Publications
Publications are in reversed chronological order. You can search for papers using the following KGML categories: KG-Loss, KG-Architecture, KG-Pretraining, KG-Post-Processing, and Hybrid Modeling. For a full list, please check Google Scholar.
2024
- ArXiv (KG-Loss, KG-Architecture)
What Do You See in Common? Learning Hierarchical Prototypes over Tree-of-Life to Discover Evolutionary TraitsarXiv preprint, 2024 - ArXiv
Fish-Vista: A Multi-Purpose Dataset for Understanding & Identification of Traits from ImagesarXiv preprint arXiv:2407.08027, 2024 - AISY
Motion Enhanced Multi-Level Tracker (MEMTrack): A Deep Learning-Based Approach to Microrobot Tracking in Dense and Low-Contrast EnvironmentsAdvanced Intelligent Systems, 2024 - ArXiv
Knowledge-guided Machine Learning: Current Trends and Future ProspectsarXiv preprint arXiv:2403.15989, 2024 - JAMES (Hybrid Modeling)Modular Compositional Learning Improves 1D Hydrodynamic Lake Model Performance by Merging Process-Based Modeling With Deep LearningJournal of Advances in Modeling Earth Systems, 2024
- ICLRA simple interpretable transformer for fine-grained image classification and analysisInternational Conference on Learning Representations (ICLR, 2024
- BB (KG-Loss)Improving biosensor accuracy and speed using dynamic signal change and theory-guided deep learningBiosensors and Bioelectronics, 2024
- MEEA FAIR and modular image-based workflow for knowledge discovery in the emerging field of imageomicsMethods in Ecology and Evolution, 2024
2023
- ArXiv
Beyond Discriminative Regions: Saliency Maps as Alternatives to CAMs for Weakly Supervised Semantic SegmentationarXiv preprint arXiv:2308.11052, 2023 - KDD (KG-Loss)
Discovering Novel Biological Traits From Images Using Phylogeny-Guided Neural NetworksIn Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023 - ArXiv
Let There Be Order: Rethinking Ordering in Autoregressive Graph GenerationarXiv preprint arXiv:2305.15562, 2023 - Sensors (KG-Architecture)Reduction of biosensor false responses and time delay using dynamic response and theory-guided machine learningACS sensors, 2023
- JCTC (Hybrid Modeling)Improving the Accuracy of Physics-Based Hydration-Free Energy Predictions by Machine Learning the Remaining Error Relative to the ExperimentJournal of chemical theory and computation, 2023
2022
- BigData
Multi-task Learning for Source Attribution and Field Reconstruction for Methane MonitoringIn 2022 IEEE International Conference on Big Data (Big Data), 2022 - TIST (KG-Loss)
CoPhy-PGNN: Learning physics-guided neural networks with competing loss functions for solving eigenvalue problemsACM Transactions on Intelligent Systems and Technology, 2022 - Book Chapter (KG-Architecture)
Physics-guided architecture (PGA) of LSTM models for uncertainty quantification in lake temperature modelingIn Knowledge Guided Machine Learning, 2022 - MEE (KG-Architecture)
Hierarchy-guided Neural Networks for Species ClassificationMethods in Ecology and Evolution, 2022 - Book Chapter (KG-Loss, Hybrid Modeling)Physics-guided neural networks (pgnn): An application in lake temperature modelingIn Knowledge Guided Machine Learning, 2022
- APR (KG-Loss)Physics-Informed Machine Learning for Optical Modes in CompositesAdvanced Photonics Research, 2022
- Nature Sc. Data (KG-Post-Processing)ReaLSAT, a global dataset of reservoir and lake surface area variationsScientific data, 2022
- Deep learning methods for predicting fluid forces in dense particle suspensionsPowder Technology, 2022
- A data-driven approach to full-field nonlinear stress distribution and failure pattern prediction in composites using deep learningComputer Methods in Applied Mechanics and Engineering, 2022
- Book Chapter (KG-Architecture)Science-Guided Design and Evaluation of Machine Learning Models: A Case-Study on Multi-Phase FlowsIn Knowledge Guided Machine Learning, 2022
- BookKnowledge guided machine learning: Accelerating discovery using scientific knowledge and data2022
- Book Chapter (KG-Loss, KG-Pretraining)Physics-guided recurrent neural networks for predicting lake water temperatureIn Knowledge Guided Machine Learning, 2022
2021
- NeurIPS
Learning compact representations of neural networks using discriminative masking (DAM)Advances in Neural Information Processing Systems, 2021 - ITSC
A graph convolutional neural network based approach for traffic monitoring using augmented detections with optical flowIn 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), 2021 - KDD (KG-Architecture)
PID-GAN: A GAN Framework based on a Physics-informed Discriminator for Uncertainty Quantification with PhysicsIn Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 2021 - TDS (KG-Loss, KG-Pretraining)Physics-guided machine learning for scientific discovery: An application in simulating lake temperature profilesACM/IMS Transactions on Data Science, 2021
- SDMMaximizing cohesion and separation in graph representation learning: A distance-aware negative sampling approachIn Proceedings of the 2021 SIAM International Conference on Data Mining (SDM), 2021
- Exploratory analysis of machine learning methods in predicting subsurface temperature and geothermal gradient of Northeastern United StatesGeothermal Energy, 2021
- SDM (KG-Loss)Quadratic residual networks: A new class of neural networks for solving forward and inverse problems in physics involving pdesIn Proceedings of the 2021 SIAM International Conference on Data Mining (SDM), 2021
