The modeling of pan evaporation (Ep) trends in Slovak river sub-basins was conducted using advanced artificial intelligence (AI) techniques algorithms to accurately calculate evaporation rates based on daily climate data from 2010 to 2023 across eight sub-basins in the Slovak Republic. The AI modeling results reveal that the Bodrog, Hornád, Ipeľ, Morava, Slaná, and Váh river basins are experiencing increases in evaporation, while the Dunaj and Hron rivers show declining trends. This divergence may indicate varying ecological factors influencing the evaporation dynamics of each river. A comprehensive set of 28 machine learning (ML) and deep learning (DL) models was employed, including ML techniques such as linear regression, tree-based, support vector machines (both with and without kernels), ensemble, and Gaussian process methods; as well as DL approaches like neural networks (narrow, medium, wide, bilayered, and trilayered). Among these, stepwise linear regression provided the most optimal fit. The minimum redundancy maximum relevance (mRMR) method was utilized for feature selection to balance relevance and redundancy effectively. The results suggest that emphasizing relative humidity (RH) and minimum temperature (t_min) significantly enhances accuracy, highlighting the critical roles of these factors in modeling pan evaporation trends. The results offer precise evaporation analyses to improve water management and lessen scarcity.

This study examines the impact of climate change on agricultural productivity in Slovakia, the Czech Republic, and Poland, focusing on temperature sums influencing the growing season. Using meteorological data from 2001 to 2020, the research analyses the onset and termination of temperatures ≥5 °C (growing season). Temperature sums for two periods (2001–2010, 2011–2020) were calculated and future temperature projections under three scenarios (+1.5 °C, +2.6 °C, +3.6 °C) were developed. Results indicate regional variation in temperature sums, with 69% of the area falling in the 2900–3100 °C range, and Poland showing the highest percentage (81%). In the second decade of the 21st century, temperature sums shifted to the 3100–3300 °C range, affecting 63% of the region. The projections indicate a substantial increase in temperature sums, with the most optimistic scenario (+1.5 °C) leading to the dominance of the 3700–3900 °C range. The warmest areas (West Pannonian Basin), show a temperature sum of 4900–5100 °C. The comparison of predicted and observed temperature sums for 2011–2020 shows a minimal error (±3% in Slovakia and ±4% in Poland and the Czech Republic), confirming the projections. These findings highlight the importance of adaptive strategies in agriculture, particularly fruit farming, to mitigate the climate change effects.

The projected climate change in Slovakia is expected to have a significant impact on temperature and moisture conditions in agricultural production, as well as on phenological patterns and soil properties. These alterations have the potential to diminish crop yields in regions experiencing summer heat, augment soil evaporation, and elevate the probability of drought. The objective of this study was to evaluate and revise the spatial extent of vegetation zones and agricultural land. A detailed analysis of the past 30 years revealed that the growing season has become both earlier in the year and later in the year in terms of its onset and cessation. Projections indicate that, by 2091–2100, the great growing season (GGS) will be 25–30 days longer and the main growing season (MGS) 20 days longer than at present. The results indicate that the extended growing seasons will encompass larger areas and gradually shift to higher altitudes. At present, the 220–240-day category of the GGS spatial domain is dominant (1.7–2.3 million hectares), while durations of the GGS exceeding 260 days, which were absent in the 1971–1980 period, are expected to increase the area of the growing season by approximately 55,000 hectares by 2100. For the MGS, the 160–190-day category remains prevalent (approximately 2.5 million hectares), with only moderate future increases of up to 220 days being expected. It is anticipated that extended durations will remain constrained, encompassing less than 50,000 hectares.

Projected climate change in Slovakia is expected to significantly influence temperature and moisture conditions in agricultural production, as well as phenological patterns and soil properties. These shifts may reduce crop yields in areas already constrained by summer heat, enhance soil evaporation, and increase drought risk. The objective of this study was to assess and generate updated spatial outputs of vegetation zones and agricultural land. Analysis of the past 30 years revealed both earlier onsets and delayed endings of the growing season. Projections indicate that by 2091–2100, the great growing season will lengthen by approximately 25–30 days, and the main growing season by about 20 days relative to the present. Results suggest that extended growing seasons will encompass larger areas and gradually shift to higher altitudes. The 220–240-day category of the great growing season currently dominates (1.7–2.3 million ha), while durations exceeding 260 days, absent in 1971–1980, are expected to expand to about 55,000 ha by 2100. For the main growing season, the 160–190-day category remains prevalent (≈2.5 million ha), with only moderate future increases expected up to 220 days. Longer durations will likely remain limited, covering less than 50,000 ha.

The modelling of pan evaporation (Ep) trends in Slovak river basins was performed by utilizing artificial intelligence (AI) techniques algorithms to accurately forecast evaporation rates based on daily climate data spanning from 2010 to 2023 across eight sub-basins within the Slovak Republic. The findings derived from the AI modelling indicate that the river basins of Bodrog, Hornád, Ipeľ, Morava, Slaná, and Váh are experiencing increases in evaporation measurements, whereas the Dunaj and Hron rivers demonstrate declining trends. This divergence may suggest the presence of differing ecological factors that affect the evaporation dynamics associated with each river. In this study, a comprehensive set of 28 machine learning and deep learning models was employed, including: Machine Learning (ML): Linear Regression, Tree-Based, Support Vector Machines (both with and without Kernels), Ensemble, and Gaussian Process methods; Deep Learning (DL): Neural Networks (Narrow, Medium, Wide, Bilayered, and Trilayered). The Stepwise Linear Regression yielded the most optimal fit. The Minimum Redundancy Maximum Relevance (mRMR) method was utilized to assess the efficacy of feature selection by concentrating on both relevance and redundancy. The results suggest that placing greater emphasis on relative humidity (RH) and minimum temperature (tmin) may significantly enhance the predictive accuracy of the model.