Prediction of damage potential in mainshock–aftershock sequences using machine learning algorithms

Assessing the potential damage caused by earthquakes is crucial for a community’s emergency response.In this study,four machine learning(ML)methods—random forest,extremely randomized trees,AdaBoost(AB),and gradient boosting(GB)—were employed to develop prediction models for the damage potential of the mainshock(DIMS)and mainshock–aftershock sequences(DIMA).Building structures were modeled using eight single-degree-of-freedom(SDOF)systems with different hysteretic rules.A set of 662 recorded mainshock–aftershock(MS-AS)ground motions was selected from the PEER database.Seven intensity measures(IMs)were chosen to represent the characteristics of the mainshock and aftershock.The results revealed that the selected ML methods can well predict the structural damage potential of the SDOF systems,except for the AB method.The GB model exhibited the best performance,making it the recommended choice for predicting DIMS and DIMA among the four ML models.Additionally,the impact of input variables in the prediction was investigated using the shapley additive explanations(SHAP)method.The high-correlation variables were sensitive to the structural period(T).At T=1.0 s,the mainshock peak ground velocity(PGVM)and aftershock peak ground displacement(PGDA)significantly influenced the prediction of DIMA.When T increased to 5.0 s,the primary high-correlation factor of the mainshock IMs changed from PGVM to the mainshock peak ground displacement(PGDM);however,the highcorrelation variable of the aftershock IMs remained PGDA.The high-correlation factors for DIMS showed trends similar to those of DIMA.Finally,a table summarizing the first and second high-correlation variables for predicting DIMS and DIMA were provided,offering a valuable reference for parameter selection in seismic damage prediction for mainshock–aftershock sequences.

The SSA-BP-based potential threat prediction for aerial target considering commander emotion

The target's threat prediction is an essential procedure for the situation analysis in an aerial defense system.However,the traditional threat prediction methods mostly ignore the effect of commander's emotion.They only predict a target's present threat from the target's features itself,which leads to their poor ability in a complex situation.To aerial targets,this paper proposes a method for its potential threat prediction considering commander emotion(PTP-CE)that uses the Bi-directional LSTM(BiLSTM)network and the backpropagation neural network(BP)optimized by the sparrow search algorithm(SSA).Furthermore,we use the BiLSTM to predict the target's future state from real-time series data,and then adopt the SSA-BP to combine the target's state with the commander's emotion to establish a threat prediction model.Therefore,the target's potential threat level can be obtained by this threat prediction model from the predicted future state and the recognized emotion.The experimental results show that the PTP-CE is efficient for aerial target's state prediction and threat prediction,regardless of commander's emotional effect.

The Potential Predictability of the South China Sea Summer Monsoon in a Dynamical Seasonal Prediction System

The potential predictability of climatological mean circulation and the interannual variation of the South China Sea summer monsoon (SCSSM) were investigated using hindcast results from the Institute of Atmospheric Physics Dynamical Seasonal Prediction System (IAP DCP),along with the National Centers for Environmental Prediction (NCEP) reanalysis data from the period of 1980-2000.The large-scale characteristics of the SCSSM monthly and seasonal mean low-level circulation have been well reproduced by IAP DCP,especially for the zonal wind at 850 hPa;furthermore,the hindcast variability also agrees quite well with observations.By introducing the South China Sea summer monsoon index,the potential predictability of IAP DCP for the intensity of the SCSSM has been evaluated.IAP DCP showed skill in predicting the interannual variation of SCSSM intensity.The result is highly encouraging;the correlation between the hindcasted and observed SCSSM Index was 0.58,which passes the 95% significance test.The result for the seasonal mean June-July-August SCSSM Index was better than that for the monthly mean,suggesting that seasonal forecasts are more reliable than monthly forecasts.

Prediction of Potential Distribution of Quadrastichus erythrinae Kim in China

Based on Maxent niche model and combined with ArcGIS,the suitable area range for Quadrastichus erythrinae Kim in China was predicted in the paper.The results showed that high suitable area for Q. erythrinae in China included most northeast coastal areas of Hainan Island,partial southern coastal area of Guangdong Province,partial northwestern coastal area and partial southeast coastal area of Taiwan Island; moderate suitable area included partial area of Hainan,some contiguous areas of Guangxi and Guangdong,most areas of Guangdong,partial area of Fujian and Taiwan; low suitable area included partial area from northwestern coast to inland of Hainan Island,west coastal area of Taiwan Island,most area in Guangxi,partial areas in Guangdong,Fujian and Yunnan.

