No abstract

No abstract

A 65-year-old upland black spruce stand was thinned and fertilized with urea in 1961. The 15-year total volume increases ranged from 3 to 9 m3 for an application of 112 kg N/ha and from 11.5 to 12.5 m3 for 448 kg N/ha. Most of the volume increases due to treatment took place in the first 10 years. Heavy thinning and fertilization had almost additive effects to produce an 86% increase in periodic gross increment. Neither periodic tree mortality nor distribution of response by tree size appeared to have been affected by treatment. Humus analyses of control plots and of plots treated with 448 kg N/ha, conducted in 1961, 1966, 1971, and 1976, indicated that after 15 years pH values were still higher, NH4-N levels approached equilibrium values twice as high as controls after 10 years, leaching and volatilization losses of N were negligible, the C/N ratios were lower, and the potential for N mineralization and total biological activity were higher on the N-treated plots. Significant black spruce stand responses to N fertilization have been shown in this stand but responses have been variable in other trials with this species. Further work is needed to explain these results.

With the development of the Cyber-Physical-Social Systems(CPSS), a large number of multidimensional time series have been generated in today's world, such as: sensor data for industrial equipment operation, vehicle driving data, and cloud server operation and maintenance data and so on. The key task of Cloud-Fog-Edge Computing in managing these systems is how to detect anomalous data in a specific time series to facilitate operator action to solve potential system problems. So multidimensional time series outlier detection become an important direction of CPSS data mining and Cloud-Fog-Edge Computing research, and it has a wide range of applications in industry, finance, medicine and other fields. This paper proposes a framework called Multidimensional time series Outlier detection based on a Time Convolutional Network AutoEncoder (MOTCN-AE), which can detect outliers in time series data, such as identifying equipment failures, dangerous driving behaviors of cars, etc. Specifically, this paper first uses a feature extraction method to transform the original time series into a feature-rich time series. Second, the proposed TCN-AE is used to reconstruct the feature-rich time series data, and the reconstruction error is used to calculate outlier scores. Finally, the MOTCN-AE framework is validated by multiple time series datasets to demonstrate its effectiveness in detecting time series outliers. INDEX TERMS Time series, outlier detection, time convolution network, autoencoder.