基于神经网络的东北地区秸秆焚烧预测

选取农作物秸秆露天燃烧严重的东北地区,采用人工神经网络的方法,结合卫星火点和气象数据,开展秸秆露天燃烧预测研究.结果表明：人工神经网络预测模型成功验证了松嫩平原地区2015年10月25日~11月15日的秸秆露天燃烧情况,其准确度为67.1%,经过多次试验,在神经网络建模与验证数据配比为80：20时,预测准确度最高,可达69.7%,同时该模型的稳定性较好.而对不同区域,不同时间段的预测研究表明,人工神经网络较适用于长时间序列的预测.就影响因素而言,相对湿度是影响秸秆露天燃烧的最重要因素.本研究结果可为空气质量模式提供火点预测数据,提高其预报预警能力,为区域联防联控政策的制定提供科技支持.     

小麦产量的遥感动态预估研究──以山东禹城县为例

本文利用现代遥感信息、数理统计和回归分析方法，研究了禹城县试验区的小麦单产与卫星遥感信息（绿度）间的关系，并建立了小麦单产与绿度关系的预估模型；阐述了直接利用遥感宏观信息动态预估小麦产量的可行性和这一方法的应用前景。     

探讨影响赤潮的物理因子及其预报

通过多年对广东沿海港湾赤潮发生机理的探讨 ,归纳出引发赤潮的主要物理因子 ,并深入研究潮汐变化与赤潮形成的关系。作者认为在沿海一些半封闭的海湾 ,在月赤纬偏小期间发生大潮易引发赤潮。大亚湾澳头水域 4～ 5月份大潮后多呈现不正规全日潮 ,易出现赤潮生物高峰期 ,较明显的赤潮从发生至消退的全过程往往跨越一个潮水期。根据实践经验总结 ,作者提出利用潮汐变化规律对大亚湾澳头水域 2 0 0 1年 5月份可能出现的赤潮初始阶段作尝试性预测 ,并在赤潮初始阶段通过对水域的浮游生物优势种和当地天气的变化趋势加强观测、研究 ,希望能对赤潮暴发作出较准确的预报。     

Adaptations to the dynamics of rural water supply from natural sources: A village example in semi-arid Nigeria

Domestic and agro-economic activities in the semi-arid region of Nigeria rely exclusively on rainfall, streamflow and groundwater in deep and alluvial (fadama) aquifers. Such water supply systems are subject to considerable seasonal and inter-annual variability. However, a combination of the various sources may mitigate the effects of water scarcity. This study describes the dynamics of the water sources for a village in northeastern Nigeria as an example that demonstrates the linkages between rainfall, streamflow and groundwater. Such linkages are important for developing strategies to mitigate the effects of climatic variation. Long-term records of rainfall were not available at the site so that the short-term data was interpreted in the context of the long-term climatic experience of the region. The stratigraphic profile of the aquifer was developed from resistivity methods, to supplement information obtained from well level hydrographs. Field observations and analysis of the data reveal that the beginning of the rainy season is a precarious period because none of the water sources are reliable. Rainfall infiltration recharges the shallow aquifers while lateral water flux from the floodwater-saturated fadama also contributes to water level rises in the deep wells. A study of the water level changes in response to deepening of the wells suggests that the wells are fed by an assortment of water-bearing lenses, separated by layers of low transmissivity. One major finding of this study is that there exists a close association between the wells in this riparian community and the recharge processes within the fadama. Upstream diversion, abstraction or impoundment could therefore undermine the viability of aquifer exploitation by the communities in the riparian zone. Analysis of the interactions among the various sources of water leads to the identification of several potential adaptation strategies for confronting the problem of water scarcity.     