AN AIR POLLUTION PREDICTION TECHNIQUE FOR URBAN DISTRICTS BASED ON MESO-SCALE NUMERICAL MODEL

Taking Shenzhen city as an example, the statistical and physical relationship between the density of pollutants and various atmospheric parameters are analyzed in detail, and a space-partitioned city air pollution potential prediction scheme is established based on it. The scheme considers quantitatively more than ten factors at the surface and planetary boundary layer (PBL), especially the effects of anisotropy of geographical environment, and treats wind direction as an independent impact factor. While the scheme treats the prediction equation respectively for different pollutants according to their differences in dilute properties, it considers as well the possible differences in dilute properties at different districts of the city under the same atmospheric condition, treating predictions respectively for different districts. Finally, the temporally and spatially high resolution predictions for the atmospheric factors are made with a high resolution numerical model, and further the space-partitioned and time-variational city pollution potential predictions are made. The scheme is objective and quantitative, and with clear physical meaning, so it is suitable to use in making high resolution air pollution predictions.

Potential predictability of Eurasian spring snow water equivalent in IAP AGCM4 hindcasts

The potential predictability and skill of Eurasian spring snow water equivalent(SWE)are explored by using a suite of ensemble hindcast experiments with the fourth-generation IAP AGCM(IAP AGCM4)and observations for the period 1982–2012.IAP AGCM4 is generally capable of reproducing the spatial distribution of Eurasian spring SWE;nevertheless,the model overestimates the SWE over Eurasia,possibly because of positive precipitation biases in wintertime.IAP AGCM4 can successfully capture the long-term trend and leading pattern of Eurasian spring SWE.Additionally,the spring SWE anomalies are generally predictable in many regions over Eurasia,especially at high latitudes;moreover,IAP AGCM4 exhibits a remarkable prediction skill for spring SWE anomalies over Eurasia in many years during 1982 to 2012.In order to reveal the relative impacts of SST anomalies and atmospheric initial conditions on the seasonal predictability of Eurasian spring SWE,two additional sets of experiments are carried out.Overall,atmospheric initial anomalies have a dominant role,though the impact of SSTs is not negligible.This study highlights the importance of atmospheric initialization in seasonal climate forecasts of spring SWE anomalies,especially at high latitudes.

Investigating the ENSO prediction skills of the Beijing Climate Center climate prediction system version 2

The El Niño-Southern Oscillation(ENSO)ensemble prediction skills of the Beijing Climate Center(BCC)climate prediction system version 2(BCC-CPS2)are examined for the period from 1991 to 2018.The upper-limit ENSO predictability of this system is quantified by measuring its“potential”predictability using information-based metrics,whereas the actual prediction skill is evaluated using deterministic and probabilistic skill measures.Results show that:(1)In general,the current operational BCC model achieves an effective 10-month lead predictability for ENSO.Moreover,prediction skills are up to 10–11 months for the warm and cold ENSO phases,while the normal phase has a prediction skill of just 6 months.(2)Similar to previous results of the intermediate coupled models,the relative entropy(RE)with a dominating ENSO signal component can more effectively quantify correlation-based prediction skills compared to the predictive information(PI)and the predictive power(PP).(3)An evaluation of the signal-dependent feature of the prediction skill scores suggests the relationship between the“Spring predictability barrier(SPB)”of ENSO prediction and the weak ENSO signal phase during boreal spring and early summer.

Structure-Based Prediction of Transcription Factor Binding Sites

Transcription Factors（TFs） are a very diverse family of DNA-binding proteins that play essential roles in the regulation of gene expression through binding to specific DNA sequences. They are considered as one of the prime drug targets since mutations and aberrant TF-DNA interactions are implicated in many diseases.Identification of TF-binding sites on a genomic scale represents a critical step in delineating transcription regulatory networks and remains a major goal in genomic annotations. Recent development of experimental high-throughput technologies has provided valuable information about TF-binding sites at genome scale under various physiological and developmental conditions. Computational approaches can provide a cost-effective alternative and complement the experimental methods by using the vast quantities of available sequence or structural information. In this review we focus on structure-based prediction of transcription factor binding sites. In addition to its potential in genomescale predictions, structure-based approaches can help us better understand the TF-DNA interaction mechanisms and the evolution of transcription factors and their target binding sites. The success of structure-based methods also bears a translational impact on targeted drug design in medicine and biotechnology.

