Harnessing Machine Learning Algorithms to Model the Association between Land Use/Land Cover Change and Heatwave Dynamics for Enhanced Environmental Management

Land, Год журнала: 2024, Номер 13(8), С. 1273 - 1273

Опубликована: Авг. 12, 2024

As we navigate the fast-paced era of urban expansion, integration machine learning (ML) and remote sensing (RS) has become a cornerstone in environmental management. This research, focusing on Silchar City, non-attainment city under National Clean Air Program (NCAP), leverages these advanced technologies to understand microclimate its implications health, resilience, sustainability built environment. The rise land surface temperature (LST) changes use cover (LULC) have been identified as key contributors thermal dynamics, particularly development heat islands (UHIs). Urban Thermal Field Variance Index (UTFVI) can assess influence UHIs, which is considered parameter for ecological quality assessment. research examines interlinkages among LST, dynamics City due substantial air temperature, poor quality, particulate matter PM2.5. Using Landsat satellite imagery, LULC maps were derived 2000, 2010, 2020 by applying supervised classification approach. LST was calculated converting band spectral radiance into brightness temperature. We utilized Cellular Automata (CA) Artificial Neural Networks (ANNs) project potential scenarios up year 2040. Over two-decade period from 2000 2020, observed 21% expansion built-up areas, primarily at expense vegetation agricultural lands. transformation contributed increased with over 10% area exceeding 25 °C compared just 1% 2000. CA model predicts areas will grow an additional 26% 2040, causing 4 °C. UTFVI analysis reveals declining comfort, worst affected zone projected expand 7 km2. increase PM2.5 aerosol optical depth past two decades further indicates deteriorating quality. study underscores ML RS management, providing valuable insights that guide policy formulation sustainable planning.

Язык: Английский

---

Spatiotemporal analysis of land surface temperature and land cover changes in Prešov city using downscaling approach and machine learning algorithms

Environmental Monitoring and Assessment, Год журнала: 2025, Номер 197(2)

Опубликована: Янв. 3, 2025

Abstract In recent decades, global climate change and rapid urbanization have aggravated the urban heat island (UHI) effect, affecting well-being of citizens. Although this significant phenomenon is more pronounced in larger metropolitan areas due to extensive impervious surfaces, small- medium-sized cities also experience UHI effects, yet research on these rare, emphasizing importance land surface temperature (LST) as a key parameter for studying dynamics. Therefore, paper focuses evaluation LST cover (LC) changes city Prešov, Slovakia, typical European that has recently undergone LC changes. study, we use relationship between Landsat-8/Landsat-9-derived spectral indices Normalized Difference Built-Up Index (NDBI), Vegetation (NDVI), Water (NDWI) derived from Landsat-8/Landsat-9 Sentinel-2 downscale 10 m. Two machine learning (ML) algorithms, support vector (SVM) random forest (RF), are used assess image classification identify how different types selected years 2017, 2019, 2023 affect pattern LST. The results show several decisions made during last decade, such construction new fabrics roads, caused increase evaluation, based RF algorithm, achieved overall accuracies 93.2% 89.6% 91.5% 2023, outperforming SVM by 0.8% 2017 4.3% 2023. This approach identifies UHI-prone with higher spatial resolution, helping planning mitigate negative effects increasing LSTs.

Язык: Английский

---

Seasonal Land Use and Land Cover Mapping in South American Agricultural Watersheds Using Multisource Remote Sensing: The Case of Cuenca Laguna Merín, Uruguay

