COVID-19 has a severe and widespread impact, especially in Indonesia. COVID-19 was first reported in Indonesia on March 03, 2020 then rapidly spread to all 34 provinces by April 09, 2020. Since then, COVID-19 is declared a state of national disaster and health emergency. This research analyzes the difference of CO, HCHO, NO2, and SO2 density in Jakarta, West Java, Central Java, and South Sulawesi before and during the pandemic. Also, this study assesses the effect of large scale restrictions on the economic growth during COVID-19 pandemic in Indonesia. In a nutshell, the results on Wilcoxon and Fisher test by significance level alpha=5% as well as odds ratio showed that there are significant differences of CO density in all regions with highest odds ratio in East Java (OR=9.07), significant differences of HCHO density in DKI Jakarta, East Java, and South Sulawesi. There are significant differences of NO2 density before and during public activities limitation in DKI Jakarta, West Java, East Java, and South Sulawesi. However, the results show that there are no significant differences of SO2 density in all regions. In addition, this research shows that there are significant differences of retail, grocery and pharmacy, and residental mobility before and during the COVID-19 pandemic in Indonesia. This research also shows that during the COVID-19 pandemic there are severe economic losses, industry, companies, and real disruptions are severe for all levels of life due to large scale restrictions. (C) 2020 GJESM. All rights reserved.

In recent years, the integration of deep learning techniques with remote sensing technology has revolutionized the way natural hazards, such as floods, are monitored and managed. However, existing methods for flood segmentation using remote sensing data often overlook the utility of correlative features among multispectral satellite information. In this study, we introduce a progressive cross-attention network (ProCANet), a deep learning model that progressively applies both self- and cross-attention mechanisms to multispectral features, generating optimal feature combinations for flood segmentation. The proposed model was compared with state-of-the-art approaches using the Sen1Floods11 dataset and our bespoke flood data generated for the Citarum River basin, Indonesia. Our model demonstrated superior performance with the highest intersection over union (IoU) score of 0.815. Our results in this study, coupled with the ablation assessment comparing scenarios with and without attention across various modalities, open a promising path for enhancing the accuracy of flood analysis using remote sensing technology.

This paper presents the dataset about the social vulnerability in Indonesia. This dataset contains several dimensions which rely on previous studies. The data was compiled mainly from the 2017 National Socioeconomic Survey (SUSENAS) done by BPS-Statistics Indonesia. We utilize the weight to obtain the estimation based on multistage sampling. We also received additional information on population, the number, and population growth from the BPS-Statistics Indonesia's 2017 Population projection. Furthermore, we provide the distance matrix as the supplementary information and the number of populations to do the Fuzzy Geographically Weighted Clustering (FGWC). This data can be utilized to do further analysis of social vulnerability to promote disaster management. The data can be accessed further at https://raw.githubusercontent.com/bmlmcmc/naspaclust/main/data/sovi_data.csv.

Classical Fuzzy C-Means (FCM) was believed as a robust clustering method when it is optimized and modified. But, at this time many researchers stated that classical FCM is less robust. So this study aims to investigate and prove the robustness of FCM by conducting studies into several data sets and optimization methods and modifications. The results show that FCM is a robust-proven method when viewed from the value of the objective function, the number of iterations, and the time being completed.

Synthetic data has a key role to play in data sharing by statistical agencies and other generators of statistical data products. Generative Adversarial Networks (GANs), typically applied to image synthesis, are also a promising method for tabular data synthesis. However, there are unique challenges in tabular data compared to images, eg tabular data may contain both continuous and discrete variables and conditional sampling, and, critically, the data should possess high utility and low disclosure risk (the risk of re-identifying a population unit or learning something new about them), providing an opportunity for multi-objective (MO) optimization. Inspired by MO GANs for images, this paper proposes a smart MO evolutionary conditional tabular GAN (SMOE-CTGAN). This approach models conditional synthetic data by applying conditional vectors in training, and uses concepts from MO optimisation to balance disclosure risk against utility. Our results indicate that SMOE-CTGAN is able to discover synthetic datasets with different risk and utility levels for multiple national census datasets. We also find a sweet spot in the early stage of training where a competitive utility and extremely low risk are achieved, by using an Improvement Score. The full code can be downloaded from github¹.