Simulation and Data Lab Remote Sensing
Major Competencies
The Simulation and Data Lab Remote Sensing (SimDataLab RS) aims to enhance the visibility of interdisciplinary research at the intersection of remote sensing applications and large-scale AI combined with distributed and innovative computing technologies. This includes supercomputing, cloud computing, quantum computing, and specialized hardware computing. SimDataLab RS collaborates closely with the Simulation and Data Lab AI and Machine Learning for Remote Sensing at the Jülich Supercomputing Centre (Forschungszentrum Jülich, Germany) and IEEE GRSS, particularly with its Technical Committees on Earth Science Informatics (ESI) and Quantum Earth Science and Technology (QUEST). Furthermore, it partners with international universities on joint activities such as research projects, teaching programs, community support, and supervising students at various academic levels.
High-Performance Computing for Remote Sensing
Specialized in harnessing distributed high-performance computing systems to process and analyze vast remote sensing datasets, ensuring that big data challenges are addressed with cutting-edge solutions.
Innovative Machine Learning & Quantum Computing
At the forefront of integrating advanced machine learning algorithms, ranging from deep learning networks to quantum computing techniques, for remote sensing applications. The focus is on pushing the boundaries of data classification and analysis using these innovative methodologies.
Scalable Data Processing Systems
Committed to the development of scalable and modular data processing systems, designed to efficiently handle the exponential growth of remote sensing data. The emphasis is on ensuring algorithms and methods can be effectively scaled to accommodate any dataset size.
Lab news and events
IEEE International Geoscience and Remote Sensing Symposium (IGARSS) - Reykjavík, 2027
The 47th annual 'International Geoscience and Remote Sensing Symposium - IGARSS 2027 will be held in Reykjavík in the summer of 2027. As the flagship conference of GRSS, IGARSS is expected to bring over 2,500 esteemed scientists and professionals in the Remote Sensing field from around the world to Iceland.
IGARSS is organized by the Geoscience and Remote Sensing Society (GRSS), one of the 39 Technical Societies of IEEE, the world's largest technical professional organization. Established in 1961, GRSS now includes over 5,000 members in 94 countries. The society is dedicated to advancing science, engineering, applications, and education in geoscience and remote sensing, aiming to make a positive contribution to society.
The IGARSS 2027 Conference, hosted in Iceland for the first time, will take place on July 4-9, 2027, at the Harpa Conference and Concert Centre and the University of Iceland, Reykjavík. The general theme of IGARSS 2027 is “Global Vision: Understanding and Mitigating Global Environmental Challenges”. The emphasis is on addressing critical issues concerning global preservation and building a resilient future for societies and ecosystems, through the use of advancements, trends, and applications in remote sensing in the digital Earth era. Special focus is given to the significant challenges faced by the Arctic region due to climate change, including the extensive melting of ice and snow. These changes have impacts that extend far beyond the Arctic, affecting the entire planet. The Scientific Program of IGARSS will include scientific publications, lectures, presentations, and technical forums, all specializing in remote sensing and processing techniques.
The main sponsor of IGARSS 2027 is the University of Iceland, supported by both domestic and international institutions. Additionally, the conference receives support from Meet in Reykjavik and KOMUM Conferences. The local organizing committee, comprising experts in remote sensing and international collaboration, is led by General Chairs, Jon Atli Benediktsson, Rector of the University of Iceland, and Professor Magnus Örn Úlfarsson, University of Iceland.
IEEE GRSS High Performance and Disruptive Computing in Remote Sensing (HDCRS) Schools
These schools are the perfect venue to network with students and young professionals, as well as senior researcher and professors who are world-renowned leaders in the field of remote sensing and work on interdisciplinary research with high performance computing, cloud computing, quantum computing and parallel programming models with specialized hardware technologies.
The 2025 edition will be hosted by the Research Center on Intelligent Technologies (CiTIUS) of the University of Santiago de Compostela (see website). Information about previous editions can be found on the IEEE GRSS website.
