scholarly journals Mapping Burn Severity of Forest Fires in Small Sample Size Scenarios

Forests ◽  
2018 ◽  
Vol 9 (10) ◽  
pp. 608 ◽  
Author(s):  
Zhong Zheng ◽  
Yongnian Zeng ◽  
Songnian Li ◽  
Wei Huang
Keyword(s):  
Regression Analysis ◽  
Support Vector Regression ◽  
Forest Fires ◽  
Small Sample Size ◽  
Mapping Method ◽  
Small Sample ◽  
Burn Severity ◽  
Support Vector ◽  
Analysis Method ◽  
Field Plots

Mapping burn severity of forest fires can contribute significantly to understanding, quantifying and monitoring of forest fire severity and its impacts on ecosystems. In recent years, several remote sensing-based methods for mapping burn severity have been reported in the literature, of which the implementations are mainly dependent on several field plots. Therefore, it is a challenge to develop alternative method of mapping burn severity using limited number of field plots. In this study, we proposed a support vector regression based method using multi-temporal satellite data to map the burn severity, evaluated its performance by calculating correlations between the predicted and the observed Composite Burn Index, and compared the performance with that of the regression analysis method (based on dNBR). The results show that the performance of support vector regression based mapping method is more accurate (RMSE = 0.46–0.57) than that of regression analysis method (RMSE = 0.53–0.68). Even with fewer training sets, it can map the detailed distribution of burn severity of forest fires and can achieve relatively better generalization, compared to regression analysis burn severity mapping methods. It could be concluded that the proposed support vector regression based mapping method is an alternative to the regression analysis method in small sample size scenarios. This method with excellent generalization performance should be recommended for future studies on burn severity of forest fires.

scholarly journals Mapping Burn Severity of Forest Fires in Small Sample Size Scenarios.

2021 ◽  
Author(s):  
Zhong Zheng ◽  
Yongnian Zeng ◽  
Songnian Li ◽  
Wei Huang
Keyword(s):  
Regression Analysis ◽  
Support Vector Regression ◽  
Forest Fires ◽  
Small Sample Size ◽  
Mapping Method ◽  
Small Sample ◽  
Burn Severity ◽  
Support Vector ◽  
Analysis Method ◽  
Field Plots

Mapping burn severity of forest fires can contribute significantly to understanding, quantifying and monitoring of forest fire severity and its impacts on ecosystems. In recent years, several remote sensing-based methods for mapping burn severity have been reported in the literature, of which the implementations are mainly dependent on several field plots. Therefore, it is a challenge to develop alternative method of mapping burn severity using limited number of field plots. In this study, we proposed a support vector regression based method using multi-temporal satellite data to map the burn severity, evaluated its performance by calculating correlations between the predicted and the observed Composite Burn Index, and compared the performance with that of the regression analysis method (based on dNBR). The results show that the performance of support vector regression based mapping method is more accurate (RMSE = 0.46–0.57) than that of regression analysis method (RMSE = 0.53–0.68). Even with fewer training sets, it can map the detailed distribution of burn severity of forest fires and can achieve relatively better generalization, compared to regression analysis burn severity mapping methods. It could be concluded that the proposed support vector regression based mapping method is an alternative to the regression analysis method in small sample size scenarios. This method with excellent generalization performance should be recommended for future studies on burn severity of forest fires.

scholarly journals Mapping Burn Severity of Forest Fires in Small Sample Size Scenarios.

2021 ◽  
Author(s):  
Zhong Zheng ◽  
Yongnian Zeng ◽  
Songnian Li ◽  
Wei Huang
Keyword(s):  
Regression Analysis ◽  
Support Vector Regression ◽  
Forest Fires ◽  
Small Sample Size ◽  
Mapping Method ◽  
Small Sample ◽  
Burn Severity ◽  
Support Vector ◽  
Analysis Method ◽  
Field Plots

Mapping burn severity of forest fires can contribute significantly to understanding, quantifying and monitoring of forest fire severity and its impacts on ecosystems. In recent years, several remote sensing-based methods for mapping burn severity have been reported in the literature, of which the implementations are mainly dependent on several field plots. Therefore, it is a challenge to develop alternative method of mapping burn severity using limited number of field plots. In this study, we proposed a support vector regression based method using multi-temporal satellite data to map the burn severity, evaluated its performance by calculating correlations between the predicted and the observed Composite Burn Index, and compared the performance with that of the regression analysis method (based on dNBR). The results show that the performance of support vector regression based mapping method is more accurate (RMSE = 0.46–0.57) than that of regression analysis method (RMSE = 0.53–0.68). Even with fewer training sets, it can map the detailed distribution of burn severity of forest fires and can achieve relatively better generalization, compared to regression analysis burn severity mapping methods. It could be concluded that the proposed support vector regression based mapping method is an alternative to the regression analysis method in small sample size scenarios. This method with excellent generalization performance should be recommended for future studies on burn severity of forest fires.

scholarly journals Research on water pollution prediction of township enterprises based on support vector regression machine

2021 ◽  
Vol 228 ◽  
pp. 02014
Author(s):  
Yue Wang ◽  
Song Xue ◽  
Junming Ding
Keyword(s):  
Water Pollution ◽  
Support Vector Regression ◽  
Rural Areas ◽  
Rural Economy ◽  
Negative Impact ◽  
Water Environment ◽  
Small Sample ◽  
Support Vector ◽  
Rural Water