Sensors, Год журнала: 2025, Номер 25(1), С. 228 - 228

Опубликована: Янв. 3, 2025

Recent advancements in Earth Observation sensors, improved accessibility to imagery and the development of corresponding processing tools have significantly empowered researchers extract insights from Multisource Remote Sensing. This study aims use these technologies for mapping summer winter Land Use/Land Cover features Cuenca de la Laguna Merín, Uruguay, while comparing performance Random Forests, Support Vector Machines, Gradient-Boosting Tree classifiers. The materials include Sentinel-2, Sentinel-1 Shuttle Radar Topography Mission imagery, Google Engine, training validation datasets quoted methods involve creating a multisource database, conducting feature importance analysis, developing models, supervised classification performing accuracy assessments. Results indicate low significance microwave inputs relative optical features. Short-wave infrared bands transformations such as Normalised Vegetation Index, Surface Water Index Enhanced demonstrate highest importance. Accuracy assessments that various classes is optimal, particularly rice paddies, which play vital role country’s economy highlight significant environmental concerns. However, challenges persist reducing confusion between classes, regarding natural vegetation versus seasonally flooded vegetation, well post-agricultural fields/bare land herbaceous areas. Forests Trees exhibited superior compared Machines. Future research should explore approaches Deep Learning pixel-based object-based integration address identified challenges. These initiatives consider data combinations, including additional indices texture metrics derived Grey-Level Co-Occurrence Matrix.

Язык: Английский

---

Ecological Management Zoning Identification by Coupling Blue-Green and Gray Infrastructure Networks: A Case Study of Guizhou Province, China

Land, Год журнала: 2025, Номер 14(1), С. 204 - 204

Опубликована: Янв. 20, 2025

Ecological management zoning is crucial for maintaining regional ecological security and realizing differentiated urban governance. However, the existing methods are overly focused on functional attributes fail to adequately consider impacts of human activities, resulting in an insufficiently rational allocation resources. Taking Guizhou Province as example, using multi-source data spatial analysis tools, this study proposed framework based coupling blue-green infrastructure (BGI) network gray (GI) network. The results indicated that (1) BGI area included 179 sources, with a total 54,228.80 km2, 232 corridors. (2) There were 53 sources GI network, totaling 709.19 corridors first, second, third levels 11,469.31 km, 6703.54 5341.30 respectively. (3) 606 barrier points identified, mainly distributed central part area, disturbance zone was 1132.50 which had largest distribution Qiandongnan, followed by Qiannan. (4) At county scale, five zones identified four indicators, namely, source ratio corridor density ratio, point. Then, we targeted optimizations restorations each zone. This organically linked anthropogenic identify zones, will provide new perspectives synergies between protection economic development.

Язык: Английский

---

Exploring the urban heat island phenomenon in a tropical medium-sized city: insights for sustainable urban development

Environmental Monitoring and Assessment, Год журнала: 2025, Номер 197(4)

Опубликована: Март 20, 2025

Язык: Английский

---

Effect of urban morphology on local-scale urban heat island intensity under varying urbanisation: A case study of Wuhan

Sustainable Cities and Society, Год журнала: 2025, Номер unknown, С. 106328 - 106328

Опубликована: Март 1, 2025

Язык: Английский

---

Identification of Key Drivers of Land Surface Temperature Within the Local Climate Zone Framework

Land, Год журнала: 2025, Номер 14(4), С. 771 - 771

Опубликована: Апрель 3, 2025

The surface urban heat island (SUHI) effect, driven by human activities and land cover changes, leads to elevated temperatures in areas, posing challenges sustainability, public health, environmental quality. While SUHI drivers at large scales are well-studied, finer-scale thermal variations remain underexplored. This study employed the Local Climate Zones (LCZs) framework analyze temperature (LST) dynamics Zhengzhou, China. Using 2022 mean LST data derived from a single-channel algorithm, combined with field surveys remote sensing techniques, we examined 30 potential driving factors spanning natural anthropogenic conditions. Results show that built-type LCZs had higher average LSTs (31.10 °C) compared non-built (28.91 °C), showing greater variability (10.48 °C vs. 6.76 °C). Among five major factor categories, landscape pattern indices dominated LCZs, accounting for 44.5% of variation, while Tasseled Cap Transformation indices, particularly brightness, drove 42.8% variation non-built-type LCZs. Partial dependence analysis revealed wetness fragmentation reduce whereas GDP, imperviousness, cohesion increase it. In population density, connectivity, brightness raise LST, atmospheric dryness provide cooling effects. These findings highlight need LCZ-specific mitigation strategies. Built-type require form optimization, enhanced expanded green infrastructure accumulation. Non-built benefit maintaining soil moisture, addressing dryness, optimizing vegetation configurations. provides actionable insights sustainable environment management resilience.

