The importance of flood damage assessment has been highlighted by the government as well as by many researchers. Nevertheless, the effort in performing the damage studies is less to be found due to the lack of awareness and some other limitations related to the data and its methodologies. The flood damage data in fact is part of an essential ingredient in developing the flood mitigation policy as well as in evaluating the effectiveness of the current flood reduction measures. However, unlike other kinds flood risk quantification study, damage assessment is the one that less concerned by the researchers. This paper has mainly provides a brief introduction towards the flood damage assessment and certain essential element need to be taken into consideration have been highlighted. An analysis of previous flood damage assessment studies and discussion towards some critical issues are presented in this paper other than proposing granular fuzzy system for enhancement in flood assessment for quality risk analysis.
With the forestry and logging activities contributing to 5.6% of the agricultural sector in Malaysia’s 2018 GDP growth, this had thus implied the forest as having a significant role in national growth and the critical need of a precise tree volume estimation. Although regression has been the most common method used for this form of estimation, the expansion of information technology had, however, led to the use of a machine learning technique that is capable of overcoming the issues posed by the regression analysis. In this paper, the estimation of the tree volume was not only conducted via the regression method but had also involved the use of two machine learning techniques, namely the artificial neural network (ANN) and that of the epsilon-Support Vector Regression (ε-SVR). By comparing the root mean square error (RMSE) and standard deviation (SD) values from each of the volume model that had been obtained in this study, the machine learning technique was thus found to have demonstrated a better precision and accuracy level than that of the regression method.
Log volume estimation is a measurement of the amount of merchantable volume and precise estimation of log volume plays an important role in sustainable forest management. There are several log volume formula which commonly used in estimating the log volume, however, there are significant differences between each formula. Therefore, this paper evaluates the performance of three different log volume formula which are Smalian’s, Huber’s and Bruce’s formula against several log sectional length. The performance of each log volume formula will be evaluated in terms of the bias, precision and accuracy of the estimation. The result shows that Huber’s formula performs the best for log sectional length of 2 m, 4 m, 6 m and 8 m log sectional length. The log sectional length and prediction accuracy is inversely related whereby the shorter the log sectional length, the better the prediction accuracy is.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.