@article{james_detecting_2024,
	title = {Detecting {Paleoclimate} {Transitions} {With} {Laplacian} {Eigenmaps} of {Recurrence} {Matrices} ({LERM})},
	volume = {39},
	issn = {2572-4517, 2572-4525},
	url = {https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2023PA004700},
	doi = {10.1029/2023PA004700},
	abstract = {Abstract 
            Paleoclimate records can be considered low‐dimensional projections of the climate system that generated them. Understanding what these projections tell us about past climates, and changes in their dynamics, is a main goal of time series analysis on such records. Laplacian eigenmaps of recurrence matrices (LERM) is a novel technique using univariate paleoclimate time series data to indicate when notable shifts in dynamics have occurred. LERM leverages time delay embedding to construct a manifold that is mappable to the attractor of the climate system; this manifold can then be analyzed for significant dynamical transitions. Through numerical experiments with observed and synthetic data, LERM is applied to detect both gradual and abrupt regime transitions. Our paragon for gradual transitions is the Mid‐Pleistocene Transition (MPT). We show that LERM can robustly detect gradual MPT‐like transitions for sufficiently high signal‐to‐noise (S/N) ratios, though with a time lag related to the embedding process. Our paragon of abrupt transitions is the “8.2 ka” event; we find that LERM is generally robust at detecting 8.2 ka‐like transitions for sufficiently high S/N ratios, though edge effects become more influential. We conclude that LERM can usefully detect dynamical transitions in paleogeoscientific time series, with the caveat that false positive rates are high when dynamical transitions are not present, suggesting the importance of using multiple records to confirm the robustness of transitions. We share an open‐source Python package to facilitate the use of LERM in paleoclimatology and paleoceanography. 

Key Points:           
                                
Laplacian eigenmaps of recurrence matrices (LERM) is a novel tool for paleoclimate time series analysis 
                 
                 
LERM can robustly detect the gradual Mid‐Pleistocene Transition in relatively low signal‐to‐noise ratio scenarios 
                 
                 
LERM can also be applied to detect abrupt climate transitions like the 8.2 ka event, though less robustly},
	language = {en},
	number = {1},
	urldate = {2024-01-03},
	journal = {Paleoceanography and Paleoclimatology},
	author = {James, Alexander and Emile‐Geay, Julien and Malik, Nishant and Khider, Deborah},
	month = jan,
	year = {2024},
	pages = {e2023PA004700},
}

Abstract Paleoclimate records can be considered low‐dimensional projections of the climate system that generated them. Understanding what these projections tell us about past climates, and changes in their dynamics, is a main goal of time series analysis on such records. Laplacian eigenmaps of recurrence matrices (LERM) is a novel technique using univariate paleoclimate time series data to indicate when notable shifts in dynamics have occurred. LERM leverages time delay embedding to construct a manifold that is mappable to the attractor of the climate system; this manifold can then be analyzed for significant dynamical transitions. Through numerical experiments with observed and synthetic data, LERM is applied to detect both gradual and abrupt regime transitions. Our paragon for gradual transitions is the Mid‐Pleistocene Transition (MPT). We show that LERM can robustly detect gradual MPT‐like transitions for sufficiently high signal‐to‐noise (S/N) ratios, though with a time lag related to the embedding process. Our paragon of abrupt transitions is the “8.2 ka” event; we find that LERM is generally robust at detecting 8.2 ka‐like transitions for sufficiently high S/N ratios, though edge effects become more influential. We conclude that LERM can usefully detect dynamical transitions in paleogeoscientific time series, with the caveat that false positive rates are high when dynamical transitions are not present, suggesting the importance of using multiple records to confirm the robustness of transitions. We share an open‐source Python package to facilitate the use of LERM in paleoclimatology and paleoceanography. Key Points: Laplacian eigenmaps of recurrence matrices (LERM) is a novel tool for paleoclimate time series analysis LERM can robustly detect the gradual Mid‐Pleistocene Transition in relatively low signal‐to‐noise ratio scenarios LERM can also be applied to detect abrupt climate transitions like the 8.2 ka event, though less robustly

@techreport{khider_building_2023,
	title = {Building {Upon} the {EarthCube} {Community}: a geoscience and cyberinfrastructure workshop - {Report}},
	copyright = {Creative Commons Attribution 4.0 International},
	shorttitle = {Building {Upon} the {EarthCube} {Community}},
	url = {https://figshare.com/articles/conference_contribution/Building_Upon_the_EarthCube_Community_a_geoscience_and_cyberinfrastructure_workshop_-_Report/23949168/2},
	abstract = {This report summarizes the discussion at the "Building Upon the EarthCube Community: A geoscience and cyberinfrastructure workshop" which was held at the University of Southern California Information Sciences Institute, June 27-28th 2023.},
	urldate = {2024-01-25},
	author = {Khider, Deborah and {Mike Daniels} and Jarboe, Nick},
	year = {2023},
	keywords = {Earth and space science informatics},
	pages = {9095054 Bytes},
}

This report summarizes the discussion at the "Building Upon the EarthCube Community: A geoscience and cyberinfrastructure workshop" which was held at the University of Southern California Information Sciences Institute, June 27-28th 2023.

