The Impact of Urban Spatial Forms on Marine Cooling Effects in Mainland and Island Regions: A Case Study of Xiamen, China

Sustainable Cities and Society, Journal Year: 2025, Volume and Issue: unknown, P. 106210 - 106210

Published: Feb. 1, 2025

Language: Английский

---

Land Use and Land Cover Changes: A Case Study in Nigeria

Land, Journal Year: 2025, Volume and Issue: 14(2), P. 389 - 389

Published: Feb. 13, 2025

Land Use and Cover (LULC) assessment is vital for achieving sustainable ecosystems. This study quantified mapped the spatiotemporal LULC changes in Ado-Odo Ota Local Government Area of Ogun State, Nigeria, between 2015 2023. The was classified into water, forest or thick bush, sparse vegetation, built-up, bare land using Landsat images. Processing, classification, image analysis were done ESRI ArcGIS Pro 3.3. changed from to 2023, with built-up areas vegetation increasing by 138.2 km2 28.7 km2, respectively. In contrast, which had greatest change among classes, decreased 153.7 over this period while water bodies 9.5 3.8 Forest bush (201.0 km2) converted reflects an increase agricultural activities region. conversion about 109.8 3.7 highlights considerable urbanization. Overall, area need use practices balance urban growth ecological preservation, achievable through effective management policy frameworks.

Language: Английский

---

A systematic literature review of remote sensing approaches in urban green space research: Towards achieving sustainable development goals

Urban Climate, Journal Year: 2025, Volume and Issue: 59, P. 102332 - 102332

Published: Feb. 1, 2025

Language: Английский

---

Multi-temporal remote sensing and geospatial analysis for urban ecosystem service dynamics: A three-decade assessment of land surface transformation in Jeddah, Saudi Arabia

Physics and Chemistry of the Earth Parts A/B/C, Journal Year: 2025, Volume and Issue: unknown, P. 103892 - 103892

Published: Feb. 1, 2025

Language: Английский

---

A Novel Deep Learning Architecture for Agriculture Land Cover and Land Use Classification from Remote Sensing Images Based on Network-Level Fusion of Self-Attention Architecture

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Journal Year: 2024, Volume and Issue: 17, P. 6338 - 6353

Published: Jan. 1, 2024

AI-driven precision agriculture applications can benefit from the large data source that remote sensing provides, as it gather agricultural monitoring at various scales throughout year. Numerous advantages for sustainable applications, including yield prediction, crop monitoring, and climate change adaptation, be obtained artificial intelligence. In this work, we proposed a fully automated Optimized Self-Attention Fused Convolutional Neural Network (CNN) architecture land use cover classification using (RS) data. A new contrast enhancement equation has been utilized in augmentation. After that, fused CNN was proposed. The initially consists of two custom models named IBNR-65 Densenet-64. Both have designed based on inverted bottleneck residual mechanism Dense Blocks. both were depth-wise concatenation append layer deep features extraction. trained model performed neural network (NN) classifiers. results NN classifiers are insufficient; therefore, implemented Bayesian Optimization fine-tuned hyperparameters NN. addition, Quantum Hippopotamus Algorithm best feature selection. selected finally classified improved accuracy 98.20, 89.50, 91.70%, highest rate is 98.23, recall f1-score 98.21 respectively, SIRI-WHU, EuroSAT, NWPU datasets. Moreover, detailed ablation study conducted, performance compared with SOTA. shows accuracy, sensitivity, computational time performance.

Language: Английский

---

Susceptibility of Landslide Debris Flow in Yanghe Township Based on Multi-Source Remote Sensing Information Extraction Technology (Sichuan, China)

Land, Journal Year: 2024, Volume and Issue: 13(2), P. 206 - 206

Published: Feb. 8, 2024

The extraction of real geological environment information is a key factor in accurately evaluating the vulnerability to hazards. Yanghe Township located mountainous area western Sichuan and lacks survey data. Therefore, it important predict spatial temporal development law landslide debris flow this improve effectiveness accuracy monitoring changes flow, article proposes method for extracting on flows combined with NDVI variation, which based short baseline interferometry (SBAS-InSAR) optical remote sensing interpretation. In article, we present relevant maps six main factors: vegetation index, slope, slope orientation, elevation, topographic relief, formation lithology. At same time, different images were compared sensitivity assessments. research showed that highest altitude region extracted by multi-source technology 2877 m, lowest 630 can truly reflect relief characteristics region. pixel binary model’s lack regional restrictions enables more accurate estimation Normalized Difference Vegetation Index (NDVI), bringing closer actual situation. study uncovered bidirectional relationship between coverage deformation area, revealing spatial–temporal evolution patterns. By employing technology, effectively utilized multi-period imagery feature methods depict process distribution flow. This approach not only offers technical support but also provides guidance

