Konstantinos Ioannou

An Integration of Statistics Temporal Methods to Track the Effect of Drought in a Shallow Mediterranean Lake

During the last decades, a progressive decrease of water level in shallow Mediterranean lakes was recorded. This contribution tried to identify whether the rapid decrease of the Lake Doiran (N. Greece) water level was associated with drought phenomena. Drought characteristics over the study area were revealed by employing the Standardized Precipitation Index (SPI) in different time scales. Negative trends of the SPI drought index were recognized by using the Mann-Kendall non parametric test, which suggested that drought conditions were intensified through time. The impact of the intense drought phenomena to the lake’s water level became evident by employing the Pearson correlation coefficient. A year ahead forecast of future drought conditions was achieved by training a hybrid ARIMA/ANN model. The predicted results indicated that mild drought conditions should be anticipated in the future and the water level would further drop as well.

Development of a decision support system for the study of an area after the occurrence of forest fire

There is a great diffusion of modern information systems in all areas of science. In the case of forestry, new information tools have emerged during the last 15 years which have helped to improve the work of foresters. Decision support systems (DSSs) are applications which are designed to help managers in the task of decision making, by accelerating the relevant decision-making processes, while simultaneously focusing on the conservation of natural, financial and human resources. In this paper, we describe the development of a DSS which has been designed to help managers in the process of decision making, in relation to areas that have been burnt by forest fires. In addition, the above system also provides the user with the capacity to create hypothetical (what-if) scenarios in order to achieve the best form of intervention. The relevant software was created using Visual C# and the weights of the various parameters were calculated using multi-criteria decision analysis.

Evaluation of artificial neural networks as a model for forecasting consumption of wood products

In specific sciences, such as forest policy, the need for anticipation becomes more urgent because it has to manage valuable natural resources whose protection and sustainable management is rendered essential. In this paper, a modern method has been used, known as artificial neural networks ANNs. In order to forecast the necessary future volumes of timber in Greece, a neural network has been developed and trained, using a variety of time series derived from the database of the Food and Agriculture Organisation of the United Nations FAO concerning Greece as external values and as internal value the Consumer Price Index has been used. Comparing the results of this project with linear and non-linear econometric forecasting models, it has been found that neural networks correspond, as confirmed by the econometric indicators MAPE average absolute percentage error and RMSE the square root of the percentage by the average sum of squares differences.

Forecasting Bank Stock Market Prices with a Hybrid Method: The Case of Alpha Bank

The present study aims at constructing Confidence Intervals (C.I) for the predicted values of a Time Series with the application of a Hybrid method. The presented methodology is complicated and thus is completed in different stages. Initially the Artificial Neural Networks (ANNs) is applied on the raw time series in order to estimate C.I of the forecasts. Then, the Bootstrap method is employed on the residuals generated by the preceded process. On the upper and lower limit of the estimated C.I., two new ANNs are employed in order to make point estimations (of the upper and lower limits) using of Object Oriented Programming. For the empirical analysis daily observations of the closing prices of Alpha Bank stocks have been used. The sample period is extended from 28/01/2004 until 30/11/2005. The nonstationarity of the time series employed in our study is not a forbidding condition for the estimation of the confidence intervals, in our case, since the level of bootstrap still provides a satisfactory approximation for the roots arbitrarily close to unity (Berkowitz, Kilian 1996). The accuracy of the forecasts was surveyed with the use of different criteria and the results were satisfactory.

Streamflow and Hydrological Drought Trend Analysis and Forecasting in Cyprus

The persistent water shortage in Cyprus has been alleviated by importing freshwater from neighbouring countries, and severe droughts have been met with financial reimbursement from the EU at least twice. The goal of this research is to investigate and perform short-term forecasting of both streamflow and hydrological drought trends over the island. Eleven hydrometric stations with a 34-year common record length of the mean daily discharge from 10/1979 to 09/2013 are used for this purpose, with the relevant upstream catchments considered to represent pristine conditions. The Streamflow Drought Index (SDI) successfully captures the hydrological drought conditions over the island, and the performance of the index is validated based on both the historic drought archives and results from other drought indices for the island. The Mann–Kendall (M-K) test reveals that the annual and seasonal time series of the discharge volumes always illustrate a decreasing but insignificant trend at a significance level of a = 0.05; additionally, the decrease per decade in the average annual streamflow volume based on Sen’s slope statistic is approximately −9.4%. The M-K test on the SDI reveals that drought conditions intensified with time. Ten autoregressive integrated moving average (ARIMA) models are built and used to forecast the mean monthly streamflow values with moderate accuracy; the best ARIMA forecast model in each catchment is derived by comparing two model-performance statistical measures for the different (p,d,q) model parameters. The predicted discharge values are processed by the SDI-3 index, revealing that non-drought conditions are expected in most catchments in the upcoming three months, although mild-drought conditions are anticipated for catchments 7, 8 and 9.

Forecasting precipitation and temperatures at the island of Cyprus to enhance wetland management

Droughts on the island of Cyprus are more frequently occurring during the last decades. This has and will have major impacts on natural resources, particularly on semi-aquatic and aquatic ecosystems. Wetlands are very important aquatic ecosystems with many functions and values, especially in semi-arid regions. The study area is the Wetland of the Larnanca Salt Lake that belongs to the Natura 2000 Network and the Ramsar Convention. It hosts thousands of migratory birds every year. Forecasting accurately the future climatic conditions of an area can greatly enhance the ability to provide the best possible managerial practices regarding a natural resource (e.g. wetland). These climate forecasts can provide significant information on future conditions of the Wetland of Larnaca Salt Lake, particularly when forecasting when and how long the drying conditions could last. In this study, an Artificial Neural Networks (ANN) was used as a tool for short term prediction of the precipitation in the study area. The methodology used two time series (temperature and precipitation) in order to train the ANN. Temperatures were used as the input variable to the ANN while precipitation was used as the output variables. The forecast was based on data from the period between 1993 and 2013. In order to estimate the accuracy of the produced results the correlation coefficient, the Root Mean Square Error (RMSE) and the Mean Absolute Percentage Error (MAPE) was correlated. Overall, this tool can help the responsible authorities of the wetland to manage it more efficiently.