Abstract Forest fires have caused considerable losses to ecologies, societies, and economies worldwide. To minimize these reduce forest fires, modeling predicting the occurrence of are meaningful because they can support fire prevention management. In recent years, convolutional neural network (CNN) has become an important state-of-the-art deep learning algorithm, its implementation enriched many fields. Therefore, we proposed a spatial prediction model for susceptibility using CNN. Past...

Abstract Developing new ABX 3 ‐type perovskites is very important for expanding the family of and obtaining excellent light absorbing material. One strategy replacing A site atoms with super‐alkali perovskites, but stable dynamics performance high efficiency have not been found until now. Herein, massive super‐alkalis, such as Li O, 2 F, H 5 O , so on, are introduced into cubic CH NH PbI these super‐alkalis systematically studied by using ab initio molecular simulation density functional...

Wildfire susceptibility is of great importance to the prevention and management global wildfires. Artificial neural networks (ANNs), particularly multilayer perceptrons (MLPs), have been widely used in wildfire susceptibility. Recently, deep (DNNs) become state-of-the-art algorithms, especially convolutional (CNNs). However, applicability different ANNs has not thoroughly discussed, interpretability CNNs remains problematic. This paper consists two parts: one part deeply compares analyses...

Southeast Asia (SEA) is a region affected by landslide and wildfire; however, few studies on susceptibility modeling for the two hazards together have been conducted this region, intersection uncertainty of are rarely assessed. Thus, wildfire spatial maps were studied in paper. Reliable necessary disaster management land use planning. This work used three advanced ensemble machine learning algorithms: RF (Random Forest), GBDT (Gradient Boosting Decision Tree) AdaBoost (Adaptive Boosting) to...

Abstract. An accurate spatially continuous air temperature data set is crucial for multiple applications in the environmental and ecological sciences. Existing spatial interpolation methods have relatively low accuracy, resolution of available long-term gridded products China coarse. Point observations from meteorological stations can provide series but cannot represent information. Here, we devised a method based on powerful machine learning tools. First, to determine optimal data, employed...

Landslide is a natural disaster that seriously affects human life and social development. In this study, the characteristics effectiveness of convolutional neural network (CNN) conventional machine learning (ML) methods in landslide susceptibility assessment (LSA) are compared. Six ML used study Adaboost, multilayer perceptron (MLP-NN), random forest (RF), naive Bayes, decision tree (DT), gradient boosting (GBDT). First, basic knowledge structures CNN methods, steps LSA introduced. Then, 11...

Transportation infrastructures are generally designed to have multi-decadal service lives. Transport infrastructure design, however, is largely based on historical conditions. Yet, in the face of global warming, we likely going experience more intense and frequent extreme events, which may put at severe risk. In this study, comprehensively analyze exposure road railway assets changes precipitation return periods globally. Under ~2 degrees warming mid-century (RCP 8.5 scenario), 43.6%...

After the Wenchuan earthquake (magnitude 7.9, May 12, 2008), intensive debates on how China should establish a natural disaster insurance system were initiated among researchers, policymakers, and professionals. Our focus was social aspects of insurance, explored in through nationwide survey. questionnaires investigated people's risk awareness, acceptance, their opinions governmental measures for management, willingness to pay house insurance. We analyzed results at both regional individual...

In this paper, a new technique exploiting the polarization properties of normal fiber Bragg grating (FBG) for twist sensing is firstly proposed and experimentally demonstrated. The evolution dependent loss (PDL) response FBG with respect to studied. physical model presented numerical simulation based on transfer matrix method used calculate PDL spectrum twisted FBG. theoretical experimental results suggest that have higher sensitivities than reflected or transmitted amplitude spectra. Based...

Satellite remote sensing provides a powerful tool for assessing lake water surface temperature (LWST) variations, particularly large bodies that reside in areas. In this study, the MODIS land (LST) product level 3 (MOD11A2) was used to investigate spatiotemporal variation of LWST 56 lakes across Tibetan Plateau and examine factors affecting variations during 2000–2015. The results show annual cycles ranged from −19.5 °C early February 25.1 late July. Obvious diurnal differences (DTDs) were...

Wildfire is a primary forest disturbance. A better understanding of wildfire susceptibility and its dominant influencing factors crucial for regional risk management. This study performed assessment using multiple methods, including logistic regression, probit an artificial neural network, random (RF) algorithm. Yunnan Province, China was used as case area. We investigated the sample ratio ignition nonignition data to avoid misleading results due overwhelming number samples in models. To...

Precipitation is the main factor that triggers landslides. Rainfall-induced landslide susceptibility mapping (LSM) crucial for disaster prevention and losses mitigation, though most studies are temporally ambiguous on a regional scale. To better reveal mechanisms provide more accurate maps risk assessment hazard prediction, developing global dynamic LSM model essential. In this study, we used Google Earth Engine (GEE) as data platform applied three tree-based ensemble machine learning...

Styrene–butadiene–styrene (SBS) modified bitumen are generally used as binders in bituminous pavement because of the good performance. Under influence traffic, environment, and other factors, SBS would be aged, which mainly includes aging base degradation modifiers. With view resource recycling, aged is usually rejuvenated to prepare recycled mixtures. The present paper reviews state-of-the-art research on rejuvenation bitumen. In detail, paths comprehensively introduced discussed. According...