@techreport{zhu_cfr_2023,
	type = {preprint},
	title = {cfr (v2023.9.14): a {Python} package for climate field reconstruction},
	shorttitle = {cfr (v2023.9.14)},
	url = {https://egusphere.copernicus.org/preprints/2023/egusphere-2023-2098/},
	abstract = {Abstract. Climate field reconstruction (CFR) refers to the estimation of spatiotemporal climate fields (such as surface temperature) from a collection of pointwise paleoclimate proxy datasets. The climate fields can provide rich information on climate dynamics and provide an out-of-sample validation of climate models. However, most CFR workflows are complex and timeconsuming, as they involve: (i) preprocessing of the proxy records, climate model simulations, and instrumental observations, (ii) application of one or more statistical methods, and (iii) analysis and visualization of the reconstruction results. Historically, this process has lacked transparency and accessibility, limiting reproducibility and experimentation by non-specialists. This article presents an open-source and object-oriented Python package called cfr that aims to make CFR workflows easy to understand and conduct, saving climatologists from technical details and facilitating efficient and reproducible research. It provides user-friendly utilities for common CFR tasks such as proxy and climate data analysis and visualization, proxy system modeling, and modularized workflows for multiple reconstruction methods, enabling methodological intercomparisons within the same framework. The package is supported with an extensive documentation of the application interface (API) and a growing number of tutorial notebooks illustrating its usage. As an example, we present two cfr-driven reconstruction experiments using the PAGES 2k temperature database: applying the last millennium reanalysis (LMR) paleoclimate data assimilation (PDA) framework and the Graphical Expectation-Maximization (GraphEM) algorithm, respectively.},
	urldate = {2023-11-17},
	institution = {Climate and Earth system modeling},
	author = {Zhu, Feng and Emile-Geay, Julien and Hakim, Gregory J. and Guillot, Dominique and Khider, Deborah and Tardif, Robert and Perkins, Walter A.},
	month = sep,
	year = {2023},
	doi = {10.5194/egusphere-2023-2098},
}

Abstract. Climate field reconstruction (CFR) refers to the estimation of spatiotemporal climate fields (such as surface temperature) from a collection of pointwise paleoclimate proxy datasets. The climate fields can provide rich information on climate dynamics and provide an out-of-sample validation of climate models. However, most CFR workflows are complex and timeconsuming, as they involve: (i) preprocessing of the proxy records, climate model simulations, and instrumental observations, (ii) application of one or more statistical methods, and (iii) analysis and visualization of the reconstruction results. Historically, this process has lacked transparency and accessibility, limiting reproducibility and experimentation by non-specialists. This article presents an open-source and object-oriented Python package called cfr that aims to make CFR workflows easy to understand and conduct, saving climatologists from technical details and facilitating efficient and reproducible research. It provides user-friendly utilities for common CFR tasks such as proxy and climate data analysis and visualization, proxy system modeling, and modularized workflows for multiple reconstruction methods, enabling methodological intercomparisons within the same framework. The package is supported with an extensive documentation of the application interface (API) and a growing number of tutorial notebooks illustrating its usage. As an example, we present two cfr-driven reconstruction experiments using the PAGES 2k temperature database: applying the last millennium reanalysis (LMR) paleoclimate data assimilation (PDA) framework and the Graphical Expectation-Maximization (GraphEM) algorithm, respectively.

@inproceedings{berhanu_ai_2022,
	title = {An {AI} {Approach} to {Integrating} {Climate}, {Hydrology}, and {Agriculture} {Models}},
	url = {http://www.isi.edu/~gil/papers/berhanu-etal-siaia-2022.pdf},
	booktitle = {Proceedings of the {First} {International} {Workshop} on {Social} {Impact} of {AI} for {Africa} ({SIAIA}), held at the 36th {Annual} {Conference} of the {Association} for the {Advancement} of {Artificial} {Intelligence} ({AAAI}-22)},
	author = {Berhanu, Belete and Bisrat, Ethiopia and Gil, Yolanda and Khider, Deborah and Osorio, Maximiliano and Ratnakar, Varun and Vargas, Hernan},
	year = {2022},
}

@inproceedings{gil_towards_2022,
	title = {Towards {Capturing} {Scientific} {Reasoning} to {Automate} {Data} {Analysis}},
	url = {http://www.isi.edu/~gil/papers/gil-etal-cogsci-2022.pdf},
	booktitle = {Proceedings of the 44th {Annual} {Conference} of the {Cognitive} {Science} {Society} ({CogSci})},
	author = {Gil, Yolanda and Khider, Deborah and Osorio, Maximiliano and Ratnakar, Varun and Vargas, Hernan and Garijo, Daniel and Pierce, Suzanne},
	year = {2022},
}

@article{khider_pyleoclim_2022,
	title = {Pyleoclim: {Paleoclimate} {Timeseries} {Analysis} and {Visualization} {With} {Python}},
	volume = {37},
	issn = {2572-4517, 2572-4525},
	shorttitle = {Pyleoclim},
	url = {https://onlinelibrary.wiley.com/doi/10.1029/2022PA004509},
	doi = {10.1029/2022PA004509},
	language = {en},
	number = {10},
	urldate = {2022-11-02},
	journal = {Paleoceanography and Paleoclimatology},
	author = {Khider, Deborah and Emile‐Geay, Julien and Zhu, Feng and James, Alexander and Landers, Jordan and Ratnakar, Varun and Gil, Yolanda},
	month = oct,
	year = {2022},
}

@article{manety_paleorec_2022,
	title = {{PaleoRec}: {A} sequential recommender system for the annotation of paleoclimate datasets},
	volume = {1},
	issn = {2634-4602},
	shorttitle = {{PaleoRec}},
	url = {https://www.cambridge.org/core/product/identifier/S2634460222000036/type/journal_article},
	doi = {10.1017/eds.2022.3},
	abstract = {Abstract 
            Studying past climate variability is fundamental to our understanding of current changes. In the era of Big Data, the value of paleoclimate information critically depends on our ability to analyze large volume of data, which itself hinges on standardization. Standardization also ensures that these datasets are more Findable, Accessible, Interoperable, and Reusable. Building upon efforts from the paleoclimate community to standardize the format, terminology, and reporting of paleoclimate data, this article describes PaleoRec, a recommender system for the annotation of such datasets. The goal is to assist scientists in the annotation task by reducing and ranking relevant entries in a drop-down menu. Scientists can either choose the best option for their metadata or enter the appropriate information manually. PaleoRec aims to reduce the time to science while ensuring adherence to community standards. PaleoRec is a type of sequential recommender system based on a recurrent neural network that takes into consideration the short-term interest of a user in a particular dataset. The model was developed using 1996 expert-annotated datasets, resulting in 6,512 sequences. The performance of the algorithm, as measured by the Hit Ratio, varies between 0.7 and 1.0. PaleoRec is currently deployed on a web interface used for the annotation of paleoclimate datasets using emerging community standards.},
	language = {en},
	urldate = {2022-11-02},
	journal = {Environmental Data Science},
	author = {Manety, Shravya and Khider, Deborah and Heiser, Christopher and McKay, Nicholas and Emile-Geay, Julien and Routson, Cody},
	year = {2022},
	pages = {e4},
}

