Kamnolom v naselju Podpeč pri Ljubljani velja za glavni kamnolom rimske kolonije Emone (Ljubljana). Obstoj antičnega kamnoloma v Podpeči je bil do sedaj utemeljen le na podlagi makroskopske podobnosti med Členom litiotidnega apnenca, ki izdanja v Podpeči, in z njim povezanimi rimskimi spomeniki, odkritimi v Ljubljani. V okviru pričujočega dela smo skušali poiskati oprijemljive arheološke in geoarheološke dokaze za njegov obstoj. V skrajno severnem delu kamnoloma smo izvedli arheološko sondiranje, hkrati pa natančno določili sestavo apnenca na tem območju in v 288 izdelkih iz antične Emone. Sondiranje severno od modernega kamnoloma je odkrilo dobro ohranjene sledove rimskodobne kamnoseške dejavnosti. Hkrati je litološka analiza spomenikov iz Emone razkrila, da je kar 182 (ali 64 odstotkov) analiziranih spomenikov izdelanih iz apnenca, litološko identičnega različkom, ki izdanjajo v Podpeči. Ti različki se prostorsko grupirajo severno od modernega kamnoloma. Pri tem sicer ostaja odprto vprašanje pripadnosti nekaterih različkov apnenca v izdelkih, ki so brez diagnostičnih komponent in bi lahko pripadali tudi nekoliko starejšemu Členu krkinega apnenca. Rekonstrukcijo obsega starega kamnoloma omogoča primerjava faciesov izvornih litostratigrafskih enot in izdelkov, pa tudi historična analiza zgodnjih kartografskih in katastrskih dokumentov. Analiza najzgodnejših izdelkov je omogočila hipotezo o prihodu kamnosekov iz kamnoloma v Nabrežini.

Pronounced tectonic and paleogeographic changes were detected in the Alpine–Pannonian region during the Miocene at the interface between the Alps, the Dinarides, and the Pannonian Basin. To understand the major tectonic, paleogeographic, and paleoclimatic changes during this period, geochemical and mineralogical investigations were carried out on the fine-grained clastic sedimentary rocks in the Tunjice Hills. The paleoweathering indicates a cold and/or arid to a warm and humid period. The paleoclimate and the regional climatic conditions correspond well with the Middle Miocene Climatic Optimum. The mineral composition shows an abundance of quartz and calcite. Quartz is associated with detrital origin from volcanic and metamorphic rocks of the Eastern and Southern Alps and with authigenic processes in sediments. Calcite is related to authigenic origin formed in shallow marine environments and to detrital provenance from the Southern Alps. Not all discriminant functions based on major oxides provided adequate results in determining the tectonic setting. The source rocks were subjected to oceanic island arc and collision. Moreover, sedimentation was influenced by both active and passive margin settings. The former is related to the Alpine collision, which continued from the Cenozoic onward, and the latter is connected to the processes associated with the formation of the Pannonian Basin System, which began in the late Early Miocene.

Determining the lithostratigraphic provenance of limestone artefacts is challenging. We addressed the issue by analysing Roman stone artefacts, where previously traditionalpetrological methods failed to identify the provenance of 72% of the products due to the predominance of micrite limestone. We applied statistical classification methods to 15 artefacts using linear discriminant analysis, decision trees, random forest, and support vector machines. The latter achieved the highest accuracy, with 73% of the samples classified to the same stratigraphic member as determined by the expert. We improved classification reliability and evaluated it by aggregating the results of different classifiers for each stone product. Combining aggregated results with additional evidence from paleontological data or precise optical microscopy leads to successful provenance determination. After a few samples were reassigned in this procedure, a support vector machine correctly classified 87% of the samples. Strontium isotope ratios (⁸⁷Sr/⁸⁶Sr) proved particularly effective as provenance indicators. We successfully assigned all stone products to local sources across four lithostratigraphic members, thereby confirming local patterns of stone use by Romans. We provide guidance for future use of statistical learning in provenance determination. Our integrated approach, combining geological and statistical expertise, provides a robust framework for challenging provenance determination.

The paper presents the lithologies used in the stone products of Neviodunum (modern Drnovo in Slovenia), a Roman municipium in south‐western Pannonia. For this purpose, 95 stone monuments were assessed. Petrographic and biostratigraphic analyses were carried out on 56 archaeological and 57 geological samples. Our research shows that, besides some rare exceptions, most stone products refer to three lithostratigraphic units: the Middle Miocene ‘Lithothamnium’ Limestone Member of the Laško Formation, the Upper Cretaceous Krško Formation and the Early Jurassic Krka Limestone Member of the Podbukovje Formation.