Among the most frequent and dangerous natural hazards, landslides often result in huge casualties and economic losses. Landslide susceptibility mapping (LSM) is an excellent approach for protecting and reducing the risks by landslides. This study aims to explore the performance of Bayesian optimization (BO) in the random forest (RF) and gradient boosting decision tree (GBDT) model for LSM and applied in Shuicheng County, China. Multiple data sources are used to obtain 17 conditioning factors of landslides, Borderline-SMOTE and Randomundersample methods are combined to solve the imbalanced sample problem. RF and GBDT models before and after BO are adopted to calculate the susceptibility value of landslides and produce LSMs and these models were compared and evaluated using multiple validation approach. The results demonstrated that the models we proposed all have high enough model accuracy to be applied to produce LSM, the performance of the RF is better than the GBDT model without BO, while after adopting the Bayesian optimized hyperparameters, the prediction accuracy of the RF and GBDT models is improved by 1% and 7%, respectively and the Bayesian optimized GBDT model is the best for LSM in this four models. In summary, the Bayesian optimized RF and GBDT models, especially the GBDT model we proposed for landslide susceptibility assessment and LSM construction has a very good application performance and development prospects.

There is increasing focus on the difficult challenge of realizing coordinated development of production, living and ecological spaces within the regional development process. An ecological–production–living space evaluation index system was established in this study based on the concept of ecological, production and living spaces (EPLSs), the relationship between land use function and land use type and the national standard of land use classification. The aim of this study was to reveal the driving forces and patterns of variation in EPLSs in Inner Mongolia from 1990 to 2015. The results indicated that Inner Mongolia is mainly dominated by ecological space, followed by production space. Production and living spaces are mainly distributed to the south of the Greater Hinggan–Yinshan–Helan mountain ranges. Spatial changes in EPLSs were accelerated with prominent regional differences, with declining ecological area and increasing living and production spaces. Regional urbanization and industrialization were identified as the driving forces for change in EPLS in Inner Mongolia. It is hoped that the findings of this study can provide rational guidance for management of land use and coordinated development of EPLSs within Inner Mongolia.

Debris flow events often pose significant damage and are a threat to infrastructure and even livelihoods. Recent studies have mainly focused on determining the susceptibility of debris flow using deterministic or heuristic/probabilistic models. However, each type of model has its own significant advantages with some irreparable disadvantages. The random forest model, which is sensitive to the region where the terrain conditions are suitable for the occurrence of debris flow, was applied along with the steady-state infinite slope method, which is capable of describing the initiation mechanism of debris flow. In this manner, a random-forest-based steady-state infinite slope method was used to conduct susceptibility assessment of debris-flow at Changbai mountain area. Results showed that the assessment accuracy of the proposed random-forest-based steady-state infinite slope method reached 90.88%; however, the accuracy of just the random forest model or steady-state infinite slope method was only 88.48% or 60.45%, respectively. Compared with the single-model assessment results, the assessment accuracy of the proposed method improved by 2.4% and 30.43%, respectively. Meanwhile, the debris-flow-prone area of the proposed method was reduced. The random-forest-based steady-state infinite slope method inherited the excellent diagnostic performance of the random-forest models in the region where the debris flow disaster already occurred; meanwhile, this method further refined the debris-flow-prone area from the suitable terrain area based on physico-mechanical properties; thus, the performance of this method was better than those of the other two models.

Landslides are among the most frequent natural hazards in the world. Rainfall is an important triggering factor for landslides and is responsible for topples, slides, and debris flows—three of the most important types of landslides. However, several previous relevant research studies covered general landslides and neglected the rainfall–topples–slides–debris flows disaster chain. Since landslide hazard mapping (LHM) is a critical tool for disaster prevention and mitigation, this study aimed to build a GeoDetector and Bayesian network (BN) model framework for LHM in Shuicheng County, China, to address these geohazards. The GeoDetector model will be used to screen factors, eliminate redundant information, and discuss the interaction between elements, while the BN model will be used for constructing a causality disaster chain network to determine the probability and risk level of the three types of landslides. The practicability of the BN model was confirmed by error rate and scoring rules validation. The prediction accuracy results were tested using overall accuracy, Matthews correlation coefficient, relative operating characteristics curve, and seed cell area index. The proposed framework is demonstrated to be sufficiently accurate to construct the complex LHM. In summary, the combination of the GeoDetector and BN model is very promising for spatial prediction of landslides.

