长江防洪决策支持系统——防洪知识库系统

防洪决策是一项十分复杂的决策性思维活动,它不仅需要大量数据型信息的支持,而且还需要大量文档型信息的支持.在分析防洪决策全过程对各种文档信息需求的基础上,广泛收集各种有关文档资料,经过整理分类,确立了防洪知识库的信息组织体系,然后在Windows系统下,利用它的联机帮助系统,通过创建帮助文件的方式建立了长江防洪知识库系统.该系统具有用户界面友好直观,操作简便,可为防洪决策者提供方便快捷的文档信息支持.     

美军数字化战场剖析及对我军测绘保障发展的几点认识

本文剖析了美军数字化部队和数字化战场的内涵，阐述了对发展我军测绘保障的一些认识。     

典型类比分析法的原理与实践

本文以我国隧道工程应用新奥法的典型工程经验和原位测试资料为基础,综合应用系统科学、工程地质力学和岩石力学方法,阐述在隧道工程锚喷支护设计与施工中,普及应用围岩稳定分析预测技术的原理和方法典型类比分析法的提出、原理框架与工程验证。     

Monthly suspended sediment load prediction using artificial intelligence: testing of a new random subspace method

ABSTRACT

The predictive capability of a new artificial intelligence method, random subspace (RS), for the prediction of suspended sediment load in rivers was compared with commonly used methods: random forest (RF) and two support vector machine (SVM) models using a radial basis function kernel (SVM-RBF) and a normalized polynomial kernel (SVM-NPK). Using river discharge, rainfall and river stage data from the Haraz River, Iran, the results revealed: (a) the RS model provided a superior predictive accuracy (NSE = 0.83) to SVM-RBF (NSE = 0.80), SVM-NPK (NSE = 0.78) and RF (NSE = 0.68), corresponding to very good, good, satisfactory and unsatisfactory accuracies in load prediction; (b) the RBF kernel outperformed the NPK kernel; (c) the predictive capability was most sensitive to gamma and epsilon in SVM models, maximum depth of a tree and the number of features in RF models, classifier type, number of trees and subspace size in RS models; and (d) suspended sediment loads were most closely correlated with river discharge (PCC = 0.76). Overall, the results show that RS models have great potential in data poor watersheds, such as that studied here, to produce strong predictions of suspended load based on monthly records of river discharge, rainfall depth and river stage alone.     

A minimalistic approach for evapotranspiration estimation using the Prophet model

ABSTRACT

This study aimed to evaluate the potential of the recently introduced Prophet model for estimating reference evapotranspiration (ETo). A comparative study was conducted for benchmarking the model results with support vector regression (SVR) and temperature-based empirical models (Thornthwaite and Hargreaves) in southern Japan. The performance of the Prophet, SVR and temperature-based empirical models was evaluated by Nash–Sutcliffe efficiency (NSE) and coefficient of determination (R²). The results indicate that temperature-based Prophet and SVR models have greater accuracy than the empirical models. The Prophet model with sole input of relative humidity, sunshine hours or windspeed showed acceptable accuracy (NSE > 0.80; R² > 0.80), while SVR models with similar inputs showed greater errors. Accuracy improved with increasing number of input parameters, giving excellent performance (NSE > 0.95; R² > 0.95) with all input parameters. Hence, the Prophet model is a new promising approach for modelling ETo with limited input variables.     

Multi-scale remote sensing to support insurance policies in agriculture: from mid-term to instantaneous deductions

ABSTRACT

Climate change is today one of the biggest issues for farmers. The increasing number of natural disasters and change of seasonal trends is making insurance companies more interested in new technologies that can somehow support them in quantifying and mapping risks. Remotely sensed data, with special focus on free ones, can certainly provide the most of information they need, making possible to better calibrate insurance fees in space and time. In this work, a prototype of service based on free remotely sensed data is proposed with the aim of supporting insurance companies’ strategies. The service is thought to calibrate annual insurance rates, longing for their reduction at such level that new customers could be attracted. The study moves from the entire Piemonte region (NW Italy), to specifically focus onto the Cuneo province (Southern Piemonte), which is mainly devoted to agriculture. MODIS MOD13Q1-v6 and Sentinel-2 L2A image time series were jointly used. NDVI maps from MODIS data were useful to describe the midterm phenological trends of main crops at regional level in the period 2000–2018; differently, Sentinel-2 data permitted to map local crop differences at field level in 2016 and 2017 years. With reference to MODIS data, the average phenological behavior of main crop classes in the area, obtained from the CORINE Land Cover map Level 3, was considered using a time series decomposition approach. Trend analyses showed that the most of the crop classes alternated three phases (about 7 years) suggesting that, presently, this is probably the time horizon to be considered to tune mid-term algorithms for risk estimates in the agricultural context. Crop classes trends were consequently split into three phases and each of them modeled by a first-order polynomial function used to update correspondent insurance risk rate. Sentinel-2 data were used to map phenological anomalies at field level for the 2016 and 2017 growing seasons; shifts from class average behavior were considered to locally and temporarily tune insurance premium around its average trend as described at the previous step. Synthesizing, one can say that this approach, integrating MODIS and Sentnel-2 data, makes possible to locally and temporarily calibrate premiums of indexed insurance policies by describing the average trends of crop performance (NDVI) at regional level by MODIS data and refining it at field and specific crop level by Sentinel-2 data.     

高应力区破裂岩体回采巷道一次强化支护技术及其应用研究

基于对高应力区破裂岩体回采巷道支护 10多年的经验和教训 ,本文首次提出了相对于主次承载区协调作用关系的关键支护技术 ,即一次强化支护技术。该支护技术不仅强调了对于高应力区破裂岩巷道支护时间的及时性 ,支护强度一次到位 ,更重要的是区别于先让后抗、二次支护的指导思想 ;同时 ,一次强化支护技术还详细明确了支护类型、支护结构以及施工工艺。该支护技术在小官庄铁矿高应力区的应用成功 ,表明该支护关键技术是正确的。     

基于支撑向量回归的高光谱混合像元非线性分解

提出了基于支撑向量回归的高光谱混合像元自动分解.首先利用投影迭代的方法自动寻找到影像的典型地物光谱,然后利用Hapke近似函数模拟出非线性的训练和测试数据.支撑向量回归的混合像元分解方法与基于基函数分解方法的不同点是不需要预先确定非线性的映射形式,它通过核函数,把像元矢量从低维空间映射到高维特征空间,使得在特征空间中构造的线性光谱组合对应着原始空间（像元空间）的非线性组合特性,从而揭示了典型地物光谱之间的高阶性质,提高了混合像元的分解精度.实验结果证明,这种方法具有很高的混合像元的分解精度.利用模拟数据作分解精度的评价,表明97%以上的像元分解绝对误差不大于10%,而各类总体平均平方根误差均小于3.5%.     

基于支撑向量机概率输出的高光谱影像混合像元分解

提出利用支撑向量机（SVM）后验概率来分解高光谱影像的混合像元，通过支撑向量机的输出值转化为两两配对的后验概率，再由两两配对的概率值求得多类后验概率，并以像元所属类别的后验概率作为地物的组分信息。实验结果表明，该方法能较好地估计出混合像元的组分比。     

使用SVM进行短期气候预测的应用试验

从气象角度介绍了利用SVM方法的预报原理,对西安短期气候预测做了实验,并分析预报结果,得出SVM方法在天气预报领域有一定的使用空间的结论。