The subject of this research is the application of remote sensing and geographic information systems (GIS) in identifying, monitoring, and analyzing wildfires in the Sana River basin in Bosnia and Herzegovina in 2017. The research aims to determine the weather conditions that favor the occurrence of wildfires and their spatial impact on vegetation and to assess the degree of land degradation after the wildfires. Through the calculation of the Standardized Precipitation-Evapotranspiration Index (SPEI), critical dry periods with significantly negative values were identified in July (− 1.60) and August (− 1.94), indicating severe droughts with a high hazard of wildfire occurrence. Additionally, the calculation of the Angstrom index identified a period of high wildfire hazard (from July 5 to August 5, 2017). Vegetation condition monitoring and burn severity during the high-hazard period were assessed by calculating the differenced Normalized Difference Vegetation Index (dNDVI) and the differenced Normalized Burn Ratio (dNBR). By intersecting dNDVI and dNBR with the results of the supervised classification, the impact of wildfires on different land use types was effectively assessed. It was determined that a total of 214.61 km² (dNDVI) and 168.77 km² (dNBR) of meadows and pastures, 270.45 km² (dNDVI) and 35.2 km² (dNBR) of forested areas, and 30.12 km² (dNDVI) and 17.95 km² (dNBR) agriculture areas where exposed to moderate, high, and very high wildfires. Additionally, a total of 19,077 residents were affected by the wildfires. The research results highlight the need to develop and implement more effective prevention and hazard management strategies, particularly in protecting the study area’s forest ecosystems and agriculture.

The subject of the research paper is the use of remote sensing in monitoring and analyzing the impact of climate change on the occurrence of extreme precipitation, and the cause-and-effect occurrence of floods in the area of the Sana River Basin in Bosnia and Herzegovina. The goal is to process the "product" of remote sensing to identify the time intervals of occurrence of extreme precipitation, to assess their impact on water levels, and to map potential floods in space. Spatial identification of zones that are at risk of flooding is an integral part of the aforementioned goal. Precipitation monitoring was performed by processing Climate Hazards Group InfraRed Precipitation with Station Data through the Google Earth Engine platform. The observed 30-year period (1992-2022) was compared with the average precipitation for 2017, 2018 and 2019. The impact of extreme precipitation on the water level of the Sana River was analyzed. Flooding periods have been identified: February and December 2017, March 2018 and May 2019. Mapping of flooded areas was carried out by pre-processing and post-processing of Sentinel-1 radar satellite images. The total flooded area is: 710.38 ha (February 2017), 496.79 ha (December 2017), 417.86 ha (March 2018) and 422.42 ha (May 2019). Based on the identified flooded areas, a flood risk map was created on the main course of the Sana River. The research contributes to a better understanding of the changes that occur in the area under the influence of climate change, and the data presented are important for numerous practical issues in the field of water resource management and flood protection.

The subject of this research is the exploration of the potential of remote sensing and Geographic Information Systems (GIS) for basin-scale spatio-temporal monitoring of drought and its impacts in the Ukrina River Basin, Bosnia and Herzegovina (BH), during the last decade (2015–2024). The aim is to integrate meteorological, hydrological, agricultural, and socio-economic drought signals and to delineate areas of long-term drought exposure. Meteorological drought was evaluated using CHIRPS precipitation and the Standardized Precipitation Index (SPI) calculated at 1-, 3-, 6-, and 12- month accumulation scales using Gamma fitting and a fixed long term reference period; hydrological drought was examined using available water-level records complemented by the Standardized Water Level Index (SWLI) and supported by correspondence with standardized ERA5-Land runoff anomalies; agricultural drought was mapped using remote sensing indices—the Temperature Condition Index (TCI), Vegetation Condition Index (VCI), and Vegetation Health Index (VHI)—calculated from MODIS satellite data; and socio-economic effects were assessed using municipal crop-production statistics (2015–2019). The results indicate that drought conditions were most pronounced in 2015, 2017, 2021, and especially 2022, showing consistent agreement between precipitation deficits, hydrological responses, and vegetation stress, while 2016, 2018–2020, 2023, and 2024 were generally more favorable. As a key novelty, a persistent drought-prone zone was delineated by intersecting drought-affected areas across major episodes, providing a basin-scale identification of chronic drought hotspots for a river basin in BH. The persistent zone covers 40.02% of the basin and spans nine cities and municipalities, with >93% located in Prnjavor, Derventa, Stanari, and Teslić. Hotspots are concentrated mainly in lowlands below 400 m a.s.l., with a statistically significant concentration across lower elevation classes, indicating higher long-term exposure in the central and northern valley sectors, and land use overlay further highlights high relative exposure of productive land. Overall, the integrated remote sensing and GIS framework strengthens drought monitoring by providing spatially explicit and repeatable evidence to support targeted adaptation planning and drought-risk management.

The paper investigates the spatial distribution of the seasonal and annual precipitation in Bosnia and Herzegovina. The mean monthly precipitation data from 40 meteorological stations covering the standard climatological thirty‐year period (1961−1990) were used for the analysis. Seven precipitation‐based parameters were used to regionalize climate in Bosnia and Herzegovina by using the Principal Component Analysis and clustering techniques. The spatial patterns of precipitation were determined by using the R‐mode principal component analysis with varimax rotation. The first two principal components, which describe 97.60% of the total variance, were taken into consideration. The varimax rotated scores were subjected to the Cluster Analysis in order to identify homogeneous precipitation regions over the territory of Bosnia and Herzegovina. The agglomerative hierarchical clustering identified three sub‐regions with different precipitation regimes. The complex orography, i.e., the influence of the Pannonian Basin, the Dinaric Alps, and the Adriatic Sea, is one of the most decisive factors that affect spatial patterns of precipitation in Bosnia and Herzegovina.

Израда карте начина коришћења земљишта са фокусом на пољопривредно земљиште и озиме културе идентификован је као примарни циљ овог истраживања. Примјеном метода даљинске детекције, одабиром, обрадом и анализом мулти-временске серије радарских Сентинел-1 и оптичких Сентинел-2 сателитских снимака изведене су варијабле неопходне за покретање надзиране пиксел базиране класификације. Покретањем алгоритама машинског учења класификовани су сателитски снимци са укупном тачношћу од 0.96 и Капа коефицијентом 0.95. Израђена је карта озимих усјева за производну сезону 2019/2020 за подручје истраживања које се налази у оквирима природно-географске цјелине Лијевча поља. Истраживање је показало да су код озимих култура убједљиво највеће површине под озимом пшеницом. Комбинација оптичких и радарских сателитских снимака дала је боље резултате него појединачно оптички или радарски. Коришћење мулти-временске серије сателитских снимака допринијело је већој тачности и поузданости класификације. Мјерење спектралне дистанце показало се корисно у процесу дефинисања оптималног времена агрегације. Читав процес припреме сателитских снимака и сам процес класификације изведен је у Google окружењу под називом Google Earth Engine употребом његових ресурса који су доступни, бесплатни и захваљујући којима је процес мулти-временске и мулти-сензорске класификације подручја истраживања био изводљив.