scholarly journals Neural Network and Multiple Linear Regression for Estimating Surface Albedo from ASTER Visible and Near-Infrared Spectral Bands

2013 ◽  
Vol 17 (3) ◽  
pp. 1-20 ◽  
Author(s):  
Mohammad H. Mokhtari ◽  
Ibrahim Busu ◽  
Hossein Mokhtari ◽  
Gholamreza Zahedi ◽  
Leila Sheikhattar ◽  
...  
Keyword(s):  
Linear Regression ◽  
Multiple Linear Regression ◽  
Surface Albedo ◽  
Near Infrared ◽  
Thermal Emission ◽  
Current Model ◽  
Primary Analysis ◽  
Aster Data ◽  
Spectral Bands ◽  
Shortwave Infrared

Abstract The current Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER)-based broadband albedo model requires shortwave infrared bands 5 (2.145–2.185 nm), 6 (2.185–2.225 nm), 8 (2.295–2.365 nm), and 9 (2.360–2.430 nm) and visible/near-infrared bands 1 (0.52–0.60 nm) and 3 (0.78–0.86 nm). However, because of sensor irregularities at high temperatures, shortwave infrared wavelengths are not recorded in the ASTER data acquired after April 2008. Therefore, this study seeks to evaluate the performance of artificial neural networks (ANN) in estimating surface albedo using visible/near-infrared bands available in the data obtained after April 2008. It also compares the outcomes with the results of multiple linear regression (MLR) modeling. First, the most influential spectral bands used in the current model as well as band 2 (0.63–0.69 nm) (which is also available after April 2008 in the visible/near-infrared part) were determined by a primary analysis of the data acquired before April 2008. Then, multiple linear regression and ANN models were developed by using bands with a relatively high level of contribution. The results showed that bands 1 and 3 were the most important spectral ones for estimating albedo where land cover consisted of soil and vegetation. These two bands were used as the study input, and the albedo (estimated through a model that utilized bands 1, 3, 5, 6, 8, and 9) served as a target to remodel albedo. Because of its high collinearity with band 1, band 2 was identified less effectively by MLR as well as ANN. The study confirmed that a combination of bands 1 and 3, which are available in the current ASTER data, could be modeled through ANN and MLR to estimate surface albedo. However, because of its higher accuracy, ANN method was superior to MLR in developing objective functions.

scholarly journals Implementation of the NHI (Normalized Hot Spot Indices) Algorithm on Infrared ASTER Data: Results and Future Perspectives

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1538
Author(s):  
Giuseppe Mazzeo ◽  
Micheal S. Ramsey ◽  
Francesco Marchese ◽  
Nicola Genzano ◽  
Nicola Pergola
Keyword(s):  
Near Infrared ◽  
Thermal Emission ◽  
Hot Spot ◽  
Thermal Anomaly ◽  
Google Earth ◽  
Thematic Mapper ◽  
Landsat 8 ◽  
Thermal Anomalies ◽  
Aster Data ◽  
Shortwave Infrared

The Normalized Hotspot Indices (NHI) tool is a Google Earth Engine (GEE)-App developed to investigate and map worldwide volcanic thermal anomalies in daylight conditions, using shortwave infrared (SWIR) and near infrared (NIR) data from the Multispectral Instrument (MSI) and the Operational Land Imager (OLI), respectively, onboard the Sentinel 2 and Landsat 8 satellites. The NHI tool offers the possibility of ingesting data from other sensors. In this direction, we tested the NHI algorithm for the first time on Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) data. In this study, we show the results of this preliminary implementation, achieved investigating the Kilauea (Hawaii, USA), Klyuchevskoy (Kamchatka; Russia), Shishaldin (Alaska; USA), and Telica (Nicaragua) thermal activities of March 2000–2008. We assessed the NHI detections through comparison with the ASTER Volcano Archive (AVA), the manual inspection of satellite imagery, and the information from volcanological reports. Results show that NHI integrated the AVA observations, with a percentage of unique thermal anomaly detections ranging between 8.8% (at Kilauea) and 100% (at Shishaldin). These results demonstrate the successful NHI exportability to ASTER data acquired before the failure of SWIR subsystem. The full ingestion of the ASTER data collection, available in GEE, within the NHI tool allows us to develop a suite of multi-platform satellite observations, including thermal anomaly products from Landsat Thematic Mapper (TM) and Enhanced Thematic Mapper Plus (ETM+), which could support the investigation of active volcanoes from space, complementing information from other systems.

scholarly journals Mapping the Lithological Features and Ore-Controlling Structures Related to Ni–Cu Mineralization in the Eastern Tian Shan, NW China from ASTER Data

