Search

Soil organic carbon (SOC) plays a crucial role in the global carbon cycle and in maintaining soil functions in the context of land use and climate change. Understanding the spatial distribution of SOC is essential for the management of agricultural land to optimize soil health and carbon storage. In this study, we investigated the spatial distribution of SOC in an agricultural lowland area of the Lombardy region, Italy, using machine learning (ML) techniques combined with residual kriging. ML models, including the artificial neural network (ANN), extreme learning machine (ELM), and random forest (RF), were trained on 120 SOC observations and eight environmental variables to predict SOC values across the study area. The performance of this ML approach was assessed using a ten-fold nested cross-validation process. The ELM and RF models showed better predictive performances based on the concordance correlation coefficient and root mean square error (RMSE), with RF slightly outperforming ELM based on the RMSE. The residuals of each iteration from the ML models were interpolated by ordinary kriging (OK) and added to the ML-based trend model in a hybrid regression-kriging approach. This approach which accounted for the spatial autocorrelation of the prediction residuals, resulting in a marginally improved prediction accuracy in the ML models. In addition, we found that vertical distance to the channel network and channel network base level are important predictor variables that should be considered in future digital soil models for SOC in lowland areas, given their importance in this study. Furthermore, this study highlights that predicted SOC values were low, particularly in Luvisols, which can be explained by the long history of agricultural land use depleting SOC due to agricultural management and loss of organic plant residues. The prediction maps depicted spatial variation and patterns of SOC in the study area. Our findings may help to refine soil management practices and contribute to improving soil health and carbon sequestration in agricultural lowland areas.

Abstract Interpretable Machine Learning (IML) has rapidly advanced in recent years, offering new opportunities to improve our understanding of the complex Earth system. IML goes beyond conventional machine learning by not only making predictions but also seeking to elucidate the reasoning behind those predictions. The combination of predictive power and enhanced transparency makes IML a promising approach for uncovering relationships in data that may be overlooked by traditional analysis. Despite its potential, the broader implications for the field have yet to be fully appreciated. Meanwhile, the rapid proliferation of IML, still in its early stages, has been accompanied by instances of careless application. In response to these challenges, this paper focuses on how IML can effectively and appropriately aid geoscientists in advancing process understanding—areas that are often underexplored in more technical discussions of IML. Specifically, we identify pragmatic application scenarios for IML in typical geoscientific studies, such as quantifying relationships in specific contexts, generating hypotheses about potential mechanisms, and evaluating process‐based models. Moreover, we present a general and practical workflow for using IML to address specific research questions. In particular, we identify several critical and common pitfalls in the use of IML that can lead to misleading conclusions, and propose corresponding good practices. Our goal is to facilitate a broader, yet more careful and thoughtful integration of IML into Earth science research, positioning it as a valuable data science tool capable of enhancing our current understanding of the Earth system.

Abstract Annual antler growth begins in the spring and is completed by late summer for male caribou (Rangifer tarandus groenlandicus) from the Qamanirjuaq herd (Nunavut, Canada), aligned with both the spring migration and a seasonal dietary shift. Antlers may provide a non‐lethal means of studying short‐ and long‐term changes in caribou ecology through incorporated isotopes of carbon (δ13C) and nitrogen (δ15N). We sampled the antlers of 12 male caribou from the Qamanirjuaq herd culled in September 1967. We predicted that serial sampling of antlers would reflect the known seasonal dietary change from lichen to grass‐like and shrub diet based on rumen contents from individuals culled during the same period. The δ13C and δ15N were analyzed in food sources and every 3 cm along each antler's length. The carbon isotope compositions of collagen (δ13Ccol) varied by ~0.5‰ among individuals and within antlers, while the carbon isotope compositions of antler bioapatite (δ13CCO3) increased by 1–1.5‰ from pedicle to tip. Values of δ15Ncol increased within antlers by 1–3‰ from pedicle to tip and varied by 3‰ among the individuals sampled. Antler collagen was lower in δ15Ncol by ~1‰ relative to bone collagen. Bayesian mixing models were conducted to test for changes in dietary proportions from antler isotope compositions. Mixing models did not indicate significant dietary shifts for any individual during antler formation, showing consistently mixed diets of fungi, horsetail, lichen, and woody plants. Increases in δ15Ncol in antler tissue could, therefore, correspond to subtle seasonal dietary changes and/or the physiological stress of antler tissue development.

