Manu Tom
Manu Tom
Embedded Files
CV, Résumé, Publications (July 2025):
CV_Tom.pdfResume_Tom.pdfPublications_list.pdfI am a computer vision engineer and remote sensing scientist with a strong background in geospatial analysis and satellite image understanding.
My academic journey includes the successful completion of a master’s degree in Electrical Engineering, Information Technology and Computer Engineering (with a specialization in computer vision) from RWTH Aachen University, Germany. Subsequently, I earned a Ph.D. in Civil, Environmental, and Geomatics Engineering, specializing in geospatial computer vision (remote sensing of the cryosphere), from the Swiss Federal Institute of Technology, Zürich (ETH Zürich). During my Ph.D., I had the privilege of working under the supervision of Prof. Konrad Schindler and Dr. Emmanuel Baltsavias. Earlier in my career, I worked on computer vision for surveillance applications with Prof. Venkatesh Babu at the Indian Institute of Science.
Currently, I am a postdoctoral researcher at NASA’s Jet Propulsion Laboratory, working on Cloud-based remote sensing and modeling of Earth's surface water under the guidance of Dr. Cedric H. David and Dr. Matthew Bonnema. Previously, I held a joint postdoctoral position at the Swiss Federal Institute of Aquatic Science and Technology (Dr. Daniel Odermatt) and the University of Zurich (Dr. Holger Frey) on geospatial computer vision (remote sensing of glacial lakes).
Research
Research
Water, in both liquid and frozen states, has always driven my research curiosity, evolving alongside my expertise in geospatial computer vision, remote sensing, applied machine learning and numerical modeling, shaping my efforts to understand the complex dynamics of surface water systems.
Monitoring surface water resources is crucial for understanding and adapting to climate change, which accelerates the global water cycle, disrupts seasonal patterns, and increases the probability of extreme events. The growing water-related disasters highlight the urgent need for precise data and analysis, as over two billion people live in highly water-stressed regions due to the uneven temporal and spatial distribution of renewable freshwater resources.
Efforts to study global water systems have a strong historical foundation, notably through UNESCO's International Hydrological Decade (1965–1974), which emphasized the need for a global perspective on water resources and laid the groundwork for coordinated hydrological research worldwide. Building on this foundation, surface water variability was identified as a critical variable in the 2007 NASA Decadal Survey and remains a key science objective of the Surface Water and Ocean Topography (SWOT) mission. Surface water monitoring also supports critical global priorities, including climate action (SDG-13), public health (SDG-6), food security (SDG-2), and sustaining life under water (SDG-14). With global population growth and rising per capita water demand driven by economic growth, the pressure on freshwater resources will continue to intensify in the coming decades.
I believe Artificial Intelligence (AI) is instrumental in harnessing the power of Earth observations to understand and mitigate the damages caused by natural and anthropogenic disasters and to build climate resilience. Now is an exciting time to work at the crossroads of AI and Earth observation, due to AI's remarkable progress and the wealth of satellite-derived data available. Deep learning methods have revolutionized the scientific landscape in the past decade, and Earth science is no exception. While classical approaches to surface water analysis—such as tailored numerical models, methods that use indices like Normalized Difference Water Index and its derivatives, and threshold-based approaches—have been largely successful, the untapped potential of learning-based approaches and cloud-based computing services, combined with the availability of petabytes of satellite data, could significantly revolutionize surface water monitoring research. A hybrid approach that integrates the strengths of classical methods with the adaptability and scalability of AI is poised to shape the future of surface water analysis.
At present, I work on remote sensing (SWOT) of lake storage and modelling (cloud-based) of river discharge. Furthermore, I explore the potential applications of deep learning in the context of mapping glacial lakes and monitoring lake ice. In the past, my research has encompassed a range of mid- and high-level computer vision challenges, including tasks such as semantic segmentation, action recognition, visual localization, and scene understanding.
I have been fortunate to contribute to research efforts within the computer vision and remote sensing research groups at various esteemed institutions, including NASA Jet Propulsion Laboratory (USA), ETH Zurich (Switzerland), Indian Institute of Science, Swiss Federal Institute of Aquatic Science and Technology, University of Zurich (Switzerland), Fraunhofer FKIE (Germany) and the RWTH Aachen University (Germany).
With over eight years of experience, I have actively contributed to international and national research and development projects supported by organizations, including NASA, UNESCO (Adaptation Fund), European Space Agency, GCOS Switzerland, Swiss Federal Office of Environment, and DRDO (India).
