Spatiotemporal deformation characteristics of Outang landslide and identification of triggering factors using data mining

Since the impoundment of Three Gorges Reservoir(TGR)in 2003,numerous slopes have experienced noticeable movement or destabilization owing to reservoir level changes and seasonal rainfall.One case is the Outang landslide,a large-scale and active landslide,on the south bank of the Yangtze River.The latest monitoring data and site investigations available are analyzed to establish spatial and temporal landslide deformation characteristics.Data mining technology,including the two-step clustering and Apriori algorithm,is then used to identify the dominant triggers of landslide movement.In the data mining process,the two-step clustering method clusters the candidate triggers and displacement rate into several groups,and the Apriori algorithm generates correlation criteria for the cause-and-effect.The analysis considers multiple locations of the landslide and incorporates two types of time scales:longterm deformation on a monthly basis and short-term deformation on a daily basis.This analysis shows that the deformations of the Outang landslide are driven by both rainfall and reservoir water while its deformation varies spatiotemporally mainly due to the difference in local responses to hydrological factors.The data mining results reveal different dominant triggering factors depending on the monitoring frequency:the monthly and bi-monthly cumulative rainfall control the monthly deformation,and the 10-d cumulative rainfall and the 5-d cumulative drop of water level in the reservoir dominate the daily deformation of the landslide.It is concluded that the spatiotemporal deformation pattern and data mining rules associated with precipitation and reservoir water level have the potential to be broadly implemented for improving landslide prevention and control in the dam reservoirs and other landslideprone areas.

Data-augmented landslide displacement prediction using generative adversarial network

Landslides are destructive natural disasters that cause catastrophic damage and loss of life worldwide.Accurately predicting landslide displacement enables effective early warning and risk management.However,the limited availability of on-site measurement data has been a substantial obstacle in developing data-driven models,such as state-of-the-art machine learning(ML)models.To address these challenges,this study proposes a data augmentation framework that uses generative adversarial networks(GANs),a recent advance in generative artificial intelligence(AI),to improve the accuracy of landslide displacement prediction.The framework provides effective data augmentation to enhance limited datasets.A recurrent GAN model,RGAN-LS,is proposed,specifically designed to generate realistic synthetic multivariate time series that mimics the characteristics of real landslide on-site measurement data.A customized moment-matching loss is incorporated in addition to the adversarial loss in GAN during the training of RGAN-LS to capture the temporal dynamics and correlations in real time series data.Then,the synthetic data generated by RGAN-LS is used to enhance the training of long short-term memory(LSTM)networks and particle swarm optimization-support vector machine(PSO-SVM)models for landslide displacement prediction tasks.Results on two landslides in the Three Gorges Reservoir(TGR)region show a significant improvement in LSTM model prediction performance when trained on augmented data.For instance,in the case of the Baishuihe landslide,the average root mean square error(RMSE)increases by 16.11%,and the mean absolute error(MAE)by 17.59%.More importantly,the model’s responsiveness during mutational stages is enhanced for early warning purposes.However,the results have shown that the static PSO-SVM model only sees marginal gains compared to recurrent models such as LSTM.Further analysis indicates that an optimal synthetic-to-real data ratio(50%on the illustration cases)maximizes the improvements.This also demonstrates the robustness and effectiveness of supplementing training data for dynamic models to obtain better results.By using the powerful generative AI approach,RGAN-LS can generate high-fidelity synthetic landslide data.This is critical for improving the performance of advanced ML models in predicting landslide displacement,particularly when there are limited training data.Additionally,this approach has the potential to expand the use of generative AI in geohazard risk management and other research areas.

