Ecosystem Health Assessment of the Zerendy District, Kazakhstan

Sustainability, Journal Year: 2025, Volume and Issue: 17(1), P. 277 - 277

Published: Jan. 2, 2025

An ecosystem health assessment (EHA) is essential for comprehensively improving the ecological environment and socio-economic conditions, thereby promoting sustainable development of a specific area. Most previous EHA studies have focused on urbanized regions, paying insufficient attention to rural areas with urban enclaves national natural parks. This study employed Basic Pressure–State–Response methodological approach. The composition indicators (35) encompassed both spatiotemporal data information. random forest algorithm was used Google Earth Engine platform classify evaluate changes in land use cover (LULC). In addition, weighting coefficients were calculated, driving factors subsequently identified. analysis revealed that administrative divisions central part Zerendy district, where city Kokshetau situated, exhibited relatively low level (EH). southwestern studied nature park reserve territories are located, higher EH. Other located eastern parts district generally moderate Interested managers can results our implement adequate measures aimed at ecosystem.

Language: Английский

---

A Novel Method for Predicting Urban Residential Quality Distribution Based on Multi-Interest Consideration

Buildings, Journal Year: 2025, Volume and Issue: 15(2), P. 192 - 192

Published: Jan. 10, 2025

Simulating and predicting urban patterns enables evidence-based decision-making for planners. Given limited resources, understanding how to improve residential quality rationally plan the distribution of different levels warrants further study. Using cellular automata (CA) agent-based modules, this study proposes a multi-stakeholder model analyze future buildings under scenarios. The proposed comprises two modules: CA module an functional layout distribution. develops city, upon which multiple interests government, developers, residents are taken as constraints by predict was applied case Guanxian County in Shandong Province, China. Three scenario analyses were conducted: free development scenario, government macro-regulation with adjusted preference value quality. results show that predictions make it possible align residents’ needs scenarios; hence, unreasonable characteristics can be explored develop effective improvement measures.

Language: Английский

---

Prediction of land cover changes in an Urban City of Bangladesh using artificial neural network-based cellular automata

Urban Lifeline, Journal Year: 2025, Volume and Issue: 3(1)

Published: March 25, 2025

Abstract Savar, a newly developed suburb of Dhaka, is rapidly urbanizing due to various socioeconomic and environmental factors. This study was conducted evaluate temporal spatial changes in Land Use Cover (LULC) for the years 1980, 2000, 2020 predict future LULC changes. Supervised classification algorithms cellular automata model based on Artificial Neural Networks (ANN) were used prepare maps simulations. The methodology designed overcome limitations traditional land use cover change modeling, including low accuracy, computational inefficiency, limited adaptability complex patterns. revealed that rate built-up area increased significantly over 40 while barren agricultural decreased drastically. Future simulation results illustrated would increase by 95.07 km 2 (33.29%) 2040. model's prediction growth areas 2040 demonstrated significant rise urban coverage with an accuracy 41.14%. Therefore, this will help us understand present dynamics along trend assist planners, policymakers, stakeholders sustainable planning techniques management.

Language: Английский

---

Relative and Combined Impacts of Climate and Land Use/Cover Change for the Streamflow Variability in the Baro River Basin (BRB)

Earth, Journal Year: 2024, Volume and Issue: 5(2), P. 149 - 168

Published: April 24, 2024

The interplay between climate and land use/cover significantly shapes streamflow characteristics within watersheds, with dominance varying based on geography watershed attributes. This study quantifies the relative combined impacts of change (LULCC) (CC) variability in Baro River Basin (BRB) using Soil Water Assessment Tool Plus (SWAT+). model was calibrated validated observed data from 1985 to 2014 projected future 2041 2070 under two Shared Socio-Economic Pathway (i.e., SSP2-4.5 SSP5-8.5) scenarios, ensemble four Coupled Model Intercomparison Project (CMIP6) models. LULCC analyzed through Google Earth Engine (GEE) predicted for Land Change Modeler (LCM), revealing reductions forest wetlands, increases agriculture, grassland, shrubland. Simulations show that decrease is attributed LULCC, whereas an increase flow impact CC. CC results a net by 9.6% 19.9% SSP5-8.5 respectively, compared baseline period. Our findings indicate outweighs (LULC) basin, emphasizing importance incorporating comprehensive water resources management adaptation approaches address changing hydrological conditions.