Although the COVID-19 crisis is a worldwide threat to individuals' physical health and psychological well-being, not all people are equally susceptible to increased ill-being. One potentially important factor in individuals' vulnerability (versus resilience) to ill-being in the face of stress is emotion regulation. On the basis of Self-Determination Theory, this study examined the role of three emotion regulation styles in individuals' mental health during the COVID-19 crisis, that is, integration, suppression, and dysregulation. Participants were 6584 adults (77% female, M.sub.age = 45.16 years) who filled out well-validated measures of emotion regulation, depression, anxiety, life satisfaction, and sleep quality. To examine naturally occurring combinations of emotion regulation strategies, hierarchical k-means clustering was performed, yielding 3 profiles: (a) low scores on all strategies (indicating rather low overall levels of worry; 27%), (b) high scores on integration only (41%), and (c) high scores on suppression and dysregulation (32%). Participants in the profiles scoring high on suppression and dysregulation displayed a less favorable pattern of outcomes (high ill-being, low life satisfaction, and poorer sleep quality) compared to the other two groups. Between-cluster differences remained significant even when taking into account the corona-related worries experienced by people. Overall, the findings underscore the important role of emotion regulation in individuals' mental health during mentally challenging periods such as the COVID-19 crisis. Practical implications and directions for future research are discussed., Author(s): Joachim Waterschoot [sup.1] , Sofie Morbée [sup.1] , Branko Vermote [sup.1] , Katrijn Brenning [sup.1] , Nele Flamant [sup.1] , Maarten Vansteenkiste [sup.1] , Bart Soenens [sup.1] Author Affiliations: [...]

Excess ice, found as massive ice and within icy sediments, is an important variable to quantify as it is a dominant control on the terrain and geotechnical response to permafrost thaw. A large amount of permafrost borehole data are available from the Tuktoyaktuk Coastlands; however, field geotechnical assessments typically only involve the estimation of visible ice. To add significant value to these data sets, a cryostratigraphic data set collected along the Inuvik–Tuktoyaktuk Highway (566 boreholes) is used to develop a beta regression model which predicts the excess ice content of icy sediments based on interval depth, visible ice content, material type, and Quaternary deposits. The resulting predictions are compared to recorded massive ice intervals and show that ground ice within icy sediments can contribute up to 65% of the excess ice and potential thaw strain within the first 10 m from the surface in this area. This study shows the general applicability of this approach and indicates that comparable, quantitative data on ground ice conditions should be collected with drilling programs to derive geotechnical variables and reduce modelling uncertainties so that ground ice data are available for quantitative analysis.

ABSTRACTMammals exhibit daily fasting and feeding patterns that produce a fluctuating environment in the gut. By colonizing germfree mice with Bacteroides thetaiotaomicron and examining gene expression through a time-restricted feeding cycle, we demonstrate that this prominent gut commensal exhibits gene expression patterns characteristic of a stringent response and increases ppGpp levels during the host-fasting phase of the feeding regimen. Mutants unable to produce (p)ppGpp fail to produce this transcriptional response, exhibit unrestrained chromosomal replication, and cannot maintain population size during the host-fasting phase. Additionally, B. thetaiotaomicron requires (p)ppGpp to utilize host glycans both in vitro and in vivo, and mutants unable to produce (p)ppGpp display deficiencies in mucus layer colonization during the host-fasting phase. Complete gut microbial communities from mice and humans also increase ppGpp levels in this manner, demonstrating that this response appears to be general across species and conserved across mammalian gut communities. Together, these results identify an intracellular signal that allows gut microbes to coordinate their physiology with a time-restricted feeding regimen of their host.IMPORTANCEMammals do not eat continuously, instead concentrating their feeding to a restricted portion of the day. This behavior presents the mammalian gut microbiota with a fluctuating environment with consequences for host-microbiome interaction, infection risk, immune response, drug metabolism, and other aspects of health. We demonstrate that in mice, gut microbes elevate levels of an intracellular signaling molecule, (p)ppGpp, during the fasting phase of a time-restricted feeding regimen. Disabling this response in a representative human gut commensal species significantly reduces colonization during this host-fasting phase. This response appears to be general across species and conserved across mammalian gut communities, highlighting a pathway that allows healthy gut microbiomes to maintain stability in an unstable environment.

