ΕΛ EN
Home | People | Demetriou, Demetris
51
Scholarly Works
22%
OA Ratio
22%
Collaborative Ratio
Scholar

Demetriou, Demetris

Lecturer

Department of Civil Engineering and Geomatics

12
H-index (Scopus)
1469
Scholar Citations

Scholarly Works

Research Output

Recent Publications

Assessing ChatGPT’s legal reasoning in statutory land consolidation: The case of Cyprus

Demetriou, Demetris
Publishing year: 2026
Journal article
Land Use Policy, 2026, Volume 164
Repository
Land consolidation remains a cornerstone of rural development, but its implementation is often hindered by complex statutory frameworks and lengthy procedures. In Cyprus, where land consolidation has historically reduced fragmentation, the process faces new challenges amid declining agricultural importance and evolving policy priorities such as climate change resilience, sustainable development, and urban land readjustment. At the same time, artificial intelligence (AI) and large language models (LLMs) like ChatGPT are increasingly being considered as tools to support legal and planning processes. This study provides the first systematic evaluation of ChatGPT’s capacity to interpret and respond to legal questions derived from Cyprus’s Land Consolidation Law. Using a corpus of 100 questions across four levels of legal complexity, responses were assessed with a rubric measuring correctness, completeness, clarity, and interpretive depth. The results show strong performance in basic factual and procedural questions (98% accuracy for Type 1), moderate reliability in procedural and hypothetical reasoning (84% and 82% respectively), but significant decline in complex interpretive tasks (55% for Type 4). These findings highlight both the potential and the limitations of LLMs in statutory interpretation: they can provide accessible explanations and procedural guidance but cannot yet replace expert legal reasoning in ambiguous or high-stakes cases. The study contributes to...

Fifty-five years of experience with land consolidation in Cyprus: Lessons learned and future directions

Demetriou, Demetris
Publishing year: 2025
Journal article
Land Tenure Journal, 2025, Volume 1-2025
Repository
Over the past fifty-five years, land consolidation in Cyprus has significantly supported agricultural and rural development. This paper reviews the process from 1969 to present, highlighting major achievements, persistent challenges, and strategic recommendations for the future. Land consolidation has effectively addressed severe land fragmentation and inadequate infrastructure, hindering agricultural productivity. However, the continuous decline in the agricultural sector, criticism of favouring land speculation, and the 2013 financial crisis raised doubts about its necessity, leading to a decline in land consolidation efforts. The study synthesizes lessons learned from 15 critical aspects, such as the legal framework, stakeholder engagement, policy alignment, environmental protection, transparency, justice, and technology. It also discusses five future directions: the UN Agenda 2030 Goals, climate change, leveraging innovative technologies, developing new business models and integrating with smart agriculture. These insights not only provide a roadmap for revitalising land consolidation in Cyprus but also serve as a valuable guide for other countries facing similar challenges.

Future directions of land consolidation to address global challenges and technological innovations

Demetriou, Demetris
Publishing year: 2024
Conference paper
Tenth International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2024), 2024, Paphos, Cyprus, 2024
Repository
Land consolidation is a primary land management approach that aims to achieve sustainable agricultural development. Land redistribution is a complex decision-making process that involves reallocating land parcels and ownership. Ideally, it involves the production of a number of alternative plans, which can be assessed using multi-criteria decision making (MCDM), to rank alternatives and select the "best" plan based on their performance. Currently, a deterministic approach (D-MCDM) is used for this purpose, which inherently ignores uncertainties and variabilities of both the scores for each criterion as well as the weights assigned to each criterion. Thus, a core research question is: What will be the ranking of alternative land redistribution plans if a stochastic multi-criteria decision-making (S-MCDM) approach is utilised? Hence, we have utilized a specific type of S-MCDM method called Stochastic Multi-criteria Acceptability Analysis (SMAA). SMAA is designed to deal with decision-making problems where there is uncertainty in the criteria weights, performance of alternatives, or both. The SMAA methodology was implemented using an open-source software called JSMAA. The comparison of outputs resulting from deterministic and stochastic MCDM showed different rankings for alternative plans. This suggests that the use of D-MCDM when uncertainties exist can lead to misleading decisions. This finding is important for land consolidation planners, decision-makers, and stakeholders inv...

Assessing land redistribution plans using stochastic multi-criteria acceptability analysis

Demetriou, Demetris
Publishing year: 2024
Conference paper
Tenth International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2024), 2024, Paphos, Cyprus, 2024
Repository

Nowcasting significant wave height by hierarchical machine learning classification

Demetriou, Demetris, Michailides, Constantine, Onoufriou, Toula, Papanastasiou, George
Publishing year: 2021
Journal article
Ocean Engineering, 2021, Volume 242
Repository
This paper proposes an alternative method for nowcasting significant wave height (Hs) through the development of hierarchical machine learning classification models. In testing the hypothesis that hierarchical classification can improve Hs prediction, flat and hierarchical classifiers were developed and tested on field-data recorded on a coastal jetty located in the southern coasts of Cyprus. A comprehensive investigation of the performance of flat over hierarchical classification models yields that the proposed method provides greater flexibility throughout the model development stages. This flexibility is attributed to the manipulation of data before training, optimization of classifier's hyperparameters during training, and the curtailment of features post-training at each level of the hierarchy. It is demonstrated that, the hierarchical approach resulted in better classification performance across a plethora of performance metrics established for a comprehensive comparison. It is also shown that the increased performance of the proposed approach comes at the expense of complexity arising from performing computationally expensive operations and the requirement for development of multiple local classifiers. Still, the increased classification performance of the hierarchical approach highlights the potential of this original method and the requirement for a rigid framework to be constructed for the development of hierarchical models for Hs prediction.

Coastal zone significant wave height prediction by supervised machine learning classification algorithms

Demetriou, Demetris, Michailides, Constantine, Onoufriou, Toula, Papanastasiou, George
Publishing year: 2021
Journal article
Ocean Engineering, 2021, Volume 221, Issue 1
Repository
Explicit wave models and expensive sensor equipment capable of predicting and measuring wave parameters often carry a prohibitive computational and financial expense. To counter this, this paper proposes an alternative method for nowcasting coastal zone significant wave heights through the joint use of meteorological and structural data in the training of supervised machine learning models. In testing the hypothesis that structural data can improve model classification, artificial neural network and decision tree models were developed, trained and tested on field data recorded on a coastal jetty located in the southern coasts of Cyprus. A comprehensive investigation of the different models yields that the joint use of meteorological and structural features can improve classification performance, regardless of the network choice. It is also demonstrated that redundancy of training parameters could inject unwanted overfitting, reducing model generalization. To address this, a method for quantifying feature importance has been proposed by exploiting the nature of decision tree algorithms and the Gini impurity index, reaffirming that structural features do indeed benefit model classification. These results highlight the potential of tapping into the untapped pool of structural data for significant wave height prediction, paving the way for new research to be undertaken in this direction.

51
Unique publications
21.6%
Open access (11 publications; 17 without information)
21.6%
With other institutions (11 publications; 23 without information)

H-Index Reports

Index type Scopus Google Scholar Web of Science
H-index 12 16 1
H5-index 2 1 0
H10-index 7 6 1

Publications per year and source

No description yet.
Faculty
Faculty of Engineering and Technology
Department
Department of Civil Engineering and Geomatics
Title
Lecturer