支持向量机在海洋随机资料分析中的应用

在随机海洋资料的分析中,需要从大量的实际数据中提取出有用的信息来建立或检验各种海洋理论模型,因此我们要正确运用适当的手段来分析处理各种实际数据。文中简要介绍了数据挖掘中一项新的技术支持向量机,着重介绍了最优化问题的求解算法,以及如何应用于海洋资料的分析处理。     

中国碳强度关键影响因子的机器学习识别及其演进

碳强度影响因子数量众多,通过在众多因子中评估其重要性以识别出关键影响因子进而解析碳强度关键因子的变化规律,是中国2030年碳强度能否实现比2005年下降60%~65%目标的科学基础。传统的回归分析方法对于评估众多因子的重要性存在多重共线性等问题,而机器学习处理海量数据则具有较好的稳健性等优点。本文从能源结构、产业结构、技术进步和居民消费等方面选取了56个中国碳强度影响因子指标,采用随机森林算法基于信息熵评估了1980-2014年逐年各项因子的重要性,通过指标数量与信息熵的对应关系统一筛选出每年重要性最大的前22个指标作为相应年度关键影响因子,最终依据关键影响因子的变化趋势划分了3个阶段作了演进分析。结果发现：1980-1991年,碳强度的关键因子主要以高耗能产业规模及占比、化石能源占比和技术进步为主;1992-2007年,中国经济进入快车道增长时期,服务业占比和化石能源价格对碳强度的影响作用开始显现,居民传统消费的影响作用在增大;2008年全球金融危机后,中国进入经济结构深化调整时期,节能减排力度大大增强,新能源占比和居民新兴消费的影响作用迅速显现。为实现2030年碳强度下降60%~65%目标,优化能源结构和产业结构,促进技术进步,提倡绿色消费,强化政策调控是未来需要采取的主要措施。     

基于EEMD和ARIMA的海温预测模型研究

类型丰富、时空分辨率高的海洋探测数据,为信号分解和机器学习算法的应用提供了可能。本文针对如何建立有效的海温预测模型这一问题,使用高时空分辨率的海表温度(SST)融合产品,引入信号处理领域的集合经验模态分解(EEMD)和机器学习领域的自回归积分滑动平均模型(ARIMA)。首先利用最适于分解自然信号的EEMD方法,将海温数据分解成多个确定频率的序列;再利用ARIMA分别对各个频率的序列进行预测,最后将各个序列的预测结果进行组合。该方法在丰富数据的支撑下,比以往直接使用海温数据所建立的预测模型精度更高,为更好地进行海温预测提供了新方法。     

结合主动学习和词袋模型的高分二号遥感影像自动化分类

高分卫星遥感影像空间分辨率的提高,使得地物的光谱和纹理变得更加丰富和复杂,这给遥感影像的自动化分类带来严重挑战。因此,本文提出了一种结合主动学习和词袋模型的高分二号遥感影像分类方法。首先,对研究区域进行多尺度分割,建立影像分割对象集;然后,采用词袋模型构建影像对象的语义特征向量;最后,充分考虑位于分类边界的不确定性样本分布,迭代选择最优样本用于训练支持向量机,用于分类遥感影像。为了验证本文方法的有效性和稳健性,以山东省某市的高分二号遥感影像为试验数据进行了试验分析。结果表明,本文提出的方法可以有效地将研究区域分为水体、地面、植被和建筑物四类,正确率达到90.6%以上。     

A novel spatial index using spatial analyses and hierarchical fuzzy expert system for obtaining green TOD: a case study in Tehran city

Sustainable development is a vital and challenging factor for managing urban growth smartly. This factor contains three main components, namely economic growth, ecological protection and social justice. Green Transit-Oriented Development (GTOD) is a consummate planning approach in line with those components. Implementation of GTOD in an urban area is underpinned by its quantification. Therefore, a quantitative spatial index based on several indicators related to TOD and Green urbanism concepts should be developed. In this study, Geo-spatial Information Science and hierarchical fuzzy inference system (HFIS) were employed to calculate the indicators and aggregate them, respectively. In order to showcase the feasibility of the proposed method, it was implemented in a case study area in the City of Tehran, Iran. The result of this method is an integrated spatial GTOD index, which measures the neighbourhoods’ GTOD levels. These measurements specify weaknesses and strengths of neighbourhoods’ factors. Therefore, this index helps decision-makers to plan neighbourhoods based on land use and public transit views. Additionally, the HFIS method helps decision-makers to consider criteria and indicators with their inherent uncertainties and aggregate them with much fewer rules. For evaluating the results, the developed GTOD index was assessed with municipal action planning and attraction maps. According to the outcomes of the assessment, it is concluded that the proposed method is adequately robust and efficient for smart and sustainable urban planning.     