Язык: Английский

---

Seasonal Spatiotemporal Dynamics and Gradients of the Urban Heat Island Effect in Subtropical Furnace Megacity

Sustainability, Год журнала: 2025, Номер 17(7), С. 3238 - 3238

Опубликована: Апрель 5, 2025

Urban heat island (UHI) effect significantly influences the urban sustainability and health of cities varies seasonally. However, spring autumn have received less attention. Furthermore, research on long-term seasonal UHI changes impacts is insufficient. This study examines spatiotemporal dynamics gradient characteristics in spring, summer, autumn, winter Changsha, a typical subtropical “furnace city” from 2006 to 2022. (1) Spatiotemporal dynamics: The high-temperature (relatively zone zone) range expands most least autumn. Additionally, migrates northward within area, proximity core results multiple effects. (2) Gradient characteristics: proportion decreases varying degrees 5 km central point, but increases 6–8 11–13 gradients, especially 8 aggregation index (AI), contagion (CONTAG), largest patch (LPI) decreased, with patches more affected by these metrics Overall, this offers new insights into effects development UHI, which are crucial for addressing climate change, promoting sustainability, improving human well-being.

Язык: Английский

---

Characterizing Land Surface Temperature (LST) through Remote Sensing Data for Small-Scale Urban Development Projects in the Gulf Cooperation Council (GCC)

Опубликована: Янв. 2, 2024

Given the context of global climate change, a worldwide increase in land surface temperature (LST) is anticipated, leading to exacerbation and broadening its impacts. This could jeopardize environmental conditions countries with predominantly hot harsh climate, such as Bahrain, one Cooperation Countries (GCC) nations. Conversely, Bahrain currently experiencing significant population growth, surge demand for accommodate construction additional residential developments. circumstance allows investigation potential impact use cover alterations on variation Land Surface Temperature (LST). In order accomplish this objective, development project was executed within timeframe spanning from 2013 2023. Four sets Landsat 8 OLI/TIRS remote sensing datasets were selected, each set corresponding four seasons. Each consisted two images: capturing study area before commencement process other depicting after completion development. The analyzed by extracting (LST), normalized difference vegetation index (NDVI), built-up (NDBI) various dates. Subsequently, correlation regression analysis employed examine interrelationships among these three variables. findings demonstrated notable rise mean throughout spring autumn seasons following conclusion activities. indicate positive robust association between LST NDBI across all Moreover, relationship strengthened activities area. there negative NDVI prior region's development, which transformed into post-development. These results provide empirical support notion that small-scale developments contribute LST, primarily driven expansion impervious surfaces areas. can potentially formulation localized adaptation strategies projects.

Язык: Английский

---

Investigation of Temperature, Precipitation, Evapotranspiration, and New Thornthwaite Climate Classification in Thailand

Atmosphere, Год журнала: 2024, Номер 15(3), С. 379 - 379

Опубликована: Март 20, 2024

This study aims (1) to the trend and characteristics of average annual air temperature (Tann), precipitation (Prann), evapotranspiration (PETann) in Thailand over present period (1987–2021) (2) extract climate pattern form a map using New Thornthwaite Climate Classification method considering period. The data were prepared by Thai Meteorological Department. Data variability, mean calculation time series, homogeneity test data, abrupt changes examined. trends each variable calculated Mann–Kendal Sen’s slope test. results indicated that high Tann found Bangkok gradually decreased next area. heterogeneous with change period, increasing found. Prann values west side southern area bottom eastern area; addition, low rainfall was inner land. homogenous no slight trends. PETann %CV spatial distribution determined for same Tann. periods rising torrid thermal index based on an overall torrid-type climate. A semi-arid small middle Thailand, then it shifted toward moist-type precipitation. most variability be extreme power changes.

Язык: Английский

---