A hybrid integrated deep learning model for the prediction of citywide spatio-temporal flow volumes     

Yibin Ren  Huanfa Chen  Tao Cheng  Yang Zhang  Ge Chen 《International journal of geographical information science》2020,34(4):802-823

ABSTRACT

The spatio-temporal residual network (ST-ResNet) leverages the power of deep learning (DL) for predicting the volume of citywide spatio-temporal flows. However, this model, neglects the dynamic dependency of the input flows in the temporal dimension, which affects what spatio-temporal features may be captured in the result. This study introduces a long short-term memory (LSTM) neural network into the ST-ResNet to form a hybrid integrated-DL model to predict the volumes of citywide spatio-temporal flows (called HIDLST). The new model can dynamically learn the temporal dependency among flows via the feedback connection in the LSTM to improve accurate captures of spatio-temporal features in the flows. We test the HIDLST model by predicting the volumes of citywide taxi flows in Beijing, China. We tune the hyperparameters of the HIDLST model to optimize the prediction accuracy. A comparative study shows that the proposed model consistently outperforms ST-ResNet and several other typical DL-based models on prediction accuracy. Furthermore, we discuss the distribution of prediction errors and the contributions of the different spatio-temporal patterns.  相似文献   

湿地土壤和沉积物异化铁还原过程研究进展     

朱晓艳  袁宇翔  宋长春  姜明 《湿地科学》2020,18(1):122-128

异化铁还原是湿地土壤和沉积物中重要的生物地球化学过程,也是有机质矿化的主要途径之一。湿地干湿交替等过程会使土壤的氧化还原状态发生改变,影响铁元素及与其相关的元素的迁移和转化。总结了湿地土壤和沉积物中异化铁还原过程及其与碳、磷、硫等元素在生物地球化学循环关键过程中的相互作用,阐述了湿地土壤和沉积物中异化铁还原过程对微量金属元素迁移和转化的影响,分析了影响湿地土壤和沉积物异化铁还原过程的主要环境因子。未来相关研究应集中于湿地土壤和沉积物中异化铁还原微生物分析和纯化、不同有机质形式对异化铁还原过程的影响以及异化铁还原对土壤有机质矿化的贡献。  相似文献   

水文情势、土壤和水电开发对河流湿地中植物的影响研究进展     

杨娇  厉恩华  夏盈  张莹莹  王学雷 《湿地科学》2020,18(1):115-121

开展环境对河流湿地中植物的影响研究,不仅有助于了解河流湿地中植物与生态环境之间的关系,而且对河流湿地中植物的保护和恢复工作具有重要意义。根据近年来发表的环境对河流湿地中植物的影响研究成果,对河流湿地中植物的范围进行了界定,综述了与河流湿地中植物关系密切的水文情势、土壤和水电开发对其的影响,指出未来对河流湿地中植物的影响研究的方向。  相似文献   

A meta-analysis of the impacts of forest logging on soil CO_2 efflux     

LongFei Chen  YangZhou Xiang  ZhiBin He  Jun Du  PengFei Lin  Xi Zhu 《寒旱区科学》2020,12(3):165-179

Soil CO_2 efflux, the second largest flux in a forest carbon budget, plays an important role in global carbon cycling. Forest logging is expected to have large effects on soil CO_2 efflux and carbon sequestration in forest ecosystems. However, a comprehensive understanding of soil CO_2 efflux dynamics in response to forest logging remains elusive due to large variability in results obtained across individual studies. Here, we used a meta-analysis approach to synthesize the results of 77 individual field studies to determine the impacts of forest logging on soil CO_2 efflux. Our results reveal that forest logging significantly stimulated soil CO_2 efflux of the growing season by 5.02%. However, averaged across all studies, nonsignificant effect was detected following forest logging. The large variation among forest logging impacts was best explained by forest type, logging type, and time since logging. Soil CO_2 efflux in coniferous forests exhibited a significant increase(4.38%) due to forest logging, while mixed and hardwood forests showed no significant change. Logging type also had a significant effect on soil CO_2 efflux, with thinning increasing soil CO_2 efflux by 12.05%, while clear-cutting decreasing soil CO_2 efflux by 8.63%. The time since logging also had variable effects, with higher soil CO_2 efflux for 2 years after logging, and lower for 3-6 years after logging; when exceeded 6 years, soil CO_2 efflux increased. As significantly negative impacts of forest logging were detected on fine root biomass, the general positive effects on soil CO_2 efflux can be explained by the accelerated decomposition of organic matter as a result of elevated soil temperature and organic substrate quality. Our results demonstrate that forest logging had potentially negative effects on carbon sequestration in forest ecosystems.  相似文献   

