Anomaly detection is a problem of finding unexpected patterns in a dataset. Unexpected patterns can be defined as those that do not conform to the general behavior of the dataset. Anomaly detection is important for several application domains such as financial and communication services, public health, and climate studies. In this paper, we focus on discovery of anomalies in monthly temperature data using DBSCAN algorithm. DBSCAN algorithm is a density-based clustering algorithm that has the capability of discovering anomalous data. In the experimental evaluation, we compared the results of DBSCAN algorithm with the results of a statistical method. The analysis showed that DBSCAN has several advantages over the statistical approach on discovering anomalies.

The main purpose of this paper is to investigate multitemporal land surface temperature (LST) changes by using satellite remote sensing data. The study included a real-time field work performed during the overpass of Landsat-5 satellite on 21/08/2011 over Salt Lake, Turkey. Normalized vegetation index (NDVI), vegetation condition index (VCI), and temperature vegetation index (TVX) were used for evaluating drought impact over the region between 1984 and 2011. In the image processing step, geometric and radiometric correction procedures were conducted to make satellite remote sensing data comparable within situmeasurements carried out using thermal infrared thermometer supported by hand-held GPS. The results showed that real-time ground and satellite remote sensing data were in good agreement with correlation coefficient (R2) values of 0.90. The remotely sensed and treated satellite images and resulting thematic indices maps showed that dramatic land surface temperature changes occurred (about2∘C) in the Salt Lake Basin area during the 28-year period (1984–2011). Analysis of air temperature data also showed increases at a rate of 1.5–2∘Cduring the same period. Intensification of irrigated agriculture particularly in the southern basin was also detected. The use of water supplies, especially groundwater, should be controlled considering particularly summer drought impacts on the basin.

This study examines the spatial and temporal dynamics of wind speeds over Turkey by analysing data from 206 weather stations for a 32‐year period (1975–2006). Trends in annual, seasonal, and monthly average wind speeds were determined using the Mann–Kendall trend test with the trend‐free pre‐whitening procedure. The strengths of trends were estimated by calculating the Sen's slope. The possible causes of wind speed changes were discussed. The analysis showed that the majority of the stations (73%) in Turkey had average wind speeds between 1.6 and 3.3 m s⁻¹ during the 32‐year period. From 1975 to 2006, 72% of stations had downward trends in annual average wind speeds. Downward trends were statistically significant at the 0.05 level for 62%. Significant upward trends were detected in only 16% of 206 stations. The rate of change in annual average wind speed data was on average −0.014 m s⁻¹ year⁻¹. The trends detected in monthly average wind speed data were mostly downward with an average strength between −0.007 and −0.017 m s⁻¹ year⁻¹. The directions and strengths of wind speed trends identified for the 1975–2006 period over Turkey are similar to the trends detected in wind speeds in many other regions over the earth. The changes in wind speeds in Turkey are most strongly related with the changes in general circulation patterns and air temperatures. The effects associated with changes in surface roughness and data quality are minor compared to other two factors.

Physically based or data-driven models can be used for understanding basinwide hydrological processes and creating predictions for future conditions. Physically based models use physical laws and principles to represent hydrological processes. In contrast, data-driven models focus on input–output relationships. Although both approaches have found applications in hydrology, studies that compare these approaches are still limited for data-scarce, semi-arid basins with altered hydrological regimes. This study aims to compare the performances of a physically based model (Soil and Water Assessment Tool (SWAT)) and a data-driven model (Nonlinear AutoRegressive eXogenous model (NARX)) for reservoir volume and streamflow prediction in a data-scarce semi-arid region. The study was conducted in the Tersakan Basin, a semi-arid agricultural basin in Türkiye, where the basin hydrology was significantly altered due to reservoirs (Ladik and Yedikir Reservoir) constructed for irrigation purposes. The models were calibrated and validated for streamflow and reservoir volumes. The results show that (1) NARX performed better in the prediction of water volumes of Ladik and Yedikir Reservoirs and streamflow at the basin outlet than SWAT (2). The SWAT and NARX models both provided the best performance when predicting water volumes at the Ladik reservoir. Both models provided the second best performance during the prediction of water volumes at the Yedikir reservoir. The model performances were the lowest for prediction of streamflow at the basin outlet (3). Comparison of physically based and data-driven models is challenging due to their different characteristics and input data requirements. In this study, the data-driven model provided higher performance than the physically based model. However, input data used for establishing the physically based model had several uncertainties, which may be responsible for the lower performance. Data-driven models can provide alternatives to physically-based models under data-scarce conditions.

The main purpose of this paper is to investigate multi-temporal land surface temperature (LST) changes of Konya Closed Basin (KCB) in Turkey using remotely sensed data. KCB is located in the semi-arid central Anatolian region of Turkey and hosts many important wetland sites including Salt Lake. Six Landsat-5 TM images selected from the 1984- 2011 period were used in the analysis. A real-time field work was performed during the overpass of Landsat-5 satellite on 21/08/2011 over Salt Lake to collect coordinated temperature measurements using a handheld GPS and thermal infrared thermometer. All satellite images were geometrically and radiometrically corrected to relate the image data with in-situ measurements. Thematic LST images were used to evaluate the conditions over the region between 1984 and 2011. The results show that real-time ground temperature and satellite remote sensing data were in good agreement with correlation coefficient (R2) values of 0.94. The remotely sensed and processed satellite images and resulting thematic indices maps show that dramatic land surface temperature changes occurred (about 2°C) in the KCB from 1984 to 2011. Analysis of climatic data supports this finding. Air temperatures and pan evaporation had significant upward trends from 1984 to 2011. Analysis conducted using both LST and climatic data prove that the basin has been experiencing drought in recent years. It is suggested that the use of water supplies, especially ground water should be controlled taking into account particularly summer drought impacts over the basin.

Water temperature affects all biological and chemical processes in water; therefore, it is an extremely important water quality parameter. Meteorological factors are among the most important factors that affect water temperatures. The aim of this study is to develop an artificial neural network (ANN) model to investigate the effects of meteorological parameters on water temperatures at Kızılırmak River in Turkey. Water temperature data were collected from gauging stations on Kızılırmak River, and meteorological data were acquired from the nearest meteorological stations. Air temperature, wind speed, relative humidity, and previous water temperatures were formed the input parameters. The model output included water temperatures. All data were available for the 1995–2007 period, with occasional missing records. The activation functions of the ANN model and the number of neurons in the hidden layer were selected by trial-and-error method to find the best results. The root mean square error and the correlation coefficient between observed and simulated water temperatures were used to assess the model success. The best results were obtained by using sigmoid activation function and scaled conjugate gradient algorithm. This study showed that meteorological data can be used to simulate water temperature with ANN model for Kızılırmak River.