Abstract Studying past climate variability is fundamental to our understanding of current changes. In the era of Big Data, the value of paleoclimate information critically depends on our ability to analyze large volume of data, which itself hinges on standardization. Standardization also ensures that these datasets are more Findable, Accessible, Interoperable, and Reusable. Building upon efforts from the paleoclimate community to standardize the format, terminology, and reporting of paleoclimate data, this article describes PaleoRec, a recommender system for the annotation of such datasets. The goal is to assist scientists in the annotation task by reducing and ranking relevant entries in a drop-down menu. Scientists can either choose the best option for their metadata or enter the appropriate information manually. PaleoRec aims to reduce the time to science while ensuring adherence to community standards. PaleoRec is a type of sequential recommender system based on a recurrent neural network that takes into consideration the short-term interest of a user in a particular dataset. The model was developed using 1996 expert-annotated datasets, resulting in 6,512 sequences. The performance of the algorithm, as measured by the Hit Ratio, varies between 0.7 and 1.0. PaleoRec is currently deployed on a web interface used for the annotation of paleoclimate datasets using emerging community standards.

@article{gil_artificial_2021,
	title = {Artificial {Intelligence} for {Modeling} {Complex} {Systems}: {Taming} the {Complexity} of {Expert} {Models} to {Improve} {Decision} {Making}},
	volume = {11},
	issn = {2160-6455},
	shorttitle = {Artificial {Intelligence} for {Modeling} {Complex} {Systems}},
	url = {https://doi.org/10.1145/3453172},
	doi = {10.1145/3453172},
	abstract = {Major societal and environmental challenges involve complex systems that have diverse multi-scale interacting processes. Consider, for example, how droughts and water reserves affect crop production and how agriculture and industrial needs affect water quality and availability. Preventive measures, such as delaying planting dates and adopting new agricultural practices in response to changing weather patterns, can reduce the damage caused by natural processes. Understanding how these natural and human processes affect one another allows forecasting the effects of undesirable situations and study interventions to take preventive measures. For many of these processes, there are expert models that incorporate state-of-the-art theories and knowledge to quantify a system's response to a diversity of conditions. A major challenge for efficient modeling is the diversity of modeling approaches across disciplines and the wide variety of data sources available only in formats that require complex conversions. Using expert models for particular problems requires integration of models with third-party data as well as integration of models across disciplines. Modelers face significant heterogeneity that requires resolving semantic, spatiotemporal, and execution mismatches, which are largely done by hand today and may take more than 2 years of effort. We are developing a modeling framework that uses artificial intelligence (AI) techniques to reduce modeling effort while ensuring utility for decision making. Our work to date makes several innovative contributions: (1) an intelligent user interface that guides analysts to frame their modeling problem and assists them by suggesting relevant choices and automating steps along the way; (2) semantic metadata for models, including their modeling variables and constraints, that ensures model relevance and proper use for a given decision-making problem; and (3) semantic representations of datasets in terms of modeling variables that enable automated data selection and data transformations. This framework is implemented in the MINT (Model INTegration) framework, and currently includes data and models to analyze the interactions between natural and human systems involving climate, water availability, agricultural production, and markets. Our work to date demonstrates the utility of AI techniques to accelerate modeling to support decision-making and uncovers several challenging directions for future work.},
	number = {2},
	urldate = {2021-09-09},
	journal = {ACM Transactions on Interactive Intelligent Systems},
	author = {Gil, Yolanda and Garijo, Daniel and Khider, Deborah and Knoblock, Craig A. and Ratnakar, Varun and Osorio, Maximiliano and Vargas, Hernán and Pham, Minh and Pujara, Jay and Shbita, Basel and Vu, Binh and Chiang, Yao-Yi and Feldman, Dan and Lin, Yijun and Song, Hayley and Kumar, Vipin and Khandelwal, Ankush and Steinbach, Michael and Tayal, Kshitij and Xu, Shaoming and Pierce, Suzanne A. and Pearson, Lissa and Hardesty-Lewis, Daniel and Deelman, Ewa and Silva, Rafael Ferreira Da and Mayani, Rajiv and Kemanian, Armen R. and Shi, Yuning and Leonard, Lorne and Peckham, Scott and Stoica, Maria and Cobourn, Kelly and Zhang, Zeya and Duffy, Christopher and Shu, Lele},
	month = jul,
	year = {2021},
	keywords = {Intelligent user interfaces, integrated modeling, model metadata, regional-level decision-making, remote sensing data},
	pages = {11:1--11:49},
}

Major societal and environmental challenges involve complex systems that have diverse multi-scale interacting processes. Consider, for example, how droughts and water reserves affect crop production and how agriculture and industrial needs affect water quality and availability. Preventive measures, such as delaying planting dates and adopting new agricultural practices in response to changing weather patterns, can reduce the damage caused by natural processes. Understanding how these natural and human processes affect one another allows forecasting the effects of undesirable situations and study interventions to take preventive measures. For many of these processes, there are expert models that incorporate state-of-the-art theories and knowledge to quantify a system's response to a diversity of conditions. A major challenge for efficient modeling is the diversity of modeling approaches across disciplines and the wide variety of data sources available only in formats that require complex conversions. Using expert models for particular problems requires integration of models with third-party data as well as integration of models across disciplines. Modelers face significant heterogeneity that requires resolving semantic, spatiotemporal, and execution mismatches, which are largely done by hand today and may take more than 2 years of effort. We are developing a modeling framework that uses artificial intelligence (AI) techniques to reduce modeling effort while ensuring utility for decision making. Our work to date makes several innovative contributions: (1) an intelligent user interface that guides analysts to frame their modeling problem and assists them by suggesting relevant choices and automating steps along the way; (2) semantic metadata for models, including their modeling variables and constraints, that ensures model relevance and proper use for a given decision-making problem; and (3) semantic representations of datasets in terms of modeling variables that enable automated data selection and data transformations. This framework is implemented in the MINT (Model INTegration) framework, and currently includes data and models to analyze the interactions between natural and human systems involving climate, water availability, agricultural production, and markets. Our work to date demonstrates the utility of AI techniques to accelerate modeling to support decision-making and uncovers several challenging directions for future work.

