Most mainstream research on assessing building damage using satellite imagery is based on scattered datasets and lacks unified standards and methods to quantify and compare the performance of different models. To mitigate these problems, the present study develops a novel end-to-end benchmark model, termed the pyramid pooling module semi-Siamese network (PPM-SSNet), based on a large-scale xBD satellite imagery dataset. The high precision of the proposed model is achieved by adding residual blocks with dilated convolution and squeeze-and-excitation blocks into the network. Simultaneously, the highly automated process of satellite imagery input and damage classification result output is reached by employing concurrent learned attention mechanisms through a semi-Siamese network for end-to-end input and output purposes. Our proposed method achieves F1 scores of 0.90, 0.41, 0.65, and 0.70 for the undamaged, minor-damaged, major-damaged, and destroyed building classes, respectively. From the perspective of end-to-end methods, the ablation experiments and comparative analysis confirm the effectiveness and originality of the PPM-SSNet method. Finally, the consistent prediction results of our model for data from the 2011 Tohoku Earthquake verify the high performance of our model in terms of the domain shift problem, which implies that it is effective for evaluating future disasters.
We propose a Bayesian spline model which uses a natural cubicB-spline basis with knots placed at every development period to estimate the unpaid claims. Analogous to the smoothing parameter in a smoothing spline, shrinkage priors are assumed for the coefficients of basis functions. The accident period effect is modeled as a random effect, which facilitate the prediction in a new accident period. For model inference, we use Stan to implement the no-U-turn sampler, an automatically tuned Hamiltonian Monte Carlo. The proposed model is applied to the workers' compensation insurance data in the United States. The lower triangle data is used to validate the model.
Catastrophic loss data are known to be heavy-tailed. Practitioners then need models that are able to capture both tail and modal parts of claim data. To this purpose, a new parametric family of loss distributions is proposed as a gamma mixture of the generalized log-Moyal distribution from Bhati and Ravi (2018), termed the generalized log-Moyal gamma (GLMGA) distribution. While the GLMGA distribution is a special case of the GB2 distribution, we show that this simpler model is effective in regression modeling of large and modal loss data. Regression modeling and applications to risk measurement are illustrated using a detailed analysis of a Chinese earthquake loss data set, comparing with the results of competing models from the literature. To this end, we discuss the probabilistic characteristics of the GLMGA and statistical estimation of the parameters through maximum likelihood. Further illustrations of the applicability of the new class of distributions are provided with the fire claim data set reported in Cummins et al. (1990) and a Norwegian fire losses data set discussed recently in Bhati and Ravi (2018).
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.