scholarly journals A Soft Computing Approach for Selecting and Combining Spectral Bands

2020 ◽  
Vol 12 (14) ◽  
pp. 2267
Author(s):  
Juan F. H. Albarracín ◽  
Rafael S. Oliveira ◽  
Marina Hirota ◽  
Jefersson A. dos Santos ◽  
Ricardo da S. Torres
Keyword(s):  
Remote Sensing ◽  
Soft Computing ◽  
Optimization Problems ◽  
Multispectral Images ◽  
Spectral Indices ◽  
Vegetation Types ◽  
Classification Problems ◽  
Spectral Bands ◽  
Classification Tasks ◽  
Computing Approach

We introduce a soft computing approach for automatically selecting and combining indices from remote sensing multispectral images that can be used for classification tasks. The proposed approach is based on a Genetic-Programming (GP) framework, a technique successfully used in a wide variety of optimization problems. Through GP, it is possible to learn indices that maximize the separability of samples from two different classes. Once the indices specialized for all the pairs of classes are obtained, they are used in pixelwise classification tasks. We used the GP-based solution to evaluate complex classification problems, such as those that are related to the discrimination of vegetation types within and between tropical biomes. Using time series defined in terms of the learned spectral indices, we show that the GP framework leads to superior results than other indices that are used to discriminate and classify tropical biomes.

scholarly journals ENHANCED CLASSIFICATION MODEL FOR MULTISPECTRAL OBSERVATIONS FROM THE EARTH

2018 ◽  
Vol IV-4 ◽  
pp. 221-226
Author(s):  
I. E. Villalon-Turrubiates ◽  
M. J. Llovera-Torres
Keyword(s):  
Remote Sensing ◽  
Decision Model ◽  
Accurate Result ◽  
Classification Model ◽  
Multispectral Images ◽  
Performance Study ◽  
Spectral Bands ◽  
The Earth ◽  
Multispectral Remote Sensing ◽  
Decision Making Rule

<p><strong>Abstract.</strong> The image classification procedure to identify remote sensing signatures from a particular geographical region can be performed with an identification model that has the ability to use large datasets to reach an accurate result. This novel methodology is referred to as the Statistical Enhanced Classification algorithm, which has been developed to employ multispectral images based in the statistical supervised learning theory and can be used for applications in environmental monitoring and analysis. This paper presents the performance study of the proposed methodology using both, multispectral synthetic images and multispectral remote sensing images. The obtained results are accurate due to the use of several spectral bands, the use of statistics such as mean and standard deviation for the training classes and for the pixel neighborhood, which provides more robust information, and the decision-making rule that has the ability to decide if the pixel is not belonging to a predefined class, which leads to an accurate decision model.</p>

Review of Spectral Indices for Urban Remote Sensing

2021 ◽  
Vol 87 (7) ◽  
pp. 513-524
Author(s):  
Akib Javed ◽  
Qimin Cheng ◽  
Hao Peng ◽  
Orhan Altan ◽  
Yan Li ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Relevant Literature ◽  
Urban Land Use ◽  
Land Use Land Cover ◽  
Spectral Indices ◽  
Urban Dynamics ◽  
Spectral Bands ◽  
Search Terms ◽  
Nighttime Lights ◽  
Urban Remote Sensing

Urban spectral indices have made promising improvements in the last two decades in urban land use land cover studies through mapping, estimation, change detection, time-series analyzing, urban dynamics, monitoring, modeling, and so on. Remote sensing spectral indices are unsupervised, unbiased, rapid, scalable, and quantitative in information extraction. Hence, we aimed to summarize the most relevant urban spectral indices by focusing on multispectral, thermal, and nighttime lights indices. We use the search terms "urban index", "built-up index", "normalized difference built-up area (NDBI )", "impervious surface index", and "spectral urban index" to collect relevant literature from the "Web of Science Core Collection" database. We found that all urban spectral indices developed since 2003, except NDBI. This review will help understand the applications of urban spectral indices, the selection of indices based on available spectral bands, and their merits and demerits.

