Spatial assessment of land surface temperature and land use/land cover in Langkawi Island

Bakar, Suzana Binti Abu; Pradhan, Biswajeet; Lay, Usman Salihu; Abdullahi, Saleh

doi:10.1088/1755-1315/37/1/012064

Cited by 17 publications

(13 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Spectral indices were predictor variables and temperature was the target variable, the gained outcome were R 2 =0.98-0.99 determination coefficients; however, the relationship was not obvious, they had to apply a threshold value with two curve fitting to reach this result. There are relevantly less experience with MNDWI, nevertheless it has favorable capability for water detection according to our results; studies found both NDVI and MNDWI useful indicators in environment monitoring (Liu et al 2009;Bakar et al 2016;). Xu (2007) found MNDWI (and SAVI and NDBI) effective in mapping built-up areas related to the application of NDVI and NDWI or even to the Principal Component Analysis of the original bands of a Landsat ETM+ image.…”

Section: Discussionmentioning

confidence: 66%

Specific features of NDVI, NDWI and MNDWI as reflected in land cover categories

Szabó¹,

Gácsi²,

Balázs³

2016

Landsc. environ.

115

View full text Add to dashboard Cite

The remote sensing techniques provide a great possibility to analyze the environmental processes in local or global scale. Landsat images with their 30 m resolution are suitable among others for land cover mapping and change monitoring. In this study three spectral indices (NDVI, NDWI, MNDWI) were investigated from the aspect of land cover types: water body (W); plough land (PL); forest (F); vineyard (V); grassland (GL) and built-up areas (BU) using Landsat-7 ETM+ data. The range, the dissimilarities and the correlation of spectral indices were examined. In BU -GL -F categories similar NDVI values were calculated, but the other land cover types differed significantly. The water related indices (NDWI, MNDWI) were more effective (especially the MNDWI) to enhance water features, but the values of other categories ranged from narrower interval. Weak correlation were found among the indices due to the differences caused by the water land cover class. Statistically, most land cover types differed from each other, but in several cases similarities can be found when delineating vegetation with various water content. MNDWI was found as the most effective in highlighting water bodies.

show abstract

Section: Discussionmentioning

confidence: 66%

Specific features of NDVI, NDWI and MNDWI as reflected in land cover categories

Szabó¹,

Gácsi²,

Balázs³

2016

Landsc. environ.

115

View full text Add to dashboard Cite

show abstract

“…Nhiều nghiên cứu trên thế giới và Việt Nam đã sử dụng dữ liệu ảnh viễn thám hồng ngoại nhiệt độ phân giải trung bình như Landsat, Aster trong đánh giá diễn biến nhiệt độ bề mặt ở các đô thị lớn, từ đó chứng minh sự tồn tại của các "đảo nhiệt" đô thị -urban heat islands. Có thể kể đêń cać nghiên cứu của Alipour et al (2004) [1], Balling and Brazel (1988) [2], Cueto et al (2007) [3], Hyung Moo Kim et al (2005) [4], Kumar (2012) [5], Maltick et al (2008) [6], Trịnh Lê Hùng (2014) [7], Yuan et al (2007) [8],…Nhiều nghiên cứu như của Anadababu et al (2018) [9], Bakar et al (2016) [10], Boori et al (2014) [11], Guha et al (2018) [12], Pal and Ziaul (2017) [13], Bùi Quang Thành (2015) [14], Nguyễn Đức Thuận và Phạm Văn Vân (2016) [15], Trần Thị Vân và cộng sự (2009) [16]…đã chứng minh mối quan hệ chặt chẽ giữa nhiệt độ và lớp phủ, trong đó các khu vực có mật độ xây dựng cao và lớp phủ thực vật thưa có nhiệt độ cao hơn rất nhiều so với các khu vực được che phủ bởi lớp phủ thực vật dày.…”

Section: Mở đầU unclassified

Kết Hợp Ảnh Vệ Tinh Landsat 8 Và Sentinel 2 Trong Nâng Cao Độ Phân Giải Nhiệt Độ Bề Mặt

