“地时”(Earthtime)研究计划:“深时”(Deep Time)记录的定年精度与时间分辨率

地质年代的精度、准确度和分辨率的水平决定了人们在多大程度上可以回答一些关于"深时"的生态、气候、生物演化和基础地质问题。目前用于定年和对比的技术主要包括放射性同位素年代学、生物地层学、磁性地层学和旋回地层学等,但各有优缺点,甚至有时不同定年系统所获得的结果存在一些矛盾。"地时"(Earhtime)研究计划就是要开展广泛的国际合作,通过整合、校正和提高地质年代学和定量地层学方法,发展出一套新的地质年代学技术,使地质年代的误差达到0.1%的水平,实现精确确定地球历史的时间及先后顺序。中国东北松辽盆地发育连续、完整的白垩系为开展高分辨率年代学研究提供了机遇,将是对"地时"研究计划在中生代陆相地层中应用的良好补充和重要贡献。

Hybrid model for BOF oxygen blowing time prediction based on oxygen balance mechanism and deep neural network

The amount of oxygen blown into the converter is one of the key parameters for the control of the converter blowing process,which directly affects the tap-to-tap time of converter. In this study, a hybrid model based on oxygen balance mechanism (OBM) and deep neural network (DNN) was established for predicting oxygen blowing time in converter. A three-step method was utilized in the hybrid model. First, the oxygen consumption volume was predicted by the OBM model and DNN model, respectively. Second, a more accurate oxygen consumption volume was obtained by integrating the OBM model and DNN model. Finally, the converter oxygen blowing time was calculated according to the oxygen consumption volume and the oxygen supply intensity of each heat. The proposed hybrid model was verified using the actual data collected from an integrated steel plant in China, and compared with multiple linear regression model, OBM model, and neural network model including extreme learning machine, back propagation neural network, and DNN. The test results indicate that the hybrid model with a network structure of 3 hidden layer layers, 32-16-8 neurons per hidden layer, and 0.1 learning rate has the best prediction accuracy and stronger generalization ability compared with other models. The predicted hit ratio of oxygen consumption volume within the error±300 m^(3)is 96.67%;determination coefficient (R^(2)) and root mean square error (RMSE) are0.6984 and 150.03 m^(3), respectively. The oxygen blow time prediction hit ratio within the error±0.6 min is 89.50%;R2and RMSE are0.9486 and 0.3592 min, respectively. As a result, the proposed model can effectively predict the oxygen consumption volume and oxygen blowing time in the converter.

Sedimentological/Palaeogeographic Data as Fundamental Building Blocks of the DDE Project:Critical Underpinning of Reconstructing Deep-time Earth Systems

1 Introduction Sedimentary rocks archive important information for understanding how the earth system operates and how life and environments have evolved through earth history.Properly identifying characteristics of sedimentary rocks,along with the subsequent interpretation of depositional processes and sedimentary environments in a basin or locality.

Preliminary research and scheme design of deep underground in situ geo-information detection experiment for Geology in Time

The deep earth,deep sea,and deep space are the main parts of the national“three deep”strategy,which is in the forefront of the strategic deployment clearly defined in China’s 14th Five-Year Plan(2021-2025)and the Long-Range Objectives Through the Year 2035.It is important to reveal the evolutionary process and mechanism of deep tectonics to understand the earth’s past,present and future.The academic con-notation of Geology in Time has been given for the first time,which refers to the multi-field evolution response process of geological bodies at different time and spatial scales caused by geological processes inside and outside the Earth.Based on the deep in situ detection space and the unique geological envi-ronment of China Jinping Underground Laboratory,the scientific issue of the correlation mechanism and law between deep internal time-varying and shallow geological response is given attention.Innovative research and frontier exploration on deep underground in situ geo-information detection experiments for Geology in Time are designed to be carried out,which will have the potential to explore the driving force of Geology in Time,reveal essential laws of deep earth science,and explore innovative technologies in deep underground engineering.

Deep Learning for Financial Time Series Prediction:A State-of-the-Art Review of Standalone and HybridModels

