Simulating large-scale urban land-use patterns and dynamics using the U-Net deep learning architecture

Wang, Jinzhu; Hadjikakou, Michalis; Hewitt, Richard J.; Bryan, Brett A.

doi:10.1016/j.compenvurbsys.2022.101855

Cited by 15 publications

(5 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, fundamentally, the neighborhood effect describes the dependence of land use at position (i, j) on land use at other positions in the CA model [33]. Additionally, other studies have adopted a top-down probabilistic ranking approach to allocate land use types without relying on the CA model [32,39]. This method effectively utilizes extracted transition probabilities but heavily depends on the accuracy of these probabilities.…”

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

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

show abstract

“…Sensitivity experiments showed that soil moisture is the most crucial factor in predicting summer rainfall in China. Wang et al [39] advances in deep learning enable complex spatial patterns such as urban development to be learned and simulated, wang used the U-Net deep learning algorithm to capture historical urban development and simulate future patterns for the North China Plain, the results showed that it can accurately predict urban land-use and mimic real-world spatial patterns. Marhamati et al [40] propose a novel approach for segmenting depressed human tongues in photographic images called the learning-toaugment incorporated U-Net (LAIU-Net).…”

Section: Introductionmentioning

confidence: 99%

Improving Convective Cloud Classification with Deep Learning: The CC-Unet Model

Rumapea,

Zarlis,

Efendy

et al. 2024

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

Analyzing and mitigating natural disasters can be a challenging task, which is why the field of computer science, specifically artificial intelligence (AI) is necessary to aid in the complexity of disaster management. AI provides the tools and analytical models to help solve the intricacies of handling natural disasters. Convective clouds, closely related to rain and can lead to large-scale, prolonged hydrometeorological disasters, are a crucial component to consider. To improve the classification of these clouds, a predictive-analytical model based on deep learning, called the CC-Unet model, was developed. This model utilizes a U-Net architecture and is trained using a dataset of convective cloud images. The researchers used satellite image data from the Himawari 8 satellite collected in May and October 2021. The images were pre-processed and verified using observational data. The model was tested using a random train-test split method, showing that the CC-Unet model had a higher accuracy of 97.29% compared to the U-Net model, which had an accuracy of 94.17%. Additionally, the significance test using the Wilcoxon method showed that the CC-Unet model had significantly different performance results from the U-Net model. The ground truth image was also compared with the predicted image, showing a low root mean square error value of 0.0218, indicating a high level of similarity between the two. Overall, this research demonstrates the potential of AI and deep learning in classifying convective clouds to aid in natural disaster management.

show abstract

“…Remote sensing data and models enrich the method to study urban land use change (Liu et al, 2022;Wang et al, 2022). Yi (1993) successfully determined the transfer probability of land use type by remote sense image, and predicted the change trend of land use type by using the Markov chain model, which put forward reasonable suggestions for the future development strategy of the city.…”

Section: Introductionmentioning

confidence: 99%

Analysis and prediction of land use change characteristics in Nanchang from 2005 to 2035

Wang

Zhong

et al. 2023

Preprint

View full text Add to dashboard Cite

With the Rapid urban expansion and development, the contradiction between human and land has gradually emerged, and how to scientifically and rationally use land is an inescapable problem. Nanchang was selected to study in the study, land use change images of Landsat from 2005 to 2020 was analyzed, and predicted land use situation of Nanchang in 2035 by CA-Markov model, to analyze and evaluate the scientific and effective use of land resources in Nanchang. The results show that from 2005 to 2020, woodland continued to decrease, with a total decrease of 300.27 km2 in 15 years; unused land was developed into construction land and agricultural land, the proportion of unused land became less and less; the proportion of grassland and construction land increased, and the expansion rate of construction land increased. Agricultural land, woodland, grassland and water area are greatly affected by elevation slope; The construction land is greatly affected by the convenience of transportation, and the old construction land as the initial boundary of expansion has driven the transformation of surrounding land use. In 2035, agricultural land will remain largely stable; wood land will slightly decrease; both grassland and water area show a decreasing trend; the construction land increase by 306.31km2. Understanding the characteristics and laws of land use change in Nanchang is conducive to urban sustainable development planning. Simultaneous development and protection are conducive to the sustainable use of land resources and sustainable regional development.

show abstract

Simulating large-scale urban land-use patterns and dynamics using the U-Net deep learning architecture

Cited by 15 publications

References 47 publications

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

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

Improving Convective Cloud Classification with Deep Learning: The CC-Unet Model

Analysis and prediction of land use change characteristics in Nanchang from 2005 to 2035

Contact Info

Product

Resources

About