为提高复杂交通场景下车辆目标检测模型的检测精度,以YOLOv8n(you only look once version 8 nano)为基准模型,设计具有复合主干的Neck-ARW(包括辅助检测分支、RepBlock模块、加权跳跃特征连接)颈部结构,减少信息瓶颈造成沿网络深度方...为提高复杂交通场景下车辆目标检测模型的检测精度,以YOLOv8n(you only look once version 8 nano)为基准模型,设计具有复合主干的Neck-ARW(包括辅助检测分支、RepBlock模块、加权跳跃特征连接)颈部结构,减少信息瓶颈造成沿网络深度方向的信息丢失;引入RepBlock结构重参数化模块,在训练过程中采用多分支结构提高模型特征提取性能;添加P2检测层捕捉更多小目标细节特征,丰富网络内小目标的特征信息流;采用Dynamic Head自注意力机制检测头,将尺度感知、空间感知和任务感知自注意力机制融合到统一框架中,提高检测性能;采用基于层自适应幅度的剪枝(layer-adaptive magnitude based pruning,LAMP)算法,移除模型的冗余参数,构建YOLO-NPDL(Neck-ARW,P2,Dynamic Head,LAMP)车辆目标检测模型。以UA-DETRAC(university at Albany detection and tracking)数据集为试验数据集,分别进行RepBlock模块嵌入位置试验、不同颈部结构对比试验、剪枝试验、消融试验、模型性能对比试验,验证YOLO-NPDL模型的平均精度均值。试验结果表明:RepBlock模块同时嵌入辅助检测分支和颈部主干结构时对多尺度目标的特征提取能力更优,在训练过程中可保留更多的细节信息,但参数量和计算量均增大;采用Neck-ARW颈部结构后模型的平均精度均值E mAP50、E mAP50-95分别提高1.1%、1.7%,参数量减小约17.9%,结构较优;剪枝率为1.3时,模型参数量、计算量分别减小约38.0%、24.0%,冗余通道占比较少,结构较紧凑;与YOLOv8n模型相比,YOLO-NPDL模型在参数量基本相同的基础上,召回率增大2.7%,E mAP50增大2.7%,达到94.7%,E mAP50-95增大6.4%,达到79.7%;与目前广泛使用的YOLO系列模型相比,YOLO-NPDL模型在较少参数量的基础上,检测精度较高。YOLO-NPDL模型在检测远端目标、雨天及夜景等实际复杂交通情景中无明显误检、漏检情况,可检测到更多的远端小目标车辆,检测效果更优。展开更多
利用新一代数值预报模式ARW(Advance Research WRF),模拟试验了在不同垂直分辨率条件下模式对"罗莎"台风的预报性能。试验结果表明,数值模式的垂直分辨率变化对台风路径预报效果的影响不大,但对台风强度和结构的预报效果有明...利用新一代数值预报模式ARW(Advance Research WRF),模拟试验了在不同垂直分辨率条件下模式对"罗莎"台风的预报性能。试验结果表明,数值模式的垂直分辨率变化对台风路径预报效果的影响不大,但对台风强度和结构的预报效果有明显影响。但是,对于一定的水平分辨率而言,有一个与之匹配的垂直分辨率,垂直分辨率低于或者高于这个相匹配的阈值,模式的预报性能都会下降。展开更多
基于NCEP(National Centers for Environmental Prediction)的FNL(Final Operational Global Analysis)资料和WRF-ARW模式,对2014年7月10—12日西南涡(SWV)暴雨天气过程进行诊断分析和数值模拟试验。研究结果表明,西南涡沿切变线东移发...基于NCEP(National Centers for Environmental Prediction)的FNL(Final Operational Global Analysis)资料和WRF-ARW模式,对2014年7月10—12日西南涡(SWV)暴雨天气过程进行诊断分析和数值模拟试验。研究结果表明,西南涡沿切变线东移发展和低空西南急流的增强是导致此次暴雨过程的主要原因。西南涡的移向和相对风暴螺旋度(SRH)大值区有很好对应关系,SRH大值区对西南涡暴雨过程强对流的落区有较好的指示作用。沿西南涡移动方向,其前部暖平流后部冷平流有利于其前移,沿假相当位温平流场的零等值线可指示西南涡的移向。引入湿螺旋度散度(MHD)来分析西南涡降水的水汽条件发现,模式结果计算的850hPa上MHD值分布与雨区和降雨强度对应较好,但对于降水的定量预测还需考虑MHD大值区延伸的高度。展开更多
角度随机游走(angle random walk,ARW)误差已成为制约长航时惯性导航系统精度的主要因素。为了减弱ARW对系统精度的影响,针对初始对准和长航时导航两个方面研究误差传播规律及抑制方法。仿真结果表明:ARW直接影响方位对准精度,在长航时...角度随机游走(angle random walk,ARW)误差已成为制约长航时惯性导航系统精度的主要因素。为了减弱ARW对系统精度的影响,针对初始对准和长航时导航两个方面研究误差传播规律及抑制方法。仿真结果表明:ARW直接影响方位对准精度,在长航时的导航中,游走系数N所产生的速度振荡幅值与60N的常值漂移大致相当,姿态振荡误差中的24 h周期因素更为关键,ARW产生的经度误差发散项均方差随时间的平方根增长;系统可采用卡尔曼滤波削弱ARW所造成的对准误差,通过水平阻尼方法可以消除由ARW引起的位置误差中的振荡项。展开更多
To describe the evolution of atmospheric processes and rainfall forecast in Tanzania, the Advanced Weather Research and Forecasting (WRF-ARW) model was used. The principal objectives of this study were 1) the understa...To describe the evolution of atmospheric processes and rainfall forecast in Tanzania, the Advanced Weather Research and Forecasting (WRF-ARW) model was used. The principal objectives of this study were 1) the understanding of mesoscale WRF model and adapting the model for Tanzania;2) to conduct numerical experiments using WRF model with different convective parameterization schemes (CP’s) and investigate the impact of each scheme on the quality of rainfall forecast;and 3) the investigation of the capability of WRF model to successfully simulate rainfall amount during strong downpour. The impact on the quality of rainfall forecast of six CP’s was investigated. Two rainy seasons, short season “Vuli” from October to December (OND) and long season “Masika” from March to May (MAM) were targeted. The results of numerical experiments showed that for rainfall prediction in Dar es Salaam and (the entire coast of the Indian Ocean), GD scheme performed better during OND and BMJ scheme during MAM. Results also showed that NC scheme should not be used, which is in agreement to the fact that in tropics rainfall is from convective activities. WRF model to some extent performs better in the cases of extreme rainfall.展开更多