Language: Английский

---

Assessing and predicting changes of ecosystem service values in response to land use/land cover dynamics in Ibb City, Yemen: a three-decade analysis and future outlook

International Journal of Digital Earth, Journal Year: 2024, Volume and Issue: 17(1)

Published: March 11, 2024

Assessing ecosystem services values (ESV) within land use/land cover (LULC) changes is crucial for promoting human well-being and sustainable development of regional ecosystems. Yet, the spatial relationship between LULC still unclear in Yemen. This study aimed to assess impacts on ESV Ibb City, over three decades (1990–2020), predict 2050. The hybrid use classification technique classifying Landsat images, CA-Markov model prediction, benefit transfer method (BTM) assessment were employed. Our findings revealed that there was a continuous increase built-up areas barren land, with decrease cultivated grassland, which are predicted continue next 30 years. Consequently, total has decreased from US$ 68.5 × 106 1990 65.2 2020 expected further reduce 61.2 by 2050, reflecting impact urban expansion socio-economic activities ESV. provides insights future monitoring, will contribute formulation effective land-use strategies more services, particularly rapidly urbanizing data-limited regions.

Language: Английский

---

Land Use and Land Cover Classification Using River Formation Dynamics Algorithm With Deep Learning on Remote Sensing Images

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 11147 - 11156

Published: Jan. 1, 2024

Currently, remote sensing images (RSIs) are often exploited in the explanation of urban and rural areas, change recognition, other domains. As majority RSI is high-resolution contains wide varied data, proper interpretation RSIs most important. Land use land cover (LULC) classification utilizing deep learning (DL) a common efficient manner geospatial study. It very important planning, environmental monitoring, mapping, management. But, one recent approaches problems like vulnerability to noise interference, low accuracy, worse generalization ability. DL approaches, mostly Convolutional Neural Networks (CNNs) revealed impressive performance image recognition tasks, making them appropriate for LULC RSIs. Therefore, this study introduces novel Use Cover Classification employing River Formation Dynamics Algorithm with Deep Learning (LULCC-RFDADL) technique on The main objective LULCC-RFDADL methodology recognize diverse types LC In presented technique, dense EfficientNet approach applied feature extraction. Furthermore, hyperparameter tuning Dense method was implemented using RFDA technique. For process, uses Multi-Scale Autoencoder (MSCAE) model. At last, seeker optimization algorithm (SOA) has been parameter choice MSCAE system. achieved outcomes were examined benchmark databases. simulation values show better result methods terms different metrics.

Language: Английский

---

Multispectral Semantic Segmentation for Land Cover Classification: An Overview

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Journal Year: 2024, Volume and Issue: 17, P. 14295 - 14336

Published: Jan. 1, 2024

Land cover classification (LCC) is a process used to categorize the Earth's surface into distinct land types. This vital for environmental conservation, urban planning, agricultural management, and climate change research, providing essential data sustainable decision-making. The use of multispectral imaging (MSI), which captures beyond visible spectrum, has emerged as one most utilized image modalities addressing this task. Additionally, semantic segmentation techniques play role in domain, enabling precise delineation labeling classes within imagery. integration these three concepts given rise an intriguing ever-evolving research field, witnessing continuous advancements aimed at enhancing (MSSS) methods LCC. Given dynamic nature there need thorough examination latest trends understand its evolving landscape. Therefore, paper presents review current aspects field MSSS LCC, following key points: (1) prevalent datasets acquisition methods, (2) preprocessing managing MSI data, (3) typical metrics evaluation criteria assessing performance (4) methodologies employed, (5) spectral bands spectrum commonly utilized. Through analysis, our objective provide valuable insights state contributing ongoing development understanding while also perspectives future directions.

Language: Английский

---

Comparative analysis of Sentinel-2 and PlanetScope imagery for chlorophyll-a prediction using machine learning models

Ecological Informatics, Journal Year: 2024, Volume and Issue: unknown, P. 102988 - 102988

Published: Dec. 1, 2024

Language: Английский

---