The construction and development of township enterprises plays a key role in promoting the development of rural economy. With the implementation of the rural revitalization strategy, township enterprises develop rapidly, but there are problems in the development process that have a negative impact on the quality of local rural water environment. Rural water environment is related to the health of farmers, the healthy development of agriculture and the sustainable development of rural areas, so it is necessary to predict the water pollution of township enterprises. The application of support vector regression forecasting model to the prediction of water pollution of township enterprises can better predict the water pollution of township enterprises with the characteristics of complexity, nonlinear and small sample. This intelligent forecasting method will help to scientifically prevent the development of township enterprises from having negative impact on the quality of local water environment.

scholarly journals How discounts impact IPOs valuation performance and underpricing? A confrontation between warranted and unwarranted discounts

2021 ◽  
Vol 3 (1) ◽  
pp. 1-14
Author(s):  
Douaa Tizniti ◽  
◽  
Mohammed Rachid Aasri ◽  
Keyword(s):  
Regression Analysis ◽  
Market Efficiency ◽  
Small Sample Size ◽  
Intrinsic Value ◽  
Fair Value ◽  
Ordinary Least Squares ◽  
Small Sample ◽  
Least Squares Regression ◽  
Final Offer ◽  
Performance Results

Purpose: We investigated the different impacts warranted and unwarranted discounts have on IPOs valuation performance and underpricing. Research methodology: We used multivariate ordinary least squares regression analysis to examine discounts’ determinants, and their impacts on valuation errors and underpricing. We also used bias and accuracy errors to examine valuation performance. Results: We find both final offer price accuracy errors and underpricing negatively related to warranted discounts and positively related to unwarranted discounts. Additionally, warranted discounts are positively related to fair value estimate bias errors, contrarily to unwarranted discounts. Limitations: The relatively small sample size represents our study’s main limitation. Contribution: Unwarranted discounts allow assessing by issuers' underpricing level and underwriters’ sub-optimal efforts and investors' positive returns. Whereas warranted discounts allow issuers to avoid overpricing IPOs and communicate their intrinsic value, investors assess their negative returns, and underwriters reveal their superior qualitative valuation. Regulators can increase after-market efficiency and protect investors by implementing unwarranted discounts’ constraints and warranted discounts’ thresholds.

scholarly journals Wideband Shaped-Beam Reflectarray Design Using Support Vector Regression Analysis

2019 ◽  
Vol 18 (11) ◽  
pp. 2287-2291 ◽  
Author(s):  
Daniel Rodriguez Prado ◽  
Jesus Alberto Lopez-Fernandez ◽  
Manuel Arrebola ◽  
Marcos Rodriguez Pino ◽  
George Goussetis
Keyword(s):  
Regression Analysis ◽  
Support Vector Regression ◽  
Support Vector ◽  
Shaped Beam

scholarly journals Optimization Performance Comparison of Three Different Group Intelligence Algorithms on a SVM for Hyperspectral Imagery Classification

2019 ◽  
Vol 11 (6) ◽  
pp. 734 ◽  
Author(s):  
Xiufang Zhu ◽  
Nan Li ◽  
Yaozhong Pan
Keyword(s):  
Convergence Rate ◽  
Sample Size ◽  
Parameter Optimization ◽  
Classification Accuracy ◽  
Small Sample Size ◽  
Original Data ◽  
Performance Comparison ◽  
Small Sample ◽  
Support Vector ◽  
Remote Sensing Classification

Group intelligence algorithms have been widely used in support vector machine (SVM) parameter optimization due to their obvious characteristics of strong parallel processing ability, fast optimization, and global optimization. However, few studies have made optimization performance comparisons of different group intelligence algorithms on SVMs, especially in terms of their application to hyperspectral remote sensing classification. In this paper, we compare the optimization performance of three different group intelligence algorithms that were run on a SVM in terms of five aspects by using three hyperspectral images (one each of the Indian Pines, University of Pavia, and Salinas): the stability to parameter settings, convergence rate, feature selection ability, sample size, and classification accuracy. Particle swarm optimization (PSO), genetic algorithms (GAs), and artificial bee colony (ABC) algorithms are the three group intelligence algorithms. Our results showed the influence of these three optimization algorithms on the C-parameter optimization of the SVM was less than their influence on the σ-parameter. The convergence rate, the number of selected features, and the accuracy of the three group intelligence algorithms were statistically significant different at the p = 0.01 level. The GA algorithm could compress more than 70% of the original data and it was the least affected by sample size. GA-SVM had the highest average overall accuracy (91.77%), followed by ABC-SVM (88.73%), and PSO-SVM (86.65%). Especially, in complex scenes (e.g., the Indian Pines image), GA-SVM showed the highest classification accuracy (87.34%, which was 8.23% higher than ABC-SVM and 16.42% higher than PSO-SVM) and the best stability (the standard deviation of its classification accuracy was 0.82%, which was 5.54% lower than ABC-SVM, and 21.63% lower than PSO-SVM). Therefore, when compared with the ABC and PSO algorithms, the GA had more advantages in terms of feature band selection, small sample size classification, and classification accuracy.

Sign in / Sign up

Export Citation Format

Share Document