@article{mckay_geochronr_2021,
	title = {{geoChronR} – an {R} package to model, analyze, and visualize age-uncertain data},
	volume = {3},
	doi = {10.5194/gchron-3-149-2021},
	number = {1},
	journal = {Geochronology},
	author = {McKay, Nicholas and Emile-Geay, Julien and Khider, Deborah},
	month = mar,
	year = {2021},
	pages = {149--169},
}

@inproceedings{khider_towards_2020,
	address = {San Diego, California, USA},
	title = {Towards automating time series analysis for the paleogeosciences},
	url = {https://github.com/khider/khider.github.io/blob/master/papers/KDD_TimeSeries_Workshop_revised.pdf},
	abstract = {There is an abundance of time series data in many domains. Analyz- ing this data effectively requires deep expertise acquired over many years of practice. Our goal is to develop automated systems for time series analysis that can take advantage of proven methods that yield the best results. Our work is motivated by paleogeosciences time series analysis where the datasets are very challenging and require sophisticated methods to find and quantify subtle patterns. We describe our initial implementation of AutoTS, an automated system for time series analysis that uses semantic workflows to rep- resent sophisticated methods and their constraints. AutoTS extends the WINGS workflow system with new capabilities to customize general methods to specific datasets based on key characteristics of the data. We discuss general methods for spectral analysis and their implementation in AutoTS.},
	publisher = {ACM, New York, NY, USA},
	author = {Khider, Deborah and Athreya, Pratheek and Ratnakar, Varun and Gil, Yolanda and Zhu, Feng and Kwan, Myron and Emile-Geay, Julien},
	year = {2020},
}

There is an abundance of time series data in many domains. Analyz- ing this data effectively requires deep expertise acquired over many years of practice. Our goal is to develop automated systems for time series analysis that can take advantage of proven methods that yield the best results. Our work is motivated by paleogeosciences time series analysis where the datasets are very challenging and require sophisticated methods to find and quantify subtle patterns. We describe our initial implementation of AutoTS, an automated system for time series analysis that uses semantic workflows to rep- resent sophisticated methods and their constraints. AutoTS extends the WINGS workflow system with new capabilities to customize general methods to specific datasets based on key characteristics of the data. We discuss general methods for spectral analysis and their implementation in AutoTS.

@article{kaufman_global_2020,
	title = {A global database of {Holocene} paleotemperature records},
	volume = {7},
	issn = {2052-4463},
	url = {https://doi.org/10.1038/s41597-020-0445-3},
	doi = {10.1038/s41597-020-0445-3},
	abstract = {A comprehensive database of paleoclimate records is needed to place recent warming into the longer-term context of natural climate variability. We present a global compilation of quality-controlled, published, temperature-sensitive proxy records extending back 12,000 years through the Holocene. Data were compiled from 679 sites where time series cover at least 4000 years, are resolved at sub-millennial scale (median spacing of 400 years or finer) and have at least one age control point every 3000 years, with cut-off values slackened in data-sparse regions. The data derive from lake sediment (51\%), marine sediment (31\%), peat (11\%), glacier ice (3\%), and other natural archives. The database contains 1319 records, including 157 from the Southern Hemisphere. The multi-proxy database comprises paleotemperature time series based on ecological assemblages, as well as biophysical and geochemical indicators that reflect mean annual or seasonal temperatures, as encoded in the database. This database can be used to reconstruct the spatiotemporal evolution of Holocene temperature at global to regional scales, and is publicly available in Linked Paleo Data (LiPD) format.},
	number = {1},
	journal = {Scientific Data},
	author = {Kaufman, Darrell and McKay, Nicholas and Routson, Cody and Erb, Michael and Davis, Basil and Heiri, Oliver and Jaccard, Samuel and Tierney, Jessica and Dätwyler, Christoph and Axford, Yarrow and Brussel, Thomas and Cartapanis, Olivier and Chase, Brian and Dawson, Andria and de Vernal, Anne and Engels, Stefan and Jonkers, Lukas and Marsicek, Jeremiah and Moffa-Sánchez, Paola and Morrill, Carrie and Orsi, Anais and Rehfeld, Kira and Saunders, Krystyna and Sommer, Philipp S. and Thomas, Elizabeth and Tonello, Marcela and Tóth, Mónika and Vachula, Richard and Andreev, Andrei and Bertrand, Sebastien and Biskaborn, Boris and Bringué, Manuel and Brooks, Stephen and Caniupán, Magaly and Chevalier, Manuel and Cwynar, Les and Emile-Geay, Julien and Fegyveresi, John and Feurdean, Angelica and Finsinger, Walter and Fortin, Marie-Claude and Foster, Louise and Fox, Mathew and Gajewski, Konrad and Grosjean, Martin and Hausmann, Sonja and Heinrichs, Markus and Holmes, Naomi and Ilyashuk, Boris and Ilyashuk, Elena and Juggins, Steve and Khider, Deborah and Koinig, Karin and Langdon, Peter and Larocque-Tobler, Isabelle and Li, Jianyong and Lotter, André and Luoto, Tomi and Mackay, Anson and Magyari, Eniko and Malevich, Steven and Mark, Bryan and Massaferro, Julieta and Montade, Vincent and Nazarova, Larisa and Novenko, Elena and Pařil, Petr and Pearson, Emma and Peros, Matthew and Pienitz, Reinhard and Płóciennik, Mateusz and Porinchu, David and Potito, Aaron and Rees, Andrew and Reinemann, Scott and Roberts, Stephen and Rolland, Nicolas and Salonen, Sakari and Self, Angela and Seppä, Heikki and Shala, Shyhrete and St-Jacques, Jeannine-Marie and Stenni, Barbara and Syrykh, Liudmila and Tarrats, Pol and Taylor, Karen and van den Bos, Valerie and Velle, Gaute and Wahl, Eugene and Walker, Ian and Wilmshurst, Janet and Zhang, Enlou and Zhilich, Snezhana},
	month = apr,
	year = {2020},
	pages = {115},
}

