In this study, different interpolation techniques are presented, assessed, and compared for the estimation of soil iron (Fe) contents in locations where observations were not available. Initially, 400 soil samples from the Kozani area, which is near Polifitou Lake in northern Greece, were randomly collected from 2013 to 2015 and were analysed in the laboratory to determine the soil Fe concentrations and pH. The soil Fe concentrations were examined for spatial autocorrelation, and semivariograms were used to determine whether pH and Fe exhibited spatial cross correlation. Three interpolation methods, including Ordinary Kriging, Universal Kriging, and Co-Kriging, were applied, and their results were compared with the use of two different cross-validation methods. In the current study, there was evidence of spatial cross correlation of soil Fe and pH for each year, which was subsequently used to improve the interpolation results in locations where there were no measurements. In nearly all cases, Co-Kriging, which takes advantage of the covariance between the two regionalized variables (Fe and pH), outperformed the other interpolation techniques each year.

In the current paper we assess different machine learning (ML) models and hybrid geostatistical methods in the prediction of soil pH using digital elevation model derivates (environmental covariates) and co-located soil parameters (soil covariates). The study was located in the area of Grevena, Greece, where 266 disturbed soil samples were collected from randomly selected locations and analyzed in the laboratory of the Soil and Water Resources Institute. The different models that were assessed were random forests (RF), random forests kriging (RFK), gradient boosting (GB), gradient boosting kriging (GBK), neural networks (NN), and neural networks kriging (NNK) and finally, multiple linear regression (MLR), ordinary kriging (OK), and regression kriging (RK) that although they are not ML models, they were used for comparison reasons. Both the GB and RF models presented the best results in the study, with NN a close second. The introduction of OK to the ML models’ residuals did not have a major impact. Classical geostatistical or hybrid geostatistical methods without ML (OK, MLR, and RK) exhibited worse prediction accuracy compared to the models that included ML. Furthermore, different implementations (methods and packages) of the same ML models were also assessed. Regarding RF and GB, the different implementations that were applied (ranger-ranger, randomForest-rf, xgboost-xgbTree, xgboost-xgbDART) led to similar results, whereas in NN, the differences between the implementations used (nnet-nnet and nnet-avNNet) were more distinct. Finally, ML models tuned through a random search optimization method were compared with the same ML models with their default values. The results showed that the predictions were improved by the optimization process only where the ML algorithms demanded a large number of hyperparameters that needed tuning and there was a significant difference between the default values and the optimized ones, like in the case of GB and NN, but not in RF. In general, the current study concluded that although RF and GB presented approximately the same prediction accuracy, RF had more consistent results, regardless of different packages, different hyperparameter selection methods, or even the inclusion of OK in the ML models’ residuals.

The sustainable management of natural resources under climate change conditions is a critical research issue. Among the many approaches emerged in recent times, the so-called ‘nexus approach’ is gaining traction in academic and policy circles. The nexus approach presupposes the analysis of bio-physical, socio-economic and policy interlinkages among sectors (e.g., water, energy, food) for the identification of integrated solutions and the support of policy decisions. Ultimately, the nexus approach aims to identify synergies and trade-offs among the nexus dimensions. Concerning policy, the nexus approach focuses on policy coherence, i.e., the systematic identification and management of trade-offs and synergies between policies across sectors. This paper investigates the coherence between policies on the water-land-energy-food-climate nexus in Greece. The systematic analysis of policy documents led to the elicitation of nexus-related policy objectives and instruments. Then, the coherence among objectives and between objectives and instruments was assessed using the methodology proposed by Nilsson et al. A stakeholder (trans-disciplinary) orientation was adopted and the need to incorporate stakeholders’ recommendations as to policy coherence assessment was highlighted. Overall, the findings revealed that climate and food/agricultural policies represent critical future priorities in Greece by stimulating progress in other nexus-related policies (energy, water, land policies) and being positively influenced by them.

In 2015 the updated Agenda 2030, outlining the new priorities towards future sustainability, was published by the United Nations reflecting the general directions towards a fairer and more sustainable pattern of socio-economic development. The specialisation of the 17 Sustainable Development Goals (SDGs) and indicators into local contexts constitutes a basic prerequisite as particular characteristics, needs and peculiarities should be considered. This paper focuses on the exploration of local-oriented indicators and policy recommendations that have the potential to boost the successful implementation of SDGs in Greece. A nexus approach is adopted underlining the need to analyse complexities, motivate systemic thinking and develop integrated policies targeting at the sustainable and efficient use of resources. It also highlights the need for designing local-specific indicators and policy initiatives, encapsulating particular characteristics and conditions and boosting the advancement of SDGs. Such an approach has the potential to be implemented not only at national but also at an operational level in local scale (e.g., River Basin Scale). The outcomes indicate that emphasis should be given on smart water management and precision agriculture, extensive use of technologies capturing Greenhouse Gases (GHGs), dynamic penetration of Renewable Energy Sources (RES) in gross final energy production/consumption and protection of terrestrial ecosystems.

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