The assessment of uncertainties in landslide susceptibility modelling in a changing environment is an important, yet often neglected, task. In an Austrian case study, we investigated the uncertainty cascade in storylines of landslide susceptibility emerging from climate change and parametric landslide model uncertainty. In June 2009, extreme events of heavy thunderstorms occurred in the Styrian Basin, triggering thousands of landslides. Using a storyline approach, we discovered a generally lower landslide susceptibility for the pre-industrial climate, while for the future climate (2071–2100) a potential increase of 35 % in highly susceptible areas (storyline of much heavier rain) may be compensated for by much drier soils (−45 % areas highly susceptible to landsliding). However, the estimated uncertainties in predictions were generally high. While uncertainties related to within-event internal climate model variability were substantially lower than parametric uncertainties in the landslide susceptibility model (ratio of around 0.25), parametric uncertainties were of the same order as the climate scenario uncertainty for the higher warming levels (+3 and +4 K). We suggest that in future uncertainty assessments, an improved availability of event-based landslide inventories and high-resolution soil and precipitation data will help to reduce parametric uncertainties in landslide susceptibility models used to assess the impacts of climate change on landslide hazard and risk.

Transferability of knowledge from well-investigated areas to a new study region is gaining importance in landslide hazard research. Considering the time-consuming compilation of landslide inventories as a prerequisite for landslide susceptibility mapping, model transferability can be key to making hazard-related information available to stakeholders in a timely manner. In this paper, we compare and combine two important transfer-learning strategies for landslide susceptibility modeling: case-based reasoning (CBR) and domain adaptation (DA). Care-based reasoning gathers knowledge from previous similar situations (source areas) and applies it to solve a new problem (target area). Domain adaptation, which is widely used in computer vision, selects data from a source area that has a similar distribution to the target area. We assess the performances of single- and multiple-source CBR, DA, and CBR–DA strategies to train and combine landslide susceptibility models using generalized additive models (GAMs) for 10 study areas with various resolutions (1, 10, and 25 m) located in Austria, Ecuador, and Italy. The performance evaluation shows that CBR and combined CBR–DA based on our proposed similarity criterion were able to achieve performances comparable to benchmark models trained in the target area itself. Particularly the CBR strategies yielded favorable results in both single- and multi-source strategies. Although DA tended to have overall lower performances than CBR, it had promising results in scenarios where the source–target similarity was low. We recommend that future transfer-learning research for landslide susceptibility modeling can build on the similarity criterion we used, as it successfully helped to transfer landslide susceptibility models by identifying suitable source regions for model training.

Accurate subseasonal weather forecasts, from 2 weeks up to a season, can help reduce costs and impacts related to weather and corresponding extremes. The quality of weather forecasts has improved considerably in recent decades as models represent more details of physical processes, and they benefit from assimilating comprehensive Earth observation data as well as increasing computing power. However, with ever-growing model complexity, it becomes increasingly difficult to pinpoint weaknesses in the forecast models' process representations which is key to improving forecast accuracy. In this study, we use a comprehensive set of observation-based ecological, hydrological, and meteorological variables to study their potential for explaining temperature forecast errors at the weekly timescale. For this purpose, we compute Spearman correlations between each considered variable and the forecast error obtained from the European Centre for Medium-Range Weather Forecasts (ECMWF) subseasonal-to-seasonal (S2S) reforecasts at lead times of 1–6 weeks. This is done across the globe for the time period 2001–2017. The results show that temperature forecast errors globally are most strongly related with climate-related variables such as surface solar radiation and precipitation, which highlights the model's difficulties in accurately capturing the evolution of the climate-related variables during the forecasting period. At the same time, we find particular regions in which other variables are more strongly related to forecast errors. For instance, in central Europe, eastern North America and southeastern Asia, vegetation greenness and soil moisture are relevant, while in western South America and central North America, circulation-related variables such as surface pressure relate more strongly with forecast errors. Overall, the identified relationships between forecast errors and independent Earth observations reveal promising variables on which future forecasting system development could focus by specifically considering related process representations and data assimilation.