Erasmus+ Courses on Machine Learning and Data Fusion for Earth Observation
The programme aims at training professionals trained in the use of geospatial data coming from satellite for Earth Observation applications, such as the monitoring of the UN Sustainable Development Goals. It is based on a virtual mobility that provides the basic of machine learning techniques applied to satellite data sets and challenges the participants to provide answers to data processing questions in groups of students by different institutions collaborating on-line. The challenges, to be completed on an open cloud computing platform, refer to environmental monitoring problems in a real urban environment, and will be selected in accordance to a more than decadal experience by some of the instructors in the organizing group in the organization of international contests using EO data sets. By learning the basic of EO data processing, experiencing the limits and advantages of machine learnings techniques applied to satellite imagery, and solving real problems for a real environment, the virtual component of this blended programme is meant to provide the participants with new abilities, as well as a first example of both distance learning, which will prove important for their future professional career, and team working in a remote environment, which is becoming more and more widespread option for technical research and development, long before COVID.
The in-person part, organized in the urban area of Cremona, will complete the training by learning and the training by on-line doing with some practical activities on site, such as ground truth collection and result validation. This last part will therefore complete the training on the cycle of problem individuation, scenario simulation and output data analysis, and finally verification of the selected solution and the corresponding recorded data.
Find more information and how to apply here.
Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications
Together with NASA and IBM Research our SDLs have jointly worked on an expanded version of the open-source geospatial artificial intelligence (AI) foundation model, Prithvi-EO. The new version Prithvi-EO-2.0 was pre-trained on the Jülich Supercomputing Centre (JSC)’s JUWELS Booster Module using 240 NVIDIA A100 GPUs. It's now available on Hugging Face with new 300M and 600M parameter models that incorporate temporal and location embeddings. A technical paper is available on arXiv.
The updated version supports a broader range of geographical applications: It integrates global satellite data, enabling advanced Earth observation applications such as tracking land use changes, disaster monitoring, crop yield prediction, and environmental analysis on a planetary scale. It is also built on community feedback in order to significantly improve various applications. We’re happy to be an integral part of the work on Prithvi-EO-2.0, as it supports our goal of promoting interdisciplinary research combining remote sensing applications, AI as well as high-performance and innovative computing.
As part of our collaboration with NASA and IBM Research, we facilitated a student exchange opportunity with a master thesis project (see thesis).
People
Prof. Dr. -Ing. Gabriele Cavallaro
Gabriele Cavallaro (Senior Member, IEEE) received his B.Sc. and M.Sc. degrees in Telecommunications Engineering from the University of Trento, Italy, in 2011 and 2013, respectively, and a Ph.D. degree in Electrical and Computer Engineering from the University ofIceland, Iceland, in 2016. From 2016 to 2021, he served as the deputy head of the "High Productivity Data Processing" (HPDP) research group at the Jülich Supercomputing Centre (JSC), Forschungszentrum Jülich, Germany. Since 2022, he has been the Head of the "AI and ML for Remote Sensing" Simulation and Data Lab at the JSC. From 2022 to 2024, he served as an Adjunct Associate Professor at the Computer Science Department of the University of Iceland. Since August 2024, he is an Associate Professor with the Faculty of Electrical and Computer Engineering at the University of Iceland.
From 2020 to2023, he held the position of Lead for the High-Performance and Disruptive Computing in Remote Sensing (HDCRS) Working Group under the IEEE GRSS Earth Science Informatics Technical Committee (ESI TC). From 2023 to 2024, he served as Co-chair for the ESI TC. Since 2025, he has been the Chair of the IEEE GRSS Quantum Earth Science and Technology Technical Committee (QUEST TC). Concurrently, he serves as a Visiting Professor at the Φ-Lab within theEuropean Space Agency (ESA), where he contributes to the Quantum Computing forEarth Observation (QC4EO) initiative. Additionally, he served as an Associate Editor for the IEEE Transactions on Image Processing (TIP) from 2022 to 2024.
He was the recipient of the IEEE GRSS Third Prize in the Student Paper Competition of the IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2015 (Milan, Italy). His research interests include remote sensing data processing with parallel machine learning algorithms that scale on distributed computing systems and innovative computing technologies.
