Relation of land surface temperature with different vegetation indices using multi-temporal remote sensing data in Sahiwal region, Pakistan

Geoscience Letters, Journal Year: 2023, Volume and Issue: 10(1)

Published: July 26, 2023

Abstract At the global and regional scales, green vegetation cover has ability to affect climate land surface fluxes. Climate is an important factor which plays role in cover. This research aimed study changes relation of different indices with temperature using multi-temporal satellite data Sahiwal region, Pakistan. Supervised classification method (maximum likelihood algorithm) was used achieve based on ground-truthing. Our denoted that during last 24 years, almost 24,773.1 ha (2.43%) area been converted roads built-up areas. The increased coverage from 43,255.54 (4.24%) 1998 2022 area. Average (LST) values were calculated at 16.6 °C 35.15 for winter summer season, respectively. In average RVI, DVI, TVI, EVI, NDVI SAVI noted as 0.19, 0.21, 0.26, 0.28, 0.30 0.25 For LST relation, statistical linear regression analysis indicated kappa coefficient R 2 = 0.79 0.75 0.78 0.81 0.83 0.80 related LST. remote sensing (RS) technology can be monitor over time, providing valuable information sustainable use management. Even though findings provide significant references reasoned optimal resources through policy implications.

Language: Английский

---

Application of Deep Learning on UAV-Based Aerial Images for Flood Detection

Smart Cities, Journal Year: 2021, Volume and Issue: 4(3), P. 1220 - 1242

Published: Sept. 18, 2021

Floods are one of the most fatal and devastating disasters, instigating an immense loss human lives damage to property, infrastructure, agricultural lands. To cater this, there is a need develop implement real-time flood management systems that could instantly detect flooded regions initiate relief activities as early possible. Current imaging systems, relying on satellites, have demonstrated low accuracy delayed response, making them unreliable impractical be used in emergency responses natural disasters such flooding. This research employs Unmanned Aerial Vehicles (UAVs) automated system can identify inundated areas from aerial images. The Haar cascade classifier was explored case study landmarks roads buildings images captured by UAVs areas. extracted added training dataset train deep learning algorithm. Experimental results show detected with 91% 94% accuracy, respectively. overall recorded classifying non-flooded input has shown promising test belonging both pre- post-flood classes. rescue workers quickly locate stranded people using this system. Such inundation will help transform disaster line modern smart cities initiatives.

Language: Английский

---

Assessment of land use/land cover changes and its effect on land surface temperature using remote sensing techniques in Southern Punjab, Pakistan

Environmental Science and Pollution Research, Journal Year: 2022, Volume and Issue: 30(44), P. 99202 - 99218

Published: June 29, 2022

Language: Английский

---

Automatic Target Detection from Satellite Imagery Using Machine Learning

Sensors, Journal Year: 2022, Volume and Issue: 22(3), P. 1147 - 1147

Published: Feb. 2, 2022

Object detection is a vital step in satellite imagery-based computer vision applications such as precision agriculture, urban planning and defense applications. In imagery, object very complicated task due to various reasons including low pixel resolution of objects small the large scale (a single image taken by Digital Globe comprises over 240 million pixels) images. images has many challenges class variations, multiple pose, high variance size, illumination dense background. This study aims compare performance existing deep learning algorithms for imagery. We created dataset imagery perform using convolutional neural network-based frameworks faster RCNN (faster region-based network), YOLO (you only look once), SSD (single-shot detector) SIMRDWN (satellite multiscale rapid with windowed networks). addition that, we also performed an analysis these approaches terms accuracy speed developed The results showed that 97% on high-resolution images, while Faster 95.31% standard (1000 × 600). YOLOv3 94.20% (416 416) other hand 84.61% (300 300). When it comes efficiency, obvious leader. real-time surveillance, fails. takes 170 190 milliseconds task, 5 103 milliseconds.

Language: Английский

---

Examining the relationship between land surface temperature and landscape features using spectral indices with Google Earth Engine

Heliyon, Journal Year: 2022, Volume and Issue: 8(9), P. e10668 - e10668

Published: Sept. 1, 2022

Land surface temperature (LST) is strongly influenced by landscape features as they change the thermal characteristics of greatly. Normalized Difference Vegetation Index (NDVI), Water (NDWI), Built-up (NDBI), and Bareness (NDBAI) correspond to vegetation cover, water bodies, impervious build-ups, bare lands, respectively. These indices were utilized demonstrate relationship between multiple LST using spectral derived from images Landsat 5 Thematic Mapper (TM), 8 Operational Imager (OLI) Sylhet Sadar Upazila (2000-2018). Google Earth Engine (GEE) cloud computing platform was used filter, process, analyze trends with logistic regression. other calculated. Changes in (2000-2018) range -6 °C +4 study area. Because higher cover reserve forest, north-eastern part region had greatest variations LST. The corresponding have a considerable explanatory capacity for describing scenarios. correlation these ranges -0.52 (NDBI) +0.57 (NDVI).

