关键词： 小推力   变比冲   轨迹优化   机器学习   间接法  

摘要： 针对变比冲小推力轨迹间接优化中的协态变量初值猜测问题,提出了一种基于机器学习的协态变量初值高精度高效估计方法。首先,基于标称最优轨迹延拓,建立了状态量边值高扰动上限情形下的数据集生成方法,并分析了扰动上限对求解效率的影响。然后,构建了基于位置速度、轨道根数和改进春分点轨道根数多形式状态量组合输入的人工神经网络(ANN)映射关系,分析并优化了神经网络结构。将提出的方法应用于深空探测小推力转移场景,仿真结果表明该方法相对于标称轨迹直接扰动的数据集生成方法及单一形式状态量输入的人工神经网络映射方法,均有效地提升了求解收敛率,能够高效高精度地估计协态变量初值,实现轨迹快速优化。

关键词： bare soil   deep machine learning   neural networks   soil degradation  

摘要： The detection of degraded soil distribution areas is an urgent task. It is difficult and very time consuming to solve this problem using ground methods. The modeling of degradation processes based on digital elevation models makes it possible to construct maps of potential degradation, which may differ from the actual spatial distribution of degradation. The use of remote sensing data (RSD) for soil degradation detection is very widespread. Most often, vegetation indices (indicative botany) have been used for this purpose. In this paper, we propose a method for constructing soil maps based on a multi-temporal analysis of the bare soil surface (BSS). It is an alternative method to the use of vegetation indices. The detection of the bare soil surface was carried out using the spectral neighborhood of the soil line (SNSL) technology. For the automatic recognition of BSS on each RSD image, computer vision based on deep machine learning (neural networks) was used. A dataset of 244 BSS distribution masks on 244 Landsat 4, 5, 7, and 8 scenes over 37 years was developed. Half of the dataset was used as a training sample (Landsat path/row 173/028). The other half was used as a test sample (Landsat path/row 174/027). Binary masks were sufficient for recognition. For each RSD pixel, value "1" was set when determining the BSS. In the absence of BSS, value "0" was set. The accuracy of the machine prediction of the presence of BSS was 75%. The detection of degradation was based on the average long-term spectral characteristics of the RED and NIR bands. The coefficient C-mean, which is the distance of the point with the average long-term values of RED and NIR from the origin of the spectral plane RED/NIR, was calculated as an integral characteristic of the mean long-term values. Higher long-term average values of spectral brightness served as indicators of the spread of soil degradation. To test the method of constructing soil degradation maps based on deep machine learning, an ac

关键词： hyperspectral   alpine grassland   above-ground biomass   machine learning   feature selection   interpretability  

摘要： Above-ground biomass (AGB) is a key indicator for studying grassland productivity and evaluating carbon sequestration capacity;it is also a key area of interest in hyperspectral ecological remote sensing. In this study, we use data from a typical alpine meadow in the Qinghai-Tibet Plateau during the main growing season (July-September), compare the results of various feature selection algorithms to extract an optimal subset of spectral variables, and use machine learning methods and data mining techniques to build an AGB prediction model and realize the optimal inversion of above-ground grassland biomass. The results show that the Lasso and RFE_SVM band filtering machine learning models can effectively select the global optimal feature and improve the prediction effect of the model. The analysis also compares the support vector machine (SVM), least squares regression boosting (LSB), and Gaussian process regression (GPR) AGB inversion models;our findings show that the results of the three models are similar, with the GPR machine learning model achieving the best outcomes. In addition, through the analysis of different data combinations, it is found that the accuracy of AGB inversion can be significantly improved by combining the spectral characteristics with the growing season. Finally, by constructing a machine learning interpretable model to analyze the specific role of features, it was found that the same band plays different roles in different records, and the related results can provide a scientific basis for the research of grassland resource monitoring and estimation.

关键词： cell marker genes   gene expression   machine learning   root development   single-cell genomics   single-cell sequencing  

摘要： An essential step in the analysis of single-cell RNA sequencing data is to classify cells into specific cell types using marker genes. In this study, we have developed a machine learning pipeline called single-cell predictive marker (SPmarker) to identify novel cell-type marker genes in the Arabidopsis root. Unlike traditional approaches, our method uses interpretable machine learning models to select marker genes. We have demonstrated that our method can: assign cell types based on cells that were labelled using published methods;project cell types identified by trajectory analysis from one data set to other data sets;and assign cell types based on internal GFP markers. Using SPmarker, we have identified hundreds of new marker genes that were not identified before. As compared to known marker genes, the new marker genes have more orthologous genes identifiable in the corresponding rice single-cell clusters. The new root hair marker genes also include 172 genes with orthologs expressed in root hair cells in five non-Arabidopsis species, which expands the number of marker genes for this cell type by 35-154%. Our results represent a new approach to identifying cell-type marker genes from scRNA-seq data and pave the way for cross-species mapping of scRNA-seq data in plants.