A comprehensive database of paleoclimate records is needed to place recent warming into the longer-term context of natural climate variability. We present a global compilation of quality-controlled, published, temperature-sensitive proxy records extending back 12,000 years through the Holocene. Data were compiled from 679 sites where time series cover at least 4000 years, are resolved at sub-millennial scale (median spacing of 400 years or finer) and have at least one age control point every 3000 years, with cut-off values slackened in data-sparse regions. The data derive from lake sediment (51%), marine sediment (31%), peat (11%), glacier ice (3%), and other natural archives. The database contains 1319 records, including 157 from the Southern Hemisphere. The multi-proxy database comprises paleotemperature time series based on ecological assemblages, as well as biophysical and geochemical indicators that reflect mean annual or seasonal temperatures, as encoded in the database. This database can be used to reconstruct the spatiotemporal evolution of Holocene temperature at global to regional scales, and is publicly available in Linked Paleo Data (LiPD) format.

@inproceedings{garijo_okg-soft_2019,
	address = {San Diego, California, USA},
	title = {{OKG}-{Soft}: {An} {Open} {Knowledge} {Graph} with {Machine} {Readable} {Scientific} {Software} {Metadata}},
	url = {http://dgarijo.com/papers/OKG-SoftEscience2019.pdf},
	booktitle = {To appear in {Proceedings} of the {Fifteen} {IEEE} {International} {Conference} on {eScience}},
	author = {Garijo, Daniel and Osorio, Maximiliano and Khider, Deborah and Ratnakar, Varun and Gil, Yolanda},
	year = {2019},
}

@article{khider_pacts_2019,
	title = {{PaCTS} 1.0: {A} {Crowdsourced} {Reporting} {Standard} for {Paleoclimate} {Data}},
	volume = {34},
	copyright = {All rights reserved},
	url = {https://github.com/khider/khider.github.io/blob/master/papers/Khider_et_al-2019-Paleoceanography_and_Paleoclimatology.pdf},
	doi = {10.1029/2019PA003632},
	abstract = {Abstract The progress of science is tied to the standardization of measurements, instruments, and data. This is especially true in the Big Data age, where analyzing large data volumes critically hinges on the data being standardized. Accordingly, the lack of community-sanctioned data standards in paleoclimatology has largely precluded the benefits of Big Data advances in the field. Building upon recent efforts to standardize the format and terminology of paleoclimate data, this article describes the Paleoclimate Community reporTing Standard (PaCTS), a crowdsourced reporting standard for such data. PaCTS captures which information should be included when reporting paleoclimate data, with the goal of maximizing the reuse value of paleoclimate datasets, particularly for synthesis work and comparison to climate model simulations. Initiated by the LinkedEarth project, the process to elicit a reporting standard involved an international workshop in 2016, various forms of digital community engagement over the next few years, and grassroots working groups. Participants in this process identified important properties across paleoclimate archives, in addition to the reporting of uncertainties and chronologies; they also identified archive-specific properties and distinguished reporting standards for new vs. legacy datasets. This work shows that at least 135 respondents overwhelmingly support a drastic increase in the amount of metadata accompanying paleoclimate datasets. Since such goals are at odds with present practices, we discuss a transparent path towards implementing or revising these recommendations in the near future, using both bottom-up and top-down approaches.},
	journal = {Paleoceanography and Paleoclimatology},
	author = {Khider, Deborah and Emile-Geay, Julien and McKay, Nicholas and Gil, Yolanda and Garijo, Daniel and Ratnakar, Varun and Alonso-Garcia, Montserrat and Bertrand, Sebastian and Bothe, Oliver and Brewer, Peter and Bunn, Andrew and Chevalier, Manuel and Comas-Bru, Laia and Csank, Adam and Dassié, Emilie and DeLong, Kristine and Felis, Thomas and Francus, Pierre and Frappier, Amy and Gray, William and Goring, Simon and Jonkers, Lukas and Kahle, Michael and Kaufman, Darrell and Kehrwald, Natalie and Martrat, Belen and McGregor, Helen and Richey, Julie and Schmittner, Andreas and Scroxton, Nick and Sutherland, Elaine and Thirumalai, Kaustubh and Allen, Katheryn and Arnaud, Fabien and Axford, Yarrow and Barrows, Timothy and Bazin, Lucie and Pilaar Birch, Suzanne and Bradley, Elizabeth and Bregy, Joshua and Capron, Emilie and Cartapanis, Olivier and Chiang, Hong-Wei and Cobb, Kim and Debret, Maxime and Dommain, René and Du, Jianhui and Dyez, Kelsey and Emerick, Suellyn and Erb, Michael and Falster, Georgina and Finsinger, Walter and Fortier, Daniel and Gauthier, Nicolas and George, Steven and Grimm, Eric and Hertzberg, Jennifer and Hibbert, Fiona and Hillman, Aubrey and Hobbs, Will and Huber, Matthew and Hughes, Anna L.C. and Jaccard, Samuel and Ruan, Jiaoyang and Kienast, Michael and Konecky, Bronwen and Le Roux, Gael and Lyubchich, Vyacheslav and Novello, Valdir F. and Olaka, Lydia and Partin, Judson and Pearce, Christof and Phipps, Steven and Pignol, Cécile and Piotrowska, Natalia and Poli, Maria-Serena and Prokopenko, Alexander and Schwanck, Franciele and Stepanek, Christian and Swann, George and Telford, Richard and Thomas, Elizabeth and Thomas, Zoë and Truebe, Sarah and von Gunten, Lucien and Waite, Amanda and Weitzel, Nils and Wilhelm, Bruno and Williams, John and Winstrup, Mai and Zhao, Ning and Zhou, Yuxin},
	year = {2019},
	keywords = {FAIR, best practices, data, paleoceanography, paleoclimate, standards},
	pages = {1570--1596},
}

