Combining LSTM and PLUS Models to Predict Future Urban Land Use and Land Cover Change: A Case in Dongying City, China

Zhao, Xin; Wang, Ping; Gao, Songhe; Yasir, Muhammad; Islam, Qamar Ul

doi:10.3390/rs15092370

Cited by 8 publications

(4 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The PLUS model is a comprehensive land use simulation tool that takes into account the environment and social economics in addition to past land use data (Li et al, 2023;Zhao, Wang, et al, 2023;Zhu et al, 2023) sured data in a single plot. Eleven models were selected for evaluation in this study (Table 1).…”

Section: The Patch-generating Land Use Simulation (Plus) Modelmentioning

confidence: 99%

The comprehensive effects of future multi‐scenario land use change and climate change on water conservation in Northwest China

Zhou,

Wu,

Song

et al. 2024

Land Degrad Dev

View full text Add to dashboard Cite

Water conservation is an important ecosystem service, which is crucial to the fragile ecological environment and serious soil erosion in Northwest China. However, water conservation has been affected by climate change and human disturbance, and its future spatial and temporal changes are still unclear. This study employed the Integrated Valuation of Ecosystem Services and Trade‐offs (InVEST) model to assess the water conservation capacity of Northwest China between 1990 and 2020. Subsequently, the Patch‐generating Land Use Simulation (PLUS) model and the NASA Earth Exchange Global Daily Downscaled Projections (NEX‐GDDP‐CMIP6) were integrated to examine changes in water conservation from 2030 to 2050. The water conservation quantity in Northwest China had a fluctuating growth tendency between 1990 and 2020, with an average of 816.61 × 108 m3. The water conservation capacity's regional distribution pattern shows a steady increase from northwest to southeast. Northwest China's forest land had the greatest water conservation capacity between 1990 and 2020, at 66 mm, while the water land had the lowest, at 1.46 mm. The water conservation capacity in the 2030–2050 future scenario is less than that in 2020 when the regional distribution pattern is comparable to 2020. Natural development scenario (ND) in 2030 has the lowest water conservation capacity (13.41 mm) under ssp1‐2.6 precipitation scenario, whereas in 2050, the highest water conservation capacity (17.47 mm) is found in same scenario. The ecological protection scenario (EP) has the greatest water retention capacity (18.15 mm in 2040) and the lowest (14.38 mm in 2050) in the ssp5‐8.5 scenario. Our research can help restore and rebuild Northwest China's natural ecosystem and offer a theoretical foundation for the protection of ecological environment and the rational utilization of water resources in the region.

show abstract

Section: The Patch-generating Land Use Simulation (Plus) Modelmentioning

confidence: 99%

The comprehensive effects of future multi‐scenario land use change and climate change on water conservation in Northwest China

Zhou,

Wu,

Song

et al. 2024

Land Degrad Dev

View full text Add to dashboard Cite

show abstract

“…Although the simulation results in this paper can meet the basic demands, there is still a certain gap with reality. In future research, some parameters can be added to the model, or multiple land use models can be coupled to combine different advantages to improve the simulation accuracy [56].…”

Section: Disadvantages and Limitationsmentioning

confidence: 99%

Simulation of Land Use Based on Multiple Models in the Western Sichuan Plateau

Xiao

Huang

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Many single-land-use simulation models are available to simulate and predict Land Use and Land Cover Change (LUCC). However, few studies have used multiple models to simulate LUCC in the same region. The paper utilizes the CA-Markov model, Land Change Modeler (LCM), and Patch-generating Land Use Simulation model (PLUS) with natural and social driving factors to simulate the LUCC on the Western Sichuan Plateau, using Kappa coefficient, overall accuracy (OA), and Figure of Merit (FoM) to verify the accuracy of the model, and selects a suitable model to predict the LUCC and landscape pattern in the study area from 2020 to 2070. The results are as follows: (1) The LCM has the highest simulation effect, and its Kappa coefficient, OA, and FoM are higher than the other two models. (2) The area of land types other than grassland and wetland will increase from 2020 to 2070. Among them, the grassland area will decrease, but is still most prominent land category in this region. The proportion of wetland areas remains unchanged. The fragmentation degree of forest (F), grassland (GL), shrubland (SL), water bodies (WBs), bare areas (BAs), and permanent ice and snow (PIS) decreases, and the distribution shows a trend of aggregation. The dominance of F and C decreases but still dominates in the landscape. The overall landscape aggregation increased and complexity decreased, and each landscape type’s diversity, evenness, and richness increased, presenting as a more reasonable development. Using multiple models to simulate the LUCC in the same region, and choosing the most suitable local land model is of great significance to scientifically manage and effectively allocate the land resources in the field.

show abstract

“…The traditional panel data regression refers to the calculation process that excludes the correction by the USL exponent. As a time-recursive neural network, LSTM has proven that it can effectively predict land cover change, owing to the spatiotemporal characteristics of input data [54][55][56]. There are many factors influencing the scale of urban land in China, and the interaction mechanism is very complex.…”

Section: The Comparison Between Usl and The Traditional Prediction Me...mentioning

confidence: 99%

A Novel Approach to Predicting Urban Expansion by the Urban Scaling Law at a Single-City Scale

Ye,

Zheng,

Liu

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Rapid urban expansion caused by vigorous urban population growth brought up various socioeconomic and eco-environmental problems, which have important ramifications for sustainable development across the world. Along with the accelerated urbanization process, accurate and realistic prediction of urban expansion is of great importance to optimize urban planning and urban development. This study proposed a new hybrid model, which combined the urban scaling law (USL) with the ANN-CA model to predict urban expansion. To employ urban scaling law in the model, we innovatively calculated the law exponent at a single-city scale. Based on USL, we estimated urban land demand in the future by panel data regression. Finally, we added the area constraint and ecological constraint into the ANN-CA model to simulate urban expansion spatially. This frame of urban expansion has been successfully applied in Shenzhen, of which the urban land area would increase from 816.45 km2 in 2020 to 842.48 km2 in 2025. By comparing this model with the traditional prediction method, we proved its effectiveness and accuracy. Besides, we found that the scaling exponent can reflect urbanization level and distinguish overconstructed cities.

show abstract

Combining LSTM and PLUS Models to Predict Future Urban Land Use and Land Cover Change: A Case in Dongying City, China

Cited by 8 publications

References 50 publications

The comprehensive effects of future multi‐scenario land use change and climate change on water conservation in Northwest China

The comprehensive effects of future multi‐scenario land use change and climate change on water conservation in Northwest China

Simulation of Land Use Based on Multiple Models in the Western Sichuan Plateau

A Novel Approach to Predicting Urban Expansion by the Urban Scaling Law at a Single-City Scale

Contact Info

Product

Resources

About