2021 ◽  
Vol 13 (2) ◽  
pp. 206
Author(s):  
Shuo Zheng ◽  
Yanfei An ◽  
Pilong Shi ◽  
Tian Zhao
Keyword(s):  
Near Infrared ◽  
Thermal Emission ◽  
Strike Slip ◽  
Fault System ◽  
Multispectral Data ◽  
Aster Data ◽  
Ore Bodies ◽  
Dextral Strike Slip Fault ◽  
Shortwave Infrared ◽  
Tian Shan

The study of lithological features and tectonic evolution related to mineralization in the eastern Tian Shan is crucial for understanding the ore-controlling mechanism. In this paper, the lithological features and ore-controlling structure of the Huangshan Ni–Cu ore belt in the eastern Tian Shan are documented using advanced spaceborne thermal emission and reflection radiometer (ASTER) multispectral data based on spectral image processing algorithms, mineral indices and directional filter technology. Our results show that the algorithms of b2/b1, b6/b7 and b4/b8 from ASTER visible and near-infrared (VNIR)- shortwave infrared (SWIR) bands and of mafic index (MI), carbonate index (CI) and silica index (SI) from thermal infrared (TIR) bands are helpful to extract regional pyroxenite, external foliated gabbro bearing Ni–Cu ore bodies as well as the country rocks in the study area. The detailed interpretations and analyses of the geometrical feature of fault system and intrusive facies suggest that the Ni–Cu metallogenic belts are related to Carboniferous arc intrusive rocks and Permian wrench tectonics locating at the intersection of EW- and NEE-striking dextral strike-slip fault system, and the emplacement at the releasing bends in the southern margin of Kanggur Fault obviously controlled by secondary faults orthogonal or oblique to the Kanggur Fault in the post-collision extensional environment. Therefore, the ASTER data-based approach to map lithological features and ore-controlling structures related to the Ni–Cu mineralization are well performed. Moreover, a 3D geodynamic sketch map proposes that the strike-slip movement of Kanggur Fault in Huangshan-Kanggur Shear Zone (HKSZ) during early Permian controlled the migration and emplacement of three mafic/ultramafic intrusions bearing Ni–Cu derived from partial mantle melting and also favored CO2-rich fluids leaking to the participation of metallogenic processes.

Prediction of water content in biscuits using near infrared hyperspectral imaging spectroscopy and chemometrics

2020 ◽  
Vol 28 (3) ◽  
pp. 140-147
Author(s):  
Eloïse Lancelot ◽  
Philippe Courcoux ◽  
Sylvie Chevallier ◽  
Alain Le-Bail ◽  
Benoît Jaillais
Keyword(s):  
Linear Regression ◽  
Multiple Linear Regression ◽  
Water Content ◽  
Hyperspectral Imaging ◽  
Analysis Of Variance ◽  
Near Infrared ◽  
Imaging Spectroscopy ◽  
Principal Component ◽  
Coefficient Of Determination ◽  
Water Contents

The possibility of using near infrared hyperspectral imaging spectroscopy to quantify the water content in commercial biscuits was investigated. Principal component analysis was successfully applied to hyperspectral images of commercial biscuits to monitor their water contents. Variables were selected and water contents quantified using analysis of variance, followed by multiple linear regression, and the results were compared with those obtained with variable importance in projection partial least squares. Initially equal to 212, the number of variables after application of analysis of variance was equal to 10. Analysis of variance–multiple linear regression gave better results: the coefficient of determination (R2) was higher than 0.92 and the root mean square error of validation was less than 0.015. The “prediction images” obtained were very relevant and can be used to study biscuit defects. The methodology developed could be implemented at the industrial level for biscuit quality control and for online monitoring of the uniform distribution of water in the superficial layer of biscuits.

Modeling Wood Crystallinity with Multiple Linear Regression

2011 ◽  
Vol 480-481 ◽  
pp. 550-555
Author(s):  
Yao Xiang Li ◽  
Li Chun Jiang
Keyword(s):  
Infrared Spectroscopy ◽  
Linear Regression ◽  
Multiple Linear Regression ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Model Development ◽  
Model Performance ◽  
Chemical Properties ◽  
Nondestructive Method ◽  
And Chemical Properties

The crystallinity of wood has an important effect on the physical, mechanical and chemical properties of cellulose fibers. Crystallinity of larch plantation wood was investigated with near infrared spectroscopy and multiple linear regression. Five typical wave lengths were selected to establish prediction model for wood crystallinity. Full-cross validation was applied to the model development. The model performance is satisfied with prediction correlation coefficient of 0.896 and bias of 0.0004. The results indicated that prediction of wood crystallinity with near infrared spectroscopy and multiple linear regression is feasible, which provides a fast and nondestructive method for wood crystallinity prediction.