Language: Английский

---

Identifying and Ranking Landfill Sites for Municipal Solid Waste Management: An Integrated Remote Sensing and GIS Approach

Buildings, Journal Year: 2022, Volume and Issue: 12(5), P. 605 - 605

Published: May 6, 2022

Disposal of municipal solid waste (MSW) is one the significant global issues that more evident in developing nations. One key methods for disposing MSW locating, assessing, and planning landfill sites. Faisalabad largest industrial cities Pakistan. It has many sustainability challenges problems, including management. This study uses as a case area humbly attempts to provide framework identifying ranking sites addressing concerns Faisalabad. method can be extended applied similar cities. The were identified using remote sensing (RS) geographic information system (GIS). Multiple datasets, normalized difference vegetation, water, built-up areas indices (NDVI, NDWI, NDBI) physical factors water bodies, roads, population influence site selection used identify, rank, select most suitable site. target was distributed into 9 Thiessen polygons ranked based on their favorability development expansion 70% favorable expanding sites, whereas 30% deemed unsuitable. Polygon 6, having smaller population, declared best region per rank mean standard deviation (SD) RS vector data. current provides reliable integrated mechanism GIS implemented expanded other countries. Accordingly, urban city management improved, managed with dexterity.

Language: Английский

---

Exploring the relationship between air temperature and urban morphology factors using machine learning under local climate zones

Case Studies in Thermal Engineering, Journal Year: 2024, Volume and Issue: 55, P. 104151 - 104151

Published: Feb. 19, 2024

Urban microclimate faces serious challenges due to increased urbanization and frequent heatwave events. Many studies focused on investigating the holistic quantitative relationships between urban morphology factors heat island intensity at city scale, but less effort has been devoted exploring a block scale. Additionally, there is lack of fast prediction methods for local climate zones (LCZ) planning design. To address these challenges, this study proposes Long Short-Term Memory Networks (LSTM) model predict effects air temperature under zones. The spatial features were characterized quantified employing post-interpretation method. Pearl River New Town (PRNT), downtown area Guangzhou, China, was considered as research implementation. results showed that accuracy best when using historical three-time step data, with R2 0.975. LCZ A highest accuracy, an 0.990. 5 lowest 0.881. Moreover, effect found be greater than land cover type. In regard, sky view factor (SVF) impact, followed by aspect ratio (AR) pervious surface fraction (PSF). Nevertheless, warming in built type stronger cover. During period, maximum minimum changes recorded 4 A, respectively, values 9.7 °C 8.6 °C. It shown low-rise areas are more resilient high-rise during periods. This because generally exhibit smaller increase temperature. These findings provide better understanding relationship form, method rapidly predicting neighborhood block. provides guidance support, great significance climate-friendly planning.

Language: Английский

---

Urban heat island effect and its drivers in large cities of Pakistan

Theoretical and Applied Climatology, Journal Year: 2024, Volume and Issue: 155(6), P. 5433 - 5452

Published: April 8, 2024

Language: Английский

---

Prediction of land surface temperature using spectral indices, air pollutants, and urbanization parameters for Hyderabad city of India using six machine learning approaches

Remote Sensing Applications Society and Environment, Journal Year: 2024, Volume and Issue: 35, P. 101265 - 101265

Published: June 2, 2024

Language: Английский

---

Investigation of changes in land use/land cover using principal component analysis and supervised classification from operational land imager satellite data: a case study of under developed regions, Pakistan

Discover Sustainability, Journal Year: 2024, Volume and Issue: 5(1)

Published: April 22, 2024

Abstract Monitoring and understanding Land Use/Land Cover (LU/LC) is critical for sustainable development, as it can impact various environmental, social, economic systems. For example, deforestation land degradation lead to soil erosion, loss of biodiversity, greenhouse gas emissions, affecting the quality soil, air, water resources. The present research examined changes in within underdeveloped regions Balochistan Sindh provinces, which are situated Pakistan. In order monitor temporal variations LU/LC, we employed Geographic Information System (GIS) technique, conduct an analysis satellite imagery obtained from Landsat 8 Operational Imager (OLI) during time period spanning 2013 2023. obtain accurate LU/LC classification, used principal component (PCA) a supervised classification approach using maximum likelihood algorithm (MLC). According results our study, there was decrease extent bodies (− 593.24 km 2 ) vegetation 68.50 by − 3.43% 0.40% respectively. contrast, area occupied settlements investigated region had 2.23% rise, reaching total 385.66 square kilometers. Similarly, barren also expanded 1.60%, encompassing 276.04 kilometers, course last decade. overall accuracy (94.25% 95.75%) K value (91.75% 93.50%) were achieved year 2023 enhancement agricultural output Pakistan utmost importance improve income farmers, mitigate food scarcity, stimulate growth, facilitate expansion exports. To enhance productivity, recommended that government undertake targeted initiatives aimed at enhancing infrastructure optimizing use foster ecological framework. Integrating framework provides foundation informed decision-making effective resource management. By identifying areas urban expansion, intensification, or alterations natural stakeholders design conservation strategies, mitigating potential environmental promoting biodiversity conservation. conclusion, integration GIS Remote Sensing (RS) may effectively monitoring patterns over time. This combined offers valuable insights recommendations judicious optimal management resources, well informing policy decisions.

Language: Английский

---