ABSTRACT Kīlauea Volcano’s active summit lava lake posed hazards to downwind residents and over 1.6 million Hawai‘i Volcanoes National Park visitors each year during 2008–2018. The lava lake surface was dynamic; crustal plates separated by incandescent cracks moved across the lake as magma circulated below. We hypothesize that these dynamic thermal patterns were related to changes in other volcanic processes, such that sequences of thermal images may provide information about eruption parameters that are sometimes difficult to measure. The ability to learn about concurrent gas emissions and seismic activity from a remote thermal time-lapse camera would be beneficial when conditions are too hazardous for field measurements. We applied a machine learning algorithm called self-organizing maps (SOM) to thermal infrared time-lapse images of the lava lake collected hourly over 23 April–21 October 2013 ( n = 4354). The SOM algorithm can take thousands of seemingly different images, each representing the spatial distribution of relative temperature across the lava lake surface, and group them into clusters based on their similarities. We then related the resulting clusters to sulfur dioxide emissions and seismic tremor activity to characterizeties between the SOM classification and different emplacement conditions. The SOM classification results are highly sensitive to the normalization method applied to the input images. The standard pixel-by-pixel normalization method yields a cluster of images defined by the highest observed SO 2 emission levels, elevated surface temperatures, and a high proportion of cracks between crustal plates. When lava lake surface patterns are isolated by minimizing the effect of temperature variation between images, relationships with seismic tremor activity emerge, revealing an “intense spatter” cluster, characterized by unstable, broken-up crustal plate patterns on the lava lake surface. This proof of concept study provides a basis for extending the SOM classification method to hazard forecasting and real-time volcanic monitoring applications, as well as comparative studies at other lava lakes.

Abstract We applied a computational method to aid in clustering 41 alluvial fans along the southern coast of the Gulf of Corinth, Greece. The morphology of the fans and their catchments was quantitatively expressed through 12 morphometric parameters estimated using geographical information system techniques and the relationships among the geomorphometric features of the fans and their catchments were examined. Self-organizing maps were used to investigate the clustering tendency of fans based on morphometric variables describing both the fans and their corresponding catchments. The results of unsupervised classification through the self-organizing maps method revealed correlations among the morphometric parameters and five groups of alluvial fans were identified. These groups had a clear physical explanation, showed a preferred geographical distribution and reflected the processes related to the development of the fans. The geographical distribution of the fan catchment groups was partially controlled by variations in the relative tectonic uplift rate, which was the main control on the accommodation space for the development and accretion of the fans. The smaller fans were located in the central part of the study area, where the uplift rates were higher, whereas larger fluvial-dominated fan deltas formed to the east and west of the central group, where the uplift rates were lower.

Abstract Autogenic dynamics and self-organization in sedimentary systems are increasingly viewed as significant and important processes that drive erosion, sediment transport, and sediment accumulation across the Earth’s surface. These internal dynamics can dramatically modulate the formation of the stratigraphic record, form biologically constructed depositional packages, affect ecological patterning in time and space, and impact aspects of geochemical sedimentation and diagenesis. The notion that autogenic processes are local phenomena of short duration and distance is now recognized as false. Understanding autogenic dynamics in sedimentary systems is thus essential for deciphering the morphodynamics of modern sedimentary systems, accurately reconstructing Earth history, and predicting the spatial and temporal distribution of sedimentary and paleobiologic features in the stratigraphic record. The 13 papers in the publication, Autogenic Dynamics and Self-Organization in Sedimentary Systems, present exciting new ideas and research related to sedimentology, stratigraphy, ecology, paleobiology, sedimentary geochemistry, and diagenesis. Five papers summarize the current state of thinking about autogenic processes, products, and patterns in fluvial–deltaic, eolian, and carbonate depositional systems, and in paleobiologic and geochemical contexts. A second group of papers provides perspectives derived from numerical modeling and laboratory experiments. Thefinal section consists of field studies that explore autogenic processes and autogenically modulated stratigraphy in five case studies covering modern and ancient fluvial, deltaic, and shelf settings. These papers should stimulate further research into how self-organization might promote a better understanding of the sedimentary record.