Maria P. Papadopoulou

Computational benefits using artificial intelligent methodologies for the solution of an environmental design problem: saltwater intrusion

Artificial Neural Networks (ANNs) comprise a powerful tool to approximate the complicated behavior and response of physical systems allowing considerable reduction in computation time during time-consuming optimization runs. In this work, a Radial Basis Function Artificial Neural Network (RBFN) is combined with a Differential Evolution (DE) algorithm to solve a water resources management problem, using an optimization procedure. The objective of the optimization scheme is to cover the daily water demand on the coastal aquifer east of the city of Heraklion, Crete, without reducing the subsurface water quality due to seawater intrusion. The RBFN is utilized as an on-line surrogate model to approximate the behavior of the aquifer and to replace some of the costly evaluations of an accurate numerical simulation model which solves the subsurface water flow differential equations. The RBFN is used as a local approximation model in such a way as to maintain the robustness of the DE algorithm. The results of this procedure are compared to the corresponding results obtained by using the Simplex method and by using the DE procedure without the surrogate model. As it is demonstrated, the use of the surrogate model accelerates the convergence of the DE optimization procedure and additionally provides a better solution at the same number of exact evaluations, compared to the original DE algorithm.

How evapotranspiration process may affect the estimation of water footprint indicator in agriculture

AbstractA critical component of water footprint (WF) indicator is the green WF that refers to the total rainwater evapotranspiration (ET) plus the water incorporated into the crop. From the definition of the WF the ET rate of an irrigated cropland needs to be reliably quantified especially in water scarce regions like Chania Valley in Crete. Based on this concept, different scenarios in terms of water consumption (basic and future) and hydrological conditions (average and dry) were evaluated. Furthermore, the WF was estimated, by applying different methods to calculate ET and effective rainfall, in order to determine whether the choice of the applied method may affect the agricultural WF estimation and lead to different outcomes as far irrigation water management practices. In this analysis, the WF was proven to be a useful tool as it is a multidimensional indicator [1], by determining the volume and the type of water use per ton of agricultural product. Furthermore, it was proved that the classification ...

Water footprint assessment considering climate change effects on future agricultural production in Mediterranean region

AbstractClimate change significantly affects every day’s human activities such as agriculture and tourism by altering the composition and parameters of global atmosphere over long period of time. In Greece, a substantial part of the national gross domestic product comes from agricultural production the efficiency (e.g. crop yield) of which mainly depends on adequacy and sufficiency of resources such as water and soil fertility. In this concept, the water footprint (WF) could be used as a monitoring indicator to evaluate applied agricultural schemes and potential adaptation measures in cultivated regions in Greece with respect to consumption of freshwater resources and deterioration of water receptors considering climate change scenarios. In the present paper, agricultural WF in two plains in Crete, Messara and Chania, are calculated in order to estimate the environmental impacts of the currently applied agricultural schemes on freshwater resources and soil productivity in the two plains. The analysis was ...

Artificial Neural Network and Differential Evolution methodologies used in single- and multi-objective formulations for the solution of subsurface water management problems

A single-objective Differential Evolution (DE) algorithm is combined with an Artificial Neural Network (ANN) to examine different operational strategies to cover the water demand in the Northern part of Rhodes Island, Greece. Successive calls to the simulator are used to provide the training data to the ANN, which is used as an approximation model to the simulator. Additionally, a multi-objective DE algorithm is combined with the pre-trained ANN to solve the same problem; the environmental constraints are realised through the definition of a second objective function, whereas the first objective function is the total pumping of the supply wells.

EVALUATION OF WATER SAVING MEASURES FOR MID-SIZED TOURIST LODGING UNITS: THE CASE OF SAMOS ISLAND, GREECE

Hotel sector causes significant environmental stress in both natural and built up areas due to their consumption of water and energy. In addition, the production of large volumes of liquid and solid waste results in a significant environmental footprint. The use of water and energy by hotels is strongly linked (e.g. energy is consumed for hot water, operation of the pool, preparation of meals, etc.) and usually referred to as the water – energy nexus. Thus, for big consumers like hotels, water and energy consumption should be addressed collectively as water-saving measures can lead to a reduction in energy consumption. The aim of this study is to assess the environmental performance of mid-sized hotel units by analyzing and quantifying their use of water. An analysis using a two-step approach was made of 8 accommodation facilities located on Samos Island, Greece: (i) a mapping of water use by adopting an end-use approach, and then (ii) an assessment of saving practices using three main criteria: savings, cost of investment and payback time. The preliminary results indicate that for small sized lodging units, water consumed inside the guest rooms accounts for the majority of all the water used and low-cost water saving measures and actions can reduce the pressure on water resources without disturbing guests, while increasing the financial profitability of a hotel.