by constructing the optimal separating hyperplane (Figure 3, left). Traditional machine learning methods try to minimize the empirical training error, causing a tendency to overfit [61,62]. They are strongly tailored to the training data, so extending them to additional data becomes difficult.…”

Section: Support Vector Machinesmentioning

confidence: 99%

See 1 more Smart Citation

The Future of Central European Cities – Optimization of a Cellular Automaton for the Spatially Explicit Prediction of Urban Sprawl

Rienow¹

2016

Optimization Algorithms - Methods and Applications

View full text Add to dashboard Cite

The quantitative and qualitative measurement, prediction and evaluation of urban sprawl have come to play a central role in land-system science. One of the most important and most implemented artificial intelligence "I techniques in terms of urban systems simulation is cellular automata C" like SLEUTH. SLEUTH models the physical urban expansion by accomplishing four simple growth rules with every modeling step. Simultaneously, SLEUTH also reflects main drawbacks of C" since they contain a higher degree of stochastic variation leading to a simulation uncertainty. This chapter will explain how the simulation power of C" can be optimized by combining them with the machine learning algorithm support vector machines SVMs . Conceptually in SVMs, input vectors are projected in a higher-dimensional feature space in which an optimal separating hyperplane can be constructed for separating the input data into two or more classes. In the comparative analysis, the integrated modeling approach is carried out for a unique postindustrial European agglomeration The Ruhr "rea. It will be demonstrated how the "I learning approach is implemented, calibrated, validated and applied for the prediction of the regional urban land-cover pattern between and . Finally, the probability effects will be visualized with the concept of urban DN".

show abstract

Section: Geosimulation -Using the Ai Of Cellsmentioning

confidence: 99%

Section: Support Vector Machinesmentioning

confidence: 99%

The Future of Central European Cities – Optimization of a Cellular Automaton for the Spatially Explicit Prediction of Urban Sprawl

Rienow¹

2016

Optimization Algorithms - Methods and Applications

View full text Add to dashboard Cite

show abstract

“…In order to balance the spatial resolution and the spatial extent of the Ruhr, a grid resolution of 100 m was used. This classification procedure is described in detail by goetzke et al sChoettker (2003).…”

Section: The Data-discretizing the Surface Of The Worldmentioning

confidence: 99%

Sprawling cities and shrinking regions – forecasting urban growth in the Ruhr for 2025 by coupling cells and agents

Rienow¹,

Stenger²,

Menz³

2014

Erdkunde

View full text Add to dashboard Cite

In the 20 th century, the environment of Central Europe was shaped by an extensive growth of urban areas leading to sprawling agglomerations. While the cities' morphological growth is still proceeding, a second major trend is emerging nowadays: urban decline. Accordingly, the polycentric agglomeration of the Ruhr (North Rhine-Westphalia, Germany) simultaneously faces a demographic decline and a physical extension. The modeling of both trends is essential in order to estimate their social and ecological impacts. Among urban land-use models are artificial intelligence techniques like cellular automata (CA) and multi-agent systems (MAS). While CA focus on discrete spatial entities, MAS are well-suited to capture individual decision making. This study presents an approach dealing with the integration of both complementary methods: the coupling of the MAS ReHoSh (Residential Mobility and the Housing Market of Shrinking City Systems) and the CA SLEUTH. SLEUTH is one of the best-assessed spatiallyexplicit urban growth models applied in numerous studies all over the world. Here, the CA will be guided by support vector machines in order to enhance its modeling performance. ReHoSh is a newly implemented MAS catching the interactions between stakeholders of housing markets and the development of potential residential areas in a declining urban environment. The concept of semi-explicit urban weights is introduced transferring the probable dwelling demand as results of individual decision making into the cellular environment. The CA-MAS combination is calibrated in order to mine the urban future of the Ruhr. Beside a "business as usual"-scenario, two further scenarios of changing housing preferences are simulated for 2025. They reflect the dissemination of sustainable thinking among stakeholders and the steady dream of owning a house in sub-and exurban areas. The created total probability maps clearly influence the future rates of SLEUTH. The CA is successfully provided with scenarios resulting in different extents of the Ruhr's urban area for the year 2025: 136,007 ha ("business as usual"), 134,285 ha ("sustainable thinking"), and 140,141 ha ("dream of owning a house"). The spatial impacts are visualized with the concept of urban DNA and a digital petri dish. Here, it becomes obvious that a sprawled pattern of the cities of the Ruhr is just prevented in the scenario "sustainable thinking". Zusammenfassung: Die Zunahme von Siedlungs-und Verkehrsflächen und die damit verbundenen ökologischen Probleme wie Landschaftszerschneidung oder Flächenversiegelung stellen in Deutschland eine noch nicht gelöste Herausforderung dar. Nach neueren Erkenntnissen geht die Flächeninanspruchnahme zwar zurück, doch ist die Erreichung des 30-Hektar-Ziels nach wie vor in weiter Ferne. Gerade auch in schrumpfenden Regionen ist eine ungebremste Ausweitung von Siedlungs-und Verkehrsflächen zu beobachten. Die Gründe für diese Entwicklung lassen sich unter anderem in der angebotsseitigen Bereitstellung von Wohn-und Gewerbeflächen im Zuge einer wachsende...

show abstract

Flächenmonitoring in der Regional- und Bauleitplanung

Bruns

Gähler

Lange

2008

STANDORT-Z Angew Geogr

View full text Add to dashboard Cite

Monitoring statewide urban development using multitemporal multisensoral satellite data covering a 40-year time span in north Rhine-Westphalia (Germany)

Cited by 3 publications

References 3 publications

The Future of Central European Cities – Optimization of a Cellular Automaton for the Spatially Explicit Prediction of Urban Sprawl

The Future of Central European Cities – Optimization of a Cellular Automaton for the Spatially Explicit Prediction of Urban Sprawl

Sprawling cities and shrinking regions – forecasting urban growth in the Ruhr for 2025 by coupling cells and agents

Flächenmonitoring in der Regional- und Bauleitplanung

Contact Info

Product

Resources

About