Financial time series prediction,whether for classification or regression,has been a heated research topic over the last decade.While traditional machine learning algorithms have experienced mediocre results,deep learning has largely contributed to the elevation of the prediction performance.Currently,the most up-to-date review of advanced machine learning techniques for financial time series prediction is still lacking,making it challenging for finance domain experts and relevant practitioners to determine which model potentially performs better,what techniques and components are involved,and how themodel can be designed and implemented.This review article provides an overview of techniques,components and frameworks for financial time series prediction,with an emphasis on state-of-the-art deep learning models in the literature from2015 to 2023,including standalonemodels like convolutional neural networks(CNN)that are capable of extracting spatial dependencies within data,and long short-term memory(LSTM)that is designed for handling temporal dependencies;and hybrid models integrating CNN,LSTM,attention mechanism(AM)and other techniques.For illustration and comparison purposes,models proposed in recent studies are mapped to relevant elements of a generalized framework comprised of input,output,feature extraction,prediction,and related processes.Among the state-of-the-artmodels,hybrid models like CNNLSTMand CNN-LSTM-AM in general have been reported superior in performance to stand-alone models like the CNN-only model.Some remaining challenges have been discussed,including non-friendliness for finance domain experts,delayed prediction,domain knowledge negligence,lack of standards,and inability of real-time and highfrequency predictions.The principal contributions of this paper are to provide a one-stop guide for both academia and industry to review,compare and summarize technologies and recent advances in this area,to facilitate smooth and informed implementation,and to highlight future research directions.

Inversion of Seabed Geotechnical Properties in the Arctic Chukchi Deep Sea Basin Based on Time Domain Adaptive Search Matching Algorithm

The chirp sub-bottom profiler,for its high resolution,easy accessibility and cost-effectiveness,has been widely used in acoustic detection.In this paper,the acoustic impedance and grain size compositions were obtained based on the chirp sub-bottom profiler data collected in the Chukchi Plateau area during the 11th Arctic Expedition of China.The time-domain adaptive search matching algorithm was used and validated on our established theoretical model.The misfit between the inversion result and the theoretical model is less than 0.067%.The grain size was calculated according to the empirical relationship between the acoustic impedance and the grain size of the sediment.The average acoustic impedance of sub-seafloor strata is 2.5026×10^(6) kg(s m^(2))^(-1)and the average grain size(θvalue)of the seafloor surface sediment is 7.1498,indicating the predominant occurrence of very fine silt sediment in the study area.Comparison of the inversion results and the laboratory measurements of nearby borehole samples shows that they are in general agreement.

“深时”(Deep Time)研究与沉积学

近百年来全球气候正在经历一次以变暖为主要特征的显著变化,人类文明的发展迫切要求我们对这种变化的发展趋势及其环境与资源效应有更加深入的了解。仅仅对现代和第四纪气候研究是有局限性的,全面了解地球表层及气候系统需要研究整个地质历史时期地球表层系统的发展演化。基于这样一种需求,从沉积记录研究前第四纪地质历史时期的地球古气候变化及重大地质事件,并为未来气候预测提供依据的"深时"(Deep Time)研究计划在国际地球科学界逐渐形成。"深时"研究将聚焦地球气候系统中的重大科学问题,通过地质历史时期极端气候事件探讨气候变化的极限和速率、大气成分和大洋成分变化、大气环流和大洋环流以及生物圈、固体地球与太阳的联系等,最终揭示地球气候系统与地球系统的联系。"深时"研究将通过解译、定年和模拟的基本方法,发展完善大陆科学钻探项目,获得保存良好、高分辨率的沉积记录是重中之重。可以预见,"深时"研究将与"深空"(Deep Space)、"深海"(Deep Sea)和"深部"(Deep Interior)研究计划一样,成为未来国际和国内地球科学重大研究领域。同时,在开展"深时"研究过程中,沉积学也将扮演核心学科的角色发挥重要的作用。

Deep medium environment of strong earthquakes occurrence in Yunnan region

The deep structure background of earth medium for strong earthquakes ccurrence in Yunnan area is discussed inthis paper, by using the results on the study of the velocity structure, elect fieal conductivity stricture, geothermalstructure in the crust and upper mantle in Yunnan area. The results show that the occurrence of strong earthquakes in Yunnan region is obviously related to the deep medium and tectonic environment such as the existenceof the high velocity zone in the upper crust, the low velocity zone or high electrical conductivity layer in themiddle crust, local uplift in the upper mantle, high geothermal activity and deep and large fault, etc. The large earthquakes could not take place at anywhere, they often occur at some regions which have a certainbackground in the deep medium structure. The activity of the earthquakes with magnitude of 5 or less is quite random,the occurrence of them have not the obvious background of the deep medium strUcture.

Integration of Real-Time Chemical Sensors for Deep Sea Research

There is a great demand for in-situ real-time chemical sensors in the oceanographic research, to measure the chemical components under the deep sea. The ISE (Ion Selective Electrode) is commonly used as a detecting part of deep-sea electro-chemical sensors. The paper highlights the solidification and micromation of the working and reference electrodes. The sensors of pH and H 2S with a thermal probe are accomplished after the solution of configuration of electrodes and signal processing. The sensor system has been tested successfully in the cruise of DY105-12, 14 sponsored by China Ocean Mineral Research and Exploitation Association(COMRA).

