Geosciences is a field of great societal relevance that requires solutions to several urgent problems facing our humanity and the planet. As geosciences enters the era of big data, machine learning (ML)-that has been widely successful in commercial domains-offers immense potential to contribute to problems in geosciences. However, problems in geosciences have several unique challenges that are seldom found in traditional applications, requiring novel problem formulations and methodologies in machine learning. This article introduces researchers in the machine learning (ML) community to these challenges offered by geoscience problems and the opportunities that exist for advancing both machine learning and geosciences. We first highlight typical sources of geoscience data and describe their properties that make it challenging to use traditional machine learning techniques. We then describe some of the common categories of geoscience problems where machine learning can play a role, and discuss some of the existing efforts and promising directions for methodological development in machine learning. We conclude by discussing some of the emerging research themes in machine learning that are applicable across all problems in the geosciences, and the importance of a deep collaboration between machine learning and geosciences for synergistic advancements in both disciplines.

A research agenda for intelligent systems that will result in fundamental new capabilities for understanding the Earth system.

Trace-element data (including the rare-earth elements) in the crustal sequence of the Neotethyan Neyriz ophiolite in southwest Iran indicate normal mid-ocean ridge basalt (N-MORB) or island-arc tholeiite chemistry for the Tang-e Hana basalt. The data suggest that the Tang-e Hana rhyodacite, basalt, plagiogranite, and gabbro derived from a low-K tholeiitic parent magma. Trace-element distributions in amphibolite clasts, in the sole detachment of the ophiolite south of Lake Neyriz, correlate well with distributions in basalt clasts in the mélange and in the Tang-e Hana basalt. These trace elements suggest that the amphibolite originated from metamorphism and deformation of a tholeiitic basalt protolith. New 40Ar/39Ar incremental heating plateau ages from two hornblende plagiogranite specimens, in the crustal sequence in Tang-e Hana, are 92.07 ± 1.69 and 93.19 ± 2.48 Ma. Isotopic data for five Tang-e Hana basalts yield εNd values of +7.8 and +7.9, and 87Sr/86Sr values of 0.70368 to 0.70476. The isotopic compositions, ophiolite tectonostratigraphy, and correlation of the 40Ar/39Ar cooling (plagiogranite) and deformation (amphibolite) ages suggest emplacement of the Neyriz ophiolite either into an accretionary prism, through offscraping and subduction erosion, and (or) formation in a supra-subduction zone environment, around 82–96 Ma. Progressive accretion probably led to the development of a fore-arc basin and deposition of Upper Cretaceous – Eocene fore-arc and arc-derived sediments on the ophiolite.

No abstract

No abstract