SOFT COMPUTING APPROACH TO DETECT FAULT IN INDUCTION MOTOR

2018 ◽  
Vol 12 (2) ◽  
pp. 6
Author(s):  
SEKHAR PUHAN PRATAP ◽  
BEHERA SUDARSAN ◽  
◽  
Keyword(s):  
Induction Motor ◽  
Soft Computing ◽  
Computing Approach

scholarly journals Monitoring the Foliar Nutrients Status of Mango Using Spectroscopy-Based Spectral Indices and PLSR-Combined Machine Learning Models

2021 ◽  
Vol 13 (4) ◽  
pp. 641
Author(s):  
Gopal Ramdas Mahajan ◽  
Bappa Das ◽  
Dayesh Murgaokar ◽  
Ittai Herrmann ◽  
Katja Berger ◽  
...  
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Regression ◽  
Support Vector ◽  
Spectral Indices ◽  
Learning Models ◽  
Leaf Nutrients ◽  
Machine Learning Models

Conventional methods of plant nutrient estimation for nutrient management need a huge number of leaf or tissue samples and extensive chemical analysis, which is time-consuming and expensive. Remote sensing is a viable tool to estimate the plant’s nutritional status to determine the appropriate amounts of fertilizer inputs. The aim of the study was to use remote sensing to characterize the foliar nutrient status of mango through the development of spectral indices, multivariate analysis, chemometrics, and machine learning modeling of the spectral data. A spectral database within the 350–1050 nm wavelength range of the leaf samples and leaf nutrients were analyzed for the development of spectral indices and multivariate model development. The normalized difference and ratio spectral indices and multivariate models–partial least square regression (PLSR), principal component regression, and support vector regression (SVR) were ineffective in predicting any of the leaf nutrients. An approach of using PLSR-combined machine learning models was found to be the best to predict most of the nutrients. Based on the independent validation performance and summed ranks, the best performing models were cubist (R2 ≥ 0.91, the ratio of performance to deviation (RPD) ≥ 3.3, and the ratio of performance to interquartile distance (RPIQ) ≥ 3.71) for nitrogen, phosphorus, potassium, and zinc, SVR (R2 ≥ 0.88, RPD ≥ 2.73, RPIQ ≥ 3.31) for calcium, iron, copper, boron, and elastic net (R2 ≥ 0.95, RPD ≥ 4.47, RPIQ ≥ 6.11) for magnesium and sulfur. The results of the study revealed the potential of using hyperspectral remote sensing data for non-destructive estimation of mango leaf macro- and micro-nutrients. The developed approach is suggested to be employed within operational retrieval workflows for precision management of mango orchard nutrients.

scholarly journals Distinguishing Planting Structures of Different Complexity from UAV Multispectral Images

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 1994
Author(s):  
Qian Ma ◽  
Wenting Han ◽  
Shenjin Huang ◽  
Shide Dong ◽  
Guang Li ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Confusion Matrix ◽  
Object Oriented ◽  
Low Complexity ◽  
Classification Model ◽  
Recursive Feature Elimination ◽  
Support Vector ◽  
Multispectral Images ◽  
High Complexity ◽  
Structure Complexity

This study explores the classification potential of a multispectral classification model for farmland with planting structures of different complexity. Unmanned aerial vehicle (UAV) remote sensing technology is used to obtain multispectral images of three study areas with low-, medium-, and high-complexity planting structures, containing three, five, and eight types of crops, respectively. The feature subsets of three study areas are selected by recursive feature elimination (RFE). Object-oriented random forest (OB-RF) and object-oriented support vector machine (OB-SVM) classification models are established for the three study areas. After training the models with the feature subsets, the classification results are evaluated using a confusion matrix. The OB-RF and OB-SVM models’ classification accuracies are 97.09% and 99.13%, respectively, for the low-complexity planting structure. The equivalent values are 92.61% and 99.08% for the medium-complexity planting structure and 88.99% and 97.21% for the high-complexity planting structure. For farmland with fragmentary plots and a high-complexity planting structure, as the planting structure complexity changed from low to high, both models’ overall accuracy levels decreased. The overall accuracy of the OB-RF model decreased by 8.1%, and that of the OB-SVM model only decreased by 1.92%. OB-SVM achieves an overall classification accuracy of 97.21%, and a single-crop extraction accuracy of at least 85.65%. Therefore, UAV multispectral remote sensing can be used for classification applications in highly complex planting structures.

scholarly journals A reconstruction of the recent fire regimes of Majete Wildlife Reserve, Malawi, using remote sensing