Tianchi volcano is a dormant active volcano with a risk of re-eruption. Volcanic soil and volcanic ash samples were collected around the volcano and the concentrations of 21 metals (major and trace elements) were determined. The spatial distribution of the metals was obtained by inverse distance weight (IDW) interpolation. The metals’ sources were identified and their pollution levels were assessed to determine their potential ecological and human health risks. The metal concentrations were higher around Tianchi and at the north to the west of the study area. According to the geo-accumulation index (Igeo), enrichment factor (EF) and contamination factor (CF) calculations, Zn pollution was high in the study area. Pearson’s correlation analysis and principal component analysis showed that with the exception of Fe, Mn and As, the metals that were investigated (Al, K, Ca, Na, Mg, Ti, Cu, Pb, Zn, Cr, Ni, Ba, Ga, Li, Co, Cd, Sn, Sr) were mostly naturally derived. A small proportion of Li, Pb and Zn may have come from vehicle traffic. There is no potential ecological risk and non-carcinogenic risk because of the low concentrations of the metals; however, it is necessary to pay attention to the carcinogenic risk of Cr and As in children.

The impacts of earthquakes and secondary disasters on ecosystems and the environment are attracting increasing global attention. Development of uncertainty reasoning models offers a chance to research these complex correlations. The primary aim of this research was to construct a disaster chain hazard assessment model that combines a Bayesian Network model and the ArcGIS program software for Changbai Mountain, China, an active volcano with a spate of reported earthquakes, collapses, and landslide events. Furthermore, the probability obtained by the Bayesian Networks was used to determine the disaster chain probability and hazard intensity of the earthquake events, while ArcGIS was used to produce the disaster chain hazard map. The performance of the Bayesian Network model was measured by error rate and scoring rules. The confirmation of the outcomes of the disaster chain hazard assessment model shows that the model demonstrated good predictive performance on the basis of the area under the curve, which was 0.7929. From visual inspection of the produced earthquake disaster chain hazard map, highly hazardous zones are located within a 15 km radius from the Tianchi center, while the northern and the western parts of the studied area are characterized mainly by very low to low hazard values.

With the changing global climate, the occurrence of drought has become more frequent and serious in Anhui Province, an important agricultural production area. It is necessary to investigate and detect characteristics of the frequent droughts, which can provide reasonable suggestions to reduce their adverse influences. In this study, temporal variability characteristics of the Standardized Precipitation Index (SPI) with different time scales were analyzed based on the daily precipitation data of 16 stations during 1961–2010. Drought characteristics, including duration and severity, were then defined using run theory based on SPI with a 3-month time scale. The most suitable distribution function was selected to define the univariate marginal distributions of drought duration and severity. Finally, the bivariate joint probability distributions for different drought partitions were assessed based on the copula function, and spatial distributions of their return periods developed. Results indicate the following: (1) the duration and severity of droughts in Anhui Province have been decreasing and the spatial distribution of return periods for drought duration and severity are similar. Average drought duration was between 3.29 and 3.69 months, increasing gradually from north to south, and average drought severity was between 2.11 and 3.54, increasing from northeast to southwest. (2) When mild droughts happen, the drought bivariate return periods were 3.78–6.56 years. The highest values of moderate, severe, and extreme droughts occurred in northern and southwestern areas of Anhui Province, and the lowest values occurred in the north-central and south-eastern areas.

Landslide identification is an increasingly important research topic in remote sensing and the study of natural hazards. It is essential for hazard prevention, mitigation, and vulnerability assessments. Despite great efforts over the past few years, its accuracy and efficiency can be further improved. Thus, this study combines the two most popular approaches: susceptibility analysis and change detection thresholding, to derive a landslide identification method employing novel identification criteria. Through a quantitative evaluation of the proposed method and masked change detection thresholding method, the proposed method exhibits improved accuracy to some extent. Our susceptibility-based change detection thresholding method has the following benefits: (1) it is a semi-automatic landslide identification method that effectively integrates a pixel-based approach with an object-oriented image analysis approach to achieve more precise landslide identification; (2) integration of the change detection result with the susceptibility analysis result represents a novel approach in the landslide identification research field.

