Research on WNN Greenhouse Temperature Prediction Method Based on GA

Temperature in agricultural production has a direct impact on the growth of crops.The emergence of greenhouses has improved the impact of the original unpredictable changes in temperature,but the temperature modeling of greenhouses is still the main direction at present.Neural network modeling relies on sufficient actual data to model greenhouses,but there is a widening gap in the application of different neural networks.This paper proposes a greenhouse temperature prediction model based on wavelet neural network with genetic algorithm(GA-WNN).With the simple network structure and the nonlinear adaptability of the wavelet basis function,wavelet neural network(WNN)improved model training speed and accuracy of prediction results compared with back propagation neural networks(BPNN),which was conducive to the prediction and control of short-term greenhouse temperature fluctuations.At the same time,the genetic algorithm(GA)was introduced to globally optimize the initial weights of the original model,which improved the insensitivity of the model to the initial weights and thresholds,and improved the training speed and stability of the model.Finally,simulation results for the greenhouse showed that the model training speed,prediction results accuracy and model stability of the GA-WNN in the greenhouse were improved in comparison to results obtained by the WNN and BPNN in the greenhouse.

Root length density distribution and associated soil water dynamics for tomato plants under furrow irrigation in a solar greenhouse

Furrow irrigation is a traditional widely-used irrigation method in the world. Understanding the dynamics of soil water distribution is essential to developing effective furrow irrigation strategies, especially in water-limited regions. The objectives of this study are to analyze root length density distribution and to explore soil water dynamics by simulating soil water content using a HYDRUS-2D model with consideration of root water uptake for furrow irrigated tomato plants in a solar greenhouse in Northwest China. Soil water contents were also in-situ observed by the ECH_2O sensors from 4 June to 19 June and from 21 June to 4 July, 2012. Results showed that the root length density of tomato plants was concentrated in the 0–50 cm soil layers, and radiated 0–18 cm toward the furrow and 0–30 cm along the bed axis. Soil water content values simulated by the HYDRUS-2D model agreed well with those observed by the ECH_2O sensors, with regression coefficient of 0.988, coefficient of determination of 0.89, and index of agreement of 0.97. The HYDRUS-2D model with the calibrated parameters was then applied to explore the optimal irrigation scheduling. Infrequent irrigation with a large amount of water for each irrigation event could result in 10%–18% of the irrigation water losses. Thus we recommend high irrigation frequency with a low amount of water for each irrigation event in greenhouses for arid region. The maximum high irrigation amount and the suitable irrigation interval required to avoid plant water stress and drainage water were 34 mm and 6 days, respectively, for given daily average transpiration rate of 4.0 mm/d. To sum up, the HYDRUS-2D model with consideration of root water uptake can be used to improve irrigation scheduling for furrow irrigated tomato plants in greenhouses in arid regions.

Simulation Platform for Greenhouse Environment Control System

The simulation system is designed to imitate a greenhouse environment with the software on computer. The relation ships between greenhouse indoor environment, outdoor environment and environment conditioner are presented The energy balance equation and humidity balance equation of the greenhouse are givea In this system, the weather data is generated by computer according to the real weather data and rules in Beijing. The state of the devices can be dynamically decided based on the given intelligent control algorithm Then the parameters of the greenhouse environment are decided based on the greenhouse model that presented All the results are showed on the screen with kindly interface and stored to disk automatically.

Developed and Developing World Contributions to Climate System Change Based on Carbon Dioxide,Methane and Nitrous Oxide Emissions

One of the key issues in international climate negotiations is the formulation of targets for emissions reduction for all countries based on the principle of ＂common but differentiated responsibilities＂. This formulation depends primarily on the quantitative attribution of the responsibilities of developed and developing countries for historical climate change. Using the Commuity Earth System Model（CESM）, we estimate the responsibilities of developed countries and developing countries for climatic change from 1850 to 2005 using their carbon dioxide, methane and nitrous oxide emissions. The results indicate that developed countries contribute approximately 53%–61%, and developing countries approximately 39%–47%, to the increase in global air temperature, upper oceanic warming, sea-ice reduction in the NH, and permafrost degradation. In addition, the spatial heterogeneity of these changes from 1850 to 2005 is primarily attributed to the emissions of greenhouse gases（GHGs）in developed countries. Although uncertainties remain in the climate model and the external forcings used, GHG emissions in developed countries are the major contributor to the observed climate system changes in the 20 th century.