- ICDM (KG-Architecture)Phyflow: Physics-guided deep learning for generating interpretable 3D flow fieldsIn 2021 IEEE International Conference on Data Mining (ICDM), 2021
2020
- Big Data (KG-Loss, KG-Architecture)
Physics-Guided Deep Learning for Drag Force Prediction in Dense Fluid-Particulate SystemsBig Data, 2020PMID: 33090021 - arXiv
Gcnnmatch: Graph convolutional neural networks for multi-object tracking via sinkhorn normalizationarXiv preprint arXiv:2010.00067, 2020 - SDM (KG-Architecture)Physics-guided architecture (pga) of neural networks for quantifying uncertainty in lake temperature modelingIn Proceedings of the 2020 siam international conference on data mining, 2020
- SDM (KG-Loss, KG-Architecture)Phynet: Physics guided neural networks for particle drag force prediction in assemblyIn Proceedings of the 2020 SIAM international conference on data mining, 2020
- Eco. M. (Hybrid Modeling)Predicting lake surface water phosphorus dynamics using process-guided machine learningEcological Modelling, 2020
- AMTA feasibility study to use machine learning as an inversion algorithm for aerosol profile and property retrieval from multi-axis differential absorption spectroscopy measurementsAtmospheric Measurement Techniques, 2020
- Best Research Paper AwardBiodiversity image quality metadata augments convolutional neural network classification of fish speciesIn Research Conference on Metadata and Semantics Research, 2020
2019
- SDM (KG-Loss, KG-Architecture)
Physics-guided design and learning of neural networks for predicting drag force on particle suspensions in moving fluidsarXiv preprint arXiv:1911.04240, 2019 - SDM (KG-Loss, KG-Pretraining)Physics guided RNNs for modeling dynamical systems: A case study in simulating lake temperature profilesIn Proceedings of the 2019 SIAM international conference on data mining, 2019
- SDMSpatial context-aware networks for mining temporal discriminative period in land cover detectionIn Proceedings of the 2019 SIAM International Conference on Data Mining, 2019
- SDMClassifying heterogeneous sequential data by cyclic domain adaptation: An application in land cover detectionIn Proceedings of the 2019 SIAM International Conference on Data Mining, 2019
- IJCAIRecurrent Generative Networks for Multi-Resolution Satellite Data: An Application in Cropland Monitoring.In IJCAI, 2019
- WRR (KG-Loss, KG-Pretraining)Process-guided deep learning predictions of lake water temperatureWater Resources Research, 2019
2018
- TKDEMachine learning for the geosciences: Challenges and opportunitiesIEEE Transactions on Knowledge and Data Engineering, 2018
- CSURSpatio-temporal data mining: A survey of problems and methodsACM Computing Surveys (CSUR), 2018
- BigData (KG-Loss)Incorporating prior domain knowledge into deep neural networksIn 2018 IEEE international conference on big data (big data), 2018
- BookIntroduction to Data Mining (2nd Edition)2018
2017
- RSE (KG-Post-Processing)An approach for global monitoring of surface water extent variations in reservoirs using MODIS dataRemote sensing of Environment, 2017
- TKDE
Theory-guided data science: A new paradigm for scientific discovery from dataIEEE Transactions on knowledge and data engineering, 2017 - KDDTripoles: A new class of relationships in time series dataIn Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2017
- BigDataJoint sparse auto-encoder: A semi-supervised spatio-temporal approach in mapping large-scale croplandsIn 2017 IEEE International Conference on Big Data (Big Data), 2017
2016
- Book ChapterGlobal monitoring of inland water dynamics: State-of-the-art, challenges, and opportunitiesComputational sustainability, 2016
- GRSMMonitoring land-cover changes: A machine-learning perspectiveIEEE Geoscience and Remote Sensing Magazine, 2016
- BigDataIdentifying dynamic changes with noisy labels in spatial-temporal data: A study on large-scale water monitoring applicationIn 2016 IEEE International Conference on Big Data (Big Data), 2016
2015
- GEBBHPMF–a hierarchical B ayesian approach to gap-filling and trait prediction for macroecology and functional biogeographyGlobal Ecology and Biogeography, 2015
- SDMEnsemble learning methods for binary classification with multi-modality within the classesIn SIAM International Conference on Data Mining (SDM), 2015
- ICDMAdaptive heterogeneous ensemble learning using the context of test instancesIn 2015 IEEE International Conference on Data Mining, 2015
- CS&EA guide to earth science data: Summary and research challengesComputing in Science & Engineering, 2015
2014
- SDMPredictive Learning in the Presence of Heterogeneity and Limited Training DataIn SDM, 2014
2013
- Book ChapterEarth science applications of sensor dataManaging and Mining Sensor Data, 2013
- Twin support vector regression for the simultaneous learning of a function and its derivativesInternational Journal of Machine Learning and Cybernetics, 2013
- Proximal support tensor machinesInternational Journal of Machine Learning and Cybernetics, 2013
2012
- CIDUImportance of vegetation type in forest cover estimationIn 2012 Conference on Intelligent Data Understanding, 2012
- CIDUA new data mining framework for forest fire mappingIn 2012 Conference on Intelligent Data Understanding, 2012
2011
- Generalized eigenvalue proximal support vector regressorExpert Systems with Applications, 2011