Diurnal and Seasonal Variations of CO2Fluxes and Their Climate Controlling Factors for a Subtropical Forest in Ningxiang

In this study, the diurnal and seasonal variations of CO2 fluxes in a subtropical mixed evergreen forest in Ningxiang of Hunan Province, part of the East Asian monsoon region, were quantified for the first time. The fluxes were based on eddy covariance measurements from a newly initiated flux tower. The relationship between the CO2 fluxes and climate factors was also analyzed. The results showed that the target ecosystem appeared to be a clear carbon sink in 2013, with integrated net ecosystem CO2exchange（NEE）, ecosystem respiration（RE）, and gross ecosystem productivity（GEP） of-428.8, 1534.8 and1963.6 g C m^-2yr^-1, respectively. The net carbon uptake（i.e. the-NEE）, RE and GEP showed obvious seasonal variability,and were lower in winter and under drought conditions and higher in the growing season. The minimum NEE occurred on12 June（-7.4 g C m^-2d^-1）, due mainly to strong radiation, adequate moisture, and moderate temperature; while a very low net CO2 uptake occurred in August（9 g C m^-2month^-1）, attributable to extreme summer drought. In addition, the NEE and GEP showed obvious diurnal variability that changed with the seasons. In winter, solar radiation and temperature were the main controlling factors for GEP, while the soil water content and vapor pressure deficit were the controlling factors in summer. Furthermore, the daytime NEE was mainly limited by the water-stress effect under dry and warm atmospheric conditions, rather than by the direct temperature-stress effect.

Holt-Winters Algorithm to Predict the Stock Value Using Recurrent Neural Network

Prediction of stock market value is highly risky because it is based on the concept of Time Series forecasting system that can be used for investments in a safe environment with minimized chances of loss.The proposed model uses a real time dataset offifteen Stocks as input into the system and based on the data,predicts or forecast future stock prices of different companies belonging to different sectors.The dataset includes approximatelyfifteen companies from different sectors and forecasts their results based on which the user can decide whether to invest in the particular company or not;the forecasting is done for the next quarter.Our model uses 3 main concepts for forecasting results.Thefirst one is for stocks that show periodic change throughout the season,the‘Holt-Winters Triple Exponential Smoothing’.3 basic things taken into conclusion by this algorithm are Base Level,Trend Level and Seasoning Factor.The value of all these are calculated by us and then decomposition of all these factors is done by the Holt-Winters Algorithm.The second concept is‘Recurrent Neural Network’.The specific model of recurrent neural network that is being used is Long-Short Term Memory and it’s the same as the Normal Neural Network,the only difference is that each intermediate cell is a memory cell and retails its value till the next feedback loop.The third concept is Recommendation System whichfilters and predict the rating based on the different factors.

Normalization of VIIRS DNB images for improved estimation of socioeconomic indicators

Monthly Visible Infrared Imaging Radiometer Suite(VIIRS)Day-Night Band(DNB)composite data are widely used in research,such as estimations of socioeconomic parameters.However,some surface conditions affect the VIIRS DNB radiance,which may create some estimation bias in certain regions.In this paper,we propose a novel normalization algorithm for VIIRS DNB monthly composite data.The aim is to normalize VIIRS radiance,collected under different surface conditions,to a reference point,so that the bias is reduced.The algorithm is based on the utilization of stable lit pixels as a reference and a nonlinear regression algorithm,to match un-normalized data to the reference data.Experimental results show that the algorithm could improve correlation(R2)between the total sum of nightlights(TOL),electric power consumption(EPC),and gross domestic product(GDP)at both a global and local scale.The algorithm could significantly diminish the seasonal component of un-normalized nightlights radiance caused by snow.The intensified nightlights radiance in sandy regions could also be reduced to a more reasonable range in comparison with other regions.Visual inspection shows that the brightness of snow-affected and sandy regions was strongly reduced after undergoing normalization.