The non-agricultural economy in post-socialist rural Romania: The insights and perceptions of national, regional and local institutions

This study evaluates some aspects of the socio-economic transformation of rural Romania with reference to the views of representative organisations (at national, regional and local levels) and other experts. Interviews conducted in ten communes of nine Romanian counties (‘judete’) focus attention on the advantages and disadvantages of system change experienced since 1989; the most important problems and constraints for future socio-economic change; and appropriate policies and perspectives for development in the immediate future. Wherever appropriate the claims of interviewees are substantiated through reference to statistics, drawn in many cases from Chambers of Commerce & Industry (CCI). Local level representatives presented much more negative views on recent change than their national and regional level counterparts, but all agreed on the crucial problem of capital shortage. Thus while specific programmes to assist rural areas are justified, they cannot fully succeed until the national economy is able to grow more rapidly and attract greater foreign investment. This revised version was published online in July 2006 with corrections to the Cover Date.     

The role of moral economy in two British Columbia fisheries: Confronting neoliberal policies

What have been the moral values and practices allowing equitable economic opportunities and a sense of fairness in North American small-scale fisheries? How have these “moral economies” been affected by neoliberal policies with their emphasis on efficiency, rational self-interest, and wealth accumulation? Focusing especially on the salmon and halibut fisheries in British Columbia, Canada, this discussion summarizes key findings on the manner in which small-scale fisheries and their moral practices tend to be marginalized and undervalued under neoliberal regimes. The paper considers the value of these moral economies for promoting social, economic, and ecological welfare as grounds for the expansion of small-scale fisheries.     

A comparative study of extensive machine learning models for predicting long-term monthly rainfall with an ensemble of climatic and meteorological predictors

Rainfall prediction is of vital importance in water resources management. Accurate long-term rainfall prediction remains an open and challenging problem. Machine learning techniques, as an increasingly popular approach, provide an attractive alternative to traditional methods. The main objective of this study was to improve the prediction accuracy of machine learning-based methods for monthly rainfall, and to improve the understanding of the role of large-scale climatic variables and local meteorological variables in rainfall prediction. One regression model autoregressive integrated moving average model (ARIMA) and five state-of-the-art machine learning algorithms, including artificial neural networks, support vector machine, random forest (RF), gradient boosting regression, and dual-stage attention-based recurrent neural network, were implemented for monthly rainfall prediction over 25 stations in the East China region. The results showed that the ML models outperformed ARIMA model, and RF relatively outperformed other models. Local meteorological variables, humidity, and sunshine duration, were the most important predictors in improving prediction accuracy. 4-month lagged Western North Pacific Monsoon had higher importance than other large-scale climatic variables. The overall output of rainfall prediction was scalable and could be readily generalized to other regions.     

成人英语学习动机行为调查与教学对策研究

动机是激励人们行动的心理动因.英语学习动机是推动英语学习的内部动因,成人英语学习动机是复杂的.了解他们的英语学习动机特点有利于教师改进教学手段和策略,激发与培养其学习的主动性和积极性,发挥其学习潜能,从而提高英语学习的效果.运用定量研究的方法,在年轻干部学员中进行学习动机调查,分析了其学习动机的特点,并提出成人英语教学的对策.     

基于高清工业相机的盾构隧道裂缝智能识别算法分析

裂缝一直是隧道病害的重点检测对象,但传统人工巡检仅能通过肉眼发现后记录,人工识别精准度与效率完全取决于个人经验判断,无信息化手段辅助,作业效率识别精度亟待提升。针对以上问题,本文借助高清工业相机成像分辨率高、采集速度快等特点,将高清工业相机部署于轨道车上获取隧道表面裂缝病害信息,大幅提高了隧道裂缝识别效率,将识别精度提升至0.2 mm,同时融入优化的Cascade R-CNN算法,在有监督情况下训练隧道裂缝样本,最终实现了隧道裂缝病害的高效提取,同时研发了一套包含硬件数据采集、数据处理软件、数据管理平台的裂缝病害识别路线,真正意义上破除了识别慢、精度低、靠经验、难管理的技术壁垒。     

建筑物立面分类与DIM点云滤波

针对目前基于近景摄影测量方法构建建筑物立面模型过程中因密集影像匹配（DIM）点云噪声所引起的建筑物立面TIN网格模型畸变问题,本文借鉴机器学习中样本学习的思想,对建筑物立面进行了分类并对DIM点云提出了相应的滤波方法,以达到去除DIM点云噪声和改善其TIN网格模型畸变的目的。其中,针对平面结构立面,采取先对点云样本进行学习计算构建数学立面模型所需参数,再对该立面模型设定阈值并对其点云进行滤波处理的方法;针对曲面结构立面,则结合DIM点云特性先将点云样本分类标记归为立面点与非立面点,再进行样本特征值学习,使用Logistic回归算法迭代计算求解最佳回归系数,从而构建滤波分类器的方法对立面点云进行滤波处理。试验结果表明,本文滤波处理方法能将立面DIM点云噪声有效识别并去除,而且使用该方法处理后所得点云构建的建筑物立面TIN网格模型精细化程度得到有效提高,模型质量得到明显改善。     

