The power network has a long transmission span and passes through wide areas with complex topography setting and various human engineering activities. They lead to frequent landslide hazards, which cause serious threats to the safe operation of the power transmission system. Thus, it is of great significance to carry out landslide susceptibility assessment for disaster prevention and mitigation of power network. We, therefore, undertake an extensive analysis and comparison study between different data-driven methods using a case study from China. Several susceptibility mapping results were generated by applying a multivariate statistical method (logistic regression (LR)) and a machine learning technique (random forest (RF)) separately with two different mapping-units and predictor sets of differing configurations. The models’ accuracies, advantages and limitations are summarized and discussed using a range of evaluation criteria, including the confusion matrix, statistical indexes, and the estimation of the area under the receiver operating characteristic curve (AUROC). The outcome showed that machine learning method is well suitable for the landslide susceptibility assessment along transmission network over grid cell units, and the accuracy of susceptibility models is evolving rapidly from statistical-based models toward machine learning techniques. However, the multivariate statistical logistic regression methods perform better when computed over heterogeneous slope terrain units, probably because the number of units is significantly reduced. Besides, the high model predictive performances cannot guarantee a high plausibility and applicability of subsequent landslide susceptibility maps. The selection of mapping unit can produce greater differences on the generated susceptibility maps than that resulting from the selection of modeling methods. The study also provided a practical example for landslide susceptibility assessment along the power transmission network and its potential application in hazard early warning, prevention, and mitigation.

Since the impoundment of the Three Gorges Reservoir (TGR) in June 2003, the fluctuation of the reservoir water level coupled with rainfall has resulted in more than 2500 landslides in this region. Among these instability problems, most colluvial landslides exhibit slow-moving patterns and pose a significant threat to local people and channel navigation. Advanced monitoring techniques are therefore implemented to investigate landslide deformation and provide insights for the subsequent countermeasures. In this study, the development pattern of a large colluvial landslide, locally named the Ganjingzi landslide, is analyzed on the basis of long-term monitoring. To understand the kinematic characteristics of the landslide, an integrated analysis based on real-time and multi-source monitoring, including the global navigation satellite system (GNSS), crackmeters, inclinometers, and piezometers, was conducted. The results indicate that the Ganjingzi landslide exhibits a time-variable response to the reservoir water fluctuation and rainfall. According to the supplement of community-based monitoring, the evolution of the landslide consists of three stages, namely the stable stage before reservoir impoundment, the initial movement stage of retrogressive failure, and the shallow movement stage with stepwise acceleration. The latter two stages are sensitive to the drawdown of reservoir water level and rainfall infiltration, respectively. All of the monitoring approaches used in this study are significant for understanding the time-variable pattern of colluvial landslides and are essential for landslide mechanism analysis and early warning for risk mitigation.

Landslide-induced tsunamis in reservoirs often pose greater risks than landslides themselves. Existing studies and mitigation practices have prioritized increasing landslide stability to meet safety standards, incurring high costs and lacking sustainability. More than 5000 landslides have developed along the Three Gorges Reservoir banks in China, and some may trigger tsunamis. To effectively and sustainably manage risk of landslide-tsunami hazard chains (LTHC), we propose a new framework (based on quantitative risk analysis) involves decision-making based on risk characteristics and local economies, a strategy for selecting optimal risk control plan through cost–benefit analyses that consider long-term effectiveness and adverse effects, and dynamic management through iterative risk reassessment-recontrol cycles. The Liangshuijing landslide accelerated in 2009, posing a tsunami threat to the Yangtze River and coastal residents. Post-mitigation, the risks under four mitigation plans and combined scenarios were quantitatively evaluated. The mass removal plan reduces total risk by approximately 68%, less than the 80% reduction from the anti-slip pile plan, but with a 30-fold greater benefit–cost ratio (BCR). The surface drainage and monitoring network plans show limited long-term cost-effectiveness due to short measure lifetimes, however, their short-term BCRs exceed those of the mass removal plan due to lower direct costs. According to comprehensive long and short-term analyses, combined plans involving mass removal are the most cost-effective. Our results reveal how to select appropriate strategies for managing LTHC risk, how landslide mitigation controls tsunami risks, and how time-related parameters affect solution effectiveness. Our findings show that partially mitigating risks may provide more cost-effective and sustainable management of LTHCs than eliminating risks to negligible levels.

Background. Cancer of unknown primary (CUP) is a type of malignant tumor, which is histologically diagnosed as a metastatic carcinoma while the tissue‐of‐origin cannot be identified. CUP accounts for roughly 5% of all cancers. Traditional treatment for CUP is primarily broad‐spectrum chemotherapy; however, the prognosis is relatively poor. Thus, it is of clinical importance to accurately infer the tissue‐of‐origin of CUP. Methods. We developed a gradient boosting framework to trace tissue‐of‐origin of 20 types of solid tumors. Specifically, we downloaded the expression profiles of 20,501 genes for 7713 samples from The Cancer Genome Atlas (TCGA), which were used as the training data set. The RNA‐seq data of 79 tumor samples from 6 cancer types with known origins were also downloaded from the Gene Expression Omnibus (GEO) for an independent data set. Results. 400 genes were selected to train a gradient boosting model for identification of the primary site of the tumor. The overall 10‐fold cross‐validation accuracy of our method was 96.1% across 20 types of cancer, while the accuracy for the independent data set reached 83.5%. Conclusion. Our gradient boosting framework was proven to be accurate in identifying tumor tissue‐of‐origin on both training data and independent testing data, which might be of practical usage.

Landslide susceptibility maps (LSMs) depict the spatial probability of landslide occurrence, typically using data-driven models based on past event distributions. However, these models often overlook temporal changes, assuming that past patterns reliably predict future events. In a rapidly changing world, influenced by factors such as climate change and urbanization, this assumption may lead to inconsistencies in LSMs over time, reducing their predictive accuracy. To investigate this issue, we analyzed a multi-temporal inventory of 1518 landslides over the past 70 years in Wanzhou District, China, a region impacted by significant environmental changes. We first examined the temporal and spatial variations in landslide patterns. Then, we employed random forest (RF) and extreme gradient boosting (XGBoost) algorithms to create five LSMs, each based on landslide data from different periods. Finally, we conducted a multi-temporal validation to evaluate the effectiveness of these maps in predicting landslides occurring in subsequent decades. Our findings reveal temporal shifts in landslide spatial patterns and changes in the model-derived importance of causal factors. These variations may be associated with changing environmental conditions in the study area. Both RF and XGBoost models produced LSMs with varying patterns depending on the temporal baseline of the landslide data used. Importantly, the accuracy of these maps decreases as the time span of the inventory data increases. Maps based on short-term data showed higher accuracy, but their predictive power declined rapidly over time, suggesting that in the context of significant environmental changes, LSMs need continuous updates and further spatiotemporal analysis to remain effective.