Coupled hydrological and atmospheric modeling is an efficient method for snowmelt runoff forecast in large basins. We use short-range precipitation forecasts of mesoscale at- mospheric Weather Research and Forecasting...Coupled hydrological and atmospheric modeling is an efficient method for snowmelt runoff forecast in large basins. We use short-range precipitation forecasts of mesoscale at- mospheric Weather Research and Forecasting （WRF） model combining them with ground-based and satellite observations for modeling snow accumulation and snowmelt processes in the Votkinsk reservoir basin （184,319 km2）. The method is tested during three winter seasons （2012-2015）. The MODIS-based vegetation map and leaf area index data are used to calculate the snowmelt intensity and snow evaporation in the studied basin. The GIS-based snow accumulation and snowmelt modeling provides a reliable and highly detailed spatial distribution for snow water equivalent （SWE） and snow-covered areas （SCA）. The modelling results are validated by comparing actual and estimated SWE and SCA data. The actual SCA results are derived from MODIS satellite data. The algorithm for assessing the SCA by MODIS data （ATBD-MOD 10） has been adapted to a forest zone. In general, the proposed method provides satisfactory results for maximum SWE calculations. The calculation accuracy is slightly degraded during snowmelt periods. The SCA data is simulated with a higher reliability than the SWE data. The differences between the simulated and actual SWE may be explained by the overestimation of the WRF-simulated total precipitation and the unrepresentativeness of the SWE measurements （snow survey）.展开更多
文摘为提高复杂交通场景下车辆目标检测模型的检测精度,以YOLOv8n(you only look once version 8 nano)为基准模型,设计具有复合主干的Neck-ARW(包括辅助检测分支、RepBlock模块、加权跳跃特征连接)颈部结构,减少信息瓶颈造成沿网络深度方向的信息丢失;引入RepBlock结构重参数化模块,在训练过程中采用多分支结构提高模型特征提取性能;添加P2检测层捕捉更多小目标细节特征,丰富网络内小目标的特征信息流;采用Dynamic Head自注意力机制检测头,将尺度感知、空间感知和任务感知自注意力机制融合到统一框架中,提高检测性能;采用基于层自适应幅度的剪枝(layer-adaptive magnitude based pruning,LAMP)算法,移除模型的冗余参数,构建YOLO-NPDL(Neck-ARW,P2,Dynamic Head,LAMP)车辆目标检测模型。以UA-DETRAC(university at Albany detection and tracking)数据集为试验数据集,分别进行RepBlock模块嵌入位置试验、不同颈部结构对比试验、剪枝试验、消融试验、模型性能对比试验,验证YOLO-NPDL模型的平均精度均值。试验结果表明:RepBlock模块同时嵌入辅助检测分支和颈部主干结构时对多尺度目标的特征提取能力更优,在训练过程中可保留更多的细节信息,但参数量和计算量均增大;采用Neck-ARW颈部结构后模型的平均精度均值E mAP50、E mAP50-95分别提高1.1%、1.7%,参数量减小约17.9%,结构较优;剪枝率为1.3时,模型参数量、计算量分别减小约38.0%、24.0%,冗余通道占比较少,结构较紧凑;与YOLOv8n模型相比,YOLO-NPDL模型在参数量基本相同的基础上,召回率增大2.7%,E mAP50增大2.7%,达到94.7%,E mAP50-95增大6.4%,达到79.7%;与目前广泛使用的YOLO系列模型相比,YOLO-NPDL模型在较少参数量的基础上,检测精度较高。YOLO-NPDL模型在检测远端目标、雨天及夜景等实际复杂交通情景中无明显误检、漏检情况,可检测到更多的远端小目标车辆,检测效果更优。
文摘利用新一代数值预报模式ARW(Advance Research WRF),模拟试验了在不同垂直分辨率条件下模式对"罗莎"台风的预报性能。试验结果表明,数值模式的垂直分辨率变化对台风路径预报效果的影响不大,但对台风强度和结构的预报效果有明显影响。但是,对于一定的水平分辨率而言,有一个与之匹配的垂直分辨率,垂直分辨率低于或者高于这个相匹配的阈值,模式的预报性能都会下降。
