Prediction And Evaluation of Forest Fire In Yunnan of China Based On Geographically Weighted Logistic Regression Model

Establishing an effective forest fire forecasting mechanism is the premise of scientific planning and management of forest fires and forest fire prevention. In recent years, the forest fire prediction mechanism has been one of the key areas of concern for the government forestry management departments and forestry researchers. One of them, is logistic regression ( LR ). It is a relatively frequent prediction probability model used in forest fire prediction and prediction in China and abroad for the past few years. However, with the gradual deepening of research, it is found that the logistic regression model fails to fully consider the spatial non-stationary relationship between forest fires and driving factors, which leads to poor fitting effect and low prediction accuracy of the model. But its extended counterpart, the Geographically weighted logistic regression ( GWLR ) model, takes into account the spatial correlation between model variables, and effectively improves the fitting ability and prediction accuracy of the model. Therefore, this paper compares the ability of the logistic regression model and the geographically weighted logistic regression model in terms of fitting ability and prediction accuracy in order to obtain the ability of the two models to predict forest fires in Yunnan Province. In this paper, the samples were divided into 60% training samples and 40% test samples, and repeated sampling was carried out 5 times for training. Variables that appeared in the training model for 3 or more times were used to construct the final LR and GWLR models. Finally, the models with better fitting ability and higher prediction accuracy were used to classify the fire risks in Yunnan Province. The results show that the geographically weighted logistic regression model is superior to the logistic regression model in terms of fitting effect and accuracy. The geographically weighted logistic regression model is more suitable for the data structure of forest fires in Yunnan Province and has better prediction ability. The AUC value of the geographically weighted logistic regression model is 0.902, and the prediction accuracy is 82.7 %; The AUC value of logistic regression model was 0.891, and the prediction accuracy was 80.1%; Fully considering the spatial heterogeneity among model variables can, to some extent, predict forest fires more accurately. The fitting of the two models shows that the relative humidity, temperature, air pressure, sunshine hours, daily precipitation, wind speed, and other meteorological factors; Vegetation type; terrain factor; Population density, road network and other human activity factors become the cause of forest fires in Yunnan Province.

Spatial Analysis of Prevalence of Early Marriage and HDI in Indonesia

Early marriage has become an important issue in Indonesia. Even though the rate of early marriage shows a decline until 2020, the number still makes Indonesia become the country with the second highest early marriage in Southeast Asia. Early marriage that occurs can hinder the achievement of the Sustainable Development Goals (SDG) and can have an impact on the Human Development Index. The existence of a relationship between early marriage and HDI encourages researchers to conduct studies that aimed at examining the effect of the prevalence of early marriage on HDI in each district/city in Indonesia on 2020. This study uses the Geographically Weighted Logistic Regression (GWLR) analysis method with the data sourced from the National Socio-Economic Survey (SUSENAS) raw data in March 2020 and publication data on the website of The Central Bureau of Statistics. The results of the analysis found that the prevalence of early marriage has a negative and significant effect in several districts/cities in the Provinces of Aceh, North Sumatra, West Sumatra, Riau, Jambi, South Sumatra, Bengkulu, Lampung, Bangka Belitung Islands, Riau Islands, West Java, Central Sulawesi, South Sulawesi, Southeast Sulawesi, Maluku, and West Papua. This research is expected to be a recommendation for the government and community organizations to conduct socialization regarding the maturity age of marriage and the adverse effects that can be caused by early marriage.

Geographical variations in maternal dietary patterns during pregnancy associated with birth weight in Shaanxi province, Northwestern China

The geographical variation of maternal dietary patterns related to birth outcomes is important for improving the health of mothers and children; however, it is currently unknown. Thus, the objective of the study was to investigate geographical variations of maternal dietary pattern during pregnancy, and evaluate the spatial varying association of maternal dietary patterns in pregnancy with abnormal birth weight. A population-based cross-sectional study was conducted in Shaanxi province in Northwest China in 2013 to evaluate the relationship between abnormal birth weight and dietary pattern using the Geographically Weighted Logistic Regression (GWLR). Three dietary patterns during pregnancy were extracted through factor analysis, explaining approximately 45.8% of the variability of food intake. Approximately 81.6% of mothers with higher scores on the equilibrium pattern was more unlikely to have small for gestational age (SGA) infants, with the lower OR observed in Central and South Shaanxi. The snacks pattern was positively associated with low birth weight (LBW) for 23.2% of participants, with the highest OR in Central Shaanxi. Among about 80.0% of participants with higher scores on the snacks pattern living in South and Central Shaanxi, there was a higher risk for SGA. The OR values tend to descend from South to North Shaanxi. The OR values of the negative association between prudent pattern and LBW decreased from South to North Shaanxi among approximately 59.3% of participants. The prudent pattern was also negatively associated with the increasing risk of fetal macrosomia among 19.2% of participants living mainly in South Shaanxi. The association of maternal dietary patterns during pregnancy with abnormal birth weight varied geographically across Shaanxi province. The findings emphasize the importance of geographical distribution to improve the dietary patterns among disadvantaged pregnant women.

Predicting Eurasian Watermilfoil and Curly-leaf Pondweed Presence-Absence in Adirondack Lakes Using Geographically Weighted Logistic Regression

Aquatic invasive species, Eurasian Watermilfoil (EWM) and Curly-leaf Pondweed (CLP), have been dispersing across New York, USA and are threatening the ecosystem of Adirondack Park, a state park with a large forest preserve and heavily frequented by tourists. In this study, the prediction of EWM and CLP invasion across Adirondack Park lakes is modeled using logistic regression (LR) and geographically weighted logistic regression (GWLR) with lake, landscape, and climate variable predictors. EWM presence-absence is found to be best predicted by nearby invaded lakes, human presence, and elevation. The presence-absence of CLP models have similar findings, with the addition of game-fish abundance being important. GWLR increases model performance and prediction, with explained variation of EWM and CLP increasing by 23% and 16% and the percent correctly predicted increasing by 2.6% and 0.9%. The study shows that GWLR, a relatively novel methodology, works better than common LR models for predicting invasion of EWM and CLP across Adirondack Park, and corroborates anthropogenic influences on dispersal of aquatic invaders.

Predicting Eurasian Watermilfoil and Curly-leaf Pondweed Presence-Absence in Adirondack Lakes Using Geographically Weighted Logistic Regression

Aquatic invasive species, Eurasian Watermilfoil (EWM) and Curly-leaf Pondweed (CLP), have been dispersing across New York, USA and are threatening the ecosystem of Adirondack Park, a state park with a large forest preserve and heavily frequented by tourists. In this study, the prediction of EWM and CLP invasion across Adirondack Park lakes is modeled using logistic regression (LR) and geographically weighted logistic regression (GWLR) with lake, landscape, and climate variable predictors. EWM presence-absence is found to be best predicted by nearby invaded lakes, human presence, and elevation. The presence-absence of CLP models have similar findings, with the addition of game-fish abundance being important. GWLR increases model performance and prediction, with explained variation of EWM and CLP increasing by 23% and 16% and the percent correctly predicted increasing by 2.6% and 0.9%. The study shows that GWLR, a relatively novel methodology, works better than common LR models for predicting invasion of EWM and CLP across Adirondack Park, and corroborates anthropogenic influences on dispersal of aquatic invaders.