Abstract The progress of science is tied to the standardization of measurements, instruments, and data. This is especially true in the Big Data age, where analyzing large data volumes critically hinges on the data being standardized. Accordingly, the lack of community-sanctioned data standards in paleoclimatology has largely precluded the benefits of Big Data advances in the field. Building upon recent efforts to standardize the format and terminology of paleoclimate data, this article describes the Paleoclimate Community reporTing Standard (PaCTS), a crowdsourced reporting standard for such data. PaCTS captures which information should be included when reporting paleoclimate data, with the goal of maximizing the reuse value of paleoclimate datasets, particularly for synthesis work and comparison to climate model simulations. Initiated by the LinkedEarth project, the process to elicit a reporting standard involved an international workshop in 2016, various forms of digital community engagement over the next few years, and grassroots working groups. Participants in this process identified important properties across paleoclimate archives, in addition to the reporting of uncertainties and chronologies; they also identified archive-specific properties and distinguished reporting standards for new vs. legacy datasets. This work shows that at least 135 respondents overwhelmingly support a drastic increase in the amount of metadata accompanying paleoclimate datasets. Since such goals are at odds with present practices, we discuss a transparent path towards implementing or revising these recommendations in the near future, using both bottom-up and top-down approaches.

@article{richey_considerations_2019,
	title = {Considerations for {Globigerinoides} ruber ({White} and {Pink}) {Paleoceanography}: {Comprehensive} {Insights} {From} a {Long}-{Running} {Sediment} {Trap}},
	volume = {34},
	url = {https://github.com/khider/khider.github.io/blob/master/papers/Richey_et_al-2019-Paleoceanography_and_Paleoclimatology.pdf},
	doi = {10.1029/2018PA003417},
	abstract = {Abstract We present a detailed analysis of the seasonal distribution, size, morphological variability, and geochemistry of co-occurring pink and white chromotypes of Globigerinoides ruber from a high-resolution (1–2 weeks) and long-running sediment trap time series in the northern Gulf of Mexico. We find no difference in the seasonal flux of the two chromotypes. Although flux of G. ruber is consistently lowest in winter, the flux-weighted signal exported to marine sediments represents mean annual conditions in the surface mixed layer. We observe the same morphological diversity among pink specimens of G. ruber as white. Comparison of the oxygen and carbon isotopic composition (δ18O and δ13C) of two morphotypes (sensu stricto and sensu lato) of pink G. ruber reveals the isotopes to be indistinguishable. The test size distribution within the population varies seasonally, with the abundance of large individuals increasing (decreasing) with increasing (decreasing) sea surface temperature. We find no systematic offsets in the Mg/Ca and δ18O of co-occurring pink and white G. ruber. The sediment trap data set shows that the Mg/Ca-temperature sensitivity for both chromotypes is much lower than the canonical 9\%/°C, which can likely be attributed to the secondary influence of both salinity and pH on foraminiferal Mg/Ca. Using paired Mg/Ca and δ18O, we evaluate the performance of a suite of published equations for calculating sea surface temperature, sea surface salinity, and isotopic composition of seawater (δ18Osw), including a new salinity-δ18Osw relationship for the northern Gulf of Mexico from water column observations.},
	number = {3},
	journal = {Paleoceanography and Paleoclimatology},
	author = {Richey, Julie N. and Thirumalai, Kaustubh and Khider, Deborah and Reynolds, Caitlin E. and Partin, Judson W. and Quinn, Terrence M.},
	year = {2019},
	keywords = {Globigerinoides ruber, Gulf of Mexico, Mg/Ca, Sediment Trap, morphotypes, planktic foraminifera},
	pages = {353--373},
}

Abstract We present a detailed analysis of the seasonal distribution, size, morphological variability, and geochemistry of co-occurring pink and white chromotypes of Globigerinoides ruber from a high-resolution (1–2 weeks) and long-running sediment trap time series in the northern Gulf of Mexico. We find no difference in the seasonal flux of the two chromotypes. Although flux of G. ruber is consistently lowest in winter, the flux-weighted signal exported to marine sediments represents mean annual conditions in the surface mixed layer. We observe the same morphological diversity among pink specimens of G. ruber as white. Comparison of the oxygen and carbon isotopic composition (δ18O and δ13C) of two morphotypes (sensu stricto and sensu lato) of pink G. ruber reveals the isotopes to be indistinguishable. The test size distribution within the population varies seasonally, with the abundance of large individuals increasing (decreasing) with increasing (decreasing) sea surface temperature. We find no systematic offsets in the Mg/Ca and δ18O of co-occurring pink and white G. ruber. The sediment trap data set shows that the Mg/Ca-temperature sensitivity for both chromotypes is much lower than the canonical 9%/°C, which can likely be attributed to the secondary influence of both salinity and pH on foraminiferal Mg/Ca. Using paired Mg/Ca and δ18O, we evaluate the performance of a suite of published equations for calculating sea surface temperature, sea surface salinity, and isotopic composition of seawater (δ18Osw), including a new salinity-δ18Osw relationship for the northern Gulf of Mexico from water column observations.

