Investigation on the Expansion of Urban Construction Land Use Based on the CART-CA Model

Abstract

Abstract:Change in urban construction land use is an important factor when studying urban expansion. Many scholars have combined cellular automata (CA) with data mining algorithms to perform relevant simulation studies. However, the parameters for rule extraction are difficult to determine and the rules are simplex, and together, these factors tend to introduce excessive fitting problems and low modeling accuracy. In this paper, we propose a method to extract the transformation rules for a CA model based on the Classification and Regression Tree (CART). In this method, CART is used to extract the transformation rules for the CA. This method first adopts the CART decision tree using the bootstrap algorithm to mine the rules from the urban land use while considering the factors that impact the geographic spatial variables in the CART regression procedure. The weights of individual impact factors are calculated to generate a logistic regression function that reflects the change in urban construction land use. Finally, a CA model is constructed to simulate and predict urban construction land expansion. The urban area of Xinyang City in China is used as an example for this experimental research. After removing the spatial invariant region, the overall simulation accuracy is 81.38% and the kappa coefficient is 0.73. The results indicate that by using the CART decision tree to train the impact factor weights and extract the rules, it can effectively increase the simulation accuracy of the CA model. From convenience and accuracy perspectives for rule extraction, the structure of the CART decision tree is clear, and it is very suitable for obtaining the cellular rules. The CART-CA model has a relatively high simulation accuracy in modeling urban construction land use expansion, it provides reliable results, and is suitable for use as a scientific reference for urban construction land use expansion.

Machine Learning Techniques for Modelling Short Term Land-Use Change

“…Distance to the street of category I (d streetI ) x 10 Distance to the street of category II (d streetII ) x 11 Number of inhabitants (no_inhabitants) x 12 Land use class (LU_class) x 13 Most frequent land use class in Moore neighbourhood 7 × 7 (mf_LU_class) x 14 Second most frequent land use class in Moore neighbourhood 7 × 7 (smf_LU_class) x 15 Previous land use class (prev_LU_class)…”

“…LUC is influenced by many driving factors, ranging from socioeconomic conditions, demography, landscape topography, physical infrastructure, and planning constraints and policies. Consequently, modeling the LUC process is a challenging undertaking that has been implemented using various techniques, from logistic and multiple regression [4][5][6], Markov models [7,8], cellular automata [9][10][11], agent-based approaches [12,13], and more recently, machine learning (ML) techniques [14,15]. Modeling the LUC process is dependent on availability of various and large data sets including demographic, geospatial, and historical data, and can be expressed as being data-driven.…”

How Human Activity Has Changed the Regional Habitat Quality in an Eco-Economic Zone: Evidence from Poyang Lake Eco-Economic Zone, China

“…This method automatically establishes the classification threshold and builds a decision tree based on manually selected training samples. It can comprehensively utilize the spectral information in the image and other auxiliary information to improve the classification accuracy [ 44 , 45 , 46 ].…”

Modeling Urban Collaborative Growth Dynamics Using a Multiscale Simulation Model for the Wuhan Urban Agglomeration Area, China

“…Nevertheless, these statistical approaches are mostly limited to capturing causal relations between explanatory and dependent variables in a quantitative way, and make it difficult to reflect the changing relationships in a space. Cellular automata as a spatial explicit approach has been used widely to simulate the processes of urban growth dynamics [17][18][19][20][21][22][23][24]. However, CA presents the growth dynamic by assuming that the change of cell states is based on the micro-scale local neighboring interaction to emerging global spatial pattern, neglecting the macro-scale driving forces [24][25][26].…”