Prof. Dr. – Ing. Morris Riedel
Morris Riedel received his PhD from the Karlsruhe Institute of Technology (KIT) and worked in data-intensive parallel and distributed systems since 2004. He is currently a Full Professor of High-Performance Computing with an emphasis on Parallel and Scalable Machine Learning at the School of Natural Sciences and Engineering of the University of Iceland. Since 2004, Prof. Dr. – Ing. Morris Riedel held various positions at the Juelich Supercomputing Centre of Forschungszentrum Juelich in Germany. In addition, he is the Head of the joint High Productivity Data Processing research group between the Juelich Supercomputing Centre and the University of Iceland. Since 2020, he is also the EuroHPC Joint Undertaking governing board member for Iceland. His research interests include high-performance computing, remote sensing applications, medicine and health applications, pattern recognition, image processing, and data sciences, and he has authored extensively in those fields. Prof. Dr. – Ing. Morris Riedel online YouTube and university lectures include High-Performance Computing – Advanced Scientific Computing, Cloud Computing and Big Data – Parallel and Scalable Machine and Deep Learning, as well as Statistical Data Mining. In addition, he has performed numerous hands-on training events in parallel and scalable machine and deep learning techniques on cutting-edge HPC systems.
.jpg)
Amer Delilbasic
Amer Delilbasic received his Bachelor and Master degree (cum laude) in Information and Communication Engineering from the University of Trento, Italy, in 2019 and 2021 respectively. He is currently pursuing his PhD in Computational Engineering at the Jülich Supercomputing Centre, Germany, and the University of Iceland, Iceland. His research is mainly focused on machine learning and optimization based on quantum computing and high-performance computing for Earth observation. He has co-authored several articles to reputed journals and conferences for the sector of remote sensing. He has been a Visiting Researcher with Φ-lab, European Space Agency ESA/European Space Research Institute ESRIN. He has won an ESA OSIP proposal in 2021.
Dr. Ing. Rocco Sedona
Rocco Sedona (Member, IEEE) received the B.Sc. and M.Sc. degrees in information engineering from the University of Trento, Trento, Italy, in 2016 and 2019, respectively, and the Ph.D. degree in computational engineering from the University of Iceland, Reykjavik, Iceland, in 2023. He is a member of the “AI and ML for Remote Sensing” Simulation and Data Lab, JSC, Germany. His research interests primarily lie in the field of deep learning and its application to remote sensing data. He has extensively utilized optical satellite data acquired by Landsat (NASA) and Sentinel (ESA) missions toward near real-time land-cover classification. In addition, he specializes in distributed deep learning on high-performance computing systems, an area of study that he has been actively engaged in since 2019.
Edoardo Pasetto
Edoardo Pasetto received the B.Sc. and M.Sc. degrees in information and communication engineering from the University of Trento, Trento, Italy, in 2019 and 2021, respectively. He is currently working toward the Ph.D. degree in physics with Forschungszentrum Jülich, Germany, and RWTH Aachen University, Aachen, Germany. His main research interest include the application of hybrid quantum-classical machine learning frameworks to RS applications.
Ehsan Zandi
Dr. Ehsan Zandi is a Postdoc researcher at “AI and ML for Remote Sensing” Simulation and Data Lab at the Jülich Supercomputing Centre, Forschungszentrum Jülich, Germany. He finished his PhD in the field of "Communication Engineering" with a focus on "Information Theory" and "Optimization Theory". With over 7 years of job experience in pioneer companies such as "Ericsson System and Services", "Huawei" and "Deutsche Telekom" and being a seasoned software developer, he is interested in deploying techniques of resource-efficient AI in the area of Remote Sensing and HPC.
Erik Scheurer
Erik Scheurer is a master's student in Simulation Technology at the University of Stuttgart, with research interests in computer vision, deep learning, and foundation models. He is currently a research assistant at Forschungszentrum Jülich, focusing on embeddings for foundation models for Earth observation. Previously, he contributed to the development of preCICE, an opensource library for solving coupled simulations at the Institute for Parallel and Distributed Systems, University of Stuttgart.
Joseph Xavier Arnold
Joseph Arnold Xavier received the bachelor’s degree in computer science and engineering from Visvesvaraya Technological University (VTU) and the master’s degree in computer science and engineering from the National Institute of Technology, Puducherry, India. He is currently pursuing the Ph.D. degree in computational engineering with the University of Iceland in conjunction with the Jülich Supercomputing Centre, Germany. His work focuses primarily on optimization of applications in high performance computing systems.