Stepwise multiple regression method of greenhouse gas emission modeling in the energy sector in Poland

The energy sector in Poland is the source of 81% of greenhouse gas（GHG） emissions. Poland,among other European Union countries, occupies a leading position with regard to coal consumption. Polish energy sector actively participates in efforts to reduce GHG emissions to the atmosphere, through a gradual decrease of the share of coal in the fuel mix and development of renewable energy sources. All evidence which completes the knowledge about issues related to GHG emissions is a valuable source of information. The article presents the results of modeling of GHG emissions which are generated by the energy sector in Poland. For a better understanding of the quantitative relationship between total consumption of primary energy and greenhouse gas emission, multiple stepwise regression model was applied. The modeling results of CO2 emissions demonstrate a high relationship（0.97） with the hard coal consumption variable. Adjustment coefficient of the model to actual data is high and equal to 95%. The backward step regression model, in the case of CH4 emission, indicated the presence of hard coal（0.66）, peat and fuel wood（0.34）, solid waste fuels, as well as other sources（- 0.64） as the most important variables. The adjusted coefficient is suitable and equals R2= 0.90. For N2 O emission modeling the obtained coefficient of determination is low and equal to 43%. A significant variable influencing the amount of N2 O emission is the peat and wood fuel consumption.

A modeling framework for the integration of electrical and thermal energy systems in greenhouses

Greenhouse horticulture is associated to a significant energy consumption in temperate countries,mainly for lighting and for heating.Interestingly,the potential for energy optimization and energy savings is high but requires detailed models capable of considering various system configurations and control systems.This paper provides an open-source modeling framework capable of simulating and optimizing the design and the control of both the greenhouse and the generation systems covering all energy needs.The proposed model is composed of sub-models from different scientific fields:a greenhouse climate model,a crop yield model,a large number of energy generation and storage units models and different rule-based control strategies.The association of such state-of-the-art models in a single framework provides a powerful tool for optimization purposes and allows the definition of completely customized systems by means of an object-oriented interface.In this work,various control strategies are defined and simulated,thus demonstrating the capabilities of the proposed model.Results indicate that,by performing minor changes to the control of the thermal screen,heating consumption can be reduced by 3%without any loss in crop yield.The control of heat-generation units also has a significant impact on the operational costs,which vary by up to 17%when self-consumption levels are accounted for in the control strategy.

Advances in greenhouse automation and controlled environment agriculture:A transition to plant factories and urban agriculture

Greenhouse cultivation has evolved from simple covered rows of open-fields crops to highly sophisticated controlled environment agriculture(CEA)facilities that projected the image of plant factories for urban agriculture.The advances and improvements in CEA have promoted the scientific solutions for the efficient production of plants in populated cities and multi-story buildings.Successful deployment of CEA for urban agriculture requires many components and subsystems,as well as the understanding of the external influencing factors that should be systematically considered and integrated.This review is an attempt to highlight some of the most recent advances in greenhouse technology and CEA in order to raise the awareness for technology transfer and adaptation,which is necessary for a successful transition to urban agriculture.This study reviewed several aspects of a high-tech CEA system including improvements in the frame and covering materials,environment perception and data sharing,and advanced microclimate control and energy optimization models.This research highlighted urban agriculture and its derivatives,including vertical farming,rooftop greenhouses and plant factories which are the extensions of CEA and have emerged as a response to the growing population,environmental degradation,and urbanization that are threatening food security.Finally,several opportunities and challenges have been identified in implementing the integrated CEA and vertical farming for urban agriculture.

Mobile-Source GHG Modeling Institutions and Capacities in China:Findings Based on Structured Interviews and On-Line Surveys

This paper provides an overview of practices of mobile-source greenhouse gas(GHG) modeling in China and related data sharing issues. It is based on structured phone interviews and two on-line surveys conducted in 2011 and finds that most cities have transportation-land use models but that few have mobile-source GHG models. A group of entities housed in the government have the strongest GHG modeling capacities and dominate the relevant consulting market. Data hoarding of public entities is the biggest barrier for entities without government ties to compete in the market. The reasons for data hoarding include government concerns over political implications of data release, a tradition of data hoarding, and a lack of confidence in reliability and accuracy of the data.