author = {Erg{\"u}ner, Yasemin and Kumar, Jitendra and Hoffman, Forrest M. and Dalfes, H. N{\"u}zhet and Hargrove, William W.},
  title = {Mapping ecoregions under climate change: a case study from the biological `crossroads' of three continents, Turkey},
  journal = {Landscape Ecology},
  year = {2019},
  volume = {34},
  number = {1},
  pages = {35--50},
  month = {Jan},
  issn = {1572-9761},
  abstract = {Besides climate change vulnerability, most ecosystems are under threat from a history of improper land-use and conservation policies, yet there is little existing long-term ecological research infrastructure in Turkey. In regions with no ecological networks across large landscapes, ecoregion concept offers opportunities for characterizing the landscape under changing climate.},
  day = {01},
  doi = {10.1007/s10980-018-0743-8},
  file = {pubs/Ergüner_LandscapeEcology_2018.pdf},
  url = {},
  note = {\url{}}
  author = {Zachary L. Langford and Jitendra Kumar and Forrest M. Hoffman and Amy L. Breen and Colleen M. Iversen},
  title = {Arctic Vegetation Mapping Using Unsupervised Training Datasets and Convolutional Neural Networks},
  journal = {Remote Sensing},
  year = {2019},
  volume = {11},
  number = {1},
  pages = {69},
  month = jan,
  abstract = {Land cover datasets are essential for modeling and analysis of Arctic ecosystem structure and function and for understanding land--atmosphere interactions at high spatial resolutions. However, most Arctic land cover products are generated at a coarse resolution, often limited due to cloud cover, polar darkness, and poor availability of high-resolution imagery. A multi-sensor remote sensing-based deep learning approach was developed for generating high-resolution (5~m) vegetation maps for the western Alaskan Arctic on the Seward Peninsula, Alaska. The fusion of hyperspectral, multispectral, and terrain datasets was performed using unsupervised and supervised classification techniques over a $\sim$343~km$^{2}$ area, and a high-resolution (5~m) vegetation classification map was generated. An unsupervised technique was developed to classify high-dimensional remote sensing datasets into cohesive clusters. We employed a quantitative method to add supervision to the unlabeled clusters, producing a fully labeled vegetation map. We then developed convolutional neural networks (CNNs) using the multi-sensor fusion datasets to map vegetation distributions using the original classes and the classes produced by the unsupervised classification method. To validate the resulting CNN maps, vegetation observations were collected at 30 field plots during the summer of 2016, and the resulting vegetation products developed were evaluated against them for accuracy. Our analysis indicates the CNN models based on the labels produced by the unsupervised classification method provided the most accurate mapping of vegetation types, increasing the validation score (i.e., precision) from 0.53 to 0.83 when evaluated against field vegetation observations.},
  article_number = {69},
  day = {2},
  doi = {10.3390/rs11010069},
  note = {\url{https;//}},
  file = {pubs/Langford_RemoteSensing_2019.pdf}
  author = {Wang, Yihui and Yuan, Fengming and Yuan, Fenghui and Gu, Baohua and Hahn, Melanie S. and Torn, Margaret S. and Ricciuto, Daniel M. and Kumar, Jitendra and He, Liyuan and Zona, Donatella and Lipson, David A. and Wagner, Robert and Oechel, Walter C. and Wullschleger, Stan D. and Thornton, Peter E. and Xu, Xiaofeng},
  title = {{Mechanistic Modeling of Microtopographic Impacts on CO2 and CH4 Fluxes in an Alaskan Tundra Ecosystem Using the CLM-Microbe Model}},
  journal = {Journal of Advances in Modeling Earth Systems},
  year = {2019},
  abstract = {Abstract Spatial heterogeneities in soil hydrology have been confirmed as a key control on CO2 and CH4 fluxes in the Arctic tundra ecosystem. In this study, we applied a mechanistic ecosystem model, CLM-Microbe, to examine the microtopographic impacts on CO2 and CH4 fluxes across seven landscape types in Utqiaġvik, Alaska: trough, low-center-polygon (LCP) center, LCP transition, LCP rim, high-center-polygon (HCP) center, HCP transition, and HCP rim. We first validated the CLM-Microbe model against static-chamber measured CO2 and CH4 fluxes in 2013 for three landscape types: trough, LCP center, and LCP rim. Model application showed that low-elevation and thus wetter landscape types (i.e., trough, transitions, and LCP center) had larger CH4 emissions rates with greater seasonal variations than high-elevation and drier landscape types (rims and HCP center). Sensitivity analysis indicated that substrate availability for methanogenesis (acetate, CO2+H2) is the most important factor determining CH4 emission, and vegetation physiological properties largely affect the net ecosystem carbon exchange and ecosystem respiration in Arctic tundra ecosystems. Modeled CH4 emissions for different microtopographic features were upscaled to the eddy covariance (EC) domain with an area-weighted approach before validation against EC-measured CH4 fluxes. The model underestimated the EC measured CH4 flux by 20\% and 25\% at daily and hourly time steps, suggesting the importance of the time step in reporting CH4 flux. The strong microtopographic impacts on CO2 and CH4 fluxes call for a model-data integration framework for better understanding and predicting carbon flux in the highly heterogeneous Arctic landscape.},
