Permafrost Distribution in the Southern Carpathians, Romania, Derived From Machine Learning Modeling

• Published in: Permafrost and periglacial processes Vol. 35; no. 3; pp. 243 - 261
• Main Authors: Popescu, Răzvan, Filhol, Simon, Etzelmüller, Bernd, Vasile, Mirela, Pleșoianu, Alin, Vîrghileanu, Marina, Onaca, Alexandru, Șandric, Ionuț, Săvulescu, Ionuț, Cruceru, Nicolae, Vespremeanu‐Stroe, Alfred, Westermann, Sebastian, Sîrbu, Flavius, Mihai, Bogdan, Nedelea, Alexandru, Gascoin, Simon
• Format: Journal Article
• Language: English
• Published: Chichester Wiley Subscription Services, Inc 01.07.2024
• Subjects: Bottom temperature; BTS; isolated patchy mountain permafrost; Learning algorithms; Machine learning; Massifs; Modelling; Mountains; Neural networks; Permafrost; Permafrost distribution; Regression models; Sensitivity analysis; Snow cover; Southern Carpathians; statistical modeling; Support vector machines; Winter snow
• ISSN: 1045-6740; 1099-1530
• DOI: 10.1002/ppp.2232

ABSTRACT Computer modeling of sporadic and isolated patches of mountain permafrost distribution is difficult to implement without overestimating it. The main challenge is to determine the very areas where the criteria for permafrost maintenance are met. This paper aims to modeling the permafrost distribution in the Southern Carpathians (SC), a typical marginal periglacial mountain range. For this purpose, a collection of 883 bottom temperature of late winter snow cover (BTS) points was used as a proxy for permafrost presence or absence in order to train several machine learning models. The performances of each model were evaluated with AUC with varying between 0.99 for Maxent and 0.74 for K‐nearest neighbors and most models (five) exhibiting values between 0.82 and 0.86. Other tests such as confusion matrices, sensitivity analyses, data shuffling, and data size reduction tests indicated that Maxent, AdaBoost, and support vector machine offered the best results while logistic regression, neural network, and gradient boosting exhibited rather poor permafrost distributions. The final ensemble median model indicated a total permafrost area of 19.2 km2 occupying 1%–9% of the alpine area of the studied massifs. NDVI proved crucial for permafrost prediction because it allows delimiting the debris surfaces where permafrost is probable.