STABILITY AND POTENTIAL PREDICTABILITY OF ANNUAL PERCIPITATION OVER CHINA

The precipitation is a primary element which directly affects the agricultural production of the country with one fifth of the world population.With the economic development the water resource stress is getting greater.In this paper,based on the data at 162 stations selected evenly over China from 1960 to 1991 the stability and potential predictability of annual precipitation have been stud- ied.The eastern and southern parts of the country having abundant precipitation enjoy more stable precipitation.The north and northwest parts of the country where the precipitations are deficient have unstable precipitations.The potential predictability approximates to the ratio of the estimated interannual variance to the climatic noise.Generally the annual precipitation over China is poten- tially predictable.In the area between the Huanghe River and Changjiang River and the east of northeastern China the potential predictability is the lowest in the country.In the north and north- west of the country the potential predictability is greater.The southeastern coast has relatively low values of potential predictability.Also,the method of estimating climatic noise of annual precipita- tion has been discussed from the idea of Yamamoto et al.(1985)in order to estimate the potential predictability.

POTENTIAL PREDICTABILITY OF MONTHLY PRECIPITATION OVER CHINA

In this paper,based on the data at 70 stations selected evenly over China for 31 years from 1961—1991.three methods to estimate climatic noise have been discussed and then the climatic noise and potential predictability of monthly precipitation(January.July.April and October)have been examined.The estimating of climatic noise is based on the method of Madden and improved methods of Trenberth and Yamamoto et al.(1985).The potential predictability is approximated by the ratio of the estimated interannual variation to the natural variation.Generally.the climatic noise of monthly precipitation over China has obvious seasonal variation and it is greater in summer than in winter,a bit greater in autumn than in spring.In most areas,the climatic noise is prominently decreasing from south to north and from coast to inland.The potential predictability of monthly precipitation also has obvious seasonal and regional difference,but the potential predictability is greater in winter than in summer in most parts of China.Whereas the comparison of spring and autumn is not obvious.Comparing with the method of Madden,the estimated values of climatic noise based on the improved methods of Trenberth and Yamamoto et al.are relatively lower.

New Metabolic Alterations and A Predictive Marker Pipecolic Acid in Sera for Esophageal Squamous Cell Carcinoma

Esophageal squamous cell carcinoma(ESCC)is a major histological subtype of esophageal cancer with a poor prognosis.Although several serum metabolomic investigations have been reported,ESCC tumor-associated metabolic alterations and predictive biomarkers in sera have not been defined.Here,we enrolled 34 treatment-naive patients with ESCC and collected their pre-and post-esophagectomy sera together with the sera from 34 healthy volunteers for a metabolomic survey.Our comprehensive analysis identified ESCC tumor-associated metabolic alterations as represented by a panel of 12 serum metabolites.Notably,postoperative abrosia and parenteral nutrition substantially perturbed the serum metabolome.Furthermore,we performed an examination using sera from carcinogen-induced mice at the dysplasia and ESCC stages and identified three ESCC tumor-associated metabolites conserved between mice and humans.Notably,among these metabolites,the level of pipecolic acid was observed to be progressively increased in mouse sera from dysplasia to cancerization,and it could be used to accurately discriminate between mice at the dysplasia stage and healthy control mice.Furthermore,this metabolite is essential for ESCC cells to restrain oxidative stress-induced DNA damage and cell proliferation arrest.Together,this study revealed a panel of 12 ESCC tumor-associated serum metabolites with potential for monitoring therapeutic efficacy and disease relapse,presented evidence for refining parenteral nutrition composition,and highlighted serum pipecolic acid as an attractive biomarker for predicting ESCC tumorigenesis.

Liquid–liquid phase separation in plants:Advances and perspectives from model species to crops

Membraneless biomolecular condensates play important roles in both normal biological activities and re-sponses to environmental stimuli in living organisms.Liquid‒liquid phase separation(LLPS)is an organi-zational mechanism that has emerged in recent years to explain the formation of biomolecular conden-sates.In the past decade,advances in LLPS research have contributed to breakthroughs in diseasefields.By contrast,although LLPS research in plants has progressed over the past 5 years,it has been concentrated on the model plant Arabidopsis,which has limited relevance to agricultural production.In this review,we provide an overview of recently reported advances in LLPS in plants,with a particular focus on photomorphogenesis,flowering,and abiotic and biotic stress responses.We propose that many potential LLPS proteins also exist in crops and may affect crop growth,development,and stress resistance.This possibility presents a great challenge as well as an opportunity for rigorous scientific research on the biological functions and applications of LLPS in crops.