“Deep-time Digital Basin” Based on Big Data and Artificial Intelligence

1 Introduction Information technology has been playing an ever-increasing role in geoscience.Sphisicated database platforms are essential for geological data storage,analysis and exchange of Big Data(Feblowitz,2013;Zhang et al.,2016;Teng et al.,2016;Tian and Li,2018).The United States has built an information-sharing platform for state-owned scientific data as a national strategy.

Prediction of Departure Aircraft Taxi Time Based on Deep Learning

With the continuous increase in the number of flights,the use of airport collaborative decision-making(ACDM)systems has been more and more widely spread.The accuracy of the taxi time prediction has an important effect on the A-CDM calculation of the departure aircraft’s take-off queue and the accurate time for the aircraft blockout.The spatial-temporal-environment deep learning(STEDL)model is presented to improve the prediction accuracy of departure aircraft taxi-out time.The model is composed of time-flow sub-model(airport capacity,number of taxiing aircraft,and different time periods),spatial sub-model(taxiing distance)and environmental sub-model(weather,air traffic control,runway configuration,and aircraft category).The STEDL model is used to predict the taxi time of departure aircraft at Hong Kong Airport and the results show that the STEDL method has a prediction accuracy of 95.4%.The proposed model also greatly reduces the prediction error rate compared with the other machine learning methods.

Coefficients of earth pressure at rest in thick and deep soils

The effect of test methods and stress paths on the experimental value of the coefficient of earth pressure at rest, K0, was investigated under high pressures. The results indicate that the rigid pressure chamber and flexible lateral confining pressure medium method gives a stress ratio at the initial stage that is not the real K0. Moreover, K0 increases during the loading process becoming greater at high pressures. In the unloading process, however, K0 increases only at the initial stage but decreases thereafter. In addition, the incremental magnitude definition, K0=dσ3/dσ1, gives higher values than the total magnitude definition, K0=σ3/σ1, under loading. This is also true during initial stages of unloading. The experiment results also indicate that earth pressure at rest in deep and thick soils can be estimated by a power function of axial and confining pressures. It is necessary to choose the appropriate Kn to avoid some accidents.

Deep mantle plumes and an increasing Earth radius

Recent space geodetic and gravimetric studies have given indications that the Earth’s radius is increasing at 0.1-0.4 mm yr-1 at present. Seismic studies have also shown that earthquakes alone could be causing the radius to increase at 0.011-0.06 mm yr-1. Deep mantle plumes provide a geophysical context within which such radial expansion, if confirmed, could possibly be explained. Both theory and observation suggest that these rising plumes more readily penetrate the 670 km barrier than do subducting slabs moving in the opposite direction towards the core-mantle boundary. If so, there would be a net flow of mass from the deep lower mantle into the upper mantle. Due to the lower pressures in the upper mantle,the excess mass of plume materials reaching there would transform to minerals with lower densities than they had at the mantle base. An increase in the mantle volume and the Earth’s radius would therefore be implied. Using previously published data for the African superplume. it is estimated that this mechanism could cause the Earth’s radius to increase at rates of 0.02-0.3 mm yr-1, similar to the rates possibly indicated in the present studies. This mechanism could also explain the very large range in current estimates of mantle plume heat and volume fluxes. A possible energy source for this plumedriven mode of expansion is discussed.

Effective relaxation time and viscosity of the earth inferred from the postseismic vertical deformations of the 1990 MS=7.0 Gonghe earthquake

The postseismic vertical deformation rates of the 1990 Gonghe M S=7.0 earthquake appears to have decreased exponentially. Based on Okada′s coseismic surface displacement solution caused by a uniform fault slip in an elastic homogeneous half space, we derived its postseismic surface displacement by using a single layer standard linear solid model, and further derived a simplified formula for determining the effective relaxation time and viscosity of the earth, which is independent of the dislocation parameters of the causative fault. From the postseismic vertical deformation of the 1990 Gonghe earthquake, we inferred that the effective relaxation time defined by τ = η/μ is 2.6 years, and the effective viscosity η is about 10 18 Pa·s.

Anomalies identification of Earth’s rotation rate time series (2012-2017) for possible correlation with strong earthquakes occurrence

The analysis of the Earth’s rotation rate time series,from January 1,2012 till December 31,2017,is performed using two different time series analysis methods,both based on signal decomposition joined with forecasting approach.Anomalies in the time series are detected making the comparison between the raw signal and the forecasting one at the 95% confidence interval.The two methods show consistent results and the best is selected according to the evaluation of the prediction uncertainty.Both methods highlight correlations between detected anomalies in the Earth’s rotation rate time series and the world’s earthquakes occurrence with magnitude≥7 and/or number of events≥150 per day,within a time interval of ±10 days from each earthquake event.This study brings an innovation in the analysis of such time series and helps to better understand the extent of this relationship.