The area affected by a landslide analogous to an Alpine foreland event in 2009 could be up to 45% larger under 4 K of global warming, or 10% if warming is limited in line with the Paris Agreement, according to simulations of event storylines with varying climate, soil moisture and land use.

Although mentoring programs for female STEM students are often carried out with a great deal of passion on the part of program managers and mentors, robust results on their effects are often missing. However, regular evaluations are indispensable for an efficient allocation of resources towards gender balances in STEM. To accomplish this requirement, empirically valid and easy-to-use evaluation concepts are needed. We therefore develop an evaluation concept which corresponds to a Logic Chart, capturing three levels of expected effects (output—outcome—impact). On each level of impact, we derive a set of success indicators that can be measured by qualitative methods. A major advantage of our evaluation design is that the effect of a mentoring program can be observed directly after the end of the program. Furthermore, the results provide information about different channels of impact (e.g., reduced stereotypes or increased self-efficacy) and hence offer concrete indications for the further development of the program.

Abstract The repeated expansion of East Asian steppe cultures was a key driver of Eurasian history, forging new social, economic, and biological links across the continent. Climate has been suggested as important driver of these poorly understood cultural expansions, but paleoclimate records from the Mongolian Plateau often suffer from poor age control or ambiguous proxy interpretation. Here, we use a combination of geochemical analyses and comprehensive radiocarbon dating to establish the first robust and detailed record of paleohydrological conditions for Lake Telmen, Mongolia, covering the past ~ 4000 years. Our record shows that humid conditions coincided with solar minima, and hydrological modeling confirms the high sensitivity of the lake to paleoclimate changes. Careful comparisons with archaeological and historical records suggest that in the vast semi-arid grasslands of eastern Eurasia, solar minima led to reduced temperatures, less evaporation, and high biomass production, expanding the power base for pastoral economies and horse cavalry. Our findings suggest a crucial link between temperature dynamics in the Eastern Steppe and key social developments, such as the emergence of pastoral empires, and fuel concerns that global warming enhances water scarcity in the semi-arid regions of interior Eurasia.

Although abundant research has demonstrated associations between psychologically controlling parenting and adolescent problem behavior, little is known about the moderating role of adolescent personality herein. This study examined whether adolescent personality moderates the associations between parental psychological control and internalizing and externalizing problems at the level of within-person change. A 3-wave longitudinal design (N = 198 families, M[subscript age] adolescent = 14.89 years, M[subscript age] mother = 45.14 years, Mage father = 46.79 years), with 1-year intervals between waves, and using multi-informant assessment was conducted. Multilevel analyses demonstrated that changes in parental psychological control related positively to changes in multi-informant scores of both internalizing and externalizing problems. Evidence for the moderating role of personality was found for only 1 out of 25 interactions in a variable-centered approach and for 2 out of 8 interactions in a person-centered approach. The interactions obtained indicated that a mature personality (i.e., higher scores on emotional stability or membership in a resilient profile in comparison to an overcontrolled profile) buffered against the detrimental effects of psychologically controlling parenting on problem behaviors. Overall, the number of interactions was limited, suggesting only a modest moderating effect of adolescent personality.

Knowing the source and runout of debris flows can help in planning strategies aimed at mitigating these hazards. Our research in this paper focuses on developing a novel approach for optimizing runout models for regional susceptibility modelling, with a case study in the upper Maipo River basin in the Andes of Santiago, Chile. We propose a two-stage optimization approach for automatically selecting parameters for estimating runout path and distance. This approach optimizes the random-walk and Perla et al.'s (PCM) two-parameter friction model components of the open-source Gravitational Process Path (GPP) modelling framework. To validate model performance, we assess the spatial transferability of the optimized runout model using spatial cross-validation, including exploring the model's sensitivity to sample size. We also present diagnostic tools for visualizing uncertainties in parameter selection and model performance. Although there was considerable variation in optimal parameters for individual events, we found our runout modelling approach performed well at regional prediction of potential runout areas. We also found that although a relatively small sample size was sufficient to achieve generally good runout modelling performance, larger samples sizes (i.e. ≥80) had higher model performance and lower uncertainties for estimating runout distances at unknown locations. We anticipate that this automated approach using the open-source R software and the System for Automated Geoscientific Analyses geographic information system (SAGA-GIS) will make process-based debris-flow models more readily accessible and thus enable researchers and spatial planners to improve regional-scale hazard assessments.

