Efficiency and Economy of a New Agricultural Rainwater Harvesting System

Shortage of water is the key limiting factor for agricultural development of Beijing.Rainwater harvesting(RWH) could provide an alternative water source for greenhouse agriculture,but local natural and socioeconomic conditions challenge the application of the technology.This article analyses the advantages and disadvantages of different types of greenhouse RWH in Beijing,and describes a new greenhouse RWH system demonstrated in 2008 in Huairou,a suburb district of Beijing.It analyses the efficiency,cost-benefit ratios and limiting factors of the new system.The results show that with the new system,RWH efficiency can be as high as 66%(of total rainfall) and the rainwater usage rate can reach 69% of total water usage.The ratio of benefit to cost of government investment can be 1.84,and the ratio of benefit to cost of a farmer's investment could be 1.68 provided the project is designed to save water and also increase income.However,the price of groundwater for agriculture directly influences the potential for applying and scaling up the project.If the RWH system does not increase the farmers' incomes at the current water price,they will not use it until the water price rises to a critical point,which is determined by external factors.This article also suggests a number of measures to increase the efficiency of the system in order to apply it on a large scale.

Solar thermal simulation and applications in greenhouse

In this study,a comprehensive review focusing on key strategies of energy saving technologies based on simulation of heat and mass transfer and also artificial intelligent for climate controlling is presented.Following the brief and concise assessment of existing greenhouse systems in terms of their role in total energy consumption;effective shape and structure,energy-efficient and new technologies are analyzed in detail for potential utilization in greenhouses for notable reductions in energy consumption and also go toward the sustainability.The technologies considered within the scope of this research are mainly renewable and sustainable based solutions such as photovoltaic(PV)modules,solar thermal(T)collectors,hybrid PV/T collectors and systems,phase change material(PCM)and underground based heat storage techniques,energy-efficient heat pumps,alternative facade materials for better thermal insulation and power generation.The findings from the research clearly reveal that up to 70%energy saving can be achieved through appropriate retrofit of conventional greenhouses.Using of solar greenhouses in Europe is more popular than others.In some countries in Asia such as Iran,it is very restrict to invest on renewable projects because of cheap fossil fuels.So it is recommended beside of investments by private investors,the Iranian government should also invest in the extension of solar energy in greenhouse by setting up a specialized agency or contracting firms.Those should target the modeling and design the best shape of solar greenhouse for all agricultural areas to receive the maximum solar radiation and decrease the need of fossil fuels.

Developing a multi-label tinyML machine learning model for an active and optimized greenhouse microclimate control from multivariate sensed data

In the uncertainties within which the worldwide food security lies nowadays,the agricultural industry is raising a crucial need for being equipped with the state-of-the-art technologies for a more efficient,climate-resilient and sustainable production.The traditional production methods have to be revisited,and opportunities should be given for the innovative solutions henceforth brought by big data analytics,cloud computing and internet of things(IoT).In this context,we develop an optimized tinyML-oriented model for an active machine learningbased greenhouse microclimate management to be integrated in an on-field microcontroller.We design an experimental strawberry greenhouse from which we collect multivariate climate data through installed sensors.The obtained values'combinations are labeled according to a five-action multi-label control strategy,then used to prepare a machine learning-ready dataset.The dataset is used to train and five-fold cross-validate 90 Multi-Layer Perceptrons(MLPs)with varied hyperparameters to select the most performant–yet optimized–model instance for the addressed task.Our multi-label control approach enables designing highly scalable models with reduced computational complexity,comprising only n control neurons instead of(1+∑n k=1Cn k)neurons(usually generated from a classic single-label approach from n input variables).Our final selected model incorporates 2 hidden layers with 7 and 8 neurons respectively and 151 parameters;it scored a mean accuracy of 97%during the cross-validation phase,then 96%on our supplementary test set.The model enables an intelligent and autonomous greenhouse management with the less required computations.It can be efficiently deployed in microcontrollers within real world operating conditions.