  doi = {10.1029/2019MS001771},
  note = {\url{}},
  eprint = {},
  file = {pubs/Wang_JAMES_2019.pdf},
  keywords = {Arctic tundra, CH4 flux, microtopographic, sensitivity analysis, net carbon exchange},
  url = {}
  author = {Salmon, Verity G. and Breen, Amy L. and Kumar, Jitendra and Lara, Mark J. and Thornton, Peter E. and Wullschleger, Stan D. and Iversen, Colleen M.},
  title = {Alder Distribution and Expansion Across a Tundra Hillslope: Implications for Local N Cycling},
  journal = {Frontiers in Plant Science},
  year = {2019},
  volume = {10},
  pages = {1099},
  issn = {1664-462X},
  doi = {10.3389/fpls.2019.01099},
  note = {\url{10.3389/fpls.2019.01099}},
  file = {pubs/SalmonEtal_2019FrontiersPlantSci.pdf},
  url = {}
  author = {Y. {Lu} and J. {Kumar}},
  title = {Convolutional Neural Networks for Hydrometeor Classification using Dual Polarization Doppler Radars},
  booktitle = {2019 International Conference on Data Mining Workshops (ICDMW)},
  year = {2019},
  pages = {288-295},
  month = {Nov},
  doi = {10.1109/ICDMW.2019.00050},
  note = {\url{}},
  file = {pubs/Lu_ICDM_2019.pdf},
  issn = {2375-9232},
  keywords = {Convolutional neural network, Hydrometeor classification, Dual polarization doppler radar, Atmospheric science}
  author = {Z. L. {Langford} and J. {Kumar} and F. M. {Hoffman}},
  title = {Deep Transfer Learning With Field-Based Measurements for Large Area Classification},
  booktitle = {2019 International Conference on Data Mining Workshops (ICDMW)},
  year = {2019},
  pages = {262-269},
  month = {Nov},
  doi = {10.1109/ICDMW.2019.00047},
  note = {\url{htps://}},
  file = {pubs/Langford_ICDM_2019.pdf},
  issn = {2375-9232},
  keywords = {transfer learning, deep learning, vegetation classification, Arctic}
  author = {J. {Kumar} and M. C. {Crow} and R. {Devarakonda} and M. {Giansiracusa} and K. {Guntupally} and J. V. {Olatt} and Z. {Price} and H. A. {Shanafield} and A. {Singh}},
  title = {Provenance–aware workflow for data quality management and improvement for large continuous scientific data streams},
  booktitle = {2019 IEEE International Conference on Big Data (Big Data)},
  year = {2019},
  pages = {3260-3266},
  doi = {10.1109/BigData47090.2019.9006358},
  note = {\url{10.1109/BigData47090.2019.9006358}},
  file = {pubs/Kumar_IEEEBigData_2019.pdf}
  author = {R. {Devarakonda} and G. {Prakash} and K. {Guntupally} and J. {Kumar}},
  title = {Big Federal Data Centers Implementing FAIR Data Principles: ARM Data Center Example},
  booktitle = {2019 IEEE International Conference on Big Data (Big Data)},
  year = {2019},
  pages = {6033-6036},
  month = {Dec},
  abstract = {Atmospheric Radiation Measurement (ARM) is a multi-laboratory/multi-institutional, US Department of Energy Office of Science National User Facility. ARM's data is currently hosted at the ARM Data Center (ADC) in Oak Ridge, Tennessee. The ADC holds more than 12,000 data products, with a total holding of more than 1.8 PB of data that dates back to 1992. This includes data from instruments, value-added products, model outputs, field campaigns, and principle investigator contributed data. In this paper, we discuss how big federal scientific data centers, such as ARM, that use modern and scalable architecture apply findable, accessible, interoperable, and reusable (FAIR) data principles to improve overall efficiency. These principles mainly emphasize machine-to-machine interactions that are directly applicable to ARM because of its data volume.},
  doi = {10.1109/BigData47090.2019.9006051},
  note = {\url{}},
  file = {Devarakonda_BigData_2019.pdf:pubs/Devarakonda_BigData_2019.pdf},
  keywords = {computer centres;data acquisition;findable accessible interoperable and reusable data principle;ARM Data Center;Science National User Facility;Atmospheric Radiation Measurement;FAIR Data principles;data volume;data products;ADC;memory size 1.8 PByte;Metadata;Data centers;Big Data;Tools;Atmospheric measurements;Distributed databases;Big data;ARM Data Center;FAIR;scientific data mining;data management}
@comment{{jabref-meta: databaseType:bibtex;}}