Interpretable Machine Learning (IML) has rapidly advanced in recent years, offering new opportunities to improve our understanding of the complex Earth system. IML goes beyond conventional machine learning by not only making predictions but also seeking to elucidate the reasoning behind those predictions. The combination of predictive power and enhanced transparency makes IML a promising approach for uncovering relationships in data that may be overlooked by traditional analysis. Despite its potential, the broader implications for the field have yet to be fully appreciated. Meanwhile, the rapid proliferation of IML, still in its early stages, has been accompanied by instances of careless application. In response to these challenges, this paper focuses on how IML can effectively and appropriately aid geoscientists in advancing process understanding—areas that are often underexplored in more technical discussions of IML. Specifically, we identify pragmatic application scenarios for IML in typical geoscientific studies, such as quantifying relationships in specific contexts, generating hypotheses about potential mechanisms, and evaluating process‐based models. Moreover, we present a general and practical workflow for using IML to address specific research questions. In particular, we identify several critical and common pitfalls in the use of IML that can lead to misleading conclusions, and propose corresponding good practices. Our goal is to facilitate a broader, yet more careful and thoughtful integration of IML into Earth science research, positioning it as a valuable data science tool capable of enhancing our current understanding of the Earth system. Plain Language Summary: Artificial Intelligence is a rapidly advancing field, in which Interpretable Machine Learning (IML) is seen as having the potential to significantly improve our understanding of Earth's complex environmental systems. IML goes beyond the predictive power of machine learning models, focusing instead on uncovering the relationships within the data that are revealed by the model's learning process. However, there is still a lack of straightforward, practical domain‐specific guidelines for geoscientists that facilitate both broader and more careful application in the field. In this paper, we aim to demonstrate the real‐world benefits of IML in typical geoscientific analysis. We provide a clear, step‐by‐step workflow that shows how IML can be used to address specific questions. We also point out some common pitfalls in using IML and offer solutions to avoid them. Our goal is to make IML more accessible and useful to a wider range of geoscientists, and we believe that IML, if used properly and thoughtfully, can become an essential and valuable tool to advance our understanding of complex Earth systems. Key Points: We demonstrate the broader relevance of Interpretable Machine Learning (IML) to most geoscientists and underexplored opportunities for its useWe describe a workflow for the effective use of IML while cautioning against potential and common pitfallsWe suggest good practices for its adoption and advocate for more careful application to ensure reliable and robust insights for the field [ABSTRACT FROM AUTHOR]

Drought and heat events affect the uptake and sequestration of carbon in terrestrial ecosystems. Factors such as the duration, timing, and intensity of extreme events influence the magnitude of impacts on ecosystem processes such as gross primary production (GPP), i.e., the ecosystem uptake of CO2. Preceding soil moisture depletion may exacerbate these impacts. However, some vegetation types may be more resilient to climate extremes than others. This effect is insufficiently understood at the global scale and is the focus of this study. Using a global upscaled product of GPP that scales up in situ land CO2 flux observations with global satellite remote sensing, we study the impact of climate extremes at the global scale. We find that GPP in grasslands and agricultural areas is generally reduced during heat and drought events. However, we also find that forests, if considered globally, appear in general to not be particularly sensitive to droughts and heat events that occurred during the analyzed period or even show increased GPP values during these events. On the one hand, normal-to-increased GPP values are in many cases plausible, e.g., when conditions prior to the event have been particularly positive. On the other hand, however, normal-to-increased GPP values in forests may also reflect a lack of sensitivity in current remote-sensing-derived GPP products to the effects of droughts and heatwaves. The overall picture calls for a differentiated consideration of different land cover types in the assessments of risks of climate extremes for ecosystem functioning.