灰色生长曲线与万元产值废水量预测

基于ＧＩＭ（１）灰色线性幂函数曲线，研究开发出ＧＰＭ（１）这一新的灰色生长曲线，并建立了ＧＰＭ（１）简捷的参数辨别方法。研究表明，ＧＰＭ（１）概念明确，结论可信，精度令人满意，比传统的皮尔生长曲线在应用上有着更大的优越性。为具有生长规律的非线性灰色环境系统的分析、预测和决策提供了新途径。     

Famine forecasting; Prices and peasant behaviour in Northern Ethiopia

This paper, completed in January 1984, begins by briefly outlining the contrasting views of price behaviour during the last Ethiopian famine (1972–1974) put forward by Seaman and Holt (1980) and Sen (1981). A hypothesis is developed to account for peasant behaviour and price responses under developing famine conditions. This is then tested with data recently made available. The paper concludes by summarizing the findings and their implications for famine forecasting, and argues that famine conditions in Northern Ethiopia are likely to worsen during 1984.     

PREDICTIVE MODEL FOR NITRATE LOAD IN THE BULL RUN WATERSHED,OREGON1

ABSTRACT: Predictive models for nitrate in four streams in the Bull Run Watershed in the Cascade Mountains of Oregon were developed from a record of 17 years of nitrate samples. The models are time series regression models written in terms of Log(nitrate load). The independent variables are logarithm of 14-day mean daily stream discharge, current day's precipitation, logarithm of the previous day's precipitation, total precipitation for the previous seven days, a hydrograph position variable that indicates rising or falling limb, and average maximum air temperature for the preceding 14 days. The models describe annual cycle and seasonable trends and variations in nitrate load, but are unable to describe large day to day variations like those associated with hydrograph peaks.     

提高洪水智能预报中洪峰预报精度方法的研究

针对防洪减灾的实际需要,对如何提高智能网络对洪峰的预报精度问题进行了深入系统的研究,提出了峰值放大修正系数和遗传算法优化网络初始权重相结合的改进算法,历史资料的检验结果表明了这些改进策略的有效性和可靠性.     

BASIN SCALE WATER MANAGEMENT AND FORECASTING USING ARTIFICIAL NEURAL NETWORKS1

ABSTRACT: Water scarcity in the Sevier River Basin in south‐central Utah has led water managers to seek advanced techniques for identifying optimal forecasting and management measures. To more efficiently use the limited quantity of water in the basin, better methods for control and forecasting are imperative. Basin scale management requires advanced forecasts of the availability of water. Information about long term water availability is important for decision making in terms of how much land to plant and what crops to grow; advanced daily predictions of streamflows and hydraulic characteristics of irrigation canals are of importance for managing water delivery and reservoir releases; and hourly forecasts of flows in tributary streams to account for diurnal fluctuations are vital to more precisely meet the day‐to‐day expectations of downstream farmers. A priori streamflow information and exogenous climate data have been used to predict future streamflows and required reservoir releases at different timescales. Data on snow water equivalent, sea surface temperatures, temperature, total solar radiation, and precipitation are fused by applying artificial neural networks to enhance long term and real time basin scale water management information. This approach has not previously been used in water resources management at the basin‐scale and could be valuable to water users in semi‐arid areas to more efficiently utilize and manage scarce water resources.     

SUMMER LOW FLOWS IN NEW ENGLAND DURING THE 20TH CENTURY1

ABSTRACT: High springtime river flows came earlier by one to two weeks in large parts of northern New England during the 20th Century. In this study it was hypothesized that late spring/early summer recessional flows and late summer/early fall low flows could also be occurring earlier. This could result in a longer period of low flow recession and a decrease in the magnitude of low flows. To test this hypothesis, variations over time in the magnitude and timing of low flows were analyzed. To help understand the relation between low flows and climatic variables in New England, low flows were correlated with air temperatures and precipitation. Analysis of data from 23 rural, unregulated rivers across New England indicated little evidence of consistent changes in the timing or magnitude of late summer/early fall low flows during the 20th Century. The interannual variability in the timing and magnitude of the low flows in northern New England was explained much more by the interannual variability in precipitation than by the interannual variability of air temperatures. The highest correlation between the magnitude of the low flows and air temperatures was with May through November temperatures (r =?0.37, p= 0.0017), while the highest correlation with precipitation was with July through August precipitation (r = 0.67, p > 0.0001).