Estimation of land surface temperature in agricultural lands using Sentinel 2 images: A case study for sunflower fields

Nasseri, Saeid; Bansouleh, Bahman Farhadi; Azari, Arash

doi:10.1002/ird.2802

Cited by 5 publications

(3 citation statements)

References 24 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, the spatial resolution of the thermal infrared band (TIR) used for LST retrieval is 120 m for Landsat 5 and 100 m for Landsat 8, which is relatively low in terms of spatial and temporal resolution and cannot provide detailed information on land surface temperature distribution [39]. To overcome these limitations, future research will utilize high spatiotemporal resolution sensor data from platforms such as Sentinel-2 to obtain comprehensive and detailed land surface temperature distribution [40][41][42]. Cloud detection and restoration algorithms will be employed to reduce the impact of cloud cover on images and improve the quality and usability of remote sensing data.…”

Section: Discussionmentioning

confidence: 99%

Effects of Production–Living–Ecological Space Patterns Changes on Land Surface Temperature

et al. 2023

View full text Add to dashboard Cite

Rapid economic and social development has triggered competition for limited land space from different industries, accelerating the evolution of Beijing’s urban landscape types. The increase in impermeable surfaces and the decrease in ecological land have led to an increase in the impact on the urban thermal environment. Since previous studies have mainly focused on the impact of a single urban landscape on the urban thermal environment and lacked an exploration of the combined impact of multiple landscapes, this study applied standard deviation ellipses, Pearson correlation analysis, land surface temperature (LST) profile analysis, and hot spot analysis to comprehensively explore the influence of the evolving production–living–ecological space (PLES) pattern on LST. The results show that the average LST of various spaces continued to increase before 2009 and decreased slowly after 2009, with the highest average temperature being living space, followed by production space, and the lowest average temperature being ecological space for each year. The spatiotemporal shift path of the thermal environment is consistent with the shift trajectory of the living space center of gravity in Beijing; LST is positively correlated with living space (LS) and negatively correlated with production space (PS) and ecological space (ES). LST is positively correlated with LS and negatively correlated with PS and ES. Influenced by the change in bedding surface type, the longitudinal thermal profile curve of LST shows a general trend of “low at both ends and high in the middle”. With the change in land space type, LST fluctuates significantly, and the horizontal thermal profile curve shows a general trend of “first decreasing, followed by increasing and finally decreasing”. In addition, the hot spot analysis shows that the coverage area of very hot spots, hot spots, and warm spots increased by 0.72%, 1.13%, and 2.03%, respectively, in the past 30 years, and the main expansion direction is southeast, and very cold spots and cold spots are distributed in the northwest ecological space, and the area change first decreases and then increases.

show abstract

Section: Discussionmentioning

confidence: 99%

Effects of Production–Living–Ecological Space Patterns Changes on Land Surface Temperature

et al. 2023

View full text Add to dashboard Cite

show abstract

“…This satellite was chosen for its resolution, which is close to data with the largest spatial resolution, and the availability of a thermal band to estimate Land Surface Temperature (LST). Sentinel 2, with superior spatial resolution, lacks a thermal band, making it impossible to estimate LST directly [28]. Landsat 8, with a longer historical data record, was the most suitable choice with high-dealing considerations.…”

Section: Data and Research Workflowmentioning

confidence: 99%

Identifying Potential Areas for Oil and Gas Well Location Planning Using Support Vector Machine Algorithm

Dwi Safira,

Nurwatik,

Hariyanto

2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

To fulfill national energy needs for the National Energy Grand Strategy (GSEN), it is necessary to increase the productivity of oil and gas exploration by involving technology that provides alternative solutions, cuts work time, and overcomes the risk of failure. This research aims to identify potential areas for planning new oil and gas well locations using a machine learning algorithm called Support Vector Machine (SVM). This research chooses four splitting ratios of 80:20, 75:25, 60:40, and 50:50 on training and testing data to produce four models and to identify the most robust model for Blora Regency. The algorithm involves fourteen conditioning parameters comprising altitude, slope, aspect, distance from the river network, land cover, distance from the road network, soil type, Normalized Difference Vegetation Index (NDVI), clay mineral index, iron oxide index, surface temperature, complete Bouguer anomaly (CBL), distance from the fault, and rock type. This research uses the confusion matrix and the ROC-AUC to evaluate all models and determine the best one. The result witnesses the best model is SVM 75:25 with an accuracy (Acc), sensitivity (Sen), specificity (Spe), and predictive value (PPV) of 0.8333; Matthew’s correlation coefficient and Cohen’s kappa of 0.6667; and area under the curve (AUC) of 0.9444. In addition, the conditioning parameter contributing the most significant influence on the best model is the slope equal to 100%.

show abstract

“…Orthorectified images from Sentinel-2, product 1C, were selected, covering regions with growing sugarcane plantations. Each image has dimensions of 10 m x 10 m, with UTM/WGS84 projection and pixel values on top of atmosphere (TOA) reflectance 12 .…”

Section: Resampling Of Imagesmentioning

confidence: 99%

Empowering Agribusiness with Simplicity: Web-based Artificial Intelligence Software Platform for Remote Sensing

Costa

Kai

et al. 2023

Preprint

View full text Add to dashboard Cite

Remote sensing techniques using satellite imagery are widely applied in various fields of agricultural sciences due to the ease of obtaining real-time information, enabling data acquisition from a region without the need for physical displacement, thus avoiding costs. It also allows for the exploration of more efficient methods for crop monitoring tasks. This article presents a software platform that collects images from publicly available sources on the internet, groups these images by category and geographic region, and allows for the application of different artificial intelligence algorithms for image classification. The experiments conducted achieved an accuracy of 89.54% for the Random Forest (RF) classifier. A neural network with three hidden layers and one output layer achieved an accuracy of 86.66%. It is believed that the lower performance is related to the small number of samples used for training the network. The results demonstrate the potential benefits involved in applying this platform in precision agriculture, considering the ability to acquire, organize, and apply artificial intelligence to image classification.

show abstract

Estimation of land surface temperature in agricultural lands using Sentinel 2 images: A case study for sunflower fields

Cited by 5 publications

References 24 publications

Effects of Production–Living–Ecological Space Patterns Changes on Land Surface Temperature

Effects of Production–Living–Ecological Space Patterns Changes on Land Surface Temperature

Identifying Potential Areas for Oil and Gas Well Location Planning Using Support Vector Machine Algorithm

Empowering Agribusiness with Simplicity: Web-based Artificial Intelligence Software Platform for Remote Sensing

Contact Info

Product

Resources

About