Due to global warming, extreme climate events have become an important issue, and different geographical regions have different sensitivities to climate change. Therefore, temporal and spatial variations in extreme temperature and precipitation events in Inner Mongolia were analyzed based on the daily maximum temperature, minimum temperature, and precipitation data during the period of 1960-2017. The results showed that warm extreme indices, such as SU25, TX90p, TN90p. and WSDI, significantly increased, whereas the cold extreme indices, such as FD0, TX10p, TN10p, and CSDI, significantly decreased; all indices have obvious abrupt changes based on the Mann-Kendall lest; nighttime warming was higher than daytime warming. Extreme precipitation indices slightly decreased overall. All of the extreme temperature and precipitation indices had long-range correlations based on detrended fluctuation analysis (a > 0.5), thereby indicating that the extreme climate indices will maintain their current trend directions in the future. ENSO, AO, and IOD had a strong positive influence on warm extremes and a strong negative influence on cold extremes in Inner Mongolia. NCEP/NCAR and ERA-20CM reanalysis showed that strengthening anticyclone circulation, increasing geopotential height, decreasing daytime cloudiness and increasing nightime cloudiness contributed to changes in climate extremes in Inner Mongolia. (C) 2018 Elsevier B.V. All rights reserved.

In this study, we used bands 7, 4, and 3 of the Advance Himawari Imager (AHI) data, combined with a Threshold Algorithm and a visual interpretation method to monitor the entire process of grassland fires that occurred on the China-Mongolia border regions, between 05:40 (UTC) on April 19th to 13:50 (UTC) on April 21st 2016. The results of the AHI data monitoring are evaluated by the fire point product data, the wind field data, and the environmental information data of the area in which the fire took place. The monitoring result shows that, the grassland fire burned for two days and eight hours with a total burned area of about 2708.29 km(2). It mainly spread from the northwest to the southeast, with a maximum burning speed of 20.9 m/s, a minimum speed of 2.52 m/s, and an average speed of about 12.07 m/s. Thus, using AHI data can not only quickly and accurately track the dynamic development of a grassland fire, but also estimate the spread speed and direction. The evaluation of fire monitoring results reveals that AHI data with high precision and timeliness can be highly consistent with the actual situation.

Taking the Changbai Mountain Nature Reserve as the research area, based on the theory of modern disaster risk, the comprehensive use of GIS spatial analysis and disaster risk assessment mathematical methods, quantitative assessment of the risk of collapse disaster in Changbai Mountain area.Remote sensing data and socio-economic statistics data were applied to research.By analyzing the relationship between the risk of collapse disasters, exposure of the disaster-bearing bodies, vulnerability, and regional disaster prevention and reduction capabilities, the corresponding evaluation indicators were selected to construct a risk assessment model for the collapse hazards and drawdangerousand risk map in the Changbai Mountain area.The results show that the risk of collapse disaster is highest in the Tianchi Center of Changbai Mountain, and is higher in the north of Chibeidistrict and south of Chinandistrict.

Environmental risk has become an area of major concern and research, drawing special attention. This study on the environmental risk assessment (ERA) of Dar es Salaam Municipal Solid Waste comes at a time when the Government of Tanzania is becoming increasingly concerned about dealing with high levels of pollution from municipal solid waste (MSW). The paper employed the Driving force-Pressure-State-Impact-Response (DPSIR) model to establish an environmental risk indicator system and the analytical hierarchy process (AHP) to calculate and analyze risk values, based on the actual situation of MSW in the city of Dar es Salaam. It lists several measures that have been taken in response to the current significantly high levels of pollution, which have assisted in maintaining the environmental risk index (ERI) at a medium level (0.4–0.6) during the period from 2006–2017. However, these measures have not been adequate enough to manage the external pressure. The ERI has been increasing gradually, calling for timely formulation of demand-specific waste management policies to reduce the possibility of reaching the critical point in near future. With the use of the DPSIR model for ERA, this study has become highly valuable, providing empirical justification to reduce environmental risk from MSW, which is one of the main sources of environmental pollution in the urban areas of developing countries.

