Integration of Markov chain analysis and similarity-weighted instance-based machine learning algorithm (SimWeight) to simulate urban expansion

Urban growth and land-use change are a few of many puzzling factors affecting our future cities. Creating a precise simulation for future land change is a challenging process that requires temporal and spatial modeling. Many recent studies developed and trained models to predict urban expansion patterns using Artificial Intelligence (AI). This study aims to enhance the simulation capability of Cellular Automata Markov Chain (CA-MC) model in predicting changes in land-use. This study integrates the Artificial Neural Network (ANN) into CA-MC to incorporate several driving forces that highly impact land-use change. The research utilizes different socio-economic, spatial, and environmental variables (slope, distance to road, distance to urban centers, distance to commercial, density, elevation, and land fertility) to generate potential transition maps using ANN Data-driven model. The generated maps are fed to CA-MC as additional inputs. We calibrated the original CA-MC and our models for 2015 cross-comparing simulated maps and actual maps obtained for Irbid city, Jordan in 2015. Validation of our model was assessed and compared to the CA-MC model using Kappa indices including the agreement in terms of quantity and location. The results elucidated that our model with an accuracy of 90.04% substantially outperforms CA-MC (86.29%) model. The improvement we obtained from integrating ANN with CA-MC suggested that the influence imposed by the driving force was necessary to be taken into account for more accurate prediction. In addition to the improved model prediction, the predicted maps of Irbid for the years 2021 and 2027 will guide local authorities in the development of management strategies that balance urban expansion and protect agricultural regions. This will play a vital role in sustaining Jordan's food security.

show abstract

“…Sim-Wight (Bununu, 2017) (Sangermano et al, 2010) A suitable model for understanding the relationship between the variables.…”

Section: Modelmentioning

confidence: 99%

“… Not appropriate to make a realistic simulation. Sim-Wight ( Bununu, 2017 ) ( Sangermano et al., 2010 ) A suitable model for understanding the relationship between the variables. SLEUTH ( Saxena and Jat, 2019 ) ( Nahavandya et al., 2017 ) Helpful to assess the effect of different scenarios of policies.…”

Section: Introductionmentioning

confidence: 99%

Improving land-use change modeling by integrating ANN with Cellular Automata-Markov Chain model

Gharaibeh

Shaamala

Obeidat

et al. 2020

Heliyon

172

View full text Add to dashboard Cite

show abstract

“…These methods are useful for observing and understanding the dynamics of urban landscapes [6,9,10]. Previously, efforts have been made to model and analyze urban spatial growth and patterns using methods such as cellular automata [11][12][13], the artificial neural network [14,15], the Markov chain [16,17], geographical weighted regression [18], the non-ordinal and Sleuth model [19][20][21], the analytic hierarchy process [22], machine learning models [23,24], and an urban sprawl matrix [25,26]. Batty demonstrated how cellular and agent-based models have the ability to clearly incorporate spatial interaction and mobility [27].…”

Section: Introductionmentioning

confidence: 99%

Monitoring and Modeling the Patterns and Trends of Urban Growth Using Urban Sprawl Matrix and CA-Markov Model: A Case Study of Karachi, Pakistan

Baqa

Fang

et al. 2021

Land

View full text Add to dashboard Cite

Understanding the spatial growth of cities is crucial for proactive planning and sustainable urbanization. The largest and most densely inhabited megapolis of Pakistan, Karachi, has experienced massive spatial growth not only in the core areas of the city, but also in the city’s suburbs and outskirts over the past decades. In this study, the land use/land cover (LULC) in Karachi was classified using Landsat data and the random forest algorithm from the Google Earth Engine cloud platform for the years 1990, 2000, 2010, and 2020. Land use/land cover classification maps as well as an urban sprawl matrix technique were used to analyze the geographical patterns and trends of urban sprawl. Six urban classes, namely, the primary urban core, secondary urban core, sub-urban fringe, scatter settlement, urban open space, and non-urban area, were determined for the exploration of urban landscape changes. Future scenarios of LULC for 2030 were predicted using a CA–Markov model. The study found that the built-up area had expanded in a considerably unpredictable manner, primarily at the expense of agricultural land. The increase in mangroves and grassland and shrub land proved the effectiveness of afforestation programs in improving vegetation coverage in the study area. The investigation of urban landscape alteration revealed that the primary urban core expanded from the core districts, namely, the Central, South, and East districts, and a new urban secondary core emerged in Malir in 2020. The CA–Markov model showed that the total urban built-up area could potentially increase from 584.78 km2 in 2020 to 652.59 km2 in 2030. The integrated method combining remote sensing, GIS, and an urban sprawl matrix has proven invaluable for the investigation of urban sprawl in a rapidly growing city.

show abstract

“…There are two major issues involved in the modeling and prediction of dynamic future urban expansion trends: (1) how to employ the most objective parameterized method to obtain optimally accurate prediction results and (2) whether urban expansion simulations based on variable scenarios lead to substantial differences [9,10]. Various models have been developed and applied to predict the future dynamic changes in urban expansion, such as system dynamics models [11], agent-based models [12], machine learning models [13], cellular automata (CA) models [7], and deep learning models [14]. Different models have their own advantages and disadvantages.…”

Section: Introductionmentioning

confidence: 99%

Simulation of Dynamic Urban Expansion under Ecological Constraints Using a Long Short Term Memory Network Model and Cellular Automata

Liu

Xiao

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Rapid urban expansion has seriously threatened ecological security and the natural environment on a global scale, thus, the simulation of dynamic urban expansion is a hot topic in current research. Existing urban expansion simulation models focus on the mining of spatial neighborhood features among driving factors, however, they ignore the over-fitting, gradient explosion, and vanishing problems caused by the long-term dependence of time series data, which results in limited model accuracy. In this study, we proposed a new dynamic urban expansion simulation model. Considering the long-time dependence issue, long short term memory (LSTM) was employed to automatically extract the transformation rules through memory units and provide the optimal attribute features for cellular automata (CA). This study selected Lanzhou, which is a semi-arid region in Northwest China, as an example to confirm the validity of the model performance using data from 2000 to 2020. The results revealed that the overall accuracy of the model was 91.01%, which was higher than that of the traditional artificial neural network (ANN)-CA and recurrent neural network (RNN)-CA models. The LSTM-CA framework resolved existing problems with the traditional algorithm, while it significantly reduced complexity and improved simulation accuracy. In addition, we predicted urban expansion to 2030 based on natural expansion (NE) and ecological constraint (EC) scenarios, and found that EC was an effective control strategy. This study provides a certain theoretical basis and reference value toward the realization of new urbanization and ecologically sound civil construction, in the context of territorial spatial planning and healthy/sustainable urban development.

show abstract

Integration of Markov chain analysis and similarity-weighted instance-based machine learning algorithm (SimWeight) to simulate urban expansion

Cited by 25 publications

References 69 publications

Improving land-use change modeling by integrating ANN with Cellular Automata-Markov Chain model

Improving land-use change modeling by integrating ANN with Cellular Automata-Markov Chain model

Monitoring and Modeling the Patterns and Trends of Urban Growth Using Urban Sprawl Matrix and CA-Markov Model: A Case Study of Karachi, Pakistan

Simulation of Dynamic Urban Expansion under Ecological Constraints Using a Long Short Term Memory Network Model and Cellular Automata

Contact Info

Product

Resources

About