Language: Английский

---

Modeling Spatiotemporal Land Use/Land Cover Dynamics by Coupling Multilayer Perceptron Neural Network and Cellular Automata Markov Chain Algorithms in the Wabe River Catchment, Omo Gibe River Basin, Ethiopia

Environmental Research Communications, Journal Year: 2024, Volume and Issue: 6(10), P. 105011 - 105011

Published: Sept. 27, 2024

Abstract Land Use/Land Cover (LULC) change has been a substantial environmental concern, hindering sustainable development over the past few decades. To that end, comprehending and future patterns of LULC is vital for conserving sustainably managing land resources. This study aimed to analyze spatiotemporal landscape dynamics from 1986 2022 predict situations 2041 2058, considering business-as-usual (BAU) scenario in Wabe River Catchment. The historical use image classification employed supervised technique using maximum likelihood algorithms ERDAS Imagine, identified six major cover classes. For projections changes multilayer perceptron neural network cellular automata-Markov chain were utilized, incorporating various driving factors independent spatial datasets. findings revealed significant ongoing catchment, with persistent trends expected. Notably, woodland, built-up areas, agriculture experienced net increases by 0.24%, 1.96%, 17.22% respectively, while grassland, forest, agroforestry faced notable decreases 4.65%, 3.58%, 11.20% respectively 2022. If current rate continues, agricultural lands will expand 1.28% 5.07%, forest decline 2.69% 3.63% 2058. However, woodland grassland exhibit divergent patterns, projected decrease 0.57% an anticipated increase 0.54% cover. Overall, observed indicated shift towards intensive agriculture, area expansion, potentially adverse consequences such as soil degradation, biodiversity loss, ecosystem decline. mitigate these promote development, immediate action necessary, including environmentally friendly conservation approaches, management practices, habitat protection, reforestation efforts, ensuring long-term resilience viability catchment’s ecosystems.

Language: Английский

---

Navigating Urban Sustainability: Urban Planning and the Predictive Analysis of Busan’s Green Area Dynamics Using the CA-ANN Model

Forests, Journal Year: 2024, Volume and Issue: 15(10), P. 1681 - 1681

Published: Sept. 24, 2024

While numerous studies have employed deep learning and high-resolution remote sensing to predict future land use cover (LULC) changes, no study has integrated these predictive tools with the current urban planning context find a potential issues for sustainability. This addresses this gap by examining of Busan Metropolitan City (BMC) analyzing paradoxical objectives within city’s 2040 Master Plan subordinate 2030 Parks Greenbelts. Although plans advocate increased green areas enhance sustainability social wellbeing, they simultaneously support policies that may lead reduction in due development. Using CA-ANN model MOLUSCE plugin, learning-based LULC change analysis, we forecast further expansion continued shrinkage natural areas. During 1980–2010, underwent high-speed expansion, wherein urbanized almost doubled agricultural lands areas, including forests grassland, reduced considerably. Forecasts years 2010–2040 show at expense agriculture forest grasslands. Given master plans, highlight critical tension between growth Despite push more spaces, replacement landscapes artificial parks threaten long-term In view apparently conflicting goals, framework BMC would take up increasingly stronger conservation adaptive practices consider environmental preservation on par economic development light trajectory urbanization.

Language: Английский

---

Prediction of Greenhouse Area Expansion in an Agricultural Hotspot Using Landsat Imagery, Machine Learning and the Markov–FLUS Model

Sustainability, Journal Year: 2024, Volume and Issue: 16(19), P. 8456 - 8456

Published: Sept. 28, 2024

Greenhouses (GHs) are important elements of agricultural production and help to ensure food security aligning with United Nations Sustainable Development Goals (SDGs). However, there still environmental concerns due excessive use plastics. Therefore, it is understand the past future trends on spatial distribution GH areas, whereby remote sensing data provides rapid valuable information. The present study aimed determine area changes in an hotspot, Serik, Türkiye, using 2008 2022 Landsat imageries machine learning, predict patterns (2036 2050) via Markov–FLUS model. Performances random forest (RF), k-nearest neighborhood (KNN), k-dimensional trees (KD-KNN) algorithms were compared for discrimination. Accordingly, RF algorithm gave highest accuracies over 90%. areas found increase by 73% between 2022. majority new converted from lands. Markov-based predictions showed that GHs likely 43% 54% before 2036 2050, respectively, reliable simulations generated FLUS This believed serve as a baseline research providing first attempt at visualization conditions Turkish Mediterranean region.

Language: Английский

---

Spatiotemporal analysis and identifying the driving forces of land use change in the Abay district (Karagandy Region, Kazakhstan)

E3S Web of Conferences, Journal Year: 2024, Volume and Issue: 590, P. 04007 - 04007

Published: Jan. 1, 2024

Land use and cover change (LUCC) affects the nature of human activities in a particular area. Therefore, manifestation driving forces these changes plays decisive role. This paper analyses LULC dynamics Abay district Karagandy oblast from 2016 to 2023. The study’s main objective is find land based on integrated assessment spatio-temporal data (STD) socio-economic, climatic environmental indicators (SECEI). Classification Sentinel- 2 images into classes carried out using Random Forest (RF) algorithm Google Earth Engine (GEE) platform. factors were assessed principal component analysis (PCA) linear regression (LR). results obtained can be used guide development planning territory.

Language: Английский

---