A quantitative succession model for nine montana forest communities

A quantitative succession model was developed both to meet resource management needs in Montana's Lewis and Clark National Forest and to develop a modeling methodology. It builds upon previous concepts and incudes three new features: quantitative prediction of all tree species and seedlings; quantitative predictions of important understory species; and successional pathways determined by fire intensity and scorch height. The method is described and demonstrated for selected Montana habitat (community) types. It is also available in managerial guidelines and has been programmed as a new module in theforplan simulator. Weaknesses of this and other models are discussed. Conclusions relate succession modeling to resource management needs.     

COMPARISON OF TWO AUTOREGRESSIVE MODELS FOR MONTHLY STREAM FLOW GENERATION1

ABSTRACT: Two autoregressive models for monthly stream flow generation are compared based on the reproduction of the historical record in terms of several important statistics such as the mean, standard deviation, skewness coefficient, correlation coefficient, and the reservoir storage components. In the comparison, both theoretical considerations and practical applications are employed to evaluate the performance of each model.     

Evaluating Alternative Temporal Survey Designs for Monitoring Wetland Area and Detecting Changes Over Time in California

Evaluation of wetland extent and changes in extent is a foundation of many wetland monitoring and assessment programs. Probabilistic sampling and mapping provides a cost‐effective alternative to comprehensive mapping for large geographic areas. One unresolved challenge for probabilistic or design‐based approaches is how best to monitor both status (e.g., extent at a single point in time) and trends (e.g., changes in extent over time) within a single monitoring program. Existing wetland status and trends (S&T) monitoring programs employ fixed sampling locations; however, theoretical evaluation and limited implementation in other landscape monitoring areas suggest that alternative designs could increase statistical efficiency and overall accuracy. In particular, designs that employ both fixed and nonfixed sampling locations (alternately termed permanent and temporary samples), termed sampling with partial replacement (SPR), are considered to efficiently and effectively balance monitoring current status with detection of trends. This study utilized simulated sampling to assess the performance of fixed sampling locations, SPR, and strictly nonfixed designs for monitoring wetland S&T over time. Modeled changes in wetland density over time were used as inputs for sampling simulations. In contrast to previous evaluations of SPR, the results of this study support the use of a fixed sampling design and show that SPR may underestimate both S&T.     

基于BERT-BILSTM-CRF模型的电力行业事故文本智能分析*

为解决电力行业事故报告文本较长、语义复杂,难以进行有效文本识别问题,提出1种以BERT作为底层的预训练模型,并设计1种双重注意力机制编码器,结合BILSTM-CRF深度挖掘事故文本语义特征,从而实现文本智能分析。首先构建电力词典,通过对BERT预训练,进行BIO标注,然后引入BILSTM-CRF模型实现对文本标签智能分类,最后将该模型与现行其他4种深度学习模型进行对比。研究结果表明:该模型智能识别精确率、召回率及F1值(查准率)均达到约97%,较其他4种模型中效果最好的模型分别提高0.02,0.03,0.02。研究结果可为电力行业事故报告文本分析提供1种新思路。     

基于变量重要性评分-随机森林的溶解氧预测模型——以深圳湾为例

运用Pearson相关性分析,变量重要性评分和随机森林方法构建了溶解氧（DO）实时预测模型,并以深圳湾为例采用浮标资料预测1,3,6和12h的溶解氧.模型预测结果表明,模型最优的输入条件为pH值,水温,叶绿素a,氧化还原电位和蓝绿藻5个水质指标,1h预报的相关系数在0.9以上,6h预报结果一定程度上可以满足工程要求,但对低溶解氧事件的预报必须在3h以内.     