News
News
new! [07. 2025] One co-authored paper accepted in Reviews of Geophysics
[05. 2025] Three co-authored papers accepted in AGU Water Resources Research
[03. 2025] One paper accepted for IEEE IGARSS 2025
[03. 2025] Two co-authored papers accepted in AGU Geophysical Research Letters
[12.2024] Attended AGU Annual Meeting 2024 in Washington DC
PhD thesis
PhD thesis
Lake Ice Monitoring from Space and Earth with Machine Learning
Manu Tom
Doctoral Thesis, ETH Zürich, 2021
http://dx.doi.org/10.3929/ethz-b-000513831
Preprints
Preprints
Monitoring Earth's Glacial Lakes from Space with Machine Learning
M. Tom, D. Odermatt, C. H. David, A. Cerbelaud, J. Wade, H. Frey
SSRN, March 2025, http://dx.doi.org/10.2139/ssrn.5200494
Numerical Modeling as a Service on the Cloud: A Case Study of River Modeling
M. Tom, C. H. David, K. M. Marlis, Q. Bonassies, J. Wade, A. Cerbelaud, T. M. Pavelsky, T. Huang
SSRN, 2024, http://dx.doi.org/10.2139/ssrn.5067650
Publications (full-paper, peer-reviewed)
Publications (full-paper, peer-reviewed)
Progress towards satellite requirements to capture water propagation in Earth's rivers
A Cerbelaud, C.H. David, T Pavelsky, G Schumann, M Bonema, P Garambois, M.J. Tourian, P. Bates, J. Benveniste, S. Biancamaria, C. Gleason, M. Durand, J. F. Cretaux, H. Oubanas, G. H. Allen, R. Frasson, J. Wade, M. Tom, P. O. Malaterre, C. Schwatke, C. Kittel, A. Paris, K. Andreadis, D.Feng, D. Yamazaki, A. Dasgupta, P. Bauer-Gottwein, A. Tarpanelli, S. Mischel, N. Picot, F. Hossain, E. Rodriguez, S. Munier, F. Papa, B. Kitambo
Reviews of Geophysics (AGU), in press, 2025, http://dx.doi.org/10.22541/essoar.173627093.35248744/v1
Bidirectional Translations Between Observational and Topography-based Hydrographic Datasets: MERIT-Basins and the SWOT River Database (SWORD)
J. Wade, C. H. David, E. L. Collins, E. H. Altenau, S. Coss, A. Cerbelaud, M. Tom, M. Durand, T. M. Pavelsky
Water Resources Research (AGU), vol 61, issue 5, e2024WR038633, 2025
https://doi.org/10.1029/2024WR038633
One-Hundred Fundamental, Open Questions to Integrate Methodological Approaches in Lake Ice Research
J. Culpepper, S. Sharma, G. Gunn, M. Magee, M. Meyer, E. Anderson, C. Arp, S. Cooley, W. Dolan, H. Dugan, C. Duguay, B. M. Jones, G. Kirillin, R. Ladwig, M. Lepparanta, X. Li, J. Magnuson, T. Pavelsky, S. Piccolroaz, D. Roberston, B. Steele, M. Tom, G. A. Weyhenmeyer, I. Woolway, M. A. Xenopoulos, X. Yang
Water Resources Research (AGU), vol 61, issue 5, e2024WR039042, 2025 https://doi.org/10.1029/2024WR039042
Spatial Hydrographs of River Flow and their Analysis for Peak Event Detection in the Context of Satellite Sampling
A. Cerbelaud, C. H. David, S. Biancamaria, J. Wade, M. Tom, R. Frasson, G. H. Allen, H. Thurman, D. Blumstein
Water Resources Research (AGU), vol 61, issue 4, e2024WR038444, 2025 https://doi.org/10.1029/2024WR038444
Intrinsic Spatial Scales of River Stores and Fluxes and their Relative Contributions to the Global Water Cycle
J. Wade, C. H. David, E. L. Collins, M. Denbina, A. Cerbelaud, M. Tom, J. T. Reager, R. P. M. Frasson, J. S. Famiglietti, T. Lee, M. M. Gierach
Geophysical Research Letters (AGU), volume 52, e2024GL113052, 2025
https://doi.org/10.1029/2024GL113052
Peak Flow Event Durations in the Mississippi River Basin and Implications for Temporal Sampling of Rivers
A. Cerbelaud, C. H. David, S. Biancamaria, J. Wade, M. Tom, R. Frasson, D. Blumstein
Geophysical Research Letters (AGU), volume 51, e2024GL109220, 2024, https://doi.org/10.1029/2024GL109220
Pixel-based mapping of open field and protected agriculture using constrained Sentinel-2 data
Daniele la Cecilia, Manu Tom, Christian Stamm and Daniel Odermatt
ISPRS Open Journal of Photogrammetry and Remote Sensing (Elsevier), volume 8, 100033, 2023,
http://dx.doi.org/10.1016/j.ophoto.2023.100033
Learning a Joint Embedding of Multiple Satellite Sensors: A Case Study for Lake Ice Monitoring
Manu Tom, Yuchang Jiang, Emmanuel Baltsavias and Konrad Schindler
Transactions on Geoscience and Remote Sensing (IEEE), volume 60, pages 1-15, 2022, Art no. 4306315,