An experimental investigation of the effects of thawed soil depth on rill flow velocity     

Xiaofeng Gao  Xiaonan Shi  Tingwu Lei  Huaqing Liu  Jiahui Yang 《水文研究》2021,35(2):e14043

Water flow velocity is an important hydraulic variable in hydrological and soil erosion models, and is greatly affected by freezing and thawing of the surface soil layer in cold high-altitude regions. The accurate measurement of rill flow velocity when impacted by the thawing process is critical to simulate runoff and sediment transport processes. In this study, an electrolyte tracer modelling method was used to measure rill flow velocity along a meadow soil slope at different thaw depths under simulated rainfall. Rill flow velocity was measured using four thawed soil depths (0, 1, 2 and 10 cm), four slope gradients (5°, 10°, 15° and 20°) and four rainfall intensities (30, 60, 90 and 120 mm·h⁻¹). The results showed that the increase in thawed soil depth caused a decrease in rill flow velocity, whereby the rate of this decrease was also diminishing. Whilst the rill flow velocity was positively correlated with slope gradient and rainfall intensity, the response of rill flow velocity to these influencing factors varied with thawed soil depth. The mechanism by which thawed soil depth influenced rill flow velocity was attributed to the consumption of runoff energy, slope surface roughness, and the headcut effect. Rill flow velocity was modelled by thawed soil depth, slope gradient and rainfall intensity using an empirical function. This function predicted values that were in good agreement with the measured data. These results provide the foundation for a better understanding of the effect of thawed soil depth on slope hydrology, erosion and the parameterization scheme for hydrological and soil erosion models.  相似文献   

Wall-to-wall spatial prediction of growing stock volume based on Italian National Forest Inventory plots and remotely sensed data     

《International Journal of Applied Earth Observation and Geoinformation》2020

Spatial predictions of forest variables are required for supporting modern national and sub-national forest planning strategies, especially in the framework of a climate change scenario. Nowadays methods for constructing wall-to-wall maps and calculating small-area estimates of forest parameters are becoming essential components of most advanced National Forest Inventory (NFI) programs. Such methods are based on the assumption of a relationship between the forest variables and predictor variables that are available for the entire forest area. Many commonly used predictors are based on data obtained from active or passive remote sensing technologies. Italy has almost 40% of its land area covered by forests. Because of the great diversity of Italian forests with respect to composition, structure and management and underlying climatic, morphological and soil conditions, a relevant question is whether methods successfully used in less complex temperate and boreal forests may be applied successfully at country level in Italy.For a study area of more than 48,657 km² in central Italy of which 43% is covered by forest, the study presents the results of a test regarding wall-to-wall, spatially explicit estimation of forest growing stock volume (GSV) based on field measurement of 1350 plots during the last Italian NFI. For the same area, we used potential predictor variables that are available across the whole of Italy: cloud-free mosaics of multispectral optical satellite imagery (Landsat 5 TM), microwave sensor data (JAXA PALSAR), a canopy height model (CHM) from satellite LiDAR, and auxiliary variables from climate, temperature and precipitation maps, soil maps, and a digital terrain model.Two non-parametric (random forests and k-NN) and two parametric (multiple linear regression and geographically weighted regression) prediction methods were tested to produce wall-to-wall map of growing stock volume at 23-m resolution. Pixel level predictions were used to produce small-area, province-level model-assisted estimates. The performances of all the methods were compared in terms of percent root mean-square error using a leave-one-out procedure and an independent dataset was used for validation. Results were comparable to those available for other ecological regions using similar predictors, but random forests produced the most accurate results with a pixel level R² = 0.69 and RMSE_% = 37.2% against the independent validation dataset. Model-assisted estimates were more precise than the original design-based estimates provided by the NFI.  相似文献   

内蒙古鄂伦春旗东部主要农耕区土壤有机碳含量及主要影响因素分析     

贺鹏飞  魏明辉  李秋燕  张哲寰  许江 《地质与资源》2020,29(6):574-578

利用鄂伦春自治旗东部主要耕地区1：25万土地质量地球化学调查数据，查明了研究区内表层和深层土壤有机碳储量和有机碳密度分布特征，分析了研究区内土壤有机碳储量、有机碳密度与土壤类型、土地利用方式之间的关系，探讨了土壤类型和土地利用方式对土壤有机碳的作用机理.结果表明研究区内土壤有机碳含量分布不均，土壤类型和土地利用方式是土壤有机碳储量和有机碳密度的主要影响因素.  相似文献   