Kennedy Adriko
Kennedy Adriko received his BSc. in Land Surveying and Geomatics from Makerere University, Uganda. He completed his MSc. in the Copernicus Master in Digital Earth jointly offered by theUniversity of Salzburg, Austria and the University of Brittany Sud, France and specialized in GeoData Science track. He is currently working towards the Ph.D in Computer and Electrical Engineering at the University of Iceland, Reykjavik, Iceland. He is a member of the “AI and ML for Remote Sensing” Simulation and Data Lab at the Jülich Supercomputing Centre, Forschungszentrum Jülich, Germany. His research focuses on efficient and scalable AI compression and data fusion techniques for Earth observation applications.
Liang Tian
Liang Tian received his B.Sc. degree and M.Sc. in Electrical Engineering and Information Technology from the Karlsruhe Institute of Technology and Technical University of Munich in 2019 and 2022, respectively. He is currently pursuing the PH.D. degree in computational engineering at the University of Iceland. His research interest lies mainly in deep learning methods for remote sensing applications with the combination of High Performance Computing (HPC) systems.
Samy Hashim
Samy Hashim received a B.Sc. degree in Smart Technologies from the University of Groningen, Netherlands, and a M.Sc. degree in Computer Science from University of Leiden, Netherlands, in 2022 and 2024, respectively. He is currently working toward the Ph.D. degree in Electrical and Computer Engineering with Forschungszentrum Jülich, Germany, and University of Iceland, Reykjavik, Iceland. His main research interests include data-centric green AI and space satellite image analysis.
Sayan Mandal
Sayan Mandal received his B.Tech. in Computer Science from University of Petroleum and Energy Studies, India, in 2017 and M.Sc. in Computer Science (major: Machine Learning, minor: Visual Computing), with distinction, from Technische Universität Graz, Austria, in 2024. Before joining Masters, he worked in the field of Computer Vision for over 4 years with two leading startups in India. For his M.Sc. thesis, he worked as a Student Project Assistant in FutureWoods Project at ICG, TU Graz, Austria, funded by FFG - Austrian Research Promotion Agency and the Vienna Scientific Cluster supercomputer. He is currently pursuing his Ph.D. degree in Electrical and Computer Engineering from University of Iceland in conjunction with the “AI and ML for Remote Sensing” Simulation and Data Lab, JSC, Forschungszentrum Jülich, Germany. His main research interests include developing robust deep learning models for remote sensing applications, foundation models and exploring AI efficiency, using HPC systems. He is also a reviewer in IEEE Access.
Stefano Maurogiovanni
Stefano Maurogiovanni researches scalability and multi-modal/multi-task pretraining of Deep Learning foundation models for Earth Observation. He received his B.Sc. in Bioengineering in 2020 and his M.Sc. in Computer Engineering in 2023 with a specialization in Data Science from the University of Pavia (UNIPV). He stayed at the Karlsruhe Institute of Technology (KIT) as a student researcher in the spring of 2022, working on open-source software for parallel iterative solvers. Until March 2024, he worked as a System Engineer at Leonardo (Italy), maintaining and authoring AI frameworks for airborne image processing. Since April 2024, he has served as a doctoral researcher at the University of Iceland and as a member of the “AI and ML for Remote Sensing” Simulation and Data Lab (SDLRS) at the Jülich Supercomputing Centre, Germany.
Surbhi Sharma
Surbhi Sharma (Student Member, IEEE) received the B.Tech. degree in electronics and communication engineering from Amity University, Noida, India, in 2015, and the M.Sc. degree in geoinformation science and earth observation with a specialization in geoinformatics jointly from the Indian Institute of Remote Sensing, Indian Space and Research Organization, Bangalore, India, and the Faculty of Geo-information Science and Earth Observation, University of Twente, Enschede, The Netherlands, in 2018. She is currently working toward the Ph.D. degree in computational engineering with the University of Iceland, Reykjavik, Iceland. She is a Member of the “AI and ML for Remote Sensing” Simulation and Data Lab, Jülich Supercomputing Centre, Germany. Her research interest lies in scalable machine learning and deep learning methods for remote sensing applications, with a particular focus on advanced deep transfer learning methods using modern high-performance computing systems.