关键词： Ultrasound directed self-assembly   Machine learning   polymer-matrix composites (PMCs)   Particle-reinforced composites   Electrical properties   3-D printing  

摘要： Engineered polymer matrix composite materials with designer electrical properties are important for a myriad of engineering applications including flexible actuators and wearable sensors. We use stereolithography in combination with ultrasound directed self-assembly to align electrically conductive microfibers in a photopolymer matrix. We relate the fabrication process parameters to the resulting filler material alignment and corresponding electrical conductivity using supervised machine learning methods and quantify the prediction accuracy of data-driven models derived from different interpretable and non-interpretable algorithms. We determine that decision tree and artificial neural network algorithms result in data-driven models with R-2 scores that are 79.8% and 83.2% higher, respectively, than a traditional multivariate regression analysis benchmark model in predicting the microfiber alignment. Similarly, random forest and artificial neural network algorithms result in data-driven models that predict composite material electrical conductivity 9.1% and 13.7% more accurately, respectively, than a logistic multivariate regression benchmark model. Relating the fabrication process parameters to the resulting electrical conductivity of the material is a crucial step towards fabricating polymer matrix composite materials with designer electrical properties for use in engineering applications.

关键词： 状态监测   分类算法   机器学习   减振器故障   悬挂元件  

摘要： 状态修利用数据采集、数据处理和决策分析,并根据部件的实际状态安排维修计划。采用状态修技术可以提高铁路系统的可靠性。本文针对不同运行工况下一系悬挂和二系悬挂系统减振器性能已经衰减的轨道车辆进行了仿真分析,生成了一个大型仿真数据库,并用于训练和测试分类算法,以检测面临的减振器故障。把车体、转向架构架和轮对的加速度计信号之间的频率响应函数作为故障指标和预测根据,并提供给分类算法。研究结果表明,1-紧邻分类器和线性支持向量机分类器对减振器性能衰减的预判均具有较高的分类能力。

关键词： 机器学习   夏季降水   预测  

摘要： 利用湖南97个国家站的逐月降水资料、国家气候中心130项气候指数集以及国家气候中心和美国国家环境预报中心两套季节预测模式的降水预测资料,采用递归特征消除法确定预测因子并使用多层前馈神经网络、支持向量回归和自然梯度提升三种算法建立了两种湖南夏季降水统计预测方案的模型,检验了预测效果。结果表明:基于机器学习的预测模型对湖南夏季雨型分布有较好的预测能力,两种统计方案提前1~6 mon起报的夏季降水平均距平相关系数分别为0.15和0.19,相比于NCEP和NCC模式有较大提升,平均PS评分分别为69.3和69.2,高于NCC模式的63.1,略低于NCEP模式的71.5;进一步分析表明,3—5月起报的机器学习模型的预测技巧可能来源于前冬极地和中高纬环流,12—2月起报的模型预测技巧则可能来自海温的前兆信号。

关键词： 碳价预测   Transformers模型   CEEMDAN模型   湖北碳市场  

摘要： 碳价是碳排放权交易市场的核心要素,对碳价的准确预测有助于政府科学制定碳市场政策;也有利于企业在碳市场中的有效决策,实现碳减排成本的最小化。本文基于CEEMDAN和Transformers模型提出一种全新的碳价预测方法,首先,从理论层面分析了影响碳价预测的主要因素,并运用皮尔森相关系数法识别出影响湖北碳价的关键因素;其次,考虑到碳价序列具有的非线性、非平稳性和多尺度特征,运用CEEMDAN模型对湖北碳价原始序列进行分解,得到7个子序列;最后,运用Transformers模型对7个碳价子序列分别进行预测,并将预测结果进行叠加,从而得到湖北碳价的最终预测结果。预测结果表明:运用该方法对湖北碳价预测的MAPE值为1.67%,是所有对比模型中预测效果最好的。基于此,要关注影响碳价的关键因素,建立碳价预测体系、开发碳价预测工具,科学设定碳配额量。

关键词： 区域性自由贸易协定   双边贸易流量   FTA深度   机器学习   XGBOOST  

摘要： 区域性贸易深度一体化是当前世界经济贸易发展的主要趋势,区域性自由贸易协定(FTA)的签订与重订是这一趋势的重要表现形式。为量化区域贸易协定对双边贸易流量的影响,区别于普遍用于外贸领域的引力模型,本文分别采用机器学习领域中的树模型XGBOOST与线性模型Ridge,选择FTA深度指标作为衡量FTA异质性的核心变量,添加协议签订国GDP等变量,对于协议生效3年内的双边贸易流量建立预测模型,探究机器学习模型在外贸领域的可用性。实证结果显示,XGBOOST模型在双边贸易流量的预测上取得了较好结果。贸易国间的双边贸易流量越大,预测结果越精准,对双边贸易流量在十亿美元以上、协议生效第一年的贸易,预测的平均绝对百分比误差约为0.077。因此,本文得到结论,机器学习模型在外贸领域中有较强的可用性,而且树模型的效果较优。

关键词： SOFM神经网络   需求模式识别   动态预测   航空消耗件  

摘要： 企业状态不稳定性、消耗件故障规律不确定性及需求特征的动态性,特别是新冠疫情期间航空公司航班的大量停飞和逐渐恢复导致固定单一需求预测方法存在较大偏差。基于平均绝对误差和均方误差进行不同需求模式预测方法筛选,构建自组织特征映射网(self-organizing feature map,SOFM)对需求时间序列聚类,提出不同聚类模式和预测方法映射关系并实现数据与方法动态自适应。此自适应预测框架能够实现不同航材需求模式识别、多预测方法决策及同一航材多阶段动态预测。通过某航空公司实例验证表明该自适应框架具有较好的应用效果,适用于各类型的消耗备件需求预测。