Natural and human factors has different effect on landslide occurrence and susceptibility analysis. Through using natural factors as the index system and put into Logistic Regression and Random Forest model to conduct susceptibility assessment, the accuracy of the results are 0.7639 and 0.8884, which is slightly higher than the assessment using human factors as the index system. Therefore, it can be concluded that the influence of natural factors on the accuracy of susceptibility assessment is higher than the human factors. Meanwhile, some human factors will lead to reduce the accuracy of assessment.

Maize is the main grain crop in Midwestern Jilin province. It's conducive to analyze the characteristics and the effects on maize of droughts. 9 stations were selected during 1960-2014 based on the crop water deficit index (CWDI) and drought grades. Results show that:(1) The district water deficit condition are the overall drought characteristics in study area. Serious spring drought occurred more frequently in the western region of China, and the autumn droughts in eastern region are more likely to occur. (2) there was a direct effect on maize yield by droughts in the north regions of all study area. Excepting the jointing-tasseling stages, the water deficit in the eastern region of the remaining three growing periods had little effect on maize yield.

Along with global warming, drought disasters are occurring more frequently and are seriously affecting normal life and food security in China. Drought risk assessments are necessary to provide support for local governments. This study aimed to establish an integrated drought risk model based on the relation curve of drought joint probabilities and drought losses of multi-hazard-affected bodies. First, drought characteristics, including duration and severity, were classified using the 1953–2010 precipitation anomaly in the Taoerhe Basin based on run theory, and their marginal distributions were identified by exponential and Gamma distributions, respectively. Then, drought duration and severity were related to construct a joint probability distribution based on the copula function. We used the EPIC (Environmental Policy Integrated Climate) model to simulate maize yield and historical data to calculate the loss rates of agriculture, industry, and animal husbandry in the study area. Next, we constructed vulnerability curves. Finally, the spatial distributions of drought risk for 10-, 20-, and 50-year return periods were expressed using inverse distance weighting. Our results indicate that the spatial distributions of the three return periods are consistent. The highest drought risk is in Ulanhot, and the duration and severity there were both highest. This means that higher drought risk corresponds to longer drought duration and larger drought severity, thus providing useful information for drought and water resource management. For 10-, 20-, and 50-year return periods, the drought risk values ranged from 0.41 to 0.53, 0.45 to 0.59, and 0.50 to 0.67, respectively. Therefore, when the return period increases, the drought risk increases.

In the past two decades, the regional climate in China has undergone significant change, resulting in crop yield reduction and complete failure. The goal of this study is to detect the variation of temperature and precipitation for different growth periods of maize and assess their impact on phenology. The daily meteorological data in the Midwest of Jilin Province during 1960–2014 were used in the study. The ensemble empirical mode decomposition method was adopted to analyze the non-linear trend and fluctuation in temperature and precipitation, and the sensitivity of the length of the maize growth period to temperature and precipitation was analyzed by the wavelet cross-transformation method. The results show that the trends of temperature and precipitation change are non-linear for different growth periods of maize, and the average temperature in the sowing-jointing stage was different from that in the other growth stages, showing a slight decrease trend, while the variation amplitude of maximum temperature is smaller than that of the minimum temperature. This indicates that the temperature difference between day and night shows a gradually decreasing trend. Precipitation in the growth period also showed a decreasing non-linear trend, while the inter-annual variability with period of quasi-3-year and quasi-6-year dominated the variation of temperature and precipitation. The whole growth period was shortened by 10.7 days, and the sowing date was advanced by approximately 11 days. We also found that there was a significant resonance period among temperature, precipitation, and phenology. Overall, a negative correlation between phenology and temperature is evident, while a positive correlation with precipitation is exhibited. The results illustrate that the climate suitability for maize has reduced over the past decades.