Molecular chirality is critical to biochemical function, but it is unknown when chiral selectivity first became important in the evolutionary transition from geochemistry to biochemistry during the emergence of life. Here, we identify key transitions in the selection of chiral molecules in metabolic evolution, showing how achiral molecules (lacking chiral centers) may have given rise to specific and abundant chiral molecules in the elaboration of metabolic networks from geochemically available precursor molecules. Simulated expansions of biosphere-scale metabolism suggest new hypotheses about the evolution of chiral molecules within biochemistry, including a prominent role for both achiral and chiral compounds as nucleation sites of early metabolic network growth, an increasing enrichment of molecules with more chiral centers as these networks expand, and conservation of broken chiral symmetries along reaction pathways as a general organizing principle. We also find an unexpected enrichment in large, non-polymeric achiral molecules. Leveraging metabolic data of 40,023 genomes and metagenomes, we analyzed the statistics of chiral and achiral molecules in the large-scale organization of metabolism, revealing a chiral-enriched phase of network organization evidenced by system-size dependent chiral scaling laws that differ for individuals and ecosystems. By uncovering how metabolic networks could lead to chiral selection, our findings open new avenues for bridging metabolism and genetics-first approaches to the origin of chirality, allowing tools for better timing of major transitions in molecular organization during the emergence of life, understanding the role of chirality in extant and synthetic metabolisms, and informing targets for chirality-based biosignatures.
Pre-training foundation models has become the de-facto procedure for deep learning approaches, yet its application remains limited in the geological studies, where in needs of the model transferability to break the shackle of data scarcity. Here we target on the X-ray fluorescence (XRF) scanning data, a standard high-resolution measurement in extensive scientific drilling projects. We propose a scalable self-supervised learner, masked autoencoders on XRF spectra (MAX), to pre-train a foundation model covering geological records from multiple regions of the Pacific and Southern Ocean. In pre-training, we find that masking a high proportion of the input spectrum (50\%) yields a nontrivial and meaningful self-supervisory task. For downstream tasks, we select the quantification of XRF spectra into two costly geochemical measurements, CaCO$_3$ and total organic carbon, due to their importance in understanding the paleo-oceanic carbon system. Our results show that MAX, requiring only one-third of the data, outperforms models without pre-training in terms of quantification accuracy. Additionally, the model's generalizability improves by more than 60\% in zero-shot tests on new materials, with explainability further ensuring its robustness. Thus, our approach offers a promising pathway to overcome data scarcity in geological discovery by leveraging the self-supervised foundation model and fast-acquired XRF scanning data.
Over the past several decades, conventional spectral analysis techniques of polluted white dwarfs have become powerful tools to learn about the geology and chemistry of extrasolar bodies. Despite their proven capabilities and extensive legacy of scientific discoveries, these techniques are however still limited by their manual, time-intensive, and iterative nature. As a result, they are susceptible to human errors and are difficult to scale up to population-wide studies of metal pollution. This paper seeks to address this problem by presenting cecilia, the first Machine Learning (ML)-powered spectral modeling code designed to measure the metal abundances of intermediate-temperature (10,000$\leq T_{\rm eff} \leq$20,000 K), Helium-rich polluted white dwarfs. Trained with more than 22,000 randomly drawn atmosphere models and stellar parameters, our pipeline aims to overcome the limitations of classical methods by replacing the generation of synthetic spectra from computationally expensive codes and uniformly spaced model grids, with a fast, automated, and efficient neural-network-based interpolator. More specifically, cecilia combines state-of-the-art atmosphere models, powerful artificial intelligence tools, and robust statistical techniques to rapidly generate synthetic spectra of polluted white dwarfs in high-dimensional space, and enable accurate ($\lesssim$0.1 dex) and simultaneous measurements of 14 stellar parameters -- including 11 elemental abundances -- from real spectroscopic observations. As massively multiplexed astronomical surveys begin scientific operations, cecilia's performance has the potential to unlock large-scale studies of extrasolar geochemistry and propel the field of white dwarf science into the era of Big Data. In doing so, we aspire to uncover new statistical insights that were previously impractical with traditional white dwarf characterisation techniques.