Dosimetric and Efficiency Comparisons between Volumetric Modulated Arc Therapy and IMRT for Cervical-Thoracic Esophageal Cancers

Purpose: This study aims to evaluate the treatment plans of Volumetric-modulated arc therapy (VMAT) and intensity-modulated radiation therapy (IMRT) techniques for cervical-thoracic esophageal cancers. Methods and Materials: Sixty patients were retrospectively identified. Several parameters were evaluated based on target conformity and dose-volume histograms of organs at risk (lung, spinal cord, and heart). A phantom for time comparison was also assessed for each plan. Results: The IMRT plans (5f-IMRT: V95% = 99.4 ± 0.3, 7f-IMRT: V95% = 99.8 ± 0.1) results in better PTV coverage than RA plans (Single-arc: V95% = 95.8 ± 3.2, Double-arc: V95% = 95.4 ± 2.3). The target dose conformity of the 5f-IMRT plan was inferior to all plans (CI = 70.4 ± 7.1). The Single-arc plan achieved the best conformity (CI = 72.5 ± 4.6), whereas the Double-arc plan (CI = 72.1 ± 5.1) was slightly inferior to the Single-arc plan but superior to the 7f-IMRT plan (CI = 71.7 ± 8.6). The total MU was reduced by 42.1% in VMAT plan. The average MU needed to deliver the dose of 60 Gy for Single-arc (423.5 ± 52.1 MU) was found to be the least. Similarly, the average MU for the 5f-IMRT, 7f-IMRT and Double-arc were 868.2 ± 182.0 MU, 870.0 ± 225.3 MU and 548.8 ± 47.2 MU, respectively. The delivery time in VMAT plans was reduced from 193.8 seconds to 99.2 seconds by around 48.8% compared to IMRT plans. Conclusion: For similar PTV parameters, VMAT delivers a lower dose to organs at risk than IMRT in a shorter time, and this has warranted clinical implementation.

Integrated Analysis of the Gene Expression Profiling and Copy Number Aberration of the Ovarian Cancer

Objective: DNA copy number alterations and difference expression are frequently observed in ovarian cancer. The purpose of this way was to pinpoint gene expression change that was associated with alterations in DNA copy number and could therefore enlighten some potential oncogenes and stability genes with functional roles in cancers, and investigated the bioinformatics significance for those correlated genes. Method: We obtained the DNA copy number and mRNA expression data from the Cancer Genomic Atlas and identified the most statistically significant copy number alteration regions using the GISTIC. Then identified the significance genes between the tumor samples within the copy number alteration regions and analyzed the correlation using a binary matrix. The selected genes were subjected to bioinformatics analysis using GSEA tool. Results: GISTIC analysis results showed there were 45 significance copy number amplification regions in the ovarian cancer, SAM and Fisher’s exact test found there have 40 genes can affect the expression level, which located in the amplification regions. That means we obtained 40 genes which have a correlation between copy number amplification and drastic up- and down-expression, which p-value < 0.05 (Fisher’s exact test) and an FDR < 0.05. GSEA enrichment analysis found these genes were overlapped with the several published studies which were focused on the gene study of tumorigenesis. Conclusion: The use of statistics and bioinformatics to analyze the microarray data can found an interaction network involved. The combination of the copy number data and expression has provided a short list of candidate genes that are consistent with tumor driving roles. These would offer new ideas for early diagnosis and treat target of ovarian cancer.

State-of-the-art review of soft computing applications in underground excavations

Soft computing techniques are becoming even more popular and particularly amenable to model the complex behaviors of most geotechnical engineering systems since they have demonstrated superior predictive capacity,compared to the traditional methods.This paper presents an overview of some soft computing techniques as well as their applications in underground excavations.A case study is adopted to compare the predictive performances of soft computing techniques including eXtreme Gradient Boosting(XGBoost),Multivariate Adaptive Regression Splines(MARS),Artificial Neural Networks(ANN),and Support Vector Machine(SVM) in estimating the maximum lateral wall deflection induced by braced excavation.This study also discusses the merits and the limitations of some soft computing techniques,compared with the conventional approaches available.

Modelling of shallow landslides with machine learning algorithms

This paper introduces three machine learning(ML)algorithms,the‘ensemble'Random Forest(RF),the‘ensemble'Gradient Boosted Regression Tree(GBRT)and the Multi Layer Perceptron neural network(MLP)and applies them to the spatial modelling of shallow landslides near Kvam in Norway.In the development of the ML models,a total of 11 significant landslide controlling factors were selected.The controlling factors relate to the geomorphology,geology,geo-environment and anthropogenic effects:slope angle,aspect,plan curvature,profile curvature,flow accumulation,flow direction,distance to rivers,water content,saturation,rainfall and distance to roads.It is observed that slope angle was the most significant controlling factor in the ML analyses.The performance of the three ML models was evaluated quantitatively based on the Receiver Operating Characteristic(ROC)analysis.The results show that the‘ensemble'GBRT machine learning model yielded the most promising results for the spatial prediction of shallow landslides,with a 95%probability of landslide detection and 87%prediction efficiency.