Le¹

2018

EES

View full text Add to dashboard Cite

Tóm tắt: Nhiệt độ bề mặt là một trong những yếu tố quan trọng nhất trong nghiên cứu hiện tượng đảo nhiệt đô thị, giám sát cháy rừng, cháy mỏ than cũng như là thông số đầu vào cho các mô hình khí hậu. Các quan trắc mặt đất chỉ phản ańh điều kiện nhiệt của khu vực cục bộ xung quanh trạm đo và trên thực tế cuñg không thể thiết lập nhiều trạm quan trắc với mâ ̣t đô ̣ daỳ do chí phí cao. Công nghê ̣ viêñ thaḿ với nhưñg ưu điêm vươ ̣t trô ̣i như diê ̣n tićh vùng phủ của mô ̣t anh rô ̣ng, chu kỳ cập nhật ngắn đã đươ ̣c ứng du ̣ng hiê ̣u quả trong nghiên cứu sự phân bố nhiê ̣t đô ̣ bề mă ̣t. Mặc dù vậy, do độ phân giải không gian ở các kênh hồng ngoại nhiệt thấp, nhiệt độ bề mặt xác định từ các ảnh vệ tinh như Landsat, Aster thường khó áp dụng hiệu quả cho các nghiên cứu ở quy mô nhỏ. Bài báo này trình bày kết quả kết hợp ảnh vệ tinh Landsat 8 và Sentinel 2 trong nâng cao độ phân giải không gian nhiệt độ bề mặt. Kết quả nhận được cho thấy, trong trường hợp kết hợp sử dụng ảnh vệ tinh Sentinel 2 và Landsat 8, độ phân giải không gian của nhiệt độ bề mặt được nâng cao lên 10 m so với 30 m khi chỉ sử dụng ảnh Landsat 8. Đối với 2 khu vực thử nghiệm, so sánh giá trị nhiệt độ thấp nhất và cao nhất cũng như tại 10 điểm kiểm tra ngẫu nhiên cho thấy, độ chênh lệch nhiệt độ bề mặt khi kết hợp ảnh Landsat 8 và Sentinel 2 so với phương pháp truyền thống chỉ sử dụng ảnh Landsat 8 là không đáng kể.Từ khóa: Viêñ thaḿ, nhiê ̣t đô ̣ bề mă ̣t, đô ̣ phân giaỉ, Landsat 8, Sentinel 2. Abstract:Land surface temperature is one of the most important factors in studying urban heat island, monitoring forest fire and coal fire as well as input parameters for climate models. Groundbased observations reflect only thermal condition of local area around the stations and in fact cannot establish the number of meteorological stations with expected density due to the high cost.Remote sensing technology with advantages such as wide area coverage and short revisiting interval has been used effectively in the study of land surface temperature distribution. However, due to the spatial resolution of thermal infrared band is low, land surface temperature calculated from satellite images, such as Landsat and Aster is not applicable to small-scales area effectively. This paper presents the results of a study of combining multi-resolution remote sensing data, including Landsat 8 and Sentiel 2A satellite imagery, to enhance the spatial resolution of land surface temperature. The results show that, in the case of combining Sentinel 2 and Landsat 8 images, the spatial resolution of land surface temperature is increased to 10m, compared to 30m in the case of using only Landsat 8 data. For the two experimental areas, comparison of the lowest and highest land surface temperature as well as the 10 random test points showed that, the difference between land surface temperatures in the case of combining Landsat 8 and Sentinel 2 and in the case of using only Landsat 8 images are negligible.

show abstract

“…Rana and Suryanarayana [ 14 ] analyzed the contribution of various LULC types on LST by comparing four machine learning models (K-Nearest Neighbor, Artificial Neural Network, Random Tree, and Support Vector Machine). Bakar et al [ 15 ] used a support vector machine and maximum likelihood method to investigate the relationship between LST and LULC. Gage and Cooper [ 16 ] evaluated the relative importance of LULC, NDVI, and vertical structure for LST patterns through random forest modeling.…”

Section: Introductionmentioning

confidence: 99%

Examining the Relationship between Land Use/Land Cover (LULC) and Land Surface Temperature (LST) Using Explainable Artificial Intelligence (XAI) Models: A Case Study of Seoul, South Korea

Kim

Kim²,

Kim

2022

IJERPH

View full text Add to dashboard Cite

Understanding the relationship between land use/land cover (LULC) and land surface temperature (LST) has long been an area of interest in urban and environmental study fields. To examine this, existing studies have utilized both white-box and black-box approaches, including regression, decision tree, and artificial intelligence models. To overcome the limitations of previous models, this study adopted the explainable artificial intelligence (XAI) approach in examining the relationships between LULC and LST. By integrating the XGBoost and SHAP model, we developed the LST prediction model in Seoul and estimated the LST reduction effects after specific LULC changes. Results showed that the prediction accuracy of LST was maximized when landscape, topographic, and LULC features within a 150 m buffer radius were adopted as independent variables. Specifically, the existence of surrounding built-up and vegetation areas were found to be the most influencing factors in explaining LST. In this study, after the LULC changes from expressway to green areas, approximately 1.5 °C of decreasing LST was predicted. The findings of our study can be utilized for assessing and monitoring the thermal environmental impact of urban planning and projects. Also, this study can contribute to determining the priorities of different policy measures for improving the thermal environment.

show abstract

Spatial assessment of land surface temperature and land use/land cover in Langkawi Island

Cited by 17 publications

References 22 publications

Specific features of NDVI, NDWI and MNDWI as reflected in land cover categories

Specific features of NDVI, NDWI and MNDWI as reflected in land cover categories

Kết Hợp Ảnh Vệ Tinh Landsat 8 Và Sentinel 2 Trong Nâng Cao Độ Phân Giải Nhiệt Độ Bề Mặt

Examining the Relationship between Land Use/Land Cover (LULC) and Land Surface Temperature (LST) Using Explainable Artificial Intelligence (XAI) Models: A Case Study of Seoul, South Korea

Contact Info

Product

Resources

About