Water shortage and drought, as the most important hydro-climatic hazards, cause significant damages in case of most continents including SE Europe. An experimental field established in Bačka region (Vojvodina Autonomous Province, North Serbia) for the purpose of droughts/water shortage monitoring and remote sensing under ongoing IPA project 'Water shortage hazard and adaptive water management strategies in the Hungarian-Serbian cross-border region' (WAHASTRAT). The main objective of this project is to determine water shortage con­flicts on a local and regional level, and to reveal the frequency, extent and severity of future hydro-cli­matic hazards. The locations of eight measurement stations selected on the principle of representativeness in term of terrain configuration and soil cover. An area in which measurement stations were placed, covers about 1000 km2 (12% of total area of Bačka) and includes geomorphic units which reliable represent the relief of the whole Bačka region. Measurement stations were placed on 4 out of 5 most common soil types in the Bačka and Vojvodina: chernozem, alluvial soils, smonitza and saline and alkali soils. A measurement equipment system was constructed for the requirements of the WAHASTRAT project. The aim was to design a user-friendly and affordable IT solution, which would enable continuous re­mote monitoring of meteorological parameters and soil moisture. Independent solar-powered meas­urement stations are able to automatically measure air temperature, air humidity, wind speed, wind di­rection, precipitation and soil moisture.

Charles Lyell (1797–1875) was an important loess pioneer. His major contribution was to distribute information on the nature and existence of loess via his influential book ‘The Principles of Geology’. He was obviously impressed by loess when he encountered it; the initial encounter can be split into three phases: conversations about loess; confronting the actual material in the field; and reading about loess in the literature. Detail can be added to an important phase in the scientific development of the study of loess. Significant events include conversations with Hibbert in 1831, conversations and explorations with von Leonhard and Bronn in 1832, the opportunity to include a section on loess in vol. 3 of ‘Principles’ for publication in 1833, a substantial Rhineland excursion in 1833, the reporting of the results of this excursion in 1834, discussions at the German Association for the Advancement of Science meeting in Bonn in 1835. Of all the people encountered perhaps H.G. Bronn was the most significant. Lyell eventually listed eleven people as relevant to the loess writings: Bronn, von Leonhard, Boue, Voltz, Steininger, Merian, Rozet, Hibbert, Noeggerath, von Meyer, Horner – of these Bronn, von Leonhard, Hibbert and Horner appear to have been the most significant, viewed from 2015.

Homolje is one of the most developed geomorphological areas in Eastern Serbia. Shallow karsts prevail across this region with cover vegetation and soil, with developed surfaces, and underground karst landforms. This type of terrain leads to the occurrence of different geomorphological landforms that stand out from the rest, primarily for their scientific, aesthetic and ecological value, uses, and tourism potential. Gorges can be singled out as the largest geosites, then uvalas, caves, karst bridges, and tufa accumulations. Two are on the National list of geoheritage of Serbia as protected natural monuments. As geoheritage protects only authentic and representative landforms, the main task of this paper is to point out the most significant measures to improve the unsatisfactory current state of geomorphosites of the Homolje area and possible solutions for their conservation, adequate use and better tourism promotion. This paper presents a review of geomorphological heritage in this region of Serbia with a focus on its conservation.

In this study we present interdisciplinary investigations of the Borkovac reservoir (Vojvodina, Serbia). The limnological characteristics of the reservoir were analysed in the scope of its sustainable use for irrigation, fishing and tourism. This multipurpose water accumulation has been established in 1975 as a part of regional hydrological system of the Fruška Gora mountain region.The main environmental problems recognized in this study were: water regime, intensive sedimentation in the reservoir, enhanced water eutrophycation and toxic cyanobacterial blooms. Observed environmental problems and proposed solutions in the case of the Borkovac accumulation including construction of the sediment precipitator at the Borkovac stream junction to lake, sediment removal, artificial water mixing and oxygenation, phosphorous inactivitation, different kinds of biomanipulations and biomass removal and introduction of ecoremedation methods could also be applied to other artificial water bodies of the Fruška Gora slopes.

The Western Balkans (Serbia, Croatia, Bosnia and Herzegovina, and Montenegro) occupy a transitional climatic position between the Mediterranean hotspot and the continental Balkan interior within Southeast Europe, yet multi-country, multi-model, station-resolved assessments of regional aridification remain scarce. We combined quality-controlled monthly temperature and precipitation records from 100 stations across Serbia, Croatia, Bosnia and Herzegovina, and Montenegro (1961–2020) with bias-corrected projections from a five-member CMIP6 ensemble (EC-Earth3, MPI-ESM1-2-HR, CNRM-CM6-1, MRI-ESM2-0, IPSL-CM6A-LR) under four SSP scenarios to 2100 and benchmarked these projections against five short-term forecasting baselines on a held-out 2019–2020 period. Aridity was quantified using the Ellenberg Climate Quotient (EQ) and De Martonne Index. Results: Ninety-eight of 100 stations showed significant warming (1961–2020, p < 0.05), and 26 showed significant aridification. Ensemble mean end-of-century EQ change ranged from −6.9% (SSP1-2.6) to +44.6% (SSP5-8.5, Montenegro), with the largest absolute increases in the Pannonian lowlands; inter-model uncertainty exceeded inter-scenario uncertainty by roughly a factor of two. Deep learning forecasters (TFT, N-HiTS) outperformed bias-corrected CMIP6 output for short-term, station-scale temperature forecasting, while a simple climatological baseline remained competitive for precipitation. CMIP6 projections and AI forecasting are complementary: multi-model ensembles remain indispensable for long-term, scenario-conditioned planning, while AI offers superior near-term predictive skill for operational decisions.

Benchmarking deep learning forecasters against classical and physically based numerical baselines remains uncommon in the time-series forecasting literature. Meteorological station networks offer an under-exploited evaluation environment, uniquely providing a physically based climate-model comparator alongside standard baselines. We evaluated eight forecasting approaches—climatology, SARIMA, Random Forest, and five deep learning architectures (TFT, N-HiTS, PatchTST, TiDE, xLSTM)—against bias-corrected output from a five-member CMIP6 ensemble, on 100 meteorological stations across four Western Balkan countries (monthly temperature and precipitation, 1961–2020), using non-parametric significance testing, a rolling-origin backtest (five windows, 2011–2020), and a five-seed robustness check. For temperature, all five deep learning architectures achieved lower MAE than the classical baselines (p < 10⁻⁹⁹), though PatchTST’s advantage over climatology was not significant; the best-performing architecture varied across seeds and evaluation windows, so we characterise a leading cluster (N-HiTS, TFT, TiDE, PatchTST) rather than a single winner. The primary temperature advantage was geographically broad-based, while the comparison against the physical-model baseline was robust to the choice of comparator GCM. For precipitation, by contrast, a simple climatological-mean baseline outperformed all five deep learning architectures with no exception across all five rolling-origin windows. The deep learning advantage over classical and physical baselines is thus variable-specific rather than universal. Meteorological station networks, combined with a physically based climate-model comparator, constitute a well-suited evaluation environment for the broader time series forecasting community.