Climate variables carry signatures of variability at multiple timescales. How these modes of variability are reflected in the state of the terrestrial biosphere is still not quantified or discussed at the global scale. Here, we set out to gain a global understanding of the relevance of different modes of variability in vegetation greenness and its covariability with climate. We used >30 years of remote sensing records of the normalized difference vegetation index (NDVI) to characterize biosphere variability across timescales from submonthly oscillations to decadal trends using discrete Fourier decomposition. Climate data of air temperature (Tair) and precipitation (Prec) were used to characterize atmosphere–biosphere covariability at each timescale. Our results show that short-term (intra-annual) and longer-term (interannual and longer) modes of variability make regionally highly important contributions to NDVI variability: short-term oscillations focus in the tropics where they shape 27 % of NDVI variability. Longer-term oscillations shape 9 % of NDVI variability, dominantly in semiarid shrublands. Assessing dominant timescales of vegetation–climate covariation, a natural surface classification emerges which captures patterns not represented by conventional classifications, especially in the tropics. Finally, we find that correlations between variables can differ and even invert signs across timescales. For southern Africa for example, correlation between NDVI and Tair is positive for the seasonal signal but negative for short-term and longer-term oscillations, indicating that both short- and long-term temperature anomalies can induce stress on vegetation dynamics. Such contrasting correlations between timescales exist for 15 % of vegetated areas for NDVI with Tair and 27 % with Prec, indicating global relevance of scale-specific climate sensitivities. Our analysis provides a detailed picture of vegetation–climate covariability globally, characterizing ecosystems by their intrinsic modes of temporal variability. We find that (i) correlations of NDVI with climate can differ between scales, (ii) nondominant subsignals in climate variables may dominate the biospheric response, and (iii) possible links may exist between short-term and longer-term scales. These heterogeneous ecosystem responses on different timescales may depend on climate zone and vegetation type, and they are to date not well understood and do not always correspond to transitions in dominant vegetation types. These scale dependencies can be a benchmark for vegetation model evaluation and for comparing remote sensing products.

Considering the critical importance of the quality of input data for landslide susceptibility, we investigate the performance improvements that can be achieved by different globally available digital elevation models (DEMs) using different state-of-the-art statistical and machine-learning models. For this purpose we compare the predictive performances achieved using terrain attributes derived from TanDEM-X DEM (12 m resolution and resampled to 30 m), ASTER DEM (30 m), SRTM DEM (30 m), and a DEM (25 m) interpolated from contour lines (1:25.000 map scale), exploiting the capabilities of logistic regression, generalized additive models, random forests and support vector machines. The study was conducted in the Buzău Sector of the Curvature Subcarpathians of Romania, a region highly susceptible to landslides. While the performances varied little among modelling techniques, the use of different DEMs strongly influenced the cross-validation accuracy of landslide susceptibility models. TanDEM-X (12 m) based susceptibility models outperformed models based on the other DEMs (median Area Under the Receiver Operating Characteristics Curve (AUROC) values 0.708–0.730). Models using ASTER-derived terrain attributes showed the poorest predictive capabilities (median AUROC 0.568–0.595). We conclude that the quality of DEMs is of critical importance in landslide susceptibility modelling, and greater efforts should be made to obtain suitable DEM products.

Sustainable agricultural landscape management needs reliable and accurate soil maps and updated geospatial soil information. Recently, machine learning (ML) models have commonly been used in digital soil mapping, together with limited data, for various types of landscapes. In this study, we tested linear and nonlinear ML models in predicting and mapping soil properties in an agricultural lowland landscape of Lombardy region, Italy. We further evaluated the ability of an ensemble learning model, based on a stacking approach, to predict the spatial variation of soil properties, such as sand, silt, and clay contents, soil organic carbon content, pH, and topsoil depth. Therefore, we combined the predictions of the base learners (ML models) with two meta-learners. Prediction accuracies were assessed using a nested cross-validation procedure. Nonetheless, the nonlinear single models generally performed well, with RF having the best results; the stacking models did not outperform all the individual base learners. The most important topographic predictors of the soil properties were vertical distance to channel network and channel network base level. The results yield valuable information for sustainable land use in an area with a particular soil water cycle, as well as for future climate and socioeconomic changes influencing water content, soil pollution dynamics, and food security.