Delineation of urban growth boundary based on FLUS model under the perspective of land use evaluation in hilly mountainous areas

Journal of Mountain Science, Journal Year: 2024, Volume and Issue: 21(5), P. 1647 - 1662

Published: May 1, 2024

Language: Английский

---

Advancing real-world visual SLAM: Integrating adaptive segmentation with dynamic object detection for enhanced environmental perception

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 255, P. 124474 - 124474

Published: June 13, 2024

Language: Английский

---

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

---

Sub-District Level Spatiotemporal Changes of Carbon Storage and Driving Factor Analysis: A Case Study in Beijing

Land, Journal Year: 2025, Volume and Issue: 14(1), P. 151 - 151

Published: Jan. 13, 2025

Analyzing the current trends and causes of carbon storage changes accurately predicting future land use under different climate scenarios is crucial for regional decision-making management. This study focuses on Beijing as its area introduces a framework that combines Markov model, Patch-based Land Use Simulation (PLUS) Integrated Valuation Ecosystem Services Tradeoffs (InVEST) model to assess at sub-district level. allows systematic analysis spatiotemporal evolution in from 2000 2020, including influence driving factors storage. Moreover, it enables simulation prediction 2025 2040 various scenarios. The results show following: (1) From overall change showed trend “Significant decrease cropland area; Forest increase gradually; Shrub grassland first then decrease; Decrease water; Impervious expands large scale”. (2) “decrease-increase” fluctuation, with an 1.3 Tg. In prediction, ecological protection scenario will contribute achieving goals peak neutrality. (3) Among factors, slope has strongest impact Beijing, followed by Human Activity Intensity (HAI) Nighttime Light Data (NTL). built-up areas, was found HAI DEM (Digital Elevation Model) have effect, NTL Fractional Vegetation Cover (FVC). findings this offer valuable insights sustainable advancement conservation urban development Beijing.

Language: Английский

---

Multi-Scenario Simulation Assessment by utilising PLUS and InVEST Model on the effect of Land Use and Carbon Storage Changes in Hohhot

Environmental and Sustainability Indicators, Journal Year: 2025, Volume and Issue: unknown, P. 100655 - 100655

Published: March 1, 2025

Language: Английский

---

Optimization‐Based Geometric Enhancement and Motion Estimation for Non‐Cooperative Spacecrafts

Journal of Field Robotics, Journal Year: 2025, Volume and Issue: unknown

Published: March 2, 2025

ABSTRACT The state estimation of non‐cooperative spacecrafts is a crucial prerequisite for on‐orbit services. Aiming at the challenges in fusion‐based scheme with monocular vision and sparse point cloud, an optimization‐based method geometric enhancement motion proposed this paper. First, novel idea shape representation using simple features, real‐time segmentation framework established. Differing from models, it can guarantee both complete high inference speed. Second, given assumption local shared planes, new label‐free algorithm cloud densification developed explainable model. To improve its efficiency, curvature‐guided strategy employed to sample depth‐incomplete points conducive feature enhancement. Compared clouds, shows higher pose observation accuracy. Third, truncation compensator built fit high‐order terms nonlinear transition model online optimization, which mitigates impairment priori estimation. Combined adaptive extended Kalman filter, be estimated fewer errors. Finally, validated through comparative simulations ground experiments.