基于多元随机效应Wiener过程的某弹用弹簧可靠性评估

目的 解决某弹用弹簧可靠性评估中存在的不确定性问题。方法 对某弹用弹簧进行加速退化试验,试验过程中发现其具有多个性能退化参数,并且其退化过程具有非线性、随机性及样本差异性的特征。为了对其退化过程进行数学表征,提出一种基于多元随机效应Wiener过程的退化模型。采用基于时间尺度变换的非线性Wiener过程,描述弹簧退化过程中的非线性与随机性。基于随机效应模型,对样本的差异性进行表征,利用Copula函数描述多元性能参数之间的相互作用关系。最后推导弹簧失效寿命的概率密度函数、可靠度函数。结果 在贮存条件为25 ℃、可靠度为0.9时,基于构建的多元随机效应Wiener过程模型,当考虑性能间的相关性时,得到某弹用弹簧的贮存寿命为12 a;不考虑性能间的相关性时,得到其贮存寿命为11.5 a。结论 构建的多元随机退化模型为该弹药健康状态管理提供了相应的理论依据。     

极端梯度提升与随机森林融合的天然气露点预测方法

目的 解决目前水露点数据多为人工采用测量仪器测得,时效性低且成本高昂的问题。方法 建立一种基于极端梯度提升(XGBoost)和随机森林(RF)的天然气水露点预测方法。采用XGBoost方法对所有监测工艺参数进行分析,筛选出主要影响水露点的关键工艺特征参数,以排除无关特征参数对预测的干扰。建立RF预测模型,输入关键特征集参数,实现对水露点的实时预测。以重庆气矿某脱水监测系统监测数据与生产数据为例,对所提预测方法进行对比分析验证。结果 相较于XGBoost、SVM等预测方法,RF模型具有最佳的预测性能,且经过XGBoost特征选择后,RF预测结果的MAE值降低了0.016 9 ℃,RMSE值降低了0.014 6 ℃。结论 基于极端梯度提升与随机森林融合的水露点预测方法具有更优的预测精度与鲁棒性,对指导脱水现场生产具有积极作用。     

基于随机森林的南京市PM2.5和O3对减排的响应

自2013年《大气污染防治行动计划》实施后,南京市大气污染有所改善,但仍面临着细颗粒物(PM_2.5)和臭氧(O₃)污染问题.为探究污染物浓度对其前体物减排的响应,获得有效的减排策略,常利用大气化学模式进行多组基于排放扰动的敏感性试验,而这需要消耗大量计算时间和计算资源.应用随机森林算法对2015年大气化学传输模式(GEOS-Chem)模拟结果进行机器学习,高效地预测了南京2019年PM_2.5浓度日均值和日最大8 h臭氧(MDA8 O₃)浓度对不同人为源排放控制情景的响应.随机森林结果表明2019年中国人为排放每减少10%,南京ρ(PM_2.5)季节平均值下降2～4μg·m^-3.当2019年中国人为源减排比例高于20%时,南京ρ(PM_2.5)年均值将低于国家二级限值(35μg·m^-3).若仅对中国地区O₃前体物氮氧化物(NO_x)和挥发性有机污染物(VOCs)同比例减排,反而...     

Does Riparian Forest Restoration Thinning Enhance Biodiversity? The Ecological Importance of Large Wood

Intact riparian ecosystems are rich in biological diversity, but throughout the world, many have been degraded. Biodiversity declines, particularly of vertebrates, have led to experimental efforts to restore riparian forests by thinning young stands to accelerate creation of large diameter live trees. However, many vertebrates depend on large diameter deadwood that is standing as snags or fallen to the forest floor or fallen into streams. Therefore, we reviewed the sizes of deadwood and live trees used by different vertebrate species to understand which species are likely to benefit from different thinning treatments. We then examined how riparian thinning affects the long‐term development of both large diameter live trees and deadwood. To this end, we used a forest growth model to examine how different forest thinning intensities might affect the long‐term production and abundance of live trees and deadwood. Our results suggest that there are long‐term habitat tradeoffs associated with different thinning intensities. Species that utilize large diameter live trees will benefit most from heavy thinning, whereas species that utilize large diameter deadwood will benefit most from light or no thinning. Because far more vertebrate species utilize large deadwood rather than large live trees, allowing riparian forests to naturally develop may result in the most rapid and sustained development of structural features important to most terrestrial and aquatic vertebrates.