A hybrid cellular automaton model integrated with 3DCNN and LSTM for simulating land use/cover change

International Journal of Digital Earth, Journal Year: 2025, Volume and Issue: 18(1)

Published: Jan. 1, 2025

Accurate simulation of land use/cover change (LUCC) is crucial for societal development. LUCC a nonlinear spatiotemporal process with complicated relationships and latent dependencies on spatial temporal neighborhoods. It challenge conventional statistical or machine learning methods to efficiently obtain high-level representations information time series features at the same time. To address this issue, we introduced hybrid model integrating deep networks cellular automata, named DST-CA. This uses 3D Convolutional Neural Network (3DCNN) capture local short-term Long Short-Term Memory (LSTM) extract long-term chronological featurereferences, thereby more comprehensively capturing characteristics LUCC. We employed DST-CA simulate in Guangdong Province from 2015 2020. The results indicate that outperforms traditional models four temporal-feature across evaluation metrics, including Overall Accuracy (OA), F1-score, Figure Merit (FoM), Kappa coefficient. Compared 3DCNN-CA LSTM-CA, these metrics improved by 1.5%, 1.61%, 14.36%, 2.75%, respectively. implies possesses outstanding global capabilities superior ability Finally, forecasted 2025.

Language: Английский

---

Multi-Scenario Simulation of Ecosystem Service Value in Beijing’s Green Belts Based on PLUS Model

Land, Journal Year: 2025, Volume and Issue: 14(2), P. 408 - 408

Published: Feb. 16, 2025

Urbanization and economic growth have substantially modified the land utilization structure, affecting ecosystem services their spatial distribution. As a crucial component of Beijing’s urban framework, city’s green belts, located at periphery its core metropolitan area, play vital role in supplying services. They also represent focal point for use transformation conflicts, making them an important study area. This research utilizes data from 2000, 2005, 2010, 2015, 2020 as primary dataset. It adopts standard equivalent factor integrates it with Patch-Generaling Land Use Simulation (PLUS) model to belts 2035 under three scenarios: natural development scenario (NDS), ecological protection (EPS) cultivated (CPS). The aims analyze project temporal evolution service values (ESVs) different scenarios Beijing. results indicate that (1) is dominated by cropland construction land. Construction has expanded significantly since increasing 500.78 km2, while decreased 488.47 km2. Woodland, grassland, water seen reduction. Overall, there trend woodland being converted into cropland, subsequently transitioning (2) In NDS, increases 91.76 decrease. EDS, decelerates 22.09 reduction decelerates, conversion limited. Grassland remain largely unchanged, experiences slight increase. CPS, notably reduced, 11.97 slightly, grassland decreasing slightly. (3) ESV ranking across follows: EPS 1830.72 mln yuan > CPS 1816.23 NDS 1723.28 yuan. Hydrological regulation climate are dominant all scenarios. attains greatest gains. contributes understanding effects changes on ESV, offering valuable empirical evidence sustainable decision-making swiftly urbanizing areas.

Language: Английский

---

Instability and uncertainty of carbon storage in karst regions under land use change: a case study in Guiyang, China

Frontiers in Environmental Science, Journal Year: 2025, Volume and Issue: 13

Published: Feb. 20, 2025

Introduction Karst regions are integral to the global carbon cycle. However, land use changes of karst driven by urbanization and desertification contribute instability storage, leading uncertainties in future. Understanding these instabilities is crucial for formulating sequestration management strategies. Methods This study employed Patch-generating Land Use Simulation (PLUS) Integrated Valuation Ecosystem Services Trade-offs (InVEST) estimate introduced Coefficient Variation (CV) assess uncertainty. Multiscale Geographically Weighted Regression (MGWR) was applied explore mechanisms, while Polynomial (PR) identified stable intervals factors, informing land-use policies. Results Discussion (1) From 2000 2020, Guiyang’s storage rose from 136.62 Tg 142.13 Tg. By 2035, projections under natural development, urban expansion, ecological protection scenarios increases 147.50 Tg, 147.40 147.82 respectively. (2) Carbon increased uncertainty expected decrease 2035. Instability primarily due transitions Cropland-Forest, Forest-Cropland, Cropland-Grassland, Cropland-Impervious, mainly arise Grassland-Impervious transitions. (3) DEM, AI, Distance national highways, SHDI, Mean annual precipitation affected significantly. (4) Encouraging Shrub-Forest, Shrub-Cropland Cropland-Forest conversions, controlling Forest-Shrub, Cropland-Impervious conversions within can enhance reduce establishes a methodology evaluating regions, which an extension research.