@inproceedings{garijo_intelligent_2019,
	address = {New York, NY, USA},
	series = {{IUI} '19},
	title = {An {Intelligent} {Interface} for {Integrating} {Climate}, {Hydrology}, {Agriculture}, and {Socioeconomic} {Models}},
	isbn = {978-1-4503-6673-1},
	url = {https://github.com/khider/khider.github.io/blob/master/papers/iuiDemo2019.pdf},
	doi = {10.1145/3308557.3308711},
	booktitle = {Proceedings of the 24th {International} {Conference} on {Intelligent} {User} {Interfaces}: {Companion}},
	publisher = {ACM},
	author = {Garijo, Daniel and Khider, Deborah and Ratnakar, Varun and Gil, Yolanda and Deelman, Ewa and da Silva, Rafael Ferreira and Knoblock, Craig and Chiang, Yao-Yi and Pham, Minh and Pujara, Jay and Vu, Binh and Feldman, Dan and Mayani, Rajiv and Cobourn, Kelly and Duffy, Chris and Kemanian, Armen and Shu, Lele and Kumar, Vipin and Khandelwal, Ankush and Tayal, Kshitij and Peckham, Scott and Stoica, Maria and Dabrowski, Anna and Hardesty-Lewis, Daniel and Pierce, Suzanne},
	year = {2019},
	note = {event-place: Marina del Ray, California},
	keywords = {environmental modeling, intelligent workflow systems, model integration, scientific discovery},
	pages = {111--112},
}

@article{zhu_climate_2019,
	title = {Climate models can correctly simulate the continuum of global-average temperature variability},
	volume = {116},
	issn = {0027-8424},
	url = {https://github.com/khider/khider.github.io/blob/master/papers/zhu_pnas.pdf},
	doi = {10.1073/pnas.1809959116},
	abstract = {Climate models are foundational to formulations of climate policy and must successfully reproduce key features of the climate system. The temporal spectrum of observed global surface temperature is one such critical benchmark. This spectrum is known to obey scaling laws connecting astronomical forcings, from orbital to annual scales. We provide evidence that the current hierarchy of climate models is capable of reproducing the increase in variance in global-mean temperature at low frequencies. We suggest that successful climate predictions at decadal-to-centennial horizons hinge critically on the accuracy of initial and boundary conditions, particularly for the deep ocean state.Climate records exhibit scaling behavior with large exponents, resulting in larger fluctuations at longer timescales. It is unclear whether climate models are capable of simulating these fluctuations, which draws into question their ability to simulate such variability in the coming decades and centuries. Using the latest simulations and data syntheses, we find agreement for spectra derived from observations and models on timescales ranging from interannual to multimillennial. Our results confirm the existence of a scaling break between orbital and annual peaks, occurring around millennial periodicities. That both simple and comprehensive ocean–atmosphere models can reproduce these features suggests that long-range persistence is a consequence of the oceanic integration of both gradual and abrupt climate forcings. This result implies that Holocene low-frequency variability is partly a consequence of the climate system’s integrated memory of orbital forcing. We conclude that climate models appear to contain the essential physics to correctly simulate the spectral continuum of global-mean temperature; however, regional discrepancies remain unresolved. A critical element of successfully simulating suborbital climate variability involves, we hypothesize, initial conditions of the deep ocean state that are consistent with observations of the recent past.},
	number = {18},
	journal = {Proceedings of the National Academy of Sciences},
	author = {Zhu, Feng and Emile-Geay, Julien and McKay, Nicholas P. and Hakim, Gregory J. and Khider, Deborah and Ault, Toby R. and Steig, Eric J. and Dee, Sylvia and Kirchner, James W.},
	year = {2019},
	pages = {8728--8733},
}

Climate models are foundational to formulations of climate policy and must successfully reproduce key features of the climate system. The temporal spectrum of observed global surface temperature is one such critical benchmark. This spectrum is known to obey scaling laws connecting astronomical forcings, from orbital to annual scales. We provide evidence that the current hierarchy of climate models is capable of reproducing the increase in variance in global-mean temperature at low frequencies. We suggest that successful climate predictions at decadal-to-centennial horizons hinge critically on the accuracy of initial and boundary conditions, particularly for the deep ocean state.Climate records exhibit scaling behavior with large exponents, resulting in larger fluctuations at longer timescales. It is unclear whether climate models are capable of simulating these fluctuations, which draws into question their ability to simulate such variability in the coming decades and centuries. Using the latest simulations and data syntheses, we find agreement for spectra derived from observations and models on timescales ranging from interannual to multimillennial. Our results confirm the existence of a scaling break between orbital and annual peaks, occurring around millennial periodicities. That both simple and comprehensive ocean–atmosphere models can reproduce these features suggests that long-range persistence is a consequence of the oceanic integration of both gradual and abrupt climate forcings. This result implies that Holocene low-frequency variability is partly a consequence of the climate system’s integrated memory of orbital forcing. We conclude that climate models appear to contain the essential physics to correctly simulate the spectral continuum of global-mean temperature; however, regional discrepancies remain unresolved. A critical element of successfully simulating suborbital climate variability involves, we hypothesize, initial conditions of the deep ocean state that are consistent with observations of the recent past.

@inproceedings{garijo_semantic_2018,
	title = {A {Semantic} {Model} {Catalog} to {Support} {Comparison} and {Reuse}},
	url = {https://github.com/khider/khider.github.io/blob/master/papers/IEMSs2018-OntoSoft.pdf},
	booktitle = {Proceedings of the 9th {International} {Congress} on {Environmental} {Modelling} and {Software}},
	author = {Garijo, Daniel and Khider, Deborah and Gil, Yolanda and Carvalho, Lucas and Essawy, Bakinam and Pierce, Suzanne and Lewis, Daniel Hardesty and Ratnakar, Varun and Peckham, Scott and Duffy, Chris and Goodal, Jonathan},
	year = {2018},
}