http://dx.doi.org/10.1109/TGRS.2022.3211184
Recent Ice Trends in Swiss Mountain Lakes: 20-year Analysis of MODIS Imagery
Manu Tom, Tianyu Wu, Emmanuel Baltsavias and Konrad Schindler
PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science (Springer), volume 90, pages 413–431, 2022
http://dx.doi.org/10.1007/s41064-022-00215-x
Ice Monitoring in Swiss Lakes from Optical Satellites and Webcams using Machine Learning
Manu Tom, Rajanie Prabha, Tianyu Wu, Emmanuel Baltsavias, Laura Leal-Taixe and Konrad Schindler
MDPI Journal on Remote Sensing, volume 12, issue 21, 3555, 2020
https://doi.org/10.3390/rs12213555
Lake Ice Detection from Sentinel-1 SAR with Deep Learning
Manu Tom*, Roberto Aguilar*, Pascal Imhof, Silvan Leinss, Emmanuel Baltsavias and Konrad Schindler (* equal contribution)
ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, V-3-2020, 409–416, 2020
(ISPRS Congress, Nice, France, August 2020)
https://doi.org/10.5194/isprs-annals-V-3-2020-409-2020
[Code | Pre-Trained Model]
Lake Ice Monitoring with Webcams and Crowd-Sourced Images
Rajanie Prabha, Manu Tom, Mathias Rothermel, Emmanuel Baltsavias, Laura Leal-Taixe and Konrad Schindler
ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, V-2-2020, 549–556, 2020
(ISPRS Congress, Nice, France, August 2020)
https://doi.org/10.5194/isprs-annals-V-2-2020-549-2020
[Code | Photi-LakeIce Dataset | Pre-Trained Model]
Lake Ice Monitoring with Webcams
Muyan Xiao, Mathias Rothermel, Manu Tom, Silvano Galliani, Emmanuel Baltsavias, and Konrad Schindler
ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, IV-2, 311-317, 2018
https://doi.org/10.5194/isprs-annals-IV-2-311-2018
(ISPRS Technical Commission II Symposium, Riva del Garda, Italy, June 2018)
[Code]
Lake Ice Detection in Low-Resolution Optical Satellite Images
Manu Tom, Ursula Kälin, Melanie Sütterlin, Emmanuel Baltsavias and Konrad Schindler
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, volume IV-2, pages 279-286, 2018
https://doi.org/10.5194/isprs-annals-IV-2-279-2018
(ISPRS Technical Commission II Symposium, Riva del Garda, Italy, June 2018)
3D Semantic Segmentation of Modular Furniture using rjMCMC
Ishrat Badami*, Manu Tom*, Markus Mathias and Bastian Leibe (*equal contribution)
IEEE Winter Conference on Applications of Computer Vision (WACV) 2017 (Santa Rosa, California, USA, March 2017)
http://dx.doi.org/10.1109/WACV.2017.15
[Project page | Code | Dataset]
A Survey on Compressed Domain Video Analysis Techniques
R. Venkatesh Babu, Manu Tom and Paras Wadekar
Multimedia Tools and Applications, volume 75, issue 2, pages 1043-1078, 2016
http://dx.doi.org/10.1007/s11042-014-2345-z
Compressed Domain Human Action Recognition in H.264/AVC Video Streams
Manu Tom, R. Venkatesh Babu and R. Gnana Praveen
Multimedia Tools and Applications, volume 74, issue 21, pages 9323-9338, 2015
http://dx.doi.org/10.1007/s11042-014-2083-2
Human action recognition in H.264/AVC compressed domain using meta-cognitive radial basis function network
R. Venkatesh Babu, Badrinarayanan Rangarajan, Suresh Sundaram, and Manu Tom
Applied Soft Computing, volume 36, issue 21, pages 218-227, 2015
https://doi.org/10.1016/j.asoc.2015.06.054
Automated Detection of Schlemm's Canal in Spectral-Domain Optical Coherence Tomography
Manu Tom, Vignesh Ramakrishnan, Christian van Oterendorp and Thomas Deserno
Proceedings of SPIE 9414, Medical Imaging 2015: Computer-Aided Diagnosis, 941430 (Orlando, Florida, USA, February 2015)
https://doi.org/10.1117/12.2082513
Fast Moving-object Detection in H.264/AVC Compressed Domain for Video Surveillance
Manu Tom and R. Venkatesh Babu
IEEE National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (Jodhpur, India, December 2013)
https://doi.org/10.1109/NCVPRIPG.2013.6776202
Contact details:
Address: NASA Jet Propulsion Laboratory, 4800 Oak Grove Dr, MS 300-331, Pasadena, 91109 California, USA
Email : firstname <dot> lastname [at] jpl [dot] nasa [dot] gov
Page updated
Google Sites
Report abuse