A Simple Method for Source Depth Estimation with Multi-path Time Delay in Deep Ocean

A method of source depth estimation based on the multi-path time delay difference is proposed. When the minimum time arrivals in all receiver depths are snapped to a certain time on time delay-depth plane, time delay arrivals of surface-bottom reflection and bottom-surface reflection intersect at the source depth. Two hydrophones deployed vertically with a certain interval are required at least. If the receiver depths are known, the pair of time delays can be used to estimate the source depth. With the proposed method the source depth can be estimated successfully in a moderate range in the deep ocean without complicated matched-field calculations in the simulations and experiments.

Underdetermined DOA estimation via multiple time-delay covariance matrices and deep residual network

Higher-order statistics based approaches and signal sparseness based approaches have emerged in recent decades to resolve the underdetermined direction-of-arrival(DOA)estimation problem.These model-based methods face great challenges in practical applications due to high computational complexity and dependence on ideal assumptions.This paper presents an effective DOA estimation approach based on a deep residual network(DRN)for the underdetermined case.We first extract an input feature from a new matrix calculated by stacking several covariance matrices corresponding to different time delays.We then provide the input feature to the trained DRN to construct the super resolution spectrum.The DRN learns the mapping relationship between the input feature and the spatial spectrum by training.The proposed approach is superior to existing model-based estimation methods in terms of calculation efficiency,independence of source sparseness and adaptive capacity to non-ideal conditions(e.g.,low signal to noise ratio,short bit sequence).Simulations demonstrate the validity and strong performance of the proposed algorithm on both overdetermined and underdetermined cases.

Classification of Short Time Series in Early Parkinson’s Disease With Deep Learning of Fuzzy Recurrence Plots

There are many techniques using sensors and wearable devices for detecting and monitoring patients with Parkinson’s disease(PD).A recent development is the utilization of human interaction with computer keyboards for analyzing and identifying motor signs in the early stages of the disease.Current designs for classification of time series of computer-key hold durations recorded from healthy control and PD subjects require the time series of length to be considerably long.With an attempt to avoid discomfort to participants in performing long physical tasks for data recording,this paper introduces the use of fuzzy recurrence plots of very short time series as input data for the machine training and classification with long short-term memory(LSTM)neural networks.Being an original approach that is able to both significantly increase the feature dimensions and provides the property of deterministic dynamical systems of very short time series for information processing carried out by an LSTM layer architecture,fuzzy recurrence plots provide promising results and outperform the direct input of the time series for the classification of healthy control and early PD subjects.

Research on trend prediction of component stock in fuzzy time series based on deep forest

With the continuous development of machine learning and the increasing complexity of financial data analysis,it is more popular to use models in the field of machine learning to solve the hot and difficult problems in the financial industry.To improve the effectiveness of stock trend prediction and solve the problems in time series data processing,this paper combines the fuzzy affiliation function with stock-related technical indicators to obtain nominal data that can widely reflect the constituent stocks in the case of time series changes by analysing the S&P 500 index.Meanwhile,in order to optimise the current machine learning algorithm in which the setting and adjustment of hyperparameters rely too much on empirical knowledge,this paper combines the deep forest model to train the stock data separately.The experimental results show that(1)the accuracy of the extreme random forest and the accuracy of the multi-grain cascade forest are both higher than that of the gated recurrent unit(GRU)model when the un-fuzzy index-adjusted dataset is used as features for input,(2)the accuracy of the extreme random forest and the accuracy of the multigranular cascade forest are improved by using the fuzzy index-adjusted dataset as features for input,(3)the accuracy of the fuzzy index-adjusted dataset as features for inputting the extreme random forest is improved by 18.89% compared to that of the un-fuzzy index-adjusted dataset as features for inputting the extreme random forest and(4)the average accuracy of the fuzzy index-adjusted dataset as features for inputting multi-grain cascade forest increased by 5.67%.

Rare-earth element geochemistry reveals the provenance of sediments on the southwestern margin of the Challenger Deep

The hadal zone represents one of the last great frontiers in modern marine science,and deciphering the provenance of sediment that is supplied to these trench settings remains a largely unanswered question.Here,we examine the mineralogical and geochemical composition of a sediment core(core CD-1)that was recovered from the southwestern margin of the Challenger Deep within the Mariana Trench.Major element abundances and rare-earth element patterns from these sediments require inputs from both terrigenous dust and locally sourced volcanic debris.We exploit a two-endmember mixing model to demonstrate that locally sourced volcanic material dominates the sediment supply to the Challenger Deep(averaging^72%).The remainder,however,is supplied by aeolian dust(averaging^28%),which is consistent with adjacent studies that utilized Sr-Nd isotopic data.Building on a growing database,we strengthen our understanding of Asian aeolian dust input into the northwestern Pacific,which ultimately improves our appreciation of sedimentation in,and around,the hadal zone.