While anomaly detection stands among the most important and valuable problems across many scientific domains, anomaly detection research often focuses on AI methods that can lack the nuance and interpretability so critical to conducting scientific inquiry. In this application paper we present the results of utilizing an alternative approach that situates the mathematical framing of machine learning based anomaly detection within a participatory design framework. In a collaboration with NASA scientists working with the PIXL instrument studying Martian planetary geochemistry as a part of the search for extra-terrestrial life; we report on over 18 months of in-context user research and co-design to define the key problems NASA scientists face when looking to detect and interpret spectral anomalies. We address these problems and develop a novel spectral anomaly detection toolkit for PIXL scientists that is highly accurate while maintaining strong transparency to scientific interpretation. We also describe outcomes from a yearlong field deployment of the algorithm and associated interface. Finally we introduce a new design framework which we developed through the course of this collaboration for co-creating anomaly detection algorithms: Iterative Semantic Heuristic Modeling of Anomalous Phenomena (ISHMAP), which provides a process for scientists and researchers to produce natively interpretable anomaly detection models. This work showcases an example of successfully bridging methodologies from AI and HCI within a scientific domain, and provides a resource in ISHMAP which may be used by other researchers and practitioners looking to partner with other scientific teams to achieve better science through more effective and interpretable anomaly detection tools.
Traditional methods for the analysis of compositional data consider the log-ratios between all different pairs of variables with equal weight, typically in the form of aggregated contributions. This is not meaningful in contexts where it is known that a relationship only exists between very specific variables (e.g.~for metabolomic pathways), while for other pairs a relationship does not exist. Modeling absence or presence of relationships is done in graph theory, where the vertices represent the variables, and the connections refer to relations. This paper links compositional data analysis with graph signal processing, and it extends the Aitchison geometry to a setting where only selected log-ratios can be considered. The presented framework retains the desirable properties of scale invariance and compositional coherence. An additional extension to include absolute information is readily made. Examples from bioinformatics and geochemistry underline the usefulness of thisapproach in comparison to standard methods for compositional data analysis.
A mechanism connecting ice algal ecodynamics with the buildup of organic macromolecules in brine channels is tested offline in a reduced model of pack geochemistry. Driver physical quantities are extracted from the global sea ice dynamics code CICE, including snow height, column thickness and internal temperature. The variables are averaged at the regional scale over ten Arctic biogeographic zones and treated as input matrices at four vertical habitat levels. Nutrient-light-salt limited ice algal growth is computed along with the associated grazing plus mortality. Vertical transport is diffusive but responds to pore structure. Simulated bottom layer chlorophyll maxima are reasonable, though delayed by about a month relative to observations. This highlights major uncertainties deriving from snow thickness variability. Upper level biota are generated intermittently through flooding. Macromolecular injections are represented by the compound classes humics, proteins, polysaccharides and lipids. The fresh biopolymers behave in a successional manner and are removed by bacteria. In baseline runs, organics are introduced solely through cell disruption, and internal carbon is biased low. Continuous exudation is therefore appended, and agreement with dissolved organic or individual biopolymer measurements is achieved when strong release is coupled to light availability. Detrital carbon then reaches hundreds of micromolar, sufficient to support physical changes to the ice matrix. Through this optimized model version we address the question, are high molecular weight organics added to the brine network over and above background spillage? The mechanism is configured for ready extension to the Antarctic, so that global ice organic chemistry issues can be targeted.
This review gives an overview of the development of machine learning in geoscience. A thorough analysis of the co-developments of machine learning applications throughout the last 70 years relates the recent enthusiasm for machine learning to developments in geoscience. I explore the shift of kriging towards a mainstream machine learning method and the historic application of neural networks in geoscience, following the general trend of machine learning enthusiasm through the decades. Furthermore, this chapter explores the shift from mathematical fundamentals and knowledge in software development towards skills in model validation, applied statistics, and integrated subject matter expertise. The review is interspersed with code examples to complement the theoretical foundations and illustrate model validation and machine learning explainability for science. The scope of this review includes various shallow machine learning methods, e.g. Decision Trees, Random Forests, Support-Vector Machines, and Gaussian Processes, as well as, deep neural networks, including feed-forward neural networks, convolutional neural networks, recurrent neural networks and generative adversarial networks. Regarding geoscience, the review has a bias towards geophysics but aims to strike a balance with geochemistry, geostatistics, and geology, however excludes remote sensing, as this would exceed the scope. In general, I aim to provide context for the recent enthusiasm surrounding deep learning with respect to research, hardware, and software developments that enable successful application of shallow and deep machine learning in all disciplines of Earth science.