吕宋和台湾岛以东黑潮季节与年际变化规律的对比分析     

武杰  张林林  闫晓梅 《海洋与湖沼》2020,51(4):839-850

黑潮是北太平洋副热带环流系统的一支重要的西边界流。前人对不同流段黑潮的季节和年际变化进行了诸多研究,然而基于不同数据所得结论仍存在差异,尤其是不同模式计算所得流量差别很大,而且以往研究往往着眼于某一流段,对不同流段黑潮变化之间的异同及其原因涉及较少。本文基于卫星高度计数据,评估了OFES(Ocean generalcir culation model For the Earth Simulator)和HYCOM(Hybrid Coordinate Ocean Model)两个模式对吕宋岛和台湾岛以东黑潮季节与年际变化的模拟能力,进而对两个海域黑潮变化的异同及其物理机制进行了分析。结果表明:HYCOM模式对黑潮季节变化的模拟较好,而OFES模式对黑潮年际变化的模拟较好。吕宋岛以东黑潮和台湾岛以东黑潮在季节与年际尺度上的变化规律均不相同,且受不同动力过程控制。吕宋岛以东黑潮呈现冬春季强而秋季弱的变化规律,主要受北赤道流分叉南北移动的影响;而台湾岛以东黑潮呈现夏季强冬季弱的变化特点,主要受该海区反气旋涡与气旋涡相对数目的季节变化影响。在年际尺度上,吕宋岛以东黑潮与北赤道流分叉及风应力旋度呈负相关,当风应力旋度超前于流量4个月时相关系数达到了-0.56;而台湾岛以东黑潮的流量变化则受制于副热带逆流区涡动能的变化,且滞后于涡动能9个月时达到最大正相关,相关系数为0.44。本研究对于深入理解不同流段黑潮的多尺度变异规律及其对邻近海区环流与气候的影响具有重要意义,同时对于黑潮研究的数值模式选取具有重要参考价值。  相似文献   

SMAP卫星海表盐度产品的检验与校正     

秦思思  王辉  朱江  万莉颖  张宇  王昊运 《海洋学报(英文版)》2020,39(3):148-158

In this study, sea surface salinity(SSS) Level 3(L3) daily product derived from soil moisture active passive(SMAP)during the year 2016, was validated and compared with SSS daily products derived from soil Moisture and ocean salinity(SMOS) and in-situ measurements. Generally, the root mean square error(RMSE) of the daily SSS products is larger along the coastal areas and at high latitudes and is smaller in the tropical regions and open oceans. Comparisons between the two types of daily satellite SSS product revealed that the RMSE was higher in the daily SMOS product than in the SMAP, whereas the bias of the daily SMOS was observed to be less than that of the SMAP when compared with Argo floats data. In addition, the latitude-dependent bias and RMSE of the SMAP SSS were found to be primarily influenced by the precipitation and the sea surface temperature(SST). Then, a regression analysis method which has adopted the precipitation and SST data was used to correct the larger bias of the daily SMAP product. It was confirmed that the corrected daily SMAP product could be used for assimilation in high-resolution forecast models, due to the fact that it was demonstrated to be unbiased and much closer to the in-situ measurements than the original uncorrected SMAP product.  相似文献   

东北黑土区侵蚀沟遥感影像特征提取与识别   总被引：3，自引：0，他引：3  

于佩鑫  周询  刘素红  王西凯 《遥感学报》2018,22(4):611-620

东北黑土区是中国重要的粮食生产区,而长期的开垦造成了严重的水土流失现象,坡耕地表面出现大量的侵蚀沟。侵蚀沟的识别是土壤侵蚀监测的重要手段之一,目前遥感技术在侵蚀沟的识别中应用广泛,但自动化程度不高。针对特定地物影像的识别,如何选取最能够有效描述该地物的特征是解决问题的关键。本文构建了耕地和侵蚀沟遥感影像的训练样本集,基于样本集分别提取了由光谱特征和纹理特征组成的浅层特征、SIFT特征经编码后得到的中层特征,以及利用卷积神经网络提取的深层特征;再基于不同层次的特征选用合适的分类器对遥感影像进行分类,识别出含有侵蚀沟的遥感影像,形成了一套针对侵蚀沟的特征提取与识别方法,为东北黑土区的耕地保护提供有力支持。测试结果表明:基于中层特征的识别精度最高,为98.5%,但该特征需要人工设计,自动化程度有限;而利用卷积神经网络可自动提取深层特征,其识别精度达到了95.5%,同时大大提高了自动化程度,满足侵蚀沟影像的识别的需求。  相似文献