Quantile BEAST Attacks the False-Sample Problem in Near-Infrared Reflectance Analysis

1988 ◽  
Vol 42 (8) ◽  
pp. 1351-1365 ◽  
Author(s):  
Robert A. Lodder ◽  
Gary M. Hieftje
Keyword(s):  
Linear Regression ◽  
Multiple Linear Regression ◽  
Near Infrared ◽  
Infrared Reflectance ◽  
Sample Problem ◽  
Training Set ◽  
Near Infrared Reflectance ◽  
Regression Approach ◽  
Reflectance Analysis ◽  
Sample Technique

The multiple linear regression approach typically used in near-infrared calibration yields equations in which any amount of reflectance at the analytical wavelengths leads to a corresponding composition value. As a result, when the sample contains a component not present in the training set, erroneous composition values can arise without any indication of error. The Quantile BEAST (Bootstrap Error-Adjusted Single-sample Technique) is described here as a method of detecting one or more “false” samples. The BEAST constructs a multidimensional form in space using the reflectance values of each training-set sample at a number of wavelengths. New samples are then projected into this space, and a confidence test is executed to determine whether the new sample is part of the training-set form. The method is more robust than other procedures because it relies on few assumptions about the structure of the data; therefore, deviations from assumptions do not affect the results of the confidence test.

VNIR-SWIR Superspectral Mineral Mapping: An Example from Cuprite, Nevada

2020 ◽  
Vol 86 (11) ◽  
pp. 695-700
Author(s):  
Kathleen E. Johnson ◽  
Krzysztof Koperski
Keyword(s):  
Near Infrared ◽  
Thermal Emission ◽  
High Spatial Resolution ◽  
Ground Truth ◽  
Random Forest Classifier ◽  
Hyperspectral Data ◽  
United States Geological Survey ◽  
Mineral Mapping ◽  
Mapping Techniques ◽  
Shortwave Infrared

Cuprite, Nevada, is a location well known for numerous studies of its hydrothermal mineralogy. This region has been used to validate geological interpretations of airborne hyperspectral imagery (AVIRIS HSI ), Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER ) imagery, and most recently eight-band WorldView-3 shortwave infrared (SWIR ) imagery. WorldView-3 is a high-spatial-resolution commercial multispectral satellite sensor with eight visible-to-near-infrared (VNIR ) bands (0.42–1.04 μm) and eight SWIR bands (1.2–2.33 μm). We have applied mineral mapping techniques to all 16 bands to perform a geological analysis of the Cuprite, Nevada, location. Ground truth for the training and validation was derived from AVIRIS hyperspectral data and United States Geological Survey mineral spectral data for this location. We present the results of a supervised mineral-mapping classification applying a random-forest classifier. Our results show that with good ground truth, WorldView-3 SWIR + VNIR imagery produces an accurate geological assessment.

scholarly journals Performance Evaluation of Newly Proposed Seaweed Enhancing Index (SEI)

2019 ◽  
Vol 11 (12) ◽  
pp. 1434 ◽  
Author(s):  
Muhammad Danish Siddiqui ◽  
Arjumand Z. Zaidi ◽  
Muhammad Abdullah
Keyword(s):  
Vegetation Index ◽  
Near Infrared ◽  
Normalized Difference Vegetation Index ◽  
Landsat 8 ◽  
Spectral Bands ◽  
Extensive Field ◽  
Reference Index ◽  
Almost All ◽  
Shortwave Infrared ◽  
Better Than

Seaweed is a valuable coastal resource for its use in food, cosmetics, and other items. This study proposed new remote sensing based seaweed enhancing index (SEI) using spectral bands of near-infrared (NIR) and shortwave-infrared (SWIR) of Landsat 8 satellite data. Nine Landsat 8 satellite images of years 2014, 2016, and 2018 for the January, February, and March months were utilized to test the performance of SEI. The seaweed patches in the coastal waters of Karachi, Pakistan were mapped using the SEI, normalized difference vegetation index (NDVI), and floating algae index (FAI). Seaweed locations recorded during a field survey on February 26, 2014, were used to determine threshold values for all three indices. The accuracy of SEI was compared with NDVI while placing FAI as the reference index. The accuracy of NDVI and SEI were assessed by matching their spatial extent of seaweed cover with FAI enhanced seaweed area. SEI images of January 2016, February 2018, and March 2018 enhanced less than 50 percent of the corresponding FAI total seaweed areas. However, on these dates the NDVI performed very well, matching more than 95 percent of FAI seaweed coverage. Except for these three times, the performance of SEI in the remaining six images was either similar to NDVI or even better than NDVI. SEI enhanced 99 percent of FAI seaweed cover on January 2018 image. Overall, seaweed area not covered by FAI was greater in SEI than NDVI in almost all images, which needs to be further explored in future studies by collecting extensive field information to validate SEI mapped additional area beyond the extent of FAI seaweed cover. Based on these results, in the majority of the satellite temporal images selected for this study, the performance of the newly proposed index—SEI, was found either better than or similar to NDVI.

Sign in / Sign up

Export Citation Format

Share Document