文摘基于NCEP(National Centers for Environmental Prediction)的FNL(Final Operational Global Analysis)资料和WRF-ARW模式,对2014年7月10—12日西南涡(SWV)暴雨天气过程进行诊断分析和数值模拟试验。研究结果表明,西南涡沿切变线东移发展和低空西南急流的增强是导致此次暴雨过程的主要原因。西南涡的移向和相对风暴螺旋度(SRH)大值区有很好对应关系,SRH大值区对西南涡暴雨过程强对流的落区有较好的指示作用。沿西南涡移动方向,其前部暖平流后部冷平流有利于其前移,沿假相当位温平流场的零等值线可指示西南涡的移向。引入湿螺旋度散度(MHD)来分析西南涡降水的水汽条件发现,模式结果计算的850hPa上MHD值分布与雨区和降雨强度对应较好,但对于降水的定量预测还需考虑MHD大值区延伸的高度。
文摘角度随机游走(angle random walk,ARW)误差已成为制约长航时惯性导航系统精度的主要因素。为了减弱ARW对系统精度的影响,针对初始对准和长航时导航两个方面研究误差传播规律及抑制方法。仿真结果表明:ARW直接影响方位对准精度,在长航时的导航中,游走系数N所产生的速度振荡幅值与60N的常值漂移大致相当,姿态振荡误差中的24 h周期因素更为关键,ARW产生的经度误差发散项均方差随时间的平方根增长;系统可采用卡尔曼滤波削弱ARW所造成的对准误差,通过水平阻尼方法可以消除由ARW引起的位置误差中的振荡项。
文摘To describe the evolution of atmospheric processes and rainfall forecast in Tanzania, the Advanced Weather Research and Forecasting (WRF-ARW) model was used. The principal objectives of this study were 1) the understanding of mesoscale WRF model and adapting the model for Tanzania;2) to conduct numerical experiments using WRF model with different convective parameterization schemes (CP’s) and investigate the impact of each scheme on the quality of rainfall forecast;and 3) the investigation of the capability of WRF model to successfully simulate rainfall amount during strong downpour. The impact on the quality of rainfall forecast of six CP’s was investigated. Two rainy seasons, short season “Vuli” from October to December (OND) and long season “Masika” from March to May (MAM) were targeted. The results of numerical experiments showed that for rainfall prediction in Dar es Salaam and (the entire coast of the Indian Ocean), GD scheme performed better during OND and BMJ scheme during MAM. Results also showed that NC scheme should not be used, which is in agreement to the fact that in tropics rainfall is from convective activities. WRF model to some extent performs better in the cases of extreme rainfall.
文摘Coupled hydrological and atmospheric modeling is an efficient method for snowmelt runoff forecast in large basins. We use short-range precipitation forecasts of mesoscale at- mospheric Weather Research and Forecasting （WRF） model combining them with ground-based and satellite observations for modeling snow accumulation and snowmelt processes in the Votkinsk reservoir basin （184,319 km2）. The method is tested during three winter seasons （2012-2015）. The MODIS-based vegetation map and leaf area index data are used to calculate the snowmelt intensity and snow evaporation in the studied basin. The GIS-based snow accumulation and snowmelt modeling provides a reliable and highly detailed spatial distribution for snow water equivalent （SWE） and snow-covered areas （SCA）. The modelling results are validated by comparing actual and estimated SWE and SCA data. The actual SCA results are derived from MODIS satellite data. The algorithm for assessing the SCA by MODIS data （ATBD-MOD 10） has been adapted to a forest zone. In general, the proposed method provides satisfactory results for maximum SWE calculations. The calculation accuracy is slightly degraded during snowmelt periods. The SCA data is simulated with a higher reliability than the SWE data. The differences between the simulated and actual SWE may be explained by the overestimation of the WRF-simulated total precipitation and the unrepresentativeness of the SWE measurements （snow survey）.