@inproceedings{gil_mint:_2018,
	title = {{MINT}: {Model} {Integration} {Through} {Knowledge}-{Powered} {Data} and {Process} {Composition}},
	url = {https://github.com/khider/khider.github.io/blob/master/papers/iemss2018-MINT.pdf},
	booktitle = {Proceedings of the 9th {International} {Congress} on {Environmental} {Modelling} and {Software}},
	author = {Gil, Yolanda and Cobourn, Kelly and Deelman, Ewa and Duffy, Chris and Silva, Rafael Ferreira da and Kemanian, Armen and Knoblock, Craig and Kumar, Vipin and Peckham, Scott and Carvalho, Lucas and Chiang, Yao-Yi and Garijo, Daniel and Khider, Deborah and Khandelwal, Ankush and Pahm, Minh and Pujara, Jay and Ratnakar, Varun and Stoica, Maria and Vu, Binh},
	year = {2018},
}

@article{khider_role_2017,
	title = {The role of uncertainty in estimating lead/lag relationships in marine sedimentary archives: a case study from the tropical {Pacific}},
	volume = {32},
	url = {https://github.com/khider/khider.github.io/blob/master/papers/Khider_et_al-2017-Paleoceanography_and_Paleoclimatology.pdf},
	number = {11},
	journal = {Paleoceanography},
	author = {Khider, Deborah and Ahn, Seonmin and Lisiecki, Lorraine and Lawrence, Charles and Kienast, Markus},
	year = {2017},
	pages = {1275--1290},
}

@inproceedings{gil_controlled_2017,
	title = {A {Controlled} {Crowdsourcing} {Approach} for {Practical} {Ontology} {Extensions} and {Metadata} {Annotations}},
	url = {https://github.com/khider/khider.github.io/blob/master/papers/linkedEarth-iswc2017.pdf},
	doi = {10.1007/978-3-319-68204-4_24},
	booktitle = {International {Semantic} {Web} {Conference}},
	publisher = {Springer, Cham},
	author = {Gil, Yolanda and Garijo, Daniel and Ratnakar, Varun and Khider, Deborah and Emile-Geay, Julien and McKay, Nicholas},
	year = {2017},
	pages = {231--246},
}

@article{ahn_probabilistic_2017,
	title = {A probabilistic {Pliocene}–{Pleistocene} stack of benthic δ{18O} using a profile hidden {Markov} model},
	volume = {2},
	url = {https://github.com/khider/khider.github.io/blob/master/papers/Ahn%20et%20al_2017_DSCS.pdf},
	doi = {10.1093/climsys/dzx002},
	number = {1},
	journal = {Dynamics and Statistics of the Climate System},
	author = {Ahn, Seonmin and Khider, Deborah and Lisiecki, Lorraine E and Lawrence, Charles E},
	year = {2017},
}

@article{tems_decadal_2016,
	title = {Decadal to centennial fluctuations in the intensity of the eastern tropical {North} {Pacific} oxygen minimum zone during the last 1200 years},
	volume = {31},
	url = {https://github.com/khider/khider.github.io/blob/master/papers/Tems_et_al-2016-Paleoceanography.pdf},
	doi = {10.1002/2015PA002904},
	number = {8},
	journal = {Paleoceanography},
	author = {Tems, Caitlin E and Berelson, William M and Thunell, Robert and Tappa, Eric and Xu, Xiaomei and Khider, Deborah and Lund, Steve and González-Yajimovich, Oscar and Hamann, Yvonne},
	year = {2016},
	pages = {1138--1151},
}

@article{khider_bayesian_2015,
	title = {A {Bayesian}, multivariate calibration for {Globigerinoides} ruber {Mg}/{Ca}},
	volume = {16},
	url = {https://github.com/khider/khider.github.io/blob/master/papers/Khider%20et%20al_2015_G3.pdf},
	doi = {10.1002/2015GC005844},
	number = {9},
	journal = {Geochemistry, Geophysics, Geosystems},
	author = {Khider, Deborah and Huerta, Gabriel and Jackson, Charles and Stott, Lowell and Emile-Geay, Julien},
	year = {2015},
	pages = {2916--2932},
}

@article{khider_assessing_2014,
	title = {Assessing millennial-scale variability during the {Holocene}: {A} perspective from the western tropical {Pacific}},
	volume = {29},
	url = {https://github.com/khider/khider.github.io/blob/master/papers/Khider%20et%20al._2014_Paleoceanography.pdf},
	doi = {10.1002/2013PA002534},
	number = {3},
	journal = {Paleoceanography},
	author = {Khider, Deborah and Jackson, Charles S and Stott, Lowell},
	year = {2014},
	pages = {143--159},
}

@article{lin_probabilistic_2014,
	title = {Probabilistic sequence alignment of stratigraphic records},
	volume = {29},
	url = {https://github.com/khider/khider.github.io/blob/master/papers/Lin%20et%20al._2014_Paleoceanography.pdf},
	doi = {10.1002/2014PA002713},
	number = {10},
	journal = {Paleoceanography},
	author = {Lin, Luan and Khider, Deborah and Lisiecki, Lorraine E and Lawrence, Charles E},
	year = {2014},
	pages = {976--989},
}

@article{khider_assessing_2011,
	title = {Assessing {El} {Niño} {Southern} {Oscillation} variability during the past millennium},
	volume = {26},
	url = {https://github.com/khider/khider.github.io/blob/master/papers/Khider%20et%20al._2011_Paleoceanography.pdf},
	doi = {10.1029/2011PA002139},
	number = {3},
	journal = {Paleoceanography},
	author = {Khider, Deborah and Stott, Lowell and Emile-Geay, Julien and Thunell, Robert and Hammond, Douglas},
	year = {2011},
}

@article{reuter_new_2009,
	title = {A new perspective on the hydroclimate variability in northern {South} {America} during the {Little} {Ice} {Age}},
	volume = {36},
	url = {https://github.com/khider/khider.github.io/blob/master/papers/reuter2009.pdf},
	doi = {10.1029/2009GL041051},
	number = {21},
	journal = {Geophysical Research Letters},
	author = {Reuter, Justin and Stott, Lowell and Khider, Deborah and Sinha, Ashish and Cheng, Hai and Edwards, R Lawrence},
	year = {2009},
}