This article describes the application of spatial statistical epidemiological modeling and its inference and applies it to COVID-19 case data, looking at it from a spatial perspective, and considering time-series data. COVID-19 cases in Indonesia are increasing and spreading in all provinces, including Kalimantan. This study uses applied mathematics and spatiotemporal analysis to determine the factors affecting the constant rise of COVID-19 cases in Kalimantan. The spatiotemporal analysis uses the Geographically Temporally Weighted Regression (GTWR) model by developing a spatial and temporal interaction distance function. The GTWR model was applied to data on positive COVID-19 cases at a scale of 56 districts/cities in Kalimantan between the period of January 2020 and August 2021. The purpose of the study was to determine the factors affecting the cumulative increase in COVID-19 cases in Kalimantan and map the spatial distribution for 56 districts/cities based on the significant predictor variables. The results of the study show that the GTWR model with the development of a spatial and temporal interaction distance function using the kernel Gaussian fixed bandwidth function is a better model compared to the Ordinary Least Squares (OLS) model. According to the significant variables, there are various factors affecting the rise in cases of COVID-19 in the region of Kalimantan, including the number of doctors, the number of TB cases, the percentage of elderly population, GRDP, and the number of hospitals. The highest factors that affect COVID-19 cases are the high number of TB cases, population density, and the lack of health services. Furthermore, an area map was produced on the basis of the significant variables affected by the rise in COVID-19 cases. The results of the study provide local governments with decision-making recommendations to overcome COVID-19-related issues in their respective regions.

Forest and land fires occur every year in Indonesia. Efforts to handle forest and land fires have not been optimal because fires occur in too many places with unclear patterns and densities. The study analyzed the spatiotemporal patterns of burned areas and fire density in fire-prone areas in Indonesia. Data of burned areas were taken from http://sipongi.menlhk.go.id/. The website collected its data from NOAA (National Oceanic and Atmospheric Administration) images. Data were analyzed using the hot spot analysis to determine the spatiotemporal patterns of the burned areas and the kernel density analysis to examine the density of land fires. Findings showed that the spatiotemporal pattern from 2016 to 2019 formed a hot spot value in the peatland area with a confidence level of 90–99%, meaning that land fires were clustered in that area. In addition, the highest density of land fires also occurred in the peatland areas. Clustered burned areas with high fire density were found in areas with low–medium vegetation density—they were the peatland areas. The peatland areas must become the priority to prevent and handle forest and land fires to reduce fire risks.

Modeling and analysis of time series are important in applications including economics, engineering, environmental science and social science. Selecting the best time series model with accurate parameters in forecasting is a challenging objective for scientists and academic researchers. Hybrid models combining neural networks and traditional Autoregressive Moving Average (ARMA) models are being used to improve the accuracy of modeling and forecasting time series. Most of the existing time series models are selected by information-theoretic approaches, such as AIC, BIC, and HQ. This paper revisits a model selection technique based on Minimum Message Length (MML) and investigates its use in hybrid time series analysis. MML is a Bayesian information-theoretic approach and has been used in selecting the best ARMA model. We utilize the long short-term memory (LSTM) approach to construct a hybrid ARMA-LSTM model and show that MML performs better than AIC, BIC, and HQ in selecting the model—both in the traditional ARMA models (without LSTM) and with hybrid ARMA-LSTM models. These results held on simulated data and both real-world datasets that we considered.We also develop a simple MML ARIMA model.

Sentinel-2 imagery can identify forest and land fires in underground parts, surface fires, and crown fires. The dNBR and RBR spectral indices on Sentinel-2 images proved accurate in identifying. This study analyzed the index value for burned area mapping in wetland areas using Sentinel-2 imagery data in 2019 and hotspot data from the MODIS data. The indices used to identify the burned area and the severity of the fire was the differenced normalized burn ratio (dNBR) and relativized burn ratio (RBR). Visual validation tests were performed by comparing RGB composite images to check the appearance before and after combustion with dNBR and RBR results. The dNBR value accuracy was 91.5%, and for a kappa, the accuracy was 89.58%. The RBR accuracy was 92.9%, and the kappa accuracy was 0.91. The results confirmed that in the Banjarbaru area, RBR was more accurate in identifying burned areas than dNBR; both indices can be used for burned area mapping in wetland areas.