Þorsteinn Elí Gíslason
Prof. Dr. – Ing. Jón Atli Benediktsson
Jón Atli Benediktsson received the Cand.Sci. degree in electrical engineering from the University of Iceland, Reykjavik, in 1984, and the M.S.E.E. and Ph.D. degrees in electrical engineering from Purdue University, West Lafayette, IN, in 1987 and 1990, respectively. Since July 1, 2015 he is the President and Rector of the University of Iceland. From 2009 to 2015 he was the Pro Rector of Science and Academic Affairs and Professor of Electrical and Computer Engineering at the University of Iceland. His research interests are in remote sensing, biomedical analysis of signals, pattern recognition, image processing, and signal processing, and he has published extensively in those fields. Prof. Benediktsson is a Highly Cited Researcher (Clarivate Analysis, 2018-2020). He was the 2011-2012 President of the IEEE Geoscience and and Remote Sensing Society (GRSS) and was on the GRSS AdCom from 2000-2014. He was Editor in Chief of the IEEE Transactions on Geoscience and Remote Sensing (TGRS) from 2003 to 2008 and has served as Associate Editor of TGRS since 1999.
Projects & Cooperations
All IHPC ProjectsSelected Publications
Journals
J. A. Xavier, J. P. G. Hermosillo Muriedas, S. Nassyr, R. Sedona, M. Götz, A. Streit, M. Riedel, and G. Cavallaro, “Vectorized Highly Parallel Density-Based Clustering for Applications With Noise,” in IEEE Access, vol. 12, pp. 181679–181692, 2024, https://doi.org/10.1109/ACCESS.2024.3507193
E. Zardini, A. Delilbasic, E. Blanzieri, G. Cavallaro, D. Pastorello, "Local Binary and Multiclass SVMs Trained on a Quantum Annealer," in IEEE Transactions on Quantum Engineering (TQE), pp. 1-13, 2024, https://doi.org/10.1109/TQE.2024.3475875
S. Sharma, R. Sedona, M. Riedel, G. Cavallaro, C. Paris, "Sen4Map: Advancing Mapping with Sentinel-2 by Providing Detailed Semantic Descriptions and Customizable Land-Use and Land-Cover Data," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS), vol. 17, pp. 13893-13907, 2024, https://doi.org/10.1109/JSTARS.2024.3435081
E. Pasetto, M. Riedel, K. Michielsen, G. Cavallaro, "Kernel Approximation on a Quantum Annealer for Remote Sensing Regression Tasks", in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS), vol. 17, pp. 3262-3269, 2024, https://doi.org/10.1109/JSTARS.2024.3350385
A. Delilbasic, B. Le Saux, M. Riedel, K. Michielsen, G. Cavallaro, "A Single-Step Multiclass SVM based on Quantum Annealing for Remote Sensing Data Classification," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS), vol. 17, pp. 1434-1445, 2024, https://doi.org/10.1109/JSTARS.2023.3336926
R. Sedona, C. Paris, J. Ebert, M. Riedel and G. Cavallaro, "Toward the Production of Spatiotemporally Consistent Annual Land Cover Maps Using Sentinel-2 Time Series," in IEEE Geoscience and Remote Sensing Letters, vol. 20, pp. 1-5, no. 2505805, 2023, https://doi.org/10.1109/LGRS.2023.3329428
S. Moreno-Álvarez, M. E. Paoletti, G. Cavallaro and J. M. Haut, "Enhancing Distributed Neural Network Training Through Node-Based Communications," in IEEE Transactions on Neural Networks and Learning Systems, 2023, https://doi.org/10.1109/TNNLS.2023.3309735
A. Farshian, M. Götz, G. Cavallaro, C. Debus, M. Nießner, J. A. Benediktsson, A. Streit, "Deep-Learning-Based 3-D Surface Reconstruction - A Survey," in Proceedings of the IEEE, vol. 111, no. 11, pp. 1464-1501, 2023, https://doi.org/10.1109/JPROC.2023.3321433