Language: Английский

---

Examining the Spatiotemporal Evolution of Land Use Conflicts from an Ecological Security Perspective: A Case Study of Tianshui City, China

Sustainability, Journal Year: 2025, Volume and Issue: 17(5), P. 2253 - 2253

Published: March 5, 2025

Land use conflicts represent an increasing challenge to sustainable development, particularly in regions undergoing rapid urbanization. This study investigated the spatiotemporal dynamics of land and their ecological implications Tianshui City from 1980 2020. The main objectives were identify patterns spatial heterogeneity, explore driving factors behind these conflicts, analyze relationship with risks. results indicate following findings. In terms early changes primarily driven by structural factors, such as topography climate, a Nugget/Still ratio <0.30 observed 2000. After 2000, however, stochastic including average annual urbanization rate increase 5.2% GDP growth 9.1%, emerged dominant drivers, reflected > 0.36. Regarding conflict intensity, high-conflict areas expanded approximately 1110 square kilometers between 2020, predominantly concentrated fertile agricultural Weihe River Basin urban core areas. Conversely, non-conflict zones decreased 38.7%. risk correlation, bivariate LISA cluster analysis revealed significant autocorrelation severe risks (Moran’s I = 0.62, p < 0.01). High-risk clusters transitioning arable built-up increased 23% after Predictions based on future land-use simulation (FLUS) model suggest that 2030, high-intensity will expand additional 16%, leading intensified competition for resources. Therefore, incorporating safety thresholds into planning policies is essential reconciling development conservation, thereby promoting transitions.

Language: Английский

---

Comparative study of multiple algorithms classification for Land Use and Land Cover Change Detection and its impact on local climate of Mardan District, Pakistan

Environmental Challenges, Journal Year: 2024, Volume and Issue: unknown, P. 101069 - 101069

Published: Dec. 1, 2024

Language: Английский

---

Driving Analysis and Multi Scenario Simulation of Ecosystem Carbon Storage Changes Based on the InVEST-PLUS Coupling Model: A Case Study of Jianli City in the Jianghan Plain of China

Sustainability, Journal Year: 2024, Volume and Issue: 16(16), P. 6736 - 6736

Published: Aug. 6, 2024

The carbon storage capacity of terrestrial ecosystems serves as a crucial metric for assessing ecosystem health and their resilience to climate change. By evaluating the effects land use alterations on this storage, management strategies can be improved, thereby promoting reduction sequestration. While county-level cities are pivotal ecological conservation high-quality development, they often face developmental challenges. Striking balance between economic growth meeting peak emissions neutrality objectives is particularly challenging. Consequently, there an urgent need bolster research into management. study focuses Jianli City, employing InVEST model data examine response patterns changes system from 2000 2020. Using PLUS model, simulated in City year 2035 under three scenarios: Natural Development scenario, Urban Expansion Ecology food security scenario. Our findings indicate following: (1) Between 2020, significant shifts were observed City. These predominantly manifested interchange Cropland Water areas enlargement impervious surfaces, leading decrease 691,790.27 Mg storage. (2) Under proposed scenarios—Natural scenario—the estimated capacities 39.95 Tg, 39.90 40.14 respectively. When compared with 2020 data, all these estimates showed increase. In essence, our offers insights optimizing structures standpoint ensure stability Jianli’s levels while mitigating risks associated fixation. This has profound implications harmonious evolution regional eco-economies.

Language: Английский

---