A novel spatio-temporal cellular automata model coupling partitioning with CNN-LSTM to urban land change simulation

Zhou, Ye; Huang, Chen; Wu, Tao; Zhang, Mingyue

doi:10.1016/j.ecolmodel.2023.110394

Cited by 23 publications

(9 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…During the study period, the urban growth was dual, implying that one space unit became urban land or not [38,39]. The changed and unchanged units had a value of 1 and 0, respectively.…”

Section: Urban Growth Potential Calculationmentioning

confidence: 99%

Quota and Space Allocations of New Urban Land Supported by Urban Growth Simulations: A Case Study of Guangzhou City, China

Zhu

Liu

et al. 2023

Land

View full text Add to dashboard Cite

Previous allocations of new urban land were ineffective because they lacked synergy between quota and space, challenging the government planning authority. This study proposes a new and more reasonable urban land allocation method to guide the smart growth of cities. We used a logistic regression model and multisource data to explore the laws of urban growth and employed a cellular automata (CA) model to simulate this under inertial and constrained scenarios. In addition, the disparities between both scenarios concerning allocation were analyzed. We realized the synergy of quota and space allocations of new urban land through urban growth simulation. Further, the allocation of new urban land was more consistent with the development strategy of Guangzhou under a constrained scenario. The allocation of space was more regular and concentrated under a constrained scenario, which aligns with the requirements of the Government Land Space Planning. Additionally, in the constrained scenario, the bottom lines of cultivated land protection, ecological service, and geological safety were better controlled. This study compensated for the shortcomings of the disjoined quota and space allocations of new urban land and proved that a constrained scenario can more effectively promote reasonable urban growth.

show abstract

“…During the study period, the urban growth was dual, implying that one space unit became urban land or not [38,39]. The changed and unchanged units had a value of 1 and 0, respectively.…”

Section: Urban Growth Potential Calculationmentioning

confidence: 99%

Quota and Space Allocations of New Urban Land Supported by Urban Growth Simulations: A Case Study of Guangzhou City, China

Zhu

Liu

et al. 2023

Land

View full text Add to dashboard Cite

show abstract

“…For example, the development of methodologies based on artificial neural networks (ANN), [5] support vector machines (SVM) and random forests (RF) [6] . Nonetheless, evaluating LULC involves a prolonged process characterized by distinct temporal and spatial variations, heightening the intricacy of the study by Zhou et al [7] In particular, the use of convolutional neural networks (CNNs) has emerged as a promising and innovative strategy that achieves comparatively good results, with an overall accuracy (OA) greater than 90 % [ 8 , 9 ]. Nowadays, a large number of neural networks has been developed and selecting the most appropriate method depends on factors such as its intended application, available computational resources, and the volume of training data accessible.…”

Section: Introductionmentioning

confidence: 99%

Development of a convolutional neural network to accurately detect land use and land cover

Acuña-Alonso,

García-Ontiyuelo,

Barba-Barragáns

et al. 2024

MethodsX

View full text Add to dashboard Cite

“…These spatial attributes determine the feasibility and sustainability of land use types within a region, thereby directly influencing the patterns of land use change [17,18]. Temporal factors encompass both long-term and short-term changes, including population shifts, economic development levels, climate change trends, and variations in policies and regulations [19]. Spatial factors provide the physical and geographical conditions for land use changes, while temporal factors reflect the evolution and dynamics of these changes over time [20].…”

Section: Introductionmentioning

confidence: 99%

VST-PCA: A Land Use Change Simulation Model Based on Spatiotemporal Feature Extraction and Pre-Allocation Strategy

Liu,

Luo,

Wang

et al. 2024

IJGI

View full text Add to dashboard Cite

Land use/cover change (LUCC) refers to the phenomenon of changes in the Earth’s surface over time. Accurate prediction of LUCC is crucial for guiding policy formulation and resource management, contributing to the sustainable use of land, and maintaining the health of the Earth’s ecosystems. LUCC is a dynamic geographical process involving complex spatiotemporal dependencies. Existing LUCC simulation models suffer from insufficient spatiotemporal feature learning, and traditional cellular automaton (CA) models exhibit limitations in neighborhood effects. This study proposes a cellular automaton model based on spatiotemporal feature learning and hotspot area pre-allocation (VST-PCA). The model utilizes the video swin transformer to acquire transformation rules, enabling a more accurate capture of the spatiotemporal dependencies inherent in LUCC. Simultaneously, a pre-allocation strategy is introduced in the CA simulation to address the local constraints of neighborhood effects, thereby enhancing the simulation accuracy. Using the Chongqing metropolitan area as the study area, two traditional CA models and two deep learning-based CA models were constructed to validate the performance of the VST-PCA model. Results indicated that the proposed VST-PCA model achieved Kappa and FOM values of 0.8654 and 0.4534, respectively. Compared to other models, Kappa increased by 0.0322–0.1036, and FOM increased by 0.0513–0.1649. This study provides an accurate and effective method for LUCC simulation, offering valuable insights for future research and land management planning.

show abstract

A novel spatio-temporal cellular automata model coupling partitioning with CNN-LSTM to urban land change simulation

Cited by 23 publications

References 39 publications

Quota and Space Allocations of New Urban Land Supported by Urban Growth Simulations: A Case Study of Guangzhou City, China

Quota and Space Allocations of New Urban Land Supported by Urban Growth Simulations: A Case Study of Guangzhou City, China

Development of a convolutional neural network to accurately detect land use and land cover

VST-PCA: A Land Use Change Simulation Model Based on Spatiotemporal Feature Extraction and Pre-Allocation Strategy

Contact Info

Product

Resources

About