Fire Ecology ◽  
2021 ◽  
Vol 17 (1) ◽  
Author(s):  
Willem A. Nieman ◽  
Brian W. van Wilgen ◽  
Alison J. Leslie
Keyword(s):  
Remote Sensing ◽  
Fire Management ◽  
Fire Regime ◽  
Fire Regimes ◽  
Dry Season ◽  
Annual Rainfall ◽  
Vegetation Types ◽  
Local Evidence ◽  
Hot Dry Season ◽  
Wildlife Reserve

Abstract Background Fire is an important process that shapes the structure and functioning of African savanna ecosystems, and managers of savanna protected areas use fire to achieve ecosystem goals. Developing appropriate fire management policies should be based on an understanding of the determinants, features, and effects of prevailing fire regimes, but this information is rarely available. In this study, we report on the use of remote sensing to develop a spatially explicit dataset on past fire regimes in Majete Wildlife Reserve, Malawi, between 2001 and 2019. Moderate Resolution Imaging Spectroradiometer (MODIS) images were used to evaluate the recent fire regime for two distinct vegetation types in Majete Wildlife Reserve, namely savanna and miombo. Additionally, a comparison was made between MODIS and Visible Infrared Imager Radiometer Suite (VIIRS) images by separately evaluating selected aspects of the fire regime between 2012 and 2019. Results Mean fire return intervals were four and six years for miombo and savanna vegetation, respectively, but the distribution of fire return intervals was skewed, with a large proportion of the area burning annually or biennially, and a smaller proportion experiencing much longer fire return intervals. Variation in inter-annual rainfall also resulted in longer fire return intervals during cycles of below-average rainfall. Fires were concentrated in the hot-dry season despite a management intent to restrict burning to the cool-dry season. Mean fire intensities were generally low, but many individual fires had intensities of 14 to 18 times higher than the mean, especially in the hot-dry season. The VIIRS sensors detected many fires that were overlooked by the MODIS sensors, as images were collected at a finer scale. Conclusions Remote sensing has provided a useful basis for reconstructing the recent fire regime of Majete Wildlife Reserve, and has highlighted a current mismatch between intended fire management goals and actual trends. Managers should re-evaluate fire policies based on our findings, setting clearly defined targets for the different vegetation types and introducing flexibility to accommodate natural variation in rainfall cycles. Local evidence of the links between fires and ecological outcomes will require further research to improve fire planning.

scholarly journals Hindcast and Near Real-Time Monitoring of Green Macroalgae Blooms in Shallow Coral Reef Lagoons Using Sentinel-2: A New-Caledonia Case Study

2021 ◽  
Vol 13 (2) ◽  
pp. 211
Author(s):  
Maële Brisset ◽  
Simon Van Wynsberge ◽  
Serge Andréfouët ◽  
Claude Payri ◽  
Benoît Soulard ◽  
...  
Keyword(s):  
Green Algae ◽  
Algal Blooms ◽  
New Caledonia ◽  
Spectral Indices ◽  
Green Macroalgae ◽  
Spectral Bands ◽  
Algae Blooms ◽  
Trade Offs ◽  
Sentinel 2

Despite the necessary trade-offs between spatial and temporal resolution, remote sensing is an effective approach to monitor macroalgae blooms, understand their origins and anticipate their developments. Monitoring of small tropical lagoons is challenging because they require high resolutions. Since 2017, the Sentinel-2 satellites has provided new perspectives, and the feasibility of monitoring green algae blooms was investigated in this study. In the Poé-Gouaro-Déva lagoon, New Caledonia, recent Ulva blooms are the cause of significant nuisances when beaching. Spectral indices using the blue and green spectral bands were confronted with field observations of algal abundances using images concurrent with fieldwork. Depending on seabed compositions and types of correction applied to reflectance data, the spectral indices explained between 1 and 64.9% of variance. The models providing the best statistical fit were used to revisit the algal dynamics using Sentinel-2 data from January 2017 to December 2019, through two image segmentation approaches: unsupervised and supervised. The latter accurately reproduced the two algal blooms that occurred in the area in 2018. This paper demonstrates that Sentinel-2 data can be an effective source to hindcast and monitor the dynamics of green algae in shallow lagoons.

Sign in / Sign up

Export Citation Format

Share Document