Analytical solution for tunnelling-induced response of an overlying pipeline considering gap formation

Soil-pipeline separation due to tunnelling has been certainly substantiated in previous model tests.However,this phenomenon has seldom been considered in current analytical solutions.This study formulates a tensionless Winkler solution that could make allowance for gap formation in soil-pipeline interaction analyses.The solution is validated by comparisons with existing experimental measurements and two recognized analytical solutions.Also,its advantage over an existing Winkler solution is addressed.Further parametric studies reveal that the effects of gap formation on the response of a pipeline rely largely on the tunnel volume loss and the pipeline’s bending stiffness and burial depth.In general,a pipeline’s bending moments and subgrade reaction forces are more susceptible than its deflections to the gap formation.

Microstructure evolution and strengthening mechanisms of a high-performance TiN-reinforced Al-Mn-Mg-Sc-Zr alloy processed by laser powder bed fusion

In this work,a high-strength crack-free TiN/Al-Mn-Mg-Sc-Zr composite was fabricated by laser powder bed fusion(L-PBF).A large amount of uniformly distributed L1_(2)-Al_(3)(Ti,Sc,Zr)nanoparticles were formed during the L-PBF process due to the partial melting and decomposition of TiN nanoparticles under a high temperature.These L1_(2)-Al_(3)(Ti,Sc,Zr)nanoparticles exhibited a highly coherent lattice relationship with the Al matrix.All the prepared TiN/Al-Mn-Mg-Sc-Zr composite samples exhibit ultrafine grain mi-crostructure.In addition,the as-built composite containing 1.5 wt%TiN shows an excellent tensile prop-erty with a yield strength of over 580 MPa and an elongation of over 8%,which were much higher than those of wrought 7xxx alloys.The effects of various strengthening mechanisms were quantitatively estimated and the high strength of the alloy was mainly attributed to the refined microstructure,solid solution strengthening,and precipitation strengthening contributed by L1_(2)-Al_(3)(Ti,Sc,Zr)nanoparticles.

Effects of ZnO nanoparticles on perfluorooctane sulfonate induced thyroid-disrupting on zebrafish larvae

Perfluorooctane sulfonate（PFOS） and ZnO nanoparticles（nano-ZnO） are widely distributed in the environment.However,the potential toxicity of co-exposure to PFOS and nano-ZnO remains to be fully elucidated.The test investigated the effects of co-exposure to PFOS and nano-ZnO on the hypothalamic–pituitary–thyroid（HPT） axis in zebrafish.Zebrafish embryos were exposed to a combination of PFOS（0.2,0.4,0.8 mg/L） and nano-ZnO（50 mg/L）from their early stages of life（0–14 days）.The whole-body content of TH and the expression of genes and proteins related to the HPT axis were analyzed.The co-exposure decreased the body length and increased the malformation rates compared with exposure to PFOS alone.Co-exposure also increased the triiodothyronine（T3） levels,whereas the thyroxine（T4）content remained unchanged.Compared with the exposure to PFOS alone,exposure to both PFOS（0.8 mg/L） and nano-ZnO（50 mg/L） significantly up-regulated the expression of corticotropin-releasing factor,sodium/iodidesymporter,iodothyronine deiodinases and thyroid receptors and significantly down-regulated the expression of thyroid-stimulating hormone,thyroglobulin（TG）,transthyretin（TTR） and thyroid receptors.The protein expression levels of TG and TTR were also significantly down-regulated in the co-exposure groups.In addition,the expression of the thyroid peroxidase gene was unchanged in all groups.The results demonstrated that PFOS and nano-ZnO co-exposure could cause more serious thyroid-disrupting effects in zebrafish than exposure to PFOS alone.Our results also provide insight into the mechanism of disruption of the thyroid status by PFOS and nano-ZnO.