Language: Английский

---

Simulation Analysis of Land Use Change via the PLUS-GMOP Coupling Model

Land, Journal Year: 2025, Volume and Issue: 14(4), P. 802 - 802

Published: April 8, 2025

It is crucial to simulate land use change and assess the corresponding impact on ecosystem services develop informed management policies conservation strategies. To comprehensively patterns of under different evaluate ecological service values (ESV), a method for coupling Generalized Multi-Objective Programming (GMOP) model Patch-generating Land Use Simulation (PLUS) proposed in this study. First, GMOP used obtain optimized solutions scenarios. Then, PLUS analyze mechanism driving expansion, explore conversion patterns, and, ultimately, achieve spatial expression quantity changes. The uncertain parameters coupled are processed by intuitionistic fuzzy numbers. successfully integrates outstanding spatiotemporal dynamic simulation capability multiobjective optimization advantages model, effectively overcoming limitations applying single analysis. Finally, four scenarios established change, namely, business as usual (BAU), economic efficiency priority (RED), protection (ELP), coordinated development (EEB), predict trends values. A case study Ningxia Hui Autonomous Region demonstrates that area agricultural exhibits stable growth trend scenarios, with majority expansion occurring through grassland. Concurrently, rate construction highest BAU scenario at 31.72%, compared 2020. This notably higher than rates observed RED (10.10%) EEB (9.47%) cases. With land, ESV decreased 3.485 billion, 1.514 1.658 billion yuan BAU, RED, ELP representing 41.72%, 24.96%, 34.05% decreases ESV, respectively. integrated methodology accounts various constraints behaviors, thereby ensuring true accurate reflection dynamics. supports quantification strategies, providing policymakers effective support data-driven sustainable planning conservation.

Language: Английский

---

Predicting the spatial pattern of land use change and carbon storage in Xinjiang: A Markov-FLUS-InVEST model approach

PLoS ONE, Journal Year: 2025, Volume and Issue: 20(4), P. e0321929 - e0321929

Published: April 17, 2025

Land-use changes significantly influence carbon storage capacity by altering the structure, layout, and function of terrestrial ecosystems. Predicting relationship between future land-use is essential for optimizing patterns making rational, ecology-based decisions. Using multi-period data from Xinjiang, we analyzed spatial pattern storage. Based on change in Xinjiang 2000 to 2020, coupled Markov-Future Land Use Simulation (FLUS)-Integrated Valuation Ecosystem Services Tradeoffs (InVEST) model simulate predict 2035 under two scenarios: natural growth ecological protection. Carbon its spatiotemporal dynamic these scenarios were evaluated, Geodetector was employed analyze heterogeneity a statistical perspective, revealing various driving factors. The results showed that: (1) From 2000–2020, grassland unused land primary types accounting over 28.85% 60.17% total area, respectively. By 2035, cropland, forest, water, construction areas are expected increase, while projected decrease. Under protection scenario, forest land, grassland—major main contributors storage—will be effectively conserved some extent. (2) Xinjiang’s exhibited an overall increasing trend, with cumulative increase 137.515×10 5 t rate 1.58%. However, this decline estimated reduction 168.344×10 compared that 2020. Ecological anticipated mitigate decline, 13.227×10 relative scenario. (3) analysis indicated had greatest explanatory power (q = 0.80), followed soil 0.41), net productivity 0.32), geomorphology 0.22). This highlights as most critical environmental factor determining These findings provide scientific insights recommendations sustainable development management enhancement functions.

Language: Английский

---

Optimization Simulation and Comprehensive Evaluation Coupled with CNN-LSTM and PLUS for Multi-Scenario Land Use in Cultivated Land Reserve Resource Area

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(9), P. 1619 - 1619

Published: May 2, 2025

The scientific development and utilization of cultivated land reserve resource areas is an important basis for realizing national food security regional ecological protection. This paper focuses on use optimization simulations to explore the paths sustainable in resources areas. Deep learning technology was introduced calculate growth probability each type. A change simulation method coupling CNN-LSTM PLUS constructed dynamically simulate pattern, spatial accuracy improved. Markov chains multi-objective planning (MOP) model were used set historical (HD) scenarios, conservation (EP) consolidation (LC) (SD) scenarios. comprehensive impact ecosystem service value (ESV), agricultural production benefits (APBs), carbon balance (CB) evaluated by systematically analyzing quantitative distribution characteristics different scenarios from 2020 2030. Da’an City, Jilin province, China selected as study area. results this show following: (1) coupled with designed capture dynamic use, which achieves high (Kappa 0.8119). (2) In EP scenario, increase ESV 4.36%, but APB only 7.33%. LC increased 22.11%, while decreased 3.44%. SD a achieved between APB, it optimal path development. (3) scenario performed best, CB 5,532,100 tons, lowest, at 1,493,500 tons. shows potential combining reduction paper, deep modeling multi-scenario integrated, management provided.

Language: Английский

---

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

Remote Sensing, Journal Year: 2023, Volume and Issue: 15(14), P. 3629 - 3629

Published: July 21, 2023

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

Language: Английский

---