深度学习PaddlePaddle框架支持下的遥感智能视觉平台研究与实现

百度深度学习PaddlePaddle框架支持下的遥感智能视觉平台,能够运用深度学习技术实现遥感影像的智能建模、训练和解译。本文通过深入分析PaddlePaddle图像分割模型库PaddleSeg的图像处理深度学习算法模型DeepLabV3+、U²-Net及RetinaNet,开发设计了遥感智能视觉平台,实现了遥感影像的地块分割、变化检测和斜框检测等专业功能。研究表明：遥感智能视觉平台提取的图斑总面积是目视解译的80%、有效图斑比例为76%、错误图斑比例为18%,实现了快速有效的遥感图像智能处理。     

深度学习支持下的丘陵山区耕地高分辨率遥感信息分区分层提取方法

耕地是丘陵山区稀缺的土地资源,具有地形条件复杂、种植结构多样的特点,导致了山地耕地信息难以快速、准确获取,并且基于传统的遥感数据及遥感监测方法开展山区耕地信息快速自动提取比较困难。针对这一问题,本文以西南山区贵州省息烽县作为试验区,根据地理空间异质性特征,提出分区控制、分层提取的耕地形态信息提取思路,构建了一种地貌单元约束条件下的分区分层耕地形态信息的提取方法。该方法首先根据地貌-植被特征将试验区划分为平坝区、山坡区、林草区3类地理分区;然后在每类分区基础上,根据耕地所呈现的视觉特征划分为不同的类型,对不同类型的耕地分别设计不同的深度学习模型进行分层提取。试验结果证明,该方法对山区复杂地形背景噪声具有较好的抑制作用,所提取的耕地地块信息相比于传统方法更符合实际耕地的实际分布形态,有效地减少了漏提率和错提率。     

数据驱动的蒸散发遥感反演方法及产品研究进展

蒸散发是水圈、大气圈和生物圈中水分循环和能量交换的纽带。在全球尺度上,蒸散发约占陆地降水总量的60%;作为其能量表达形式,潜热通量约占地表净辐射的80%。随着通量观测技术的发展,全球长期持续的观测数据得以获取和共享,近年来基于数据驱动的蒸散发遥感反演方法取得了较好的研究进展。本文针对数据驱动的蒸散发遥感反演方法和产品,从经验回归、机器学习和数据融合3个方面展开,对现有的研究进展进行了梳理、归纳和总结,并从驱动数据、反演方法、已有产品等方面指出目前仍存在的问题和不足。未来仍需开展数据驱动的高时空分辨率的蒸散发遥感反演方法的研究,有效考虑地表温度和土壤水分等可以指示地表蒸散发短期变化的重要信息,同时加强基于过程驱动的物理模型与数据驱动的模型的结合,使两类模型能互为补充、各自发挥所长,共同推动蒸散发遥感反演研究水平的进步。     

Data selection using support vector regression

Geophysical data sets are growing at an ever-increasing rate, requiring computationally efficient data selection(thinning)methods to preserve essential information. Satellites, such as Wind Sat, provide large data sets for assessing the accuracy and computational efficiency of data selection techniques. A new data thinning technique, based on support vector regression(SVR), is developed and tested. To manage large on-line satellite data streams, observations from Wind Sat are formed into subsets by Voronoi tessellation and then each is thinned by SVR(TSVR). Three experiments are performed. The first confirms the viability of TSVR for a relatively small sample, comparing it to several commonly used data thinning methods(random selection, averaging and Barnes filtering), producing a 10% thinning rate(90% data reduction), low mean absolute errors(MAE) and large correlations with the original data. A second experiment, using a larger dataset, shows TSVR retrievals with MAE < 1 m s-1and correlations 0.98. TSVR was an order of magnitude faster than the commonly used thinning methods. A third experiment applies a two-stage pipeline to TSVR, to accommodate online data. The pipeline subsets reconstruct the wind field with the same accuracy as the second experiment, is an order of magnitude faster than the nonpipeline TSVR. Therefore, pipeline TSVR is two orders of magnitude faster than commonly used thinning methods that ingest the entire data set. This study demonstrates that TSVR pipeline thinning is an accurate and computationally efficient alternative to commonly used data selection techniques.