Y. Bazi, G. Cavallaro, B. Demir, F. Melgani, "Learning from Data for Remote Sensing Image Analysis", in International Journal of Remote Sensing (IJRS), vol. 43, no. 15-16, pp. 5527-5533, 2022, https://doi.org/10.1080/01431161.2022.2131481
E. Pasetto, M. Riedel, F. Melgani, K. Michielsen and G. Cavallaro, "Quantum SVR for Chlorophyll Concentration Estimation in Water With Remote Sensing," in IEEE Geoscience and Remote Sensing Letters (GRSL), vol. 19, pp. 1-5, 2022, https://doi.org/10.1109/LGRS.2022.3200325
S. Moreno-Álvarez, M. E. Paoletti, G. Cavallaro, J. A. Rico and J. M. Haut, "Remote Sensing Image Classification Using CNNs With Balanced Gradient for Distributed Heterogeneous Computing," in IEEE Geoscience and Remote Sensing Letters (GRSL), no. 3512205, vol. 19, pp. 1-5, 2022, https://doi.org/10.1109/LGRS.2022.3173052
B. Zhao, H. I. Ragnarsson, M. O. Ulfarsson, G. Cavallaro and J. A. Benediktsson, "Predicting Classification Performance for Benchmark Hyperspectral Datasets," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS), vol. 15, pp. 4180-4193, 2022, https://doi.org/10.1109/JSTARS.2022.3173893
R. Sedona, C. Paris, G. Cavallaro, L. Bruzzone, and M. Riedel, “A High-Performance Multispectral Adaptation GAN for Harmonizing Dense Time Series of Landsat-8 and Sentinel-2 Images,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS), vol. 14, pp. 10134–10146, 2021, https://doi.org/10.1109/JSTARS.2021.3115604
R. Sedona, L Hoffmann, R. Spang, G. Cavallaro, S. Griessbach, M. Höpfner, M., Book, M. Riedel, "Exploration of Machine Learning Methods for the Classification of Infrared Limb Spectra of Polar Stratospheric Clouds", in Atmospheric Measurement Techniques, vol 13, no. 7, pp. 3661–3682, 2020, https://doi.org/10.5194/amt-13-3661-2020
R. Sedona, G. Cavallaro, J. Jitsev, A. Strube, M. Riedel, and J. A. Benediktsson, ”Remote Sensing Big Data Classification with High Performance Distributed Deep Learning”, Remote Sensing, vol. 11, no. 24, pp. 3056, 2019.
J. M. Haut, J. A. Gallardo, M. E. Paoletti, G. Cavallaro, J. Plaza, A. Plaza, and M. Riedel, ”Cloud Deep Networks for Hyperspectral Image Analysis”, IEEE Transactions on Geoscience and Remote Sensing”, vol. 57, no. 12, pp. 9832-9848, 2019.
M. Goetz, G. Cavallaro, T. Geraud, M. Book, and M. Riedel, ”Parallel Computation of Component Trees on Distributed Memory Machines“, IEEE Transactions on Parallel and Distributed Systems, vol. 29, no. 11, pp. 2582-2598, 2018.
G. Cavallaro, M. Riedel, M. Richerzhagen, J. A. Benediktsson, and A. Plaza, ”On Understanding Big Data Impacts in Remotely Sensed Image Classification Using Support Vector Machine Methods,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (J-STARS), vol. 8, no. 10, pp. 4634-4646, 2015.
R. Sedona, C. Paris, G. Cavallaro, L. Bruzzone, and M. Riedel, “A High-Performance Multispectral Adaptation GAN for Harmonizing Dense Time Series of Landsat-8 and Sentinel-2 Images,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS), vol. 14, pp. 10134–10146, 2021, https://doi.org/10.1109/JSTARS.2021.3115604
S. Moreno-Álvarez, M. E. Paoletti, G. Cavallaro, J. A. Rico and J. M. Haut, "Remote Sensing Image Classification Using CNNs With Balanced Gradient for Distributed Heterogeneous Computing," in IEEE Geoscience and Remote Sensing Letters (GRSL), no. 3512205, vol. 19, pp. 1-5, 2022, https://doi.org/10.1109/LGRS.2022.3173052
B. Zhao, H. I. Ragnarsson, M. O. Ulfarsson, G. Cavallaro and J. A. Benediktsson, "Predicting Classification Performance for Benchmark Hyperspectral Datasets," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS), vol. 15, pp. 4180-4193, 2022, https://doi.org/10.1109/JSTARS.2022.3173893