Building a model-based personalised recommendation approach for tourist attractions from geotagged social media data

When travelling, people are accustomed to taking and uploading photos on social media websites, which has led to the accumulation of huge numbers of geotagged photos. Combined with multisource information (e.g. weather, transportation, or textual information), these geotagged photos could help us in constructing user preference profiles at a high level of detail. Therefore, using these geotagged photos, we built a personalised recommendation system to provide attraction recommendations that match a user's preferences. Specifically, we retrieved a geotagged photo collection from the public API for Flickr (Flickr.com) and fetched a large amount of other contextual information to rebuild a user's travel history. We then created a model-based recommendation method with a two-stage architecture that consists of candidate generation (the matching process) and candidate ranking. In the matching process, we used a support vector machine model that was modified for multiclass classification to generate the candidate list. In addition, we used a gradient boosting regression tree to score each candidate and rerank the list. Finally, we evaluated our recommendation results with respect to accuracy and ranking ability. Compared with widely used memory-based methods, our proposed method performs significantly better in the cold-start situation and when mining ‘long-tail’ data.     

梅雨降水季节预测的多方法比较

基于1961—2000年逐月降水观测资料和全球大气再分析资料,分析了6—7月长江中下游(108°～123°E,27°～33°N)梅雨的时空分布特征。通过观测诊断和数值试验确定了影响梅雨异常偏多的3个前期因子:4—5月平均的西北太平洋海平面气压正异常;3月至5月北大西洋海平面气压负变压倾向;1月至4月西伯利亚的2 m温度负倾向。利用这3个具有物理意义的影响因子构建了梅雨季节预测模型,该模型在训练期(1961—2000年)和独立预测期(2001—2022年)均具有显著的预测技巧(相关系数分别为0.79和0.77,均方根误差分别为0.59和0.68)。同时,基于相似的潜在预测因子,对比了利用偏最小二乘回归方法和5种机器学习方法(随机森林、轻量级梯度提升机、自适应提升、类别型特征提升、极端梯度提升)建立的预测模型的技巧。虽然训练期(1961—2000年)偏最小二乘回归和机器学习建模拟合效果更高,但在独立预测期(2001—2022年)上述模型的预测技巧显著降低(相关系数均低于0.44,均方根误差均大于0.93),出现了明显的过拟合问题。本研究强调梅雨的短期气候预测应建立在物理机制基础之上,而使用机器学习方法需谨慎。     

Landslide susceptibility modeling based on ANFIS with teaching-learning-based optimization and Satin bowerbird optimizer

As threats of landslide hazards have become gradually more severe in recent decades,studies on landslide prevention and mitigation have attracted widespread attention in relevant domains.A hot research topic has been the ability to predict landslide susceptibility,which can be used to design schemes of land exploitation and urban development in mountainous areas.In this study,the teaching-learning-based optimization(TLBO)and satin bowerbird optimizer(SBO)algorithms were applied to optimize the adaptive neuro-fuzzy inference system(ANFIS)model for landslide susceptibility mapping.In the study area,152 landslides were identified and randomly divided into two groups as training(70%)and validation(30%)dataset.Additionally,a total of fifteen landslide influencing factors were selected.The relative importance and weights of various influencing factors were determined using the step-wise weight assessment ratio analysis(SWARA)method.Finally,the comprehensive performance of the two models was validated and compared using various indexes,such as the root mean square error(RMSE),processing time,convergence,and area under receiver operating characteristic curves(AUROC).The results demonstrated that the AUROC values of the ANFIS,ANFIS-TLBO and ANFIS-SBO models with the training data were 0.808,0.785 and 0.755,respectively.In terms of the validation dataset,the ANFISSBO model exhibited a higher AUROC value of 0.781,while the AUROC value of the ANFIS-TLBO and ANFIS models were 0.749 and 0.681,respectively.Moreover,the ANFIS-SBO model showed lower RMSE values for the validation dataset,indicating that the SBO algorithm had a better optimization capability.Meanwhile,the processing time and convergence of the ANFIS-SBO model were far superior to those of the ANFIS-TLBO model.Therefore,both the ensemble models proposed in this paper can generate adequate results,and the ANFIS-SBO model is recommended as the more suitable model for landslide susceptibility assessment in the study area considered due to its excellent accuracy and efficiency.     

基于谱聚类算法的海底滑坡危险性评价

海底滑坡的危险性评价与分区,对海洋工程设施的选址和危险预防具有指导作用.本文基于无监督机器学习的谱聚类算法对黄河口埕岛海域展开了海底滑坡危险性评价,构建了输入参数为9、输出类别为4、核函数参数为0.08的海底滑坡危险性评价模型.使用该模型进行评价,将研究区分为了海底滑坡危险性高、较高、较低和低的区域.评价结果与地质环境...     

人工智能在飞机颠簸预报中的应用进展及未来趋势展望

飞机颠簸对飞机运行安全及旅客舒适度具有很大危害,提高飞机颠簸的预报准确率对于减轻人员伤害和财产损失具有重要意义,且一直是航空气象研究的重点领域。随着观测手段的丰富和科学技术的进步,飞机颠簸预报也取得了长足发展。本文首先从定性预报和定量预报的角度对国内外飞机颠簸预报的主要方法,特别是人工智能(AI)方法在其中的最新应用进行了综述。在此基础上,归纳总结出AI用于飞机湍流预报存在的主要问题和未来的重点研究方向：1)飞机实况数据的开放共享以及多源湍流数据的融合构建问题;2)基于人工智能构建飞机颠簸预报模型的可解释性及物理机制问题;3)基于人工智能构建飞机颠簸的集合预报问题。最后,提出了气象领域未来第三代人工智能的发展思路。